Hugging Face's logo

lemonilia
/
Mistral-Small-3-Reasoner-s1

Safetensors
GGUF
English
Inference Endpoints
conversational
Model card Files Community
1
lemonilia commited on
Commit
9607abb
·
verified ·
1 Parent(s): 771b2bf

Upload 55 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +5 -0
  2. checkpoints/checkpoint-120/README.md +202 -0
  3. checkpoints/checkpoint-120/adapter_config.json +37 -0
  4. checkpoints/checkpoint-120/adapter_model.safetensors +3 -0
  5. checkpoints/checkpoint-120/optimizer.pt +3 -0
  6. checkpoints/checkpoint-120/rng_state.pth +3 -0
  7. checkpoints/checkpoint-120/scheduler.pt +3 -0
  8. checkpoints/checkpoint-120/special_tokens_map.json +1026 -0
  9. checkpoints/checkpoint-120/tokenizer.json +3 -0
  10. checkpoints/checkpoint-120/tokenizer_config.json +0 -0
  11. checkpoints/checkpoint-120/trainer_state.json +1369 -0
  12. checkpoints/checkpoint-120/training_args.bin +3 -0
  13. checkpoints/checkpoint-180/README.md +202 -0
  14. checkpoints/checkpoint-180/adapter_config.json +37 -0
  15. checkpoints/checkpoint-180/adapter_model.safetensors +3 -0
  16. checkpoints/checkpoint-180/optimizer.pt +3 -0
  17. checkpoints/checkpoint-180/rng_state.pth +3 -0
  18. checkpoints/checkpoint-180/scheduler.pt +3 -0
  19. checkpoints/checkpoint-180/special_tokens_map.json +1026 -0
  20. checkpoints/checkpoint-180/tokenizer.json +3 -0
  21. checkpoints/checkpoint-180/tokenizer_config.json +0 -0
  22. checkpoints/checkpoint-180/trainer_state.json +2029 -0
  23. checkpoints/checkpoint-180/training_args.bin +3 -0
  24. checkpoints/checkpoint-240/README.md +202 -0
  25. checkpoints/checkpoint-240/adapter_config.json +37 -0
  26. checkpoints/checkpoint-240/adapter_model.safetensors +3 -0
  27. checkpoints/checkpoint-240/optimizer.pt +3 -0
  28. checkpoints/checkpoint-240/rng_state.pth +3 -0
  29. checkpoints/checkpoint-240/scheduler.pt +3 -0
  30. checkpoints/checkpoint-240/special_tokens_map.json +1026 -0
  31. checkpoints/checkpoint-240/tokenizer.json +3 -0
  32. checkpoints/checkpoint-240/tokenizer_config.json +0 -0
  33. checkpoints/checkpoint-240/trainer_state.json +2697 -0
  34. checkpoints/checkpoint-240/training_args.bin +3 -0
  35. checkpoints/checkpoint-300/README.md +202 -0
  36. checkpoints/checkpoint-300/adapter_config.json +37 -0
  37. checkpoints/checkpoint-300/adapter_model.safetensors +3 -0
  38. checkpoints/checkpoint-300/optimizer.pt +3 -0
  39. checkpoints/checkpoint-300/rng_state.pth +3 -0
  40. checkpoints/checkpoint-300/scheduler.pt +3 -0
  41. checkpoints/checkpoint-300/special_tokens_map.json +1026 -0
  42. checkpoints/checkpoint-300/tokenizer.json +3 -0
  43. checkpoints/checkpoint-300/tokenizer_config.json +0 -0
  44. checkpoints/checkpoint-300/trainer_state.json +3357 -0
  45. checkpoints/checkpoint-300/training_args.bin +3 -0
  46. checkpoints/checkpoint-60/README.md +202 -0
  47. checkpoints/checkpoint-60/adapter_config.json +37 -0
  48. checkpoints/checkpoint-60/adapter_model.safetensors +3 -0
  49. checkpoints/checkpoint-60/optimizer.pt +3 -0
  50. checkpoints/checkpoint-60/rng_state.pth +3 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoints/checkpoint-120/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoints/checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoints/checkpoint-240/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ checkpoints/checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
+ checkpoints/checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoints/checkpoint-120/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoints/checkpoint-120/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints/checkpoint-120/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0faa2476f28faf21b38e0851785373c1de609c214e1cdbc1c51b44903b109dd7
3
+ size 739321784
checkpoints/checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b1895bffc34094178ee7f7fa2ecc8bed0cfa3562fe1c3fdcc762e93808ae04e
3
+ size 377514226
checkpoints/checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080e3707f2674e292f8d2bd48717f5918ac7cf1fddaf52276c4053d270f41ab3
3
+ size 14244
checkpoints/checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998ed495ac3030ef1ab402e333a99c939a4f47d52e97f32f076279d919077cba
3
+ size 1064
checkpoints/checkpoint-120/special_tokens_map.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[INST]",
7
+ "[/INST]",
8
+ "[AVAILABLE_TOOLS]",
9
+ "[/AVAILABLE_TOOLS]",
10
+ "[TOOL_RESULTS]",
11
+ "[/TOOL_RESULTS]",
12
+ "[TOOL_CALLS]",
13
+ "[IMG]",
14
+ "<pad>",
15
+ "[IMG_BREAK]",
16
+ "[IMG_END]",
17
+ "[PREFIX]",
18
+ "[MIDDLE]",
19
+ "[SUFFIX]",
20
+ "[SYSTEM_PROMPT]",
21
+ "[/SYSTEM_PROMPT]",
22
+ "[TOOL_CONTENT]",
23
+ "<SPECIAL_20>",
24
+ "<SPECIAL_21>",
25
+ "<SPECIAL_22>",
26
+ "<SPECIAL_23>",
27
+ "<SPECIAL_24>",
28
+ "<SPECIAL_25>",
29
+ "<SPECIAL_26>",
30
+ "<SPECIAL_27>",
31
+ "<SPECIAL_28>",
32
+ "<SPECIAL_29>",
33
+ "<SPECIAL_30>",
34
+ "<SPECIAL_31>",
35
+ "<SPECIAL_32>",
36
+ "<SPECIAL_33>",
37
+ "<SPECIAL_34>",
38
+ "<SPECIAL_35>",
39
+ "<SPECIAL_36>",
40
+ "<SPECIAL_37>",
41
+ "<SPECIAL_38>",
42
+ "<SPECIAL_39>",
43
+ "<SPECIAL_40>",
44
+ "<SPECIAL_41>",
45
+ "<SPECIAL_42>",
46
+ "<SPECIAL_43>",
47
+ "<SPECIAL_44>",
48
+ "<SPECIAL_45>",
49
+ "<SPECIAL_46>",
50
+ "<SPECIAL_47>",
51
+ "<SPECIAL_48>",
52
+ "<SPECIAL_49>",
53
+ "<SPECIAL_50>",
54
+ "<SPECIAL_51>",
55
+ "<SPECIAL_52>",
56
+ "<SPECIAL_53>",
57
+ "<SPECIAL_54>",
58
+ "<SPECIAL_55>",
59
+ "<SPECIAL_56>",
60
+ "<SPECIAL_57>",
61
+ "<SPECIAL_58>",
62
+ "<SPECIAL_59>",
63
+ "<SPECIAL_60>",
64
+ "<SPECIAL_61>",
65
+ "<SPECIAL_62>",
66
+ "<SPECIAL_63>",
67
+ "<SPECIAL_64>",
68
+ "<SPECIAL_65>",
69
+ "<SPECIAL_66>",
70
+ "<SPECIAL_67>",
71
+ "<SPECIAL_68>",
72
+ "<SPECIAL_69>",
73
+ "<SPECIAL_70>",
74
+ "<SPECIAL_71>",
75
+ "<SPECIAL_72>",
76
+ "<SPECIAL_73>",
77
+ "<SPECIAL_74>",
78
+ "<SPECIAL_75>",
79
+ "<SPECIAL_76>",
80
+ "<SPECIAL_77>",
81
+ "<SPECIAL_78>",
82
+ "<SPECIAL_79>",
83
+ "<SPECIAL_80>",
84
+ "<SPECIAL_81>",
85
+ "<SPECIAL_82>",
86
+ "<SPECIAL_83>",
87
+ "<SPECIAL_84>",
88
+ "<SPECIAL_85>",
89
+ "<SPECIAL_86>",
90
+ "<SPECIAL_87>",
91
+ "<SPECIAL_88>",
92
+ "<SPECIAL_89>",
93
+ "<SPECIAL_90>",
94
+ "<SPECIAL_91>",
95
+ "<SPECIAL_92>",
96
+ "<SPECIAL_93>",
97
+ "<SPECIAL_94>",
98
+ "<SPECIAL_95>",
99
+ "<SPECIAL_96>",
100
+ "<SPECIAL_97>",
101
+ "<SPECIAL_98>",
102
+ "<SPECIAL_99>",
103
+ "<SPECIAL_100>",
104
+ "<SPECIAL_101>",
105
+ "<SPECIAL_102>",
106
+ "<SPECIAL_103>",
107
+ "<SPECIAL_104>",
108
+ "<SPECIAL_105>",
109
+ "<SPECIAL_106>",
110
+ "<SPECIAL_107>",
111
+ "<SPECIAL_108>",
112
+ "<SPECIAL_109>",
113
+ "<SPECIAL_110>",
114
+ "<SPECIAL_111>",
115
+ "<SPECIAL_112>",
116
+ "<SPECIAL_113>",
117
+ "<SPECIAL_114>",
118
+ "<SPECIAL_115>",
119
+ "<SPECIAL_116>",
120
+ "<SPECIAL_117>",
121
+ "<SPECIAL_118>",
122
+ "<SPECIAL_119>",
123
+ "<SPECIAL_120>",
124
+ "<SPECIAL_121>",
125
+ "<SPECIAL_122>",
126
+ "<SPECIAL_123>",
127
+ "<SPECIAL_124>",
128
+ "<SPECIAL_125>",
129
+ "<SPECIAL_126>",
130
+ "<SPECIAL_127>",
131
+ "<SPECIAL_128>",
132
+ "<SPECIAL_129>",
133
+ "<SPECIAL_130>",
134
+ "<SPECIAL_131>",
135
+ "<SPECIAL_132>",
136
+ "<SPECIAL_133>",
137
+ "<SPECIAL_134>",
138
+ "<SPECIAL_135>",
139
+ "<SPECIAL_136>",
140
+ "<SPECIAL_137>",
141
+ "<SPECIAL_138>",
142
+ "<SPECIAL_139>",
143
+ "<SPECIAL_140>",
144
+ "<SPECIAL_141>",
145
+ "<SPECIAL_142>",
146
+ "<SPECIAL_143>",
147
+ "<SPECIAL_144>",
148
+ "<SPECIAL_145>",
149
+ "<SPECIAL_146>",
150
+ "<SPECIAL_147>",
151
+ "<SPECIAL_148>",
152
+ "<SPECIAL_149>",
153
+ "<SPECIAL_150>",
154
+ "<SPECIAL_151>",
155
+ "<SPECIAL_152>",
156
+ "<SPECIAL_153>",
157
+ "<SPECIAL_154>",
158
+ "<SPECIAL_155>",
159
+ "<SPECIAL_156>",
160
+ "<SPECIAL_157>",
161
+ "<SPECIAL_158>",
162
+ "<SPECIAL_159>",
163
+ "<SPECIAL_160>",
164
+ "<SPECIAL_161>",
165
+ "<SPECIAL_162>",
166
+ "<SPECIAL_163>",
167
+ "<SPECIAL_164>",
168
+ "<SPECIAL_165>",
169
+ "<SPECIAL_166>",
170
+ "<SPECIAL_167>",
171
+ "<SPECIAL_168>",
172
+ "<SPECIAL_169>",
173
+ "<SPECIAL_170>",
174
+ "<SPECIAL_171>",
175
+ "<SPECIAL_172>",
176
+ "<SPECIAL_173>",
177
+ "<SPECIAL_174>",
178
+ "<SPECIAL_175>",
179
+ "<SPECIAL_176>",
180
+ "<SPECIAL_177>",
181
+ "<SPECIAL_178>",
182
+ "<SPECIAL_179>",
183
+ "<SPECIAL_180>",
184
+ "<SPECIAL_181>",
185
+ "<SPECIAL_182>",
186
+ "<SPECIAL_183>",
187
+ "<SPECIAL_184>",
188
+ "<SPECIAL_185>",
189
+ "<SPECIAL_186>",
190
+ "<SPECIAL_187>",
191
+ "<SPECIAL_188>",
192
+ "<SPECIAL_189>",
193
+ "<SPECIAL_190>",
194
+ "<SPECIAL_191>",
195
+ "<SPECIAL_192>",
196
+ "<SPECIAL_193>",
197
+ "<SPECIAL_194>",
198
+ "<SPECIAL_195>",
199
+ "<SPECIAL_196>",
200
+ "<SPECIAL_197>",
201
+ "<SPECIAL_198>",
202
+ "<SPECIAL_199>",
203
+ "<SPECIAL_200>",
204
+ "<SPECIAL_201>",
205
+ "<SPECIAL_202>",
206
+ "<SPECIAL_203>",
207
+ "<SPECIAL_204>",
208
+ "<SPECIAL_205>",
209
+ "<SPECIAL_206>",
210
+ "<SPECIAL_207>",
211
+ "<SPECIAL_208>",
212
+ "<SPECIAL_209>",
213
+ "<SPECIAL_210>",
214
+ "<SPECIAL_211>",
215
+ "<SPECIAL_212>",
216
+ "<SPECIAL_213>",
217
+ "<SPECIAL_214>",
218
+ "<SPECIAL_215>",
219
+ "<SPECIAL_216>",
220
+ "<SPECIAL_217>",
221
+ "<SPECIAL_218>",
222
+ "<SPECIAL_219>",
223
+ "<SPECIAL_220>",
224
+ "<SPECIAL_221>",
225
+ "<SPECIAL_222>",
226
+ "<SPECIAL_223>",
227
+ "<SPECIAL_224>",
228
+ "<SPECIAL_225>",
229
+ "<SPECIAL_226>",
230
+ "<SPECIAL_227>",
231
+ "<SPECIAL_228>",
232
+ "<SPECIAL_229>",
233
+ "<SPECIAL_230>",
234
+ "<SPECIAL_231>",
235
+ "<SPECIAL_232>",
236
+ "<SPECIAL_233>",
237
+ "<SPECIAL_234>",
238
+ "<SPECIAL_235>",
239
+ "<SPECIAL_236>",
240
+ "<SPECIAL_237>",
241
+ "<SPECIAL_238>",
242
+ "<SPECIAL_239>",
243
+ "<SPECIAL_240>",
244
+ "<SPECIAL_241>",
245
+ "<SPECIAL_242>",
246
+ "<SPECIAL_243>",
247
+ "<SPECIAL_244>",
248
+ "<SPECIAL_245>",
249
+ "<SPECIAL_246>",
250
+ "<SPECIAL_247>",
251
+ "<SPECIAL_248>",
252
+ "<SPECIAL_249>",
253
+ "<SPECIAL_250>",
254
+ "<SPECIAL_251>",
255
+ "<SPECIAL_252>",
256
+ "<SPECIAL_253>",
257
+ "<SPECIAL_254>",
258
+ "<SPECIAL_255>",
259
+ "<SPECIAL_256>",
260
+ "<SPECIAL_257>",
261
+ "<SPECIAL_258>",
262
+ "<SPECIAL_259>",
263
+ "<SPECIAL_260>",
264
+ "<SPECIAL_261>",
265
+ "<SPECIAL_262>",
266
+ "<SPECIAL_263>",
267
+ "<SPECIAL_264>",
268
+ "<SPECIAL_265>",
269
+ "<SPECIAL_266>",
270
+ "<SPECIAL_267>",
271
+ "<SPECIAL_268>",
272
+ "<SPECIAL_269>",
273
+ "<SPECIAL_270>",
274
+ "<SPECIAL_271>",
275
+ "<SPECIAL_272>",
276
+ "<SPECIAL_273>",
277
+ "<SPECIAL_274>",
278
+ "<SPECIAL_275>",
279
+ "<SPECIAL_276>",
280
+ "<SPECIAL_277>",
281
+ "<SPECIAL_278>",
282
+ "<SPECIAL_279>",
283
+ "<SPECIAL_280>",
284
+ "<SPECIAL_281>",
285
+ "<SPECIAL_282>",
286
+ "<SPECIAL_283>",
287
+ "<SPECIAL_284>",
288
+ "<SPECIAL_285>",
289
+ "<SPECIAL_286>",
290
+ "<SPECIAL_287>",
291
+ "<SPECIAL_288>",
292
+ "<SPECIAL_289>",
293
+ "<SPECIAL_290>",
294
+ "<SPECIAL_291>",
295
+ "<SPECIAL_292>",
296
+ "<SPECIAL_293>",
297
+ "<SPECIAL_294>",
298
+ "<SPECIAL_295>",
299
+ "<SPECIAL_296>",
300
+ "<SPECIAL_297>",
301
+ "<SPECIAL_298>",
302
+ "<SPECIAL_299>",
303
+ "<SPECIAL_300>",
304
+ "<SPECIAL_301>",
305
+ "<SPECIAL_302>",
306
+ "<SPECIAL_303>",
307
+ "<SPECIAL_304>",
308
+ "<SPECIAL_305>",
309
+ "<SPECIAL_306>",
310
+ "<SPECIAL_307>",
311
+ "<SPECIAL_308>",
312
+ "<SPECIAL_309>",
313
+ "<SPECIAL_310>",
314
+ "<SPECIAL_311>",
315
+ "<SPECIAL_312>",
316
+ "<SPECIAL_313>",
317
+ "<SPECIAL_314>",
318
+ "<SPECIAL_315>",
319
+ "<SPECIAL_316>",
320
+ "<SPECIAL_317>",
321
+ "<SPECIAL_318>",
322
+ "<SPECIAL_319>",
323
+ "<SPECIAL_320>",
324
+ "<SPECIAL_321>",
325
+ "<SPECIAL_322>",
326
+ "<SPECIAL_323>",
327
+ "<SPECIAL_324>",
328
+ "<SPECIAL_325>",
329
+ "<SPECIAL_326>",
330
+ "<SPECIAL_327>",
331
+ "<SPECIAL_328>",
332
+ "<SPECIAL_329>",
333
+ "<SPECIAL_330>",
334
+ "<SPECIAL_331>",
335
+ "<SPECIAL_332>",
336
+ "<SPECIAL_333>",
337
+ "<SPECIAL_334>",
338
+ "<SPECIAL_335>",
339
+ "<SPECIAL_336>",
340
+ "<SPECIAL_337>",
341
+ "<SPECIAL_338>",
342
+ "<SPECIAL_339>",
343
+ "<SPECIAL_340>",
344
+ "<SPECIAL_341>",
345
+ "<SPECIAL_342>",
346
+ "<SPECIAL_343>",
347
+ "<SPECIAL_344>",
348
+ "<SPECIAL_345>",
349
+ "<SPECIAL_346>",
350
+ "<SPECIAL_347>",
351
+ "<SPECIAL_348>",
352
+ "<SPECIAL_349>",
353
+ "<SPECIAL_350>",
354
+ "<SPECIAL_351>",
355
+ "<SPECIAL_352>",
356
+ "<SPECIAL_353>",
357
+ "<SPECIAL_354>",
358
+ "<SPECIAL_355>",
359
+ "<SPECIAL_356>",
360
+ "<SPECIAL_357>",
361
+ "<SPECIAL_358>",
362
+ "<SPECIAL_359>",
363
+ "<SPECIAL_360>",
364
+ "<SPECIAL_361>",
365
+ "<SPECIAL_362>",
366
+ "<SPECIAL_363>",
367
+ "<SPECIAL_364>",
368
+ "<SPECIAL_365>",
369
+ "<SPECIAL_366>",
370
+ "<SPECIAL_367>",
371
+ "<SPECIAL_368>",
372
+ "<SPECIAL_369>",
373
+ "<SPECIAL_370>",
374
+ "<SPECIAL_371>",
375
+ "<SPECIAL_372>",
376
+ "<SPECIAL_373>",
377
+ "<SPECIAL_374>",
378
+ "<SPECIAL_375>",
379
+ "<SPECIAL_376>",
380
+ "<SPECIAL_377>",
381
+ "<SPECIAL_378>",
382
+ "<SPECIAL_379>",
383
+ "<SPECIAL_380>",
384
+ "<SPECIAL_381>",
385
+ "<SPECIAL_382>",
386
+ "<SPECIAL_383>",
387
+ "<SPECIAL_384>",
388
+ "<SPECIAL_385>",
389
+ "<SPECIAL_386>",
390
+ "<SPECIAL_387>",
391
+ "<SPECIAL_388>",
392
+ "<SPECIAL_389>",
393
+ "<SPECIAL_390>",
394
+ "<SPECIAL_391>",
395
+ "<SPECIAL_392>",
396
+ "<SPECIAL_393>",
397
+ "<SPECIAL_394>",
398
+ "<SPECIAL_395>",
399
+ "<SPECIAL_396>",
400
+ "<SPECIAL_397>",
401
+ "<SPECIAL_398>",
402
+ "<SPECIAL_399>",
403
+ "<SPECIAL_400>",
404
+ "<SPECIAL_401>",
405
+ "<SPECIAL_402>",
406
+ "<SPECIAL_403>",
407
+ "<SPECIAL_404>",
408
+ "<SPECIAL_405>",
409
+ "<SPECIAL_406>",
410
+ "<SPECIAL_407>",
411
+ "<SPECIAL_408>",
412
+ "<SPECIAL_409>",
413
+ "<SPECIAL_410>",
414
+ "<SPECIAL_411>",
415
+ "<SPECIAL_412>",
416
+ "<SPECIAL_413>",
417
+ "<SPECIAL_414>",
418
+ "<SPECIAL_415>",
419
+ "<SPECIAL_416>",
420
+ "<SPECIAL_417>",
421
+ "<SPECIAL_418>",
422
+ "<SPECIAL_419>",
423
+ "<SPECIAL_420>",
424
+ "<SPECIAL_421>",
425
+ "<SPECIAL_422>",
426
+ "<SPECIAL_423>",
427
+ "<SPECIAL_424>",
428
+ "<SPECIAL_425>",
429
+ "<SPECIAL_426>",
430
+ "<SPECIAL_427>",
431
+ "<SPECIAL_428>",
432
+ "<SPECIAL_429>",
433
+ "<SPECIAL_430>",
434
+ "<SPECIAL_431>",
435
+ "<SPECIAL_432>",
436
+ "<SPECIAL_433>",
437
+ "<SPECIAL_434>",
438
+ "<SPECIAL_435>",
439
+ "<SPECIAL_436>",
440
+ "<SPECIAL_437>",
441
+ "<SPECIAL_438>",
442
+ "<SPECIAL_439>",
443
+ "<SPECIAL_440>",
444
+ "<SPECIAL_441>",
445
+ "<SPECIAL_442>",
446
+ "<SPECIAL_443>",
447
+ "<SPECIAL_444>",
448
+ "<SPECIAL_445>",
449
+ "<SPECIAL_446>",
450
+ "<SPECIAL_447>",
451
+ "<SPECIAL_448>",
452
+ "<SPECIAL_449>",
453
+ "<SPECIAL_450>",
454
+ "<SPECIAL_451>",
455
+ "<SPECIAL_452>",
456
+ "<SPECIAL_453>",
457
+ "<SPECIAL_454>",
458
+ "<SPECIAL_455>",
459
+ "<SPECIAL_456>",
460
+ "<SPECIAL_457>",
461
+ "<SPECIAL_458>",
462
+ "<SPECIAL_459>",
463
+ "<SPECIAL_460>",
464
+ "<SPECIAL_461>",
465
+ "<SPECIAL_462>",
466
+ "<SPECIAL_463>",
467
+ "<SPECIAL_464>",
468
+ "<SPECIAL_465>",
469
+ "<SPECIAL_466>",
470
+ "<SPECIAL_467>",
471
+ "<SPECIAL_468>",
472
+ "<SPECIAL_469>",
473
+ "<SPECIAL_470>",
474
+ "<SPECIAL_471>",
475
+ "<SPECIAL_472>",
476
+ "<SPECIAL_473>",
477
+ "<SPECIAL_474>",
478
+ "<SPECIAL_475>",
479
+ "<SPECIAL_476>",
480
+ "<SPECIAL_477>",
481
+ "<SPECIAL_478>",
482
+ "<SPECIAL_479>",
483
+ "<SPECIAL_480>",
484
+ "<SPECIAL_481>",
485
+ "<SPECIAL_482>",
486
+ "<SPECIAL_483>",
487
+ "<SPECIAL_484>",
488
+ "<SPECIAL_485>",
489
+ "<SPECIAL_486>",
490
+ "<SPECIAL_487>",
491
+ "<SPECIAL_488>",
492
+ "<SPECIAL_489>",
493
+ "<SPECIAL_490>",
494
+ "<SPECIAL_491>",
495
+ "<SPECIAL_492>",
496
+ "<SPECIAL_493>",
497
+ "<SPECIAL_494>",
498
+ "<SPECIAL_495>",
499
+ "<SPECIAL_496>",
500
+ "<SPECIAL_497>",
501
+ "<SPECIAL_498>",
502
+ "<SPECIAL_499>",
503
+ "<SPECIAL_500>",
504
+ "<SPECIAL_501>",
505
+ "<SPECIAL_502>",
506
+ "<SPECIAL_503>",
507
+ "<SPECIAL_504>",
508
+ "<SPECIAL_505>",
509
+ "<SPECIAL_506>",
510
+ "<SPECIAL_507>",
511
+ "<SPECIAL_508>",
512
+ "<SPECIAL_509>",
513
+ "<SPECIAL_510>",
514
+ "<SPECIAL_511>",
515
+ "<SPECIAL_512>",
516
+ "<SPECIAL_513>",
517
+ "<SPECIAL_514>",
518
+ "<SPECIAL_515>",
519
+ "<SPECIAL_516>",
520
+ "<SPECIAL_517>",
521
+ "<SPECIAL_518>",
522
+ "<SPECIAL_519>",
523
+ "<SPECIAL_520>",
524
+ "<SPECIAL_521>",
525
+ "<SPECIAL_522>",
526
+ "<SPECIAL_523>",
527
+ "<SPECIAL_524>",
528
+ "<SPECIAL_525>",
529
+ "<SPECIAL_526>",
530
+ "<SPECIAL_527>",
531
+ "<SPECIAL_528>",
532
+ "<SPECIAL_529>",
533
+ "<SPECIAL_530>",
534
+ "<SPECIAL_531>",
535
+ "<SPECIAL_532>",
536
+ "<SPECIAL_533>",
537
+ "<SPECIAL_534>",
538
+ "<SPECIAL_535>",
539
+ "<SPECIAL_536>",
540
+ "<SPECIAL_537>",
541
+ "<SPECIAL_538>",
542
+ "<SPECIAL_539>",
543
+ "<SPECIAL_540>",
544
+ "<SPECIAL_541>",
545
+ "<SPECIAL_542>",
546
+ "<SPECIAL_543>",
547
+ "<SPECIAL_544>",
548
+ "<SPECIAL_545>",
549
+ "<SPECIAL_546>",
550
+ "<SPECIAL_547>",
551
+ "<SPECIAL_548>",
552
+ "<SPECIAL_549>",
553
+ "<SPECIAL_550>",
554
+ "<SPECIAL_551>",
555
+ "<SPECIAL_552>",
556
+ "<SPECIAL_553>",
557
+ "<SPECIAL_554>",
558
+ "<SPECIAL_555>",
559
+ "<SPECIAL_556>",
560
+ "<SPECIAL_557>",
561
+ "<SPECIAL_558>",
562
+ "<SPECIAL_559>",
563
+ "<SPECIAL_560>",
564
+ "<SPECIAL_561>",
565
+ "<SPECIAL_562>",
566
+ "<SPECIAL_563>",
567
+ "<SPECIAL_564>",
568
+ "<SPECIAL_565>",
569
+ "<SPECIAL_566>",
570
+ "<SPECIAL_567>",
571
+ "<SPECIAL_568>",
572
+ "<SPECIAL_569>",
573
+ "<SPECIAL_570>",
574
+ "<SPECIAL_571>",
575
+ "<SPECIAL_572>",
576
+ "<SPECIAL_573>",
577
+ "<SPECIAL_574>",
578
+ "<SPECIAL_575>",
579
+ "<SPECIAL_576>",
580
+ "<SPECIAL_577>",
581
+ "<SPECIAL_578>",
582
+ "<SPECIAL_579>",
583
+ "<SPECIAL_580>",
584
+ "<SPECIAL_581>",
585
+ "<SPECIAL_582>",
586
+ "<SPECIAL_583>",
587
+ "<SPECIAL_584>",
588
+ "<SPECIAL_585>",
589
+ "<SPECIAL_586>",
590
+ "<SPECIAL_587>",
591
+ "<SPECIAL_588>",
592
+ "<SPECIAL_589>",
593
+ "<SPECIAL_590>",
594
+ "<SPECIAL_591>",
595
+ "<SPECIAL_592>",
596
+ "<SPECIAL_593>",
597
+ "<SPECIAL_594>",
598
+ "<SPECIAL_595>",
599
+ "<SPECIAL_596>",
600
+ "<SPECIAL_597>",
601
+ "<SPECIAL_598>",
602
+ "<SPECIAL_599>",
603
+ "<SPECIAL_600>",
604
+ "<SPECIAL_601>",
605
+ "<SPECIAL_602>",
606
+ "<SPECIAL_603>",
607
+ "<SPECIAL_604>",
608
+ "<SPECIAL_605>",
609
+ "<SPECIAL_606>",
610
+ "<SPECIAL_607>",
611
+ "<SPECIAL_608>",
612
+ "<SPECIAL_609>",
613
+ "<SPECIAL_610>",
614
+ "<SPECIAL_611>",
615
+ "<SPECIAL_612>",
616
+ "<SPECIAL_613>",
617
+ "<SPECIAL_614>",
618
+ "<SPECIAL_615>",
619
+ "<SPECIAL_616>",
620
+ "<SPECIAL_617>",
621
+ "<SPECIAL_618>",
622
+ "<SPECIAL_619>",
623
+ "<SPECIAL_620>",
624
+ "<SPECIAL_621>",
625
+ "<SPECIAL_622>",
626
+ "<SPECIAL_623>",
627
+ "<SPECIAL_624>",
628
+ "<SPECIAL_625>",
629
+ "<SPECIAL_626>",
630
+ "<SPECIAL_627>",
631
+ "<SPECIAL_628>",
632
+ "<SPECIAL_629>",
633
+ "<SPECIAL_630>",
634
+ "<SPECIAL_631>",
635
+ "<SPECIAL_632>",
636
+ "<SPECIAL_633>",
637
+ "<SPECIAL_634>",
638
+ "<SPECIAL_635>",
639
+ "<SPECIAL_636>",
640
+ "<SPECIAL_637>",
641
+ "<SPECIAL_638>",
642
+ "<SPECIAL_639>",
643
+ "<SPECIAL_640>",
644
+ "<SPECIAL_641>",
645
+ "<SPECIAL_642>",
646
+ "<SPECIAL_643>",
647
+ "<SPECIAL_644>",
648
+ "<SPECIAL_645>",
649
+ "<SPECIAL_646>",
650
+ "<SPECIAL_647>",
651
+ "<SPECIAL_648>",
652
+ "<SPECIAL_649>",
653
+ "<SPECIAL_650>",
654
+ "<SPECIAL_651>",
655
+ "<SPECIAL_652>",
656
+ "<SPECIAL_653>",
657
+ "<SPECIAL_654>",
658
+ "<SPECIAL_655>",
659
+ "<SPECIAL_656>",
660
+ "<SPECIAL_657>",
661
+ "<SPECIAL_658>",
662
+ "<SPECIAL_659>",
663
+ "<SPECIAL_660>",
664
+ "<SPECIAL_661>",
665
+ "<SPECIAL_662>",
666
+ "<SPECIAL_663>",
667
+ "<SPECIAL_664>",
668
+ "<SPECIAL_665>",
669
+ "<SPECIAL_666>",
670
+ "<SPECIAL_667>",
671
+ "<SPECIAL_668>",
672
+ "<SPECIAL_669>",
673
+ "<SPECIAL_670>",
674
+ "<SPECIAL_671>",
675
+ "<SPECIAL_672>",
676
+ "<SPECIAL_673>",
677
+ "<SPECIAL_674>",
678
+ "<SPECIAL_675>",
679
+ "<SPECIAL_676>",
680
+ "<SPECIAL_677>",
681
+ "<SPECIAL_678>",
682
+ "<SPECIAL_679>",
683
+ "<SPECIAL_680>",
684
+ "<SPECIAL_681>",
685
+ "<SPECIAL_682>",
686
+ "<SPECIAL_683>",
687
+ "<SPECIAL_684>",
688
+ "<SPECIAL_685>",
689
+ "<SPECIAL_686>",
690
+ "<SPECIAL_687>",
691
+ "<SPECIAL_688>",
692
+ "<SPECIAL_689>",
693
+ "<SPECIAL_690>",
694
+ "<SPECIAL_691>",
695
+ "<SPECIAL_692>",
696
+ "<SPECIAL_693>",
697
+ "<SPECIAL_694>",
698
+ "<SPECIAL_695>",
699
+ "<SPECIAL_696>",
700
+ "<SPECIAL_697>",
701
+ "<SPECIAL_698>",
702
+ "<SPECIAL_699>",
703
+ "<SPECIAL_700>",
704
+ "<SPECIAL_701>",
705
+ "<SPECIAL_702>",
706
+ "<SPECIAL_703>",
707
+ "<SPECIAL_704>",
708
+ "<SPECIAL_705>",
709
+ "<SPECIAL_706>",
710
+ "<SPECIAL_707>",
711
+ "<SPECIAL_708>",
712
+ "<SPECIAL_709>",
713
+ "<SPECIAL_710>",
714
+ "<SPECIAL_711>",
715
+ "<SPECIAL_712>",
716
+ "<SPECIAL_713>",
717
+ "<SPECIAL_714>",
718
+ "<SPECIAL_715>",
719
+ "<SPECIAL_716>",
720
+ "<SPECIAL_717>",
721
+ "<SPECIAL_718>",
722
+ "<SPECIAL_719>",
723
+ "<SPECIAL_720>",
724
+ "<SPECIAL_721>",
725
+ "<SPECIAL_722>",
726
+ "<SPECIAL_723>",
727
+ "<SPECIAL_724>",
728
+ "<SPECIAL_725>",
729
+ "<SPECIAL_726>",
730
+ "<SPECIAL_727>",
731
+ "<SPECIAL_728>",
732
+ "<SPECIAL_729>",
733
+ "<SPECIAL_730>",
734
+ "<SPECIAL_731>",
735
+ "<SPECIAL_732>",
736
+ "<SPECIAL_733>",
737
+ "<SPECIAL_734>",
738
+ "<SPECIAL_735>",
739
+ "<SPECIAL_736>",
740
+ "<SPECIAL_737>",
741
+ "<SPECIAL_738>",
742
+ "<SPECIAL_739>",
743
+ "<SPECIAL_740>",
744
+ "<SPECIAL_741>",
745
+ "<SPECIAL_742>",
746
+ "<SPECIAL_743>",
747
+ "<SPECIAL_744>",
748
+ "<SPECIAL_745>",
749
+ "<SPECIAL_746>",
750
+ "<SPECIAL_747>",
751
+ "<SPECIAL_748>",
752
+ "<SPECIAL_749>",
753
+ "<SPECIAL_750>",
754
+ "<SPECIAL_751>",
755
+ "<SPECIAL_752>",
756
+ "<SPECIAL_753>",
757
+ "<SPECIAL_754>",
758
+ "<SPECIAL_755>",
759
+ "<SPECIAL_756>",
760
+ "<SPECIAL_757>",
761
+ "<SPECIAL_758>",
762
+ "<SPECIAL_759>",
763
+ "<SPECIAL_760>",
764
+ "<SPECIAL_761>",
765
+ "<SPECIAL_762>",
766
+ "<SPECIAL_763>",
767
+ "<SPECIAL_764>",
768
+ "<SPECIAL_765>",
769
+ "<SPECIAL_766>",
770
+ "<SPECIAL_767>",
771
+ "<SPECIAL_768>",
772
+ "<SPECIAL_769>",
773
+ "<SPECIAL_770>",
774
+ "<SPECIAL_771>",
775
+ "<SPECIAL_772>",
776
+ "<SPECIAL_773>",
777
+ "<SPECIAL_774>",
778
+ "<SPECIAL_775>",
779
+ "<SPECIAL_776>",
780
+ "<SPECIAL_777>",
781
+ "<SPECIAL_778>",
782
+ "<SPECIAL_779>",
783
+ "<SPECIAL_780>",
784
+ "<SPECIAL_781>",
785
+ "<SPECIAL_782>",
786
+ "<SPECIAL_783>",
787
+ "<SPECIAL_784>",
788
+ "<SPECIAL_785>",
789
+ "<SPECIAL_786>",
790
+ "<SPECIAL_787>",
791
+ "<SPECIAL_788>",
792
+ "<SPECIAL_789>",
793
+ "<SPECIAL_790>",
794
+ "<SPECIAL_791>",
795
+ "<SPECIAL_792>",
796
+ "<SPECIAL_793>",
797
+ "<SPECIAL_794>",
798
+ "<SPECIAL_795>",
799
+ "<SPECIAL_796>",
800
+ "<SPECIAL_797>",
801
+ "<SPECIAL_798>",
802
+ "<SPECIAL_799>",
803
+ "<SPECIAL_800>",
804
+ "<SPECIAL_801>",
805
+ "<SPECIAL_802>",
806
+ "<SPECIAL_803>",
807
+ "<SPECIAL_804>",
808
+ "<SPECIAL_805>",
809
+ "<SPECIAL_806>",
810
+ "<SPECIAL_807>",
811
+ "<SPECIAL_808>",
812
+ "<SPECIAL_809>",
813
+ "<SPECIAL_810>",
814
+ "<SPECIAL_811>",
815
+ "<SPECIAL_812>",
816
+ "<SPECIAL_813>",
817
+ "<SPECIAL_814>",
818
+ "<SPECIAL_815>",
819
+ "<SPECIAL_816>",
820
+ "<SPECIAL_817>",
821
+ "<SPECIAL_818>",
822
+ "<SPECIAL_819>",
823
+ "<SPECIAL_820>",
824
+ "<SPECIAL_821>",
825
+ "<SPECIAL_822>",
826
+ "<SPECIAL_823>",
827
+ "<SPECIAL_824>",
828
+ "<SPECIAL_825>",
829
+ "<SPECIAL_826>",
830
+ "<SPECIAL_827>",
831
+ "<SPECIAL_828>",
832
+ "<SPECIAL_829>",
833
+ "<SPECIAL_830>",
834
+ "<SPECIAL_831>",
835
+ "<SPECIAL_832>",
836
+ "<SPECIAL_833>",
837
+ "<SPECIAL_834>",
838
+ "<SPECIAL_835>",
839
+ "<SPECIAL_836>",
840
+ "<SPECIAL_837>",
841
+ "<SPECIAL_838>",
842
+ "<SPECIAL_839>",
843
+ "<SPECIAL_840>",
844
+ "<SPECIAL_841>",
845
+ "<SPECIAL_842>",
846
+ "<SPECIAL_843>",
847
+ "<SPECIAL_844>",
848
+ "<SPECIAL_845>",
849
+ "<SPECIAL_846>",
850
+ "<SPECIAL_847>",
851
+ "<SPECIAL_848>",
852
+ "<SPECIAL_849>",
853
+ "<SPECIAL_850>",
854
+ "<SPECIAL_851>",
855
+ "<SPECIAL_852>",
856
+ "<SPECIAL_853>",
857
+ "<SPECIAL_854>",
858
+ "<SPECIAL_855>",
859
+ "<SPECIAL_856>",
860
+ "<SPECIAL_857>",
861
+ "<SPECIAL_858>",
862
+ "<SPECIAL_859>",
863
+ "<SPECIAL_860>",
864
+ "<SPECIAL_861>",
865
+ "<SPECIAL_862>",
866
+ "<SPECIAL_863>",
867
+ "<SPECIAL_864>",
868
+ "<SPECIAL_865>",
869
+ "<SPECIAL_866>",
870
+ "<SPECIAL_867>",
871
+ "<SPECIAL_868>",
872
+ "<SPECIAL_869>",
873
+ "<SPECIAL_870>",
874
+ "<SPECIAL_871>",
875
+ "<SPECIAL_872>",
876
+ "<SPECIAL_873>",
877
+ "<SPECIAL_874>",
878
+ "<SPECIAL_875>",
879
+ "<SPECIAL_876>",
880
+ "<SPECIAL_877>",
881
+ "<SPECIAL_878>",
882
+ "<SPECIAL_879>",
883
+ "<SPECIAL_880>",
884
+ "<SPECIAL_881>",
885
+ "<SPECIAL_882>",
886
+ "<SPECIAL_883>",
887
+ "<SPECIAL_884>",
888
+ "<SPECIAL_885>",
889
+ "<SPECIAL_886>",
890
+ "<SPECIAL_887>",
891
+ "<SPECIAL_888>",
892
+ "<SPECIAL_889>",
893
+ "<SPECIAL_890>",
894
+ "<SPECIAL_891>",
895
+ "<SPECIAL_892>",
896
+ "<SPECIAL_893>",
897
+ "<SPECIAL_894>",
898
+ "<SPECIAL_895>",
899
+ "<SPECIAL_896>",
900
+ "<SPECIAL_897>",
901
+ "<SPECIAL_898>",
902
+ "<SPECIAL_899>",
903
+ "<SPECIAL_900>",
904
+ "<SPECIAL_901>",
905
+ "<SPECIAL_902>",
906
+ "<SPECIAL_903>",
907
+ "<SPECIAL_904>",
908
+ "<SPECIAL_905>",
909
+ "<SPECIAL_906>",
910
+ "<SPECIAL_907>",
911
+ "<SPECIAL_908>",
912
+ "<SPECIAL_909>",
913
+ "<SPECIAL_910>",
914
+ "<SPECIAL_911>",
915
+ "<SPECIAL_912>",
916
+ "<SPECIAL_913>",
917
+ "<SPECIAL_914>",
918
+ "<SPECIAL_915>",
919
+ "<SPECIAL_916>",
920
+ "<SPECIAL_917>",
921
+ "<SPECIAL_918>",
922
+ "<SPECIAL_919>",
923
+ "<SPECIAL_920>",
924
+ "<SPECIAL_921>",
925
+ "<SPECIAL_922>",
926
+ "<SPECIAL_923>",
927
+ "<SPECIAL_924>",
928
+ "<SPECIAL_925>",
929
+ "<SPECIAL_926>",
930
+ "<SPECIAL_927>",
931
+ "<SPECIAL_928>",
932
+ "<SPECIAL_929>",
933
+ "<SPECIAL_930>",
934
+ "<SPECIAL_931>",
935
+ "<SPECIAL_932>",
936
+ "<SPECIAL_933>",
937
+ "<SPECIAL_934>",
938
+ "<SPECIAL_935>",
939
+ "<SPECIAL_936>",
940
+ "<SPECIAL_937>",
941
+ "<SPECIAL_938>",
942
+ "<SPECIAL_939>",
943
+ "<SPECIAL_940>",
944
+ "<SPECIAL_941>",
945
+ "<SPECIAL_942>",
946
+ "<SPECIAL_943>",
947
+ "<SPECIAL_944>",
948
+ "<SPECIAL_945>",
949
+ "<SPECIAL_946>",
950
+ "<SPECIAL_947>",
951
+ "<SPECIAL_948>",
952
+ "<SPECIAL_949>",
953
+ "<SPECIAL_950>",
954
+ "<SPECIAL_951>",
955
+ "<SPECIAL_952>",
956
+ "<SPECIAL_953>",
957
+ "<SPECIAL_954>",
958
+ "<SPECIAL_955>",
959
+ "<SPECIAL_956>",
960
+ "<SPECIAL_957>",
961
+ "<SPECIAL_958>",
962
+ "<SPECIAL_959>",
963
+ "<SPECIAL_960>",
964
+ "<SPECIAL_961>",
965
+ "<SPECIAL_962>",
966
+ "<SPECIAL_963>",
967
+ "<SPECIAL_964>",
968
+ "<SPECIAL_965>",
969
+ "<SPECIAL_966>",
970
+ "<SPECIAL_967>",
971
+ "<SPECIAL_968>",
972
+ "<SPECIAL_969>",
973
+ "<SPECIAL_970>",
974
+ "<SPECIAL_971>",
975
+ "<SPECIAL_972>",
976
+ "<SPECIAL_973>",
977
+ "<SPECIAL_974>",
978
+ "<SPECIAL_975>",
979
+ "<SPECIAL_976>",
980
+ "<SPECIAL_977>",
981
+ "<SPECIAL_978>",
982
+ "<SPECIAL_979>",
983
+ "<SPECIAL_980>",
984
+ "<SPECIAL_981>",
985
+ "<SPECIAL_982>",
986
+ "<SPECIAL_983>",
987
+ "<SPECIAL_984>",
988
+ "<SPECIAL_985>",
989
+ "<SPECIAL_986>",
990
+ "<SPECIAL_987>",
991
+ "<SPECIAL_988>",
992
+ "<SPECIAL_989>",
993
+ "<SPECIAL_990>",
994
+ "<SPECIAL_991>",
995
+ "<SPECIAL_992>",
996
+ "<SPECIAL_993>",
997
+ "<SPECIAL_994>",
998
+ "<SPECIAL_995>",
999
+ "<SPECIAL_996>",
1000
+ "<SPECIAL_997>",
1001
+ "<SPECIAL_998>",
1002
+ "<SPECIAL_999>"
1003
+ ],
1004
+ "bos_token": {
1005
+ "content": "<s>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ "eos_token": {
1012
+ "content": "</s>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ "pad_token": "<pad>",
1019
+ "unk_token": {
1020
+ "content": "<unk>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false
1025
+ }
1026
+ }
checkpoints/checkpoint-120/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
checkpoints/checkpoint-120/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,1369 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.9591836734693877,
5
+ "eval_steps": 2,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 1.2313029766082764,
14
+ "eval_runtime": 18.2352,
15
+ "eval_samples_per_second": 0.877,
16
+ "eval_steps_per_second": 0.877,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0163265306122449,
21
+ "grad_norm": 0.37113556265830994,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 0.4085,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0326530612244898,
28
+ "grad_norm": 0.35803329944610596,
29
+ "learning_rate": 5e-05,
30
+ "loss": 0.3876,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0326530612244898,
35
+ "eval_loss": 1.2231345176696777,
36
+ "eval_runtime": 18.2243,
37
+ "eval_samples_per_second": 0.878,
38
+ "eval_steps_per_second": 0.878,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04897959183673469,
43
+ "grad_norm": 0.3112759590148926,
44
+ "learning_rate": 7.500000000000001e-05,
45
+ "loss": 0.3946,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0653061224489796,
50
+ "grad_norm": 0.2448713332414627,
51
+ "learning_rate": 0.0001,
52
+ "loss": 0.4363,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0653061224489796,
57
+ "eval_loss": 1.1564743518829346,
58
+ "eval_runtime": 18.253,
59
+ "eval_samples_per_second": 0.877,
60
+ "eval_steps_per_second": 0.877,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.08163265306122448,
65
+ "grad_norm": 0.2955642342567444,
66
+ "learning_rate": 0.000125,
67
+ "loss": 0.4394,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.09795918367346938,
72
+ "grad_norm": 0.41399946808815,
73
+ "learning_rate": 0.00015000000000000001,
74
+ "loss": 0.4902,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.09795918367346938,
79
+ "eval_loss": 1.1353044509887695,
80
+ "eval_runtime": 18.2664,
81
+ "eval_samples_per_second": 0.876,
82
+ "eval_steps_per_second": 0.876,
83
+ "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.11428571428571428,
87
+ "grad_norm": 0.2643347978591919,
88
+ "learning_rate": 0.000175,
89
+ "loss": 0.3528,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.1306122448979592,
94
+ "grad_norm": 0.21472330391407013,
95
+ "learning_rate": 0.0002,
96
+ "loss": 0.357,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.1306122448979592,
101
+ "eval_loss": 1.1218546628952026,
102
+ "eval_runtime": 18.2139,
103
+ "eval_samples_per_second": 0.878,
104
+ "eval_steps_per_second": 0.878,
105
+ "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.1469387755102041,
109
+ "grad_norm": 0.23261462152004242,
110
+ "learning_rate": 0.00022500000000000002,
111
+ "loss": 0.3924,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.16326530612244897,
116
+ "grad_norm": 0.18365171551704407,
117
+ "learning_rate": 0.00025,
118
+ "loss": 0.283,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.16326530612244897,
123
+ "eval_loss": 1.1094393730163574,
124
+ "eval_runtime": 18.249,
125
+ "eval_samples_per_second": 0.877,
126
+ "eval_steps_per_second": 0.877,
127
+ "step": 10
128
+ },
129
+ {
130
+ "epoch": 0.17959183673469387,
131
+ "grad_norm": 0.20431634783744812,
132
+ "learning_rate": 0.000275,
133
+ "loss": 0.3178,
134
+ "step": 11
135
+ },
136
+ {
137
+ "epoch": 0.19591836734693877,
138
+ "grad_norm": 0.2033773809671402,
139
+ "learning_rate": 0.00030000000000000003,
140
+ "loss": 0.3366,
141
+ "step": 12
142
+ },
143
+ {
144
+ "epoch": 0.19591836734693877,
145
+ "eval_loss": 1.1021316051483154,
146
+ "eval_runtime": 18.2562,
147
+ "eval_samples_per_second": 0.876,
148
+ "eval_steps_per_second": 0.876,
149
+ "step": 12
150
+ },
151
+ {
152
+ "epoch": 0.21224489795918366,
153
+ "grad_norm": 0.27416911721229553,
154
+ "learning_rate": 0.00032500000000000004,
155
+ "loss": 0.3367,
156
+ "step": 13
157
+ },
158
+ {
159
+ "epoch": 0.22857142857142856,
160
+ "grad_norm": 0.32283130288124084,
161
+ "learning_rate": 0.00035,
162
+ "loss": 0.3364,
163
+ "step": 14
164
+ },
165
+ {
166
+ "epoch": 0.22857142857142856,
167
+ "eval_loss": 1.0523244142532349,
168
+ "eval_runtime": 18.2347,
169
+ "eval_samples_per_second": 0.877,
170
+ "eval_steps_per_second": 0.877,
171
+ "step": 14
172
+ },
173
+ {
174
+ "epoch": 0.24489795918367346,
175
+ "grad_norm": 0.21469368040561676,
176
+ "learning_rate": 0.000375,
177
+ "loss": 0.3496,
178
+ "step": 15
179
+ },
180
+ {
181
+ "epoch": 0.2612244897959184,
182
+ "grad_norm": 0.19361759722232819,
183
+ "learning_rate": 0.0004,
184
+ "loss": 0.2961,
185
+ "step": 16
186
+ },
187
+ {
188
+ "epoch": 0.2612244897959184,
189
+ "eval_loss": 1.0401124954223633,
190
+ "eval_runtime": 18.2288,
191
+ "eval_samples_per_second": 0.878,
192
+ "eval_steps_per_second": 0.878,
193
+ "step": 16
194
+ },
195
+ {
196
+ "epoch": 0.27755102040816326,
197
+ "grad_norm": 0.1797463297843933,
198
+ "learning_rate": 0.0004,
199
+ "loss": 0.3016,
200
+ "step": 17
201
+ },
202
+ {
203
+ "epoch": 0.2938775510204082,
204
+ "grad_norm": 0.28122591972351074,
205
+ "learning_rate": 0.0004,
206
+ "loss": 0.3656,
207
+ "step": 18
208
+ },
209
+ {
210
+ "epoch": 0.2938775510204082,
211
+ "eval_loss": 1.0228931903839111,
212
+ "eval_runtime": 18.2429,
213
+ "eval_samples_per_second": 0.877,
214
+ "eval_steps_per_second": 0.877,
215
+ "step": 18
216
+ },
217
+ {
218
+ "epoch": 0.31020408163265306,
219
+ "grad_norm": 0.227556511759758,
220
+ "learning_rate": 0.0004,
221
+ "loss": 0.3246,
222
+ "step": 19
223
+ },
224
+ {
225
+ "epoch": 0.32653061224489793,
226
+ "grad_norm": 0.211012601852417,
227
+ "learning_rate": 0.0004,
228
+ "loss": 0.3453,
229
+ "step": 20
230
+ },
231
+ {
232
+ "epoch": 0.32653061224489793,
233
+ "eval_loss": 1.017521858215332,
234
+ "eval_runtime": 18.2213,
235
+ "eval_samples_per_second": 0.878,
236
+ "eval_steps_per_second": 0.878,
237
+ "step": 20
238
+ },
239
+ {
240
+ "epoch": 0.34285714285714286,
241
+ "grad_norm": 0.20422972738742828,
242
+ "learning_rate": 0.0004,
243
+ "loss": 0.3258,
244
+ "step": 21
245
+ },
246
+ {
247
+ "epoch": 0.35918367346938773,
248
+ "grad_norm": 0.206649512052536,
249
+ "learning_rate": 0.0004,
250
+ "loss": 0.3248,
251
+ "step": 22
252
+ },
253
+ {
254
+ "epoch": 0.35918367346938773,
255
+ "eval_loss": 0.9992413520812988,
256
+ "eval_runtime": 18.249,
257
+ "eval_samples_per_second": 0.877,
258
+ "eval_steps_per_second": 0.877,
259
+ "step": 22
260
+ },
261
+ {
262
+ "epoch": 0.37551020408163266,
263
+ "grad_norm": 0.19837401807308197,
264
+ "learning_rate": 0.0004,
265
+ "loss": 0.3181,
266
+ "step": 23
267
+ },
268
+ {
269
+ "epoch": 0.39183673469387753,
270
+ "grad_norm": 0.20325997471809387,
271
+ "learning_rate": 0.0004,
272
+ "loss": 0.2826,
273
+ "step": 24
274
+ },
275
+ {
276
+ "epoch": 0.39183673469387753,
277
+ "eval_loss": 0.9943413734436035,
278
+ "eval_runtime": 18.2482,
279
+ "eval_samples_per_second": 0.877,
280
+ "eval_steps_per_second": 0.877,
281
+ "step": 24
282
+ },
283
+ {
284
+ "epoch": 0.40816326530612246,
285
+ "grad_norm": 0.3371317386627197,
286
+ "learning_rate": 0.0004,
287
+ "loss": 0.3197,
288
+ "step": 25
289
+ },
290
+ {
291
+ "epoch": 0.42448979591836733,
292
+ "grad_norm": 0.21709182858467102,
293
+ "learning_rate": 0.0004,
294
+ "loss": 0.3272,
295
+ "step": 26
296
+ },
297
+ {
298
+ "epoch": 0.42448979591836733,
299
+ "eval_loss": 0.9733779430389404,
300
+ "eval_runtime": 18.2232,
301
+ "eval_samples_per_second": 0.878,
302
+ "eval_steps_per_second": 0.878,
303
+ "step": 26
304
+ },
305
+ {
306
+ "epoch": 0.44081632653061226,
307
+ "grad_norm": 0.2420857548713684,
308
+ "learning_rate": 0.0004,
309
+ "loss": 0.3293,
310
+ "step": 27
311
+ },
312
+ {
313
+ "epoch": 0.45714285714285713,
314
+ "grad_norm": 0.30486994981765747,
315
+ "learning_rate": 0.0004,
316
+ "loss": 0.3958,
317
+ "step": 28
318
+ },
319
+ {
320
+ "epoch": 0.45714285714285713,
321
+ "eval_loss": 0.9588731527328491,
322
+ "eval_runtime": 18.2458,
323
+ "eval_samples_per_second": 0.877,
324
+ "eval_steps_per_second": 0.877,
325
+ "step": 28
326
+ },
327
+ {
328
+ "epoch": 0.47346938775510206,
329
+ "grad_norm": 0.24714964628219604,
330
+ "learning_rate": 0.0004,
331
+ "loss": 0.3305,
332
+ "step": 29
333
+ },
334
+ {
335
+ "epoch": 0.4897959183673469,
336
+ "grad_norm": 0.21984225511550903,
337
+ "learning_rate": 0.0004,
338
+ "loss": 0.3395,
339
+ "step": 30
340
+ },
341
+ {
342
+ "epoch": 0.4897959183673469,
343
+ "eval_loss": 0.9427903890609741,
344
+ "eval_runtime": 18.2414,
345
+ "eval_samples_per_second": 0.877,
346
+ "eval_steps_per_second": 0.877,
347
+ "step": 30
348
+ },
349
+ {
350
+ "epoch": 0.5061224489795918,
351
+ "grad_norm": 0.19778016209602356,
352
+ "learning_rate": 0.0004,
353
+ "loss": 0.2918,
354
+ "step": 31
355
+ },
356
+ {
357
+ "epoch": 0.5224489795918368,
358
+ "grad_norm": 0.21754617989063263,
359
+ "learning_rate": 0.0004,
360
+ "loss": 0.2855,
361
+ "step": 32
362
+ },
363
+ {
364
+ "epoch": 0.5224489795918368,
365
+ "eval_loss": 0.9335330128669739,
366
+ "eval_runtime": 18.275,
367
+ "eval_samples_per_second": 0.876,
368
+ "eval_steps_per_second": 0.876,
369
+ "step": 32
370
+ },
371
+ {
372
+ "epoch": 0.5387755102040817,
373
+ "grad_norm": 0.2221430391073227,
374
+ "learning_rate": 0.0004,
375
+ "loss": 0.2946,
376
+ "step": 33
377
+ },
378
+ {
379
+ "epoch": 0.5551020408163265,
380
+ "grad_norm": 0.2112974375486374,
381
+ "learning_rate": 0.0004,
382
+ "loss": 0.3149,
383
+ "step": 34
384
+ },
385
+ {
386
+ "epoch": 0.5551020408163265,
387
+ "eval_loss": 0.9311869144439697,
388
+ "eval_runtime": 18.2431,
389
+ "eval_samples_per_second": 0.877,
390
+ "eval_steps_per_second": 0.877,
391
+ "step": 34
392
+ },
393
+ {
394
+ "epoch": 0.5714285714285714,
395
+ "grad_norm": 0.19651219248771667,
396
+ "learning_rate": 0.0004,
397
+ "loss": 0.2606,
398
+ "step": 35
399
+ },
400
+ {
401
+ "epoch": 0.5877551020408164,
402
+ "grad_norm": 0.22742077708244324,
403
+ "learning_rate": 0.0004,
404
+ "loss": 0.3245,
405
+ "step": 36
406
+ },
407
+ {
408
+ "epoch": 0.5877551020408164,
409
+ "eval_loss": 0.9281033873558044,
410
+ "eval_runtime": 18.2248,
411
+ "eval_samples_per_second": 0.878,
412
+ "eval_steps_per_second": 0.878,
413
+ "step": 36
414
+ },
415
+ {
416
+ "epoch": 0.6040816326530613,
417
+ "grad_norm": 0.2320890575647354,
418
+ "learning_rate": 0.0004,
419
+ "loss": 0.3532,
420
+ "step": 37
421
+ },
422
+ {
423
+ "epoch": 0.6204081632653061,
424
+ "grad_norm": 0.21191200613975525,
425
+ "learning_rate": 0.0004,
426
+ "loss": 0.2973,
427
+ "step": 38
428
+ },
429
+ {
430
+ "epoch": 0.6204081632653061,
431
+ "eval_loss": 0.9274996519088745,
432
+ "eval_runtime": 18.2309,
433
+ "eval_samples_per_second": 0.878,
434
+ "eval_steps_per_second": 0.878,
435
+ "step": 38
436
+ },
437
+ {
438
+ "epoch": 0.636734693877551,
439
+ "grad_norm": 0.24098484218120575,
440
+ "learning_rate": 0.0004,
441
+ "loss": 0.3194,
442
+ "step": 39
443
+ },
444
+ {
445
+ "epoch": 0.6530612244897959,
446
+ "grad_norm": 0.3358725607395172,
447
+ "learning_rate": 0.0004,
448
+ "loss": 0.2833,
449
+ "step": 40
450
+ },
451
+ {
452
+ "epoch": 0.6530612244897959,
453
+ "eval_loss": 0.9254183769226074,
454
+ "eval_runtime": 18.2685,
455
+ "eval_samples_per_second": 0.876,
456
+ "eval_steps_per_second": 0.876,
457
+ "step": 40
458
+ },
459
+ {
460
+ "epoch": 0.6693877551020408,
461
+ "grad_norm": 0.2399401068687439,
462
+ "learning_rate": 0.0004,
463
+ "loss": 0.3381,
464
+ "step": 41
465
+ },
466
+ {
467
+ "epoch": 0.6857142857142857,
468
+ "grad_norm": 0.23229075968265533,
469
+ "learning_rate": 0.0004,
470
+ "loss": 0.3501,
471
+ "step": 42
472
+ },
473
+ {
474
+ "epoch": 0.6857142857142857,
475
+ "eval_loss": 0.9213573932647705,
476
+ "eval_runtime": 18.2788,
477
+ "eval_samples_per_second": 0.875,
478
+ "eval_steps_per_second": 0.875,
479
+ "step": 42
480
+ },
481
+ {
482
+ "epoch": 0.7020408163265306,
483
+ "grad_norm": 0.2341497391462326,
484
+ "learning_rate": 0.0004,
485
+ "loss": 0.3033,
486
+ "step": 43
487
+ },
488
+ {
489
+ "epoch": 0.7183673469387755,
490
+ "grad_norm": 0.22997914254665375,
491
+ "learning_rate": 0.0004,
492
+ "loss": 0.3675,
493
+ "step": 44
494
+ },
495
+ {
496
+ "epoch": 0.7183673469387755,
497
+ "eval_loss": 0.9130539298057556,
498
+ "eval_runtime": 18.2601,
499
+ "eval_samples_per_second": 0.876,
500
+ "eval_steps_per_second": 0.876,
501
+ "step": 44
502
+ },
503
+ {
504
+ "epoch": 0.7346938775510204,
505
+ "grad_norm": 0.23445634543895721,
506
+ "learning_rate": 0.0004,
507
+ "loss": 0.3113,
508
+ "step": 45
509
+ },
510
+ {
511
+ "epoch": 0.7510204081632653,
512
+ "grad_norm": 0.22852188348770142,
513
+ "learning_rate": 0.0004,
514
+ "loss": 0.3593,
515
+ "step": 46
516
+ },
517
+ {
518
+ "epoch": 0.7510204081632653,
519
+ "eval_loss": 0.9100953936576843,
520
+ "eval_runtime": 18.2446,
521
+ "eval_samples_per_second": 0.877,
522
+ "eval_steps_per_second": 0.877,
523
+ "step": 46
524
+ },
525
+ {
526
+ "epoch": 0.7673469387755102,
527
+ "grad_norm": 0.2316325306892395,
528
+ "learning_rate": 0.0004,
529
+ "loss": 0.3121,
530
+ "step": 47
531
+ },
532
+ {
533
+ "epoch": 0.7836734693877551,
534
+ "grad_norm": 0.2397606372833252,
535
+ "learning_rate": 0.0004,
536
+ "loss": 0.2979,
537
+ "step": 48
538
+ },
539
+ {
540
+ "epoch": 0.7836734693877551,
541
+ "eval_loss": 0.9087210297584534,
542
+ "eval_runtime": 18.2833,
543
+ "eval_samples_per_second": 0.875,
544
+ "eval_steps_per_second": 0.875,
545
+ "step": 48
546
+ },
547
+ {
548
+ "epoch": 0.8,
549
+ "grad_norm": 0.22637659311294556,
550
+ "learning_rate": 0.0004,
551
+ "loss": 0.2919,
552
+ "step": 49
553
+ },
554
+ {
555
+ "epoch": 0.8163265306122449,
556
+ "grad_norm": 0.255599707365036,
557
+ "learning_rate": 0.0004,
558
+ "loss": 0.3741,
559
+ "step": 50
560
+ },
561
+ {
562
+ "epoch": 0.8163265306122449,
563
+ "eval_loss": 0.9020435810089111,
564
+ "eval_runtime": 18.2931,
565
+ "eval_samples_per_second": 0.875,
566
+ "eval_steps_per_second": 0.875,
567
+ "step": 50
568
+ },
569
+ {
570
+ "epoch": 0.8163265306122449,
571
+ "eval_loss": 0.9020435810089111,
572
+ "eval_runtime": 18.1276,
573
+ "eval_samples_per_second": 0.883,
574
+ "eval_steps_per_second": 0.883,
575
+ "step": 50
576
+ },
577
+ {
578
+ "epoch": 0.8326530612244898,
579
+ "grad_norm": 0.2062978744506836,
580
+ "learning_rate": 0.0003877467715307749,
581
+ "loss": 0.3303,
582
+ "step": 51
583
+ },
584
+ {
585
+ "epoch": 0.8489795918367347,
586
+ "grad_norm": 0.20149795711040497,
587
+ "learning_rate": 0.0003870443502801494,
588
+ "loss": 0.3212,
589
+ "step": 52
590
+ },
591
+ {
592
+ "epoch": 0.8489795918367347,
593
+ "eval_loss": 0.8994156718254089,
594
+ "eval_runtime": 18.1853,
595
+ "eval_samples_per_second": 0.88,
596
+ "eval_steps_per_second": 0.88,
597
+ "step": 52
598
+ },
599
+ {
600
+ "epoch": 0.8653061224489796,
601
+ "grad_norm": 0.17913399636745453,
602
+ "learning_rate": 0.0003863230255984052,
603
+ "loss": 0.2637,
604
+ "step": 53
605
+ },
606
+ {
607
+ "epoch": 0.8816326530612245,
608
+ "grad_norm": 0.19331133365631104,
609
+ "learning_rate": 0.00038558287038542615,
610
+ "loss": 0.3564,
611
+ "step": 54
612
+ },
613
+ {
614
+ "epoch": 0.8816326530612245,
615
+ "eval_loss": 0.8963940143585205,
616
+ "eval_runtime": 18.223,
617
+ "eval_samples_per_second": 0.878,
618
+ "eval_steps_per_second": 0.878,
619
+ "step": 54
620
+ },
621
+ {
622
+ "epoch": 0.8979591836734694,
623
+ "grad_norm": 0.20378044247627258,
624
+ "learning_rate": 0.00038482395944418313,
625
+ "loss": 0.3253,
626
+ "step": 55
627
+ },
628
+ {
629
+ "epoch": 0.9142857142857143,
630
+ "grad_norm": 0.19742076098918915,
631
+ "learning_rate": 0.0003840463694731741,
632
+ "loss": 0.3715,
633
+ "step": 56
634
+ },
635
+ {
636
+ "epoch": 0.9142857142857143,
637
+ "eval_loss": 0.8902382850646973,
638
+ "eval_runtime": 18.2093,
639
+ "eval_samples_per_second": 0.879,
640
+ "eval_steps_per_second": 0.879,
641
+ "step": 56
642
+ },
643
+ {
644
+ "epoch": 0.9306122448979591,
645
+ "grad_norm": 0.1908055692911148,
646
+ "learning_rate": 0.0003832501790586724,
647
+ "loss": 0.3305,
648
+ "step": 57
649
+ },
650
+ {
651
+ "epoch": 0.9469387755102041,
652
+ "grad_norm": 0.21527761220932007,
653
+ "learning_rate": 0.0003824354686667848,
654
+ "loss": 0.3523,
655
+ "step": 58
656
+ },
657
+ {
658
+ "epoch": 0.9469387755102041,
659
+ "eval_loss": 0.8786917328834534,
660
+ "eval_runtime": 18.2124,
661
+ "eval_samples_per_second": 0.879,
662
+ "eval_steps_per_second": 0.879,
663
+ "step": 58
664
+ },
665
+ {
666
+ "epoch": 0.963265306122449,
667
+ "grad_norm": 0.1817687749862671,
668
+ "learning_rate": 0.00038160232063531917,
669
+ "loss": 0.2616,
670
+ "step": 59
671
+ },
672
+ {
673
+ "epoch": 0.9795918367346939,
674
+ "grad_norm": 0.17659063637256622,
675
+ "learning_rate": 0.0003807508191654631,
676
+ "loss": 0.251,
677
+ "step": 60
678
+ },
679
+ {
680
+ "epoch": 0.9795918367346939,
681
+ "eval_loss": 0.8799586296081543,
682
+ "eval_runtime": 18.2543,
683
+ "eval_samples_per_second": 0.877,
684
+ "eval_steps_per_second": 0.877,
685
+ "step": 60
686
+ },
687
+ {
688
+ "epoch": 0.9959183673469387,
689
+ "grad_norm": 0.22647982835769653,
690
+ "learning_rate": 0.0003798810503132742,
691
+ "loss": 0.2881,
692
+ "step": 61
693
+ },
694
+ {
695
+ "epoch": 1.0122448979591836,
696
+ "grad_norm": 0.45377442240715027,
697
+ "learning_rate": 0.00037899310198098295,
698
+ "loss": 0.5515,
699
+ "step": 62
700
+ },
701
+ {
702
+ "epoch": 1.0122448979591836,
703
+ "eval_loss": 0.8895297050476074,
704
+ "eval_runtime": 18.2212,
705
+ "eval_samples_per_second": 0.878,
706
+ "eval_steps_per_second": 0.878,
707
+ "step": 62
708
+ },
709
+ {
710
+ "epoch": 1.0285714285714285,
711
+ "grad_norm": 0.3527546226978302,
712
+ "learning_rate": 0.000378087063908109,
713
+ "loss": 0.2427,
714
+ "step": 63
715
+ },
716
+ {
717
+ "epoch": 1.0448979591836736,
718
+ "grad_norm": 0.2781178951263428,
719
+ "learning_rate": 0.0003771630276623915,
720
+ "loss": 0.2215,
721
+ "step": 64
722
+ },
723
+ {
724
+ "epoch": 1.0448979591836736,
725
+ "eval_loss": 0.9294220209121704,
726
+ "eval_runtime": 18.226,
727
+ "eval_samples_per_second": 0.878,
728
+ "eval_steps_per_second": 0.878,
729
+ "step": 64
730
+ },
731
+ {
732
+ "epoch": 1.0612244897959184,
733
+ "grad_norm": 0.2543565034866333,
734
+ "learning_rate": 0.00037622108663053536,
735
+ "loss": 0.2761,
736
+ "step": 65
737
+ },
738
+ {
739
+ "epoch": 1.0775510204081633,
740
+ "grad_norm": 0.26259011030197144,
741
+ "learning_rate": 0.0003752613360087727,
742
+ "loss": 0.2425,
743
+ "step": 66
744
+ },
745
+ {
746
+ "epoch": 1.0775510204081633,
747
+ "eval_loss": 0.9212721586227417,
748
+ "eval_runtime": 18.2309,
749
+ "eval_samples_per_second": 0.878,
750
+ "eval_steps_per_second": 0.878,
751
+ "step": 66
752
+ },
753
+ {
754
+ "epoch": 1.0938775510204082,
755
+ "grad_norm": 0.36850446462631226,
756
+ "learning_rate": 0.00037428387279324257,
757
+ "loss": 0.225,
758
+ "step": 67
759
+ },
760
+ {
761
+ "epoch": 1.110204081632653,
762
+ "grad_norm": 0.23748713731765747,
763
+ "learning_rate": 0.0003732887957701874,
764
+ "loss": 0.2363,
765
+ "step": 68
766
+ },
767
+ {
768
+ "epoch": 1.110204081632653,
769
+ "eval_loss": 0.9431418776512146,
770
+ "eval_runtime": 18.2471,
771
+ "eval_samples_per_second": 0.877,
772
+ "eval_steps_per_second": 0.877,
773
+ "step": 68
774
+ },
775
+ {
776
+ "epoch": 1.126530612244898,
777
+ "grad_norm": 0.23217403888702393,
778
+ "learning_rate": 0.00037227620550597,
779
+ "loss": 0.2364,
780
+ "step": 69
781
+ },
782
+ {
783
+ "epoch": 1.1428571428571428,
784
+ "grad_norm": 0.28124868869781494,
785
+ "learning_rate": 0.0003712462043369093,
786
+ "loss": 0.2197,
787
+ "step": 70
788
+ },
789
+ {
790
+ "epoch": 1.1428571428571428,
791
+ "eval_loss": 0.9205393195152283,
792
+ "eval_runtime": 18.2662,
793
+ "eval_samples_per_second": 0.876,
794
+ "eval_steps_per_second": 0.876,
795
+ "step": 70
796
+ },
797
+ {
798
+ "epoch": 1.1591836734693877,
799
+ "grad_norm": 0.2142041176557541,
800
+ "learning_rate": 0.00037019889635893843,
801
+ "loss": 0.1958,
802
+ "step": 71
803
+ },
804
+ {
805
+ "epoch": 1.1755102040816325,
806
+ "grad_norm": 0.34761127829551697,
807
+ "learning_rate": 0.0003691343874170838,
808
+ "loss": 0.2183,
809
+ "step": 72
810
+ },
811
+ {
812
+ "epoch": 1.1755102040816325,
813
+ "eval_loss": 0.9254322648048401,
814
+ "eval_runtime": 18.2303,
815
+ "eval_samples_per_second": 0.878,
816
+ "eval_steps_per_second": 0.878,
817
+ "step": 72
818
+ },
819
+ {
820
+ "epoch": 1.1918367346938776,
821
+ "grad_norm": 0.2560065686702728,
822
+ "learning_rate": 0.00036805278509476844,
823
+ "loss": 0.248,
824
+ "step": 73
825
+ },
826
+ {
827
+ "epoch": 1.2081632653061225,
828
+ "grad_norm": 0.7435296773910522,
829
+ "learning_rate": 0.00036695419870293915,
830
+ "loss": 0.2356,
831
+ "step": 74
832
+ },
833
+ {
834
+ "epoch": 1.2081632653061225,
835
+ "eval_loss": 0.9271378517150879,
836
+ "eval_runtime": 18.2503,
837
+ "eval_samples_per_second": 0.877,
838
+ "eval_steps_per_second": 0.877,
839
+ "step": 74
840
+ },
841
+ {
842
+ "epoch": 1.2244897959183674,
843
+ "grad_norm": 0.8685758113861084,
844
+ "learning_rate": 0.00036583873926901867,
845
+ "loss": 0.2129,
846
+ "step": 75
847
+ },
848
+ {
849
+ "epoch": 1.2408163265306122,
850
+ "grad_norm": 1.2740998268127441,
851
+ "learning_rate": 0.0003647065195256855,
852
+ "loss": 0.2469,
853
+ "step": 76
854
+ },
855
+ {
856
+ "epoch": 1.2408163265306122,
857
+ "eval_loss": 0.9236885905265808,
858
+ "eval_runtime": 18.2226,
859
+ "eval_samples_per_second": 0.878,
860
+ "eval_steps_per_second": 0.878,
861
+ "step": 76
862
+ },
863
+ {
864
+ "epoch": 1.2571428571428571,
865
+ "grad_norm": 0.28524693846702576,
866
+ "learning_rate": 0.0003635576538994801,
867
+ "loss": 0.2278,
868
+ "step": 77
869
+ },
870
+ {
871
+ "epoch": 1.273469387755102,
872
+ "grad_norm": 1.0116885900497437,
873
+ "learning_rate": 0.0003623922584992409,
874
+ "loss": 0.2488,
875
+ "step": 78
876
+ },
877
+ {
878
+ "epoch": 1.273469387755102,
879
+ "eval_loss": 0.923646867275238,
880
+ "eval_runtime": 18.2519,
881
+ "eval_samples_per_second": 0.877,
882
+ "eval_steps_per_second": 0.877,
883
+ "step": 78
884
+ },
885
+ {
886
+ "epoch": 1.2897959183673469,
887
+ "grad_norm": 0.9336573481559753,
888
+ "learning_rate": 0.0003612104511043694,
889
+ "loss": 0.3095,
890
+ "step": 79
891
+ },
892
+ {
893
+ "epoch": 1.306122448979592,
894
+ "grad_norm": 0.43459734320640564,
895
+ "learning_rate": 0.0003600123511529278,
896
+ "loss": 0.2215,
897
+ "step": 80
898
+ },
899
+ {
900
+ "epoch": 1.306122448979592,
901
+ "eval_loss": 0.941472589969635,
902
+ "eval_runtime": 18.251,
903
+ "eval_samples_per_second": 0.877,
904
+ "eval_steps_per_second": 0.877,
905
+ "step": 80
906
+ },
907
+ {
908
+ "epoch": 1.3224489795918366,
909
+ "grad_norm": 0.39941656589508057,
910
+ "learning_rate": 0.0003587980797295671,
911
+ "loss": 0.251,
912
+ "step": 81
913
+ },
914
+ {
915
+ "epoch": 1.3387755102040817,
916
+ "grad_norm": 0.2876632511615753,
917
+ "learning_rate": 0.0003575677595532904,
918
+ "loss": 0.208,
919
+ "step": 82
920
+ },
921
+ {
922
+ "epoch": 1.3387755102040817,
923
+ "eval_loss": 0.932316780090332,
924
+ "eval_runtime": 18.2326,
925
+ "eval_samples_per_second": 0.878,
926
+ "eval_steps_per_second": 0.878,
927
+ "step": 82
928
+ },
929
+ {
930
+ "epoch": 1.3551020408163266,
931
+ "grad_norm": 0.30556565523147583,
932
+ "learning_rate": 0.0003563215149650505,
933
+ "loss": 0.2821,
934
+ "step": 83
935
+ },
936
+ {
937
+ "epoch": 1.3714285714285714,
938
+ "grad_norm": 0.3039940595626831,
939
+ "learning_rate": 0.00035505947191518316,
940
+ "loss": 0.2177,
941
+ "step": 84
942
+ },
943
+ {
944
+ "epoch": 1.3714285714285714,
945
+ "eval_loss": 0.9171479344367981,
946
+ "eval_runtime": 18.2397,
947
+ "eval_samples_per_second": 0.877,
948
+ "eval_steps_per_second": 0.877,
949
+ "step": 84
950
+ },
951
+ {
952
+ "epoch": 1.3877551020408163,
953
+ "grad_norm": 0.32876476645469666,
954
+ "learning_rate": 0.0003537817579506783,
955
+ "loss": 0.2142,
956
+ "step": 85
957
+ },
958
+ {
959
+ "epoch": 1.4040816326530612,
960
+ "grad_norm": 0.26468542218208313,
961
+ "learning_rate": 0.0003524885022022896,
962
+ "loss": 0.2293,
963
+ "step": 86
964
+ },
965
+ {
966
+ "epoch": 1.4040816326530612,
967
+ "eval_loss": 0.9176874756813049,
968
+ "eval_runtime": 18.2553,
969
+ "eval_samples_per_second": 0.876,
970
+ "eval_steps_per_second": 0.876,
971
+ "step": 86
972
+ },
973
+ {
974
+ "epoch": 1.420408163265306,
975
+ "grad_norm": 0.9715031981468201,
976
+ "learning_rate": 0.000351179835371484,
977
+ "loss": 0.235,
978
+ "step": 87
979
+ },
980
+ {
981
+ "epoch": 1.436734693877551,
982
+ "grad_norm": 0.8392952680587769,
983
+ "learning_rate": 0.00034985588971723233,
984
+ "loss": 0.2307,
985
+ "step": 88
986
+ },
987
+ {
988
+ "epoch": 1.436734693877551,
989
+ "eval_loss": 0.9272938370704651,
990
+ "eval_runtime": 18.2194,
991
+ "eval_samples_per_second": 0.878,
992
+ "eval_steps_per_second": 0.878,
993
+ "step": 88
994
+ },
995
+ {
996
+ "epoch": 1.453061224489796,
997
+ "grad_norm": 0.28850337862968445,
998
+ "learning_rate": 0.00034851679904264314,
999
+ "loss": 0.2403,
1000
+ "step": 89
1001
+ },
1002
+ {
1003
+ "epoch": 1.469387755102041,
1004
+ "grad_norm": 0.46389341354370117,
1005
+ "learning_rate": 0.00034716269868143956,
1006
+ "loss": 0.2464,
1007
+ "step": 90
1008
+ },
1009
+ {
1010
+ "epoch": 1.469387755102041,
1011
+ "eval_loss": 0.9267984628677368,
1012
+ "eval_runtime": 18.2514,
1013
+ "eval_samples_per_second": 0.877,
1014
+ "eval_steps_per_second": 0.877,
1015
+ "step": 90
1016
+ },
1017
+ {
1018
+ "epoch": 1.4857142857142858,
1019
+ "grad_norm": 0.29597121477127075,
1020
+ "learning_rate": 0.00034579372548428235,
1021
+ "loss": 0.2307,
1022
+ "step": 91
1023
+ },
1024
+ {
1025
+ "epoch": 1.5020408163265306,
1026
+ "grad_norm": 0.3392711877822876,
1027
+ "learning_rate": 0.00034441001780493886,
1028
+ "loss": 0.231,
1029
+ "step": 92
1030
+ },
1031
+ {
1032
+ "epoch": 1.5020408163265306,
1033
+ "eval_loss": 0.9267009496688843,
1034
+ "eval_runtime": 18.2179,
1035
+ "eval_samples_per_second": 0.878,
1036
+ "eval_steps_per_second": 0.878,
1037
+ "step": 92
1038
+ },
1039
+ {
1040
+ "epoch": 1.5183673469387755,
1041
+ "grad_norm": 0.2309531569480896,
1042
+ "learning_rate": 0.00034301171548630063,
1043
+ "loss": 0.2307,
1044
+ "step": 93
1045
+ },
1046
+ {
1047
+ "epoch": 1.5346938775510204,
1048
+ "grad_norm": 0.28941744565963745,
1049
+ "learning_rate": 0.0003415989598462506,
1050
+ "loss": 0.2384,
1051
+ "step": 94
1052
+ },
1053
+ {
1054
+ "epoch": 1.5346938775510204,
1055
+ "eval_loss": 0.9336121082305908,
1056
+ "eval_runtime": 18.2184,
1057
+ "eval_samples_per_second": 0.878,
1058
+ "eval_steps_per_second": 0.878,
1059
+ "step": 94
1060
+ },
1061
+ {
1062
+ "epoch": 1.5510204081632653,
1063
+ "grad_norm": 0.22579389810562134,
1064
+ "learning_rate": 0.00034017189366338034,
1065
+ "loss": 0.1949,
1066
+ "step": 95
1067
+ },
1068
+ {
1069
+ "epoch": 1.5673469387755103,
1070
+ "grad_norm": 0.2894729971885681,
1071
+ "learning_rate": 0.000338730661162561,
1072
+ "loss": 0.2348,
1073
+ "step": 96
1074
+ },
1075
+ {
1076
+ "epoch": 1.5673469387755103,
1077
+ "eval_loss": 0.9432627558708191,
1078
+ "eval_runtime": 18.2158,
1079
+ "eval_samples_per_second": 0.878,
1080
+ "eval_steps_per_second": 0.878,
1081
+ "step": 96
1082
+ },
1083
+ {
1084
+ "epoch": 1.583673469387755,
1085
+ "grad_norm": 0.24218647181987762,
1086
+ "learning_rate": 0.00033727540800036683,
1087
+ "loss": 0.2113,
1088
+ "step": 97
1089
+ },
1090
+ {
1091
+ "epoch": 1.6,
1092
+ "grad_norm": 0.2695946991443634,
1093
+ "learning_rate": 0.0003358062812503548,
1094
+ "loss": 0.2209,
1095
+ "step": 98
1096
+ },
1097
+ {
1098
+ "epoch": 1.6,
1099
+ "eval_loss": 0.9510765075683594,
1100
+ "eval_runtime": 18.2181,
1101
+ "eval_samples_per_second": 0.878,
1102
+ "eval_steps_per_second": 0.878,
1103
+ "step": 98
1104
+ },
1105
+ {
1106
+ "epoch": 1.6163265306122447,
1107
+ "grad_norm": 0.27196425199508667,
1108
+ "learning_rate": 0.00033432342938820086,
1109
+ "loss": 0.2366,
1110
+ "step": 99
1111
+ },
1112
+ {
1113
+ "epoch": 1.6326530612244898,
1114
+ "grad_norm": 0.2302471101284027,
1115
+ "learning_rate": 0.0003328270022766941,
1116
+ "loss": 0.2099,
1117
+ "step": 100
1118
+ },
1119
+ {
1120
+ "epoch": 1.6326530612244898,
1121
+ "eval_loss": 0.9363111853599548,
1122
+ "eval_runtime": 18.2175,
1123
+ "eval_samples_per_second": 0.878,
1124
+ "eval_steps_per_second": 0.878,
1125
+ "step": 100
1126
+ },
1127
+ {
1128
+ "epoch": 1.6489795918367347,
1129
+ "grad_norm": 0.24810455739498138,
1130
+ "learning_rate": 0.0003313171511505913,
1131
+ "loss": 0.2196,
1132
+ "step": 101
1133
+ },
1134
+ {
1135
+ "epoch": 1.6653061224489796,
1136
+ "grad_norm": 0.25561368465423584,
1137
+ "learning_rate": 0.0003297940286013326,
1138
+ "loss": 0.253,
1139
+ "step": 102
1140
+ },
1141
+ {
1142
+ "epoch": 1.6653061224489796,
1143
+ "eval_loss": 0.942488431930542,
1144
+ "eval_runtime": 18.2068,
1145
+ "eval_samples_per_second": 0.879,
1146
+ "eval_steps_per_second": 0.879,
1147
+ "step": 102
1148
+ },
1149
+ {
1150
+ "epoch": 1.6816326530612244,
1151
+ "grad_norm": 0.22677375376224518,
1152
+ "learning_rate": 0.0003282577885616198,
1153
+ "loss": 0.1789,
1154
+ "step": 103
1155
+ },
1156
+ {
1157
+ "epoch": 1.6979591836734693,
1158
+ "grad_norm": 0.26009589433670044,
1159
+ "learning_rate": 0.0003267085862898594,
1160
+ "loss": 0.2541,
1161
+ "step": 104
1162
+ },
1163
+ {
1164
+ "epoch": 1.6979591836734693,
1165
+ "eval_loss": 0.9335595369338989,
1166
+ "eval_runtime": 18.2507,
1167
+ "eval_samples_per_second": 0.877,
1168
+ "eval_steps_per_second": 0.877,
1169
+ "step": 104
1170
+ },
1171
+ {
1172
+ "epoch": 1.7142857142857144,
1173
+ "grad_norm": 0.20782141387462616,
1174
+ "learning_rate": 0.0003251465783544716,
1175
+ "loss": 0.2308,
1176
+ "step": 105
1177
+ },
1178
+ {
1179
+ "epoch": 1.730612244897959,
1180
+ "grad_norm": 0.22768278419971466,
1181
+ "learning_rate": 0.0003235719226180669,
1182
+ "loss": 0.2354,
1183
+ "step": 106
1184
+ },
1185
+ {
1186
+ "epoch": 1.730612244897959,
1187
+ "eval_loss": 0.9376662373542786,
1188
+ "eval_runtime": 18.2284,
1189
+ "eval_samples_per_second": 0.878,
1190
+ "eval_steps_per_second": 0.878,
1191
+ "step": 106
1192
+ },
1193
+ {
1194
+ "epoch": 1.7469387755102042,
1195
+ "grad_norm": 0.23742002248764038,
1196
+ "learning_rate": 0.00032198477822149185,
1197
+ "loss": 0.2306,
1198
+ "step": 107
1199
+ },
1200
+ {
1201
+ "epoch": 1.763265306122449,
1202
+ "grad_norm": 0.25688832998275757,
1203
+ "learning_rate": 0.0003203853055677457,
1204
+ "loss": 0.2816,
1205
+ "step": 108
1206
+ },
1207
+ {
1208
+ "epoch": 1.763265306122449,
1209
+ "eval_loss": 0.9434496164321899,
1210
+ "eval_runtime": 18.2263,
1211
+ "eval_samples_per_second": 0.878,
1212
+ "eval_steps_per_second": 0.878,
1213
+ "step": 108
1214
+ },
1215
+ {
1216
+ "epoch": 1.779591836734694,
1217
+ "grad_norm": 0.2690117359161377,
1218
+ "learning_rate": 0.00031877366630576946,
1219
+ "loss": 0.2013,
1220
+ "step": 109
1221
+ },
1222
+ {
1223
+ "epoch": 1.7959183673469388,
1224
+ "grad_norm": 0.2317412942647934,
1225
+ "learning_rate": 0.0003171500233141089,
1226
+ "loss": 0.2398,
1227
+ "step": 110
1228
+ },
1229
+ {
1230
+ "epoch": 1.7959183673469388,
1231
+ "eval_loss": 0.9329774975776672,
1232
+ "eval_runtime": 18.2112,
1233
+ "eval_samples_per_second": 0.879,
1234
+ "eval_steps_per_second": 0.879,
1235
+ "step": 110
1236
+ },
1237
+ {
1238
+ "epoch": 1.8122448979591836,
1239
+ "grad_norm": 0.2262117713689804,
1240
+ "learning_rate": 0.0003155145406844535,
1241
+ "loss": 0.207,
1242
+ "step": 111
1243
+ },
1244
+ {
1245
+ "epoch": 1.8285714285714287,
1246
+ "grad_norm": 0.22458741068840027,
1247
+ "learning_rate": 0.00031386738370505293,
1248
+ "loss": 0.2093,
1249
+ "step": 112
1250
+ },
1251
+ {
1252
+ "epoch": 1.8285714285714287,
1253
+ "eval_loss": 0.9222925901412964,
1254
+ "eval_runtime": 18.2333,
1255
+ "eval_samples_per_second": 0.878,
1256
+ "eval_steps_per_second": 0.878,
1257
+ "step": 112
1258
+ },
1259
+ {
1260
+ "epoch": 1.8448979591836734,
1261
+ "grad_norm": 0.24273625016212463,
1262
+ "learning_rate": 0.0003122087188440118,
1263
+ "loss": 0.2434,
1264
+ "step": 113
1265
+ },
1266
+ {
1267
+ "epoch": 1.8612244897959185,
1268
+ "grad_norm": 0.2206314653158188,
1269
+ "learning_rate": 0.0003105387137324663,
1270
+ "loss": 0.2056,
1271
+ "step": 114
1272
+ },
1273
+ {
1274
+ "epoch": 1.8612244897959185,
1275
+ "eval_loss": 0.9319095015525818,
1276
+ "eval_runtime": 18.2327,
1277
+ "eval_samples_per_second": 0.878,
1278
+ "eval_steps_per_second": 0.878,
1279
+ "step": 114
1280
+ },
1281
+ {
1282
+ "epoch": 1.8775510204081631,
1283
+ "grad_norm": 0.2606954574584961,
1284
+ "learning_rate": 0.0003088575371476426,
1285
+ "loss": 0.2198,
1286
+ "step": 115
1287
+ },
1288
+ {
1289
+ "epoch": 1.8938775510204082,
1290
+ "grad_norm": 0.23156337440013885,
1291
+ "learning_rate": 0.0003071653589957993,
1292
+ "loss": 0.1957,
1293
+ "step": 116
1294
+ },
1295
+ {
1296
+ "epoch": 1.8938775510204082,
1297
+ "eval_loss": 0.9314719438552856,
1298
+ "eval_runtime": 18.2411,
1299
+ "eval_samples_per_second": 0.877,
1300
+ "eval_steps_per_second": 0.877,
1301
+ "step": 116
1302
+ },
1303
+ {
1304
+ "epoch": 1.910204081632653,
1305
+ "grad_norm": 0.2253030389547348,
1306
+ "learning_rate": 0.0003054623502950565,
1307
+ "loss": 0.266,
1308
+ "step": 117
1309
+ },
1310
+ {
1311
+ "epoch": 1.926530612244898,
1312
+ "grad_norm": 0.24510890245437622,
1313
+ "learning_rate": 0.0003037486831581115,
1314
+ "loss": 0.2493,
1315
+ "step": 118
1316
+ },
1317
+ {
1318
+ "epoch": 1.926530612244898,
1319
+ "eval_loss": 0.926245927810669,
1320
+ "eval_runtime": 18.2428,
1321
+ "eval_samples_per_second": 0.877,
1322
+ "eval_steps_per_second": 0.877,
1323
+ "step": 118
1324
+ },
1325
+ {
1326
+ "epoch": 1.9428571428571428,
1327
+ "grad_norm": 0.22151368856430054,
1328
+ "learning_rate": 0.00030202453077484494,
1329
+ "loss": 0.2666,
1330
+ "step": 119
1331
+ },
1332
+ {
1333
+ "epoch": 1.9591836734693877,
1334
+ "grad_norm": 0.21714863181114197,
1335
+ "learning_rate": 0.0003002900673948173,
1336
+ "loss": 0.253,
1337
+ "step": 120
1338
+ },
1339
+ {
1340
+ "epoch": 1.9591836734693877,
1341
+ "eval_loss": 0.9263309240341187,
1342
+ "eval_runtime": 18.2196,
1343
+ "eval_samples_per_second": 0.878,
1344
+ "eval_steps_per_second": 0.878,
1345
+ "step": 120
1346
+ }
1347
+ ],
1348
+ "logging_steps": 1,
1349
+ "max_steps": 305,
1350
+ "num_input_tokens_seen": 0,
1351
+ "num_train_epochs": 5,
1352
+ "save_steps": 30,
1353
+ "stateful_callbacks": {
1354
+ "TrainerControl": {
1355
+ "args": {
1356
+ "should_epoch_stop": false,
1357
+ "should_evaluate": false,
1358
+ "should_log": false,
1359
+ "should_save": true,
1360
+ "should_training_stop": false
1361
+ },
1362
+ "attributes": {}
1363
+ }
1364
+ },
1365
+ "total_flos": 1.4518993974018048e+18,
1366
+ "train_batch_size": 1,
1367
+ "trial_name": null,
1368
+ "trial_params": null
1369
+ }
checkpoints/checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac79da65aef3f639fd69fe9d54dd5e1ca8bfcbd1838c7de53d38cfdae9e20ab
3
+ size 5624
checkpoints/checkpoint-180/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoints/checkpoint-180/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints/checkpoint-180/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cb289e4cee59343a94343dd874464e2a3f16b0b7ef0f16fc2ff409230ff316
3
+ size 739321784
checkpoints/checkpoint-180/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05eaeff95032235c8a447c9d107dcdae244337617e1601027085ff18f6bb0cc1
3
+ size 377514226
checkpoints/checkpoint-180/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c864ce42a9a54412e587d71096559f64cc5a5031a374acb69829bcf806c879b
3
+ size 14244
checkpoints/checkpoint-180/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29013f31ab50632e86727b6939407ca902816c2e84145ce53c10f8589737e61f
3
+ size 1064
checkpoints/checkpoint-180/special_tokens_map.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[INST]",
7
+ "[/INST]",
8
+ "[AVAILABLE_TOOLS]",
9
+ "[/AVAILABLE_TOOLS]",
10
+ "[TOOL_RESULTS]",
11
+ "[/TOOL_RESULTS]",
12
+ "[TOOL_CALLS]",
13
+ "[IMG]",
14
+ "<pad>",
15
+ "[IMG_BREAK]",
16
+ "[IMG_END]",
17
+ "[PREFIX]",
18
+ "[MIDDLE]",
19
+ "[SUFFIX]",
20
+ "[SYSTEM_PROMPT]",
21
+ "[/SYSTEM_PROMPT]",
22
+ "[TOOL_CONTENT]",
23
+ "<SPECIAL_20>",
24
+ "<SPECIAL_21>",
25
+ "<SPECIAL_22>",
26
+ "<SPECIAL_23>",
27
+ "<SPECIAL_24>",
28
+ "<SPECIAL_25>",
29
+ "<SPECIAL_26>",
30
+ "<SPECIAL_27>",
31
+ "<SPECIAL_28>",
32
+ "<SPECIAL_29>",
33
+ "<SPECIAL_30>",
34
+ "<SPECIAL_31>",
35
+ "<SPECIAL_32>",
36
+ "<SPECIAL_33>",
37
+ "<SPECIAL_34>",
38
+ "<SPECIAL_35>",
39
+ "<SPECIAL_36>",
40
+ "<SPECIAL_37>",
41
+ "<SPECIAL_38>",
42
+ "<SPECIAL_39>",
43
+ "<SPECIAL_40>",
44
+ "<SPECIAL_41>",
45
+ "<SPECIAL_42>",
46
+ "<SPECIAL_43>",
47
+ "<SPECIAL_44>",
48
+ "<SPECIAL_45>",
49
+ "<SPECIAL_46>",
50
+ "<SPECIAL_47>",
51
+ "<SPECIAL_48>",
52
+ "<SPECIAL_49>",
53
+ "<SPECIAL_50>",
54
+ "<SPECIAL_51>",
55
+ "<SPECIAL_52>",
56
+ "<SPECIAL_53>",
57
+ "<SPECIAL_54>",
58
+ "<SPECIAL_55>",
59
+ "<SPECIAL_56>",
60
+ "<SPECIAL_57>",
61
+ "<SPECIAL_58>",
62
+ "<SPECIAL_59>",
63
+ "<SPECIAL_60>",
64
+ "<SPECIAL_61>",
65
+ "<SPECIAL_62>",
66
+ "<SPECIAL_63>",
67
+ "<SPECIAL_64>",
68
+ "<SPECIAL_65>",
69
+ "<SPECIAL_66>",
70
+ "<SPECIAL_67>",
71
+ "<SPECIAL_68>",
72
+ "<SPECIAL_69>",
73
+ "<SPECIAL_70>",
74
+ "<SPECIAL_71>",
75
+ "<SPECIAL_72>",
76
+ "<SPECIAL_73>",
77
+ "<SPECIAL_74>",
78
+ "<SPECIAL_75>",
79
+ "<SPECIAL_76>",
80
+ "<SPECIAL_77>",
81
+ "<SPECIAL_78>",
82
+ "<SPECIAL_79>",
83
+ "<SPECIAL_80>",
84
+ "<SPECIAL_81>",
85
+ "<SPECIAL_82>",
86
+ "<SPECIAL_83>",
87
+ "<SPECIAL_84>",
88
+ "<SPECIAL_85>",
89
+ "<SPECIAL_86>",
90
+ "<SPECIAL_87>",
91
+ "<SPECIAL_88>",
92
+ "<SPECIAL_89>",
93
+ "<SPECIAL_90>",
94
+ "<SPECIAL_91>",
95
+ "<SPECIAL_92>",
96
+ "<SPECIAL_93>",
97
+ "<SPECIAL_94>",
98
+ "<SPECIAL_95>",
99
+ "<SPECIAL_96>",
100
+ "<SPECIAL_97>",
101
+ "<SPECIAL_98>",
102
+ "<SPECIAL_99>",
103
+ "<SPECIAL_100>",
104
+ "<SPECIAL_101>",
105
+ "<SPECIAL_102>",
106
+ "<SPECIAL_103>",
107
+ "<SPECIAL_104>",
108
+ "<SPECIAL_105>",
109
+ "<SPECIAL_106>",
110
+ "<SPECIAL_107>",
111
+ "<SPECIAL_108>",
112
+ "<SPECIAL_109>",
113
+ "<SPECIAL_110>",
114
+ "<SPECIAL_111>",
115
+ "<SPECIAL_112>",
116
+ "<SPECIAL_113>",
117
+ "<SPECIAL_114>",
118
+ "<SPECIAL_115>",
119
+ "<SPECIAL_116>",
120
+ "<SPECIAL_117>",
121
+ "<SPECIAL_118>",
122
+ "<SPECIAL_119>",
123
+ "<SPECIAL_120>",
124
+ "<SPECIAL_121>",
125
+ "<SPECIAL_122>",
126
+ "<SPECIAL_123>",
127
+ "<SPECIAL_124>",
128
+ "<SPECIAL_125>",
129
+ "<SPECIAL_126>",
130
+ "<SPECIAL_127>",
131
+ "<SPECIAL_128>",
132
+ "<SPECIAL_129>",
133
+ "<SPECIAL_130>",
134
+ "<SPECIAL_131>",
135
+ "<SPECIAL_132>",
136
+ "<SPECIAL_133>",
137
+ "<SPECIAL_134>",
138
+ "<SPECIAL_135>",
139
+ "<SPECIAL_136>",
140
+ "<SPECIAL_137>",
141
+ "<SPECIAL_138>",
142
+ "<SPECIAL_139>",
143
+ "<SPECIAL_140>",
144
+ "<SPECIAL_141>",
145
+ "<SPECIAL_142>",
146
+ "<SPECIAL_143>",
147
+ "<SPECIAL_144>",
148
+ "<SPECIAL_145>",
149
+ "<SPECIAL_146>",
150
+ "<SPECIAL_147>",
151
+ "<SPECIAL_148>",
152
+ "<SPECIAL_149>",
153
+ "<SPECIAL_150>",
154
+ "<SPECIAL_151>",
155
+ "<SPECIAL_152>",
156
+ "<SPECIAL_153>",
157
+ "<SPECIAL_154>",
158
+ "<SPECIAL_155>",
159
+ "<SPECIAL_156>",
160
+ "<SPECIAL_157>",
161
+ "<SPECIAL_158>",
162
+ "<SPECIAL_159>",
163
+ "<SPECIAL_160>",
164
+ "<SPECIAL_161>",
165
+ "<SPECIAL_162>",
166
+ "<SPECIAL_163>",
167
+ "<SPECIAL_164>",
168
+ "<SPECIAL_165>",
169
+ "<SPECIAL_166>",
170
+ "<SPECIAL_167>",
171
+ "<SPECIAL_168>",
172
+ "<SPECIAL_169>",
173
+ "<SPECIAL_170>",
174
+ "<SPECIAL_171>",
175
+ "<SPECIAL_172>",
176
+ "<SPECIAL_173>",
177
+ "<SPECIAL_174>",
178
+ "<SPECIAL_175>",
179
+ "<SPECIAL_176>",
180
+ "<SPECIAL_177>",
181
+ "<SPECIAL_178>",
182
+ "<SPECIAL_179>",
183
+ "<SPECIAL_180>",
184
+ "<SPECIAL_181>",
185
+ "<SPECIAL_182>",
186
+ "<SPECIAL_183>",
187
+ "<SPECIAL_184>",
188
+ "<SPECIAL_185>",
189
+ "<SPECIAL_186>",
190
+ "<SPECIAL_187>",
191
+ "<SPECIAL_188>",
192
+ "<SPECIAL_189>",
193
+ "<SPECIAL_190>",
194
+ "<SPECIAL_191>",
195
+ "<SPECIAL_192>",
196
+ "<SPECIAL_193>",
197
+ "<SPECIAL_194>",
198
+ "<SPECIAL_195>",
199
+ "<SPECIAL_196>",
200
+ "<SPECIAL_197>",
201
+ "<SPECIAL_198>",
202
+ "<SPECIAL_199>",
203
+ "<SPECIAL_200>",
204
+ "<SPECIAL_201>",
205
+ "<SPECIAL_202>",
206
+ "<SPECIAL_203>",
207
+ "<SPECIAL_204>",
208
+ "<SPECIAL_205>",
209
+ "<SPECIAL_206>",
210
+ "<SPECIAL_207>",
211
+ "<SPECIAL_208>",
212
+ "<SPECIAL_209>",
213
+ "<SPECIAL_210>",
214
+ "<SPECIAL_211>",
215
+ "<SPECIAL_212>",
216
+ "<SPECIAL_213>",
217
+ "<SPECIAL_214>",
218
+ "<SPECIAL_215>",
219
+ "<SPECIAL_216>",
220
+ "<SPECIAL_217>",
221
+ "<SPECIAL_218>",
222
+ "<SPECIAL_219>",
223
+ "<SPECIAL_220>",
224
+ "<SPECIAL_221>",
225
+ "<SPECIAL_222>",
226
+ "<SPECIAL_223>",
227
+ "<SPECIAL_224>",
228
+ "<SPECIAL_225>",
229
+ "<SPECIAL_226>",
230
+ "<SPECIAL_227>",
231
+ "<SPECIAL_228>",
232
+ "<SPECIAL_229>",
233
+ "<SPECIAL_230>",
234
+ "<SPECIAL_231>",
235
+ "<SPECIAL_232>",
236
+ "<SPECIAL_233>",
237
+ "<SPECIAL_234>",
238
+ "<SPECIAL_235>",
239
+ "<SPECIAL_236>",
240
+ "<SPECIAL_237>",
241
+ "<SPECIAL_238>",
242
+ "<SPECIAL_239>",
243
+ "<SPECIAL_240>",
244
+ "<SPECIAL_241>",
245
+ "<SPECIAL_242>",
246
+ "<SPECIAL_243>",
247
+ "<SPECIAL_244>",
248
+ "<SPECIAL_245>",
249
+ "<SPECIAL_246>",
250
+ "<SPECIAL_247>",
251
+ "<SPECIAL_248>",
252
+ "<SPECIAL_249>",
253
+ "<SPECIAL_250>",
254
+ "<SPECIAL_251>",
255
+ "<SPECIAL_252>",
256
+ "<SPECIAL_253>",
257
+ "<SPECIAL_254>",
258
+ "<SPECIAL_255>",
259
+ "<SPECIAL_256>",
260
+ "<SPECIAL_257>",
261
+ "<SPECIAL_258>",
262
+ "<SPECIAL_259>",
263
+ "<SPECIAL_260>",
264
+ "<SPECIAL_261>",
265
+ "<SPECIAL_262>",
266
+ "<SPECIAL_263>",
267
+ "<SPECIAL_264>",
268
+ "<SPECIAL_265>",
269
+ "<SPECIAL_266>",
270
+ "<SPECIAL_267>",
271
+ "<SPECIAL_268>",
272
+ "<SPECIAL_269>",
273
+ "<SPECIAL_270>",
274
+ "<SPECIAL_271>",
275
+ "<SPECIAL_272>",
276
+ "<SPECIAL_273>",
277
+ "<SPECIAL_274>",
278
+ "<SPECIAL_275>",
279
+ "<SPECIAL_276>",
280
+ "<SPECIAL_277>",
281
+ "<SPECIAL_278>",
282
+ "<SPECIAL_279>",
283
+ "<SPECIAL_280>",
284
+ "<SPECIAL_281>",
285
+ "<SPECIAL_282>",
286
+ "<SPECIAL_283>",
287
+ "<SPECIAL_284>",
288
+ "<SPECIAL_285>",
289
+ "<SPECIAL_286>",
290
+ "<SPECIAL_287>",
291
+ "<SPECIAL_288>",
292
+ "<SPECIAL_289>",
293
+ "<SPECIAL_290>",
294
+ "<SPECIAL_291>",
295
+ "<SPECIAL_292>",
296
+ "<SPECIAL_293>",
297
+ "<SPECIAL_294>",
298
+ "<SPECIAL_295>",
299
+ "<SPECIAL_296>",
300
+ "<SPECIAL_297>",
301
+ "<SPECIAL_298>",
302
+ "<SPECIAL_299>",
303
+ "<SPECIAL_300>",
304
+ "<SPECIAL_301>",
305
+ "<SPECIAL_302>",
306
+ "<SPECIAL_303>",
307
+ "<SPECIAL_304>",
308
+ "<SPECIAL_305>",
309
+ "<SPECIAL_306>",
310
+ "<SPECIAL_307>",
311
+ "<SPECIAL_308>",
312
+ "<SPECIAL_309>",
313
+ "<SPECIAL_310>",
314
+ "<SPECIAL_311>",
315
+ "<SPECIAL_312>",
316
+ "<SPECIAL_313>",
317
+ "<SPECIAL_314>",
318
+ "<SPECIAL_315>",
319
+ "<SPECIAL_316>",
320
+ "<SPECIAL_317>",
321
+ "<SPECIAL_318>",
322
+ "<SPECIAL_319>",
323
+ "<SPECIAL_320>",
324
+ "<SPECIAL_321>",
325
+ "<SPECIAL_322>",
326
+ "<SPECIAL_323>",
327
+ "<SPECIAL_324>",
328
+ "<SPECIAL_325>",
329
+ "<SPECIAL_326>",
330
+ "<SPECIAL_327>",
331
+ "<SPECIAL_328>",
332
+ "<SPECIAL_329>",
333
+ "<SPECIAL_330>",
334
+ "<SPECIAL_331>",
335
+ "<SPECIAL_332>",
336
+ "<SPECIAL_333>",
337
+ "<SPECIAL_334>",
338
+ "<SPECIAL_335>",
339
+ "<SPECIAL_336>",
340
+ "<SPECIAL_337>",
341
+ "<SPECIAL_338>",
342
+ "<SPECIAL_339>",
343
+ "<SPECIAL_340>",
344
+ "<SPECIAL_341>",
345
+ "<SPECIAL_342>",
346
+ "<SPECIAL_343>",
347
+ "<SPECIAL_344>",
348
+ "<SPECIAL_345>",
349
+ "<SPECIAL_346>",
350
+ "<SPECIAL_347>",
351
+ "<SPECIAL_348>",
352
+ "<SPECIAL_349>",
353
+ "<SPECIAL_350>",
354
+ "<SPECIAL_351>",
355
+ "<SPECIAL_352>",
356
+ "<SPECIAL_353>",
357
+ "<SPECIAL_354>",
358
+ "<SPECIAL_355>",
359
+ "<SPECIAL_356>",
360
+ "<SPECIAL_357>",
361
+ "<SPECIAL_358>",
362
+ "<SPECIAL_359>",
363
+ "<SPECIAL_360>",
364
+ "<SPECIAL_361>",
365
+ "<SPECIAL_362>",
366
+ "<SPECIAL_363>",
367
+ "<SPECIAL_364>",
368
+ "<SPECIAL_365>",
369
+ "<SPECIAL_366>",
370
+ "<SPECIAL_367>",
371
+ "<SPECIAL_368>",
372
+ "<SPECIAL_369>",
373
+ "<SPECIAL_370>",
374
+ "<SPECIAL_371>",
375
+ "<SPECIAL_372>",
376
+ "<SPECIAL_373>",
377
+ "<SPECIAL_374>",
378
+ "<SPECIAL_375>",
379
+ "<SPECIAL_376>",
380
+ "<SPECIAL_377>",
381
+ "<SPECIAL_378>",
382
+ "<SPECIAL_379>",
383
+ "<SPECIAL_380>",
384
+ "<SPECIAL_381>",
385
+ "<SPECIAL_382>",
386
+ "<SPECIAL_383>",
387
+ "<SPECIAL_384>",
388
+ "<SPECIAL_385>",
389
+ "<SPECIAL_386>",
390
+ "<SPECIAL_387>",
391
+ "<SPECIAL_388>",
392
+ "<SPECIAL_389>",
393
+ "<SPECIAL_390>",
394
+ "<SPECIAL_391>",
395
+ "<SPECIAL_392>",
396
+ "<SPECIAL_393>",
397
+ "<SPECIAL_394>",
398
+ "<SPECIAL_395>",
399
+ "<SPECIAL_396>",
400
+ "<SPECIAL_397>",
401
+ "<SPECIAL_398>",
402
+ "<SPECIAL_399>",
403
+ "<SPECIAL_400>",
404
+ "<SPECIAL_401>",
405
+ "<SPECIAL_402>",
406
+ "<SPECIAL_403>",
407
+ "<SPECIAL_404>",
408
+ "<SPECIAL_405>",
409
+ "<SPECIAL_406>",
410
+ "<SPECIAL_407>",
411
+ "<SPECIAL_408>",
412
+ "<SPECIAL_409>",
413
+ "<SPECIAL_410>",
414
+ "<SPECIAL_411>",
415
+ "<SPECIAL_412>",
416
+ "<SPECIAL_413>",
417
+ "<SPECIAL_414>",
418
+ "<SPECIAL_415>",
419
+ "<SPECIAL_416>",
420
+ "<SPECIAL_417>",
421
+ "<SPECIAL_418>",
422
+ "<SPECIAL_419>",
423
+ "<SPECIAL_420>",
424
+ "<SPECIAL_421>",
425
+ "<SPECIAL_422>",
426
+ "<SPECIAL_423>",
427
+ "<SPECIAL_424>",
428
+ "<SPECIAL_425>",
429
+ "<SPECIAL_426>",
430
+ "<SPECIAL_427>",
431
+ "<SPECIAL_428>",
432
+ "<SPECIAL_429>",
433
+ "<SPECIAL_430>",
434
+ "<SPECIAL_431>",
435
+ "<SPECIAL_432>",
436
+ "<SPECIAL_433>",
437
+ "<SPECIAL_434>",
438
+ "<SPECIAL_435>",
439
+ "<SPECIAL_436>",
440
+ "<SPECIAL_437>",
441
+ "<SPECIAL_438>",
442
+ "<SPECIAL_439>",
443
+ "<SPECIAL_440>",
444
+ "<SPECIAL_441>",
445
+ "<SPECIAL_442>",
446
+ "<SPECIAL_443>",
447
+ "<SPECIAL_444>",
448
+ "<SPECIAL_445>",
449
+ "<SPECIAL_446>",
450
+ "<SPECIAL_447>",
451
+ "<SPECIAL_448>",
452
+ "<SPECIAL_449>",
453
+ "<SPECIAL_450>",
454
+ "<SPECIAL_451>",
455
+ "<SPECIAL_452>",
456
+ "<SPECIAL_453>",
457
+ "<SPECIAL_454>",
458
+ "<SPECIAL_455>",
459
+ "<SPECIAL_456>",
460
+ "<SPECIAL_457>",
461
+ "<SPECIAL_458>",
462
+ "<SPECIAL_459>",
463
+ "<SPECIAL_460>",
464
+ "<SPECIAL_461>",
465
+ "<SPECIAL_462>",
466
+ "<SPECIAL_463>",
467
+ "<SPECIAL_464>",
468
+ "<SPECIAL_465>",
469
+ "<SPECIAL_466>",
470
+ "<SPECIAL_467>",
471
+ "<SPECIAL_468>",
472
+ "<SPECIAL_469>",
473
+ "<SPECIAL_470>",
474
+ "<SPECIAL_471>",
475
+ "<SPECIAL_472>",
476
+ "<SPECIAL_473>",
477
+ "<SPECIAL_474>",
478
+ "<SPECIAL_475>",
479
+ "<SPECIAL_476>",
480
+ "<SPECIAL_477>",
481
+ "<SPECIAL_478>",
482
+ "<SPECIAL_479>",
483
+ "<SPECIAL_480>",
484
+ "<SPECIAL_481>",
485
+ "<SPECIAL_482>",
486
+ "<SPECIAL_483>",
487
+ "<SPECIAL_484>",
488
+ "<SPECIAL_485>",
489
+ "<SPECIAL_486>",
490
+ "<SPECIAL_487>",
491
+ "<SPECIAL_488>",
492
+ "<SPECIAL_489>",
493
+ "<SPECIAL_490>",
494
+ "<SPECIAL_491>",
495
+ "<SPECIAL_492>",
496
+ "<SPECIAL_493>",
497
+ "<SPECIAL_494>",
498
+ "<SPECIAL_495>",
499
+ "<SPECIAL_496>",
500
+ "<SPECIAL_497>",
501
+ "<SPECIAL_498>",
502
+ "<SPECIAL_499>",
503
+ "<SPECIAL_500>",
504
+ "<SPECIAL_501>",
505
+ "<SPECIAL_502>",
506
+ "<SPECIAL_503>",
507
+ "<SPECIAL_504>",
508
+ "<SPECIAL_505>",
509
+ "<SPECIAL_506>",
510
+ "<SPECIAL_507>",
511
+ "<SPECIAL_508>",
512
+ "<SPECIAL_509>",
513
+ "<SPECIAL_510>",
514
+ "<SPECIAL_511>",
515
+ "<SPECIAL_512>",
516
+ "<SPECIAL_513>",
517
+ "<SPECIAL_514>",
518
+ "<SPECIAL_515>",
519
+ "<SPECIAL_516>",
520
+ "<SPECIAL_517>",
521
+ "<SPECIAL_518>",
522
+ "<SPECIAL_519>",
523
+ "<SPECIAL_520>",
524
+ "<SPECIAL_521>",
525
+ "<SPECIAL_522>",
526
+ "<SPECIAL_523>",
527
+ "<SPECIAL_524>",
528
+ "<SPECIAL_525>",
529
+ "<SPECIAL_526>",
530
+ "<SPECIAL_527>",
531
+ "<SPECIAL_528>",
532
+ "<SPECIAL_529>",
533
+ "<SPECIAL_530>",
534
+ "<SPECIAL_531>",
535
+ "<SPECIAL_532>",
536
+ "<SPECIAL_533>",
537
+ "<SPECIAL_534>",
538
+ "<SPECIAL_535>",
539
+ "<SPECIAL_536>",
540
+ "<SPECIAL_537>",
541
+ "<SPECIAL_538>",
542
+ "<SPECIAL_539>",
543
+ "<SPECIAL_540>",
544
+ "<SPECIAL_541>",
545
+ "<SPECIAL_542>",
546
+ "<SPECIAL_543>",
547
+ "<SPECIAL_544>",
548
+ "<SPECIAL_545>",
549
+ "<SPECIAL_546>",
550
+ "<SPECIAL_547>",
551
+ "<SPECIAL_548>",
552
+ "<SPECIAL_549>",
553
+ "<SPECIAL_550>",
554
+ "<SPECIAL_551>",
555
+ "<SPECIAL_552>",
556
+ "<SPECIAL_553>",
557
+ "<SPECIAL_554>",
558
+ "<SPECIAL_555>",
559
+ "<SPECIAL_556>",
560
+ "<SPECIAL_557>",
561
+ "<SPECIAL_558>",
562
+ "<SPECIAL_559>",
563
+ "<SPECIAL_560>",
564
+ "<SPECIAL_561>",
565
+ "<SPECIAL_562>",
566
+ "<SPECIAL_563>",
567
+ "<SPECIAL_564>",
568
+ "<SPECIAL_565>",
569
+ "<SPECIAL_566>",
570
+ "<SPECIAL_567>",
571
+ "<SPECIAL_568>",
572
+ "<SPECIAL_569>",
573
+ "<SPECIAL_570>",
574
+ "<SPECIAL_571>",
575
+ "<SPECIAL_572>",
576
+ "<SPECIAL_573>",
577
+ "<SPECIAL_574>",
578
+ "<SPECIAL_575>",
579
+ "<SPECIAL_576>",
580
+ "<SPECIAL_577>",
581
+ "<SPECIAL_578>",
582
+ "<SPECIAL_579>",
583
+ "<SPECIAL_580>",
584
+ "<SPECIAL_581>",
585
+ "<SPECIAL_582>",
586
+ "<SPECIAL_583>",
587
+ "<SPECIAL_584>",
588
+ "<SPECIAL_585>",
589
+ "<SPECIAL_586>",
590
+ "<SPECIAL_587>",
591
+ "<SPECIAL_588>",
592
+ "<SPECIAL_589>",
593
+ "<SPECIAL_590>",
594
+ "<SPECIAL_591>",
595
+ "<SPECIAL_592>",
596
+ "<SPECIAL_593>",
597
+ "<SPECIAL_594>",
598
+ "<SPECIAL_595>",
599
+ "<SPECIAL_596>",
600
+ "<SPECIAL_597>",
601
+ "<SPECIAL_598>",
602
+ "<SPECIAL_599>",
603
+ "<SPECIAL_600>",
604
+ "<SPECIAL_601>",
605
+ "<SPECIAL_602>",
606
+ "<SPECIAL_603>",
607
+ "<SPECIAL_604>",
608
+ "<SPECIAL_605>",
609
+ "<SPECIAL_606>",
610
+ "<SPECIAL_607>",
611
+ "<SPECIAL_608>",
612
+ "<SPECIAL_609>",
613
+ "<SPECIAL_610>",
614
+ "<SPECIAL_611>",
615
+ "<SPECIAL_612>",
616
+ "<SPECIAL_613>",
617
+ "<SPECIAL_614>",
618
+ "<SPECIAL_615>",
619
+ "<SPECIAL_616>",
620
+ "<SPECIAL_617>",
621
+ "<SPECIAL_618>",
622
+ "<SPECIAL_619>",
623
+ "<SPECIAL_620>",
624
+ "<SPECIAL_621>",
625
+ "<SPECIAL_622>",
626
+ "<SPECIAL_623>",
627
+ "<SPECIAL_624>",
628
+ "<SPECIAL_625>",
629
+ "<SPECIAL_626>",
630
+ "<SPECIAL_627>",
631
+ "<SPECIAL_628>",
632
+ "<SPECIAL_629>",
633
+ "<SPECIAL_630>",
634
+ "<SPECIAL_631>",
635
+ "<SPECIAL_632>",
636
+ "<SPECIAL_633>",
637
+ "<SPECIAL_634>",
638
+ "<SPECIAL_635>",
639
+ "<SPECIAL_636>",
640
+ "<SPECIAL_637>",
641
+ "<SPECIAL_638>",
642
+ "<SPECIAL_639>",
643
+ "<SPECIAL_640>",
644
+ "<SPECIAL_641>",
645
+ "<SPECIAL_642>",
646
+ "<SPECIAL_643>",
647
+ "<SPECIAL_644>",
648
+ "<SPECIAL_645>",
649
+ "<SPECIAL_646>",
650
+ "<SPECIAL_647>",
651
+ "<SPECIAL_648>",
652
+ "<SPECIAL_649>",
653
+ "<SPECIAL_650>",
654
+ "<SPECIAL_651>",
655
+ "<SPECIAL_652>",
656
+ "<SPECIAL_653>",
657
+ "<SPECIAL_654>",
658
+ "<SPECIAL_655>",
659
+ "<SPECIAL_656>",
660
+ "<SPECIAL_657>",
661
+ "<SPECIAL_658>",
662
+ "<SPECIAL_659>",
663
+ "<SPECIAL_660>",
664
+ "<SPECIAL_661>",
665
+ "<SPECIAL_662>",
666
+ "<SPECIAL_663>",
667
+ "<SPECIAL_664>",
668
+ "<SPECIAL_665>",
669
+ "<SPECIAL_666>",
670
+ "<SPECIAL_667>",
671
+ "<SPECIAL_668>",
672
+ "<SPECIAL_669>",
673
+ "<SPECIAL_670>",
674
+ "<SPECIAL_671>",
675
+ "<SPECIAL_672>",
676
+ "<SPECIAL_673>",
677
+ "<SPECIAL_674>",
678
+ "<SPECIAL_675>",
679
+ "<SPECIAL_676>",
680
+ "<SPECIAL_677>",
681
+ "<SPECIAL_678>",
682
+ "<SPECIAL_679>",
683
+ "<SPECIAL_680>",
684
+ "<SPECIAL_681>",
685
+ "<SPECIAL_682>",
686
+ "<SPECIAL_683>",
687
+ "<SPECIAL_684>",
688
+ "<SPECIAL_685>",
689
+ "<SPECIAL_686>",
690
+ "<SPECIAL_687>",
691
+ "<SPECIAL_688>",
692
+ "<SPECIAL_689>",
693
+ "<SPECIAL_690>",
694
+ "<SPECIAL_691>",
695
+ "<SPECIAL_692>",
696
+ "<SPECIAL_693>",
697
+ "<SPECIAL_694>",
698
+ "<SPECIAL_695>",
699
+ "<SPECIAL_696>",
700
+ "<SPECIAL_697>",
701
+ "<SPECIAL_698>",
702
+ "<SPECIAL_699>",
703
+ "<SPECIAL_700>",
704
+ "<SPECIAL_701>",
705
+ "<SPECIAL_702>",
706
+ "<SPECIAL_703>",
707
+ "<SPECIAL_704>",
708
+ "<SPECIAL_705>",
709
+ "<SPECIAL_706>",
710
+ "<SPECIAL_707>",
711
+ "<SPECIAL_708>",
712
+ "<SPECIAL_709>",
713
+ "<SPECIAL_710>",
714
+ "<SPECIAL_711>",
715
+ "<SPECIAL_712>",
716
+ "<SPECIAL_713>",
717
+ "<SPECIAL_714>",
718
+ "<SPECIAL_715>",
719
+ "<SPECIAL_716>",
720
+ "<SPECIAL_717>",
721
+ "<SPECIAL_718>",
722
+ "<SPECIAL_719>",
723
+ "<SPECIAL_720>",
724
+ "<SPECIAL_721>",
725
+ "<SPECIAL_722>",
726
+ "<SPECIAL_723>",
727
+ "<SPECIAL_724>",
728
+ "<SPECIAL_725>",
729
+ "<SPECIAL_726>",
730
+ "<SPECIAL_727>",
731
+ "<SPECIAL_728>",
732
+ "<SPECIAL_729>",
733
+ "<SPECIAL_730>",
734
+ "<SPECIAL_731>",
735
+ "<SPECIAL_732>",
736
+ "<SPECIAL_733>",
737
+ "<SPECIAL_734>",
738
+ "<SPECIAL_735>",
739
+ "<SPECIAL_736>",
740
+ "<SPECIAL_737>",
741
+ "<SPECIAL_738>",
742
+ "<SPECIAL_739>",
743
+ "<SPECIAL_740>",
744
+ "<SPECIAL_741>",
745
+ "<SPECIAL_742>",
746
+ "<SPECIAL_743>",
747
+ "<SPECIAL_744>",
748
+ "<SPECIAL_745>",
749
+ "<SPECIAL_746>",
750
+ "<SPECIAL_747>",
751
+ "<SPECIAL_748>",
752
+ "<SPECIAL_749>",
753
+ "<SPECIAL_750>",
754
+ "<SPECIAL_751>",
755
+ "<SPECIAL_752>",
756
+ "<SPECIAL_753>",
757
+ "<SPECIAL_754>",
758
+ "<SPECIAL_755>",
759
+ "<SPECIAL_756>",
760
+ "<SPECIAL_757>",
761
+ "<SPECIAL_758>",
762
+ "<SPECIAL_759>",
763
+ "<SPECIAL_760>",
764
+ "<SPECIAL_761>",
765
+ "<SPECIAL_762>",
766
+ "<SPECIAL_763>",
767
+ "<SPECIAL_764>",
768
+ "<SPECIAL_765>",
769
+ "<SPECIAL_766>",
770
+ "<SPECIAL_767>",
771
+ "<SPECIAL_768>",
772
+ "<SPECIAL_769>",
773
+ "<SPECIAL_770>",
774
+ "<SPECIAL_771>",
775
+ "<SPECIAL_772>",
776
+ "<SPECIAL_773>",
777
+ "<SPECIAL_774>",
778
+ "<SPECIAL_775>",
779
+ "<SPECIAL_776>",
780
+ "<SPECIAL_777>",
781
+ "<SPECIAL_778>",
782
+ "<SPECIAL_779>",
783
+ "<SPECIAL_780>",
784
+ "<SPECIAL_781>",
785
+ "<SPECIAL_782>",
786
+ "<SPECIAL_783>",
787
+ "<SPECIAL_784>",
788
+ "<SPECIAL_785>",
789
+ "<SPECIAL_786>",
790
+ "<SPECIAL_787>",
791
+ "<SPECIAL_788>",
792
+ "<SPECIAL_789>",
793
+ "<SPECIAL_790>",
794
+ "<SPECIAL_791>",
795
+ "<SPECIAL_792>",
796
+ "<SPECIAL_793>",
797
+ "<SPECIAL_794>",
798
+ "<SPECIAL_795>",
799
+ "<SPECIAL_796>",
800
+ "<SPECIAL_797>",
801
+ "<SPECIAL_798>",
802
+ "<SPECIAL_799>",
803
+ "<SPECIAL_800>",
804
+ "<SPECIAL_801>",
805
+ "<SPECIAL_802>",
806
+ "<SPECIAL_803>",
807
+ "<SPECIAL_804>",
808
+ "<SPECIAL_805>",
809
+ "<SPECIAL_806>",
810
+ "<SPECIAL_807>",
811
+ "<SPECIAL_808>",
812
+ "<SPECIAL_809>",
813
+ "<SPECIAL_810>",
814
+ "<SPECIAL_811>",
815
+ "<SPECIAL_812>",
816
+ "<SPECIAL_813>",
817
+ "<SPECIAL_814>",
818
+ "<SPECIAL_815>",
819
+ "<SPECIAL_816>",
820
+ "<SPECIAL_817>",
821
+ "<SPECIAL_818>",
822
+ "<SPECIAL_819>",
823
+ "<SPECIAL_820>",
824
+ "<SPECIAL_821>",
825
+ "<SPECIAL_822>",
826
+ "<SPECIAL_823>",
827
+ "<SPECIAL_824>",
828
+ "<SPECIAL_825>",
829
+ "<SPECIAL_826>",
830
+ "<SPECIAL_827>",
831
+ "<SPECIAL_828>",
832
+ "<SPECIAL_829>",
833
+ "<SPECIAL_830>",
834
+ "<SPECIAL_831>",
835
+ "<SPECIAL_832>",
836
+ "<SPECIAL_833>",
837
+ "<SPECIAL_834>",
838
+ "<SPECIAL_835>",
839
+ "<SPECIAL_836>",
840
+ "<SPECIAL_837>",
841
+ "<SPECIAL_838>",
842
+ "<SPECIAL_839>",
843
+ "<SPECIAL_840>",
844
+ "<SPECIAL_841>",
845
+ "<SPECIAL_842>",
846
+ "<SPECIAL_843>",
847
+ "<SPECIAL_844>",
848
+ "<SPECIAL_845>",
849
+ "<SPECIAL_846>",
850
+ "<SPECIAL_847>",
851
+ "<SPECIAL_848>",
852
+ "<SPECIAL_849>",
853
+ "<SPECIAL_850>",
854
+ "<SPECIAL_851>",
855
+ "<SPECIAL_852>",
856
+ "<SPECIAL_853>",
857
+ "<SPECIAL_854>",
858
+ "<SPECIAL_855>",
859
+ "<SPECIAL_856>",
860
+ "<SPECIAL_857>",
861
+ "<SPECIAL_858>",
862
+ "<SPECIAL_859>",
863
+ "<SPECIAL_860>",
864
+ "<SPECIAL_861>",
865
+ "<SPECIAL_862>",
866
+ "<SPECIAL_863>",
867
+ "<SPECIAL_864>",
868
+ "<SPECIAL_865>",
869
+ "<SPECIAL_866>",
870
+ "<SPECIAL_867>",
871
+ "<SPECIAL_868>",
872
+ "<SPECIAL_869>",
873
+ "<SPECIAL_870>",
874
+ "<SPECIAL_871>",
875
+ "<SPECIAL_872>",
876
+ "<SPECIAL_873>",
877
+ "<SPECIAL_874>",
878
+ "<SPECIAL_875>",
879
+ "<SPECIAL_876>",
880
+ "<SPECIAL_877>",
881
+ "<SPECIAL_878>",
882
+ "<SPECIAL_879>",
883
+ "<SPECIAL_880>",
884
+ "<SPECIAL_881>",
885
+ "<SPECIAL_882>",
886
+ "<SPECIAL_883>",
887
+ "<SPECIAL_884>",
888
+ "<SPECIAL_885>",
889
+ "<SPECIAL_886>",
890
+ "<SPECIAL_887>",
891
+ "<SPECIAL_888>",
892
+ "<SPECIAL_889>",
893
+ "<SPECIAL_890>",
894
+ "<SPECIAL_891>",
895
+ "<SPECIAL_892>",
896
+ "<SPECIAL_893>",
897
+ "<SPECIAL_894>",
898
+ "<SPECIAL_895>",
899
+ "<SPECIAL_896>",
900
+ "<SPECIAL_897>",
901
+ "<SPECIAL_898>",
902
+ "<SPECIAL_899>",
903
+ "<SPECIAL_900>",
904
+ "<SPECIAL_901>",
905
+ "<SPECIAL_902>",
906
+ "<SPECIAL_903>",
907
+ "<SPECIAL_904>",
908
+ "<SPECIAL_905>",
909
+ "<SPECIAL_906>",
910
+ "<SPECIAL_907>",
911
+ "<SPECIAL_908>",
912
+ "<SPECIAL_909>",
913
+ "<SPECIAL_910>",
914
+ "<SPECIAL_911>",
915
+ "<SPECIAL_912>",
916
+ "<SPECIAL_913>",
917
+ "<SPECIAL_914>",
918
+ "<SPECIAL_915>",
919
+ "<SPECIAL_916>",
920
+ "<SPECIAL_917>",
921
+ "<SPECIAL_918>",
922
+ "<SPECIAL_919>",
923
+ "<SPECIAL_920>",
924
+ "<SPECIAL_921>",
925
+ "<SPECIAL_922>",
926
+ "<SPECIAL_923>",
927
+ "<SPECIAL_924>",
928
+ "<SPECIAL_925>",
929
+ "<SPECIAL_926>",
930
+ "<SPECIAL_927>",
931
+ "<SPECIAL_928>",
932
+ "<SPECIAL_929>",
933
+ "<SPECIAL_930>",
934
+ "<SPECIAL_931>",
935
+ "<SPECIAL_932>",
936
+ "<SPECIAL_933>",
937
+ "<SPECIAL_934>",
938
+ "<SPECIAL_935>",
939
+ "<SPECIAL_936>",
940
+ "<SPECIAL_937>",
941
+ "<SPECIAL_938>",
942
+ "<SPECIAL_939>",
943
+ "<SPECIAL_940>",
944
+ "<SPECIAL_941>",
945
+ "<SPECIAL_942>",
946
+ "<SPECIAL_943>",
947
+ "<SPECIAL_944>",
948
+ "<SPECIAL_945>",
949
+ "<SPECIAL_946>",
950
+ "<SPECIAL_947>",
951
+ "<SPECIAL_948>",
952
+ "<SPECIAL_949>",
953
+ "<SPECIAL_950>",
954
+ "<SPECIAL_951>",
955
+ "<SPECIAL_952>",
956
+ "<SPECIAL_953>",
957
+ "<SPECIAL_954>",
958
+ "<SPECIAL_955>",
959
+ "<SPECIAL_956>",
960
+ "<SPECIAL_957>",
961
+ "<SPECIAL_958>",
962
+ "<SPECIAL_959>",
963
+ "<SPECIAL_960>",
964
+ "<SPECIAL_961>",
965
+ "<SPECIAL_962>",
966
+ "<SPECIAL_963>",
967
+ "<SPECIAL_964>",
968
+ "<SPECIAL_965>",
969
+ "<SPECIAL_966>",
970
+ "<SPECIAL_967>",
971
+ "<SPECIAL_968>",
972
+ "<SPECIAL_969>",
973
+ "<SPECIAL_970>",
974
+ "<SPECIAL_971>",
975
+ "<SPECIAL_972>",
976
+ "<SPECIAL_973>",
977
+ "<SPECIAL_974>",
978
+ "<SPECIAL_975>",
979
+ "<SPECIAL_976>",
980
+ "<SPECIAL_977>",
981
+ "<SPECIAL_978>",
982
+ "<SPECIAL_979>",
983
+ "<SPECIAL_980>",
984
+ "<SPECIAL_981>",
985
+ "<SPECIAL_982>",
986
+ "<SPECIAL_983>",
987
+ "<SPECIAL_984>",
988
+ "<SPECIAL_985>",
989
+ "<SPECIAL_986>",
990
+ "<SPECIAL_987>",
991
+ "<SPECIAL_988>",
992
+ "<SPECIAL_989>",
993
+ "<SPECIAL_990>",
994
+ "<SPECIAL_991>",
995
+ "<SPECIAL_992>",
996
+ "<SPECIAL_993>",
997
+ "<SPECIAL_994>",
998
+ "<SPECIAL_995>",
999
+ "<SPECIAL_996>",
1000
+ "<SPECIAL_997>",
1001
+ "<SPECIAL_998>",
1002
+ "<SPECIAL_999>"
1003
+ ],
1004
+ "bos_token": {
1005
+ "content": "<s>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ "eos_token": {
1012
+ "content": "</s>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ "pad_token": "<pad>",
1019
+ "unk_token": {
1020
+ "content": "<unk>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false
1025
+ }
1026
+ }
checkpoints/checkpoint-180/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
checkpoints/checkpoint-180/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-180/trainer_state.json ADDED
@@ -0,0 +1,2029 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.938775510204082,
5
+ "eval_steps": 2,
6
+ "global_step": 180,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 1.2313029766082764,
14
+ "eval_runtime": 18.2352,
15
+ "eval_samples_per_second": 0.877,
16
+ "eval_steps_per_second": 0.877,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0163265306122449,
21
+ "grad_norm": 0.37113556265830994,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 0.4085,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0326530612244898,
28
+ "grad_norm": 0.35803329944610596,
29
+ "learning_rate": 5e-05,
30
+ "loss": 0.3876,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0326530612244898,
35
+ "eval_loss": 1.2231345176696777,
36
+ "eval_runtime": 18.2243,
37
+ "eval_samples_per_second": 0.878,
38
+ "eval_steps_per_second": 0.878,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04897959183673469,
43
+ "grad_norm": 0.3112759590148926,
44
+ "learning_rate": 7.500000000000001e-05,
45
+ "loss": 0.3946,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0653061224489796,
50
+ "grad_norm": 0.2448713332414627,
51
+ "learning_rate": 0.0001,
52
+ "loss": 0.4363,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0653061224489796,
57
+ "eval_loss": 1.1564743518829346,
58
+ "eval_runtime": 18.253,
59
+ "eval_samples_per_second": 0.877,
60
+ "eval_steps_per_second": 0.877,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.08163265306122448,
65
+ "grad_norm": 0.2955642342567444,
66
+ "learning_rate": 0.000125,
67
+ "loss": 0.4394,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.09795918367346938,
72
+ "grad_norm": 0.41399946808815,
73
+ "learning_rate": 0.00015000000000000001,
74
+ "loss": 0.4902,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.09795918367346938,
79
+ "eval_loss": 1.1353044509887695,
80
+ "eval_runtime": 18.2664,
81
+ "eval_samples_per_second": 0.876,
82
+ "eval_steps_per_second": 0.876,
83
+ "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.11428571428571428,
87
+ "grad_norm": 0.2643347978591919,
88
+ "learning_rate": 0.000175,
89
+ "loss": 0.3528,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.1306122448979592,
94
+ "grad_norm": 0.21472330391407013,
95
+ "learning_rate": 0.0002,
96
+ "loss": 0.357,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.1306122448979592,
101
+ "eval_loss": 1.1218546628952026,
102
+ "eval_runtime": 18.2139,
103
+ "eval_samples_per_second": 0.878,
104
+ "eval_steps_per_second": 0.878,
105
+ "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.1469387755102041,
109
+ "grad_norm": 0.23261462152004242,
110
+ "learning_rate": 0.00022500000000000002,
111
+ "loss": 0.3924,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.16326530612244897,
116
+ "grad_norm": 0.18365171551704407,
117
+ "learning_rate": 0.00025,
118
+ "loss": 0.283,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.16326530612244897,
123
+ "eval_loss": 1.1094393730163574,
124
+ "eval_runtime": 18.249,
125
+ "eval_samples_per_second": 0.877,
126
+ "eval_steps_per_second": 0.877,
127
+ "step": 10
128
+ },
129
+ {
130
+ "epoch": 0.17959183673469387,
131
+ "grad_norm": 0.20431634783744812,
132
+ "learning_rate": 0.000275,
133
+ "loss": 0.3178,
134
+ "step": 11
135
+ },
136
+ {
137
+ "epoch": 0.19591836734693877,
138
+ "grad_norm": 0.2033773809671402,
139
+ "learning_rate": 0.00030000000000000003,
140
+ "loss": 0.3366,
141
+ "step": 12
142
+ },
143
+ {
144
+ "epoch": 0.19591836734693877,
145
+ "eval_loss": 1.1021316051483154,
146
+ "eval_runtime": 18.2562,
147
+ "eval_samples_per_second": 0.876,
148
+ "eval_steps_per_second": 0.876,
149
+ "step": 12
150
+ },
151
+ {
152
+ "epoch": 0.21224489795918366,
153
+ "grad_norm": 0.27416911721229553,
154
+ "learning_rate": 0.00032500000000000004,
155
+ "loss": 0.3367,
156
+ "step": 13
157
+ },
158
+ {
159
+ "epoch": 0.22857142857142856,
160
+ "grad_norm": 0.32283130288124084,
161
+ "learning_rate": 0.00035,
162
+ "loss": 0.3364,
163
+ "step": 14
164
+ },
165
+ {
166
+ "epoch": 0.22857142857142856,
167
+ "eval_loss": 1.0523244142532349,
168
+ "eval_runtime": 18.2347,
169
+ "eval_samples_per_second": 0.877,
170
+ "eval_steps_per_second": 0.877,
171
+ "step": 14
172
+ },
173
+ {
174
+ "epoch": 0.24489795918367346,
175
+ "grad_norm": 0.21469368040561676,
176
+ "learning_rate": 0.000375,
177
+ "loss": 0.3496,
178
+ "step": 15
179
+ },
180
+ {
181
+ "epoch": 0.2612244897959184,
182
+ "grad_norm": 0.19361759722232819,
183
+ "learning_rate": 0.0004,
184
+ "loss": 0.2961,
185
+ "step": 16
186
+ },
187
+ {
188
+ "epoch": 0.2612244897959184,
189
+ "eval_loss": 1.0401124954223633,
190
+ "eval_runtime": 18.2288,
191
+ "eval_samples_per_second": 0.878,
192
+ "eval_steps_per_second": 0.878,
193
+ "step": 16
194
+ },
195
+ {
196
+ "epoch": 0.27755102040816326,
197
+ "grad_norm": 0.1797463297843933,
198
+ "learning_rate": 0.0004,
199
+ "loss": 0.3016,
200
+ "step": 17
201
+ },
202
+ {
203
+ "epoch": 0.2938775510204082,
204
+ "grad_norm": 0.28122591972351074,
205
+ "learning_rate": 0.0004,
206
+ "loss": 0.3656,
207
+ "step": 18
208
+ },
209
+ {
210
+ "epoch": 0.2938775510204082,
211
+ "eval_loss": 1.0228931903839111,
212
+ "eval_runtime": 18.2429,
213
+ "eval_samples_per_second": 0.877,
214
+ "eval_steps_per_second": 0.877,
215
+ "step": 18
216
+ },
217
+ {
218
+ "epoch": 0.31020408163265306,
219
+ "grad_norm": 0.227556511759758,
220
+ "learning_rate": 0.0004,
221
+ "loss": 0.3246,
222
+ "step": 19
223
+ },
224
+ {
225
+ "epoch": 0.32653061224489793,
226
+ "grad_norm": 0.211012601852417,
227
+ "learning_rate": 0.0004,
228
+ "loss": 0.3453,
229
+ "step": 20
230
+ },
231
+ {
232
+ "epoch": 0.32653061224489793,
233
+ "eval_loss": 1.017521858215332,
234
+ "eval_runtime": 18.2213,
235
+ "eval_samples_per_second": 0.878,
236
+ "eval_steps_per_second": 0.878,
237
+ "step": 20
238
+ },
239
+ {
240
+ "epoch": 0.34285714285714286,
241
+ "grad_norm": 0.20422972738742828,
242
+ "learning_rate": 0.0004,
243
+ "loss": 0.3258,
244
+ "step": 21
245
+ },
246
+ {
247
+ "epoch": 0.35918367346938773,
248
+ "grad_norm": 0.206649512052536,
249
+ "learning_rate": 0.0004,
250
+ "loss": 0.3248,
251
+ "step": 22
252
+ },
253
+ {
254
+ "epoch": 0.35918367346938773,
255
+ "eval_loss": 0.9992413520812988,
256
+ "eval_runtime": 18.249,
257
+ "eval_samples_per_second": 0.877,
258
+ "eval_steps_per_second": 0.877,
259
+ "step": 22
260
+ },
261
+ {
262
+ "epoch": 0.37551020408163266,
263
+ "grad_norm": 0.19837401807308197,
264
+ "learning_rate": 0.0004,
265
+ "loss": 0.3181,
266
+ "step": 23
267
+ },
268
+ {
269
+ "epoch": 0.39183673469387753,
270
+ "grad_norm": 0.20325997471809387,
271
+ "learning_rate": 0.0004,
272
+ "loss": 0.2826,
273
+ "step": 24
274
+ },
275
+ {
276
+ "epoch": 0.39183673469387753,
277
+ "eval_loss": 0.9943413734436035,
278
+ "eval_runtime": 18.2482,
279
+ "eval_samples_per_second": 0.877,
280
+ "eval_steps_per_second": 0.877,
281
+ "step": 24
282
+ },
283
+ {
284
+ "epoch": 0.40816326530612246,
285
+ "grad_norm": 0.3371317386627197,
286
+ "learning_rate": 0.0004,
287
+ "loss": 0.3197,
288
+ "step": 25
289
+ },
290
+ {
291
+ "epoch": 0.42448979591836733,
292
+ "grad_norm": 0.21709182858467102,
293
+ "learning_rate": 0.0004,
294
+ "loss": 0.3272,
295
+ "step": 26
296
+ },
297
+ {
298
+ "epoch": 0.42448979591836733,
299
+ "eval_loss": 0.9733779430389404,
300
+ "eval_runtime": 18.2232,
301
+ "eval_samples_per_second": 0.878,
302
+ "eval_steps_per_second": 0.878,
303
+ "step": 26
304
+ },
305
+ {
306
+ "epoch": 0.44081632653061226,
307
+ "grad_norm": 0.2420857548713684,
308
+ "learning_rate": 0.0004,
309
+ "loss": 0.3293,
310
+ "step": 27
311
+ },
312
+ {
313
+ "epoch": 0.45714285714285713,
314
+ "grad_norm": 0.30486994981765747,
315
+ "learning_rate": 0.0004,
316
+ "loss": 0.3958,
317
+ "step": 28
318
+ },
319
+ {
320
+ "epoch": 0.45714285714285713,
321
+ "eval_loss": 0.9588731527328491,
322
+ "eval_runtime": 18.2458,
323
+ "eval_samples_per_second": 0.877,
324
+ "eval_steps_per_second": 0.877,
325
+ "step": 28
326
+ },
327
+ {
328
+ "epoch": 0.47346938775510206,
329
+ "grad_norm": 0.24714964628219604,
330
+ "learning_rate": 0.0004,
331
+ "loss": 0.3305,
332
+ "step": 29
333
+ },
334
+ {
335
+ "epoch": 0.4897959183673469,
336
+ "grad_norm": 0.21984225511550903,
337
+ "learning_rate": 0.0004,
338
+ "loss": 0.3395,
339
+ "step": 30
340
+ },
341
+ {
342
+ "epoch": 0.4897959183673469,
343
+ "eval_loss": 0.9427903890609741,
344
+ "eval_runtime": 18.2414,
345
+ "eval_samples_per_second": 0.877,
346
+ "eval_steps_per_second": 0.877,
347
+ "step": 30
348
+ },
349
+ {
350
+ "epoch": 0.5061224489795918,
351
+ "grad_norm": 0.19778016209602356,
352
+ "learning_rate": 0.0004,
353
+ "loss": 0.2918,
354
+ "step": 31
355
+ },
356
+ {
357
+ "epoch": 0.5224489795918368,
358
+ "grad_norm": 0.21754617989063263,
359
+ "learning_rate": 0.0004,
360
+ "loss": 0.2855,
361
+ "step": 32
362
+ },
363
+ {
364
+ "epoch": 0.5224489795918368,
365
+ "eval_loss": 0.9335330128669739,
366
+ "eval_runtime": 18.275,
367
+ "eval_samples_per_second": 0.876,
368
+ "eval_steps_per_second": 0.876,
369
+ "step": 32
370
+ },
371
+ {
372
+ "epoch": 0.5387755102040817,
373
+ "grad_norm": 0.2221430391073227,
374
+ "learning_rate": 0.0004,
375
+ "loss": 0.2946,
376
+ "step": 33
377
+ },
378
+ {
379
+ "epoch": 0.5551020408163265,
380
+ "grad_norm": 0.2112974375486374,
381
+ "learning_rate": 0.0004,
382
+ "loss": 0.3149,
383
+ "step": 34
384
+ },
385
+ {
386
+ "epoch": 0.5551020408163265,
387
+ "eval_loss": 0.9311869144439697,
388
+ "eval_runtime": 18.2431,
389
+ "eval_samples_per_second": 0.877,
390
+ "eval_steps_per_second": 0.877,
391
+ "step": 34
392
+ },
393
+ {
394
+ "epoch": 0.5714285714285714,
395
+ "grad_norm": 0.19651219248771667,
396
+ "learning_rate": 0.0004,
397
+ "loss": 0.2606,
398
+ "step": 35
399
+ },
400
+ {
401
+ "epoch": 0.5877551020408164,
402
+ "grad_norm": 0.22742077708244324,
403
+ "learning_rate": 0.0004,
404
+ "loss": 0.3245,
405
+ "step": 36
406
+ },
407
+ {
408
+ "epoch": 0.5877551020408164,
409
+ "eval_loss": 0.9281033873558044,
410
+ "eval_runtime": 18.2248,
411
+ "eval_samples_per_second": 0.878,
412
+ "eval_steps_per_second": 0.878,
413
+ "step": 36
414
+ },
415
+ {
416
+ "epoch": 0.6040816326530613,
417
+ "grad_norm": 0.2320890575647354,
418
+ "learning_rate": 0.0004,
419
+ "loss": 0.3532,
420
+ "step": 37
421
+ },
422
+ {
423
+ "epoch": 0.6204081632653061,
424
+ "grad_norm": 0.21191200613975525,
425
+ "learning_rate": 0.0004,
426
+ "loss": 0.2973,
427
+ "step": 38
428
+ },
429
+ {
430
+ "epoch": 0.6204081632653061,
431
+ "eval_loss": 0.9274996519088745,
432
+ "eval_runtime": 18.2309,
433
+ "eval_samples_per_second": 0.878,
434
+ "eval_steps_per_second": 0.878,
435
+ "step": 38
436
+ },
437
+ {
438
+ "epoch": 0.636734693877551,
439
+ "grad_norm": 0.24098484218120575,
440
+ "learning_rate": 0.0004,
441
+ "loss": 0.3194,
442
+ "step": 39
443
+ },
444
+ {
445
+ "epoch": 0.6530612244897959,
446
+ "grad_norm": 0.3358725607395172,
447
+ "learning_rate": 0.0004,
448
+ "loss": 0.2833,
449
+ "step": 40
450
+ },
451
+ {
452
+ "epoch": 0.6530612244897959,
453
+ "eval_loss": 0.9254183769226074,
454
+ "eval_runtime": 18.2685,
455
+ "eval_samples_per_second": 0.876,
456
+ "eval_steps_per_second": 0.876,
457
+ "step": 40
458
+ },
459
+ {
460
+ "epoch": 0.6693877551020408,
461
+ "grad_norm": 0.2399401068687439,
462
+ "learning_rate": 0.0004,
463
+ "loss": 0.3381,
464
+ "step": 41
465
+ },
466
+ {
467
+ "epoch": 0.6857142857142857,
468
+ "grad_norm": 0.23229075968265533,
469
+ "learning_rate": 0.0004,
470
+ "loss": 0.3501,
471
+ "step": 42
472
+ },
473
+ {
474
+ "epoch": 0.6857142857142857,
475
+ "eval_loss": 0.9213573932647705,
476
+ "eval_runtime": 18.2788,
477
+ "eval_samples_per_second": 0.875,
478
+ "eval_steps_per_second": 0.875,
479
+ "step": 42
480
+ },
481
+ {
482
+ "epoch": 0.7020408163265306,
483
+ "grad_norm": 0.2341497391462326,
484
+ "learning_rate": 0.0004,
485
+ "loss": 0.3033,
486
+ "step": 43
487
+ },
488
+ {
489
+ "epoch": 0.7183673469387755,
490
+ "grad_norm": 0.22997914254665375,
491
+ "learning_rate": 0.0004,
492
+ "loss": 0.3675,
493
+ "step": 44
494
+ },
495
+ {
496
+ "epoch": 0.7183673469387755,
497
+ "eval_loss": 0.9130539298057556,
498
+ "eval_runtime": 18.2601,
499
+ "eval_samples_per_second": 0.876,
500
+ "eval_steps_per_second": 0.876,
501
+ "step": 44
502
+ },
503
+ {
504
+ "epoch": 0.7346938775510204,
505
+ "grad_norm": 0.23445634543895721,
506
+ "learning_rate": 0.0004,
507
+ "loss": 0.3113,
508
+ "step": 45
509
+ },
510
+ {
511
+ "epoch": 0.7510204081632653,
512
+ "grad_norm": 0.22852188348770142,
513
+ "learning_rate": 0.0004,
514
+ "loss": 0.3593,
515
+ "step": 46
516
+ },
517
+ {
518
+ "epoch": 0.7510204081632653,
519
+ "eval_loss": 0.9100953936576843,
520
+ "eval_runtime": 18.2446,
521
+ "eval_samples_per_second": 0.877,
522
+ "eval_steps_per_second": 0.877,
523
+ "step": 46
524
+ },
525
+ {
526
+ "epoch": 0.7673469387755102,
527
+ "grad_norm": 0.2316325306892395,
528
+ "learning_rate": 0.0004,
529
+ "loss": 0.3121,
530
+ "step": 47
531
+ },
532
+ {
533
+ "epoch": 0.7836734693877551,
534
+ "grad_norm": 0.2397606372833252,
535
+ "learning_rate": 0.0004,
536
+ "loss": 0.2979,
537
+ "step": 48
538
+ },
539
+ {
540
+ "epoch": 0.7836734693877551,
541
+ "eval_loss": 0.9087210297584534,
542
+ "eval_runtime": 18.2833,
543
+ "eval_samples_per_second": 0.875,
544
+ "eval_steps_per_second": 0.875,
545
+ "step": 48
546
+ },
547
+ {
548
+ "epoch": 0.8,
549
+ "grad_norm": 0.22637659311294556,
550
+ "learning_rate": 0.0004,
551
+ "loss": 0.2919,
552
+ "step": 49
553
+ },
554
+ {
555
+ "epoch": 0.8163265306122449,
556
+ "grad_norm": 0.255599707365036,
557
+ "learning_rate": 0.0004,
558
+ "loss": 0.3741,
559
+ "step": 50
560
+ },
561
+ {
562
+ "epoch": 0.8163265306122449,
563
+ "eval_loss": 0.9020435810089111,
564
+ "eval_runtime": 18.2931,
565
+ "eval_samples_per_second": 0.875,
566
+ "eval_steps_per_second": 0.875,
567
+ "step": 50
568
+ },
569
+ {
570
+ "epoch": 0.8163265306122449,
571
+ "eval_loss": 0.9020435810089111,
572
+ "eval_runtime": 18.1276,
573
+ "eval_samples_per_second": 0.883,
574
+ "eval_steps_per_second": 0.883,
575
+ "step": 50
576
+ },
577
+ {
578
+ "epoch": 0.8326530612244898,
579
+ "grad_norm": 0.2062978744506836,
580
+ "learning_rate": 0.0003877467715307749,
581
+ "loss": 0.3303,
582
+ "step": 51
583
+ },
584
+ {
585
+ "epoch": 0.8489795918367347,
586
+ "grad_norm": 0.20149795711040497,
587
+ "learning_rate": 0.0003870443502801494,
588
+ "loss": 0.3212,
589
+ "step": 52
590
+ },
591
+ {
592
+ "epoch": 0.8489795918367347,
593
+ "eval_loss": 0.8994156718254089,
594
+ "eval_runtime": 18.1853,
595
+ "eval_samples_per_second": 0.88,
596
+ "eval_steps_per_second": 0.88,
597
+ "step": 52
598
+ },
599
+ {
600
+ "epoch": 0.8653061224489796,
601
+ "grad_norm": 0.17913399636745453,
602
+ "learning_rate": 0.0003863230255984052,
603
+ "loss": 0.2637,
604
+ "step": 53
605
+ },
606
+ {
607
+ "epoch": 0.8816326530612245,
608
+ "grad_norm": 0.19331133365631104,
609
+ "learning_rate": 0.00038558287038542615,
610
+ "loss": 0.3564,
611
+ "step": 54
612
+ },
613
+ {
614
+ "epoch": 0.8816326530612245,
615
+ "eval_loss": 0.8963940143585205,
616
+ "eval_runtime": 18.223,
617
+ "eval_samples_per_second": 0.878,
618
+ "eval_steps_per_second": 0.878,
619
+ "step": 54
620
+ },
621
+ {
622
+ "epoch": 0.8979591836734694,
623
+ "grad_norm": 0.20378044247627258,
624
+ "learning_rate": 0.00038482395944418313,
625
+ "loss": 0.3253,
626
+ "step": 55
627
+ },
628
+ {
629
+ "epoch": 0.9142857142857143,
630
+ "grad_norm": 0.19742076098918915,
631
+ "learning_rate": 0.0003840463694731741,
632
+ "loss": 0.3715,
633
+ "step": 56
634
+ },
635
+ {
636
+ "epoch": 0.9142857142857143,
637
+ "eval_loss": 0.8902382850646973,
638
+ "eval_runtime": 18.2093,
639
+ "eval_samples_per_second": 0.879,
640
+ "eval_steps_per_second": 0.879,
641
+ "step": 56
642
+ },
643
+ {
644
+ "epoch": 0.9306122448979591,
645
+ "grad_norm": 0.1908055692911148,
646
+ "learning_rate": 0.0003832501790586724,
647
+ "loss": 0.3305,
648
+ "step": 57
649
+ },
650
+ {
651
+ "epoch": 0.9469387755102041,
652
+ "grad_norm": 0.21527761220932007,
653
+ "learning_rate": 0.0003824354686667848,
654
+ "loss": 0.3523,
655
+ "step": 58
656
+ },
657
+ {
658
+ "epoch": 0.9469387755102041,
659
+ "eval_loss": 0.8786917328834534,
660
+ "eval_runtime": 18.2124,
661
+ "eval_samples_per_second": 0.879,
662
+ "eval_steps_per_second": 0.879,
663
+ "step": 58
664
+ },
665
+ {
666
+ "epoch": 0.963265306122449,
667
+ "grad_norm": 0.1817687749862671,
668
+ "learning_rate": 0.00038160232063531917,
669
+ "loss": 0.2616,
670
+ "step": 59
671
+ },
672
+ {
673
+ "epoch": 0.9795918367346939,
674
+ "grad_norm": 0.17659063637256622,
675
+ "learning_rate": 0.0003807508191654631,
676
+ "loss": 0.251,
677
+ "step": 60
678
+ },
679
+ {
680
+ "epoch": 0.9795918367346939,
681
+ "eval_loss": 0.8799586296081543,
682
+ "eval_runtime": 18.2543,
683
+ "eval_samples_per_second": 0.877,
684
+ "eval_steps_per_second": 0.877,
685
+ "step": 60
686
+ },
687
+ {
688
+ "epoch": 0.9959183673469387,
689
+ "grad_norm": 0.22647982835769653,
690
+ "learning_rate": 0.0003798810503132742,
691
+ "loss": 0.2881,
692
+ "step": 61
693
+ },
694
+ {
695
+ "epoch": 1.0122448979591836,
696
+ "grad_norm": 0.45377442240715027,
697
+ "learning_rate": 0.00037899310198098295,
698
+ "loss": 0.5515,
699
+ "step": 62
700
+ },
701
+ {
702
+ "epoch": 1.0122448979591836,
703
+ "eval_loss": 0.8895297050476074,
704
+ "eval_runtime": 18.2212,
705
+ "eval_samples_per_second": 0.878,
706
+ "eval_steps_per_second": 0.878,
707
+ "step": 62
708
+ },
709
+ {
710
+ "epoch": 1.0285714285714285,
711
+ "grad_norm": 0.3527546226978302,
712
+ "learning_rate": 0.000378087063908109,
713
+ "loss": 0.2427,
714
+ "step": 63
715
+ },
716
+ {
717
+ "epoch": 1.0448979591836736,
718
+ "grad_norm": 0.2781178951263428,
719
+ "learning_rate": 0.0003771630276623915,
720
+ "loss": 0.2215,
721
+ "step": 64
722
+ },
723
+ {
724
+ "epoch": 1.0448979591836736,
725
+ "eval_loss": 0.9294220209121704,
726
+ "eval_runtime": 18.226,
727
+ "eval_samples_per_second": 0.878,
728
+ "eval_steps_per_second": 0.878,
729
+ "step": 64
730
+ },
731
+ {
732
+ "epoch": 1.0612244897959184,
733
+ "grad_norm": 0.2543565034866333,
734
+ "learning_rate": 0.00037622108663053536,
735
+ "loss": 0.2761,
736
+ "step": 65
737
+ },
738
+ {
739
+ "epoch": 1.0775510204081633,
740
+ "grad_norm": 0.26259011030197144,
741
+ "learning_rate": 0.0003752613360087727,
742
+ "loss": 0.2425,
743
+ "step": 66
744
+ },
745
+ {
746
+ "epoch": 1.0775510204081633,
747
+ "eval_loss": 0.9212721586227417,
748
+ "eval_runtime": 18.2309,
749
+ "eval_samples_per_second": 0.878,
750
+ "eval_steps_per_second": 0.878,
751
+ "step": 66
752
+ },
753
+ {
754
+ "epoch": 1.0938775510204082,
755
+ "grad_norm": 0.36850446462631226,
756
+ "learning_rate": 0.00037428387279324257,
757
+ "loss": 0.225,
758
+ "step": 67
759
+ },
760
+ {
761
+ "epoch": 1.110204081632653,
762
+ "grad_norm": 0.23748713731765747,
763
+ "learning_rate": 0.0003732887957701874,
764
+ "loss": 0.2363,
765
+ "step": 68
766
+ },
767
+ {
768
+ "epoch": 1.110204081632653,
769
+ "eval_loss": 0.9431418776512146,
770
+ "eval_runtime": 18.2471,
771
+ "eval_samples_per_second": 0.877,
772
+ "eval_steps_per_second": 0.877,
773
+ "step": 68
774
+ },
775
+ {
776
+ "epoch": 1.126530612244898,
777
+ "grad_norm": 0.23217403888702393,
778
+ "learning_rate": 0.00037227620550597,
779
+ "loss": 0.2364,
780
+ "step": 69
781
+ },
782
+ {
783
+ "epoch": 1.1428571428571428,
784
+ "grad_norm": 0.28124868869781494,
785
+ "learning_rate": 0.0003712462043369093,
786
+ "loss": 0.2197,
787
+ "step": 70
788
+ },
789
+ {
790
+ "epoch": 1.1428571428571428,
791
+ "eval_loss": 0.9205393195152283,
792
+ "eval_runtime": 18.2662,
793
+ "eval_samples_per_second": 0.876,
794
+ "eval_steps_per_second": 0.876,
795
+ "step": 70
796
+ },
797
+ {
798
+ "epoch": 1.1591836734693877,
799
+ "grad_norm": 0.2142041176557541,
800
+ "learning_rate": 0.00037019889635893843,
801
+ "loss": 0.1958,
802
+ "step": 71
803
+ },
804
+ {
805
+ "epoch": 1.1755102040816325,
806
+ "grad_norm": 0.34761127829551697,
807
+ "learning_rate": 0.0003691343874170838,
808
+ "loss": 0.2183,
809
+ "step": 72
810
+ },
811
+ {
812
+ "epoch": 1.1755102040816325,
813
+ "eval_loss": 0.9254322648048401,
814
+ "eval_runtime": 18.2303,
815
+ "eval_samples_per_second": 0.878,
816
+ "eval_steps_per_second": 0.878,
817
+ "step": 72
818
+ },
819
+ {
820
+ "epoch": 1.1918367346938776,
821
+ "grad_norm": 0.2560065686702728,
822
+ "learning_rate": 0.00036805278509476844,
823
+ "loss": 0.248,
824
+ "step": 73
825
+ },
826
+ {
827
+ "epoch": 1.2081632653061225,
828
+ "grad_norm": 0.7435296773910522,
829
+ "learning_rate": 0.00036695419870293915,
830
+ "loss": 0.2356,
831
+ "step": 74
832
+ },
833
+ {
834
+ "epoch": 1.2081632653061225,
835
+ "eval_loss": 0.9271378517150879,
836
+ "eval_runtime": 18.2503,
837
+ "eval_samples_per_second": 0.877,
838
+ "eval_steps_per_second": 0.877,
839
+ "step": 74
840
+ },
841
+ {
842
+ "epoch": 1.2244897959183674,
843
+ "grad_norm": 0.8685758113861084,
844
+ "learning_rate": 0.00036583873926901867,
845
+ "loss": 0.2129,
846
+ "step": 75
847
+ },
848
+ {
849
+ "epoch": 1.2408163265306122,
850
+ "grad_norm": 1.2740998268127441,
851
+ "learning_rate": 0.0003647065195256855,
852
+ "loss": 0.2469,
853
+ "step": 76
854
+ },
855
+ {
856
+ "epoch": 1.2408163265306122,
857
+ "eval_loss": 0.9236885905265808,
858
+ "eval_runtime": 18.2226,
859
+ "eval_samples_per_second": 0.878,
860
+ "eval_steps_per_second": 0.878,
861
+ "step": 76
862
+ },
863
+ {
864
+ "epoch": 1.2571428571428571,
865
+ "grad_norm": 0.28524693846702576,
866
+ "learning_rate": 0.0003635576538994801,
867
+ "loss": 0.2278,
868
+ "step": 77
869
+ },
870
+ {
871
+ "epoch": 1.273469387755102,
872
+ "grad_norm": 1.0116885900497437,
873
+ "learning_rate": 0.0003623922584992409,
874
+ "loss": 0.2488,
875
+ "step": 78
876
+ },
877
+ {
878
+ "epoch": 1.273469387755102,
879
+ "eval_loss": 0.923646867275238,
880
+ "eval_runtime": 18.2519,
881
+ "eval_samples_per_second": 0.877,
882
+ "eval_steps_per_second": 0.877,
883
+ "step": 78
884
+ },
885
+ {
886
+ "epoch": 1.2897959183673469,
887
+ "grad_norm": 0.9336573481559753,
888
+ "learning_rate": 0.0003612104511043694,
889
+ "loss": 0.3095,
890
+ "step": 79
891
+ },
892
+ {
893
+ "epoch": 1.306122448979592,
894
+ "grad_norm": 0.43459734320640564,
895
+ "learning_rate": 0.0003600123511529278,
896
+ "loss": 0.2215,
897
+ "step": 80
898
+ },
899
+ {
900
+ "epoch": 1.306122448979592,
901
+ "eval_loss": 0.941472589969635,
902
+ "eval_runtime": 18.251,
903
+ "eval_samples_per_second": 0.877,
904
+ "eval_steps_per_second": 0.877,
905
+ "step": 80
906
+ },
907
+ {
908
+ "epoch": 1.3224489795918366,
909
+ "grad_norm": 0.39941656589508057,
910
+ "learning_rate": 0.0003587980797295671,
911
+ "loss": 0.251,
912
+ "step": 81
913
+ },
914
+ {
915
+ "epoch": 1.3387755102040817,
916
+ "grad_norm": 0.2876632511615753,
917
+ "learning_rate": 0.0003575677595532904,
918
+ "loss": 0.208,
919
+ "step": 82
920
+ },
921
+ {
922
+ "epoch": 1.3387755102040817,
923
+ "eval_loss": 0.932316780090332,
924
+ "eval_runtime": 18.2326,
925
+ "eval_samples_per_second": 0.878,
926
+ "eval_steps_per_second": 0.878,
927
+ "step": 82
928
+ },
929
+ {
930
+ "epoch": 1.3551020408163266,
931
+ "grad_norm": 0.30556565523147583,
932
+ "learning_rate": 0.0003563215149650505,
933
+ "loss": 0.2821,
934
+ "step": 83
935
+ },
936
+ {
937
+ "epoch": 1.3714285714285714,
938
+ "grad_norm": 0.3039940595626831,
939
+ "learning_rate": 0.00035505947191518316,
940
+ "loss": 0.2177,
941
+ "step": 84
942
+ },
943
+ {
944
+ "epoch": 1.3714285714285714,
945
+ "eval_loss": 0.9171479344367981,
946
+ "eval_runtime": 18.2397,
947
+ "eval_samples_per_second": 0.877,
948
+ "eval_steps_per_second": 0.877,
949
+ "step": 84
950
+ },
951
+ {
952
+ "epoch": 1.3877551020408163,
953
+ "grad_norm": 0.32876476645469666,
954
+ "learning_rate": 0.0003537817579506783,
955
+ "loss": 0.2142,
956
+ "step": 85
957
+ },
958
+ {
959
+ "epoch": 1.4040816326530612,
960
+ "grad_norm": 0.26468542218208313,
961
+ "learning_rate": 0.0003524885022022896,
962
+ "loss": 0.2293,
963
+ "step": 86
964
+ },
965
+ {
966
+ "epoch": 1.4040816326530612,
967
+ "eval_loss": 0.9176874756813049,
968
+ "eval_runtime": 18.2553,
969
+ "eval_samples_per_second": 0.876,
970
+ "eval_steps_per_second": 0.876,
971
+ "step": 86
972
+ },
973
+ {
974
+ "epoch": 1.420408163265306,
975
+ "grad_norm": 0.9715031981468201,
976
+ "learning_rate": 0.000351179835371484,
977
+ "loss": 0.235,
978
+ "step": 87
979
+ },
980
+ {
981
+ "epoch": 1.436734693877551,
982
+ "grad_norm": 0.8392952680587769,
983
+ "learning_rate": 0.00034985588971723233,
984
+ "loss": 0.2307,
985
+ "step": 88
986
+ },
987
+ {
988
+ "epoch": 1.436734693877551,
989
+ "eval_loss": 0.9272938370704651,
990
+ "eval_runtime": 18.2194,
991
+ "eval_samples_per_second": 0.878,
992
+ "eval_steps_per_second": 0.878,
993
+ "step": 88
994
+ },
995
+ {
996
+ "epoch": 1.453061224489796,
997
+ "grad_norm": 0.28850337862968445,
998
+ "learning_rate": 0.00034851679904264314,
999
+ "loss": 0.2403,
1000
+ "step": 89
1001
+ },
1002
+ {
1003
+ "epoch": 1.469387755102041,
1004
+ "grad_norm": 0.46389341354370117,
1005
+ "learning_rate": 0.00034716269868143956,
1006
+ "loss": 0.2464,
1007
+ "step": 90
1008
+ },
1009
+ {
1010
+ "epoch": 1.469387755102041,
1011
+ "eval_loss": 0.9267984628677368,
1012
+ "eval_runtime": 18.2514,
1013
+ "eval_samples_per_second": 0.877,
1014
+ "eval_steps_per_second": 0.877,
1015
+ "step": 90
1016
+ },
1017
+ {
1018
+ "epoch": 1.4857142857142858,
1019
+ "grad_norm": 0.29597121477127075,
1020
+ "learning_rate": 0.00034579372548428235,
1021
+ "loss": 0.2307,
1022
+ "step": 91
1023
+ },
1024
+ {
1025
+ "epoch": 1.5020408163265306,
1026
+ "grad_norm": 0.3392711877822876,
1027
+ "learning_rate": 0.00034441001780493886,
1028
+ "loss": 0.231,
1029
+ "step": 92
1030
+ },
1031
+ {
1032
+ "epoch": 1.5020408163265306,
1033
+ "eval_loss": 0.9267009496688843,
1034
+ "eval_runtime": 18.2179,
1035
+ "eval_samples_per_second": 0.878,
1036
+ "eval_steps_per_second": 0.878,
1037
+ "step": 92
1038
+ },
1039
+ {
1040
+ "epoch": 1.5183673469387755,
1041
+ "grad_norm": 0.2309531569480896,
1042
+ "learning_rate": 0.00034301171548630063,
1043
+ "loss": 0.2307,
1044
+ "step": 93
1045
+ },
1046
+ {
1047
+ "epoch": 1.5346938775510204,
1048
+ "grad_norm": 0.28941744565963745,
1049
+ "learning_rate": 0.0003415989598462506,
1050
+ "loss": 0.2384,
1051
+ "step": 94
1052
+ },
1053
+ {
1054
+ "epoch": 1.5346938775510204,
1055
+ "eval_loss": 0.9336121082305908,
1056
+ "eval_runtime": 18.2184,
1057
+ "eval_samples_per_second": 0.878,
1058
+ "eval_steps_per_second": 0.878,
1059
+ "step": 94
1060
+ },
1061
+ {
1062
+ "epoch": 1.5510204081632653,
1063
+ "grad_norm": 0.22579389810562134,
1064
+ "learning_rate": 0.00034017189366338034,
1065
+ "loss": 0.1949,
1066
+ "step": 95
1067
+ },
1068
+ {
1069
+ "epoch": 1.5673469387755103,
1070
+ "grad_norm": 0.2894729971885681,
1071
+ "learning_rate": 0.000338730661162561,
1072
+ "loss": 0.2348,
1073
+ "step": 96
1074
+ },
1075
+ {
1076
+ "epoch": 1.5673469387755103,
1077
+ "eval_loss": 0.9432627558708191,
1078
+ "eval_runtime": 18.2158,
1079
+ "eval_samples_per_second": 0.878,
1080
+ "eval_steps_per_second": 0.878,
1081
+ "step": 96
1082
+ },
1083
+ {
1084
+ "epoch": 1.583673469387755,
1085
+ "grad_norm": 0.24218647181987762,
1086
+ "learning_rate": 0.00033727540800036683,
1087
+ "loss": 0.2113,
1088
+ "step": 97
1089
+ },
1090
+ {
1091
+ "epoch": 1.6,
1092
+ "grad_norm": 0.2695946991443634,
1093
+ "learning_rate": 0.0003358062812503548,
1094
+ "loss": 0.2209,
1095
+ "step": 98
1096
+ },
1097
+ {
1098
+ "epoch": 1.6,
1099
+ "eval_loss": 0.9510765075683594,
1100
+ "eval_runtime": 18.2181,
1101
+ "eval_samples_per_second": 0.878,
1102
+ "eval_steps_per_second": 0.878,
1103
+ "step": 98
1104
+ },
1105
+ {
1106
+ "epoch": 1.6163265306122447,
1107
+ "grad_norm": 0.27196425199508667,
1108
+ "learning_rate": 0.00033432342938820086,
1109
+ "loss": 0.2366,
1110
+ "step": 99
1111
+ },
1112
+ {
1113
+ "epoch": 1.6326530612244898,
1114
+ "grad_norm": 0.2302471101284027,
1115
+ "learning_rate": 0.0003328270022766941,
1116
+ "loss": 0.2099,
1117
+ "step": 100
1118
+ },
1119
+ {
1120
+ "epoch": 1.6326530612244898,
1121
+ "eval_loss": 0.9363111853599548,
1122
+ "eval_runtime": 18.2175,
1123
+ "eval_samples_per_second": 0.878,
1124
+ "eval_steps_per_second": 0.878,
1125
+ "step": 100
1126
+ },
1127
+ {
1128
+ "epoch": 1.6489795918367347,
1129
+ "grad_norm": 0.24810455739498138,
1130
+ "learning_rate": 0.0003313171511505913,
1131
+ "loss": 0.2196,
1132
+ "step": 101
1133
+ },
1134
+ {
1135
+ "epoch": 1.6653061224489796,
1136
+ "grad_norm": 0.25561368465423584,
1137
+ "learning_rate": 0.0003297940286013326,
1138
+ "loss": 0.253,
1139
+ "step": 102
1140
+ },
1141
+ {
1142
+ "epoch": 1.6653061224489796,
1143
+ "eval_loss": 0.942488431930542,
1144
+ "eval_runtime": 18.2068,
1145
+ "eval_samples_per_second": 0.879,
1146
+ "eval_steps_per_second": 0.879,
1147
+ "step": 102
1148
+ },
1149
+ {
1150
+ "epoch": 1.6816326530612244,
1151
+ "grad_norm": 0.22677375376224518,
1152
+ "learning_rate": 0.0003282577885616198,
1153
+ "loss": 0.1789,
1154
+ "step": 103
1155
+ },
1156
+ {
1157
+ "epoch": 1.6979591836734693,
1158
+ "grad_norm": 0.26009589433670044,
1159
+ "learning_rate": 0.0003267085862898594,
1160
+ "loss": 0.2541,
1161
+ "step": 104
1162
+ },
1163
+ {
1164
+ "epoch": 1.6979591836734693,
1165
+ "eval_loss": 0.9335595369338989,
1166
+ "eval_runtime": 18.2507,
1167
+ "eval_samples_per_second": 0.877,
1168
+ "eval_steps_per_second": 0.877,
1169
+ "step": 104
1170
+ },
1171
+ {
1172
+ "epoch": 1.7142857142857144,
1173
+ "grad_norm": 0.20782141387462616,
1174
+ "learning_rate": 0.0003251465783544716,
1175
+ "loss": 0.2308,
1176
+ "step": 105
1177
+ },
1178
+ {
1179
+ "epoch": 1.730612244897959,
1180
+ "grad_norm": 0.22768278419971466,
1181
+ "learning_rate": 0.0003235719226180669,
1182
+ "loss": 0.2354,
1183
+ "step": 106
1184
+ },
1185
+ {
1186
+ "epoch": 1.730612244897959,
1187
+ "eval_loss": 0.9376662373542786,
1188
+ "eval_runtime": 18.2284,
1189
+ "eval_samples_per_second": 0.878,
1190
+ "eval_steps_per_second": 0.878,
1191
+ "step": 106
1192
+ },
1193
+ {
1194
+ "epoch": 1.7469387755102042,
1195
+ "grad_norm": 0.23742002248764038,
1196
+ "learning_rate": 0.00032198477822149185,
1197
+ "loss": 0.2306,
1198
+ "step": 107
1199
+ },
1200
+ {
1201
+ "epoch": 1.763265306122449,
1202
+ "grad_norm": 0.25688832998275757,
1203
+ "learning_rate": 0.0003203853055677457,
1204
+ "loss": 0.2816,
1205
+ "step": 108
1206
+ },
1207
+ {
1208
+ "epoch": 1.763265306122449,
1209
+ "eval_loss": 0.9434496164321899,
1210
+ "eval_runtime": 18.2263,
1211
+ "eval_samples_per_second": 0.878,
1212
+ "eval_steps_per_second": 0.878,
1213
+ "step": 108
1214
+ },
1215
+ {
1216
+ "epoch": 1.779591836734694,
1217
+ "grad_norm": 0.2690117359161377,
1218
+ "learning_rate": 0.00031877366630576946,
1219
+ "loss": 0.2013,
1220
+ "step": 109
1221
+ },
1222
+ {
1223
+ "epoch": 1.7959183673469388,
1224
+ "grad_norm": 0.2317412942647934,
1225
+ "learning_rate": 0.0003171500233141089,
1226
+ "loss": 0.2398,
1227
+ "step": 110
1228
+ },
1229
+ {
1230
+ "epoch": 1.7959183673469388,
1231
+ "eval_loss": 0.9329774975776672,
1232
+ "eval_runtime": 18.2112,
1233
+ "eval_samples_per_second": 0.879,
1234
+ "eval_steps_per_second": 0.879,
1235
+ "step": 110
1236
+ },
1237
+ {
1238
+ "epoch": 1.8122448979591836,
1239
+ "grad_norm": 0.2262117713689804,
1240
+ "learning_rate": 0.0003155145406844535,
1241
+ "loss": 0.207,
1242
+ "step": 111
1243
+ },
1244
+ {
1245
+ "epoch": 1.8285714285714287,
1246
+ "grad_norm": 0.22458741068840027,
1247
+ "learning_rate": 0.00031386738370505293,
1248
+ "loss": 0.2093,
1249
+ "step": 112
1250
+ },
1251
+ {
1252
+ "epoch": 1.8285714285714287,
1253
+ "eval_loss": 0.9222925901412964,
1254
+ "eval_runtime": 18.2333,
1255
+ "eval_samples_per_second": 0.878,
1256
+ "eval_steps_per_second": 0.878,
1257
+ "step": 112
1258
+ },
1259
+ {
1260
+ "epoch": 1.8448979591836734,
1261
+ "grad_norm": 0.24273625016212463,
1262
+ "learning_rate": 0.0003122087188440118,
1263
+ "loss": 0.2434,
1264
+ "step": 113
1265
+ },
1266
+ {
1267
+ "epoch": 1.8612244897959185,
1268
+ "grad_norm": 0.2206314653158188,
1269
+ "learning_rate": 0.0003105387137324663,
1270
+ "loss": 0.2056,
1271
+ "step": 114
1272
+ },
1273
+ {
1274
+ "epoch": 1.8612244897959185,
1275
+ "eval_loss": 0.9319095015525818,
1276
+ "eval_runtime": 18.2327,
1277
+ "eval_samples_per_second": 0.878,
1278
+ "eval_steps_per_second": 0.878,
1279
+ "step": 114
1280
+ },
1281
+ {
1282
+ "epoch": 1.8775510204081631,
1283
+ "grad_norm": 0.2606954574584961,
1284
+ "learning_rate": 0.0003088575371476426,
1285
+ "loss": 0.2198,
1286
+ "step": 115
1287
+ },
1288
+ {
1289
+ "epoch": 1.8938775510204082,
1290
+ "grad_norm": 0.23156337440013885,
1291
+ "learning_rate": 0.0003071653589957993,
1292
+ "loss": 0.1957,
1293
+ "step": 116
1294
+ },
1295
+ {
1296
+ "epoch": 1.8938775510204082,
1297
+ "eval_loss": 0.9314719438552856,
1298
+ "eval_runtime": 18.2411,
1299
+ "eval_samples_per_second": 0.877,
1300
+ "eval_steps_per_second": 0.877,
1301
+ "step": 116
1302
+ },
1303
+ {
1304
+ "epoch": 1.910204081632653,
1305
+ "grad_norm": 0.2253030389547348,
1306
+ "learning_rate": 0.0003054623502950565,
1307
+ "loss": 0.266,
1308
+ "step": 117
1309
+ },
1310
+ {
1311
+ "epoch": 1.926530612244898,
1312
+ "grad_norm": 0.24510890245437622,
1313
+ "learning_rate": 0.0003037486831581115,
1314
+ "loss": 0.2493,
1315
+ "step": 118
1316
+ },
1317
+ {
1318
+ "epoch": 1.926530612244898,
1319
+ "eval_loss": 0.926245927810669,
1320
+ "eval_runtime": 18.2428,
1321
+ "eval_samples_per_second": 0.877,
1322
+ "eval_steps_per_second": 0.877,
1323
+ "step": 118
1324
+ },
1325
+ {
1326
+ "epoch": 1.9428571428571428,
1327
+ "grad_norm": 0.22151368856430054,
1328
+ "learning_rate": 0.00030202453077484494,
1329
+ "loss": 0.2666,
1330
+ "step": 119
1331
+ },
1332
+ {
1333
+ "epoch": 1.9591836734693877,
1334
+ "grad_norm": 0.21714863181114197,
1335
+ "learning_rate": 0.0003002900673948173,
1336
+ "loss": 0.253,
1337
+ "step": 120
1338
+ },
1339
+ {
1340
+ "epoch": 1.9591836734693877,
1341
+ "eval_loss": 0.9263309240341187,
1342
+ "eval_runtime": 18.2196,
1343
+ "eval_samples_per_second": 0.878,
1344
+ "eval_steps_per_second": 0.878,
1345
+ "step": 120
1346
+ },
1347
+ {
1348
+ "epoch": 1.9755102040816328,
1349
+ "grad_norm": 0.2149583399295807,
1350
+ "learning_rate": 0.0002985454683096583,
1351
+ "loss": 0.2208,
1352
+ "step": 121
1353
+ },
1354
+ {
1355
+ "epoch": 1.9918367346938775,
1356
+ "grad_norm": 0.23067210614681244,
1357
+ "learning_rate": 0.000296790909835352,
1358
+ "loss": 0.2225,
1359
+ "step": 122
1360
+ },
1361
+ {
1362
+ "epoch": 1.9918367346938775,
1363
+ "eval_loss": 0.9324613809585571,
1364
+ "eval_runtime": 18.2438,
1365
+ "eval_samples_per_second": 0.877,
1366
+ "eval_steps_per_second": 0.877,
1367
+ "step": 122
1368
+ },
1369
+ {
1370
+ "epoch": 2.0081632653061225,
1371
+ "grad_norm": 0.4510343074798584,
1372
+ "learning_rate": 0.00029502656929441683,
1373
+ "loss": 0.3179,
1374
+ "step": 123
1375
+ },
1376
+ {
1377
+ "epoch": 2.024489795918367,
1378
+ "grad_norm": 0.24402837455272675,
1379
+ "learning_rate": 0.000293252624997985,
1380
+ "loss": 0.1501,
1381
+ "step": 124
1382
+ },
1383
+ {
1384
+ "epoch": 2.024489795918367,
1385
+ "eval_loss": 0.9700677394866943,
1386
+ "eval_runtime": 18.2313,
1387
+ "eval_samples_per_second": 0.878,
1388
+ "eval_steps_per_second": 0.878,
1389
+ "step": 124
1390
+ },
1391
+ {
1392
+ "epoch": 2.0408163265306123,
1393
+ "grad_norm": 0.31533220410346985,
1394
+ "learning_rate": 0.00029146925622778176,
1395
+ "loss": 0.1353,
1396
+ "step": 125
1397
+ },
1398
+ {
1399
+ "epoch": 2.057142857142857,
1400
+ "grad_norm": 0.24323108792304993,
1401
+ "learning_rate": 0.0002896766432180065,
1402
+ "loss": 0.1297,
1403
+ "step": 126
1404
+ },
1405
+ {
1406
+ "epoch": 2.057142857142857,
1407
+ "eval_loss": 0.9890408515930176,
1408
+ "eval_runtime": 18.2073,
1409
+ "eval_samples_per_second": 0.879,
1410
+ "eval_steps_per_second": 0.879,
1411
+ "step": 126
1412
+ },
1413
+ {
1414
+ "epoch": 2.073469387755102,
1415
+ "grad_norm": 0.24305571615695953,
1416
+ "learning_rate": 0.00028787496713711733,
1417
+ "loss": 0.1389,
1418
+ "step": 127
1419
+ },
1420
+ {
1421
+ "epoch": 2.089795918367347,
1422
+ "grad_norm": 0.21282273530960083,
1423
+ "learning_rate": 0.0002860644100695218,
1424
+ "loss": 0.0994,
1425
+ "step": 128
1426
+ },
1427
+ {
1428
+ "epoch": 2.089795918367347,
1429
+ "eval_loss": 1.0023484230041504,
1430
+ "eval_runtime": 18.2257,
1431
+ "eval_samples_per_second": 0.878,
1432
+ "eval_steps_per_second": 0.878,
1433
+ "step": 128
1434
+ },
1435
+ {
1436
+ "epoch": 2.1061224489795918,
1437
+ "grad_norm": 0.20902425050735474,
1438
+ "learning_rate": 0.0002842451549971745,
1439
+ "loss": 0.1195,
1440
+ "step": 129
1441
+ },
1442
+ {
1443
+ "epoch": 2.122448979591837,
1444
+ "grad_norm": 0.21242493391036987,
1445
+ "learning_rate": 0.0002824173857810842,
1446
+ "loss": 0.1256,
1447
+ "step": 130
1448
+ },
1449
+ {
1450
+ "epoch": 2.122448979591837,
1451
+ "eval_loss": 1.0186381340026855,
1452
+ "eval_runtime": 18.1967,
1453
+ "eval_samples_per_second": 0.879,
1454
+ "eval_steps_per_second": 0.879,
1455
+ "step": 130
1456
+ },
1457
+ {
1458
+ "epoch": 2.1387755102040815,
1459
+ "grad_norm": 0.26445460319519043,
1460
+ "learning_rate": 0.00028058128714273257,
1461
+ "loss": 0.1268,
1462
+ "step": 131
1463
+ },
1464
+ {
1465
+ "epoch": 2.1551020408163266,
1466
+ "grad_norm": 0.24118709564208984,
1467
+ "learning_rate": 0.0002787370446454047,
1468
+ "loss": 0.1192,
1469
+ "step": 132
1470
+ },
1471
+ {
1472
+ "epoch": 2.1551020408163266,
1473
+ "eval_loss": 1.0201678276062012,
1474
+ "eval_runtime": 18.2377,
1475
+ "eval_samples_per_second": 0.877,
1476
+ "eval_steps_per_second": 0.877,
1477
+ "step": 132
1478
+ },
1479
+ {
1480
+ "epoch": 2.1714285714285713,
1481
+ "grad_norm": 0.23629823327064514,
1482
+ "learning_rate": 0.0002768848446754362,
1483
+ "loss": 0.1114,
1484
+ "step": 133
1485
+ },
1486
+ {
1487
+ "epoch": 2.1877551020408164,
1488
+ "grad_norm": 0.23851804435253143,
1489
+ "learning_rate": 0.0002750248744233756,
1490
+ "loss": 0.1455,
1491
+ "step": 134
1492
+ },
1493
+ {
1494
+ "epoch": 2.1877551020408164,
1495
+ "eval_loss": 1.027251124382019,
1496
+ "eval_runtime": 18.2111,
1497
+ "eval_samples_per_second": 0.879,
1498
+ "eval_steps_per_second": 0.879,
1499
+ "step": 134
1500
+ },
1501
+ {
1502
+ "epoch": 2.204081632653061,
1503
+ "grad_norm": 0.2159481793642044,
1504
+ "learning_rate": 0.00027315732186506656,
1505
+ "loss": 0.1036,
1506
+ "step": 135
1507
+ },
1508
+ {
1509
+ "epoch": 2.220408163265306,
1510
+ "grad_norm": 0.2521194815635681,
1511
+ "learning_rate": 0.0002712823757426501,
1512
+ "loss": 0.1539,
1513
+ "step": 136
1514
+ },
1515
+ {
1516
+ "epoch": 2.220408163265306,
1517
+ "eval_loss": 1.0327486991882324,
1518
+ "eval_runtime": 18.2282,
1519
+ "eval_samples_per_second": 0.878,
1520
+ "eval_steps_per_second": 0.878,
1521
+ "step": 136
1522
+ },
1523
+ {
1524
+ "epoch": 2.236734693877551,
1525
+ "grad_norm": 0.23456163704395294,
1526
+ "learning_rate": 0.00026940022554548993,
1527
+ "loss": 0.14,
1528
+ "step": 137
1529
+ },
1530
+ {
1531
+ "epoch": 2.253061224489796,
1532
+ "grad_norm": 0.25591009855270386,
1533
+ "learning_rate": 0.0002675110614910212,
1534
+ "loss": 0.1485,
1535
+ "step": 138
1536
+ },
1537
+ {
1538
+ "epoch": 2.253061224489796,
1539
+ "eval_loss": 1.0385500192642212,
1540
+ "eval_runtime": 18.1962,
1541
+ "eval_samples_per_second": 0.879,
1542
+ "eval_steps_per_second": 0.879,
1543
+ "step": 138
1544
+ },
1545
+ {
1546
+ "epoch": 2.269387755102041,
1547
+ "grad_norm": 0.2525387108325958,
1548
+ "learning_rate": 0.00026561507450552704,
1549
+ "loss": 0.1164,
1550
+ "step": 139
1551
+ },
1552
+ {
1553
+ "epoch": 2.2857142857142856,
1554
+ "grad_norm": 0.25320008397102356,
1555
+ "learning_rate": 0.00026371245620484255,
1556
+ "loss": 0.1307,
1557
+ "step": 140
1558
+ },
1559
+ {
1560
+ "epoch": 2.2857142857142856,
1561
+ "eval_loss": 1.028091311454773,
1562
+ "eval_runtime": 18.2167,
1563
+ "eval_samples_per_second": 0.878,
1564
+ "eval_steps_per_second": 0.878,
1565
+ "step": 140
1566
+ },
1567
+ {
1568
+ "epoch": 2.3020408163265307,
1569
+ "grad_norm": 0.27121609449386597,
1570
+ "learning_rate": 0.00026180339887498953,
1571
+ "loss": 0.1475,
1572
+ "step": 141
1573
+ },
1574
+ {
1575
+ "epoch": 2.3183673469387753,
1576
+ "grad_norm": 0.2442832738161087,
1577
+ "learning_rate": 0.00025988809545274293,
1578
+ "loss": 0.112,
1579
+ "step": 142
1580
+ },
1581
+ {
1582
+ "epoch": 2.3183673469387753,
1583
+ "eval_loss": 0.9875463247299194,
1584
+ "eval_runtime": 18.2364,
1585
+ "eval_samples_per_second": 0.877,
1586
+ "eval_steps_per_second": 0.877,
1587
+ "step": 142
1588
+ },
1589
+ {
1590
+ "epoch": 2.3346938775510204,
1591
+ "grad_norm": 0.23179620504379272,
1592
+ "learning_rate": 0.0002579667395061322,
1593
+ "loss": 0.1428,
1594
+ "step": 143
1595
+ },
1596
+ {
1597
+ "epoch": 2.351020408163265,
1598
+ "grad_norm": 0.21805799007415771,
1599
+ "learning_rate": 0.00025603952521487876,
1600
+ "loss": 0.1157,
1601
+ "step": 144
1602
+ },
1603
+ {
1604
+ "epoch": 2.351020408163265,
1605
+ "eval_loss": 0.9967271089553833,
1606
+ "eval_runtime": 18.2289,
1607
+ "eval_samples_per_second": 0.878,
1608
+ "eval_steps_per_second": 0.878,
1609
+ "step": 144
1610
+ },
1611
+ {
1612
+ "epoch": 2.36734693877551,
1613
+ "grad_norm": 0.2379518747329712,
1614
+ "learning_rate": 0.0002541066473507708,
1615
+ "loss": 0.1368,
1616
+ "step": 145
1617
+ },
1618
+ {
1619
+ "epoch": 2.3836734693877553,
1620
+ "grad_norm": 0.27792760729789734,
1621
+ "learning_rate": 0.00025216830125797943,
1622
+ "loss": 0.1369,
1623
+ "step": 146
1624
+ },
1625
+ {
1626
+ "epoch": 2.3836734693877553,
1627
+ "eval_loss": 0.9868496656417847,
1628
+ "eval_runtime": 18.2074,
1629
+ "eval_samples_per_second": 0.879,
1630
+ "eval_steps_per_second": 0.879,
1631
+ "step": 146
1632
+ },
1633
+ {
1634
+ "epoch": 2.4,
1635
+ "grad_norm": 0.2362203449010849,
1636
+ "learning_rate": 0.0002502246828333163,
1637
+ "loss": 0.1275,
1638
+ "step": 147
1639
+ },
1640
+ {
1641
+ "epoch": 2.416326530612245,
1642
+ "grad_norm": 0.27191162109375,
1643
+ "learning_rate": 0.00024827598850643546,
1644
+ "loss": 0.1582,
1645
+ "step": 148
1646
+ },
1647
+ {
1648
+ "epoch": 2.416326530612245,
1649
+ "eval_loss": 0.962943434715271,
1650
+ "eval_runtime": 18.2207,
1651
+ "eval_samples_per_second": 0.878,
1652
+ "eval_steps_per_second": 0.878,
1653
+ "step": 148
1654
+ },
1655
+ {
1656
+ "epoch": 2.4326530612244897,
1657
+ "grad_norm": 0.23347483575344086,
1658
+ "learning_rate": 0.0002463224152199813,
1659
+ "loss": 0.1309,
1660
+ "step": 149
1661
+ },
1662
+ {
1663
+ "epoch": 2.4489795918367347,
1664
+ "grad_norm": 0.2181580364704132,
1665
+ "learning_rate": 0.0002443641604096851,
1666
+ "loss": 0.1261,
1667
+ "step": 150
1668
+ },
1669
+ {
1670
+ "epoch": 2.4489795918367347,
1671
+ "eval_loss": 0.9731823205947876,
1672
+ "eval_runtime": 18.2136,
1673
+ "eval_samples_per_second": 0.878,
1674
+ "eval_steps_per_second": 0.878,
1675
+ "step": 150
1676
+ },
1677
+ {
1678
+ "epoch": 2.4653061224489794,
1679
+ "grad_norm": 0.2505442202091217,
1680
+ "learning_rate": 0.00024240142198441098,
1681
+ "loss": 0.1335,
1682
+ "step": 151
1683
+ },
1684
+ {
1685
+ "epoch": 2.4816326530612245,
1686
+ "grad_norm": 0.23964084684848785,
1687
+ "learning_rate": 0.00024043439830615472,
1688
+ "loss": 0.1249,
1689
+ "step": 152
1690
+ },
1691
+ {
1692
+ "epoch": 2.4816326530612245,
1693
+ "eval_loss": 0.9946855306625366,
1694
+ "eval_runtime": 18.2384,
1695
+ "eval_samples_per_second": 0.877,
1696
+ "eval_steps_per_second": 0.877,
1697
+ "step": 152
1698
+ },
1699
+ {
1700
+ "epoch": 2.497959183673469,
1701
+ "grad_norm": 0.2175896167755127,
1702
+ "learning_rate": 0.00023846328816999658,
1703
+ "loss": 0.101,
1704
+ "step": 153
1705
+ },
1706
+ {
1707
+ "epoch": 2.5142857142857142,
1708
+ "grad_norm": 0.2787061929702759,
1709
+ "learning_rate": 0.00023648829078401007,
1710
+ "loss": 0.1421,
1711
+ "step": 154
1712
+ },
1713
+ {
1714
+ "epoch": 2.5142857142857142,
1715
+ "eval_loss": 0.9933134317398071,
1716
+ "eval_runtime": 18.2349,
1717
+ "eval_samples_per_second": 0.877,
1718
+ "eval_steps_per_second": 0.877,
1719
+ "step": 154
1720
+ },
1721
+ {
1722
+ "epoch": 2.5306122448979593,
1723
+ "grad_norm": 0.22405166923999786,
1724
+ "learning_rate": 0.00023450960574912934,
1725
+ "loss": 0.1237,
1726
+ "step": 155
1727
+ },
1728
+ {
1729
+ "epoch": 2.546938775510204,
1730
+ "grad_norm": 0.25058048963546753,
1731
+ "learning_rate": 0.00023252743303897675,
1732
+ "loss": 0.1635,
1733
+ "step": 156
1734
+ },
1735
+ {
1736
+ "epoch": 2.546938775510204,
1737
+ "eval_loss": 0.9882242679595947,
1738
+ "eval_runtime": 18.2562,
1739
+ "eval_samples_per_second": 0.876,
1740
+ "eval_steps_per_second": 0.876,
1741
+ "step": 156
1742
+ },
1743
+ {
1744
+ "epoch": 2.563265306122449,
1745
+ "grad_norm": 0.3842501938343048,
1746
+ "learning_rate": 0.00023054197297965264,
1747
+ "loss": 0.1417,
1748
+ "step": 157
1749
+ },
1750
+ {
1751
+ "epoch": 2.5795918367346937,
1752
+ "grad_norm": 0.22574357688426971,
1753
+ "learning_rate": 0.00022855342622948976,
1754
+ "loss": 0.1221,
1755
+ "step": 158
1756
+ },
1757
+ {
1758
+ "epoch": 2.5795918367346937,
1759
+ "eval_loss": 1.0112800598144531,
1760
+ "eval_runtime": 18.2537,
1761
+ "eval_samples_per_second": 0.877,
1762
+ "eval_steps_per_second": 0.877,
1763
+ "step": 158
1764
+ },
1765
+ {
1766
+ "epoch": 2.595918367346939,
1767
+ "grad_norm": 0.22760067880153656,
1768
+ "learning_rate": 0.0002265619937587739,
1769
+ "loss": 0.1319,
1770
+ "step": 159
1771
+ },
1772
+ {
1773
+ "epoch": 2.612244897959184,
1774
+ "grad_norm": 0.25777938961982727,
1775
+ "learning_rate": 0.00022456787682943285,
1776
+ "loss": 0.149,
1777
+ "step": 160
1778
+ },
1779
+ {
1780
+ "epoch": 2.612244897959184,
1781
+ "eval_loss": 1.0162885189056396,
1782
+ "eval_runtime": 18.2574,
1783
+ "eval_samples_per_second": 0.876,
1784
+ "eval_steps_per_second": 0.876,
1785
+ "step": 160
1786
+ },
1787
+ {
1788
+ "epoch": 2.6285714285714286,
1789
+ "grad_norm": 0.23430375754833221,
1790
+ "learning_rate": 0.00022257127697469632,
1791
+ "loss": 0.1342,
1792
+ "step": 161
1793
+ },
1794
+ {
1795
+ "epoch": 2.644897959183673,
1796
+ "grad_norm": 0.25381889939308167,
1797
+ "learning_rate": 0.00022057239597872834,
1798
+ "loss": 0.1558,
1799
+ "step": 162
1800
+ },
1801
+ {
1802
+ "epoch": 2.644897959183673,
1803
+ "eval_loss": 1.0097148418426514,
1804
+ "eval_runtime": 18.2572,
1805
+ "eval_samples_per_second": 0.876,
1806
+ "eval_steps_per_second": 0.876,
1807
+ "step": 162
1808
+ },
1809
+ {
1810
+ "epoch": 2.6612244897959183,
1811
+ "grad_norm": 0.22818055748939514,
1812
+ "learning_rate": 0.0002185714358562336,
1813
+ "loss": 0.1382,
1814
+ "step": 163
1815
+ },
1816
+ {
1817
+ "epoch": 2.6775510204081634,
1818
+ "grad_norm": 0.21377477049827576,
1819
+ "learning_rate": 0.00021656859883204167,
1820
+ "loss": 0.1138,
1821
+ "step": 164
1822
+ },
1823
+ {
1824
+ "epoch": 2.6775510204081634,
1825
+ "eval_loss": 1.0100345611572266,
1826
+ "eval_runtime": 18.246,
1827
+ "eval_samples_per_second": 0.877,
1828
+ "eval_steps_per_second": 0.877,
1829
+ "step": 164
1830
+ },
1831
+ {
1832
+ "epoch": 2.693877551020408,
1833
+ "grad_norm": 0.20805473625659943,
1834
+ "learning_rate": 0.00021456408732066918,
1835
+ "loss": 0.1103,
1836
+ "step": 165
1837
+ },
1838
+ {
1839
+ "epoch": 2.710204081632653,
1840
+ "grad_norm": 0.23223794996738434,
1841
+ "learning_rate": 0.0002125581039058627,
1842
+ "loss": 0.1229,
1843
+ "step": 166
1844
+ },
1845
+ {
1846
+ "epoch": 2.710204081632653,
1847
+ "eval_loss": 1.0152215957641602,
1848
+ "eval_runtime": 18.2339,
1849
+ "eval_samples_per_second": 0.877,
1850
+ "eval_steps_per_second": 0.877,
1851
+ "step": 166
1852
+ },
1853
+ {
1854
+ "epoch": 2.726530612244898,
1855
+ "grad_norm": 0.22925834357738495,
1856
+ "learning_rate": 0.0002105508513201253,
1857
+ "loss": 0.112,
1858
+ "step": 167
1859
+ },
1860
+ {
1861
+ "epoch": 2.742857142857143,
1862
+ "grad_norm": 0.23402348160743713,
1863
+ "learning_rate": 0.00020854253242422744,
1864
+ "loss": 0.111,
1865
+ "step": 168
1866
+ },
1867
+ {
1868
+ "epoch": 2.742857142857143,
1869
+ "eval_loss": 1.0134178400039673,
1870
+ "eval_runtime": 18.2312,
1871
+ "eval_samples_per_second": 0.878,
1872
+ "eval_steps_per_second": 0.878,
1873
+ "step": 168
1874
+ },
1875
+ {
1876
+ "epoch": 2.759183673469388,
1877
+ "grad_norm": 0.21745020151138306,
1878
+ "learning_rate": 0.00020653335018670478,
1879
+ "loss": 0.1148,
1880
+ "step": 169
1881
+ },
1882
+ {
1883
+ "epoch": 2.7755102040816326,
1884
+ "grad_norm": 0.23371770977973938,
1885
+ "learning_rate": 0.00020452350766334595,
1886
+ "loss": 0.1378,
1887
+ "step": 170
1888
+ },
1889
+ {
1890
+ "epoch": 2.7755102040816326,
1891
+ "eval_loss": 1.008978247642517,
1892
+ "eval_runtime": 18.2393,
1893
+ "eval_samples_per_second": 0.877,
1894
+ "eval_steps_per_second": 0.877,
1895
+ "step": 170
1896
+ },
1897
+ {
1898
+ "epoch": 2.7918367346938773,
1899
+ "grad_norm": 0.23733730614185333,
1900
+ "learning_rate": 0.00020251320797667056,
1901
+ "loss": 0.1362,
1902
+ "step": 171
1903
+ },
1904
+ {
1905
+ "epoch": 2.8081632653061224,
1906
+ "grad_norm": 0.22156459093093872,
1907
+ "learning_rate": 0.00020050265429540082,
1908
+ "loss": 0.1197,
1909
+ "step": 172
1910
+ },
1911
+ {
1912
+ "epoch": 2.8081632653061224,
1913
+ "eval_loss": 0.996375560760498,
1914
+ "eval_runtime": 18.2572,
1915
+ "eval_samples_per_second": 0.876,
1916
+ "eval_steps_per_second": 0.876,
1917
+ "step": 172
1918
+ },
1919
+ {
1920
+ "epoch": 2.8244897959183675,
1921
+ "grad_norm": 0.21871179342269897,
1922
+ "learning_rate": 0.00019849204981392863,
1923
+ "loss": 0.1262,
1924
+ "step": 173
1925
+ },
1926
+ {
1927
+ "epoch": 2.840816326530612,
1928
+ "grad_norm": 0.2262168973684311,
1929
+ "learning_rate": 0.00019648159773178007,
1930
+ "loss": 0.1329,
1931
+ "step": 174
1932
+ },
1933
+ {
1934
+ "epoch": 2.840816326530612,
1935
+ "eval_loss": 0.9993283748626709,
1936
+ "eval_runtime": 18.2401,
1937
+ "eval_samples_per_second": 0.877,
1938
+ "eval_steps_per_second": 0.877,
1939
+ "step": 174
1940
+ },
1941
+ {
1942
+ "epoch": 2.857142857142857,
1943
+ "grad_norm": 0.24742639064788818,
1944
+ "learning_rate": 0.00019447150123307915,
1945
+ "loss": 0.1243,
1946
+ "step": 175
1947
+ },
1948
+ {
1949
+ "epoch": 2.873469387755102,
1950
+ "grad_norm": 0.21919304132461548,
1951
+ "learning_rate": 0.00019246196346601308,
1952
+ "loss": 0.1218,
1953
+ "step": 176
1954
+ },
1955
+ {
1956
+ "epoch": 2.873469387755102,
1957
+ "eval_loss": 1.0055768489837646,
1958
+ "eval_runtime": 18.2419,
1959
+ "eval_samples_per_second": 0.877,
1960
+ "eval_steps_per_second": 0.877,
1961
+ "step": 176
1962
+ },
1963
+ {
1964
+ "epoch": 2.889795918367347,
1965
+ "grad_norm": 0.21882188320159912,
1966
+ "learning_rate": 0.0001904531875223017,
1967
+ "loss": 0.1347,
1968
+ "step": 177
1969
+ },
1970
+ {
1971
+ "epoch": 2.906122448979592,
1972
+ "grad_norm": 0.24942266941070557,
1973
+ "learning_rate": 0.00018844537641667176,
1974
+ "loss": 0.1526,
1975
+ "step": 178
1976
+ },
1977
+ {
1978
+ "epoch": 2.906122448979592,
1979
+ "eval_loss": 0.9967045783996582,
1980
+ "eval_runtime": 18.2597,
1981
+ "eval_samples_per_second": 0.876,
1982
+ "eval_steps_per_second": 0.876,
1983
+ "step": 178
1984
+ },
1985
+ {
1986
+ "epoch": 2.9224489795918367,
1987
+ "grad_norm": 0.2336956411600113,
1988
+ "learning_rate": 0.0001864387330663399,
1989
+ "loss": 0.1352,
1990
+ "step": 179
1991
+ },
1992
+ {
1993
+ "epoch": 2.938775510204082,
1994
+ "grad_norm": 0.2014392614364624,
1995
+ "learning_rate": 0.0001844334602705047,
1996
+ "loss": 0.1177,
1997
+ "step": 180
1998
+ },
1999
+ {
2000
+ "epoch": 2.938775510204082,
2001
+ "eval_loss": 0.9912804365158081,
2002
+ "eval_runtime": 18.2221,
2003
+ "eval_samples_per_second": 0.878,
2004
+ "eval_steps_per_second": 0.878,
2005
+ "step": 180
2006
+ }
2007
+ ],
2008
+ "logging_steps": 1,
2009
+ "max_steps": 305,
2010
+ "num_input_tokens_seen": 0,
2011
+ "num_train_epochs": 5,
2012
+ "save_steps": 30,
2013
+ "stateful_callbacks": {
2014
+ "TrainerControl": {
2015
+ "args": {
2016
+ "should_epoch_stop": false,
2017
+ "should_evaluate": false,
2018
+ "should_log": false,
2019
+ "should_save": true,
2020
+ "should_training_stop": false
2021
+ },
2022
+ "attributes": {}
2023
+ }
2024
+ },
2025
+ "total_flos": 2.1779063035231334e+18,
2026
+ "train_batch_size": 1,
2027
+ "trial_name": null,
2028
+ "trial_params": null
2029
+ }
checkpoints/checkpoint-180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac79da65aef3f639fd69fe9d54dd5e1ca8bfcbd1838c7de53d38cfdae9e20ab
3
+ size 5624
checkpoints/checkpoint-240/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoints/checkpoint-240/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "gate_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "o_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints/checkpoint-240/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0879a46a85dc48dffe0439ebd81aeed6f468f47e56f31f8c69316528f90693d4
3
+ size 739321784
checkpoints/checkpoint-240/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f8f30ada439466a82d965e26710eacdb526a954cbcefacb72b86c0c7d294bd
3
+ size 377514226
checkpoints/checkpoint-240/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70e560cf0cb34b2fd66f93f7d8c05f0fafe9ec2eaf76fa01a0112e188f2076a
3
+ size 14244
checkpoints/checkpoint-240/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baf8413d64b5acdebf80d7fe1db4a7ba3c002b396bc77e2aed5acedef330752c
3
+ size 1064
checkpoints/checkpoint-240/special_tokens_map.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[INST]",
7
+ "[/INST]",
8
+ "[AVAILABLE_TOOLS]",
9
+ "[/AVAILABLE_TOOLS]",
10
+ "[TOOL_RESULTS]",
11
+ "[/TOOL_RESULTS]",
12
+ "[TOOL_CALLS]",
13
+ "[IMG]",
14
+ "<pad>",
15
+ "[IMG_BREAK]",
16
+ "[IMG_END]",
17
+ "[PREFIX]",
18
+ "[MIDDLE]",
19
+ "[SUFFIX]",
20
+ "[SYSTEM_PROMPT]",
21
+ "[/SYSTEM_PROMPT]",
22
+ "[TOOL_CONTENT]",
23
+ "<SPECIAL_20>",
24
+ "<SPECIAL_21>",
25
+ "<SPECIAL_22>",
26
+ "<SPECIAL_23>",
27
+ "<SPECIAL_24>",
28
+ "<SPECIAL_25>",
29
+ "<SPECIAL_26>",
30
+ "<SPECIAL_27>",
31
+ "<SPECIAL_28>",
32
+ "<SPECIAL_29>",
33
+ "<SPECIAL_30>",
34
+ "<SPECIAL_31>",
35
+ "<SPECIAL_32>",
36
+ "<SPECIAL_33>",
37
+ "<SPECIAL_34>",
38
+ "<SPECIAL_35>",
39
+ "<SPECIAL_36>",
40
+ "<SPECIAL_37>",
41
+ "<SPECIAL_38>",
42
+ "<SPECIAL_39>",
43
+ "<SPECIAL_40>",
44
+ "<SPECIAL_41>",
45
+ "<SPECIAL_42>",
46
+ "<SPECIAL_43>",
47
+ "<SPECIAL_44>",
48
+ "<SPECIAL_45>",
49
+ "<SPECIAL_46>",
50
+ "<SPECIAL_47>",
51
+ "<SPECIAL_48>",
52
+ "<SPECIAL_49>",
53
+ "<SPECIAL_50>",
54
+ "<SPECIAL_51>",
55
+ "<SPECIAL_52>",
56
+ "<SPECIAL_53>",
57
+ "<SPECIAL_54>",
58
+ "<SPECIAL_55>",
59
+ "<SPECIAL_56>",
60
+ "<SPECIAL_57>",
61
+ "<SPECIAL_58>",
62
+ "<SPECIAL_59>",
63
+ "<SPECIAL_60>",
64
+ "<SPECIAL_61>",
65
+ "<SPECIAL_62>",
66
+ "<SPECIAL_63>",
67
+ "<SPECIAL_64>",
68
+ "<SPECIAL_65>",
69
+ "<SPECIAL_66>",
70
+ "<SPECIAL_67>",
71
+ "<SPECIAL_68>",
72
+ "<SPECIAL_69>",
73
+ "<SPECIAL_70>",
74
+ "<SPECIAL_71>",
75
+ "<SPECIAL_72>",
76
+ "<SPECIAL_73>",
77
+ "<SPECIAL_74>",
78
+ "<SPECIAL_75>",
79
+ "<SPECIAL_76>",
80
+ "<SPECIAL_77>",
81
+ "<SPECIAL_78>",
82
+ "<SPECIAL_79>",
83
+ "<SPECIAL_80>",
84
+ "<SPECIAL_81>",
85
+ "<SPECIAL_82>",
86
+ "<SPECIAL_83>",
87
+ "<SPECIAL_84>",
88
+ "<SPECIAL_85>",
89
+ "<SPECIAL_86>",
90
+ "<SPECIAL_87>",
91
+ "<SPECIAL_88>",
92
+ "<SPECIAL_89>",
93
+ "<SPECIAL_90>",
94
+ "<SPECIAL_91>",
95
+ "<SPECIAL_92>",
96
+ "<SPECIAL_93>",
97
+ "<SPECIAL_94>",
98
+ "<SPECIAL_95>",
99
+ "<SPECIAL_96>",
100
+ "<SPECIAL_97>",
101
+ "<SPECIAL_98>",
102
+ "<SPECIAL_99>",
103
+ "<SPECIAL_100>",
104
+ "<SPECIAL_101>",
105
+ "<SPECIAL_102>",
106
+ "<SPECIAL_103>",
107
+ "<SPECIAL_104>",
108
+ "<SPECIAL_105>",
109
+ "<SPECIAL_106>",
110
+ "<SPECIAL_107>",
111
+ "<SPECIAL_108>",
112
+ "<SPECIAL_109>",
113
+ "<SPECIAL_110>",
114
+ "<SPECIAL_111>",
115
+ "<SPECIAL_112>",
116
+ "<SPECIAL_113>",
117
+ "<SPECIAL_114>",
118
+ "<SPECIAL_115>",
119
+ "<SPECIAL_116>",
120
+ "<SPECIAL_117>",
121
+ "<SPECIAL_118>",
122
+ "<SPECIAL_119>",
123
+ "<SPECIAL_120>",
124
+ "<SPECIAL_121>",
125
+ "<SPECIAL_122>",
126
+ "<SPECIAL_123>",
127
+ "<SPECIAL_124>",
128
+ "<SPECIAL_125>",
129
+ "<SPECIAL_126>",
130
+ "<SPECIAL_127>",
131
+ "<SPECIAL_128>",
132
+ "<SPECIAL_129>",
133
+ "<SPECIAL_130>",
134
+ "<SPECIAL_131>",
135
+ "<SPECIAL_132>",
136
+ "<SPECIAL_133>",
137
+ "<SPECIAL_134>",
138
+ "<SPECIAL_135>",
139
+ "<SPECIAL_136>",
140
+ "<SPECIAL_137>",
141
+ "<SPECIAL_138>",
142
+ "<SPECIAL_139>",
143
+ "<SPECIAL_140>",
144
+ "<SPECIAL_141>",
145
+ "<SPECIAL_142>",
146
+ "<SPECIAL_143>",
147
+ "<SPECIAL_144>",
148
+ "<SPECIAL_145>",
149
+ "<SPECIAL_146>",
150
+ "<SPECIAL_147>",
151
+ "<SPECIAL_148>",
152
+ "<SPECIAL_149>",
153
+ "<SPECIAL_150>",
154
+ "<SPECIAL_151>",
155
+ "<SPECIAL_152>",
156
+ "<SPECIAL_153>",
157
+ "<SPECIAL_154>",
158
+ "<SPECIAL_155>",
159
+ "<SPECIAL_156>",
160
+ "<SPECIAL_157>",
161
+ "<SPECIAL_158>",
162
+ "<SPECIAL_159>",
163
+ "<SPECIAL_160>",
164
+ "<SPECIAL_161>",
165
+ "<SPECIAL_162>",
166
+ "<SPECIAL_163>",
167
+ "<SPECIAL_164>",
168
+ "<SPECIAL_165>",
169
+ "<SPECIAL_166>",
170
+ "<SPECIAL_167>",
171
+ "<SPECIAL_168>",
172
+ "<SPECIAL_169>",
173
+ "<SPECIAL_170>",
174
+ "<SPECIAL_171>",
175
+ "<SPECIAL_172>",
176
+ "<SPECIAL_173>",
177
+ "<SPECIAL_174>",
178
+ "<SPECIAL_175>",
179
+ "<SPECIAL_176>",
180
+ "<SPECIAL_177>",
181
+ "<SPECIAL_178>",
182
+ "<SPECIAL_179>",
183
+ "<SPECIAL_180>",
184
+ "<SPECIAL_181>",
185
+ "<SPECIAL_182>",
186
+ "<SPECIAL_183>",
187
+ "<SPECIAL_184>",
188
+ "<SPECIAL_185>",
189
+ "<SPECIAL_186>",
190
+ "<SPECIAL_187>",
191
+ "<SPECIAL_188>",
192
+ "<SPECIAL_189>",
193
+ "<SPECIAL_190>",
194
+ "<SPECIAL_191>",
195
+ "<SPECIAL_192>",
196
+ "<SPECIAL_193>",
197
+ "<SPECIAL_194>",
198
+ "<SPECIAL_195>",
199
+ "<SPECIAL_196>",
200
+ "<SPECIAL_197>",
201
+ "<SPECIAL_198>",
202
+ "<SPECIAL_199>",
203
+ "<SPECIAL_200>",
204
+ "<SPECIAL_201>",
205
+ "<SPECIAL_202>",
206
+ "<SPECIAL_203>",
207
+ "<SPECIAL_204>",
208
+ "<SPECIAL_205>",
209
+ "<SPECIAL_206>",
210
+ "<SPECIAL_207>",
211
+ "<SPECIAL_208>",
212
+ "<SPECIAL_209>",
213
+ "<SPECIAL_210>",
214
+ "<SPECIAL_211>",
215
+ "<SPECIAL_212>",
216
+ "<SPECIAL_213>",
217
+ "<SPECIAL_214>",
218
+ "<SPECIAL_215>",
219
+ "<SPECIAL_216>",
220
+ "<SPECIAL_217>",
221
+ "<SPECIAL_218>",
222
+ "<SPECIAL_219>",
223
+ "<SPECIAL_220>",
224
+ "<SPECIAL_221>",
225
+ "<SPECIAL_222>",
226
+ "<SPECIAL_223>",
227
+ "<SPECIAL_224>",
228
+ "<SPECIAL_225>",
229
+ "<SPECIAL_226>",
230
+ "<SPECIAL_227>",
231
+ "<SPECIAL_228>",
232
+ "<SPECIAL_229>",
233
+ "<SPECIAL_230>",
234
+ "<SPECIAL_231>",
235
+ "<SPECIAL_232>",
236
+ "<SPECIAL_233>",
237
+ "<SPECIAL_234>",
238
+ "<SPECIAL_235>",
239
+ "<SPECIAL_236>",
240
+ "<SPECIAL_237>",
241
+ "<SPECIAL_238>",
242
+ "<SPECIAL_239>",
243
+ "<SPECIAL_240>",
244
+ "<SPECIAL_241>",
245
+ "<SPECIAL_242>",
246
+ "<SPECIAL_243>",
247
+ "<SPECIAL_244>",
248
+ "<SPECIAL_245>",
249
+ "<SPECIAL_246>",
250
+ "<SPECIAL_247>",
251
+ "<SPECIAL_248>",
252
+ "<SPECIAL_249>",
253
+ "<SPECIAL_250>",
254
+ "<SPECIAL_251>",
255
+ "<SPECIAL_252>",
256
+ "<SPECIAL_253>",
257
+ "<SPECIAL_254>",
258
+ "<SPECIAL_255>",
259
+ "<SPECIAL_256>",
260
+ "<SPECIAL_257>",
261
+ "<SPECIAL_258>",
262
+ "<SPECIAL_259>",
263
+ "<SPECIAL_260>",
264
+ "<SPECIAL_261>",
265
+ "<SPECIAL_262>",
266
+ "<SPECIAL_263>",
267
+ "<SPECIAL_264>",
268
+ "<SPECIAL_265>",
269
+ "<SPECIAL_266>",
270
+ "<SPECIAL_267>",
271
+ "<SPECIAL_268>",
272
+ "<SPECIAL_269>",
273
+ "<SPECIAL_270>",
274
+ "<SPECIAL_271>",
275
+ "<SPECIAL_272>",
276
+ "<SPECIAL_273>",
277
+ "<SPECIAL_274>",
278
+ "<SPECIAL_275>",
279
+ "<SPECIAL_276>",
280
+ "<SPECIAL_277>",
281
+ "<SPECIAL_278>",
282
+ "<SPECIAL_279>",
283
+ "<SPECIAL_280>",
284
+ "<SPECIAL_281>",
285
+ "<SPECIAL_282>",
286
+ "<SPECIAL_283>",
287
+ "<SPECIAL_284>",
288
+ "<SPECIAL_285>",
289
+ "<SPECIAL_286>",
290
+ "<SPECIAL_287>",
291
+ "<SPECIAL_288>",
292
+ "<SPECIAL_289>",
293
+ "<SPECIAL_290>",
294
+ "<SPECIAL_291>",
295
+ "<SPECIAL_292>",
296
+ "<SPECIAL_293>",
297
+ "<SPECIAL_294>",
298
+ "<SPECIAL_295>",
299
+ "<SPECIAL_296>",
300
+ "<SPECIAL_297>",
301
+ "<SPECIAL_298>",
302
+ "<SPECIAL_299>",
303
+ "<SPECIAL_300>",
304
+ "<SPECIAL_301>",
305
+ "<SPECIAL_302>",
306
+ "<SPECIAL_303>",
307
+ "<SPECIAL_304>",
308
+ "<SPECIAL_305>",
309
+ "<SPECIAL_306>",
310
+ "<SPECIAL_307>",
311
+ "<SPECIAL_308>",
312
+ "<SPECIAL_309>",
313
+ "<SPECIAL_310>",
314
+ "<SPECIAL_311>",
315
+ "<SPECIAL_312>",
316
+ "<SPECIAL_313>",
317
+ "<SPECIAL_314>",
318
+ "<SPECIAL_315>",
319
+ "<SPECIAL_316>",
320
+ "<SPECIAL_317>",
321
+ "<SPECIAL_318>",
322
+ "<SPECIAL_319>",
323
+ "<SPECIAL_320>",
324
+ "<SPECIAL_321>",
325
+ "<SPECIAL_322>",
326
+ "<SPECIAL_323>",
327
+ "<SPECIAL_324>",
328
+ "<SPECIAL_325>",
329
+ "<SPECIAL_326>",
330
+ "<SPECIAL_327>",
331
+ "<SPECIAL_328>",
332
+ "<SPECIAL_329>",
333
+ "<SPECIAL_330>",
334
+ "<SPECIAL_331>",
335
+ "<SPECIAL_332>",
336
+ "<SPECIAL_333>",
337
+ "<SPECIAL_334>",
338
+ "<SPECIAL_335>",
339
+ "<SPECIAL_336>",
340
+ "<SPECIAL_337>",
341
+ "<SPECIAL_338>",
342
+ "<SPECIAL_339>",
343
+ "<SPECIAL_340>",
344
+ "<SPECIAL_341>",
345
+ "<SPECIAL_342>",
346
+ "<SPECIAL_343>",
347
+ "<SPECIAL_344>",
348
+ "<SPECIAL_345>",
349
+ "<SPECIAL_346>",
350
+ "<SPECIAL_347>",
351
+ "<SPECIAL_348>",
352
+ "<SPECIAL_349>",
353
+ "<SPECIAL_350>",
354
+ "<SPECIAL_351>",
355
+ "<SPECIAL_352>",
356
+ "<SPECIAL_353>",
357
+ "<SPECIAL_354>",
358
+ "<SPECIAL_355>",
359
+ "<SPECIAL_356>",
360
+ "<SPECIAL_357>",
361
+ "<SPECIAL_358>",
362
+ "<SPECIAL_359>",
363
+ "<SPECIAL_360>",
364
+ "<SPECIAL_361>",
365
+ "<SPECIAL_362>",
366
+ "<SPECIAL_363>",
367
+ "<SPECIAL_364>",
368
+ "<SPECIAL_365>",
369
+ "<SPECIAL_366>",
370
+ "<SPECIAL_367>",
371
+ "<SPECIAL_368>",
372
+ "<SPECIAL_369>",
373
+ "<SPECIAL_370>",
374
+ "<SPECIAL_371>",
375
+ "<SPECIAL_372>",
376
+ "<SPECIAL_373>",
377
+ "<SPECIAL_374>",
378
+ "<SPECIAL_375>",
379
+ "<SPECIAL_376>",
380
+ "<SPECIAL_377>",
381
+ "<SPECIAL_378>",
382
+ "<SPECIAL_379>",
383
+ "<SPECIAL_380>",
384
+ "<SPECIAL_381>",
385
+ "<SPECIAL_382>",
386
+ "<SPECIAL_383>",
387
+ "<SPECIAL_384>",
388
+ "<SPECIAL_385>",
389
+ "<SPECIAL_386>",
390
+ "<SPECIAL_387>",
391
+ "<SPECIAL_388>",
392
+ "<SPECIAL_389>",
393
+ "<SPECIAL_390>",
394
+ "<SPECIAL_391>",
395
+ "<SPECIAL_392>",
396
+ "<SPECIAL_393>",
397
+ "<SPECIAL_394>",
398
+ "<SPECIAL_395>",
399
+ "<SPECIAL_396>",
400
+ "<SPECIAL_397>",
401
+ "<SPECIAL_398>",
402
+ "<SPECIAL_399>",
403
+ "<SPECIAL_400>",
404
+ "<SPECIAL_401>",
405
+ "<SPECIAL_402>",
406
+ "<SPECIAL_403>",
407
+ "<SPECIAL_404>",
408
+ "<SPECIAL_405>",
409
+ "<SPECIAL_406>",
410
+ "<SPECIAL_407>",
411
+ "<SPECIAL_408>",
412
+ "<SPECIAL_409>",
413
+ "<SPECIAL_410>",
414
+ "<SPECIAL_411>",
415
+ "<SPECIAL_412>",
416
+ "<SPECIAL_413>",
417
+ "<SPECIAL_414>",
418
+ "<SPECIAL_415>",
419
+ "<SPECIAL_416>",
420
+ "<SPECIAL_417>",
421
+ "<SPECIAL_418>",
422
+ "<SPECIAL_419>",
423
+ "<SPECIAL_420>",
424
+ "<SPECIAL_421>",
425
+ "<SPECIAL_422>",
426
+ "<SPECIAL_423>",
427
+ "<SPECIAL_424>",
428
+ "<SPECIAL_425>",
429
+ "<SPECIAL_426>",
430
+ "<SPECIAL_427>",
431
+ "<SPECIAL_428>",
432
+ "<SPECIAL_429>",
433
+ "<SPECIAL_430>",
434
+ "<SPECIAL_431>",
435
+ "<SPECIAL_432>",
436
+ "<SPECIAL_433>",
437
+ "<SPECIAL_434>",
438
+ "<SPECIAL_435>",
439
+ "<SPECIAL_436>",
440
+ "<SPECIAL_437>",
441
+ "<SPECIAL_438>",
442
+ "<SPECIAL_439>",
443
+ "<SPECIAL_440>",
444
+ "<SPECIAL_441>",
445
+ "<SPECIAL_442>",
446
+ "<SPECIAL_443>",
447
+ "<SPECIAL_444>",
448
+ "<SPECIAL_445>",
449
+ "<SPECIAL_446>",
450
+ "<SPECIAL_447>",
451
+ "<SPECIAL_448>",
452
+ "<SPECIAL_449>",
453
+ "<SPECIAL_450>",
454
+ "<SPECIAL_451>",
455
+ "<SPECIAL_452>",
456
+ "<SPECIAL_453>",
457
+ "<SPECIAL_454>",
458
+ "<SPECIAL_455>",
459
+ "<SPECIAL_456>",
460
+ "<SPECIAL_457>",
461
+ "<SPECIAL_458>",
462
+ "<SPECIAL_459>",
463
+ "<SPECIAL_460>",
464
+ "<SPECIAL_461>",
465
+ "<SPECIAL_462>",
466
+ "<SPECIAL_463>",
467
+ "<SPECIAL_464>",
468
+ "<SPECIAL_465>",
469
+ "<SPECIAL_466>",
470
+ "<SPECIAL_467>",
471
+ "<SPECIAL_468>",
472
+ "<SPECIAL_469>",
473
+ "<SPECIAL_470>",
474
+ "<SPECIAL_471>",
475
+ "<SPECIAL_472>",
476
+ "<SPECIAL_473>",
477
+ "<SPECIAL_474>",
478
+ "<SPECIAL_475>",
479
+ "<SPECIAL_476>",
480
+ "<SPECIAL_477>",
481
+ "<SPECIAL_478>",
482
+ "<SPECIAL_479>",
483
+ "<SPECIAL_480>",
484
+ "<SPECIAL_481>",
485
+ "<SPECIAL_482>",
486
+ "<SPECIAL_483>",
487
+ "<SPECIAL_484>",
488
+ "<SPECIAL_485>",
489
+ "<SPECIAL_486>",
490
+ "<SPECIAL_487>",
491
+ "<SPECIAL_488>",
492
+ "<SPECIAL_489>",
493
+ "<SPECIAL_490>",
494
+ "<SPECIAL_491>",
495
+ "<SPECIAL_492>",
496
+ "<SPECIAL_493>",
497
+ "<SPECIAL_494>",
498
+ "<SPECIAL_495>",
499
+ "<SPECIAL_496>",
500
+ "<SPECIAL_497>",
501
+ "<SPECIAL_498>",
502
+ "<SPECIAL_499>",
503
+ "<SPECIAL_500>",
504
+ "<SPECIAL_501>",
505
+ "<SPECIAL_502>",
506
+ "<SPECIAL_503>",
507
+ "<SPECIAL_504>",
508
+ "<SPECIAL_505>",
509
+ "<SPECIAL_506>",
510
+ "<SPECIAL_507>",
511
+ "<SPECIAL_508>",
512
+ "<SPECIAL_509>",
513
+ "<SPECIAL_510>",
514
+ "<SPECIAL_511>",
515
+ "<SPECIAL_512>",
516
+ "<SPECIAL_513>",
517
+ "<SPECIAL_514>",
518
+ "<SPECIAL_515>",
519
+ "<SPECIAL_516>",
520
+ "<SPECIAL_517>",
521
+ "<SPECIAL_518>",
522
+ "<SPECIAL_519>",
523
+ "<SPECIAL_520>",
524
+ "<SPECIAL_521>",
525
+ "<SPECIAL_522>",
526
+ "<SPECIAL_523>",
527
+ "<SPECIAL_524>",
528
+ "<SPECIAL_525>",
529
+ "<SPECIAL_526>",
530
+ "<SPECIAL_527>",
531
+ "<SPECIAL_528>",
532
+ "<SPECIAL_529>",
533
+ "<SPECIAL_530>",
534
+ "<SPECIAL_531>",
535
+ "<SPECIAL_532>",
536
+ "<SPECIAL_533>",
537
+ "<SPECIAL_534>",
538
+ "<SPECIAL_535>",
539
+ "<SPECIAL_536>",
540
+ "<SPECIAL_537>",
541
+ "<SPECIAL_538>",
542
+ "<SPECIAL_539>",
543
+ "<SPECIAL_540>",
544
+ "<SPECIAL_541>",
545
+ "<SPECIAL_542>",
546
+ "<SPECIAL_543>",
547
+ "<SPECIAL_544>",
548
+ "<SPECIAL_545>",
549
+ "<SPECIAL_546>",
550
+ "<SPECIAL_547>",
551
+ "<SPECIAL_548>",
552
+ "<SPECIAL_549>",
553
+ "<SPECIAL_550>",
554
+ "<SPECIAL_551>",
555
+ "<SPECIAL_552>",
556
+ "<SPECIAL_553>",
557
+ "<SPECIAL_554>",
558
+ "<SPECIAL_555>",
559
+ "<SPECIAL_556>",
560
+ "<SPECIAL_557>",
561
+ "<SPECIAL_558>",
562
+ "<SPECIAL_559>",
563
+ "<SPECIAL_560>",
564
+ "<SPECIAL_561>",
565
+ "<SPECIAL_562>",
566
+ "<SPECIAL_563>",
567
+ "<SPECIAL_564>",
568
+ "<SPECIAL_565>",
569
+ "<SPECIAL_566>",
570
+ "<SPECIAL_567>",
571
+ "<SPECIAL_568>",
572
+ "<SPECIAL_569>",
573
+ "<SPECIAL_570>",
574
+ "<SPECIAL_571>",
575
+ "<SPECIAL_572>",
576
+ "<SPECIAL_573>",
577
+ "<SPECIAL_574>",
578
+ "<SPECIAL_575>",
579
+ "<SPECIAL_576>",
580
+ "<SPECIAL_577>",
581
+ "<SPECIAL_578>",
582
+ "<SPECIAL_579>",
583
+ "<SPECIAL_580>",
584
+ "<SPECIAL_581>",
585
+ "<SPECIAL_582>",
586
+ "<SPECIAL_583>",
587
+ "<SPECIAL_584>",
588
+ "<SPECIAL_585>",
589
+ "<SPECIAL_586>",
590
+ "<SPECIAL_587>",
591
+ "<SPECIAL_588>",
592
+ "<SPECIAL_589>",
593
+ "<SPECIAL_590>",
594
+ "<SPECIAL_591>",
595
+ "<SPECIAL_592>",
596
+ "<SPECIAL_593>",
597
+ "<SPECIAL_594>",
598
+ "<SPECIAL_595>",
599
+ "<SPECIAL_596>",
600
+ "<SPECIAL_597>",
601
+ "<SPECIAL_598>",
602
+ "<SPECIAL_599>",
603
+ "<SPECIAL_600>",
604
+ "<SPECIAL_601>",
605
+ "<SPECIAL_602>",
606
+ "<SPECIAL_603>",
607
+ "<SPECIAL_604>",
608
+ "<SPECIAL_605>",
609
+ "<SPECIAL_606>",
610
+ "<SPECIAL_607>",
611
+ "<SPECIAL_608>",
612
+ "<SPECIAL_609>",
613
+ "<SPECIAL_610>",
614
+ "<SPECIAL_611>",
615
+ "<SPECIAL_612>",
616
+ "<SPECIAL_613>",
617
+ "<SPECIAL_614>",
618
+ "<SPECIAL_615>",
619
+ "<SPECIAL_616>",
620
+ "<SPECIAL_617>",
621
+ "<SPECIAL_618>",
622
+ "<SPECIAL_619>",
623
+ "<SPECIAL_620>",
624
+ "<SPECIAL_621>",
625
+ "<SPECIAL_622>",
626
+ "<SPECIAL_623>",
627
+ "<SPECIAL_624>",
628
+ "<SPECIAL_625>",
629
+ "<SPECIAL_626>",
630
+ "<SPECIAL_627>",
631
+ "<SPECIAL_628>",
632
+ "<SPECIAL_629>",
633
+ "<SPECIAL_630>",
634
+ "<SPECIAL_631>",
635
+ "<SPECIAL_632>",
636
+ "<SPECIAL_633>",
637
+ "<SPECIAL_634>",
638
+ "<SPECIAL_635>",
639
+ "<SPECIAL_636>",
640
+ "<SPECIAL_637>",
641
+ "<SPECIAL_638>",
642
+ "<SPECIAL_639>",
643
+ "<SPECIAL_640>",
644
+ "<SPECIAL_641>",
645
+ "<SPECIAL_642>",
646
+ "<SPECIAL_643>",
647
+ "<SPECIAL_644>",
648
+ "<SPECIAL_645>",
649
+ "<SPECIAL_646>",
650
+ "<SPECIAL_647>",
651
+ "<SPECIAL_648>",
652
+ "<SPECIAL_649>",
653
+ "<SPECIAL_650>",
654
+ "<SPECIAL_651>",
655
+ "<SPECIAL_652>",
656
+ "<SPECIAL_653>",
657
+ "<SPECIAL_654>",
658
+ "<SPECIAL_655>",
659
+ "<SPECIAL_656>",
660
+ "<SPECIAL_657>",
661
+ "<SPECIAL_658>",
662
+ "<SPECIAL_659>",
663
+ "<SPECIAL_660>",
664
+ "<SPECIAL_661>",
665
+ "<SPECIAL_662>",
666
+ "<SPECIAL_663>",
667
+ "<SPECIAL_664>",
668
+ "<SPECIAL_665>",
669
+ "<SPECIAL_666>",
670
+ "<SPECIAL_667>",
671
+ "<SPECIAL_668>",
672
+ "<SPECIAL_669>",
673
+ "<SPECIAL_670>",
674
+ "<SPECIAL_671>",
675
+ "<SPECIAL_672>",
676
+ "<SPECIAL_673>",
677
+ "<SPECIAL_674>",
678
+ "<SPECIAL_675>",
679
+ "<SPECIAL_676>",
680
+ "<SPECIAL_677>",
681
+ "<SPECIAL_678>",
682
+ "<SPECIAL_679>",
683
+ "<SPECIAL_680>",
684
+ "<SPECIAL_681>",
685
+ "<SPECIAL_682>",
686
+ "<SPECIAL_683>",
687
+ "<SPECIAL_684>",
688
+ "<SPECIAL_685>",
689
+ "<SPECIAL_686>",
690
+ "<SPECIAL_687>",
691
+ "<SPECIAL_688>",
692
+ "<SPECIAL_689>",
693
+ "<SPECIAL_690>",
694
+ "<SPECIAL_691>",
695
+ "<SPECIAL_692>",
696
+ "<SPECIAL_693>",
697
+ "<SPECIAL_694>",
698
+ "<SPECIAL_695>",
699
+ "<SPECIAL_696>",
700
+ "<SPECIAL_697>",
701
+ "<SPECIAL_698>",
702
+ "<SPECIAL_699>",
703
+ "<SPECIAL_700>",
704
+ "<SPECIAL_701>",
705
+ "<SPECIAL_702>",
706
+ "<SPECIAL_703>",
707
+ "<SPECIAL_704>",
708
+ "<SPECIAL_705>",
709
+ "<SPECIAL_706>",
710
+ "<SPECIAL_707>",
711
+ "<SPECIAL_708>",
712
+ "<SPECIAL_709>",
713
+ "<SPECIAL_710>",
714
+ "<SPECIAL_711>",
715
+ "<SPECIAL_712>",
716
+ "<SPECIAL_713>",
717
+ "<SPECIAL_714>",
718
+ "<SPECIAL_715>",
719
+ "<SPECIAL_716>",
720
+ "<SPECIAL_717>",
721
+ "<SPECIAL_718>",
722
+ "<SPECIAL_719>",
723
+ "<SPECIAL_720>",
724
+ "<SPECIAL_721>",
725
+ "<SPECIAL_722>",
726
+ "<SPECIAL_723>",
727
+ "<SPECIAL_724>",
728
+ "<SPECIAL_725>",
729
+ "<SPECIAL_726>",
730
+ "<SPECIAL_727>",
731
+ "<SPECIAL_728>",
732
+ "<SPECIAL_729>",
733
+ "<SPECIAL_730>",
734
+ "<SPECIAL_731>",
735
+ "<SPECIAL_732>",
736
+ "<SPECIAL_733>",
737
+ "<SPECIAL_734>",
738
+ "<SPECIAL_735>",
739
+ "<SPECIAL_736>",
740
+ "<SPECIAL_737>",
741
+ "<SPECIAL_738>",
742
+ "<SPECIAL_739>",
743
+ "<SPECIAL_740>",
744
+ "<SPECIAL_741>",
745
+ "<SPECIAL_742>",
746
+ "<SPECIAL_743>",
747
+ "<SPECIAL_744>",
748
+ "<SPECIAL_745>",
749
+ "<SPECIAL_746>",
750
+ "<SPECIAL_747>",
751
+ "<SPECIAL_748>",
752
+ "<SPECIAL_749>",
753
+ "<SPECIAL_750>",
754
+ "<SPECIAL_751>",
755
+ "<SPECIAL_752>",
756
+ "<SPECIAL_753>",
757
+ "<SPECIAL_754>",
758
+ "<SPECIAL_755>",
759
+ "<SPECIAL_756>",
760
+ "<SPECIAL_757>",
761
+ "<SPECIAL_758>",
762
+ "<SPECIAL_759>",
763
+ "<SPECIAL_760>",
764
+ "<SPECIAL_761>",
765
+ "<SPECIAL_762>",
766
+ "<SPECIAL_763>",
767
+ "<SPECIAL_764>",
768
+ "<SPECIAL_765>",
769
+ "<SPECIAL_766>",
770
+ "<SPECIAL_767>",
771
+ "<SPECIAL_768>",
772
+ "<SPECIAL_769>",
773
+ "<SPECIAL_770>",
774
+ "<SPECIAL_771>",
775
+ "<SPECIAL_772>",
776
+ "<SPECIAL_773>",
777
+ "<SPECIAL_774>",
778
+ "<SPECIAL_775>",
779
+ "<SPECIAL_776>",
780
+ "<SPECIAL_777>",
781
+ "<SPECIAL_778>",
782
+ "<SPECIAL_779>",
783
+ "<SPECIAL_780>",
784
+ "<SPECIAL_781>",
785
+ "<SPECIAL_782>",
786
+ "<SPECIAL_783>",
787
+ "<SPECIAL_784>",
788
+ "<SPECIAL_785>",
789
+ "<SPECIAL_786>",
790
+ "<SPECIAL_787>",
791
+ "<SPECIAL_788>",
792
+ "<SPECIAL_789>",
793
+ "<SPECIAL_790>",
794
+ "<SPECIAL_791>",
795
+ "<SPECIAL_792>",
796
+ "<SPECIAL_793>",
797
+ "<SPECIAL_794>",
798
+ "<SPECIAL_795>",
799
+ "<SPECIAL_796>",
800
+ "<SPECIAL_797>",
801
+ "<SPECIAL_798>",
802
+ "<SPECIAL_799>",
803
+ "<SPECIAL_800>",
804
+ "<SPECIAL_801>",
805
+ "<SPECIAL_802>",
806
+ "<SPECIAL_803>",
807
+ "<SPECIAL_804>",
808
+ "<SPECIAL_805>",
809
+ "<SPECIAL_806>",
810
+ "<SPECIAL_807>",
811
+ "<SPECIAL_808>",
812
+ "<SPECIAL_809>",
813
+ "<SPECIAL_810>",
814
+ "<SPECIAL_811>",
815
+ "<SPECIAL_812>",
816
+ "<SPECIAL_813>",
817
+ "<SPECIAL_814>",
818
+ "<SPECIAL_815>",
819
+ "<SPECIAL_816>",
820
+ "<SPECIAL_817>",
821
+ "<SPECIAL_818>",
822
+ "<SPECIAL_819>",
823
+ "<SPECIAL_820>",
824
+ "<SPECIAL_821>",
825
+ "<SPECIAL_822>",
826
+ "<SPECIAL_823>",
827
+ "<SPECIAL_824>",
828
+ "<SPECIAL_825>",
829
+ "<SPECIAL_826>",
830
+ "<SPECIAL_827>",
831
+ "<SPECIAL_828>",
832
+ "<SPECIAL_829>",
833
+ "<SPECIAL_830>",
834
+ "<SPECIAL_831>",
835
+ "<SPECIAL_832>",
836
+ "<SPECIAL_833>",
837
+ "<SPECIAL_834>",
838
+ "<SPECIAL_835>",
839
+ "<SPECIAL_836>",
840
+ "<SPECIAL_837>",
841
+ "<SPECIAL_838>",
842
+ "<SPECIAL_839>",
843
+ "<SPECIAL_840>",
844
+ "<SPECIAL_841>",
845
+ "<SPECIAL_842>",
846
+ "<SPECIAL_843>",
847
+ "<SPECIAL_844>",
848
+ "<SPECIAL_845>",
849
+ "<SPECIAL_846>",
850
+ "<SPECIAL_847>",
851
+ "<SPECIAL_848>",
852
+ "<SPECIAL_849>",
853
+ "<SPECIAL_850>",
854
+ "<SPECIAL_851>",
855
+ "<SPECIAL_852>",
856
+ "<SPECIAL_853>",
857
+ "<SPECIAL_854>",
858
+ "<SPECIAL_855>",
859
+ "<SPECIAL_856>",
860
+ "<SPECIAL_857>",
861
+ "<SPECIAL_858>",
862
+ "<SPECIAL_859>",
863
+ "<SPECIAL_860>",
864
+ "<SPECIAL_861>",
865
+ "<SPECIAL_862>",
866
+ "<SPECIAL_863>",
867
+ "<SPECIAL_864>",
868
+ "<SPECIAL_865>",
869
+ "<SPECIAL_866>",
870
+ "<SPECIAL_867>",
871
+ "<SPECIAL_868>",
872
+ "<SPECIAL_869>",
873
+ "<SPECIAL_870>",
874
+ "<SPECIAL_871>",
875
+ "<SPECIAL_872>",
876
+ "<SPECIAL_873>",
877
+ "<SPECIAL_874>",
878
+ "<SPECIAL_875>",
879
+ "<SPECIAL_876>",
880
+ "<SPECIAL_877>",
881
+ "<SPECIAL_878>",
882
+ "<SPECIAL_879>",
883
+ "<SPECIAL_880>",
884
+ "<SPECIAL_881>",
885
+ "<SPECIAL_882>",
886
+ "<SPECIAL_883>",
887
+ "<SPECIAL_884>",
888
+ "<SPECIAL_885>",
889
+ "<SPECIAL_886>",
890
+ "<SPECIAL_887>",
891
+ "<SPECIAL_888>",
892
+ "<SPECIAL_889>",
893
+ "<SPECIAL_890>",
894
+ "<SPECIAL_891>",
895
+ "<SPECIAL_892>",
896
+ "<SPECIAL_893>",
897
+ "<SPECIAL_894>",
898
+ "<SPECIAL_895>",
899
+ "<SPECIAL_896>",
900
+ "<SPECIAL_897>",
901
+ "<SPECIAL_898>",
902
+ "<SPECIAL_899>",
903
+ "<SPECIAL_900>",
904
+ "<SPECIAL_901>",
905
+ "<SPECIAL_902>",
906
+ "<SPECIAL_903>",
907
+ "<SPECIAL_904>",
908
+ "<SPECIAL_905>",
909
+ "<SPECIAL_906>",
910
+ "<SPECIAL_907>",
911
+ "<SPECIAL_908>",
912
+ "<SPECIAL_909>",
913
+ "<SPECIAL_910>",
914
+ "<SPECIAL_911>",
915
+ "<SPECIAL_912>",
916
+ "<SPECIAL_913>",
917
+ "<SPECIAL_914>",
918
+ "<SPECIAL_915>",
919
+ "<SPECIAL_916>",
920
+ "<SPECIAL_917>",
921
+ "<SPECIAL_918>",
922
+ "<SPECIAL_919>",
923
+ "<SPECIAL_920>",
924
+ "<SPECIAL_921>",
925
+ "<SPECIAL_922>",
926
+ "<SPECIAL_923>",
927
+ "<SPECIAL_924>",
928
+ "<SPECIAL_925>",
929
+ "<SPECIAL_926>",
930
+ "<SPECIAL_927>",
931
+ "<SPECIAL_928>",
932
+ "<SPECIAL_929>",
933
+ "<SPECIAL_930>",
934
+ "<SPECIAL_931>",
935
+ "<SPECIAL_932>",
936
+ "<SPECIAL_933>",
937
+ "<SPECIAL_934>",
938
+ "<SPECIAL_935>",
939
+ "<SPECIAL_936>",
940
+ "<SPECIAL_937>",
941
+ "<SPECIAL_938>",
942
+ "<SPECIAL_939>",
943
+ "<SPECIAL_940>",
944
+ "<SPECIAL_941>",
945
+ "<SPECIAL_942>",
946
+ "<SPECIAL_943>",
947
+ "<SPECIAL_944>",
948
+ "<SPECIAL_945>",
949
+ "<SPECIAL_946>",
950
+ "<SPECIAL_947>",
951
+ "<SPECIAL_948>",
952
+ "<SPECIAL_949>",
953
+ "<SPECIAL_950>",
954
+ "<SPECIAL_951>",
955
+ "<SPECIAL_952>",
956
+ "<SPECIAL_953>",
957
+ "<SPECIAL_954>",
958
+ "<SPECIAL_955>",
959
+ "<SPECIAL_956>",
960
+ "<SPECIAL_957>",
961
+ "<SPECIAL_958>",
962
+ "<SPECIAL_959>",
963
+ "<SPECIAL_960>",
964
+ "<SPECIAL_961>",
965
+ "<SPECIAL_962>",
966
+ "<SPECIAL_963>",
967
+ "<SPECIAL_964>",
968
+ "<SPECIAL_965>",
969
+ "<SPECIAL_966>",
970
+ "<SPECIAL_967>",
971
+ "<SPECIAL_968>",
972
+ "<SPECIAL_969>",
973
+ "<SPECIAL_970>",
974
+ "<SPECIAL_971>",
975
+ "<SPECIAL_972>",
976
+ "<SPECIAL_973>",
977
+ "<SPECIAL_974>",
978
+ "<SPECIAL_975>",
979
+ "<SPECIAL_976>",
980
+ "<SPECIAL_977>",
981
+ "<SPECIAL_978>",
982
+ "<SPECIAL_979>",
983
+ "<SPECIAL_980>",
984
+ "<SPECIAL_981>",
985
+ "<SPECIAL_982>",
986
+ "<SPECIAL_983>",
987
+ "<SPECIAL_984>",
988
+ "<SPECIAL_985>",
989
+ "<SPECIAL_986>",
990
+ "<SPECIAL_987>",
991
+ "<SPECIAL_988>",
992
+ "<SPECIAL_989>",
993
+ "<SPECIAL_990>",
994
+ "<SPECIAL_991>",
995
+ "<SPECIAL_992>",
996
+ "<SPECIAL_993>",
997
+ "<SPECIAL_994>",
998
+ "<SPECIAL_995>",
999
+ "<SPECIAL_996>",
1000
+ "<SPECIAL_997>",
1001
+ "<SPECIAL_998>",
1002
+ "<SPECIAL_999>"
1003
+ ],
1004
+ "bos_token": {
1005
+ "content": "<s>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ "eos_token": {
1012
+ "content": "</s>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ "pad_token": "<pad>",
1019
+ "unk_token": {
1020
+ "content": "<unk>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false
1025
+ }
1026
+ }
checkpoints/checkpoint-240/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
checkpoints/checkpoint-240/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-240/trainer_state.json ADDED
@@ -0,0 +1,2697 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.926530612244898,
5
+ "eval_steps": 2,
6
+ "global_step": 240,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 1.2313029766082764,
14
+ "eval_runtime": 18.2352,
15
+ "eval_samples_per_second": 0.877,
16
+ "eval_steps_per_second": 0.877,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0163265306122449,
21
+ "grad_norm": 0.37113556265830994,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 0.4085,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0326530612244898,
28
+ "grad_norm": 0.35803329944610596,
29
+ "learning_rate": 5e-05,
30
+ "loss": 0.3876,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0326530612244898,
35
+ "eval_loss": 1.2231345176696777,
36
+ "eval_runtime": 18.2243,
37
+ "eval_samples_per_second": 0.878,
38
+ "eval_steps_per_second": 0.878,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04897959183673469,
43
+ "grad_norm": 0.3112759590148926,
44
+ "learning_rate": 7.500000000000001e-05,
45
+ "loss": 0.3946,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0653061224489796,
50
+ "grad_norm": 0.2448713332414627,
51
+ "learning_rate": 0.0001,
52
+ "loss": 0.4363,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0653061224489796,
57
+ "eval_loss": 1.1564743518829346,
58
+ "eval_runtime": 18.253,
59
+ "eval_samples_per_second": 0.877,
60
+ "eval_steps_per_second": 0.877,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.08163265306122448,
65
+ "grad_norm": 0.2955642342567444,
66
+ "learning_rate": 0.000125,
67
+ "loss": 0.4394,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.09795918367346938,
72
+ "grad_norm": 0.41399946808815,
73
+ "learning_rate": 0.00015000000000000001,
74
+ "loss": 0.4902,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.09795918367346938,
79
+ "eval_loss": 1.1353044509887695,
80
+ "eval_runtime": 18.2664,
81
+ "eval_samples_per_second": 0.876,
82
+ "eval_steps_per_second": 0.876,
83
+ "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.11428571428571428,
87
+ "grad_norm": 0.2643347978591919,
88
+ "learning_rate": 0.000175,
89
+ "loss": 0.3528,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.1306122448979592,
94
+ "grad_norm": 0.21472330391407013,
95
+ "learning_rate": 0.0002,
96
+ "loss": 0.357,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.1306122448979592,
101
+ "eval_loss": 1.1218546628952026,
102
+ "eval_runtime": 18.2139,
103
+ "eval_samples_per_second": 0.878,
104
+ "eval_steps_per_second": 0.878,
105
+ "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.1469387755102041,
109
+ "grad_norm": 0.23261462152004242,
110
+ "learning_rate": 0.00022500000000000002,
111
+ "loss": 0.3924,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.16326530612244897,
116
+ "grad_norm": 0.18365171551704407,
117
+ "learning_rate": 0.00025,
118
+ "loss": 0.283,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.16326530612244897,
123
+ "eval_loss": 1.1094393730163574,
124
+ "eval_runtime": 18.249,
125
+ "eval_samples_per_second": 0.877,
126
+ "eval_steps_per_second": 0.877,
127
+ "step": 10
128
+ },
129
+ {
130
+ "epoch": 0.17959183673469387,
131
+ "grad_norm": 0.20431634783744812,
132
+ "learning_rate": 0.000275,
133
+ "loss": 0.3178,
134
+ "step": 11
135
+ },
136
+ {
137
+ "epoch": 0.19591836734693877,
138
+ "grad_norm": 0.2033773809671402,
139
+ "learning_rate": 0.00030000000000000003,
140
+ "loss": 0.3366,
141
+ "step": 12
142
+ },
143
+ {
144
+ "epoch": 0.19591836734693877,
145
+ "eval_loss": 1.1021316051483154,
146
+ "eval_runtime": 18.2562,
147
+ "eval_samples_per_second": 0.876,
148
+ "eval_steps_per_second": 0.876,
149
+ "step": 12
150
+ },
151
+ {
152
+ "epoch": 0.21224489795918366,
153
+ "grad_norm": 0.27416911721229553,
154
+ "learning_rate": 0.00032500000000000004,
155
+ "loss": 0.3367,
156
+ "step": 13
157
+ },
158
+ {
159
+ "epoch": 0.22857142857142856,
160
+ "grad_norm": 0.32283130288124084,
161
+ "learning_rate": 0.00035,
162
+ "loss": 0.3364,
163
+ "step": 14
164
+ },
165
+ {
166
+ "epoch": 0.22857142857142856,
167
+ "eval_loss": 1.0523244142532349,
168
+ "eval_runtime": 18.2347,
169
+ "eval_samples_per_second": 0.877,
170
+ "eval_steps_per_second": 0.877,
171
+ "step": 14
172
+ },
173
+ {
174
+ "epoch": 0.24489795918367346,
175
+ "grad_norm": 0.21469368040561676,
176
+ "learning_rate": 0.000375,
177
+ "loss": 0.3496,
178
+ "step": 15
179
+ },
180
+ {
181
+ "epoch": 0.2612244897959184,
182
+ "grad_norm": 0.19361759722232819,
183
+ "learning_rate": 0.0004,
184
+ "loss": 0.2961,
185
+ "step": 16
186
+ },
187
+ {
188
+ "epoch": 0.2612244897959184,
189
+ "eval_loss": 1.0401124954223633,
190
+ "eval_runtime": 18.2288,
191
+ "eval_samples_per_second": 0.878,
192
+ "eval_steps_per_second": 0.878,
193
+ "step": 16
194
+ },
195
+ {
196
+ "epoch": 0.27755102040816326,
197
+ "grad_norm": 0.1797463297843933,
198
+ "learning_rate": 0.0004,
199
+ "loss": 0.3016,
200
+ "step": 17
201
+ },
202
+ {
203
+ "epoch": 0.2938775510204082,
204
+ "grad_norm": 0.28122591972351074,
205
+ "learning_rate": 0.0004,
206
+ "loss": 0.3656,
207
+ "step": 18
208
+ },
209
+ {
210
+ "epoch": 0.2938775510204082,
211
+ "eval_loss": 1.0228931903839111,
212
+ "eval_runtime": 18.2429,
213
+ "eval_samples_per_second": 0.877,
214
+ "eval_steps_per_second": 0.877,
215
+ "step": 18
216
+ },
217
+ {
218
+ "epoch": 0.31020408163265306,
219
+ "grad_norm": 0.227556511759758,
220
+ "learning_rate": 0.0004,
221
+ "loss": 0.3246,
222
+ "step": 19
223
+ },
224
+ {
225
+ "epoch": 0.32653061224489793,
226
+ "grad_norm": 0.211012601852417,
227
+ "learning_rate": 0.0004,
228
+ "loss": 0.3453,
229
+ "step": 20
230
+ },
231
+ {
232
+ "epoch": 0.32653061224489793,
233
+ "eval_loss": 1.017521858215332,
234
+ "eval_runtime": 18.2213,
235
+ "eval_samples_per_second": 0.878,
236
+ "eval_steps_per_second": 0.878,
237
+ "step": 20
238
+ },
239
+ {
240
+ "epoch": 0.34285714285714286,
241
+ "grad_norm": 0.20422972738742828,
242
+ "learning_rate": 0.0004,
243
+ "loss": 0.3258,
244
+ "step": 21
245
+ },
246
+ {
247
+ "epoch": 0.35918367346938773,
248
+ "grad_norm": 0.206649512052536,
249
+ "learning_rate": 0.0004,
250
+ "loss": 0.3248,
251
+ "step": 22
252
+ },
253
+ {
254
+ "epoch": 0.35918367346938773,
255
+ "eval_loss": 0.9992413520812988,
256
+ "eval_runtime": 18.249,
257
+ "eval_samples_per_second": 0.877,
258
+ "eval_steps_per_second": 0.877,
259
+ "step": 22
260
+ },
261
+ {
262
+ "epoch": 0.37551020408163266,
263
+ "grad_norm": 0.19837401807308197,
264
+ "learning_rate": 0.0004,
265
+ "loss": 0.3181,
266
+ "step": 23
267
+ },
268
+ {
269
+ "epoch": 0.39183673469387753,
270
+ "grad_norm": 0.20325997471809387,
271
+ "learning_rate": 0.0004,
272
+ "loss": 0.2826,
273
+ "step": 24
274
+ },
275
+ {
276
+ "epoch": 0.39183673469387753,
277
+ "eval_loss": 0.9943413734436035,
278
+ "eval_runtime": 18.2482,
279
+ "eval_samples_per_second": 0.877,
280
+ "eval_steps_per_second": 0.877,
281
+ "step": 24
282
+ },
283
+ {
284
+ "epoch": 0.40816326530612246,
285
+ "grad_norm": 0.3371317386627197,
286
+ "learning_rate": 0.0004,
287
+ "loss": 0.3197,
288
+ "step": 25
289
+ },
290
+ {
291
+ "epoch": 0.42448979591836733,
292
+ "grad_norm": 0.21709182858467102,
293
+ "learning_rate": 0.0004,
294
+ "loss": 0.3272,
295
+ "step": 26
296
+ },
297
+ {
298
+ "epoch": 0.42448979591836733,
299
+ "eval_loss": 0.9733779430389404,
300
+ "eval_runtime": 18.2232,
301
+ "eval_samples_per_second": 0.878,
302
+ "eval_steps_per_second": 0.878,
303
+ "step": 26
304
+ },
305
+ {
306
+ "epoch": 0.44081632653061226,
307
+ "grad_norm": 0.2420857548713684,
308
+ "learning_rate": 0.0004,
309
+ "loss": 0.3293,
310
+ "step": 27
311
+ },
312
+ {
313
+ "epoch": 0.45714285714285713,
314
+ "grad_norm": 0.30486994981765747,
315
+ "learning_rate": 0.0004,
316
+ "loss": 0.3958,
317
+ "step": 28
318
+ },
319
+ {
320
+ "epoch": 0.45714285714285713,
321
+ "eval_loss": 0.9588731527328491,
322
+ "eval_runtime": 18.2458,
323
+ "eval_samples_per_second": 0.877,
324
+ "eval_steps_per_second": 0.877,
325
+ "step": 28
326
+ },
327
+ {
328
+ "epoch": 0.47346938775510206,
329
+ "grad_norm": 0.24714964628219604,
330
+ "learning_rate": 0.0004,
331
+ "loss": 0.3305,
332
+ "step": 29
333
+ },
334
+ {
335
+ "epoch": 0.4897959183673469,
336
+ "grad_norm": 0.21984225511550903,
337
+ "learning_rate": 0.0004,
338
+ "loss": 0.3395,
339
+ "step": 30
340
+ },
341
+ {
342
+ "epoch": 0.4897959183673469,
343
+ "eval_loss": 0.9427903890609741,
344
+ "eval_runtime": 18.2414,
345
+ "eval_samples_per_second": 0.877,
346
+ "eval_steps_per_second": 0.877,
347
+ "step": 30
348
+ },
349
+ {
350
+ "epoch": 0.5061224489795918,
351
+ "grad_norm": 0.19778016209602356,
352
+ "learning_rate": 0.0004,
353
+ "loss": 0.2918,
354
+ "step": 31
355
+ },
356
+ {
357
+ "epoch": 0.5224489795918368,
358
+ "grad_norm": 0.21754617989063263,
359
+ "learning_rate": 0.0004,
360
+ "loss": 0.2855,
361
+ "step": 32
362
+ },
363
+ {
364
+ "epoch": 0.5224489795918368,
365
+ "eval_loss": 0.9335330128669739,
366
+ "eval_runtime": 18.275,
367
+ "eval_samples_per_second": 0.876,
368
+ "eval_steps_per_second": 0.876,
369
+ "step": 32
370
+ },
371
+ {
372
+ "epoch": 0.5387755102040817,
373
+ "grad_norm": 0.2221430391073227,
374
+ "learning_rate": 0.0004,
375
+ "loss": 0.2946,
376
+ "step": 33
377
+ },
378
+ {
379
+ "epoch": 0.5551020408163265,
380
+ "grad_norm": 0.2112974375486374,
381
+ "learning_rate": 0.0004,
382
+ "loss": 0.3149,
383
+ "step": 34
384
+ },
385
+ {
386
+ "epoch": 0.5551020408163265,
387
+ "eval_loss": 0.9311869144439697,
388
+ "eval_runtime": 18.2431,
389
+ "eval_samples_per_second": 0.877,
390
+ "eval_steps_per_second": 0.877,
391
+ "step": 34
392
+ },
393
+ {
394
+ "epoch": 0.5714285714285714,
395
+ "grad_norm": 0.19651219248771667,
396
+ "learning_rate": 0.0004,
397
+ "loss": 0.2606,
398
+ "step": 35
399
+ },
400
+ {
401
+ "epoch": 0.5877551020408164,
402
+ "grad_norm": 0.22742077708244324,
403
+ "learning_rate": 0.0004,
404
+ "loss": 0.3245,
405
+ "step": 36
406
+ },
407
+ {
408
+ "epoch": 0.5877551020408164,
409
+ "eval_loss": 0.9281033873558044,
410
+ "eval_runtime": 18.2248,
411
+ "eval_samples_per_second": 0.878,
412
+ "eval_steps_per_second": 0.878,
413
+ "step": 36
414
+ },
415
+ {
416
+ "epoch": 0.6040816326530613,
417
+ "grad_norm": 0.2320890575647354,
418
+ "learning_rate": 0.0004,
419
+ "loss": 0.3532,
420
+ "step": 37
421
+ },
422
+ {
423
+ "epoch": 0.6204081632653061,
424
+ "grad_norm": 0.21191200613975525,
425
+ "learning_rate": 0.0004,
426
+ "loss": 0.2973,
427
+ "step": 38
428
+ },
429
+ {
430
+ "epoch": 0.6204081632653061,
431
+ "eval_loss": 0.9274996519088745,
432
+ "eval_runtime": 18.2309,
433
+ "eval_samples_per_second": 0.878,
434
+ "eval_steps_per_second": 0.878,
435
+ "step": 38
436
+ },
437
+ {
438
+ "epoch": 0.636734693877551,
439
+ "grad_norm": 0.24098484218120575,
440
+ "learning_rate": 0.0004,
441
+ "loss": 0.3194,
442
+ "step": 39
443
+ },
444
+ {
445
+ "epoch": 0.6530612244897959,
446
+ "grad_norm": 0.3358725607395172,
447
+ "learning_rate": 0.0004,
448
+ "loss": 0.2833,
449
+ "step": 40
450
+ },
451
+ {
452
+ "epoch": 0.6530612244897959,
453
+ "eval_loss": 0.9254183769226074,
454
+ "eval_runtime": 18.2685,
455
+ "eval_samples_per_second": 0.876,
456
+ "eval_steps_per_second": 0.876,
457
+ "step": 40
458
+ },
459
+ {
460
+ "epoch": 0.6693877551020408,
461
+ "grad_norm": 0.2399401068687439,
462
+ "learning_rate": 0.0004,
463
+ "loss": 0.3381,
464
+ "step": 41
465
+ },
466
+ {
467
+ "epoch": 0.6857142857142857,
468
+ "grad_norm": 0.23229075968265533,
469
+ "learning_rate": 0.0004,
470
+ "loss": 0.3501,
471
+ "step": 42
472
+ },
473
+ {
474
+ "epoch": 0.6857142857142857,
475
+ "eval_loss": 0.9213573932647705,
476
+ "eval_runtime": 18.2788,
477
+ "eval_samples_per_second": 0.875,
478
+ "eval_steps_per_second": 0.875,
479
+ "step": 42
480
+ },
481
+ {
482
+ "epoch": 0.7020408163265306,
483
+ "grad_norm": 0.2341497391462326,
484
+ "learning_rate": 0.0004,
485
+ "loss": 0.3033,
486
+ "step": 43
487
+ },
488
+ {
489
+ "epoch": 0.7183673469387755,
490
+ "grad_norm": 0.22997914254665375,
491
+ "learning_rate": 0.0004,
492
+ "loss": 0.3675,
493
+ "step": 44
494
+ },
495
+ {
496
+ "epoch": 0.7183673469387755,
497
+ "eval_loss": 0.9130539298057556,
498
+ "eval_runtime": 18.2601,
499
+ "eval_samples_per_second": 0.876,
500
+ "eval_steps_per_second": 0.876,
501
+ "step": 44
502
+ },
503
+ {
504
+ "epoch": 0.7346938775510204,
505
+ "grad_norm": 0.23445634543895721,
506
+ "learning_rate": 0.0004,
507
+ "loss": 0.3113,
508
+ "step": 45
509
+ },
510
+ {
511
+ "epoch": 0.7510204081632653,
512
+ "grad_norm": 0.22852188348770142,
513
+ "learning_rate": 0.0004,
514
+ "loss": 0.3593,
515
+ "step": 46
516
+ },
517
+ {
518
+ "epoch": 0.7510204081632653,
519
+ "eval_loss": 0.9100953936576843,
520
+ "eval_runtime": 18.2446,
521
+ "eval_samples_per_second": 0.877,
522
+ "eval_steps_per_second": 0.877,
523
+ "step": 46
524
+ },
525
+ {
526
+ "epoch": 0.7673469387755102,
527
+ "grad_norm": 0.2316325306892395,
528
+ "learning_rate": 0.0004,
529
+ "loss": 0.3121,
530
+ "step": 47
531
+ },
532
+ {
533
+ "epoch": 0.7836734693877551,
534
+ "grad_norm": 0.2397606372833252,
535
+ "learning_rate": 0.0004,
536
+ "loss": 0.2979,
537
+ "step": 48
538
+ },
539
+ {
540
+ "epoch": 0.7836734693877551,
541
+ "eval_loss": 0.9087210297584534,
542
+ "eval_runtime": 18.2833,
543
+ "eval_samples_per_second": 0.875,
544
+ "eval_steps_per_second": 0.875,
545
+ "step": 48
546
+ },
547
+ {
548
+ "epoch": 0.8,
549
+ "grad_norm": 0.22637659311294556,
550
+ "learning_rate": 0.0004,
551
+ "loss": 0.2919,
552
+ "step": 49
553
+ },
554
+ {
555
+ "epoch": 0.8163265306122449,
556
+ "grad_norm": 0.255599707365036,
557
+ "learning_rate": 0.0004,
558
+ "loss": 0.3741,
559
+ "step": 50
560
+ },
561
+ {
562
+ "epoch": 0.8163265306122449,
563
+ "eval_loss": 0.9020435810089111,
564
+ "eval_runtime": 18.2931,
565
+ "eval_samples_per_second": 0.875,
566
+ "eval_steps_per_second": 0.875,
567
+ "step": 50
568
+ },
569
+ {
570
+ "epoch": 0.8163265306122449,
571
+ "eval_loss": 0.9020435810089111,
572
+ "eval_runtime": 18.1276,
573
+ "eval_samples_per_second": 0.883,
574
+ "eval_steps_per_second": 0.883,
575
+ "step": 50
576
+ },
577
+ {
578
+ "epoch": 0.8326530612244898,
579
+ "grad_norm": 0.2062978744506836,
580
+ "learning_rate": 0.0003877467715307749,
581
+ "loss": 0.3303,
582
+ "step": 51
583
+ },
584
+ {
585
+ "epoch": 0.8489795918367347,
586
+ "grad_norm": 0.20149795711040497,
587
+ "learning_rate": 0.0003870443502801494,
588
+ "loss": 0.3212,
589
+ "step": 52
590
+ },
591
+ {
592
+ "epoch": 0.8489795918367347,
593
+ "eval_loss": 0.8994156718254089,
594
+ "eval_runtime": 18.1853,
595
+ "eval_samples_per_second": 0.88,
596
+ "eval_steps_per_second": 0.88,
597
+ "step": 52
598
+ },
599
+ {
600
+ "epoch": 0.8653061224489796,
601
+ "grad_norm": 0.17913399636745453,
602
+ "learning_rate": 0.0003863230255984052,
603
+ "loss": 0.2637,
604
+ "step": 53
605
+ },
606
+ {
607
+ "epoch": 0.8816326530612245,
608
+ "grad_norm": 0.19331133365631104,
609
+ "learning_rate": 0.00038558287038542615,
610
+ "loss": 0.3564,
611
+ "step": 54
612
+ },
613
+ {
614
+ "epoch": 0.8816326530612245,
615
+ "eval_loss": 0.8963940143585205,
616
+ "eval_runtime": 18.223,
617
+ "eval_samples_per_second": 0.878,
618
+ "eval_steps_per_second": 0.878,
619
+ "step": 54
620
+ },
621
+ {
622
+ "epoch": 0.8979591836734694,
623
+ "grad_norm": 0.20378044247627258,
624
+ "learning_rate": 0.00038482395944418313,
625
+ "loss": 0.3253,
626
+ "step": 55
627
+ },
628
+ {
629
+ "epoch": 0.9142857142857143,
630
+ "grad_norm": 0.19742076098918915,
631
+ "learning_rate": 0.0003840463694731741,
632
+ "loss": 0.3715,
633
+ "step": 56
634
+ },
635
+ {
636
+ "epoch": 0.9142857142857143,
637
+ "eval_loss": 0.8902382850646973,
638
+ "eval_runtime": 18.2093,
639
+ "eval_samples_per_second": 0.879,
640
+ "eval_steps_per_second": 0.879,
641
+ "step": 56
642
+ },
643
+ {
644
+ "epoch": 0.9306122448979591,
645
+ "grad_norm": 0.1908055692911148,
646
+ "learning_rate": 0.0003832501790586724,
647
+ "loss": 0.3305,
648
+ "step": 57
649
+ },
650
+ {
651
+ "epoch": 0.9469387755102041,
652
+ "grad_norm": 0.21527761220932007,
653
+ "learning_rate": 0.0003824354686667848,
654
+ "loss": 0.3523,
655
+ "step": 58
656
+ },
657
+ {
658
+ "epoch": 0.9469387755102041,
659
+ "eval_loss": 0.8786917328834534,
660
+ "eval_runtime": 18.2124,
661
+ "eval_samples_per_second": 0.879,
662
+ "eval_steps_per_second": 0.879,
663
+ "step": 58
664
+ },
665
+ {
666
+ "epoch": 0.963265306122449,
667
+ "grad_norm": 0.1817687749862671,
668
+ "learning_rate": 0.00038160232063531917,
669
+ "loss": 0.2616,
670
+ "step": 59
671
+ },
672
+ {
673
+ "epoch": 0.9795918367346939,
674
+ "grad_norm": 0.17659063637256622,
675
+ "learning_rate": 0.0003807508191654631,
676
+ "loss": 0.251,
677
+ "step": 60
678
+ },
679
+ {
680
+ "epoch": 0.9795918367346939,
681
+ "eval_loss": 0.8799586296081543,
682
+ "eval_runtime": 18.2543,
683
+ "eval_samples_per_second": 0.877,
684
+ "eval_steps_per_second": 0.877,
685
+ "step": 60
686
+ },
687
+ {
688
+ "epoch": 0.9959183673469387,
689
+ "grad_norm": 0.22647982835769653,
690
+ "learning_rate": 0.0003798810503132742,
691
+ "loss": 0.2881,
692
+ "step": 61
693
+ },
694
+ {
695
+ "epoch": 1.0122448979591836,
696
+ "grad_norm": 0.45377442240715027,
697
+ "learning_rate": 0.00037899310198098295,
698
+ "loss": 0.5515,
699
+ "step": 62
700
+ },
701
+ {
702
+ "epoch": 1.0122448979591836,
703
+ "eval_loss": 0.8895297050476074,
704
+ "eval_runtime": 18.2212,
705
+ "eval_samples_per_second": 0.878,
706
+ "eval_steps_per_second": 0.878,
707
+ "step": 62
708
+ },
709
+ {
710
+ "epoch": 1.0285714285714285,
711
+ "grad_norm": 0.3527546226978302,
712
+ "learning_rate": 0.000378087063908109,
713
+ "loss": 0.2427,
714
+ "step": 63
715
+ },
716
+ {
717
+ "epoch": 1.0448979591836736,
718
+ "grad_norm": 0.2781178951263428,
719
+ "learning_rate": 0.0003771630276623915,
720
+ "loss": 0.2215,
721
+ "step": 64
722
+ },
723
+ {
724
+ "epoch": 1.0448979591836736,
725
+ "eval_loss": 0.9294220209121704,
726
+ "eval_runtime": 18.226,
727
+ "eval_samples_per_second": 0.878,
728
+ "eval_steps_per_second": 0.878,
729
+ "step": 64
730
+ },
731
+ {
732
+ "epoch": 1.0612244897959184,
733
+ "grad_norm": 0.2543565034866333,
734
+ "learning_rate": 0.00037622108663053536,
735
+ "loss": 0.2761,
736
+ "step": 65
737
+ },
738
+ {
739
+ "epoch": 1.0775510204081633,
740
+ "grad_norm": 0.26259011030197144,
741
+ "learning_rate": 0.0003752613360087727,
742
+ "loss": 0.2425,
743
+ "step": 66
744
+ },
745
+ {
746
+ "epoch": 1.0775510204081633,
747
+ "eval_loss": 0.9212721586227417,
748
+ "eval_runtime": 18.2309,
749
+ "eval_samples_per_second": 0.878,
750
+ "eval_steps_per_second": 0.878,
751
+ "step": 66
752
+ },
753
+ {
754
+ "epoch": 1.0938775510204082,
755
+ "grad_norm": 0.36850446462631226,
756
+ "learning_rate": 0.00037428387279324257,
757
+ "loss": 0.225,
758
+ "step": 67
759
+ },
760
+ {
761
+ "epoch": 1.110204081632653,
762
+ "grad_norm": 0.23748713731765747,
763
+ "learning_rate": 0.0003732887957701874,
764
+ "loss": 0.2363,
765
+ "step": 68
766
+ },
767
+ {
768
+ "epoch": 1.110204081632653,
769
+ "eval_loss": 0.9431418776512146,
770
+ "eval_runtime": 18.2471,
771
+ "eval_samples_per_second": 0.877,
772
+ "eval_steps_per_second": 0.877,
773
+ "step": 68
774
+ },
775
+ {
776
+ "epoch": 1.126530612244898,
777
+ "grad_norm": 0.23217403888702393,
778
+ "learning_rate": 0.00037227620550597,
779
+ "loss": 0.2364,
780
+ "step": 69
781
+ },
782
+ {
783
+ "epoch": 1.1428571428571428,
784
+ "grad_norm": 0.28124868869781494,
785
+ "learning_rate": 0.0003712462043369093,
786
+ "loss": 0.2197,
787
+ "step": 70
788
+ },
789
+ {
790
+ "epoch": 1.1428571428571428,
791
+ "eval_loss": 0.9205393195152283,
792
+ "eval_runtime": 18.2662,
793
+ "eval_samples_per_second": 0.876,
794
+ "eval_steps_per_second": 0.876,
795
+ "step": 70
796
+ },
797
+ {
798
+ "epoch": 1.1591836734693877,
799
+ "grad_norm": 0.2142041176557541,
800
+ "learning_rate": 0.00037019889635893843,
801
+ "loss": 0.1958,
802
+ "step": 71
803
+ },
804
+ {
805
+ "epoch": 1.1755102040816325,
806
+ "grad_norm": 0.34761127829551697,
807
+ "learning_rate": 0.0003691343874170838,
808
+ "loss": 0.2183,
809
+ "step": 72
810
+ },
811
+ {
812
+ "epoch": 1.1755102040816325,
813
+ "eval_loss": 0.9254322648048401,
814
+ "eval_runtime": 18.2303,
815
+ "eval_samples_per_second": 0.878,
816
+ "eval_steps_per_second": 0.878,
817
+ "step": 72
818
+ },
819
+ {
820
+ "epoch": 1.1918367346938776,
821
+ "grad_norm": 0.2560065686702728,
822
+ "learning_rate": 0.00036805278509476844,
823
+ "loss": 0.248,
824
+ "step": 73
825
+ },
826
+ {
827
+ "epoch": 1.2081632653061225,
828
+ "grad_norm": 0.7435296773910522,
829
+ "learning_rate": 0.00036695419870293915,
830
+ "loss": 0.2356,
831
+ "step": 74
832
+ },
833
+ {
834
+ "epoch": 1.2081632653061225,
835
+ "eval_loss": 0.9271378517150879,
836
+ "eval_runtime": 18.2503,
837
+ "eval_samples_per_second": 0.877,
838
+ "eval_steps_per_second": 0.877,
839
+ "step": 74
840
+ },
841
+ {
842
+ "epoch": 1.2244897959183674,
843
+ "grad_norm": 0.8685758113861084,
844
+ "learning_rate": 0.00036583873926901867,
845
+ "loss": 0.2129,
846
+ "step": 75
847
+ },
848
+ {
849
+ "epoch": 1.2408163265306122,
850
+ "grad_norm": 1.2740998268127441,
851
+ "learning_rate": 0.0003647065195256855,
852
+ "loss": 0.2469,
853
+ "step": 76
854
+ },
855
+ {
856
+ "epoch": 1.2408163265306122,
857
+ "eval_loss": 0.9236885905265808,
858
+ "eval_runtime": 18.2226,
859
+ "eval_samples_per_second": 0.878,
860
+ "eval_steps_per_second": 0.878,
861
+ "step": 76
862
+ },
863
+ {
864
+ "epoch": 1.2571428571428571,
865
+ "grad_norm": 0.28524693846702576,
866
+ "learning_rate": 0.0003635576538994801,
867
+ "loss": 0.2278,
868
+ "step": 77
869
+ },
870
+ {
871
+ "epoch": 1.273469387755102,
872
+ "grad_norm": 1.0116885900497437,
873
+ "learning_rate": 0.0003623922584992409,
874
+ "loss": 0.2488,
875
+ "step": 78
876
+ },
877
+ {
878
+ "epoch": 1.273469387755102,
879
+ "eval_loss": 0.923646867275238,
880
+ "eval_runtime": 18.2519,
881
+ "eval_samples_per_second": 0.877,
882
+ "eval_steps_per_second": 0.877,
883
+ "step": 78
884
+ },
885
+ {
886
+ "epoch": 1.2897959183673469,
887
+ "grad_norm": 0.9336573481559753,
888
+ "learning_rate": 0.0003612104511043694,
889
+ "loss": 0.3095,
890
+ "step": 79
891
+ },
892
+ {
893
+ "epoch": 1.306122448979592,
894
+ "grad_norm": 0.43459734320640564,
895
+ "learning_rate": 0.0003600123511529278,
896
+ "loss": 0.2215,
897
+ "step": 80
898
+ },
899
+ {
900
+ "epoch": 1.306122448979592,
901
+ "eval_loss": 0.941472589969635,
902
+ "eval_runtime": 18.251,
903
+ "eval_samples_per_second": 0.877,
904
+ "eval_steps_per_second": 0.877,
905
+ "step": 80
906
+ },
907
+ {
908
+ "epoch": 1.3224489795918366,
909
+ "grad_norm": 0.39941656589508057,
910
+ "learning_rate": 0.0003587980797295671,
911
+ "loss": 0.251,
912
+ "step": 81
913
+ },
914
+ {
915
+ "epoch": 1.3387755102040817,
916
+ "grad_norm": 0.2876632511615753,
917
+ "learning_rate": 0.0003575677595532904,
918
+ "loss": 0.208,
919
+ "step": 82
920
+ },
921
+ {
922
+ "epoch": 1.3387755102040817,
923
+ "eval_loss": 0.932316780090332,
924
+ "eval_runtime": 18.2326,
925
+ "eval_samples_per_second": 0.878,
926
+ "eval_steps_per_second": 0.878,
927
+ "step": 82
928
+ },
929
+ {
930
+ "epoch": 1.3551020408163266,
931
+ "grad_norm": 0.30556565523147583,
932
+ "learning_rate": 0.0003563215149650505,
933
+ "loss": 0.2821,
934
+ "step": 83
935
+ },
936
+ {
937
+ "epoch": 1.3714285714285714,
938
+ "grad_norm": 0.3039940595626831,
939
+ "learning_rate": 0.00035505947191518316,
940
+ "loss": 0.2177,
941
+ "step": 84
942
+ },
943
+ {
944
+ "epoch": 1.3714285714285714,
945
+ "eval_loss": 0.9171479344367981,
946
+ "eval_runtime": 18.2397,
947
+ "eval_samples_per_second": 0.877,
948
+ "eval_steps_per_second": 0.877,
949
+ "step": 84
950
+ },
951
+ {
952
+ "epoch": 1.3877551020408163,
953
+ "grad_norm": 0.32876476645469666,
954
+ "learning_rate": 0.0003537817579506783,
955
+ "loss": 0.2142,
956
+ "step": 85
957
+ },
958
+ {
959
+ "epoch": 1.4040816326530612,
960
+ "grad_norm": 0.26468542218208313,
961
+ "learning_rate": 0.0003524885022022896,
962
+ "loss": 0.2293,
963
+ "step": 86
964
+ },
965
+ {
966
+ "epoch": 1.4040816326530612,
967
+ "eval_loss": 0.9176874756813049,
968
+ "eval_runtime": 18.2553,
969
+ "eval_samples_per_second": 0.876,
970
+ "eval_steps_per_second": 0.876,
971
+ "step": 86
972
+ },
973
+ {
974
+ "epoch": 1.420408163265306,
975
+ "grad_norm": 0.9715031981468201,
976
+ "learning_rate": 0.000351179835371484,
977
+ "loss": 0.235,
978
+ "step": 87
979
+ },
980
+ {
981
+ "epoch": 1.436734693877551,
982
+ "grad_norm": 0.8392952680587769,
983
+ "learning_rate": 0.00034985588971723233,
984
+ "loss": 0.2307,
985
+ "step": 88
986
+ },
987
+ {
988
+ "epoch": 1.436734693877551,
989
+ "eval_loss": 0.9272938370704651,
990
+ "eval_runtime": 18.2194,
991
+ "eval_samples_per_second": 0.878,
992
+ "eval_steps_per_second": 0.878,
993
+ "step": 88
994
+ },
995
+ {
996
+ "epoch": 1.453061224489796,
997
+ "grad_norm": 0.28850337862968445,
998
+ "learning_rate": 0.00034851679904264314,
999
+ "loss": 0.2403,
1000
+ "step": 89
1001
+ },
1002
+ {
1003
+ "epoch": 1.469387755102041,
1004
+ "grad_norm": 0.46389341354370117,
1005
+ "learning_rate": 0.00034716269868143956,
1006
+ "loss": 0.2464,
1007
+ "step": 90
1008
+ },
1009
+ {
1010
+ "epoch": 1.469387755102041,
1011
+ "eval_loss": 0.9267984628677368,
1012
+ "eval_runtime": 18.2514,
1013
+ "eval_samples_per_second": 0.877,
1014
+ "eval_steps_per_second": 0.877,
1015
+ "step": 90
1016
+ },
1017
+ {
1018
+ "epoch": 1.4857142857142858,
1019
+ "grad_norm": 0.29597121477127075,
1020
+ "learning_rate": 0.00034579372548428235,
1021
+ "loss": 0.2307,
1022
+ "step": 91
1023
+ },
1024
+ {
1025
+ "epoch": 1.5020408163265306,
1026
+ "grad_norm": 0.3392711877822876,
1027
+ "learning_rate": 0.00034441001780493886,
1028
+ "loss": 0.231,
1029
+ "step": 92
1030
+ },
1031
+ {
1032
+ "epoch": 1.5020408163265306,
1033
+ "eval_loss": 0.9267009496688843,
1034
+ "eval_runtime": 18.2179,
1035
+ "eval_samples_per_second": 0.878,
1036
+ "eval_steps_per_second": 0.878,
1037
+ "step": 92
1038
+ },
1039
+ {
1040
+ "epoch": 1.5183673469387755,
1041
+ "grad_norm": 0.2309531569480896,
1042
+ "learning_rate": 0.00034301171548630063,
1043
+ "loss": 0.2307,
1044
+ "step": 93
1045
+ },
1046
+ {
1047
+ "epoch": 1.5346938775510204,
1048
+ "grad_norm": 0.28941744565963745,
1049
+ "learning_rate": 0.0003415989598462506,
1050
+ "loss": 0.2384,
1051
+ "step": 94
1052
+ },
1053
+ {
1054
+ "epoch": 1.5346938775510204,
1055
+ "eval_loss": 0.9336121082305908,
1056
+ "eval_runtime": 18.2184,
1057
+ "eval_samples_per_second": 0.878,
1058
+ "eval_steps_per_second": 0.878,
1059
+ "step": 94
1060
+ },
1061
+ {
1062
+ "epoch": 1.5510204081632653,
1063
+ "grad_norm": 0.22579389810562134,
1064
+ "learning_rate": 0.00034017189366338034,
1065
+ "loss": 0.1949,
1066
+ "step": 95
1067
+ },
1068
+ {
1069
+ "epoch": 1.5673469387755103,
1070
+ "grad_norm": 0.2894729971885681,
1071
+ "learning_rate": 0.000338730661162561,
1072
+ "loss": 0.2348,
1073
+ "step": 96
1074
+ },
1075
+ {
1076
+ "epoch": 1.5673469387755103,
1077
+ "eval_loss": 0.9432627558708191,
1078
+ "eval_runtime": 18.2158,
1079
+ "eval_samples_per_second": 0.878,
1080
+ "eval_steps_per_second": 0.878,
1081
+ "step": 96
1082
+ },
1083
+ {
1084
+ "epoch": 1.583673469387755,
1085
+ "grad_norm": 0.24218647181987762,
1086
+ "learning_rate": 0.00033727540800036683,
1087
+ "loss": 0.2113,
1088
+ "step": 97
1089
+ },
1090
+ {
1091
+ "epoch": 1.6,
1092
+ "grad_norm": 0.2695946991443634,
1093
+ "learning_rate": 0.0003358062812503548,
1094
+ "loss": 0.2209,
1095
+ "step": 98
1096
+ },
1097
+ {
1098
+ "epoch": 1.6,
1099
+ "eval_loss": 0.9510765075683594,
1100
+ "eval_runtime": 18.2181,
1101
+ "eval_samples_per_second": 0.878,
1102
+ "eval_steps_per_second": 0.878,
1103
+ "step": 98
1104
+ },
1105
+ {
1106
+ "epoch": 1.6163265306122447,
1107
+ "grad_norm": 0.27196425199508667,
1108
+ "learning_rate": 0.00033432342938820086,
1109
+ "loss": 0.2366,
1110
+ "step": 99
1111
+ },
1112
+ {
1113
+ "epoch": 1.6326530612244898,
1114
+ "grad_norm": 0.2302471101284027,
1115
+ "learning_rate": 0.0003328270022766941,
1116
+ "loss": 0.2099,
1117
+ "step": 100
1118
+ },
1119
+ {
1120
+ "epoch": 1.6326530612244898,
1121
+ "eval_loss": 0.9363111853599548,
1122
+ "eval_runtime": 18.2175,
1123
+ "eval_samples_per_second": 0.878,
1124
+ "eval_steps_per_second": 0.878,
1125
+ "step": 100
1126
+ },
1127
+ {
1128
+ "epoch": 1.6489795918367347,
1129
+ "grad_norm": 0.24810455739498138,
1130
+ "learning_rate": 0.0003313171511505913,
1131
+ "loss": 0.2196,
1132
+ "step": 101
1133
+ },
1134
+ {
1135
+ "epoch": 1.6653061224489796,
1136
+ "grad_norm": 0.25561368465423584,
1137
+ "learning_rate": 0.0003297940286013326,
1138
+ "loss": 0.253,
1139
+ "step": 102
1140
+ },
1141
+ {
1142
+ "epoch": 1.6653061224489796,
1143
+ "eval_loss": 0.942488431930542,
1144
+ "eval_runtime": 18.2068,
1145
+ "eval_samples_per_second": 0.879,
1146
+ "eval_steps_per_second": 0.879,
1147
+ "step": 102
1148
+ },
1149
+ {
1150
+ "epoch": 1.6816326530612244,
1151
+ "grad_norm": 0.22677375376224518,
1152
+ "learning_rate": 0.0003282577885616198,
1153
+ "loss": 0.1789,
1154
+ "step": 103
1155
+ },
1156
+ {
1157
+ "epoch": 1.6979591836734693,
1158
+ "grad_norm": 0.26009589433670044,
1159
+ "learning_rate": 0.0003267085862898594,
1160
+ "loss": 0.2541,
1161
+ "step": 104
1162
+ },
1163
+ {
1164
+ "epoch": 1.6979591836734693,
1165
+ "eval_loss": 0.9335595369338989,
1166
+ "eval_runtime": 18.2507,
1167
+ "eval_samples_per_second": 0.877,
1168
+ "eval_steps_per_second": 0.877,
1169
+ "step": 104
1170
+ },
1171
+ {
1172
+ "epoch": 1.7142857142857144,
1173
+ "grad_norm": 0.20782141387462616,
1174
+ "learning_rate": 0.0003251465783544716,
1175
+ "loss": 0.2308,
1176
+ "step": 105
1177
+ },
1178
+ {
1179
+ "epoch": 1.730612244897959,
1180
+ "grad_norm": 0.22768278419971466,
1181
+ "learning_rate": 0.0003235719226180669,
1182
+ "loss": 0.2354,
1183
+ "step": 106
1184
+ },
1185
+ {
1186
+ "epoch": 1.730612244897959,
1187
+ "eval_loss": 0.9376662373542786,
1188
+ "eval_runtime": 18.2284,
1189
+ "eval_samples_per_second": 0.878,
1190
+ "eval_steps_per_second": 0.878,
1191
+ "step": 106
1192
+ },
1193
+ {
1194
+ "epoch": 1.7469387755102042,
1195
+ "grad_norm": 0.23742002248764038,
1196
+ "learning_rate": 0.00032198477822149185,
1197
+ "loss": 0.2306,
1198
+ "step": 107
1199
+ },
1200
+ {
1201
+ "epoch": 1.763265306122449,
1202
+ "grad_norm": 0.25688832998275757,
1203
+ "learning_rate": 0.0003203853055677457,
1204
+ "loss": 0.2816,
1205
+ "step": 108
1206
+ },
1207
+ {
1208
+ "epoch": 1.763265306122449,
1209
+ "eval_loss": 0.9434496164321899,
1210
+ "eval_runtime": 18.2263,
1211
+ "eval_samples_per_second": 0.878,
1212
+ "eval_steps_per_second": 0.878,
1213
+ "step": 108
1214
+ },
1215
+ {
1216
+ "epoch": 1.779591836734694,
1217
+ "grad_norm": 0.2690117359161377,
1218
+ "learning_rate": 0.00031877366630576946,
1219
+ "loss": 0.2013,
1220
+ "step": 109
1221
+ },
1222
+ {
1223
+ "epoch": 1.7959183673469388,
1224
+ "grad_norm": 0.2317412942647934,
1225
+ "learning_rate": 0.0003171500233141089,
1226
+ "loss": 0.2398,
1227
+ "step": 110
1228
+ },
1229
+ {
1230
+ "epoch": 1.7959183673469388,
1231
+ "eval_loss": 0.9329774975776672,
1232
+ "eval_runtime": 18.2112,
1233
+ "eval_samples_per_second": 0.879,
1234
+ "eval_steps_per_second": 0.879,
1235
+ "step": 110
1236
+ },
1237
+ {
1238
+ "epoch": 1.8122448979591836,
1239
+ "grad_norm": 0.2262117713689804,
1240
+ "learning_rate": 0.0003155145406844535,
1241
+ "loss": 0.207,
1242
+ "step": 111
1243
+ },
1244
+ {
1245
+ "epoch": 1.8285714285714287,
1246
+ "grad_norm": 0.22458741068840027,
1247
+ "learning_rate": 0.00031386738370505293,
1248
+ "loss": 0.2093,
1249
+ "step": 112
1250
+ },
1251
+ {
1252
+ "epoch": 1.8285714285714287,
1253
+ "eval_loss": 0.9222925901412964,
1254
+ "eval_runtime": 18.2333,
1255
+ "eval_samples_per_second": 0.878,
1256
+ "eval_steps_per_second": 0.878,
1257
+ "step": 112
1258
+ },
1259
+ {
1260
+ "epoch": 1.8448979591836734,
1261
+ "grad_norm": 0.24273625016212463,
1262
+ "learning_rate": 0.0003122087188440118,
1263
+ "loss": 0.2434,
1264
+ "step": 113
1265
+ },
1266
+ {
1267
+ "epoch": 1.8612244897959185,
1268
+ "grad_norm": 0.2206314653158188,
1269
+ "learning_rate": 0.0003105387137324663,
1270
+ "loss": 0.2056,
1271
+ "step": 114
1272
+ },
1273
+ {
1274
+ "epoch": 1.8612244897959185,
1275
+ "eval_loss": 0.9319095015525818,
1276
+ "eval_runtime": 18.2327,
1277
+ "eval_samples_per_second": 0.878,
1278
+ "eval_steps_per_second": 0.878,
1279
+ "step": 114
1280
+ },
1281
+ {
1282
+ "epoch": 1.8775510204081631,
1283
+ "grad_norm": 0.2606954574584961,
1284
+ "learning_rate": 0.0003088575371476426,
1285
+ "loss": 0.2198,
1286
+ "step": 115
1287
+ },
1288
+ {
1289
+ "epoch": 1.8938775510204082,
1290
+ "grad_norm": 0.23156337440013885,
1291
+ "learning_rate": 0.0003071653589957993,
1292
+ "loss": 0.1957,
1293
+ "step": 116
1294
+ },
1295
+ {
1296
+ "epoch": 1.8938775510204082,
1297
+ "eval_loss": 0.9314719438552856,
1298
+ "eval_runtime": 18.2411,
1299
+ "eval_samples_per_second": 0.877,
1300
+ "eval_steps_per_second": 0.877,
1301
+ "step": 116
1302
+ },
1303
+ {
1304
+ "epoch": 1.910204081632653,
1305
+ "grad_norm": 0.2253030389547348,
1306
+ "learning_rate": 0.0003054623502950565,
1307
+ "loss": 0.266,
1308
+ "step": 117
1309
+ },
1310
+ {
1311
+ "epoch": 1.926530612244898,
1312
+ "grad_norm": 0.24510890245437622,
1313
+ "learning_rate": 0.0003037486831581115,
1314
+ "loss": 0.2493,
1315
+ "step": 118
1316
+ },
1317
+ {
1318
+ "epoch": 1.926530612244898,
1319
+ "eval_loss": 0.926245927810669,
1320
+ "eval_runtime": 18.2428,
1321
+ "eval_samples_per_second": 0.877,
1322
+ "eval_steps_per_second": 0.877,
1323
+ "step": 118
1324
+ },
1325
+ {
1326
+ "epoch": 1.9428571428571428,
1327
+ "grad_norm": 0.22151368856430054,
1328
+ "learning_rate": 0.00030202453077484494,
1329
+ "loss": 0.2666,
1330
+ "step": 119
1331
+ },
1332
+ {
1333
+ "epoch": 1.9591836734693877,
1334
+ "grad_norm": 0.21714863181114197,
1335
+ "learning_rate": 0.0003002900673948173,
1336
+ "loss": 0.253,
1337
+ "step": 120
1338
+ },
1339
+ {
1340
+ "epoch": 1.9591836734693877,
1341
+ "eval_loss": 0.9263309240341187,
1342
+ "eval_runtime": 18.2196,
1343
+ "eval_samples_per_second": 0.878,
1344
+ "eval_steps_per_second": 0.878,
1345
+ "step": 120
1346
+ },
1347
+ {
1348
+ "epoch": 1.9755102040816328,
1349
+ "grad_norm": 0.2149583399295807,
1350
+ "learning_rate": 0.0002985454683096583,
1351
+ "loss": 0.2208,
1352
+ "step": 121
1353
+ },
1354
+ {
1355
+ "epoch": 1.9918367346938775,
1356
+ "grad_norm": 0.23067210614681244,
1357
+ "learning_rate": 0.000296790909835352,
1358
+ "loss": 0.2225,
1359
+ "step": 122
1360
+ },
1361
+ {
1362
+ "epoch": 1.9918367346938775,
1363
+ "eval_loss": 0.9324613809585571,
1364
+ "eval_runtime": 18.2438,
1365
+ "eval_samples_per_second": 0.877,
1366
+ "eval_steps_per_second": 0.877,
1367
+ "step": 122
1368
+ },
1369
+ {
1370
+ "epoch": 2.0081632653061225,
1371
+ "grad_norm": 0.4510343074798584,
1372
+ "learning_rate": 0.00029502656929441683,
1373
+ "loss": 0.3179,
1374
+ "step": 123
1375
+ },
1376
+ {
1377
+ "epoch": 2.024489795918367,
1378
+ "grad_norm": 0.24402837455272675,
1379
+ "learning_rate": 0.000293252624997985,
1380
+ "loss": 0.1501,
1381
+ "step": 124
1382
+ },
1383
+ {
1384
+ "epoch": 2.024489795918367,
1385
+ "eval_loss": 0.9700677394866943,
1386
+ "eval_runtime": 18.2313,
1387
+ "eval_samples_per_second": 0.878,
1388
+ "eval_steps_per_second": 0.878,
1389
+ "step": 124
1390
+ },
1391
+ {
1392
+ "epoch": 2.0408163265306123,
1393
+ "grad_norm": 0.31533220410346985,
1394
+ "learning_rate": 0.00029146925622778176,
1395
+ "loss": 0.1353,
1396
+ "step": 125
1397
+ },
1398
+ {
1399
+ "epoch": 2.057142857142857,
1400
+ "grad_norm": 0.24323108792304993,
1401
+ "learning_rate": 0.0002896766432180065,
1402
+ "loss": 0.1297,
1403
+ "step": 126
1404
+ },
1405
+ {
1406
+ "epoch": 2.057142857142857,
1407
+ "eval_loss": 0.9890408515930176,
1408
+ "eval_runtime": 18.2073,
1409
+ "eval_samples_per_second": 0.879,
1410
+ "eval_steps_per_second": 0.879,
1411
+ "step": 126
1412
+ },
1413
+ {
1414
+ "epoch": 2.073469387755102,
1415
+ "grad_norm": 0.24305571615695953,
1416
+ "learning_rate": 0.00028787496713711733,
1417
+ "loss": 0.1389,
1418
+ "step": 127
1419
+ },
1420
+ {
1421
+ "epoch": 2.089795918367347,
1422
+ "grad_norm": 0.21282273530960083,
1423
+ "learning_rate": 0.0002860644100695218,
1424
+ "loss": 0.0994,
1425
+ "step": 128
1426
+ },
1427
+ {
1428
+ "epoch": 2.089795918367347,
1429
+ "eval_loss": 1.0023484230041504,
1430
+ "eval_runtime": 18.2257,
1431
+ "eval_samples_per_second": 0.878,
1432
+ "eval_steps_per_second": 0.878,
1433
+ "step": 128
1434
+ },
1435
+ {
1436
+ "epoch": 2.1061224489795918,
1437
+ "grad_norm": 0.20902425050735474,
1438
+ "learning_rate": 0.0002842451549971745,
1439
+ "loss": 0.1195,
1440
+ "step": 129
1441
+ },
1442
+ {
1443
+ "epoch": 2.122448979591837,
1444
+ "grad_norm": 0.21242493391036987,
1445
+ "learning_rate": 0.0002824173857810842,
1446
+ "loss": 0.1256,
1447
+ "step": 130
1448
+ },
1449
+ {
1450
+ "epoch": 2.122448979591837,
1451
+ "eval_loss": 1.0186381340026855,
1452
+ "eval_runtime": 18.1967,
1453
+ "eval_samples_per_second": 0.879,
1454
+ "eval_steps_per_second": 0.879,
1455
+ "step": 130
1456
+ },
1457
+ {
1458
+ "epoch": 2.1387755102040815,
1459
+ "grad_norm": 0.26445460319519043,
1460
+ "learning_rate": 0.00028058128714273257,
1461
+ "loss": 0.1268,
1462
+ "step": 131
1463
+ },
1464
+ {
1465
+ "epoch": 2.1551020408163266,
1466
+ "grad_norm": 0.24118709564208984,
1467
+ "learning_rate": 0.0002787370446454047,
1468
+ "loss": 0.1192,
1469
+ "step": 132
1470
+ },
1471
+ {
1472
+ "epoch": 2.1551020408163266,
1473
+ "eval_loss": 1.0201678276062012,
1474
+ "eval_runtime": 18.2377,
1475
+ "eval_samples_per_second": 0.877,
1476
+ "eval_steps_per_second": 0.877,
1477
+ "step": 132
1478
+ },
1479
+ {
1480
+ "epoch": 2.1714285714285713,
1481
+ "grad_norm": 0.23629823327064514,
1482
+ "learning_rate": 0.0002768848446754362,
1483
+ "loss": 0.1114,
1484
+ "step": 133
1485
+ },
1486
+ {
1487
+ "epoch": 2.1877551020408164,
1488
+ "grad_norm": 0.23851804435253143,
1489
+ "learning_rate": 0.0002750248744233756,
1490
+ "loss": 0.1455,
1491
+ "step": 134
1492
+ },
1493
+ {
1494
+ "epoch": 2.1877551020408164,
1495
+ "eval_loss": 1.027251124382019,
1496
+ "eval_runtime": 18.2111,
1497
+ "eval_samples_per_second": 0.879,
1498
+ "eval_steps_per_second": 0.879,
1499
+ "step": 134
1500
+ },
1501
+ {
1502
+ "epoch": 2.204081632653061,
1503
+ "grad_norm": 0.2159481793642044,
1504
+ "learning_rate": 0.00027315732186506656,
1505
+ "loss": 0.1036,
1506
+ "step": 135
1507
+ },
1508
+ {
1509
+ "epoch": 2.220408163265306,
1510
+ "grad_norm": 0.2521194815635681,
1511
+ "learning_rate": 0.0002712823757426501,
1512
+ "loss": 0.1539,
1513
+ "step": 136
1514
+ },
1515
+ {
1516
+ "epoch": 2.220408163265306,
1517
+ "eval_loss": 1.0327486991882324,
1518
+ "eval_runtime": 18.2282,
1519
+ "eval_samples_per_second": 0.878,
1520
+ "eval_steps_per_second": 0.878,
1521
+ "step": 136
1522
+ },
1523
+ {
1524
+ "epoch": 2.236734693877551,
1525
+ "grad_norm": 0.23456163704395294,
1526
+ "learning_rate": 0.00026940022554548993,
1527
+ "loss": 0.14,
1528
+ "step": 137
1529
+ },
1530
+ {
1531
+ "epoch": 2.253061224489796,
1532
+ "grad_norm": 0.25591009855270386,
1533
+ "learning_rate": 0.0002675110614910212,
1534
+ "loss": 0.1485,
1535
+ "step": 138
1536
+ },
1537
+ {
1538
+ "epoch": 2.253061224489796,
1539
+ "eval_loss": 1.0385500192642212,
1540
+ "eval_runtime": 18.1962,
1541
+ "eval_samples_per_second": 0.879,
1542
+ "eval_steps_per_second": 0.879,
1543
+ "step": 138
1544
+ },
1545
+ {
1546
+ "epoch": 2.269387755102041,
1547
+ "grad_norm": 0.2525387108325958,
1548
+ "learning_rate": 0.00026561507450552704,
1549
+ "loss": 0.1164,
1550
+ "step": 139
1551
+ },
1552
+ {
1553
+ "epoch": 2.2857142857142856,
1554
+ "grad_norm": 0.25320008397102356,
1555
+ "learning_rate": 0.00026371245620484255,
1556
+ "loss": 0.1307,
1557
+ "step": 140
1558
+ },
1559
+ {
1560
+ "epoch": 2.2857142857142856,
1561
+ "eval_loss": 1.028091311454773,
1562
+ "eval_runtime": 18.2167,
1563
+ "eval_samples_per_second": 0.878,
1564
+ "eval_steps_per_second": 0.878,
1565
+ "step": 140
1566
+ },
1567
+ {
1568
+ "epoch": 2.3020408163265307,
1569
+ "grad_norm": 0.27121609449386597,
1570
+ "learning_rate": 0.00026180339887498953,
1571
+ "loss": 0.1475,
1572
+ "step": 141
1573
+ },
1574
+ {
1575
+ "epoch": 2.3183673469387753,
1576
+ "grad_norm": 0.2442832738161087,
1577
+ "learning_rate": 0.00025988809545274293,
1578
+ "loss": 0.112,
1579
+ "step": 142
1580
+ },
1581
+ {
1582
+ "epoch": 2.3183673469387753,
1583
+ "eval_loss": 0.9875463247299194,
1584
+ "eval_runtime": 18.2364,
1585
+ "eval_samples_per_second": 0.877,
1586
+ "eval_steps_per_second": 0.877,
1587
+ "step": 142
1588
+ },
1589
+ {
1590
+ "epoch": 2.3346938775510204,
1591
+ "grad_norm": 0.23179620504379272,
1592
+ "learning_rate": 0.0002579667395061322,
1593
+ "loss": 0.1428,
1594
+ "step": 143
1595
+ },
1596
+ {
1597
+ "epoch": 2.351020408163265,
1598
+ "grad_norm": 0.21805799007415771,
1599
+ "learning_rate": 0.00025603952521487876,
1600
+ "loss": 0.1157,
1601
+ "step": 144
1602
+ },
1603
+ {
1604
+ "epoch": 2.351020408163265,
1605
+ "eval_loss": 0.9967271089553833,
1606
+ "eval_runtime": 18.2289,
1607
+ "eval_samples_per_second": 0.878,
1608
+ "eval_steps_per_second": 0.878,
1609
+ "step": 144
1610
+ },
1611
+ {
1612
+ "epoch": 2.36734693877551,
1613
+ "grad_norm": 0.2379518747329712,
1614
+ "learning_rate": 0.0002541066473507708,
1615
+ "loss": 0.1368,
1616
+ "step": 145
1617
+ },
1618
+ {
1619
+ "epoch": 2.3836734693877553,
1620
+ "grad_norm": 0.27792760729789734,
1621
+ "learning_rate": 0.00025216830125797943,
1622
+ "loss": 0.1369,
1623
+ "step": 146
1624
+ },
1625
+ {
1626
+ "epoch": 2.3836734693877553,
1627
+ "eval_loss": 0.9868496656417847,
1628
+ "eval_runtime": 18.2074,
1629
+ "eval_samples_per_second": 0.879,
1630
+ "eval_steps_per_second": 0.879,
1631
+ "step": 146
1632
+ },
1633
+ {
1634
+ "epoch": 2.4,
1635
+ "grad_norm": 0.2362203449010849,
1636
+ "learning_rate": 0.0002502246828333163,
1637
+ "loss": 0.1275,
1638
+ "step": 147
1639
+ },
1640
+ {
1641
+ "epoch": 2.416326530612245,
1642
+ "grad_norm": 0.27191162109375,
1643
+ "learning_rate": 0.00024827598850643546,
1644
+ "loss": 0.1582,
1645
+ "step": 148
1646
+ },
1647
+ {
1648
+ "epoch": 2.416326530612245,
1649
+ "eval_loss": 0.962943434715271,
1650
+ "eval_runtime": 18.2207,
1651
+ "eval_samples_per_second": 0.878,
1652
+ "eval_steps_per_second": 0.878,
1653
+ "step": 148
1654
+ },
1655
+ {
1656
+ "epoch": 2.4326530612244897,
1657
+ "grad_norm": 0.23347483575344086,
1658
+ "learning_rate": 0.0002463224152199813,
1659
+ "loss": 0.1309,
1660
+ "step": 149
1661
+ },
1662
+ {
1663
+ "epoch": 2.4489795918367347,
1664
+ "grad_norm": 0.2181580364704132,
1665
+ "learning_rate": 0.0002443641604096851,
1666
+ "loss": 0.1261,
1667
+ "step": 150
1668
+ },
1669
+ {
1670
+ "epoch": 2.4489795918367347,
1671
+ "eval_loss": 0.9731823205947876,
1672
+ "eval_runtime": 18.2136,
1673
+ "eval_samples_per_second": 0.878,
1674
+ "eval_steps_per_second": 0.878,
1675
+ "step": 150
1676
+ },
1677
+ {
1678
+ "epoch": 2.4653061224489794,
1679
+ "grad_norm": 0.2505442202091217,
1680
+ "learning_rate": 0.00024240142198441098,
1681
+ "loss": 0.1335,
1682
+ "step": 151
1683
+ },
1684
+ {
1685
+ "epoch": 2.4816326530612245,
1686
+ "grad_norm": 0.23964084684848785,
1687
+ "learning_rate": 0.00024043439830615472,
1688
+ "loss": 0.1249,
1689
+ "step": 152
1690
+ },
1691
+ {
1692
+ "epoch": 2.4816326530612245,
1693
+ "eval_loss": 0.9946855306625366,
1694
+ "eval_runtime": 18.2384,
1695
+ "eval_samples_per_second": 0.877,
1696
+ "eval_steps_per_second": 0.877,
1697
+ "step": 152
1698
+ },
1699
+ {
1700
+ "epoch": 2.497959183673469,
1701
+ "grad_norm": 0.2175896167755127,
1702
+ "learning_rate": 0.00023846328816999658,
1703
+ "loss": 0.101,
1704
+ "step": 153
1705
+ },
1706
+ {
1707
+ "epoch": 2.5142857142857142,
1708
+ "grad_norm": 0.2787061929702759,
1709
+ "learning_rate": 0.00023648829078401007,
1710
+ "loss": 0.1421,
1711
+ "step": 154
1712
+ },
1713
+ {
1714
+ "epoch": 2.5142857142857142,
1715
+ "eval_loss": 0.9933134317398071,
1716
+ "eval_runtime": 18.2349,
1717
+ "eval_samples_per_second": 0.877,
1718
+ "eval_steps_per_second": 0.877,
1719
+ "step": 154
1720
+ },
1721
+ {
1722
+ "epoch": 2.5306122448979593,
1723
+ "grad_norm": 0.22405166923999786,
1724
+ "learning_rate": 0.00023450960574912934,
1725
+ "loss": 0.1237,
1726
+ "step": 155
1727
+ },
1728
+ {
1729
+ "epoch": 2.546938775510204,
1730
+ "grad_norm": 0.25058048963546753,
1731
+ "learning_rate": 0.00023252743303897675,
1732
+ "loss": 0.1635,
1733
+ "step": 156
1734
+ },
1735
+ {
1736
+ "epoch": 2.546938775510204,
1737
+ "eval_loss": 0.9882242679595947,
1738
+ "eval_runtime": 18.2562,
1739
+ "eval_samples_per_second": 0.876,
1740
+ "eval_steps_per_second": 0.876,
1741
+ "step": 156
1742
+ },
1743
+ {
1744
+ "epoch": 2.563265306122449,
1745
+ "grad_norm": 0.3842501938343048,
1746
+ "learning_rate": 0.00023054197297965264,
1747
+ "loss": 0.1417,
1748
+ "step": 157
1749
+ },
1750
+ {
1751
+ "epoch": 2.5795918367346937,
1752
+ "grad_norm": 0.22574357688426971,
1753
+ "learning_rate": 0.00022855342622948976,
1754
+ "loss": 0.1221,
1755
+ "step": 158
1756
+ },
1757
+ {
1758
+ "epoch": 2.5795918367346937,
1759
+ "eval_loss": 1.0112800598144531,
1760
+ "eval_runtime": 18.2537,
1761
+ "eval_samples_per_second": 0.877,
1762
+ "eval_steps_per_second": 0.877,
1763
+ "step": 158
1764
+ },
1765
+ {
1766
+ "epoch": 2.595918367346939,
1767
+ "grad_norm": 0.22760067880153656,
1768
+ "learning_rate": 0.0002265619937587739,
1769
+ "loss": 0.1319,
1770
+ "step": 159
1771
+ },
1772
+ {
1773
+ "epoch": 2.612244897959184,
1774
+ "grad_norm": 0.25777938961982727,
1775
+ "learning_rate": 0.00022456787682943285,
1776
+ "loss": 0.149,
1777
+ "step": 160
1778
+ },
1779
+ {
1780
+ "epoch": 2.612244897959184,
1781
+ "eval_loss": 1.0162885189056396,
1782
+ "eval_runtime": 18.2574,
1783
+ "eval_samples_per_second": 0.876,
1784
+ "eval_steps_per_second": 0.876,
1785
+ "step": 160
1786
+ },
1787
+ {
1788
+ "epoch": 2.6285714285714286,
1789
+ "grad_norm": 0.23430375754833221,
1790
+ "learning_rate": 0.00022257127697469632,
1791
+ "loss": 0.1342,
1792
+ "step": 161
1793
+ },
1794
+ {
1795
+ "epoch": 2.644897959183673,
1796
+ "grad_norm": 0.25381889939308167,
1797
+ "learning_rate": 0.00022057239597872834,
1798
+ "loss": 0.1558,
1799
+ "step": 162
1800
+ },
1801
+ {
1802
+ "epoch": 2.644897959183673,
1803
+ "eval_loss": 1.0097148418426514,
1804
+ "eval_runtime": 18.2572,
1805
+ "eval_samples_per_second": 0.876,
1806
+ "eval_steps_per_second": 0.876,
1807
+ "step": 162
1808
+ },
1809
+ {
1810
+ "epoch": 2.6612244897959183,
1811
+ "grad_norm": 0.22818055748939514,
1812
+ "learning_rate": 0.0002185714358562336,
1813
+ "loss": 0.1382,
1814
+ "step": 163
1815
+ },
1816
+ {
1817
+ "epoch": 2.6775510204081634,
1818
+ "grad_norm": 0.21377477049827576,
1819
+ "learning_rate": 0.00021656859883204167,
1820
+ "loss": 0.1138,
1821
+ "step": 164
1822
+ },
1823
+ {
1824
+ "epoch": 2.6775510204081634,
1825
+ "eval_loss": 1.0100345611572266,
1826
+ "eval_runtime": 18.246,
1827
+ "eval_samples_per_second": 0.877,
1828
+ "eval_steps_per_second": 0.877,
1829
+ "step": 164
1830
+ },
1831
+ {
1832
+ "epoch": 2.693877551020408,
1833
+ "grad_norm": 0.20805473625659943,
1834
+ "learning_rate": 0.00021456408732066918,
1835
+ "loss": 0.1103,
1836
+ "step": 165
1837
+ },
1838
+ {
1839
+ "epoch": 2.710204081632653,
1840
+ "grad_norm": 0.23223794996738434,
1841
+ "learning_rate": 0.0002125581039058627,
1842
+ "loss": 0.1229,
1843
+ "step": 166
1844
+ },
1845
+ {
1846
+ "epoch": 2.710204081632653,
1847
+ "eval_loss": 1.0152215957641602,
1848
+ "eval_runtime": 18.2339,
1849
+ "eval_samples_per_second": 0.877,
1850
+ "eval_steps_per_second": 0.877,
1851
+ "step": 166
1852
+ },
1853
+ {
1854
+ "epoch": 2.726530612244898,
1855
+ "grad_norm": 0.22925834357738495,
1856
+ "learning_rate": 0.0002105508513201253,
1857
+ "loss": 0.112,
1858
+ "step": 167
1859
+ },
1860
+ {
1861
+ "epoch": 2.742857142857143,
1862
+ "grad_norm": 0.23402348160743713,
1863
+ "learning_rate": 0.00020854253242422744,
1864
+ "loss": 0.111,
1865
+ "step": 168
1866
+ },
1867
+ {
1868
+ "epoch": 2.742857142857143,
1869
+ "eval_loss": 1.0134178400039673,
1870
+ "eval_runtime": 18.2312,
1871
+ "eval_samples_per_second": 0.878,
1872
+ "eval_steps_per_second": 0.878,
1873
+ "step": 168
1874
+ },
1875
+ {
1876
+ "epoch": 2.759183673469388,
1877
+ "grad_norm": 0.21745020151138306,
1878
+ "learning_rate": 0.00020653335018670478,
1879
+ "loss": 0.1148,
1880
+ "step": 169
1881
+ },
1882
+ {
1883
+ "epoch": 2.7755102040816326,
1884
+ "grad_norm": 0.23371770977973938,
1885
+ "learning_rate": 0.00020452350766334595,
1886
+ "loss": 0.1378,
1887
+ "step": 170
1888
+ },
1889
+ {
1890
+ "epoch": 2.7755102040816326,
1891
+ "eval_loss": 1.008978247642517,
1892
+ "eval_runtime": 18.2393,
1893
+ "eval_samples_per_second": 0.877,
1894
+ "eval_steps_per_second": 0.877,
1895
+ "step": 170
1896
+ },
1897
+ {
1898
+ "epoch": 2.7918367346938773,
1899
+ "grad_norm": 0.23733730614185333,
1900
+ "learning_rate": 0.00020251320797667056,
1901
+ "loss": 0.1362,
1902
+ "step": 171
1903
+ },
1904
+ {
1905
+ "epoch": 2.8081632653061224,
1906
+ "grad_norm": 0.22156459093093872,
1907
+ "learning_rate": 0.00020050265429540082,
1908
+ "loss": 0.1197,
1909
+ "step": 172
1910
+ },
1911
+ {
1912
+ "epoch": 2.8081632653061224,
1913
+ "eval_loss": 0.996375560760498,
1914
+ "eval_runtime": 18.2572,
1915
+ "eval_samples_per_second": 0.876,
1916
+ "eval_steps_per_second": 0.876,
1917
+ "step": 172
1918
+ },
1919
+ {
1920
+ "epoch": 2.8244897959183675,
1921
+ "grad_norm": 0.21871179342269897,
1922
+ "learning_rate": 0.00019849204981392863,
1923
+ "loss": 0.1262,
1924
+ "step": 173
1925
+ },
1926
+ {
1927
+ "epoch": 2.840816326530612,
1928
+ "grad_norm": 0.2262168973684311,
1929
+ "learning_rate": 0.00019648159773178007,
1930
+ "loss": 0.1329,
1931
+ "step": 174
1932
+ },
1933
+ {
1934
+ "epoch": 2.840816326530612,
1935
+ "eval_loss": 0.9993283748626709,
1936
+ "eval_runtime": 18.2401,
1937
+ "eval_samples_per_second": 0.877,
1938
+ "eval_steps_per_second": 0.877,
1939
+ "step": 174
1940
+ },
1941
+ {
1942
+ "epoch": 2.857142857142857,
1943
+ "grad_norm": 0.24742639064788818,
1944
+ "learning_rate": 0.00019447150123307915,
1945
+ "loss": 0.1243,
1946
+ "step": 175
1947
+ },
1948
+ {
1949
+ "epoch": 2.873469387755102,
1950
+ "grad_norm": 0.21919304132461548,
1951
+ "learning_rate": 0.00019246196346601308,
1952
+ "loss": 0.1218,
1953
+ "step": 176
1954
+ },
1955
+ {
1956
+ "epoch": 2.873469387755102,
1957
+ "eval_loss": 1.0055768489837646,
1958
+ "eval_runtime": 18.2419,
1959
+ "eval_samples_per_second": 0.877,
1960
+ "eval_steps_per_second": 0.877,
1961
+ "step": 176
1962
+ },
1963
+ {
1964
+ "epoch": 2.889795918367347,
1965
+ "grad_norm": 0.21882188320159912,
1966
+ "learning_rate": 0.0001904531875223017,
1967
+ "loss": 0.1347,
1968
+ "step": 177
1969
+ },
1970
+ {
1971
+ "epoch": 2.906122448979592,
1972
+ "grad_norm": 0.24942266941070557,
1973
+ "learning_rate": 0.00018844537641667176,
1974
+ "loss": 0.1526,
1975
+ "step": 178
1976
+ },
1977
+ {
1978
+ "epoch": 2.906122448979592,
1979
+ "eval_loss": 0.9967045783996582,
1980
+ "eval_runtime": 18.2597,
1981
+ "eval_samples_per_second": 0.876,
1982
+ "eval_steps_per_second": 0.876,
1983
+ "step": 178
1984
+ },
1985
+ {
1986
+ "epoch": 2.9224489795918367,
1987
+ "grad_norm": 0.2336956411600113,
1988
+ "learning_rate": 0.0001864387330663399,
1989
+ "loss": 0.1352,
1990
+ "step": 179
1991
+ },
1992
+ {
1993
+ "epoch": 2.938775510204082,
1994
+ "grad_norm": 0.2014392614364624,
1995
+ "learning_rate": 0.0001844334602705047,
1996
+ "loss": 0.1177,
1997
+ "step": 180
1998
+ },
1999
+ {
2000
+ "epoch": 2.938775510204082,
2001
+ "eval_loss": 0.9912804365158081,
2002
+ "eval_runtime": 18.2221,
2003
+ "eval_samples_per_second": 0.878,
2004
+ "eval_steps_per_second": 0.878,
2005
+ "step": 180
2006
+ },
2007
+ {
2008
+ "epoch": 2.938775510204082,
2009
+ "eval_loss": 0.9912804365158081,
2010
+ "eval_runtime": 18.3966,
2011
+ "eval_samples_per_second": 0.87,
2012
+ "eval_steps_per_second": 0.87,
2013
+ "step": 180
2014
+ },
2015
+ {
2016
+ "epoch": 2.963265306122449,
2017
+ "grad_norm": 0.2360977977514267,
2018
+ "learning_rate": 0.00018242976068985137,
2019
+ "loss": 0.1276,
2020
+ "step": 181
2021
+ },
2022
+ {
2023
+ "epoch": 2.979591836734694,
2024
+ "grad_norm": 0.22097723186016083,
2025
+ "learning_rate": 0.0001804278368260697,
2026
+ "loss": 0.1292,
2027
+ "step": 182
2028
+ },
2029
+ {
2030
+ "epoch": 2.979591836734694,
2031
+ "eval_loss": 0.9996596574783325,
2032
+ "eval_runtime": 18.2418,
2033
+ "eval_samples_per_second": 0.877,
2034
+ "eval_steps_per_second": 0.877,
2035
+ "step": 182
2036
+ },
2037
+ {
2038
+ "epoch": 2.9959183673469387,
2039
+ "grad_norm": 0.19727876782417297,
2040
+ "learning_rate": 0.00017842789100138868,
2041
+ "loss": 0.0994,
2042
+ "step": 183
2043
+ },
2044
+ {
2045
+ "epoch": 3.012244897959184,
2046
+ "grad_norm": 0.4426736533641815,
2047
+ "learning_rate": 0.0001764301253381289,
2048
+ "loss": 0.1507,
2049
+ "step": 184
2050
+ },
2051
+ {
2052
+ "epoch": 3.012244897959184,
2053
+ "eval_loss": 1.0262768268585205,
2054
+ "eval_runtime": 18.259,
2055
+ "eval_samples_per_second": 0.876,
2056
+ "eval_steps_per_second": 0.876,
2057
+ "step": 184
2058
+ },
2059
+ {
2060
+ "epoch": 3.0285714285714285,
2061
+ "grad_norm": 0.1821659505367279,
2062
+ "learning_rate": 0.00017443474173827532,
2063
+ "loss": 0.0588,
2064
+ "step": 185
2065
+ },
2066
+ {
2067
+ "epoch": 3.0448979591836736,
2068
+ "grad_norm": 0.2281961441040039,
2069
+ "learning_rate": 0.0001724419418630724,
2070
+ "loss": 0.0765,
2071
+ "step": 186
2072
+ },
2073
+ {
2074
+ "epoch": 3.0448979591836736,
2075
+ "eval_loss": 1.0732572078704834,
2076
+ "eval_runtime": 18.2807,
2077
+ "eval_samples_per_second": 0.875,
2078
+ "eval_steps_per_second": 0.875,
2079
+ "step": 186
2080
+ },
2081
+ {
2082
+ "epoch": 3.061224489795918,
2083
+ "grad_norm": 0.19735883176326752,
2084
+ "learning_rate": 0.0001704519271126433,
2085
+ "loss": 0.0542,
2086
+ "step": 187
2087
+ },
2088
+ {
2089
+ "epoch": 3.0775510204081633,
2090
+ "grad_norm": 0.23131243884563446,
2091
+ "learning_rate": 0.0001684648986056355,
2092
+ "loss": 0.0604,
2093
+ "step": 188
2094
+ },
2095
+ {
2096
+ "epoch": 3.0775510204081633,
2097
+ "eval_loss": 1.10750150680542,
2098
+ "eval_runtime": 18.2728,
2099
+ "eval_samples_per_second": 0.876,
2100
+ "eval_steps_per_second": 0.876,
2101
+ "step": 188
2102
+ },
2103
+ {
2104
+ "epoch": 3.093877551020408,
2105
+ "grad_norm": 0.25719910860061646,
2106
+ "learning_rate": 0.0001664810571588952,
2107
+ "loss": 0.0705,
2108
+ "step": 189
2109
+ },
2110
+ {
2111
+ "epoch": 3.110204081632653,
2112
+ "grad_norm": 0.23448176681995392,
2113
+ "learning_rate": 0.00016450060326717177,
2114
+ "loss": 0.061,
2115
+ "step": 190
2116
+ },
2117
+ {
2118
+ "epoch": 3.110204081632653,
2119
+ "eval_loss": 1.0981874465942383,
2120
+ "eval_runtime": 18.2548,
2121
+ "eval_samples_per_second": 0.876,
2122
+ "eval_steps_per_second": 0.876,
2123
+ "step": 190
2124
+ },
2125
+ {
2126
+ "epoch": 3.126530612244898,
2127
+ "grad_norm": 0.2236451804637909,
2128
+ "learning_rate": 0.00016252373708285504,
2129
+ "loss": 0.0492,
2130
+ "step": 191
2131
+ },
2132
+ {
2133
+ "epoch": 3.142857142857143,
2134
+ "grad_norm": 0.22379790246486664,
2135
+ "learning_rate": 0.00016055065839574743,
2136
+ "loss": 0.0622,
2137
+ "step": 192
2138
+ },
2139
+ {
2140
+ "epoch": 3.142857142857143,
2141
+ "eval_loss": 1.0731853246688843,
2142
+ "eval_runtime": 18.2828,
2143
+ "eval_samples_per_second": 0.875,
2144
+ "eval_steps_per_second": 0.875,
2145
+ "step": 192
2146
+ },
2147
+ {
2148
+ "epoch": 3.159183673469388,
2149
+ "grad_norm": 0.23106735944747925,
2150
+ "learning_rate": 0.00015858156661287178,
2151
+ "loss": 0.0715,
2152
+ "step": 193
2153
+ },
2154
+ {
2155
+ "epoch": 3.1755102040816325,
2156
+ "grad_norm": 0.23755702376365662,
2157
+ "learning_rate": 0.00015661666073831895,
2158
+ "loss": 0.0794,
2159
+ "step": 194
2160
+ },
2161
+ {
2162
+ "epoch": 3.1755102040816325,
2163
+ "eval_loss": 1.06235671043396,
2164
+ "eval_runtime": 18.305,
2165
+ "eval_samples_per_second": 0.874,
2166
+ "eval_steps_per_second": 0.874,
2167
+ "step": 194
2168
+ },
2169
+ {
2170
+ "epoch": 3.1918367346938776,
2171
+ "grad_norm": 0.22150100767612457,
2172
+ "learning_rate": 0.0001546561393531357,
2173
+ "loss": 0.0687,
2174
+ "step": 195
2175
+ },
2176
+ {
2177
+ "epoch": 3.2081632653061223,
2178
+ "grad_norm": 0.1758776307106018,
2179
+ "learning_rate": 0.0001527002005952551,
2180
+ "loss": 0.0498,
2181
+ "step": 196
2182
+ },
2183
+ {
2184
+ "epoch": 3.2081632653061223,
2185
+ "eval_loss": 1.073830008506775,
2186
+ "eval_runtime": 18.3237,
2187
+ "eval_samples_per_second": 0.873,
2188
+ "eval_steps_per_second": 0.873,
2189
+ "step": 196
2190
+ },
2191
+ {
2192
+ "epoch": 3.2244897959183674,
2193
+ "grad_norm": 0.23125389218330383,
2194
+ "learning_rate": 0.000150749042139472,
2195
+ "loss": 0.08,
2196
+ "step": 197
2197
+ },
2198
+ {
2199
+ "epoch": 3.240816326530612,
2200
+ "grad_norm": 0.2143053263425827,
2201
+ "learning_rate": 0.00014880286117746548,
2202
+ "loss": 0.06,
2203
+ "step": 198
2204
+ },
2205
+ {
2206
+ "epoch": 3.240816326530612,
2207
+ "eval_loss": 1.1210918426513672,
2208
+ "eval_runtime": 18.3294,
2209
+ "eval_samples_per_second": 0.873,
2210
+ "eval_steps_per_second": 0.873,
2211
+ "step": 198
2212
+ },
2213
+ {
2214
+ "epoch": 3.257142857142857,
2215
+ "grad_norm": 0.20991010963916779,
2216
+ "learning_rate": 0.0001468618543978695,
2217
+ "loss": 0.0549,
2218
+ "step": 199
2219
+ },
2220
+ {
2221
+ "epoch": 3.273469387755102,
2222
+ "grad_norm": 0.21787025034427643,
2223
+ "learning_rate": 0.00014492621796639504,
2224
+ "loss": 0.0515,
2225
+ "step": 200
2226
+ },
2227
+ {
2228
+ "epoch": 3.273469387755102,
2229
+ "eval_loss": 1.15009343624115,
2230
+ "eval_runtime": 18.3182,
2231
+ "eval_samples_per_second": 0.873,
2232
+ "eval_steps_per_second": 0.873,
2233
+ "step": 200
2234
+ },
2235
+ {
2236
+ "epoch": 3.289795918367347,
2237
+ "grad_norm": 0.22523745894432068,
2238
+ "learning_rate": 0.00014299614750600478,
2239
+ "loss": 0.0499,
2240
+ "step": 201
2241
+ },
2242
+ {
2243
+ "epoch": 3.306122448979592,
2244
+ "grad_norm": 0.21396824717521667,
2245
+ "learning_rate": 0.00014107183807714275,
2246
+ "loss": 0.0484,
2247
+ "step": 202
2248
+ },
2249
+ {
2250
+ "epoch": 3.306122448979592,
2251
+ "eval_loss": 1.1507196426391602,
2252
+ "eval_runtime": 18.3345,
2253
+ "eval_samples_per_second": 0.873,
2254
+ "eval_steps_per_second": 0.873,
2255
+ "step": 202
2256
+ },
2257
+ {
2258
+ "epoch": 3.3224489795918366,
2259
+ "grad_norm": 0.23024530708789825,
2260
+ "learning_rate": 0.00013915348415802036,
2261
+ "loss": 0.0647,
2262
+ "step": 203
2263
+ },
2264
+ {
2265
+ "epoch": 3.3387755102040817,
2266
+ "grad_norm": 0.20833072066307068,
2267
+ "learning_rate": 0.0001372412796249625,
2268
+ "loss": 0.0576,
2269
+ "step": 204
2270
+ },
2271
+ {
2272
+ "epoch": 3.3387755102040817,
2273
+ "eval_loss": 1.1334972381591797,
2274
+ "eval_runtime": 18.3296,
2275
+ "eval_samples_per_second": 0.873,
2276
+ "eval_steps_per_second": 0.873,
2277
+ "step": 204
2278
+ },
2279
+ {
2280
+ "epoch": 3.3551020408163263,
2281
+ "grad_norm": 0.2296619713306427,
2282
+ "learning_rate": 0.00013533541773281274,
2283
+ "loss": 0.0843,
2284
+ "step": 205
2285
+ },
2286
+ {
2287
+ "epoch": 3.3714285714285714,
2288
+ "grad_norm": 0.1846872717142105,
2289
+ "learning_rate": 0.0001334360910954027,
2290
+ "loss": 0.0562,
2291
+ "step": 206
2292
+ },
2293
+ {
2294
+ "epoch": 3.3714285714285714,
2295
+ "eval_loss": 1.1273655891418457,
2296
+ "eval_runtime": 18.3216,
2297
+ "eval_samples_per_second": 0.873,
2298
+ "eval_steps_per_second": 0.873,
2299
+ "step": 206
2300
+ },
2301
+ {
2302
+ "epoch": 3.387755102040816,
2303
+ "grad_norm": 0.1895626038312912,
2304
+ "learning_rate": 0.00013154349166608577,
2305
+ "loss": 0.0556,
2306
+ "step": 207
2307
+ },
2308
+ {
2309
+ "epoch": 3.404081632653061,
2310
+ "grad_norm": 0.34628579020500183,
2311
+ "learning_rate": 0.00012965781071833752,
2312
+ "loss": 0.1337,
2313
+ "step": 208
2314
+ },
2315
+ {
2316
+ "epoch": 3.404081632653061,
2317
+ "eval_loss": 1.1414172649383545,
2318
+ "eval_runtime": 18.3347,
2319
+ "eval_samples_per_second": 0.873,
2320
+ "eval_steps_per_second": 0.873,
2321
+ "step": 208
2322
+ },
2323
+ {
2324
+ "epoch": 3.4204081632653063,
2325
+ "grad_norm": 0.20633243024349213,
2326
+ "learning_rate": 0.0001277792388264245,
2327
+ "loss": 0.0627,
2328
+ "step": 209
2329
+ },
2330
+ {
2331
+ "epoch": 3.436734693877551,
2332
+ "grad_norm": 0.19947534799575806,
2333
+ "learning_rate": 0.00012590796584614484,
2334
+ "loss": 0.0478,
2335
+ "step": 210
2336
+ },
2337
+ {
2338
+ "epoch": 3.436734693877551,
2339
+ "eval_loss": 1.1656532287597656,
2340
+ "eval_runtime": 18.3137,
2341
+ "eval_samples_per_second": 0.874,
2342
+ "eval_steps_per_second": 0.874,
2343
+ "step": 210
2344
+ },
2345
+ {
2346
+ "epoch": 3.453061224489796,
2347
+ "grad_norm": 0.21546797454357147,
2348
+ "learning_rate": 0.0001240441808956398,
2349
+ "loss": 0.0672,
2350
+ "step": 211
2351
+ },
2352
+ {
2353
+ "epoch": 3.4693877551020407,
2354
+ "grad_norm": 0.2232857644557953,
2355
+ "learning_rate": 0.00012218807233628138,
2356
+ "loss": 0.0597,
2357
+ "step": 212
2358
+ },
2359
+ {
2360
+ "epoch": 3.4693877551020407,
2361
+ "eval_loss": 1.1744612455368042,
2362
+ "eval_runtime": 18.3397,
2363
+ "eval_samples_per_second": 0.872,
2364
+ "eval_steps_per_second": 0.872,
2365
+ "step": 212
2366
+ },
2367
+ {
2368
+ "epoch": 3.4857142857142858,
2369
+ "grad_norm": 0.23030999302864075,
2370
+ "learning_rate": 0.00012033982775363548,
2371
+ "loss": 0.0586,
2372
+ "step": 213
2373
+ },
2374
+ {
2375
+ "epoch": 3.502040816326531,
2376
+ "grad_norm": 0.21055705845355988,
2377
+ "learning_rate": 0.00011849963393850383,
2378
+ "loss": 0.0618,
2379
+ "step": 214
2380
+ },
2381
+ {
2382
+ "epoch": 3.502040816326531,
2383
+ "eval_loss": 1.1754231452941895,
2384
+ "eval_runtime": 18.3637,
2385
+ "eval_samples_per_second": 0.871,
2386
+ "eval_steps_per_second": 0.871,
2387
+ "step": 214
2388
+ },
2389
+ {
2390
+ "epoch": 3.5183673469387755,
2391
+ "grad_norm": 0.18197622895240784,
2392
+ "learning_rate": 0.00011666767686804641,
2393
+ "loss": 0.0475,
2394
+ "step": 215
2395
+ },
2396
+ {
2397
+ "epoch": 3.53469387755102,
2398
+ "grad_norm": 0.24238142371177673,
2399
+ "learning_rate": 0.00011484414168698547,
2400
+ "loss": 0.0686,
2401
+ "step": 216
2402
+ },
2403
+ {
2404
+ "epoch": 3.53469387755102,
2405
+ "eval_loss": 1.1673252582550049,
2406
+ "eval_runtime": 18.3403,
2407
+ "eval_samples_per_second": 0.872,
2408
+ "eval_steps_per_second": 0.872,
2409
+ "step": 216
2410
+ },
2411
+ {
2412
+ "epoch": 3.5510204081632653,
2413
+ "grad_norm": 0.2360972762107849,
2414
+ "learning_rate": 0.00011302921268889432,
2415
+ "loss": 0.0738,
2416
+ "step": 217
2417
+ },
2418
+ {
2419
+ "epoch": 3.5673469387755103,
2420
+ "grad_norm": 0.2011600285768509,
2421
+ "learning_rate": 0.00011122307329757206,
2422
+ "loss": 0.0501,
2423
+ "step": 218
2424
+ },
2425
+ {
2426
+ "epoch": 3.5673469387755103,
2427
+ "eval_loss": 1.1578516960144043,
2428
+ "eval_runtime": 18.3646,
2429
+ "eval_samples_per_second": 0.871,
2430
+ "eval_steps_per_second": 0.871,
2431
+ "step": 218
2432
+ },
2433
+ {
2434
+ "epoch": 3.583673469387755,
2435
+ "grad_norm": 0.22133193910121918,
2436
+ "learning_rate": 0.00010942590604850553,
2437
+ "loss": 0.0662,
2438
+ "step": 219
2439
+ },
2440
+ {
2441
+ "epoch": 3.6,
2442
+ "grad_norm": 0.19864347577095032,
2443
+ "learning_rate": 0.0001076378925704221,
2444
+ "loss": 0.0525,
2445
+ "step": 220
2446
+ },
2447
+ {
2448
+ "epoch": 3.6,
2449
+ "eval_loss": 1.147334337234497,
2450
+ "eval_runtime": 18.3364,
2451
+ "eval_samples_per_second": 0.873,
2452
+ "eval_steps_per_second": 0.873,
2453
+ "step": 220
2454
+ },
2455
+ {
2456
+ "epoch": 3.6163265306122447,
2457
+ "grad_norm": 0.1864493042230606,
2458
+ "learning_rate": 0.0001058592135669335,
2459
+ "loss": 0.0584,
2460
+ "step": 221
2461
+ },
2462
+ {
2463
+ "epoch": 3.63265306122449,
2464
+ "grad_norm": 0.1753772795200348,
2465
+ "learning_rate": 0.00010409004879827282,
2466
+ "loss": 0.0508,
2467
+ "step": 222
2468
+ },
2469
+ {
2470
+ "epoch": 3.63265306122449,
2471
+ "eval_loss": 1.1439639329910278,
2472
+ "eval_runtime": 18.3232,
2473
+ "eval_samples_per_second": 0.873,
2474
+ "eval_steps_per_second": 0.873,
2475
+ "step": 222
2476
+ },
2477
+ {
2478
+ "epoch": 3.648979591836735,
2479
+ "grad_norm": 0.18084004521369934,
2480
+ "learning_rate": 0.00010233057706312767,
2481
+ "loss": 0.0486,
2482
+ "step": 223
2483
+ },
2484
+ {
2485
+ "epoch": 3.6653061224489796,
2486
+ "grad_norm": 0.19728556275367737,
2487
+ "learning_rate": 0.00010058097618056992,
2488
+ "loss": 0.0545,
2489
+ "step": 224
2490
+ },
2491
+ {
2492
+ "epoch": 3.6653061224489796,
2493
+ "eval_loss": 1.1501585245132446,
2494
+ "eval_runtime": 18.2988,
2495
+ "eval_samples_per_second": 0.874,
2496
+ "eval_steps_per_second": 0.874,
2497
+ "step": 224
2498
+ },
2499
+ {
2500
+ "epoch": 3.6816326530612242,
2501
+ "grad_norm": 0.22434309124946594,
2502
+ "learning_rate": 9.88414229720843e-05,
2503
+ "loss": 0.0502,
2504
+ "step": 225
2505
+ },
2506
+ {
2507
+ "epoch": 3.6979591836734693,
2508
+ "grad_norm": 0.20542308688163757,
2509
+ "learning_rate": 9.711209324369869e-05,
2510
+ "loss": 0.0513,
2511
+ "step": 226
2512
+ },
2513
+ {
2514
+ "epoch": 3.6979591836734693,
2515
+ "eval_loss": 1.160825490951538,
2516
+ "eval_runtime": 18.2895,
2517
+ "eval_samples_per_second": 0.875,
2518
+ "eval_steps_per_second": 0.875,
2519
+ "step": 226
2520
+ },
2521
+ {
2522
+ "epoch": 3.7142857142857144,
2523
+ "grad_norm": 0.1923072785139084,
2524
+ "learning_rate": 9.539316176821638e-05,
2525
+ "loss": 0.0495,
2526
+ "step": 227
2527
+ },
2528
+ {
2529
+ "epoch": 3.730612244897959,
2530
+ "grad_norm": 0.22612810134887695,
2531
+ "learning_rate": 9.368480226755238e-05,
2532
+ "loss": 0.0678,
2533
+ "step": 228
2534
+ },
2535
+ {
2536
+ "epoch": 3.730612244897959,
2537
+ "eval_loss": 1.167827844619751,
2538
+ "eval_runtime": 18.2707,
2539
+ "eval_samples_per_second": 0.876,
2540
+ "eval_steps_per_second": 0.876,
2541
+ "step": 228
2542
+ },
2543
+ {
2544
+ "epoch": 3.746938775510204,
2545
+ "grad_norm": 0.20918408036231995,
2546
+ "learning_rate": 9.198718739517685e-05,
2547
+ "loss": 0.0584,
2548
+ "step": 229
2549
+ },
2550
+ {
2551
+ "epoch": 3.763265306122449,
2552
+ "grad_norm": 0.20327749848365784,
2553
+ "learning_rate": 9.030048871866599e-05,
2554
+ "loss": 0.064,
2555
+ "step": 230
2556
+ },
2557
+ {
2558
+ "epoch": 3.763265306122449,
2559
+ "eval_loss": 1.1593577861785889,
2560
+ "eval_runtime": 18.2836,
2561
+ "eval_samples_per_second": 0.875,
2562
+ "eval_steps_per_second": 0.875,
2563
+ "step": 230
2564
+ },
2565
+ {
2566
+ "epoch": 3.779591836734694,
2567
+ "grad_norm": 0.2150719165802002,
2568
+ "learning_rate": 8.862487670236248e-05,
2569
+ "loss": 0.0649,
2570
+ "step": 231
2571
+ },
2572
+ {
2573
+ "epoch": 3.795918367346939,
2574
+ "grad_norm": 0.2021542638540268,
2575
+ "learning_rate": 8.696052069014804e-05,
2576
+ "loss": 0.0578,
2577
+ "step": 232
2578
+ },
2579
+ {
2580
+ "epoch": 3.795918367346939,
2581
+ "eval_loss": 1.1511321067810059,
2582
+ "eval_runtime": 18.2561,
2583
+ "eval_samples_per_second": 0.876,
2584
+ "eval_steps_per_second": 0.876,
2585
+ "step": 232
2586
+ },
2587
+ {
2588
+ "epoch": 3.8122448979591836,
2589
+ "grad_norm": 0.18323124945163727,
2590
+ "learning_rate": 8.53075888883289e-05,
2591
+ "loss": 0.0462,
2592
+ "step": 233
2593
+ },
2594
+ {
2595
+ "epoch": 3.8285714285714287,
2596
+ "grad_norm": 0.20034129917621613,
2597
+ "learning_rate": 8.366624834863585e-05,
2598
+ "loss": 0.0548,
2599
+ "step": 234
2600
+ },
2601
+ {
2602
+ "epoch": 3.8285714285714287,
2603
+ "eval_loss": 1.1508455276489258,
2604
+ "eval_runtime": 18.2577,
2605
+ "eval_samples_per_second": 0.876,
2606
+ "eval_steps_per_second": 0.876,
2607
+ "step": 234
2608
+ },
2609
+ {
2610
+ "epoch": 3.8448979591836734,
2611
+ "grad_norm": 0.2235688865184784,
2612
+ "learning_rate": 8.203666495134159e-05,
2613
+ "loss": 0.0642,
2614
+ "step": 235
2615
+ },
2616
+ {
2617
+ "epoch": 3.8612244897959185,
2618
+ "grad_norm": 0.22254431247711182,
2619
+ "learning_rate": 8.04190033884963e-05,
2620
+ "loss": 0.0671,
2621
+ "step": 236
2622
+ },
2623
+ {
2624
+ "epoch": 3.8612244897959185,
2625
+ "eval_loss": 1.1543577909469604,
2626
+ "eval_runtime": 18.2697,
2627
+ "eval_samples_per_second": 0.876,
2628
+ "eval_steps_per_second": 0.876,
2629
+ "step": 236
2630
+ },
2631
+ {
2632
+ "epoch": 3.877551020408163,
2633
+ "grad_norm": 0.18185441195964813,
2634
+ "learning_rate": 7.881342714728275e-05,
2635
+ "loss": 0.0556,
2636
+ "step": 237
2637
+ },
2638
+ {
2639
+ "epoch": 3.8938775510204082,
2640
+ "grad_norm": 0.19241996109485626,
2641
+ "learning_rate": 7.722009849349447e-05,
2642
+ "loss": 0.0477,
2643
+ "step": 238
2644
+ },
2645
+ {
2646
+ "epoch": 3.8938775510204082,
2647
+ "eval_loss": 1.1588821411132812,
2648
+ "eval_runtime": 18.2702,
2649
+ "eval_samples_per_second": 0.876,
2650
+ "eval_steps_per_second": 0.876,
2651
+ "step": 238
2652
+ },
2653
+ {
2654
+ "epoch": 3.910204081632653,
2655
+ "grad_norm": 0.2237924337387085,
2656
+ "learning_rate": 7.563917845513577e-05,
2657
+ "loss": 0.0617,
2658
+ "step": 239
2659
+ },
2660
+ {
2661
+ "epoch": 3.926530612244898,
2662
+ "grad_norm": 0.2120658904314041,
2663
+ "learning_rate": 7.407082680614799e-05,
2664
+ "loss": 0.0533,
2665
+ "step": 240
2666
+ },
2667
+ {
2668
+ "epoch": 3.926530612244898,
2669
+ "eval_loss": 1.158017635345459,
2670
+ "eval_runtime": 18.2939,
2671
+ "eval_samples_per_second": 0.875,
2672
+ "eval_steps_per_second": 0.875,
2673
+ "step": 240
2674
+ }
2675
+ ],
2676
+ "logging_steps": 1,
2677
+ "max_steps": 305,
2678
+ "num_input_tokens_seen": 0,
2679
+ "num_train_epochs": 5,
2680
+ "save_steps": 30,
2681
+ "stateful_callbacks": {
2682
+ "TrainerControl": {
2683
+ "args": {
2684
+ "should_epoch_stop": false,
2685
+ "should_evaluate": false,
2686
+ "should_log": false,
2687
+ "should_save": true,
2688
+ "should_training_stop": false
2689
+ },
2690
+ "attributes": {}
2691
+ }
2692
+ },
2693
+ "total_flos": 2.8990937961362534e+18,
2694
+ "train_batch_size": 1,
2695
+ "trial_name": null,
2696
+ "trial_params": null
2697
+ }
checkpoints/checkpoint-240/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5208f4e9c07bb6bd2f0bc574a52273bdf74ca404d495a5bf559488089674f2f5
3
+ size 5624
checkpoints/checkpoint-300/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoints/checkpoint-300/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "gate_proj",
28
+ "v_proj",
29
+ "q_proj",
30
+ "down_proj",
31
+ "up_proj",
32
+ "o_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints/checkpoint-300/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84ceedc535ec016bab8a1b1e772f1421f7e0742e5b4da801f52e2157e82374ec
3
+ size 739321784
checkpoints/checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00520aad3349bec9751fea73edd6203fffab99de4f9c47a40415accc217d7c77
3
+ size 377514802
checkpoints/checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1e4d0fb06f43088fdaf67dfddf73d6ddc58e4ecb4647d4c0c8c693bda0afbfb
3
+ size 14244
checkpoints/checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5e276cc1df9beb86a4aca85c7c51fce85a96007c7e7a6a22ef913f2618ef09a
3
+ size 1064
checkpoints/checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,1026 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>",
6
+ "[INST]",
7
+ "[/INST]",
8
+ "[AVAILABLE_TOOLS]",
9
+ "[/AVAILABLE_TOOLS]",
10
+ "[TOOL_RESULTS]",
11
+ "[/TOOL_RESULTS]",
12
+ "[TOOL_CALLS]",
13
+ "[IMG]",
14
+ "<pad>",
15
+ "[IMG_BREAK]",
16
+ "[IMG_END]",
17
+ "[PREFIX]",
18
+ "[MIDDLE]",
19
+ "[SUFFIX]",
20
+ "[SYSTEM_PROMPT]",
21
+ "[/SYSTEM_PROMPT]",
22
+ "[TOOL_CONTENT]",
23
+ "<SPECIAL_20>",
24
+ "<SPECIAL_21>",
25
+ "<SPECIAL_22>",
26
+ "<SPECIAL_23>",
27
+ "<SPECIAL_24>",
28
+ "<SPECIAL_25>",
29
+ "<SPECIAL_26>",
30
+ "<SPECIAL_27>",
31
+ "<SPECIAL_28>",
32
+ "<SPECIAL_29>",
33
+ "<SPECIAL_30>",
34
+ "<SPECIAL_31>",
35
+ "<SPECIAL_32>",
36
+ "<SPECIAL_33>",
37
+ "<SPECIAL_34>",
38
+ "<SPECIAL_35>",
39
+ "<SPECIAL_36>",
40
+ "<SPECIAL_37>",
41
+ "<SPECIAL_38>",
42
+ "<SPECIAL_39>",
43
+ "<SPECIAL_40>",
44
+ "<SPECIAL_41>",
45
+ "<SPECIAL_42>",
46
+ "<SPECIAL_43>",
47
+ "<SPECIAL_44>",
48
+ "<SPECIAL_45>",
49
+ "<SPECIAL_46>",
50
+ "<SPECIAL_47>",
51
+ "<SPECIAL_48>",
52
+ "<SPECIAL_49>",
53
+ "<SPECIAL_50>",
54
+ "<SPECIAL_51>",
55
+ "<SPECIAL_52>",
56
+ "<SPECIAL_53>",
57
+ "<SPECIAL_54>",
58
+ "<SPECIAL_55>",
59
+ "<SPECIAL_56>",
60
+ "<SPECIAL_57>",
61
+ "<SPECIAL_58>",
62
+ "<SPECIAL_59>",
63
+ "<SPECIAL_60>",
64
+ "<SPECIAL_61>",
65
+ "<SPECIAL_62>",
66
+ "<SPECIAL_63>",
67
+ "<SPECIAL_64>",
68
+ "<SPECIAL_65>",
69
+ "<SPECIAL_66>",
70
+ "<SPECIAL_67>",
71
+ "<SPECIAL_68>",
72
+ "<SPECIAL_69>",
73
+ "<SPECIAL_70>",
74
+ "<SPECIAL_71>",
75
+ "<SPECIAL_72>",
76
+ "<SPECIAL_73>",
77
+ "<SPECIAL_74>",
78
+ "<SPECIAL_75>",
79
+ "<SPECIAL_76>",
80
+ "<SPECIAL_77>",
81
+ "<SPECIAL_78>",
82
+ "<SPECIAL_79>",
83
+ "<SPECIAL_80>",
84
+ "<SPECIAL_81>",
85
+ "<SPECIAL_82>",
86
+ "<SPECIAL_83>",
87
+ "<SPECIAL_84>",
88
+ "<SPECIAL_85>",
89
+ "<SPECIAL_86>",
90
+ "<SPECIAL_87>",
91
+ "<SPECIAL_88>",
92
+ "<SPECIAL_89>",
93
+ "<SPECIAL_90>",
94
+ "<SPECIAL_91>",
95
+ "<SPECIAL_92>",
96
+ "<SPECIAL_93>",
97
+ "<SPECIAL_94>",
98
+ "<SPECIAL_95>",
99
+ "<SPECIAL_96>",
100
+ "<SPECIAL_97>",
101
+ "<SPECIAL_98>",
102
+ "<SPECIAL_99>",
103
+ "<SPECIAL_100>",
104
+ "<SPECIAL_101>",
105
+ "<SPECIAL_102>",
106
+ "<SPECIAL_103>",
107
+ "<SPECIAL_104>",
108
+ "<SPECIAL_105>",
109
+ "<SPECIAL_106>",
110
+ "<SPECIAL_107>",
111
+ "<SPECIAL_108>",
112
+ "<SPECIAL_109>",
113
+ "<SPECIAL_110>",
114
+ "<SPECIAL_111>",
115
+ "<SPECIAL_112>",
116
+ "<SPECIAL_113>",
117
+ "<SPECIAL_114>",
118
+ "<SPECIAL_115>",
119
+ "<SPECIAL_116>",
120
+ "<SPECIAL_117>",
121
+ "<SPECIAL_118>",
122
+ "<SPECIAL_119>",
123
+ "<SPECIAL_120>",
124
+ "<SPECIAL_121>",
125
+ "<SPECIAL_122>",
126
+ "<SPECIAL_123>",
127
+ "<SPECIAL_124>",
128
+ "<SPECIAL_125>",
129
+ "<SPECIAL_126>",
130
+ "<SPECIAL_127>",
131
+ "<SPECIAL_128>",
132
+ "<SPECIAL_129>",
133
+ "<SPECIAL_130>",
134
+ "<SPECIAL_131>",
135
+ "<SPECIAL_132>",
136
+ "<SPECIAL_133>",
137
+ "<SPECIAL_134>",
138
+ "<SPECIAL_135>",
139
+ "<SPECIAL_136>",
140
+ "<SPECIAL_137>",
141
+ "<SPECIAL_138>",
142
+ "<SPECIAL_139>",
143
+ "<SPECIAL_140>",
144
+ "<SPECIAL_141>",
145
+ "<SPECIAL_142>",
146
+ "<SPECIAL_143>",
147
+ "<SPECIAL_144>",
148
+ "<SPECIAL_145>",
149
+ "<SPECIAL_146>",
150
+ "<SPECIAL_147>",
151
+ "<SPECIAL_148>",
152
+ "<SPECIAL_149>",
153
+ "<SPECIAL_150>",
154
+ "<SPECIAL_151>",
155
+ "<SPECIAL_152>",
156
+ "<SPECIAL_153>",
157
+ "<SPECIAL_154>",
158
+ "<SPECIAL_155>",
159
+ "<SPECIAL_156>",
160
+ "<SPECIAL_157>",
161
+ "<SPECIAL_158>",
162
+ "<SPECIAL_159>",
163
+ "<SPECIAL_160>",
164
+ "<SPECIAL_161>",
165
+ "<SPECIAL_162>",
166
+ "<SPECIAL_163>",
167
+ "<SPECIAL_164>",
168
+ "<SPECIAL_165>",
169
+ "<SPECIAL_166>",
170
+ "<SPECIAL_167>",
171
+ "<SPECIAL_168>",
172
+ "<SPECIAL_169>",
173
+ "<SPECIAL_170>",
174
+ "<SPECIAL_171>",
175
+ "<SPECIAL_172>",
176
+ "<SPECIAL_173>",
177
+ "<SPECIAL_174>",
178
+ "<SPECIAL_175>",
179
+ "<SPECIAL_176>",
180
+ "<SPECIAL_177>",
181
+ "<SPECIAL_178>",
182
+ "<SPECIAL_179>",
183
+ "<SPECIAL_180>",
184
+ "<SPECIAL_181>",
185
+ "<SPECIAL_182>",
186
+ "<SPECIAL_183>",
187
+ "<SPECIAL_184>",
188
+ "<SPECIAL_185>",
189
+ "<SPECIAL_186>",
190
+ "<SPECIAL_187>",
191
+ "<SPECIAL_188>",
192
+ "<SPECIAL_189>",
193
+ "<SPECIAL_190>",
194
+ "<SPECIAL_191>",
195
+ "<SPECIAL_192>",
196
+ "<SPECIAL_193>",
197
+ "<SPECIAL_194>",
198
+ "<SPECIAL_195>",
199
+ "<SPECIAL_196>",
200
+ "<SPECIAL_197>",
201
+ "<SPECIAL_198>",
202
+ "<SPECIAL_199>",
203
+ "<SPECIAL_200>",
204
+ "<SPECIAL_201>",
205
+ "<SPECIAL_202>",
206
+ "<SPECIAL_203>",
207
+ "<SPECIAL_204>",
208
+ "<SPECIAL_205>",
209
+ "<SPECIAL_206>",
210
+ "<SPECIAL_207>",
211
+ "<SPECIAL_208>",
212
+ "<SPECIAL_209>",
213
+ "<SPECIAL_210>",
214
+ "<SPECIAL_211>",
215
+ "<SPECIAL_212>",
216
+ "<SPECIAL_213>",
217
+ "<SPECIAL_214>",
218
+ "<SPECIAL_215>",
219
+ "<SPECIAL_216>",
220
+ "<SPECIAL_217>",
221
+ "<SPECIAL_218>",
222
+ "<SPECIAL_219>",
223
+ "<SPECIAL_220>",
224
+ "<SPECIAL_221>",
225
+ "<SPECIAL_222>",
226
+ "<SPECIAL_223>",
227
+ "<SPECIAL_224>",
228
+ "<SPECIAL_225>",
229
+ "<SPECIAL_226>",
230
+ "<SPECIAL_227>",
231
+ "<SPECIAL_228>",
232
+ "<SPECIAL_229>",
233
+ "<SPECIAL_230>",
234
+ "<SPECIAL_231>",
235
+ "<SPECIAL_232>",
236
+ "<SPECIAL_233>",
237
+ "<SPECIAL_234>",
238
+ "<SPECIAL_235>",
239
+ "<SPECIAL_236>",
240
+ "<SPECIAL_237>",
241
+ "<SPECIAL_238>",
242
+ "<SPECIAL_239>",
243
+ "<SPECIAL_240>",
244
+ "<SPECIAL_241>",
245
+ "<SPECIAL_242>",
246
+ "<SPECIAL_243>",
247
+ "<SPECIAL_244>",
248
+ "<SPECIAL_245>",
249
+ "<SPECIAL_246>",
250
+ "<SPECIAL_247>",
251
+ "<SPECIAL_248>",
252
+ "<SPECIAL_249>",
253
+ "<SPECIAL_250>",
254
+ "<SPECIAL_251>",
255
+ "<SPECIAL_252>",
256
+ "<SPECIAL_253>",
257
+ "<SPECIAL_254>",
258
+ "<SPECIAL_255>",
259
+ "<SPECIAL_256>",
260
+ "<SPECIAL_257>",
261
+ "<SPECIAL_258>",
262
+ "<SPECIAL_259>",
263
+ "<SPECIAL_260>",
264
+ "<SPECIAL_261>",
265
+ "<SPECIAL_262>",
266
+ "<SPECIAL_263>",
267
+ "<SPECIAL_264>",
268
+ "<SPECIAL_265>",
269
+ "<SPECIAL_266>",
270
+ "<SPECIAL_267>",
271
+ "<SPECIAL_268>",
272
+ "<SPECIAL_269>",
273
+ "<SPECIAL_270>",
274
+ "<SPECIAL_271>",
275
+ "<SPECIAL_272>",
276
+ "<SPECIAL_273>",
277
+ "<SPECIAL_274>",
278
+ "<SPECIAL_275>",
279
+ "<SPECIAL_276>",
280
+ "<SPECIAL_277>",
281
+ "<SPECIAL_278>",
282
+ "<SPECIAL_279>",
283
+ "<SPECIAL_280>",
284
+ "<SPECIAL_281>",
285
+ "<SPECIAL_282>",
286
+ "<SPECIAL_283>",
287
+ "<SPECIAL_284>",
288
+ "<SPECIAL_285>",
289
+ "<SPECIAL_286>",
290
+ "<SPECIAL_287>",
291
+ "<SPECIAL_288>",
292
+ "<SPECIAL_289>",
293
+ "<SPECIAL_290>",
294
+ "<SPECIAL_291>",
295
+ "<SPECIAL_292>",
296
+ "<SPECIAL_293>",
297
+ "<SPECIAL_294>",
298
+ "<SPECIAL_295>",
299
+ "<SPECIAL_296>",
300
+ "<SPECIAL_297>",
301
+ "<SPECIAL_298>",
302
+ "<SPECIAL_299>",
303
+ "<SPECIAL_300>",
304
+ "<SPECIAL_301>",
305
+ "<SPECIAL_302>",
306
+ "<SPECIAL_303>",
307
+ "<SPECIAL_304>",
308
+ "<SPECIAL_305>",
309
+ "<SPECIAL_306>",
310
+ "<SPECIAL_307>",
311
+ "<SPECIAL_308>",
312
+ "<SPECIAL_309>",
313
+ "<SPECIAL_310>",
314
+ "<SPECIAL_311>",
315
+ "<SPECIAL_312>",
316
+ "<SPECIAL_313>",
317
+ "<SPECIAL_314>",
318
+ "<SPECIAL_315>",
319
+ "<SPECIAL_316>",
320
+ "<SPECIAL_317>",
321
+ "<SPECIAL_318>",
322
+ "<SPECIAL_319>",
323
+ "<SPECIAL_320>",
324
+ "<SPECIAL_321>",
325
+ "<SPECIAL_322>",
326
+ "<SPECIAL_323>",
327
+ "<SPECIAL_324>",
328
+ "<SPECIAL_325>",
329
+ "<SPECIAL_326>",
330
+ "<SPECIAL_327>",
331
+ "<SPECIAL_328>",
332
+ "<SPECIAL_329>",
333
+ "<SPECIAL_330>",
334
+ "<SPECIAL_331>",
335
+ "<SPECIAL_332>",
336
+ "<SPECIAL_333>",
337
+ "<SPECIAL_334>",
338
+ "<SPECIAL_335>",
339
+ "<SPECIAL_336>",
340
+ "<SPECIAL_337>",
341
+ "<SPECIAL_338>",
342
+ "<SPECIAL_339>",
343
+ "<SPECIAL_340>",
344
+ "<SPECIAL_341>",
345
+ "<SPECIAL_342>",
346
+ "<SPECIAL_343>",
347
+ "<SPECIAL_344>",
348
+ "<SPECIAL_345>",
349
+ "<SPECIAL_346>",
350
+ "<SPECIAL_347>",
351
+ "<SPECIAL_348>",
352
+ "<SPECIAL_349>",
353
+ "<SPECIAL_350>",
354
+ "<SPECIAL_351>",
355
+ "<SPECIAL_352>",
356
+ "<SPECIAL_353>",
357
+ "<SPECIAL_354>",
358
+ "<SPECIAL_355>",
359
+ "<SPECIAL_356>",
360
+ "<SPECIAL_357>",
361
+ "<SPECIAL_358>",
362
+ "<SPECIAL_359>",
363
+ "<SPECIAL_360>",
364
+ "<SPECIAL_361>",
365
+ "<SPECIAL_362>",
366
+ "<SPECIAL_363>",
367
+ "<SPECIAL_364>",
368
+ "<SPECIAL_365>",
369
+ "<SPECIAL_366>",
370
+ "<SPECIAL_367>",
371
+ "<SPECIAL_368>",
372
+ "<SPECIAL_369>",
373
+ "<SPECIAL_370>",
374
+ "<SPECIAL_371>",
375
+ "<SPECIAL_372>",
376
+ "<SPECIAL_373>",
377
+ "<SPECIAL_374>",
378
+ "<SPECIAL_375>",
379
+ "<SPECIAL_376>",
380
+ "<SPECIAL_377>",
381
+ "<SPECIAL_378>",
382
+ "<SPECIAL_379>",
383
+ "<SPECIAL_380>",
384
+ "<SPECIAL_381>",
385
+ "<SPECIAL_382>",
386
+ "<SPECIAL_383>",
387
+ "<SPECIAL_384>",
388
+ "<SPECIAL_385>",
389
+ "<SPECIAL_386>",
390
+ "<SPECIAL_387>",
391
+ "<SPECIAL_388>",
392
+ "<SPECIAL_389>",
393
+ "<SPECIAL_390>",
394
+ "<SPECIAL_391>",
395
+ "<SPECIAL_392>",
396
+ "<SPECIAL_393>",
397
+ "<SPECIAL_394>",
398
+ "<SPECIAL_395>",
399
+ "<SPECIAL_396>",
400
+ "<SPECIAL_397>",
401
+ "<SPECIAL_398>",
402
+ "<SPECIAL_399>",
403
+ "<SPECIAL_400>",
404
+ "<SPECIAL_401>",
405
+ "<SPECIAL_402>",
406
+ "<SPECIAL_403>",
407
+ "<SPECIAL_404>",
408
+ "<SPECIAL_405>",
409
+ "<SPECIAL_406>",
410
+ "<SPECIAL_407>",
411
+ "<SPECIAL_408>",
412
+ "<SPECIAL_409>",
413
+ "<SPECIAL_410>",
414
+ "<SPECIAL_411>",
415
+ "<SPECIAL_412>",
416
+ "<SPECIAL_413>",
417
+ "<SPECIAL_414>",
418
+ "<SPECIAL_415>",
419
+ "<SPECIAL_416>",
420
+ "<SPECIAL_417>",
421
+ "<SPECIAL_418>",
422
+ "<SPECIAL_419>",
423
+ "<SPECIAL_420>",
424
+ "<SPECIAL_421>",
425
+ "<SPECIAL_422>",
426
+ "<SPECIAL_423>",
427
+ "<SPECIAL_424>",
428
+ "<SPECIAL_425>",
429
+ "<SPECIAL_426>",
430
+ "<SPECIAL_427>",
431
+ "<SPECIAL_428>",
432
+ "<SPECIAL_429>",
433
+ "<SPECIAL_430>",
434
+ "<SPECIAL_431>",
435
+ "<SPECIAL_432>",
436
+ "<SPECIAL_433>",
437
+ "<SPECIAL_434>",
438
+ "<SPECIAL_435>",
439
+ "<SPECIAL_436>",
440
+ "<SPECIAL_437>",
441
+ "<SPECIAL_438>",
442
+ "<SPECIAL_439>",
443
+ "<SPECIAL_440>",
444
+ "<SPECIAL_441>",
445
+ "<SPECIAL_442>",
446
+ "<SPECIAL_443>",
447
+ "<SPECIAL_444>",
448
+ "<SPECIAL_445>",
449
+ "<SPECIAL_446>",
450
+ "<SPECIAL_447>",
451
+ "<SPECIAL_448>",
452
+ "<SPECIAL_449>",
453
+ "<SPECIAL_450>",
454
+ "<SPECIAL_451>",
455
+ "<SPECIAL_452>",
456
+ "<SPECIAL_453>",
457
+ "<SPECIAL_454>",
458
+ "<SPECIAL_455>",
459
+ "<SPECIAL_456>",
460
+ "<SPECIAL_457>",
461
+ "<SPECIAL_458>",
462
+ "<SPECIAL_459>",
463
+ "<SPECIAL_460>",
464
+ "<SPECIAL_461>",
465
+ "<SPECIAL_462>",
466
+ "<SPECIAL_463>",
467
+ "<SPECIAL_464>",
468
+ "<SPECIAL_465>",
469
+ "<SPECIAL_466>",
470
+ "<SPECIAL_467>",
471
+ "<SPECIAL_468>",
472
+ "<SPECIAL_469>",
473
+ "<SPECIAL_470>",
474
+ "<SPECIAL_471>",
475
+ "<SPECIAL_472>",
476
+ "<SPECIAL_473>",
477
+ "<SPECIAL_474>",
478
+ "<SPECIAL_475>",
479
+ "<SPECIAL_476>",
480
+ "<SPECIAL_477>",
481
+ "<SPECIAL_478>",
482
+ "<SPECIAL_479>",
483
+ "<SPECIAL_480>",
484
+ "<SPECIAL_481>",
485
+ "<SPECIAL_482>",
486
+ "<SPECIAL_483>",
487
+ "<SPECIAL_484>",
488
+ "<SPECIAL_485>",
489
+ "<SPECIAL_486>",
490
+ "<SPECIAL_487>",
491
+ "<SPECIAL_488>",
492
+ "<SPECIAL_489>",
493
+ "<SPECIAL_490>",
494
+ "<SPECIAL_491>",
495
+ "<SPECIAL_492>",
496
+ "<SPECIAL_493>",
497
+ "<SPECIAL_494>",
498
+ "<SPECIAL_495>",
499
+ "<SPECIAL_496>",
500
+ "<SPECIAL_497>",
501
+ "<SPECIAL_498>",
502
+ "<SPECIAL_499>",
503
+ "<SPECIAL_500>",
504
+ "<SPECIAL_501>",
505
+ "<SPECIAL_502>",
506
+ "<SPECIAL_503>",
507
+ "<SPECIAL_504>",
508
+ "<SPECIAL_505>",
509
+ "<SPECIAL_506>",
510
+ "<SPECIAL_507>",
511
+ "<SPECIAL_508>",
512
+ "<SPECIAL_509>",
513
+ "<SPECIAL_510>",
514
+ "<SPECIAL_511>",
515
+ "<SPECIAL_512>",
516
+ "<SPECIAL_513>",
517
+ "<SPECIAL_514>",
518
+ "<SPECIAL_515>",
519
+ "<SPECIAL_516>",
520
+ "<SPECIAL_517>",
521
+ "<SPECIAL_518>",
522
+ "<SPECIAL_519>",
523
+ "<SPECIAL_520>",
524
+ "<SPECIAL_521>",
525
+ "<SPECIAL_522>",
526
+ "<SPECIAL_523>",
527
+ "<SPECIAL_524>",
528
+ "<SPECIAL_525>",
529
+ "<SPECIAL_526>",
530
+ "<SPECIAL_527>",
531
+ "<SPECIAL_528>",
532
+ "<SPECIAL_529>",
533
+ "<SPECIAL_530>",
534
+ "<SPECIAL_531>",
535
+ "<SPECIAL_532>",
536
+ "<SPECIAL_533>",
537
+ "<SPECIAL_534>",
538
+ "<SPECIAL_535>",
539
+ "<SPECIAL_536>",
540
+ "<SPECIAL_537>",
541
+ "<SPECIAL_538>",
542
+ "<SPECIAL_539>",
543
+ "<SPECIAL_540>",
544
+ "<SPECIAL_541>",
545
+ "<SPECIAL_542>",
546
+ "<SPECIAL_543>",
547
+ "<SPECIAL_544>",
548
+ "<SPECIAL_545>",
549
+ "<SPECIAL_546>",
550
+ "<SPECIAL_547>",
551
+ "<SPECIAL_548>",
552
+ "<SPECIAL_549>",
553
+ "<SPECIAL_550>",
554
+ "<SPECIAL_551>",
555
+ "<SPECIAL_552>",
556
+ "<SPECIAL_553>",
557
+ "<SPECIAL_554>",
558
+ "<SPECIAL_555>",
559
+ "<SPECIAL_556>",
560
+ "<SPECIAL_557>",
561
+ "<SPECIAL_558>",
562
+ "<SPECIAL_559>",
563
+ "<SPECIAL_560>",
564
+ "<SPECIAL_561>",
565
+ "<SPECIAL_562>",
566
+ "<SPECIAL_563>",
567
+ "<SPECIAL_564>",
568
+ "<SPECIAL_565>",
569
+ "<SPECIAL_566>",
570
+ "<SPECIAL_567>",
571
+ "<SPECIAL_568>",
572
+ "<SPECIAL_569>",
573
+ "<SPECIAL_570>",
574
+ "<SPECIAL_571>",
575
+ "<SPECIAL_572>",
576
+ "<SPECIAL_573>",
577
+ "<SPECIAL_574>",
578
+ "<SPECIAL_575>",
579
+ "<SPECIAL_576>",
580
+ "<SPECIAL_577>",
581
+ "<SPECIAL_578>",
582
+ "<SPECIAL_579>",
583
+ "<SPECIAL_580>",
584
+ "<SPECIAL_581>",
585
+ "<SPECIAL_582>",
586
+ "<SPECIAL_583>",
587
+ "<SPECIAL_584>",
588
+ "<SPECIAL_585>",
589
+ "<SPECIAL_586>",
590
+ "<SPECIAL_587>",
591
+ "<SPECIAL_588>",
592
+ "<SPECIAL_589>",
593
+ "<SPECIAL_590>",
594
+ "<SPECIAL_591>",
595
+ "<SPECIAL_592>",
596
+ "<SPECIAL_593>",
597
+ "<SPECIAL_594>",
598
+ "<SPECIAL_595>",
599
+ "<SPECIAL_596>",
600
+ "<SPECIAL_597>",
601
+ "<SPECIAL_598>",
602
+ "<SPECIAL_599>",
603
+ "<SPECIAL_600>",
604
+ "<SPECIAL_601>",
605
+ "<SPECIAL_602>",
606
+ "<SPECIAL_603>",
607
+ "<SPECIAL_604>",
608
+ "<SPECIAL_605>",
609
+ "<SPECIAL_606>",
610
+ "<SPECIAL_607>",
611
+ "<SPECIAL_608>",
612
+ "<SPECIAL_609>",
613
+ "<SPECIAL_610>",
614
+ "<SPECIAL_611>",
615
+ "<SPECIAL_612>",
616
+ "<SPECIAL_613>",
617
+ "<SPECIAL_614>",
618
+ "<SPECIAL_615>",
619
+ "<SPECIAL_616>",
620
+ "<SPECIAL_617>",
621
+ "<SPECIAL_618>",
622
+ "<SPECIAL_619>",
623
+ "<SPECIAL_620>",
624
+ "<SPECIAL_621>",
625
+ "<SPECIAL_622>",
626
+ "<SPECIAL_623>",
627
+ "<SPECIAL_624>",
628
+ "<SPECIAL_625>",
629
+ "<SPECIAL_626>",
630
+ "<SPECIAL_627>",
631
+ "<SPECIAL_628>",
632
+ "<SPECIAL_629>",
633
+ "<SPECIAL_630>",
634
+ "<SPECIAL_631>",
635
+ "<SPECIAL_632>",
636
+ "<SPECIAL_633>",
637
+ "<SPECIAL_634>",
638
+ "<SPECIAL_635>",
639
+ "<SPECIAL_636>",
640
+ "<SPECIAL_637>",
641
+ "<SPECIAL_638>",
642
+ "<SPECIAL_639>",
643
+ "<SPECIAL_640>",
644
+ "<SPECIAL_641>",
645
+ "<SPECIAL_642>",
646
+ "<SPECIAL_643>",
647
+ "<SPECIAL_644>",
648
+ "<SPECIAL_645>",
649
+ "<SPECIAL_646>",
650
+ "<SPECIAL_647>",
651
+ "<SPECIAL_648>",
652
+ "<SPECIAL_649>",
653
+ "<SPECIAL_650>",
654
+ "<SPECIAL_651>",
655
+ "<SPECIAL_652>",
656
+ "<SPECIAL_653>",
657
+ "<SPECIAL_654>",
658
+ "<SPECIAL_655>",
659
+ "<SPECIAL_656>",
660
+ "<SPECIAL_657>",
661
+ "<SPECIAL_658>",
662
+ "<SPECIAL_659>",
663
+ "<SPECIAL_660>",
664
+ "<SPECIAL_661>",
665
+ "<SPECIAL_662>",
666
+ "<SPECIAL_663>",
667
+ "<SPECIAL_664>",
668
+ "<SPECIAL_665>",
669
+ "<SPECIAL_666>",
670
+ "<SPECIAL_667>",
671
+ "<SPECIAL_668>",
672
+ "<SPECIAL_669>",
673
+ "<SPECIAL_670>",
674
+ "<SPECIAL_671>",
675
+ "<SPECIAL_672>",
676
+ "<SPECIAL_673>",
677
+ "<SPECIAL_674>",
678
+ "<SPECIAL_675>",
679
+ "<SPECIAL_676>",
680
+ "<SPECIAL_677>",
681
+ "<SPECIAL_678>",
682
+ "<SPECIAL_679>",
683
+ "<SPECIAL_680>",
684
+ "<SPECIAL_681>",
685
+ "<SPECIAL_682>",
686
+ "<SPECIAL_683>",
687
+ "<SPECIAL_684>",
688
+ "<SPECIAL_685>",
689
+ "<SPECIAL_686>",
690
+ "<SPECIAL_687>",
691
+ "<SPECIAL_688>",
692
+ "<SPECIAL_689>",
693
+ "<SPECIAL_690>",
694
+ "<SPECIAL_691>",
695
+ "<SPECIAL_692>",
696
+ "<SPECIAL_693>",
697
+ "<SPECIAL_694>",
698
+ "<SPECIAL_695>",
699
+ "<SPECIAL_696>",
700
+ "<SPECIAL_697>",
701
+ "<SPECIAL_698>",
702
+ "<SPECIAL_699>",
703
+ "<SPECIAL_700>",
704
+ "<SPECIAL_701>",
705
+ "<SPECIAL_702>",
706
+ "<SPECIAL_703>",
707
+ "<SPECIAL_704>",
708
+ "<SPECIAL_705>",
709
+ "<SPECIAL_706>",
710
+ "<SPECIAL_707>",
711
+ "<SPECIAL_708>",
712
+ "<SPECIAL_709>",
713
+ "<SPECIAL_710>",
714
+ "<SPECIAL_711>",
715
+ "<SPECIAL_712>",
716
+ "<SPECIAL_713>",
717
+ "<SPECIAL_714>",
718
+ "<SPECIAL_715>",
719
+ "<SPECIAL_716>",
720
+ "<SPECIAL_717>",
721
+ "<SPECIAL_718>",
722
+ "<SPECIAL_719>",
723
+ "<SPECIAL_720>",
724
+ "<SPECIAL_721>",
725
+ "<SPECIAL_722>",
726
+ "<SPECIAL_723>",
727
+ "<SPECIAL_724>",
728
+ "<SPECIAL_725>",
729
+ "<SPECIAL_726>",
730
+ "<SPECIAL_727>",
731
+ "<SPECIAL_728>",
732
+ "<SPECIAL_729>",
733
+ "<SPECIAL_730>",
734
+ "<SPECIAL_731>",
735
+ "<SPECIAL_732>",
736
+ "<SPECIAL_733>",
737
+ "<SPECIAL_734>",
738
+ "<SPECIAL_735>",
739
+ "<SPECIAL_736>",
740
+ "<SPECIAL_737>",
741
+ "<SPECIAL_738>",
742
+ "<SPECIAL_739>",
743
+ "<SPECIAL_740>",
744
+ "<SPECIAL_741>",
745
+ "<SPECIAL_742>",
746
+ "<SPECIAL_743>",
747
+ "<SPECIAL_744>",
748
+ "<SPECIAL_745>",
749
+ "<SPECIAL_746>",
750
+ "<SPECIAL_747>",
751
+ "<SPECIAL_748>",
752
+ "<SPECIAL_749>",
753
+ "<SPECIAL_750>",
754
+ "<SPECIAL_751>",
755
+ "<SPECIAL_752>",
756
+ "<SPECIAL_753>",
757
+ "<SPECIAL_754>",
758
+ "<SPECIAL_755>",
759
+ "<SPECIAL_756>",
760
+ "<SPECIAL_757>",
761
+ "<SPECIAL_758>",
762
+ "<SPECIAL_759>",
763
+ "<SPECIAL_760>",
764
+ "<SPECIAL_761>",
765
+ "<SPECIAL_762>",
766
+ "<SPECIAL_763>",
767
+ "<SPECIAL_764>",
768
+ "<SPECIAL_765>",
769
+ "<SPECIAL_766>",
770
+ "<SPECIAL_767>",
771
+ "<SPECIAL_768>",
772
+ "<SPECIAL_769>",
773
+ "<SPECIAL_770>",
774
+ "<SPECIAL_771>",
775
+ "<SPECIAL_772>",
776
+ "<SPECIAL_773>",
777
+ "<SPECIAL_774>",
778
+ "<SPECIAL_775>",
779
+ "<SPECIAL_776>",
780
+ "<SPECIAL_777>",
781
+ "<SPECIAL_778>",
782
+ "<SPECIAL_779>",
783
+ "<SPECIAL_780>",
784
+ "<SPECIAL_781>",
785
+ "<SPECIAL_782>",
786
+ "<SPECIAL_783>",
787
+ "<SPECIAL_784>",
788
+ "<SPECIAL_785>",
789
+ "<SPECIAL_786>",
790
+ "<SPECIAL_787>",
791
+ "<SPECIAL_788>",
792
+ "<SPECIAL_789>",
793
+ "<SPECIAL_790>",
794
+ "<SPECIAL_791>",
795
+ "<SPECIAL_792>",
796
+ "<SPECIAL_793>",
797
+ "<SPECIAL_794>",
798
+ "<SPECIAL_795>",
799
+ "<SPECIAL_796>",
800
+ "<SPECIAL_797>",
801
+ "<SPECIAL_798>",
802
+ "<SPECIAL_799>",
803
+ "<SPECIAL_800>",
804
+ "<SPECIAL_801>",
805
+ "<SPECIAL_802>",
806
+ "<SPECIAL_803>",
807
+ "<SPECIAL_804>",
808
+ "<SPECIAL_805>",
809
+ "<SPECIAL_806>",
810
+ "<SPECIAL_807>",
811
+ "<SPECIAL_808>",
812
+ "<SPECIAL_809>",
813
+ "<SPECIAL_810>",
814
+ "<SPECIAL_811>",
815
+ "<SPECIAL_812>",
816
+ "<SPECIAL_813>",
817
+ "<SPECIAL_814>",
818
+ "<SPECIAL_815>",
819
+ "<SPECIAL_816>",
820
+ "<SPECIAL_817>",
821
+ "<SPECIAL_818>",
822
+ "<SPECIAL_819>",
823
+ "<SPECIAL_820>",
824
+ "<SPECIAL_821>",
825
+ "<SPECIAL_822>",
826
+ "<SPECIAL_823>",
827
+ "<SPECIAL_824>",
828
+ "<SPECIAL_825>",
829
+ "<SPECIAL_826>",
830
+ "<SPECIAL_827>",
831
+ "<SPECIAL_828>",
832
+ "<SPECIAL_829>",
833
+ "<SPECIAL_830>",
834
+ "<SPECIAL_831>",
835
+ "<SPECIAL_832>",
836
+ "<SPECIAL_833>",
837
+ "<SPECIAL_834>",
838
+ "<SPECIAL_835>",
839
+ "<SPECIAL_836>",
840
+ "<SPECIAL_837>",
841
+ "<SPECIAL_838>",
842
+ "<SPECIAL_839>",
843
+ "<SPECIAL_840>",
844
+ "<SPECIAL_841>",
845
+ "<SPECIAL_842>",
846
+ "<SPECIAL_843>",
847
+ "<SPECIAL_844>",
848
+ "<SPECIAL_845>",
849
+ "<SPECIAL_846>",
850
+ "<SPECIAL_847>",
851
+ "<SPECIAL_848>",
852
+ "<SPECIAL_849>",
853
+ "<SPECIAL_850>",
854
+ "<SPECIAL_851>",
855
+ "<SPECIAL_852>",
856
+ "<SPECIAL_853>",
857
+ "<SPECIAL_854>",
858
+ "<SPECIAL_855>",
859
+ "<SPECIAL_856>",
860
+ "<SPECIAL_857>",
861
+ "<SPECIAL_858>",
862
+ "<SPECIAL_859>",
863
+ "<SPECIAL_860>",
864
+ "<SPECIAL_861>",
865
+ "<SPECIAL_862>",
866
+ "<SPECIAL_863>",
867
+ "<SPECIAL_864>",
868
+ "<SPECIAL_865>",
869
+ "<SPECIAL_866>",
870
+ "<SPECIAL_867>",
871
+ "<SPECIAL_868>",
872
+ "<SPECIAL_869>",
873
+ "<SPECIAL_870>",
874
+ "<SPECIAL_871>",
875
+ "<SPECIAL_872>",
876
+ "<SPECIAL_873>",
877
+ "<SPECIAL_874>",
878
+ "<SPECIAL_875>",
879
+ "<SPECIAL_876>",
880
+ "<SPECIAL_877>",
881
+ "<SPECIAL_878>",
882
+ "<SPECIAL_879>",
883
+ "<SPECIAL_880>",
884
+ "<SPECIAL_881>",
885
+ "<SPECIAL_882>",
886
+ "<SPECIAL_883>",
887
+ "<SPECIAL_884>",
888
+ "<SPECIAL_885>",
889
+ "<SPECIAL_886>",
890
+ "<SPECIAL_887>",
891
+ "<SPECIAL_888>",
892
+ "<SPECIAL_889>",
893
+ "<SPECIAL_890>",
894
+ "<SPECIAL_891>",
895
+ "<SPECIAL_892>",
896
+ "<SPECIAL_893>",
897
+ "<SPECIAL_894>",
898
+ "<SPECIAL_895>",
899
+ "<SPECIAL_896>",
900
+ "<SPECIAL_897>",
901
+ "<SPECIAL_898>",
902
+ "<SPECIAL_899>",
903
+ "<SPECIAL_900>",
904
+ "<SPECIAL_901>",
905
+ "<SPECIAL_902>",
906
+ "<SPECIAL_903>",
907
+ "<SPECIAL_904>",
908
+ "<SPECIAL_905>",
909
+ "<SPECIAL_906>",
910
+ "<SPECIAL_907>",
911
+ "<SPECIAL_908>",
912
+ "<SPECIAL_909>",
913
+ "<SPECIAL_910>",
914
+ "<SPECIAL_911>",
915
+ "<SPECIAL_912>",
916
+ "<SPECIAL_913>",
917
+ "<SPECIAL_914>",
918
+ "<SPECIAL_915>",
919
+ "<SPECIAL_916>",
920
+ "<SPECIAL_917>",
921
+ "<SPECIAL_918>",
922
+ "<SPECIAL_919>",
923
+ "<SPECIAL_920>",
924
+ "<SPECIAL_921>",
925
+ "<SPECIAL_922>",
926
+ "<SPECIAL_923>",
927
+ "<SPECIAL_924>",
928
+ "<SPECIAL_925>",
929
+ "<SPECIAL_926>",
930
+ "<SPECIAL_927>",
931
+ "<SPECIAL_928>",
932
+ "<SPECIAL_929>",
933
+ "<SPECIAL_930>",
934
+ "<SPECIAL_931>",
935
+ "<SPECIAL_932>",
936
+ "<SPECIAL_933>",
937
+ "<SPECIAL_934>",
938
+ "<SPECIAL_935>",
939
+ "<SPECIAL_936>",
940
+ "<SPECIAL_937>",
941
+ "<SPECIAL_938>",
942
+ "<SPECIAL_939>",
943
+ "<SPECIAL_940>",
944
+ "<SPECIAL_941>",
945
+ "<SPECIAL_942>",
946
+ "<SPECIAL_943>",
947
+ "<SPECIAL_944>",
948
+ "<SPECIAL_945>",
949
+ "<SPECIAL_946>",
950
+ "<SPECIAL_947>",
951
+ "<SPECIAL_948>",
952
+ "<SPECIAL_949>",
953
+ "<SPECIAL_950>",
954
+ "<SPECIAL_951>",
955
+ "<SPECIAL_952>",
956
+ "<SPECIAL_953>",
957
+ "<SPECIAL_954>",
958
+ "<SPECIAL_955>",
959
+ "<SPECIAL_956>",
960
+ "<SPECIAL_957>",
961
+ "<SPECIAL_958>",
962
+ "<SPECIAL_959>",
963
+ "<SPECIAL_960>",
964
+ "<SPECIAL_961>",
965
+ "<SPECIAL_962>",
966
+ "<SPECIAL_963>",
967
+ "<SPECIAL_964>",
968
+ "<SPECIAL_965>",
969
+ "<SPECIAL_966>",
970
+ "<SPECIAL_967>",
971
+ "<SPECIAL_968>",
972
+ "<SPECIAL_969>",
973
+ "<SPECIAL_970>",
974
+ "<SPECIAL_971>",
975
+ "<SPECIAL_972>",
976
+ "<SPECIAL_973>",
977
+ "<SPECIAL_974>",
978
+ "<SPECIAL_975>",
979
+ "<SPECIAL_976>",
980
+ "<SPECIAL_977>",
981
+ "<SPECIAL_978>",
982
+ "<SPECIAL_979>",
983
+ "<SPECIAL_980>",
984
+ "<SPECIAL_981>",
985
+ "<SPECIAL_982>",
986
+ "<SPECIAL_983>",
987
+ "<SPECIAL_984>",
988
+ "<SPECIAL_985>",
989
+ "<SPECIAL_986>",
990
+ "<SPECIAL_987>",
991
+ "<SPECIAL_988>",
992
+ "<SPECIAL_989>",
993
+ "<SPECIAL_990>",
994
+ "<SPECIAL_991>",
995
+ "<SPECIAL_992>",
996
+ "<SPECIAL_993>",
997
+ "<SPECIAL_994>",
998
+ "<SPECIAL_995>",
999
+ "<SPECIAL_996>",
1000
+ "<SPECIAL_997>",
1001
+ "<SPECIAL_998>",
1002
+ "<SPECIAL_999>"
1003
+ ],
1004
+ "bos_token": {
1005
+ "content": "<s>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ "eos_token": {
1012
+ "content": "</s>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ "pad_token": "<pad>",
1019
+ "unk_token": {
1020
+ "content": "<unk>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false
1025
+ }
1026
+ }
checkpoints/checkpoint-300/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
3
+ size 17078037
checkpoints/checkpoint-300/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,3357 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.906122448979592,
5
+ "eval_steps": 2,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_loss": 1.2313029766082764,
14
+ "eval_runtime": 18.2352,
15
+ "eval_samples_per_second": 0.877,
16
+ "eval_steps_per_second": 0.877,
17
+ "step": 0
18
+ },
19
+ {
20
+ "epoch": 0.0163265306122449,
21
+ "grad_norm": 0.37113556265830994,
22
+ "learning_rate": 2.5e-05,
23
+ "loss": 0.4085,
24
+ "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.0326530612244898,
28
+ "grad_norm": 0.35803329944610596,
29
+ "learning_rate": 5e-05,
30
+ "loss": 0.3876,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.0326530612244898,
35
+ "eval_loss": 1.2231345176696777,
36
+ "eval_runtime": 18.2243,
37
+ "eval_samples_per_second": 0.878,
38
+ "eval_steps_per_second": 0.878,
39
+ "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04897959183673469,
43
+ "grad_norm": 0.3112759590148926,
44
+ "learning_rate": 7.500000000000001e-05,
45
+ "loss": 0.3946,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0653061224489796,
50
+ "grad_norm": 0.2448713332414627,
51
+ "learning_rate": 0.0001,
52
+ "loss": 0.4363,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0653061224489796,
57
+ "eval_loss": 1.1564743518829346,
58
+ "eval_runtime": 18.253,
59
+ "eval_samples_per_second": 0.877,
60
+ "eval_steps_per_second": 0.877,
61
+ "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.08163265306122448,
65
+ "grad_norm": 0.2955642342567444,
66
+ "learning_rate": 0.000125,
67
+ "loss": 0.4394,
68
+ "step": 5
69
+ },
70
+ {
71
+ "epoch": 0.09795918367346938,
72
+ "grad_norm": 0.41399946808815,
73
+ "learning_rate": 0.00015000000000000001,
74
+ "loss": 0.4902,
75
+ "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.09795918367346938,
79
+ "eval_loss": 1.1353044509887695,
80
+ "eval_runtime": 18.2664,
81
+ "eval_samples_per_second": 0.876,
82
+ "eval_steps_per_second": 0.876,
83
+ "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.11428571428571428,
87
+ "grad_norm": 0.2643347978591919,
88
+ "learning_rate": 0.000175,
89
+ "loss": 0.3528,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 0.1306122448979592,
94
+ "grad_norm": 0.21472330391407013,
95
+ "learning_rate": 0.0002,
96
+ "loss": 0.357,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 0.1306122448979592,
101
+ "eval_loss": 1.1218546628952026,
102
+ "eval_runtime": 18.2139,
103
+ "eval_samples_per_second": 0.878,
104
+ "eval_steps_per_second": 0.878,
105
+ "step": 8
106
+ },
107
+ {
108
+ "epoch": 0.1469387755102041,
109
+ "grad_norm": 0.23261462152004242,
110
+ "learning_rate": 0.00022500000000000002,
111
+ "loss": 0.3924,
112
+ "step": 9
113
+ },
114
+ {
115
+ "epoch": 0.16326530612244897,
116
+ "grad_norm": 0.18365171551704407,
117
+ "learning_rate": 0.00025,
118
+ "loss": 0.283,
119
+ "step": 10
120
+ },
121
+ {
122
+ "epoch": 0.16326530612244897,
123
+ "eval_loss": 1.1094393730163574,
124
+ "eval_runtime": 18.249,
125
+ "eval_samples_per_second": 0.877,
126
+ "eval_steps_per_second": 0.877,
127
+ "step": 10
128
+ },
129
+ {
130
+ "epoch": 0.17959183673469387,
131
+ "grad_norm": 0.20431634783744812,
132
+ "learning_rate": 0.000275,
133
+ "loss": 0.3178,
134
+ "step": 11
135
+ },
136
+ {
137
+ "epoch": 0.19591836734693877,
138
+ "grad_norm": 0.2033773809671402,
139
+ "learning_rate": 0.00030000000000000003,
140
+ "loss": 0.3366,
141
+ "step": 12
142
+ },
143
+ {
144
+ "epoch": 0.19591836734693877,
145
+ "eval_loss": 1.1021316051483154,
146
+ "eval_runtime": 18.2562,
147
+ "eval_samples_per_second": 0.876,
148
+ "eval_steps_per_second": 0.876,
149
+ "step": 12
150
+ },
151
+ {
152
+ "epoch": 0.21224489795918366,
153
+ "grad_norm": 0.27416911721229553,
154
+ "learning_rate": 0.00032500000000000004,
155
+ "loss": 0.3367,
156
+ "step": 13
157
+ },
158
+ {
159
+ "epoch": 0.22857142857142856,
160
+ "grad_norm": 0.32283130288124084,
161
+ "learning_rate": 0.00035,
162
+ "loss": 0.3364,
163
+ "step": 14
164
+ },
165
+ {
166
+ "epoch": 0.22857142857142856,
167
+ "eval_loss": 1.0523244142532349,
168
+ "eval_runtime": 18.2347,
169
+ "eval_samples_per_second": 0.877,
170
+ "eval_steps_per_second": 0.877,
171
+ "step": 14
172
+ },
173
+ {
174
+ "epoch": 0.24489795918367346,
175
+ "grad_norm": 0.21469368040561676,
176
+ "learning_rate": 0.000375,
177
+ "loss": 0.3496,
178
+ "step": 15
179
+ },
180
+ {
181
+ "epoch": 0.2612244897959184,
182
+ "grad_norm": 0.19361759722232819,
183
+ "learning_rate": 0.0004,
184
+ "loss": 0.2961,
185
+ "step": 16
186
+ },
187
+ {
188
+ "epoch": 0.2612244897959184,
189
+ "eval_loss": 1.0401124954223633,
190
+ "eval_runtime": 18.2288,
191
+ "eval_samples_per_second": 0.878,
192
+ "eval_steps_per_second": 0.878,
193
+ "step": 16
194
+ },
195
+ {
196
+ "epoch": 0.27755102040816326,
197
+ "grad_norm": 0.1797463297843933,
198
+ "learning_rate": 0.0004,
199
+ "loss": 0.3016,
200
+ "step": 17
201
+ },
202
+ {
203
+ "epoch": 0.2938775510204082,
204
+ "grad_norm": 0.28122591972351074,
205
+ "learning_rate": 0.0004,
206
+ "loss": 0.3656,
207
+ "step": 18
208
+ },
209
+ {
210
+ "epoch": 0.2938775510204082,
211
+ "eval_loss": 1.0228931903839111,
212
+ "eval_runtime": 18.2429,
213
+ "eval_samples_per_second": 0.877,
214
+ "eval_steps_per_second": 0.877,
215
+ "step": 18
216
+ },
217
+ {
218
+ "epoch": 0.31020408163265306,
219
+ "grad_norm": 0.227556511759758,
220
+ "learning_rate": 0.0004,
221
+ "loss": 0.3246,
222
+ "step": 19
223
+ },
224
+ {
225
+ "epoch": 0.32653061224489793,
226
+ "grad_norm": 0.211012601852417,
227
+ "learning_rate": 0.0004,
228
+ "loss": 0.3453,
229
+ "step": 20
230
+ },
231
+ {
232
+ "epoch": 0.32653061224489793,
233
+ "eval_loss": 1.017521858215332,
234
+ "eval_runtime": 18.2213,
235
+ "eval_samples_per_second": 0.878,
236
+ "eval_steps_per_second": 0.878,
237
+ "step": 20
238
+ },
239
+ {
240
+ "epoch": 0.34285714285714286,
241
+ "grad_norm": 0.20422972738742828,
242
+ "learning_rate": 0.0004,
243
+ "loss": 0.3258,
244
+ "step": 21
245
+ },
246
+ {
247
+ "epoch": 0.35918367346938773,
248
+ "grad_norm": 0.206649512052536,
249
+ "learning_rate": 0.0004,
250
+ "loss": 0.3248,
251
+ "step": 22
252
+ },
253
+ {
254
+ "epoch": 0.35918367346938773,
255
+ "eval_loss": 0.9992413520812988,
256
+ "eval_runtime": 18.249,
257
+ "eval_samples_per_second": 0.877,
258
+ "eval_steps_per_second": 0.877,
259
+ "step": 22
260
+ },
261
+ {
262
+ "epoch": 0.37551020408163266,
263
+ "grad_norm": 0.19837401807308197,
264
+ "learning_rate": 0.0004,
265
+ "loss": 0.3181,
266
+ "step": 23
267
+ },
268
+ {
269
+ "epoch": 0.39183673469387753,
270
+ "grad_norm": 0.20325997471809387,
271
+ "learning_rate": 0.0004,
272
+ "loss": 0.2826,
273
+ "step": 24
274
+ },
275
+ {
276
+ "epoch": 0.39183673469387753,
277
+ "eval_loss": 0.9943413734436035,
278
+ "eval_runtime": 18.2482,
279
+ "eval_samples_per_second": 0.877,
280
+ "eval_steps_per_second": 0.877,
281
+ "step": 24
282
+ },
283
+ {
284
+ "epoch": 0.40816326530612246,
285
+ "grad_norm": 0.3371317386627197,
286
+ "learning_rate": 0.0004,
287
+ "loss": 0.3197,
288
+ "step": 25
289
+ },
290
+ {
291
+ "epoch": 0.42448979591836733,
292
+ "grad_norm": 0.21709182858467102,
293
+ "learning_rate": 0.0004,
294
+ "loss": 0.3272,
295
+ "step": 26
296
+ },
297
+ {
298
+ "epoch": 0.42448979591836733,
299
+ "eval_loss": 0.9733779430389404,
300
+ "eval_runtime": 18.2232,
301
+ "eval_samples_per_second": 0.878,
302
+ "eval_steps_per_second": 0.878,
303
+ "step": 26
304
+ },
305
+ {
306
+ "epoch": 0.44081632653061226,
307
+ "grad_norm": 0.2420857548713684,
308
+ "learning_rate": 0.0004,
309
+ "loss": 0.3293,
310
+ "step": 27
311
+ },
312
+ {
313
+ "epoch": 0.45714285714285713,
314
+ "grad_norm": 0.30486994981765747,
315
+ "learning_rate": 0.0004,
316
+ "loss": 0.3958,
317
+ "step": 28
318
+ },
319
+ {
320
+ "epoch": 0.45714285714285713,
321
+ "eval_loss": 0.9588731527328491,
322
+ "eval_runtime": 18.2458,
323
+ "eval_samples_per_second": 0.877,
324
+ "eval_steps_per_second": 0.877,
325
+ "step": 28
326
+ },
327
+ {
328
+ "epoch": 0.47346938775510206,
329
+ "grad_norm": 0.24714964628219604,
330
+ "learning_rate": 0.0004,
331
+ "loss": 0.3305,
332
+ "step": 29
333
+ },
334
+ {
335
+ "epoch": 0.4897959183673469,
336
+ "grad_norm": 0.21984225511550903,
337
+ "learning_rate": 0.0004,
338
+ "loss": 0.3395,
339
+ "step": 30
340
+ },
341
+ {
342
+ "epoch": 0.4897959183673469,
343
+ "eval_loss": 0.9427903890609741,
344
+ "eval_runtime": 18.2414,
345
+ "eval_samples_per_second": 0.877,
346
+ "eval_steps_per_second": 0.877,
347
+ "step": 30
348
+ },
349
+ {
350
+ "epoch": 0.5061224489795918,
351
+ "grad_norm": 0.19778016209602356,
352
+ "learning_rate": 0.0004,
353
+ "loss": 0.2918,
354
+ "step": 31
355
+ },
356
+ {
357
+ "epoch": 0.5224489795918368,
358
+ "grad_norm": 0.21754617989063263,
359
+ "learning_rate": 0.0004,
360
+ "loss": 0.2855,
361
+ "step": 32
362
+ },
363
+ {
364
+ "epoch": 0.5224489795918368,
365
+ "eval_loss": 0.9335330128669739,
366
+ "eval_runtime": 18.275,
367
+ "eval_samples_per_second": 0.876,
368
+ "eval_steps_per_second": 0.876,
369
+ "step": 32
370
+ },
371
+ {
372
+ "epoch": 0.5387755102040817,
373
+ "grad_norm": 0.2221430391073227,
374
+ "learning_rate": 0.0004,
375
+ "loss": 0.2946,
376
+ "step": 33
377
+ },
378
+ {
379
+ "epoch": 0.5551020408163265,
380
+ "grad_norm": 0.2112974375486374,
381
+ "learning_rate": 0.0004,
382
+ "loss": 0.3149,
383
+ "step": 34
384
+ },
385
+ {
386
+ "epoch": 0.5551020408163265,
387
+ "eval_loss": 0.9311869144439697,
388
+ "eval_runtime": 18.2431,
389
+ "eval_samples_per_second": 0.877,
390
+ "eval_steps_per_second": 0.877,
391
+ "step": 34
392
+ },
393
+ {
394
+ "epoch": 0.5714285714285714,
395
+ "grad_norm": 0.19651219248771667,
396
+ "learning_rate": 0.0004,
397
+ "loss": 0.2606,
398
+ "step": 35
399
+ },
400
+ {
401
+ "epoch": 0.5877551020408164,
402
+ "grad_norm": 0.22742077708244324,
403
+ "learning_rate": 0.0004,
404
+ "loss": 0.3245,
405
+ "step": 36
406
+ },
407
+ {
408
+ "epoch": 0.5877551020408164,
409
+ "eval_loss": 0.9281033873558044,
410
+ "eval_runtime": 18.2248,
411
+ "eval_samples_per_second": 0.878,
412
+ "eval_steps_per_second": 0.878,
413
+ "step": 36
414
+ },
415
+ {
416
+ "epoch": 0.6040816326530613,
417
+ "grad_norm": 0.2320890575647354,
418
+ "learning_rate": 0.0004,
419
+ "loss": 0.3532,
420
+ "step": 37
421
+ },
422
+ {
423
+ "epoch": 0.6204081632653061,
424
+ "grad_norm": 0.21191200613975525,
425
+ "learning_rate": 0.0004,
426
+ "loss": 0.2973,
427
+ "step": 38
428
+ },
429
+ {
430
+ "epoch": 0.6204081632653061,
431
+ "eval_loss": 0.9274996519088745,
432
+ "eval_runtime": 18.2309,
433
+ "eval_samples_per_second": 0.878,
434
+ "eval_steps_per_second": 0.878,
435
+ "step": 38
436
+ },
437
+ {
438
+ "epoch": 0.636734693877551,
439
+ "grad_norm": 0.24098484218120575,
440
+ "learning_rate": 0.0004,
441
+ "loss": 0.3194,
442
+ "step": 39
443
+ },
444
+ {
445
+ "epoch": 0.6530612244897959,
446
+ "grad_norm": 0.3358725607395172,
447
+ "learning_rate": 0.0004,
448
+ "loss": 0.2833,
449
+ "step": 40
450
+ },
451
+ {
452
+ "epoch": 0.6530612244897959,
453
+ "eval_loss": 0.9254183769226074,
454
+ "eval_runtime": 18.2685,
455
+ "eval_samples_per_second": 0.876,
456
+ "eval_steps_per_second": 0.876,
457
+ "step": 40
458
+ },
459
+ {
460
+ "epoch": 0.6693877551020408,
461
+ "grad_norm": 0.2399401068687439,
462
+ "learning_rate": 0.0004,
463
+ "loss": 0.3381,
464
+ "step": 41
465
+ },
466
+ {
467
+ "epoch": 0.6857142857142857,
468
+ "grad_norm": 0.23229075968265533,
469
+ "learning_rate": 0.0004,
470
+ "loss": 0.3501,
471
+ "step": 42
472
+ },
473
+ {
474
+ "epoch": 0.6857142857142857,
475
+ "eval_loss": 0.9213573932647705,
476
+ "eval_runtime": 18.2788,
477
+ "eval_samples_per_second": 0.875,
478
+ "eval_steps_per_second": 0.875,
479
+ "step": 42
480
+ },
481
+ {
482
+ "epoch": 0.7020408163265306,
483
+ "grad_norm": 0.2341497391462326,
484
+ "learning_rate": 0.0004,
485
+ "loss": 0.3033,
486
+ "step": 43
487
+ },
488
+ {
489
+ "epoch": 0.7183673469387755,
490
+ "grad_norm": 0.22997914254665375,
491
+ "learning_rate": 0.0004,
492
+ "loss": 0.3675,
493
+ "step": 44
494
+ },
495
+ {
496
+ "epoch": 0.7183673469387755,
497
+ "eval_loss": 0.9130539298057556,
498
+ "eval_runtime": 18.2601,
499
+ "eval_samples_per_second": 0.876,
500
+ "eval_steps_per_second": 0.876,
501
+ "step": 44
502
+ },
503
+ {
504
+ "epoch": 0.7346938775510204,
505
+ "grad_norm": 0.23445634543895721,
506
+ "learning_rate": 0.0004,
507
+ "loss": 0.3113,
508
+ "step": 45
509
+ },
510
+ {
511
+ "epoch": 0.7510204081632653,
512
+ "grad_norm": 0.22852188348770142,
513
+ "learning_rate": 0.0004,
514
+ "loss": 0.3593,
515
+ "step": 46
516
+ },
517
+ {
518
+ "epoch": 0.7510204081632653,
519
+ "eval_loss": 0.9100953936576843,
520
+ "eval_runtime": 18.2446,
521
+ "eval_samples_per_second": 0.877,
522
+ "eval_steps_per_second": 0.877,
523
+ "step": 46
524
+ },
525
+ {
526
+ "epoch": 0.7673469387755102,
527
+ "grad_norm": 0.2316325306892395,
528
+ "learning_rate": 0.0004,
529
+ "loss": 0.3121,
530
+ "step": 47
531
+ },
532
+ {
533
+ "epoch": 0.7836734693877551,
534
+ "grad_norm": 0.2397606372833252,
535
+ "learning_rate": 0.0004,
536
+ "loss": 0.2979,
537
+ "step": 48
538
+ },
539
+ {
540
+ "epoch": 0.7836734693877551,
541
+ "eval_loss": 0.9087210297584534,
542
+ "eval_runtime": 18.2833,
543
+ "eval_samples_per_second": 0.875,
544
+ "eval_steps_per_second": 0.875,
545
+ "step": 48
546
+ },
547
+ {
548
+ "epoch": 0.8,
549
+ "grad_norm": 0.22637659311294556,
550
+ "learning_rate": 0.0004,
551
+ "loss": 0.2919,
552
+ "step": 49
553
+ },
554
+ {
555
+ "epoch": 0.8163265306122449,
556
+ "grad_norm": 0.255599707365036,
557
+ "learning_rate": 0.0004,
558
+ "loss": 0.3741,
559
+ "step": 50
560
+ },
561
+ {
562
+ "epoch": 0.8163265306122449,
563
+ "eval_loss": 0.9020435810089111,
564
+ "eval_runtime": 18.2931,
565
+ "eval_samples_per_second": 0.875,
566
+ "eval_steps_per_second": 0.875,
567
+ "step": 50
568
+ },
569
+ {
570
+ "epoch": 0.8163265306122449,
571
+ "eval_loss": 0.9020435810089111,
572
+ "eval_runtime": 18.1276,
573
+ "eval_samples_per_second": 0.883,
574
+ "eval_steps_per_second": 0.883,
575
+ "step": 50
576
+ },
577
+ {
578
+ "epoch": 0.8326530612244898,
579
+ "grad_norm": 0.2062978744506836,
580
+ "learning_rate": 0.0003877467715307749,
581
+ "loss": 0.3303,
582
+ "step": 51
583
+ },
584
+ {
585
+ "epoch": 0.8489795918367347,
586
+ "grad_norm": 0.20149795711040497,
587
+ "learning_rate": 0.0003870443502801494,
588
+ "loss": 0.3212,
589
+ "step": 52
590
+ },
591
+ {
592
+ "epoch": 0.8489795918367347,
593
+ "eval_loss": 0.8994156718254089,
594
+ "eval_runtime": 18.1853,
595
+ "eval_samples_per_second": 0.88,
596
+ "eval_steps_per_second": 0.88,
597
+ "step": 52
598
+ },
599
+ {
600
+ "epoch": 0.8653061224489796,
601
+ "grad_norm": 0.17913399636745453,
602
+ "learning_rate": 0.0003863230255984052,
603
+ "loss": 0.2637,
604
+ "step": 53
605
+ },
606
+ {
607
+ "epoch": 0.8816326530612245,
608
+ "grad_norm": 0.19331133365631104,
609
+ "learning_rate": 0.00038558287038542615,
610
+ "loss": 0.3564,
611
+ "step": 54
612
+ },
613
+ {
614
+ "epoch": 0.8816326530612245,
615
+ "eval_loss": 0.8963940143585205,
616
+ "eval_runtime": 18.223,
617
+ "eval_samples_per_second": 0.878,
618
+ "eval_steps_per_second": 0.878,
619
+ "step": 54
620
+ },
621
+ {
622
+ "epoch": 0.8979591836734694,
623
+ "grad_norm": 0.20378044247627258,
624
+ "learning_rate": 0.00038482395944418313,
625
+ "loss": 0.3253,
626
+ "step": 55
627
+ },
628
+ {
629
+ "epoch": 0.9142857142857143,
630
+ "grad_norm": 0.19742076098918915,
631
+ "learning_rate": 0.0003840463694731741,
632
+ "loss": 0.3715,
633
+ "step": 56
634
+ },
635
+ {
636
+ "epoch": 0.9142857142857143,
637
+ "eval_loss": 0.8902382850646973,
638
+ "eval_runtime": 18.2093,
639
+ "eval_samples_per_second": 0.879,
640
+ "eval_steps_per_second": 0.879,
641
+ "step": 56
642
+ },
643
+ {
644
+ "epoch": 0.9306122448979591,
645
+ "grad_norm": 0.1908055692911148,
646
+ "learning_rate": 0.0003832501790586724,
647
+ "loss": 0.3305,
648
+ "step": 57
649
+ },
650
+ {
651
+ "epoch": 0.9469387755102041,
652
+ "grad_norm": 0.21527761220932007,
653
+ "learning_rate": 0.0003824354686667848,
654
+ "loss": 0.3523,
655
+ "step": 58
656
+ },
657
+ {
658
+ "epoch": 0.9469387755102041,
659
+ "eval_loss": 0.8786917328834534,
660
+ "eval_runtime": 18.2124,
661
+ "eval_samples_per_second": 0.879,
662
+ "eval_steps_per_second": 0.879,
663
+ "step": 58
664
+ },
665
+ {
666
+ "epoch": 0.963265306122449,
667
+ "grad_norm": 0.1817687749862671,
668
+ "learning_rate": 0.00038160232063531917,
669
+ "loss": 0.2616,
670
+ "step": 59
671
+ },
672
+ {
673
+ "epoch": 0.9795918367346939,
674
+ "grad_norm": 0.17659063637256622,
675
+ "learning_rate": 0.0003807508191654631,
676
+ "loss": 0.251,
677
+ "step": 60
678
+ },
679
+ {
680
+ "epoch": 0.9795918367346939,
681
+ "eval_loss": 0.8799586296081543,
682
+ "eval_runtime": 18.2543,
683
+ "eval_samples_per_second": 0.877,
684
+ "eval_steps_per_second": 0.877,
685
+ "step": 60
686
+ },
687
+ {
688
+ "epoch": 0.9959183673469387,
689
+ "grad_norm": 0.22647982835769653,
690
+ "learning_rate": 0.0003798810503132742,
691
+ "loss": 0.2881,
692
+ "step": 61
693
+ },
694
+ {
695
+ "epoch": 1.0122448979591836,
696
+ "grad_norm": 0.45377442240715027,
697
+ "learning_rate": 0.00037899310198098295,
698
+ "loss": 0.5515,
699
+ "step": 62
700
+ },
701
+ {
702
+ "epoch": 1.0122448979591836,
703
+ "eval_loss": 0.8895297050476074,
704
+ "eval_runtime": 18.2212,
705
+ "eval_samples_per_second": 0.878,
706
+ "eval_steps_per_second": 0.878,
707
+ "step": 62
708
+ },
709
+ {
710
+ "epoch": 1.0285714285714285,
711
+ "grad_norm": 0.3527546226978302,
712
+ "learning_rate": 0.000378087063908109,
713
+ "loss": 0.2427,
714
+ "step": 63
715
+ },
716
+ {
717
+ "epoch": 1.0448979591836736,
718
+ "grad_norm": 0.2781178951263428,
719
+ "learning_rate": 0.0003771630276623915,
720
+ "loss": 0.2215,
721
+ "step": 64
722
+ },
723
+ {
724
+ "epoch": 1.0448979591836736,
725
+ "eval_loss": 0.9294220209121704,
726
+ "eval_runtime": 18.226,
727
+ "eval_samples_per_second": 0.878,
728
+ "eval_steps_per_second": 0.878,
729
+ "step": 64
730
+ },
731
+ {
732
+ "epoch": 1.0612244897959184,
733
+ "grad_norm": 0.2543565034866333,
734
+ "learning_rate": 0.00037622108663053536,
735
+ "loss": 0.2761,
736
+ "step": 65
737
+ },
738
+ {
739
+ "epoch": 1.0775510204081633,
740
+ "grad_norm": 0.26259011030197144,
741
+ "learning_rate": 0.0003752613360087727,
742
+ "loss": 0.2425,
743
+ "step": 66
744
+ },
745
+ {
746
+ "epoch": 1.0775510204081633,
747
+ "eval_loss": 0.9212721586227417,
748
+ "eval_runtime": 18.2309,
749
+ "eval_samples_per_second": 0.878,
750
+ "eval_steps_per_second": 0.878,
751
+ "step": 66
752
+ },
753
+ {
754
+ "epoch": 1.0938775510204082,
755
+ "grad_norm": 0.36850446462631226,
756
+ "learning_rate": 0.00037428387279324257,
757
+ "loss": 0.225,
758
+ "step": 67
759
+ },
760
+ {
761
+ "epoch": 1.110204081632653,
762
+ "grad_norm": 0.23748713731765747,
763
+ "learning_rate": 0.0003732887957701874,
764
+ "loss": 0.2363,
765
+ "step": 68
766
+ },
767
+ {
768
+ "epoch": 1.110204081632653,
769
+ "eval_loss": 0.9431418776512146,
770
+ "eval_runtime": 18.2471,
771
+ "eval_samples_per_second": 0.877,
772
+ "eval_steps_per_second": 0.877,
773
+ "step": 68
774
+ },
775
+ {
776
+ "epoch": 1.126530612244898,
777
+ "grad_norm": 0.23217403888702393,
778
+ "learning_rate": 0.00037227620550597,
779
+ "loss": 0.2364,
780
+ "step": 69
781
+ },
782
+ {
783
+ "epoch": 1.1428571428571428,
784
+ "grad_norm": 0.28124868869781494,
785
+ "learning_rate": 0.0003712462043369093,
786
+ "loss": 0.2197,
787
+ "step": 70
788
+ },
789
+ {
790
+ "epoch": 1.1428571428571428,
791
+ "eval_loss": 0.9205393195152283,
792
+ "eval_runtime": 18.2662,
793
+ "eval_samples_per_second": 0.876,
794
+ "eval_steps_per_second": 0.876,
795
+ "step": 70
796
+ },
797
+ {
798
+ "epoch": 1.1591836734693877,
799
+ "grad_norm": 0.2142041176557541,
800
+ "learning_rate": 0.00037019889635893843,
801
+ "loss": 0.1958,
802
+ "step": 71
803
+ },
804
+ {
805
+ "epoch": 1.1755102040816325,
806
+ "grad_norm": 0.34761127829551697,
807
+ "learning_rate": 0.0003691343874170838,
808
+ "loss": 0.2183,
809
+ "step": 72
810
+ },
811
+ {
812
+ "epoch": 1.1755102040816325,
813
+ "eval_loss": 0.9254322648048401,
814
+ "eval_runtime": 18.2303,
815
+ "eval_samples_per_second": 0.878,
816
+ "eval_steps_per_second": 0.878,
817
+ "step": 72
818
+ },
819
+ {
820
+ "epoch": 1.1918367346938776,
821
+ "grad_norm": 0.2560065686702728,
822
+ "learning_rate": 0.00036805278509476844,
823
+ "loss": 0.248,
824
+ "step": 73
825
+ },
826
+ {
827
+ "epoch": 1.2081632653061225,
828
+ "grad_norm": 0.7435296773910522,
829
+ "learning_rate": 0.00036695419870293915,
830
+ "loss": 0.2356,
831
+ "step": 74
832
+ },
833
+ {
834
+ "epoch": 1.2081632653061225,
835
+ "eval_loss": 0.9271378517150879,
836
+ "eval_runtime": 18.2503,
837
+ "eval_samples_per_second": 0.877,
838
+ "eval_steps_per_second": 0.877,
839
+ "step": 74
840
+ },
841
+ {
842
+ "epoch": 1.2244897959183674,
843
+ "grad_norm": 0.8685758113861084,
844
+ "learning_rate": 0.00036583873926901867,
845
+ "loss": 0.2129,
846
+ "step": 75
847
+ },
848
+ {
849
+ "epoch": 1.2408163265306122,
850
+ "grad_norm": 1.2740998268127441,
851
+ "learning_rate": 0.0003647065195256855,
852
+ "loss": 0.2469,
853
+ "step": 76
854
+ },
855
+ {
856
+ "epoch": 1.2408163265306122,
857
+ "eval_loss": 0.9236885905265808,
858
+ "eval_runtime": 18.2226,
859
+ "eval_samples_per_second": 0.878,
860
+ "eval_steps_per_second": 0.878,
861
+ "step": 76
862
+ },
863
+ {
864
+ "epoch": 1.2571428571428571,
865
+ "grad_norm": 0.28524693846702576,
866
+ "learning_rate": 0.0003635576538994801,
867
+ "loss": 0.2278,
868
+ "step": 77
869
+ },
870
+ {
871
+ "epoch": 1.273469387755102,
872
+ "grad_norm": 1.0116885900497437,
873
+ "learning_rate": 0.0003623922584992409,
874
+ "loss": 0.2488,
875
+ "step": 78
876
+ },
877
+ {
878
+ "epoch": 1.273469387755102,
879
+ "eval_loss": 0.923646867275238,
880
+ "eval_runtime": 18.2519,
881
+ "eval_samples_per_second": 0.877,
882
+ "eval_steps_per_second": 0.877,
883
+ "step": 78
884
+ },
885
+ {
886
+ "epoch": 1.2897959183673469,
887
+ "grad_norm": 0.9336573481559753,
888
+ "learning_rate": 0.0003612104511043694,
889
+ "loss": 0.3095,
890
+ "step": 79
891
+ },
892
+ {
893
+ "epoch": 1.306122448979592,
894
+ "grad_norm": 0.43459734320640564,
895
+ "learning_rate": 0.0003600123511529278,
896
+ "loss": 0.2215,
897
+ "step": 80
898
+ },
899
+ {
900
+ "epoch": 1.306122448979592,
901
+ "eval_loss": 0.941472589969635,
902
+ "eval_runtime": 18.251,
903
+ "eval_samples_per_second": 0.877,
904
+ "eval_steps_per_second": 0.877,
905
+ "step": 80
906
+ },
907
+ {
908
+ "epoch": 1.3224489795918366,
909
+ "grad_norm": 0.39941656589508057,
910
+ "learning_rate": 0.0003587980797295671,
911
+ "loss": 0.251,
912
+ "step": 81
913
+ },
914
+ {
915
+ "epoch": 1.3387755102040817,
916
+ "grad_norm": 0.2876632511615753,
917
+ "learning_rate": 0.0003575677595532904,
918
+ "loss": 0.208,
919
+ "step": 82
920
+ },
921
+ {
922
+ "epoch": 1.3387755102040817,
923
+ "eval_loss": 0.932316780090332,
924
+ "eval_runtime": 18.2326,
925
+ "eval_samples_per_second": 0.878,
926
+ "eval_steps_per_second": 0.878,
927
+ "step": 82
928
+ },
929
+ {
930
+ "epoch": 1.3551020408163266,
931
+ "grad_norm": 0.30556565523147583,
932
+ "learning_rate": 0.0003563215149650505,
933
+ "loss": 0.2821,
934
+ "step": 83
935
+ },
936
+ {
937
+ "epoch": 1.3714285714285714,
938
+ "grad_norm": 0.3039940595626831,
939
+ "learning_rate": 0.00035505947191518316,
940
+ "loss": 0.2177,
941
+ "step": 84
942
+ },
943
+ {
944
+ "epoch": 1.3714285714285714,
945
+ "eval_loss": 0.9171479344367981,
946
+ "eval_runtime": 18.2397,
947
+ "eval_samples_per_second": 0.877,
948
+ "eval_steps_per_second": 0.877,
949
+ "step": 84
950
+ },
951
+ {
952
+ "epoch": 1.3877551020408163,
953
+ "grad_norm": 0.32876476645469666,
954
+ "learning_rate": 0.0003537817579506783,
955
+ "loss": 0.2142,
956
+ "step": 85
957
+ },
958
+ {
959
+ "epoch": 1.4040816326530612,
960
+ "grad_norm": 0.26468542218208313,
961
+ "learning_rate": 0.0003524885022022896,
962
+ "loss": 0.2293,
963
+ "step": 86
964
+ },
965
+ {
966
+ "epoch": 1.4040816326530612,
967
+ "eval_loss": 0.9176874756813049,
968
+ "eval_runtime": 18.2553,
969
+ "eval_samples_per_second": 0.876,
970
+ "eval_steps_per_second": 0.876,
971
+ "step": 86
972
+ },
973
+ {
974
+ "epoch": 1.420408163265306,
975
+ "grad_norm": 0.9715031981468201,
976
+ "learning_rate": 0.000351179835371484,
977
+ "loss": 0.235,
978
+ "step": 87
979
+ },
980
+ {
981
+ "epoch": 1.436734693877551,
982
+ "grad_norm": 0.8392952680587769,
983
+ "learning_rate": 0.00034985588971723233,
984
+ "loss": 0.2307,
985
+ "step": 88
986
+ },
987
+ {
988
+ "epoch": 1.436734693877551,
989
+ "eval_loss": 0.9272938370704651,
990
+ "eval_runtime": 18.2194,
991
+ "eval_samples_per_second": 0.878,
992
+ "eval_steps_per_second": 0.878,
993
+ "step": 88
994
+ },
995
+ {
996
+ "epoch": 1.453061224489796,
997
+ "grad_norm": 0.28850337862968445,
998
+ "learning_rate": 0.00034851679904264314,
999
+ "loss": 0.2403,
1000
+ "step": 89
1001
+ },
1002
+ {
1003
+ "epoch": 1.469387755102041,
1004
+ "grad_norm": 0.46389341354370117,
1005
+ "learning_rate": 0.00034716269868143956,
1006
+ "loss": 0.2464,
1007
+ "step": 90
1008
+ },
1009
+ {
1010
+ "epoch": 1.469387755102041,
1011
+ "eval_loss": 0.9267984628677368,
1012
+ "eval_runtime": 18.2514,
1013
+ "eval_samples_per_second": 0.877,
1014
+ "eval_steps_per_second": 0.877,
1015
+ "step": 90
1016
+ },
1017
+ {
1018
+ "epoch": 1.4857142857142858,
1019
+ "grad_norm": 0.29597121477127075,
1020
+ "learning_rate": 0.00034579372548428235,
1021
+ "loss": 0.2307,
1022
+ "step": 91
1023
+ },
1024
+ {
1025
+ "epoch": 1.5020408163265306,
1026
+ "grad_norm": 0.3392711877822876,
1027
+ "learning_rate": 0.00034441001780493886,
1028
+ "loss": 0.231,
1029
+ "step": 92
1030
+ },
1031
+ {
1032
+ "epoch": 1.5020408163265306,
1033
+ "eval_loss": 0.9267009496688843,
1034
+ "eval_runtime": 18.2179,
1035
+ "eval_samples_per_second": 0.878,
1036
+ "eval_steps_per_second": 0.878,
1037
+ "step": 92
1038
+ },
1039
+ {
1040
+ "epoch": 1.5183673469387755,
1041
+ "grad_norm": 0.2309531569480896,
1042
+ "learning_rate": 0.00034301171548630063,
1043
+ "loss": 0.2307,
1044
+ "step": 93
1045
+ },
1046
+ {
1047
+ "epoch": 1.5346938775510204,
1048
+ "grad_norm": 0.28941744565963745,
1049
+ "learning_rate": 0.0003415989598462506,
1050
+ "loss": 0.2384,
1051
+ "step": 94
1052
+ },
1053
+ {
1054
+ "epoch": 1.5346938775510204,
1055
+ "eval_loss": 0.9336121082305908,
1056
+ "eval_runtime": 18.2184,
1057
+ "eval_samples_per_second": 0.878,
1058
+ "eval_steps_per_second": 0.878,
1059
+ "step": 94
1060
+ },
1061
+ {
1062
+ "epoch": 1.5510204081632653,
1063
+ "grad_norm": 0.22579389810562134,
1064
+ "learning_rate": 0.00034017189366338034,
1065
+ "loss": 0.1949,
1066
+ "step": 95
1067
+ },
1068
+ {
1069
+ "epoch": 1.5673469387755103,
1070
+ "grad_norm": 0.2894729971885681,
1071
+ "learning_rate": 0.000338730661162561,
1072
+ "loss": 0.2348,
1073
+ "step": 96
1074
+ },
1075
+ {
1076
+ "epoch": 1.5673469387755103,
1077
+ "eval_loss": 0.9432627558708191,
1078
+ "eval_runtime": 18.2158,
1079
+ "eval_samples_per_second": 0.878,
1080
+ "eval_steps_per_second": 0.878,
1081
+ "step": 96
1082
+ },
1083
+ {
1084
+ "epoch": 1.583673469387755,
1085
+ "grad_norm": 0.24218647181987762,
1086
+ "learning_rate": 0.00033727540800036683,
1087
+ "loss": 0.2113,
1088
+ "step": 97
1089
+ },
1090
+ {
1091
+ "epoch": 1.6,
1092
+ "grad_norm": 0.2695946991443634,
1093
+ "learning_rate": 0.0003358062812503548,
1094
+ "loss": 0.2209,
1095
+ "step": 98
1096
+ },
1097
+ {
1098
+ "epoch": 1.6,
1099
+ "eval_loss": 0.9510765075683594,
1100
+ "eval_runtime": 18.2181,
1101
+ "eval_samples_per_second": 0.878,
1102
+ "eval_steps_per_second": 0.878,
1103
+ "step": 98
1104
+ },
1105
+ {
1106
+ "epoch": 1.6163265306122447,
1107
+ "grad_norm": 0.27196425199508667,
1108
+ "learning_rate": 0.00033432342938820086,
1109
+ "loss": 0.2366,
1110
+ "step": 99
1111
+ },
1112
+ {
1113
+ "epoch": 1.6326530612244898,
1114
+ "grad_norm": 0.2302471101284027,
1115
+ "learning_rate": 0.0003328270022766941,
1116
+ "loss": 0.2099,
1117
+ "step": 100
1118
+ },
1119
+ {
1120
+ "epoch": 1.6326530612244898,
1121
+ "eval_loss": 0.9363111853599548,
1122
+ "eval_runtime": 18.2175,
1123
+ "eval_samples_per_second": 0.878,
1124
+ "eval_steps_per_second": 0.878,
1125
+ "step": 100
1126
+ },
1127
+ {
1128
+ "epoch": 1.6489795918367347,
1129
+ "grad_norm": 0.24810455739498138,
1130
+ "learning_rate": 0.0003313171511505913,
1131
+ "loss": 0.2196,
1132
+ "step": 101
1133
+ },
1134
+ {
1135
+ "epoch": 1.6653061224489796,
1136
+ "grad_norm": 0.25561368465423584,
1137
+ "learning_rate": 0.0003297940286013326,
1138
+ "loss": 0.253,
1139
+ "step": 102
1140
+ },
1141
+ {
1142
+ "epoch": 1.6653061224489796,
1143
+ "eval_loss": 0.942488431930542,
1144
+ "eval_runtime": 18.2068,
1145
+ "eval_samples_per_second": 0.879,
1146
+ "eval_steps_per_second": 0.879,
1147
+ "step": 102
1148
+ },
1149
+ {
1150
+ "epoch": 1.6816326530612244,
1151
+ "grad_norm": 0.22677375376224518,
1152
+ "learning_rate": 0.0003282577885616198,
1153
+ "loss": 0.1789,
1154
+ "step": 103
1155
+ },
1156
+ {
1157
+ "epoch": 1.6979591836734693,
1158
+ "grad_norm": 0.26009589433670044,
1159
+ "learning_rate": 0.0003267085862898594,
1160
+ "loss": 0.2541,
1161
+ "step": 104
1162
+ },
1163
+ {
1164
+ "epoch": 1.6979591836734693,
1165
+ "eval_loss": 0.9335595369338989,
1166
+ "eval_runtime": 18.2507,
1167
+ "eval_samples_per_second": 0.877,
1168
+ "eval_steps_per_second": 0.877,
1169
+ "step": 104
1170
+ },
1171
+ {
1172
+ "epoch": 1.7142857142857144,
1173
+ "grad_norm": 0.20782141387462616,
1174
+ "learning_rate": 0.0003251465783544716,
1175
+ "loss": 0.2308,
1176
+ "step": 105
1177
+ },
1178
+ {
1179
+ "epoch": 1.730612244897959,
1180
+ "grad_norm": 0.22768278419971466,
1181
+ "learning_rate": 0.0003235719226180669,
1182
+ "loss": 0.2354,
1183
+ "step": 106
1184
+ },
1185
+ {
1186
+ "epoch": 1.730612244897959,
1187
+ "eval_loss": 0.9376662373542786,
1188
+ "eval_runtime": 18.2284,
1189
+ "eval_samples_per_second": 0.878,
1190
+ "eval_steps_per_second": 0.878,
1191
+ "step": 106
1192
+ },
1193
+ {
1194
+ "epoch": 1.7469387755102042,
1195
+ "grad_norm": 0.23742002248764038,
1196
+ "learning_rate": 0.00032198477822149185,
1197
+ "loss": 0.2306,
1198
+ "step": 107
1199
+ },
1200
+ {
1201
+ "epoch": 1.763265306122449,
1202
+ "grad_norm": 0.25688832998275757,
1203
+ "learning_rate": 0.0003203853055677457,
1204
+ "loss": 0.2816,
1205
+ "step": 108
1206
+ },
1207
+ {
1208
+ "epoch": 1.763265306122449,
1209
+ "eval_loss": 0.9434496164321899,
1210
+ "eval_runtime": 18.2263,
1211
+ "eval_samples_per_second": 0.878,
1212
+ "eval_steps_per_second": 0.878,
1213
+ "step": 108
1214
+ },
1215
+ {
1216
+ "epoch": 1.779591836734694,
1217
+ "grad_norm": 0.2690117359161377,
1218
+ "learning_rate": 0.00031877366630576946,
1219
+ "loss": 0.2013,
1220
+ "step": 109
1221
+ },
1222
+ {
1223
+ "epoch": 1.7959183673469388,
1224
+ "grad_norm": 0.2317412942647934,
1225
+ "learning_rate": 0.0003171500233141089,
1226
+ "loss": 0.2398,
1227
+ "step": 110
1228
+ },
1229
+ {
1230
+ "epoch": 1.7959183673469388,
1231
+ "eval_loss": 0.9329774975776672,
1232
+ "eval_runtime": 18.2112,
1233
+ "eval_samples_per_second": 0.879,
1234
+ "eval_steps_per_second": 0.879,
1235
+ "step": 110
1236
+ },
1237
+ {
1238
+ "epoch": 1.8122448979591836,
1239
+ "grad_norm": 0.2262117713689804,
1240
+ "learning_rate": 0.0003155145406844535,
1241
+ "loss": 0.207,
1242
+ "step": 111
1243
+ },
1244
+ {
1245
+ "epoch": 1.8285714285714287,
1246
+ "grad_norm": 0.22458741068840027,
1247
+ "learning_rate": 0.00031386738370505293,
1248
+ "loss": 0.2093,
1249
+ "step": 112
1250
+ },
1251
+ {
1252
+ "epoch": 1.8285714285714287,
1253
+ "eval_loss": 0.9222925901412964,
1254
+ "eval_runtime": 18.2333,
1255
+ "eval_samples_per_second": 0.878,
1256
+ "eval_steps_per_second": 0.878,
1257
+ "step": 112
1258
+ },
1259
+ {
1260
+ "epoch": 1.8448979591836734,
1261
+ "grad_norm": 0.24273625016212463,
1262
+ "learning_rate": 0.0003122087188440118,
1263
+ "loss": 0.2434,
1264
+ "step": 113
1265
+ },
1266
+ {
1267
+ "epoch": 1.8612244897959185,
1268
+ "grad_norm": 0.2206314653158188,
1269
+ "learning_rate": 0.0003105387137324663,
1270
+ "loss": 0.2056,
1271
+ "step": 114
1272
+ },
1273
+ {
1274
+ "epoch": 1.8612244897959185,
1275
+ "eval_loss": 0.9319095015525818,
1276
+ "eval_runtime": 18.2327,
1277
+ "eval_samples_per_second": 0.878,
1278
+ "eval_steps_per_second": 0.878,
1279
+ "step": 114
1280
+ },
1281
+ {
1282
+ "epoch": 1.8775510204081631,
1283
+ "grad_norm": 0.2606954574584961,
1284
+ "learning_rate": 0.0003088575371476426,
1285
+ "loss": 0.2198,
1286
+ "step": 115
1287
+ },
1288
+ {
1289
+ "epoch": 1.8938775510204082,
1290
+ "grad_norm": 0.23156337440013885,
1291
+ "learning_rate": 0.0003071653589957993,
1292
+ "loss": 0.1957,
1293
+ "step": 116
1294
+ },
1295
+ {
1296
+ "epoch": 1.8938775510204082,
1297
+ "eval_loss": 0.9314719438552856,
1298
+ "eval_runtime": 18.2411,
1299
+ "eval_samples_per_second": 0.877,
1300
+ "eval_steps_per_second": 0.877,
1301
+ "step": 116
1302
+ },
1303
+ {
1304
+ "epoch": 1.910204081632653,
1305
+ "grad_norm": 0.2253030389547348,
1306
+ "learning_rate": 0.0003054623502950565,
1307
+ "loss": 0.266,
1308
+ "step": 117
1309
+ },
1310
+ {
1311
+ "epoch": 1.926530612244898,
1312
+ "grad_norm": 0.24510890245437622,
1313
+ "learning_rate": 0.0003037486831581115,
1314
+ "loss": 0.2493,
1315
+ "step": 118
1316
+ },
1317
+ {
1318
+ "epoch": 1.926530612244898,
1319
+ "eval_loss": 0.926245927810669,
1320
+ "eval_runtime": 18.2428,
1321
+ "eval_samples_per_second": 0.877,
1322
+ "eval_steps_per_second": 0.877,
1323
+ "step": 118
1324
+ },
1325
+ {
1326
+ "epoch": 1.9428571428571428,
1327
+ "grad_norm": 0.22151368856430054,
1328
+ "learning_rate": 0.00030202453077484494,
1329
+ "loss": 0.2666,
1330
+ "step": 119
1331
+ },
1332
+ {
1333
+ "epoch": 1.9591836734693877,
1334
+ "grad_norm": 0.21714863181114197,
1335
+ "learning_rate": 0.0003002900673948173,
1336
+ "loss": 0.253,
1337
+ "step": 120
1338
+ },
1339
+ {
1340
+ "epoch": 1.9591836734693877,
1341
+ "eval_loss": 0.9263309240341187,
1342
+ "eval_runtime": 18.2196,
1343
+ "eval_samples_per_second": 0.878,
1344
+ "eval_steps_per_second": 0.878,
1345
+ "step": 120
1346
+ },
1347
+ {
1348
+ "epoch": 1.9755102040816328,
1349
+ "grad_norm": 0.2149583399295807,
1350
+ "learning_rate": 0.0002985454683096583,
1351
+ "loss": 0.2208,
1352
+ "step": 121
1353
+ },
1354
+ {
1355
+ "epoch": 1.9918367346938775,
1356
+ "grad_norm": 0.23067210614681244,
1357
+ "learning_rate": 0.000296790909835352,
1358
+ "loss": 0.2225,
1359
+ "step": 122
1360
+ },
1361
+ {
1362
+ "epoch": 1.9918367346938775,
1363
+ "eval_loss": 0.9324613809585571,
1364
+ "eval_runtime": 18.2438,
1365
+ "eval_samples_per_second": 0.877,
1366
+ "eval_steps_per_second": 0.877,
1367
+ "step": 122
1368
+ },
1369
+ {
1370
+ "epoch": 2.0081632653061225,
1371
+ "grad_norm": 0.4510343074798584,
1372
+ "learning_rate": 0.00029502656929441683,
1373
+ "loss": 0.3179,
1374
+ "step": 123
1375
+ },
1376
+ {
1377
+ "epoch": 2.024489795918367,
1378
+ "grad_norm": 0.24402837455272675,
1379
+ "learning_rate": 0.000293252624997985,
1380
+ "loss": 0.1501,
1381
+ "step": 124
1382
+ },
1383
+ {
1384
+ "epoch": 2.024489795918367,
1385
+ "eval_loss": 0.9700677394866943,
1386
+ "eval_runtime": 18.2313,
1387
+ "eval_samples_per_second": 0.878,
1388
+ "eval_steps_per_second": 0.878,
1389
+ "step": 124
1390
+ },
1391
+ {
1392
+ "epoch": 2.0408163265306123,
1393
+ "grad_norm": 0.31533220410346985,
1394
+ "learning_rate": 0.00029146925622778176,
1395
+ "loss": 0.1353,
1396
+ "step": 125
1397
+ },
1398
+ {
1399
+ "epoch": 2.057142857142857,
1400
+ "grad_norm": 0.24323108792304993,
1401
+ "learning_rate": 0.0002896766432180065,
1402
+ "loss": 0.1297,
1403
+ "step": 126
1404
+ },
1405
+ {
1406
+ "epoch": 2.057142857142857,
1407
+ "eval_loss": 0.9890408515930176,
1408
+ "eval_runtime": 18.2073,
1409
+ "eval_samples_per_second": 0.879,
1410
+ "eval_steps_per_second": 0.879,
1411
+ "step": 126
1412
+ },
1413
+ {
1414
+ "epoch": 2.073469387755102,
1415
+ "grad_norm": 0.24305571615695953,
1416
+ "learning_rate": 0.00028787496713711733,
1417
+ "loss": 0.1389,
1418
+ "step": 127
1419
+ },
1420
+ {
1421
+ "epoch": 2.089795918367347,
1422
+ "grad_norm": 0.21282273530960083,
1423
+ "learning_rate": 0.0002860644100695218,
1424
+ "loss": 0.0994,
1425
+ "step": 128
1426
+ },
1427
+ {
1428
+ "epoch": 2.089795918367347,
1429
+ "eval_loss": 1.0023484230041504,
1430
+ "eval_runtime": 18.2257,
1431
+ "eval_samples_per_second": 0.878,
1432
+ "eval_steps_per_second": 0.878,
1433
+ "step": 128
1434
+ },
1435
+ {
1436
+ "epoch": 2.1061224489795918,
1437
+ "grad_norm": 0.20902425050735474,
1438
+ "learning_rate": 0.0002842451549971745,
1439
+ "loss": 0.1195,
1440
+ "step": 129
1441
+ },
1442
+ {
1443
+ "epoch": 2.122448979591837,
1444
+ "grad_norm": 0.21242493391036987,
1445
+ "learning_rate": 0.0002824173857810842,
1446
+ "loss": 0.1256,
1447
+ "step": 130
1448
+ },
1449
+ {
1450
+ "epoch": 2.122448979591837,
1451
+ "eval_loss": 1.0186381340026855,
1452
+ "eval_runtime": 18.1967,
1453
+ "eval_samples_per_second": 0.879,
1454
+ "eval_steps_per_second": 0.879,
1455
+ "step": 130
1456
+ },
1457
+ {
1458
+ "epoch": 2.1387755102040815,
1459
+ "grad_norm": 0.26445460319519043,
1460
+ "learning_rate": 0.00028058128714273257,
1461
+ "loss": 0.1268,
1462
+ "step": 131
1463
+ },
1464
+ {
1465
+ "epoch": 2.1551020408163266,
1466
+ "grad_norm": 0.24118709564208984,
1467
+ "learning_rate": 0.0002787370446454047,
1468
+ "loss": 0.1192,
1469
+ "step": 132
1470
+ },
1471
+ {
1472
+ "epoch": 2.1551020408163266,
1473
+ "eval_loss": 1.0201678276062012,
1474
+ "eval_runtime": 18.2377,
1475
+ "eval_samples_per_second": 0.877,
1476
+ "eval_steps_per_second": 0.877,
1477
+ "step": 132
1478
+ },
1479
+ {
1480
+ "epoch": 2.1714285714285713,
1481
+ "grad_norm": 0.23629823327064514,
1482
+ "learning_rate": 0.0002768848446754362,
1483
+ "loss": 0.1114,
1484
+ "step": 133
1485
+ },
1486
+ {
1487
+ "epoch": 2.1877551020408164,
1488
+ "grad_norm": 0.23851804435253143,
1489
+ "learning_rate": 0.0002750248744233756,
1490
+ "loss": 0.1455,
1491
+ "step": 134
1492
+ },
1493
+ {
1494
+ "epoch": 2.1877551020408164,
1495
+ "eval_loss": 1.027251124382019,
1496
+ "eval_runtime": 18.2111,
1497
+ "eval_samples_per_second": 0.879,
1498
+ "eval_steps_per_second": 0.879,
1499
+ "step": 134
1500
+ },
1501
+ {
1502
+ "epoch": 2.204081632653061,
1503
+ "grad_norm": 0.2159481793642044,
1504
+ "learning_rate": 0.00027315732186506656,
1505
+ "loss": 0.1036,
1506
+ "step": 135
1507
+ },
1508
+ {
1509
+ "epoch": 2.220408163265306,
1510
+ "grad_norm": 0.2521194815635681,
1511
+ "learning_rate": 0.0002712823757426501,
1512
+ "loss": 0.1539,
1513
+ "step": 136
1514
+ },
1515
+ {
1516
+ "epoch": 2.220408163265306,
1517
+ "eval_loss": 1.0327486991882324,
1518
+ "eval_runtime": 18.2282,
1519
+ "eval_samples_per_second": 0.878,
1520
+ "eval_steps_per_second": 0.878,
1521
+ "step": 136
1522
+ },
1523
+ {
1524
+ "epoch": 2.236734693877551,
1525
+ "grad_norm": 0.23456163704395294,
1526
+ "learning_rate": 0.00026940022554548993,
1527
+ "loss": 0.14,
1528
+ "step": 137
1529
+ },
1530
+ {
1531
+ "epoch": 2.253061224489796,
1532
+ "grad_norm": 0.25591009855270386,
1533
+ "learning_rate": 0.0002675110614910212,
1534
+ "loss": 0.1485,
1535
+ "step": 138
1536
+ },
1537
+ {
1538
+ "epoch": 2.253061224489796,
1539
+ "eval_loss": 1.0385500192642212,
1540
+ "eval_runtime": 18.1962,
1541
+ "eval_samples_per_second": 0.879,
1542
+ "eval_steps_per_second": 0.879,
1543
+ "step": 138
1544
+ },
1545
+ {
1546
+ "epoch": 2.269387755102041,
1547
+ "grad_norm": 0.2525387108325958,
1548
+ "learning_rate": 0.00026561507450552704,
1549
+ "loss": 0.1164,
1550
+ "step": 139
1551
+ },
1552
+ {
1553
+ "epoch": 2.2857142857142856,
1554
+ "grad_norm": 0.25320008397102356,
1555
+ "learning_rate": 0.00026371245620484255,
1556
+ "loss": 0.1307,
1557
+ "step": 140
1558
+ },
1559
+ {
1560
+ "epoch": 2.2857142857142856,
1561
+ "eval_loss": 1.028091311454773,
1562
+ "eval_runtime": 18.2167,
1563
+ "eval_samples_per_second": 0.878,
1564
+ "eval_steps_per_second": 0.878,
1565
+ "step": 140
1566
+ },
1567
+ {
1568
+ "epoch": 2.3020408163265307,
1569
+ "grad_norm": 0.27121609449386597,
1570
+ "learning_rate": 0.00026180339887498953,
1571
+ "loss": 0.1475,
1572
+ "step": 141
1573
+ },
1574
+ {
1575
+ "epoch": 2.3183673469387753,
1576
+ "grad_norm": 0.2442832738161087,
1577
+ "learning_rate": 0.00025988809545274293,
1578
+ "loss": 0.112,
1579
+ "step": 142
1580
+ },
1581
+ {
1582
+ "epoch": 2.3183673469387753,
1583
+ "eval_loss": 0.9875463247299194,
1584
+ "eval_runtime": 18.2364,
1585
+ "eval_samples_per_second": 0.877,
1586
+ "eval_steps_per_second": 0.877,
1587
+ "step": 142
1588
+ },
1589
+ {
1590
+ "epoch": 2.3346938775510204,
1591
+ "grad_norm": 0.23179620504379272,
1592
+ "learning_rate": 0.0002579667395061322,
1593
+ "loss": 0.1428,
1594
+ "step": 143
1595
+ },
1596
+ {
1597
+ "epoch": 2.351020408163265,
1598
+ "grad_norm": 0.21805799007415771,
1599
+ "learning_rate": 0.00025603952521487876,
1600
+ "loss": 0.1157,
1601
+ "step": 144
1602
+ },
1603
+ {
1604
+ "epoch": 2.351020408163265,
1605
+ "eval_loss": 0.9967271089553833,
1606
+ "eval_runtime": 18.2289,
1607
+ "eval_samples_per_second": 0.878,
1608
+ "eval_steps_per_second": 0.878,
1609
+ "step": 144
1610
+ },
1611
+ {
1612
+ "epoch": 2.36734693877551,
1613
+ "grad_norm": 0.2379518747329712,
1614
+ "learning_rate": 0.0002541066473507708,
1615
+ "loss": 0.1368,
1616
+ "step": 145
1617
+ },
1618
+ {
1619
+ "epoch": 2.3836734693877553,
1620
+ "grad_norm": 0.27792760729789734,
1621
+ "learning_rate": 0.00025216830125797943,
1622
+ "loss": 0.1369,
1623
+ "step": 146
1624
+ },
1625
+ {
1626
+ "epoch": 2.3836734693877553,
1627
+ "eval_loss": 0.9868496656417847,
1628
+ "eval_runtime": 18.2074,
1629
+ "eval_samples_per_second": 0.879,
1630
+ "eval_steps_per_second": 0.879,
1631
+ "step": 146
1632
+ },
1633
+ {
1634
+ "epoch": 2.4,
1635
+ "grad_norm": 0.2362203449010849,
1636
+ "learning_rate": 0.0002502246828333163,
1637
+ "loss": 0.1275,
1638
+ "step": 147
1639
+ },
1640
+ {
1641
+ "epoch": 2.416326530612245,
1642
+ "grad_norm": 0.27191162109375,
1643
+ "learning_rate": 0.00024827598850643546,
1644
+ "loss": 0.1582,
1645
+ "step": 148
1646
+ },
1647
+ {
1648
+ "epoch": 2.416326530612245,
1649
+ "eval_loss": 0.962943434715271,
1650
+ "eval_runtime": 18.2207,
1651
+ "eval_samples_per_second": 0.878,
1652
+ "eval_steps_per_second": 0.878,
1653
+ "step": 148
1654
+ },
1655
+ {
1656
+ "epoch": 2.4326530612244897,
1657
+ "grad_norm": 0.23347483575344086,
1658
+ "learning_rate": 0.0002463224152199813,
1659
+ "loss": 0.1309,
1660
+ "step": 149
1661
+ },
1662
+ {
1663
+ "epoch": 2.4489795918367347,
1664
+ "grad_norm": 0.2181580364704132,
1665
+ "learning_rate": 0.0002443641604096851,
1666
+ "loss": 0.1261,
1667
+ "step": 150
1668
+ },
1669
+ {
1670
+ "epoch": 2.4489795918367347,
1671
+ "eval_loss": 0.9731823205947876,
1672
+ "eval_runtime": 18.2136,
1673
+ "eval_samples_per_second": 0.878,
1674
+ "eval_steps_per_second": 0.878,
1675
+ "step": 150
1676
+ },
1677
+ {
1678
+ "epoch": 2.4653061224489794,
1679
+ "grad_norm": 0.2505442202091217,
1680
+ "learning_rate": 0.00024240142198441098,
1681
+ "loss": 0.1335,
1682
+ "step": 151
1683
+ },
1684
+ {
1685
+ "epoch": 2.4816326530612245,
1686
+ "grad_norm": 0.23964084684848785,
1687
+ "learning_rate": 0.00024043439830615472,
1688
+ "loss": 0.1249,
1689
+ "step": 152
1690
+ },
1691
+ {
1692
+ "epoch": 2.4816326530612245,
1693
+ "eval_loss": 0.9946855306625366,
1694
+ "eval_runtime": 18.2384,
1695
+ "eval_samples_per_second": 0.877,
1696
+ "eval_steps_per_second": 0.877,
1697
+ "step": 152
1698
+ },
1699
+ {
1700
+ "epoch": 2.497959183673469,
1701
+ "grad_norm": 0.2175896167755127,
1702
+ "learning_rate": 0.00023846328816999658,
1703
+ "loss": 0.101,
1704
+ "step": 153
1705
+ },
1706
+ {
1707
+ "epoch": 2.5142857142857142,
1708
+ "grad_norm": 0.2787061929702759,
1709
+ "learning_rate": 0.00023648829078401007,
1710
+ "loss": 0.1421,
1711
+ "step": 154
1712
+ },
1713
+ {
1714
+ "epoch": 2.5142857142857142,
1715
+ "eval_loss": 0.9933134317398071,
1716
+ "eval_runtime": 18.2349,
1717
+ "eval_samples_per_second": 0.877,
1718
+ "eval_steps_per_second": 0.877,
1719
+ "step": 154
1720
+ },
1721
+ {
1722
+ "epoch": 2.5306122448979593,
1723
+ "grad_norm": 0.22405166923999786,
1724
+ "learning_rate": 0.00023450960574912934,
1725
+ "loss": 0.1237,
1726
+ "step": 155
1727
+ },
1728
+ {
1729
+ "epoch": 2.546938775510204,
1730
+ "grad_norm": 0.25058048963546753,
1731
+ "learning_rate": 0.00023252743303897675,
1732
+ "loss": 0.1635,
1733
+ "step": 156
1734
+ },
1735
+ {
1736
+ "epoch": 2.546938775510204,
1737
+ "eval_loss": 0.9882242679595947,
1738
+ "eval_runtime": 18.2562,
1739
+ "eval_samples_per_second": 0.876,
1740
+ "eval_steps_per_second": 0.876,
1741
+ "step": 156
1742
+ },
1743
+ {
1744
+ "epoch": 2.563265306122449,
1745
+ "grad_norm": 0.3842501938343048,
1746
+ "learning_rate": 0.00023054197297965264,
1747
+ "loss": 0.1417,
1748
+ "step": 157
1749
+ },
1750
+ {
1751
+ "epoch": 2.5795918367346937,
1752
+ "grad_norm": 0.22574357688426971,
1753
+ "learning_rate": 0.00022855342622948976,
1754
+ "loss": 0.1221,
1755
+ "step": 158
1756
+ },
1757
+ {
1758
+ "epoch": 2.5795918367346937,
1759
+ "eval_loss": 1.0112800598144531,
1760
+ "eval_runtime": 18.2537,
1761
+ "eval_samples_per_second": 0.877,
1762
+ "eval_steps_per_second": 0.877,
1763
+ "step": 158
1764
+ },
1765
+ {
1766
+ "epoch": 2.595918367346939,
1767
+ "grad_norm": 0.22760067880153656,
1768
+ "learning_rate": 0.0002265619937587739,
1769
+ "loss": 0.1319,
1770
+ "step": 159
1771
+ },
1772
+ {
1773
+ "epoch": 2.612244897959184,
1774
+ "grad_norm": 0.25777938961982727,
1775
+ "learning_rate": 0.00022456787682943285,
1776
+ "loss": 0.149,
1777
+ "step": 160
1778
+ },
1779
+ {
1780
+ "epoch": 2.612244897959184,
1781
+ "eval_loss": 1.0162885189056396,
1782
+ "eval_runtime": 18.2574,
1783
+ "eval_samples_per_second": 0.876,
1784
+ "eval_steps_per_second": 0.876,
1785
+ "step": 160
1786
+ },
1787
+ {
1788
+ "epoch": 2.6285714285714286,
1789
+ "grad_norm": 0.23430375754833221,
1790
+ "learning_rate": 0.00022257127697469632,
1791
+ "loss": 0.1342,
1792
+ "step": 161
1793
+ },
1794
+ {
1795
+ "epoch": 2.644897959183673,
1796
+ "grad_norm": 0.25381889939308167,
1797
+ "learning_rate": 0.00022057239597872834,
1798
+ "loss": 0.1558,
1799
+ "step": 162
1800
+ },
1801
+ {
1802
+ "epoch": 2.644897959183673,
1803
+ "eval_loss": 1.0097148418426514,
1804
+ "eval_runtime": 18.2572,
1805
+ "eval_samples_per_second": 0.876,
1806
+ "eval_steps_per_second": 0.876,
1807
+ "step": 162
1808
+ },
1809
+ {
1810
+ "epoch": 2.6612244897959183,
1811
+ "grad_norm": 0.22818055748939514,
1812
+ "learning_rate": 0.0002185714358562336,
1813
+ "loss": 0.1382,
1814
+ "step": 163
1815
+ },
1816
+ {
1817
+ "epoch": 2.6775510204081634,
1818
+ "grad_norm": 0.21377477049827576,
1819
+ "learning_rate": 0.00021656859883204167,
1820
+ "loss": 0.1138,
1821
+ "step": 164
1822
+ },
1823
+ {
1824
+ "epoch": 2.6775510204081634,
1825
+ "eval_loss": 1.0100345611572266,
1826
+ "eval_runtime": 18.246,
1827
+ "eval_samples_per_second": 0.877,
1828
+ "eval_steps_per_second": 0.877,
1829
+ "step": 164
1830
+ },
1831
+ {
1832
+ "epoch": 2.693877551020408,
1833
+ "grad_norm": 0.20805473625659943,
1834
+ "learning_rate": 0.00021456408732066918,
1835
+ "loss": 0.1103,
1836
+ "step": 165
1837
+ },
1838
+ {
1839
+ "epoch": 2.710204081632653,
1840
+ "grad_norm": 0.23223794996738434,
1841
+ "learning_rate": 0.0002125581039058627,
1842
+ "loss": 0.1229,
1843
+ "step": 166
1844
+ },
1845
+ {
1846
+ "epoch": 2.710204081632653,
1847
+ "eval_loss": 1.0152215957641602,
1848
+ "eval_runtime": 18.2339,
1849
+ "eval_samples_per_second": 0.877,
1850
+ "eval_steps_per_second": 0.877,
1851
+ "step": 166
1852
+ },
1853
+ {
1854
+ "epoch": 2.726530612244898,
1855
+ "grad_norm": 0.22925834357738495,
1856
+ "learning_rate": 0.0002105508513201253,
1857
+ "loss": 0.112,
1858
+ "step": 167
1859
+ },
1860
+ {
1861
+ "epoch": 2.742857142857143,
1862
+ "grad_norm": 0.23402348160743713,
1863
+ "learning_rate": 0.00020854253242422744,
1864
+ "loss": 0.111,
1865
+ "step": 168
1866
+ },
1867
+ {
1868
+ "epoch": 2.742857142857143,
1869
+ "eval_loss": 1.0134178400039673,
1870
+ "eval_runtime": 18.2312,
1871
+ "eval_samples_per_second": 0.878,
1872
+ "eval_steps_per_second": 0.878,
1873
+ "step": 168
1874
+ },
1875
+ {
1876
+ "epoch": 2.759183673469388,
1877
+ "grad_norm": 0.21745020151138306,
1878
+ "learning_rate": 0.00020653335018670478,
1879
+ "loss": 0.1148,
1880
+ "step": 169
1881
+ },
1882
+ {
1883
+ "epoch": 2.7755102040816326,
1884
+ "grad_norm": 0.23371770977973938,
1885
+ "learning_rate": 0.00020452350766334595,
1886
+ "loss": 0.1378,
1887
+ "step": 170
1888
+ },
1889
+ {
1890
+ "epoch": 2.7755102040816326,
1891
+ "eval_loss": 1.008978247642517,
1892
+ "eval_runtime": 18.2393,
1893
+ "eval_samples_per_second": 0.877,
1894
+ "eval_steps_per_second": 0.877,
1895
+ "step": 170
1896
+ },
1897
+ {
1898
+ "epoch": 2.7918367346938773,
1899
+ "grad_norm": 0.23733730614185333,
1900
+ "learning_rate": 0.00020251320797667056,
1901
+ "loss": 0.1362,
1902
+ "step": 171
1903
+ },
1904
+ {
1905
+ "epoch": 2.8081632653061224,
1906
+ "grad_norm": 0.22156459093093872,
1907
+ "learning_rate": 0.00020050265429540082,
1908
+ "loss": 0.1197,
1909
+ "step": 172
1910
+ },
1911
+ {
1912
+ "epoch": 2.8081632653061224,
1913
+ "eval_loss": 0.996375560760498,
1914
+ "eval_runtime": 18.2572,
1915
+ "eval_samples_per_second": 0.876,
1916
+ "eval_steps_per_second": 0.876,
1917
+ "step": 172
1918
+ },
1919
+ {
1920
+ "epoch": 2.8244897959183675,
1921
+ "grad_norm": 0.21871179342269897,
1922
+ "learning_rate": 0.00019849204981392863,
1923
+ "loss": 0.1262,
1924
+ "step": 173
1925
+ },
1926
+ {
1927
+ "epoch": 2.840816326530612,
1928
+ "grad_norm": 0.2262168973684311,
1929
+ "learning_rate": 0.00019648159773178007,
1930
+ "loss": 0.1329,
1931
+ "step": 174
1932
+ },
1933
+ {
1934
+ "epoch": 2.840816326530612,
1935
+ "eval_loss": 0.9993283748626709,
1936
+ "eval_runtime": 18.2401,
1937
+ "eval_samples_per_second": 0.877,
1938
+ "eval_steps_per_second": 0.877,
1939
+ "step": 174
1940
+ },
1941
+ {
1942
+ "epoch": 2.857142857142857,
1943
+ "grad_norm": 0.24742639064788818,
1944
+ "learning_rate": 0.00019447150123307915,
1945
+ "loss": 0.1243,
1946
+ "step": 175
1947
+ },
1948
+ {
1949
+ "epoch": 2.873469387755102,
1950
+ "grad_norm": 0.21919304132461548,
1951
+ "learning_rate": 0.00019246196346601308,
1952
+ "loss": 0.1218,
1953
+ "step": 176
1954
+ },
1955
+ {
1956
+ "epoch": 2.873469387755102,
1957
+ "eval_loss": 1.0055768489837646,
1958
+ "eval_runtime": 18.2419,
1959
+ "eval_samples_per_second": 0.877,
1960
+ "eval_steps_per_second": 0.877,
1961
+ "step": 176
1962
+ },
1963
+ {
1964
+ "epoch": 2.889795918367347,
1965
+ "grad_norm": 0.21882188320159912,
1966
+ "learning_rate": 0.0001904531875223017,
1967
+ "loss": 0.1347,
1968
+ "step": 177
1969
+ },
1970
+ {
1971
+ "epoch": 2.906122448979592,
1972
+ "grad_norm": 0.24942266941070557,
1973
+ "learning_rate": 0.00018844537641667176,
1974
+ "loss": 0.1526,
1975
+ "step": 178
1976
+ },
1977
+ {
1978
+ "epoch": 2.906122448979592,
1979
+ "eval_loss": 0.9967045783996582,
1980
+ "eval_runtime": 18.2597,
1981
+ "eval_samples_per_second": 0.876,
1982
+ "eval_steps_per_second": 0.876,
1983
+ "step": 178
1984
+ },
1985
+ {
1986
+ "epoch": 2.9224489795918367,
1987
+ "grad_norm": 0.2336956411600113,
1988
+ "learning_rate": 0.0001864387330663399,
1989
+ "loss": 0.1352,
1990
+ "step": 179
1991
+ },
1992
+ {
1993
+ "epoch": 2.938775510204082,
1994
+ "grad_norm": 0.2014392614364624,
1995
+ "learning_rate": 0.0001844334602705047,
1996
+ "loss": 0.1177,
1997
+ "step": 180
1998
+ },
1999
+ {
2000
+ "epoch": 2.938775510204082,
2001
+ "eval_loss": 0.9912804365158081,
2002
+ "eval_runtime": 18.2221,
2003
+ "eval_samples_per_second": 0.878,
2004
+ "eval_steps_per_second": 0.878,
2005
+ "step": 180
2006
+ },
2007
+ {
2008
+ "epoch": 2.938775510204082,
2009
+ "eval_loss": 0.9912804365158081,
2010
+ "eval_runtime": 18.3966,
2011
+ "eval_samples_per_second": 0.87,
2012
+ "eval_steps_per_second": 0.87,
2013
+ "step": 180
2014
+ },
2015
+ {
2016
+ "epoch": 2.963265306122449,
2017
+ "grad_norm": 0.2360977977514267,
2018
+ "learning_rate": 0.00018242976068985137,
2019
+ "loss": 0.1276,
2020
+ "step": 181
2021
+ },
2022
+ {
2023
+ "epoch": 2.979591836734694,
2024
+ "grad_norm": 0.22097723186016083,
2025
+ "learning_rate": 0.0001804278368260697,
2026
+ "loss": 0.1292,
2027
+ "step": 182
2028
+ },
2029
+ {
2030
+ "epoch": 2.979591836734694,
2031
+ "eval_loss": 0.9996596574783325,
2032
+ "eval_runtime": 18.2418,
2033
+ "eval_samples_per_second": 0.877,
2034
+ "eval_steps_per_second": 0.877,
2035
+ "step": 182
2036
+ },
2037
+ {
2038
+ "epoch": 2.9959183673469387,
2039
+ "grad_norm": 0.19727876782417297,
2040
+ "learning_rate": 0.00017842789100138868,
2041
+ "loss": 0.0994,
2042
+ "step": 183
2043
+ },
2044
+ {
2045
+ "epoch": 3.012244897959184,
2046
+ "grad_norm": 0.4426736533641815,
2047
+ "learning_rate": 0.0001764301253381289,
2048
+ "loss": 0.1507,
2049
+ "step": 184
2050
+ },
2051
+ {
2052
+ "epoch": 3.012244897959184,
2053
+ "eval_loss": 1.0262768268585205,
2054
+ "eval_runtime": 18.259,
2055
+ "eval_samples_per_second": 0.876,
2056
+ "eval_steps_per_second": 0.876,
2057
+ "step": 184
2058
+ },
2059
+ {
2060
+ "epoch": 3.0285714285714285,
2061
+ "grad_norm": 0.1821659505367279,
2062
+ "learning_rate": 0.00017443474173827532,
2063
+ "loss": 0.0588,
2064
+ "step": 185
2065
+ },
2066
+ {
2067
+ "epoch": 3.0448979591836736,
2068
+ "grad_norm": 0.2281961441040039,
2069
+ "learning_rate": 0.0001724419418630724,
2070
+ "loss": 0.0765,
2071
+ "step": 186
2072
+ },
2073
+ {
2074
+ "epoch": 3.0448979591836736,
2075
+ "eval_loss": 1.0732572078704834,
2076
+ "eval_runtime": 18.2807,
2077
+ "eval_samples_per_second": 0.875,
2078
+ "eval_steps_per_second": 0.875,
2079
+ "step": 186
2080
+ },
2081
+ {
2082
+ "epoch": 3.061224489795918,
2083
+ "grad_norm": 0.19735883176326752,
2084
+ "learning_rate": 0.0001704519271126433,
2085
+ "loss": 0.0542,
2086
+ "step": 187
2087
+ },
2088
+ {
2089
+ "epoch": 3.0775510204081633,
2090
+ "grad_norm": 0.23131243884563446,
2091
+ "learning_rate": 0.0001684648986056355,
2092
+ "loss": 0.0604,
2093
+ "step": 188
2094
+ },
2095
+ {
2096
+ "epoch": 3.0775510204081633,
2097
+ "eval_loss": 1.10750150680542,
2098
+ "eval_runtime": 18.2728,
2099
+ "eval_samples_per_second": 0.876,
2100
+ "eval_steps_per_second": 0.876,
2101
+ "step": 188
2102
+ },
2103
+ {
2104
+ "epoch": 3.093877551020408,
2105
+ "grad_norm": 0.25719910860061646,
2106
+ "learning_rate": 0.0001664810571588952,
2107
+ "loss": 0.0705,
2108
+ "step": 189
2109
+ },
2110
+ {
2111
+ "epoch": 3.110204081632653,
2112
+ "grad_norm": 0.23448176681995392,
2113
+ "learning_rate": 0.00016450060326717177,
2114
+ "loss": 0.061,
2115
+ "step": 190
2116
+ },
2117
+ {
2118
+ "epoch": 3.110204081632653,
2119
+ "eval_loss": 1.0981874465942383,
2120
+ "eval_runtime": 18.2548,
2121
+ "eval_samples_per_second": 0.876,
2122
+ "eval_steps_per_second": 0.876,
2123
+ "step": 190
2124
+ },
2125
+ {
2126
+ "epoch": 3.126530612244898,
2127
+ "grad_norm": 0.2236451804637909,
2128
+ "learning_rate": 0.00016252373708285504,
2129
+ "loss": 0.0492,
2130
+ "step": 191
2131
+ },
2132
+ {
2133
+ "epoch": 3.142857142857143,
2134
+ "grad_norm": 0.22379790246486664,
2135
+ "learning_rate": 0.00016055065839574743,
2136
+ "loss": 0.0622,
2137
+ "step": 192
2138
+ },
2139
+ {
2140
+ "epoch": 3.142857142857143,
2141
+ "eval_loss": 1.0731853246688843,
2142
+ "eval_runtime": 18.2828,
2143
+ "eval_samples_per_second": 0.875,
2144
+ "eval_steps_per_second": 0.875,
2145
+ "step": 192
2146
+ },
2147
+ {
2148
+ "epoch": 3.159183673469388,
2149
+ "grad_norm": 0.23106735944747925,
2150
+ "learning_rate": 0.00015858156661287178,
2151
+ "loss": 0.0715,
2152
+ "step": 193
2153
+ },
2154
+ {
2155
+ "epoch": 3.1755102040816325,
2156
+ "grad_norm": 0.23755702376365662,
2157
+ "learning_rate": 0.00015661666073831895,
2158
+ "loss": 0.0794,
2159
+ "step": 194
2160
+ },
2161
+ {
2162
+ "epoch": 3.1755102040816325,
2163
+ "eval_loss": 1.06235671043396,
2164
+ "eval_runtime": 18.305,
2165
+ "eval_samples_per_second": 0.874,
2166
+ "eval_steps_per_second": 0.874,
2167
+ "step": 194
2168
+ },
2169
+ {
2170
+ "epoch": 3.1918367346938776,
2171
+ "grad_norm": 0.22150100767612457,
2172
+ "learning_rate": 0.0001546561393531357,
2173
+ "loss": 0.0687,
2174
+ "step": 195
2175
+ },
2176
+ {
2177
+ "epoch": 3.2081632653061223,
2178
+ "grad_norm": 0.1758776307106018,
2179
+ "learning_rate": 0.0001527002005952551,
2180
+ "loss": 0.0498,
2181
+ "step": 196
2182
+ },
2183
+ {
2184
+ "epoch": 3.2081632653061223,
2185
+ "eval_loss": 1.073830008506775,
2186
+ "eval_runtime": 18.3237,
2187
+ "eval_samples_per_second": 0.873,
2188
+ "eval_steps_per_second": 0.873,
2189
+ "step": 196
2190
+ },
2191
+ {
2192
+ "epoch": 3.2244897959183674,
2193
+ "grad_norm": 0.23125389218330383,
2194
+ "learning_rate": 0.000150749042139472,
2195
+ "loss": 0.08,
2196
+ "step": 197
2197
+ },
2198
+ {
2199
+ "epoch": 3.240816326530612,
2200
+ "grad_norm": 0.2143053263425827,
2201
+ "learning_rate": 0.00014880286117746548,
2202
+ "loss": 0.06,
2203
+ "step": 198
2204
+ },
2205
+ {
2206
+ "epoch": 3.240816326530612,
2207
+ "eval_loss": 1.1210918426513672,
2208
+ "eval_runtime": 18.3294,
2209
+ "eval_samples_per_second": 0.873,
2210
+ "eval_steps_per_second": 0.873,
2211
+ "step": 198
2212
+ },
2213
+ {
2214
+ "epoch": 3.257142857142857,
2215
+ "grad_norm": 0.20991010963916779,
2216
+ "learning_rate": 0.0001468618543978695,
2217
+ "loss": 0.0549,
2218
+ "step": 199
2219
+ },
2220
+ {
2221
+ "epoch": 3.273469387755102,
2222
+ "grad_norm": 0.21787025034427643,
2223
+ "learning_rate": 0.00014492621796639504,
2224
+ "loss": 0.0515,
2225
+ "step": 200
2226
+ },
2227
+ {
2228
+ "epoch": 3.273469387755102,
2229
+ "eval_loss": 1.15009343624115,
2230
+ "eval_runtime": 18.3182,
2231
+ "eval_samples_per_second": 0.873,
2232
+ "eval_steps_per_second": 0.873,
2233
+ "step": 200
2234
+ },
2235
+ {
2236
+ "epoch": 3.289795918367347,
2237
+ "grad_norm": 0.22523745894432068,
2238
+ "learning_rate": 0.00014299614750600478,
2239
+ "loss": 0.0499,
2240
+ "step": 201
2241
+ },
2242
+ {
2243
+ "epoch": 3.306122448979592,
2244
+ "grad_norm": 0.21396824717521667,
2245
+ "learning_rate": 0.00014107183807714275,
2246
+ "loss": 0.0484,
2247
+ "step": 202
2248
+ },
2249
+ {
2250
+ "epoch": 3.306122448979592,
2251
+ "eval_loss": 1.1507196426391602,
2252
+ "eval_runtime": 18.3345,
2253
+ "eval_samples_per_second": 0.873,
2254
+ "eval_steps_per_second": 0.873,
2255
+ "step": 202
2256
+ },
2257
+ {
2258
+ "epoch": 3.3224489795918366,
2259
+ "grad_norm": 0.23024530708789825,
2260
+ "learning_rate": 0.00013915348415802036,
2261
+ "loss": 0.0647,
2262
+ "step": 203
2263
+ },
2264
+ {
2265
+ "epoch": 3.3387755102040817,
2266
+ "grad_norm": 0.20833072066307068,
2267
+ "learning_rate": 0.0001372412796249625,
2268
+ "loss": 0.0576,
2269
+ "step": 204
2270
+ },
2271
+ {
2272
+ "epoch": 3.3387755102040817,
2273
+ "eval_loss": 1.1334972381591797,
2274
+ "eval_runtime": 18.3296,
2275
+ "eval_samples_per_second": 0.873,
2276
+ "eval_steps_per_second": 0.873,
2277
+ "step": 204
2278
+ },
2279
+ {
2280
+ "epoch": 3.3551020408163263,
2281
+ "grad_norm": 0.2296619713306427,
2282
+ "learning_rate": 0.00013533541773281274,
2283
+ "loss": 0.0843,
2284
+ "step": 205
2285
+ },
2286
+ {
2287
+ "epoch": 3.3714285714285714,
2288
+ "grad_norm": 0.1846872717142105,
2289
+ "learning_rate": 0.0001334360910954027,
2290
+ "loss": 0.0562,
2291
+ "step": 206
2292
+ },
2293
+ {
2294
+ "epoch": 3.3714285714285714,
2295
+ "eval_loss": 1.1273655891418457,
2296
+ "eval_runtime": 18.3216,
2297
+ "eval_samples_per_second": 0.873,
2298
+ "eval_steps_per_second": 0.873,
2299
+ "step": 206
2300
+ },
2301
+ {
2302
+ "epoch": 3.387755102040816,
2303
+ "grad_norm": 0.1895626038312912,
2304
+ "learning_rate": 0.00013154349166608577,
2305
+ "loss": 0.0556,
2306
+ "step": 207
2307
+ },
2308
+ {
2309
+ "epoch": 3.404081632653061,
2310
+ "grad_norm": 0.34628579020500183,
2311
+ "learning_rate": 0.00012965781071833752,
2312
+ "loss": 0.1337,
2313
+ "step": 208
2314
+ },
2315
+ {
2316
+ "epoch": 3.404081632653061,
2317
+ "eval_loss": 1.1414172649383545,
2318
+ "eval_runtime": 18.3347,
2319
+ "eval_samples_per_second": 0.873,
2320
+ "eval_steps_per_second": 0.873,
2321
+ "step": 208
2322
+ },
2323
+ {
2324
+ "epoch": 3.4204081632653063,
2325
+ "grad_norm": 0.20633243024349213,
2326
+ "learning_rate": 0.0001277792388264245,
2327
+ "loss": 0.0627,
2328
+ "step": 209
2329
+ },
2330
+ {
2331
+ "epoch": 3.436734693877551,
2332
+ "grad_norm": 0.19947534799575806,
2333
+ "learning_rate": 0.00012590796584614484,
2334
+ "loss": 0.0478,
2335
+ "step": 210
2336
+ },
2337
+ {
2338
+ "epoch": 3.436734693877551,
2339
+ "eval_loss": 1.1656532287597656,
2340
+ "eval_runtime": 18.3137,
2341
+ "eval_samples_per_second": 0.874,
2342
+ "eval_steps_per_second": 0.874,
2343
+ "step": 210
2344
+ },
2345
+ {
2346
+ "epoch": 3.453061224489796,
2347
+ "grad_norm": 0.21546797454357147,
2348
+ "learning_rate": 0.0001240441808956398,
2349
+ "loss": 0.0672,
2350
+ "step": 211
2351
+ },
2352
+ {
2353
+ "epoch": 3.4693877551020407,
2354
+ "grad_norm": 0.2232857644557953,
2355
+ "learning_rate": 0.00012218807233628138,
2356
+ "loss": 0.0597,
2357
+ "step": 212
2358
+ },
2359
+ {
2360
+ "epoch": 3.4693877551020407,
2361
+ "eval_loss": 1.1744612455368042,
2362
+ "eval_runtime": 18.3397,
2363
+ "eval_samples_per_second": 0.872,
2364
+ "eval_steps_per_second": 0.872,
2365
+ "step": 212
2366
+ },
2367
+ {
2368
+ "epoch": 3.4857142857142858,
2369
+ "grad_norm": 0.23030999302864075,
2370
+ "learning_rate": 0.00012033982775363548,
2371
+ "loss": 0.0586,
2372
+ "step": 213
2373
+ },
2374
+ {
2375
+ "epoch": 3.502040816326531,
2376
+ "grad_norm": 0.21055705845355988,
2377
+ "learning_rate": 0.00011849963393850383,
2378
+ "loss": 0.0618,
2379
+ "step": 214
2380
+ },
2381
+ {
2382
+ "epoch": 3.502040816326531,
2383
+ "eval_loss": 1.1754231452941895,
2384
+ "eval_runtime": 18.3637,
2385
+ "eval_samples_per_second": 0.871,
2386
+ "eval_steps_per_second": 0.871,
2387
+ "step": 214
2388
+ },
2389
+ {
2390
+ "epoch": 3.5183673469387755,
2391
+ "grad_norm": 0.18197622895240784,
2392
+ "learning_rate": 0.00011666767686804641,
2393
+ "loss": 0.0475,
2394
+ "step": 215
2395
+ },
2396
+ {
2397
+ "epoch": 3.53469387755102,
2398
+ "grad_norm": 0.24238142371177673,
2399
+ "learning_rate": 0.00011484414168698547,
2400
+ "loss": 0.0686,
2401
+ "step": 216
2402
+ },
2403
+ {
2404
+ "epoch": 3.53469387755102,
2405
+ "eval_loss": 1.1673252582550049,
2406
+ "eval_runtime": 18.3403,
2407
+ "eval_samples_per_second": 0.872,
2408
+ "eval_steps_per_second": 0.872,
2409
+ "step": 216
2410
+ },
2411
+ {
2412
+ "epoch": 3.5510204081632653,
2413
+ "grad_norm": 0.2360972762107849,
2414
+ "learning_rate": 0.00011302921268889432,
2415
+ "loss": 0.0738,
2416
+ "step": 217
2417
+ },
2418
+ {
2419
+ "epoch": 3.5673469387755103,
2420
+ "grad_norm": 0.2011600285768509,
2421
+ "learning_rate": 0.00011122307329757206,
2422
+ "loss": 0.0501,
2423
+ "step": 218
2424
+ },
2425
+ {
2426
+ "epoch": 3.5673469387755103,
2427
+ "eval_loss": 1.1578516960144043,
2428
+ "eval_runtime": 18.3646,
2429
+ "eval_samples_per_second": 0.871,
2430
+ "eval_steps_per_second": 0.871,
2431
+ "step": 218
2432
+ },
2433
+ {
2434
+ "epoch": 3.583673469387755,
2435
+ "grad_norm": 0.22133193910121918,
2436
+ "learning_rate": 0.00010942590604850553,
2437
+ "loss": 0.0662,
2438
+ "step": 219
2439
+ },
2440
+ {
2441
+ "epoch": 3.6,
2442
+ "grad_norm": 0.19864347577095032,
2443
+ "learning_rate": 0.0001076378925704221,
2444
+ "loss": 0.0525,
2445
+ "step": 220
2446
+ },
2447
+ {
2448
+ "epoch": 3.6,
2449
+ "eval_loss": 1.147334337234497,
2450
+ "eval_runtime": 18.3364,
2451
+ "eval_samples_per_second": 0.873,
2452
+ "eval_steps_per_second": 0.873,
2453
+ "step": 220
2454
+ },
2455
+ {
2456
+ "epoch": 3.6163265306122447,
2457
+ "grad_norm": 0.1864493042230606,
2458
+ "learning_rate": 0.0001058592135669335,
2459
+ "loss": 0.0584,
2460
+ "step": 221
2461
+ },
2462
+ {
2463
+ "epoch": 3.63265306122449,
2464
+ "grad_norm": 0.1753772795200348,
2465
+ "learning_rate": 0.00010409004879827282,
2466
+ "loss": 0.0508,
2467
+ "step": 222
2468
+ },
2469
+ {
2470
+ "epoch": 3.63265306122449,
2471
+ "eval_loss": 1.1439639329910278,
2472
+ "eval_runtime": 18.3232,
2473
+ "eval_samples_per_second": 0.873,
2474
+ "eval_steps_per_second": 0.873,
2475
+ "step": 222
2476
+ },
2477
+ {
2478
+ "epoch": 3.648979591836735,
2479
+ "grad_norm": 0.18084004521369934,
2480
+ "learning_rate": 0.00010233057706312767,
2481
+ "loss": 0.0486,
2482
+ "step": 223
2483
+ },
2484
+ {
2485
+ "epoch": 3.6653061224489796,
2486
+ "grad_norm": 0.19728556275367737,
2487
+ "learning_rate": 0.00010058097618056992,
2488
+ "loss": 0.0545,
2489
+ "step": 224
2490
+ },
2491
+ {
2492
+ "epoch": 3.6653061224489796,
2493
+ "eval_loss": 1.1501585245132446,
2494
+ "eval_runtime": 18.2988,
2495
+ "eval_samples_per_second": 0.874,
2496
+ "eval_steps_per_second": 0.874,
2497
+ "step": 224
2498
+ },
2499
+ {
2500
+ "epoch": 3.6816326530612242,
2501
+ "grad_norm": 0.22434309124946594,
2502
+ "learning_rate": 9.88414229720843e-05,
2503
+ "loss": 0.0502,
2504
+ "step": 225
2505
+ },
2506
+ {
2507
+ "epoch": 3.6979591836734693,
2508
+ "grad_norm": 0.20542308688163757,
2509
+ "learning_rate": 9.711209324369869e-05,
2510
+ "loss": 0.0513,
2511
+ "step": 226
2512
+ },
2513
+ {
2514
+ "epoch": 3.6979591836734693,
2515
+ "eval_loss": 1.160825490951538,
2516
+ "eval_runtime": 18.2895,
2517
+ "eval_samples_per_second": 0.875,
2518
+ "eval_steps_per_second": 0.875,
2519
+ "step": 226
2520
+ },
2521
+ {
2522
+ "epoch": 3.7142857142857144,
2523
+ "grad_norm": 0.1923072785139084,
2524
+ "learning_rate": 9.539316176821638e-05,
2525
+ "loss": 0.0495,
2526
+ "step": 227
2527
+ },
2528
+ {
2529
+ "epoch": 3.730612244897959,
2530
+ "grad_norm": 0.22612810134887695,
2531
+ "learning_rate": 9.368480226755238e-05,
2532
+ "loss": 0.0678,
2533
+ "step": 228
2534
+ },
2535
+ {
2536
+ "epoch": 3.730612244897959,
2537
+ "eval_loss": 1.167827844619751,
2538
+ "eval_runtime": 18.2707,
2539
+ "eval_samples_per_second": 0.876,
2540
+ "eval_steps_per_second": 0.876,
2541
+ "step": 228
2542
+ },
2543
+ {
2544
+ "epoch": 3.746938775510204,
2545
+ "grad_norm": 0.20918408036231995,
2546
+ "learning_rate": 9.198718739517685e-05,
2547
+ "loss": 0.0584,
2548
+ "step": 229
2549
+ },
2550
+ {
2551
+ "epoch": 3.763265306122449,
2552
+ "grad_norm": 0.20327749848365784,
2553
+ "learning_rate": 9.030048871866599e-05,
2554
+ "loss": 0.064,
2555
+ "step": 230
2556
+ },
2557
+ {
2558
+ "epoch": 3.763265306122449,
2559
+ "eval_loss": 1.1593577861785889,
2560
+ "eval_runtime": 18.2836,
2561
+ "eval_samples_per_second": 0.875,
2562
+ "eval_steps_per_second": 0.875,
2563
+ "step": 230
2564
+ },
2565
+ {
2566
+ "epoch": 3.779591836734694,
2567
+ "grad_norm": 0.2150719165802002,
2568
+ "learning_rate": 8.862487670236248e-05,
2569
+ "loss": 0.0649,
2570
+ "step": 231
2571
+ },
2572
+ {
2573
+ "epoch": 3.795918367346939,
2574
+ "grad_norm": 0.2021542638540268,
2575
+ "learning_rate": 8.696052069014804e-05,
2576
+ "loss": 0.0578,
2577
+ "step": 232
2578
+ },
2579
+ {
2580
+ "epoch": 3.795918367346939,
2581
+ "eval_loss": 1.1511321067810059,
2582
+ "eval_runtime": 18.2561,
2583
+ "eval_samples_per_second": 0.876,
2584
+ "eval_steps_per_second": 0.876,
2585
+ "step": 232
2586
+ },
2587
+ {
2588
+ "epoch": 3.8122448979591836,
2589
+ "grad_norm": 0.18323124945163727,
2590
+ "learning_rate": 8.53075888883289e-05,
2591
+ "loss": 0.0462,
2592
+ "step": 233
2593
+ },
2594
+ {
2595
+ "epoch": 3.8285714285714287,
2596
+ "grad_norm": 0.20034129917621613,
2597
+ "learning_rate": 8.366624834863585e-05,
2598
+ "loss": 0.0548,
2599
+ "step": 234
2600
+ },
2601
+ {
2602
+ "epoch": 3.8285714285714287,
2603
+ "eval_loss": 1.1508455276489258,
2604
+ "eval_runtime": 18.2577,
2605
+ "eval_samples_per_second": 0.876,
2606
+ "eval_steps_per_second": 0.876,
2607
+ "step": 234
2608
+ },
2609
+ {
2610
+ "epoch": 3.8448979591836734,
2611
+ "grad_norm": 0.2235688865184784,
2612
+ "learning_rate": 8.203666495134159e-05,
2613
+ "loss": 0.0642,
2614
+ "step": 235
2615
+ },
2616
+ {
2617
+ "epoch": 3.8612244897959185,
2618
+ "grad_norm": 0.22254431247711182,
2619
+ "learning_rate": 8.04190033884963e-05,
2620
+ "loss": 0.0671,
2621
+ "step": 236
2622
+ },
2623
+ {
2624
+ "epoch": 3.8612244897959185,
2625
+ "eval_loss": 1.1543577909469604,
2626
+ "eval_runtime": 18.2697,
2627
+ "eval_samples_per_second": 0.876,
2628
+ "eval_steps_per_second": 0.876,
2629
+ "step": 236
2630
+ },
2631
+ {
2632
+ "epoch": 3.877551020408163,
2633
+ "grad_norm": 0.18185441195964813,
2634
+ "learning_rate": 7.881342714728275e-05,
2635
+ "loss": 0.0556,
2636
+ "step": 237
2637
+ },
2638
+ {
2639
+ "epoch": 3.8938775510204082,
2640
+ "grad_norm": 0.19241996109485626,
2641
+ "learning_rate": 7.722009849349447e-05,
2642
+ "loss": 0.0477,
2643
+ "step": 238
2644
+ },
2645
+ {
2646
+ "epoch": 3.8938775510204082,
2647
+ "eval_loss": 1.1588821411132812,
2648
+ "eval_runtime": 18.2702,
2649
+ "eval_samples_per_second": 0.876,
2650
+ "eval_steps_per_second": 0.876,
2651
+ "step": 238
2652
+ },
2653
+ {
2654
+ "epoch": 3.910204081632653,
2655
+ "grad_norm": 0.2237924337387085,
2656
+ "learning_rate": 7.563917845513577e-05,
2657
+ "loss": 0.0617,
2658
+ "step": 239
2659
+ },
2660
+ {
2661
+ "epoch": 3.926530612244898,
2662
+ "grad_norm": 0.2120658904314041,
2663
+ "learning_rate": 7.407082680614799e-05,
2664
+ "loss": 0.0533,
2665
+ "step": 240
2666
+ },
2667
+ {
2668
+ "epoch": 3.926530612244898,
2669
+ "eval_loss": 1.158017635345459,
2670
+ "eval_runtime": 18.2939,
2671
+ "eval_samples_per_second": 0.875,
2672
+ "eval_steps_per_second": 0.875,
2673
+ "step": 240
2674
+ },
2675
+ {
2676
+ "epoch": 3.942857142857143,
2677
+ "grad_norm": 0.227312833070755,
2678
+ "learning_rate": 7.251520205026205e-05,
2679
+ "loss": 0.0706,
2680
+ "step": 241
2681
+ },
2682
+ {
2683
+ "epoch": 3.9591836734693877,
2684
+ "grad_norm": 0.18778285384178162,
2685
+ "learning_rate": 7.097246140497953e-05,
2686
+ "loss": 0.0527,
2687
+ "step": 242
2688
+ },
2689
+ {
2690
+ "epoch": 3.9591836734693877,
2691
+ "eval_loss": 1.1489660739898682,
2692
+ "eval_runtime": 18.262,
2693
+ "eval_samples_per_second": 0.876,
2694
+ "eval_steps_per_second": 0.876,
2695
+ "step": 242
2696
+ },
2697
+ {
2698
+ "epoch": 3.975510204081633,
2699
+ "grad_norm": 0.19356583058834076,
2700
+ "learning_rate": 6.944276078568326e-05,
2701
+ "loss": 0.0493,
2702
+ "step": 243
2703
+ },
2704
+ {
2705
+ "epoch": 3.9918367346938775,
2706
+ "grad_norm": 0.19286511838436127,
2707
+ "learning_rate": 6.792625478988064e-05,
2708
+ "loss": 0.0509,
2709
+ "step": 244
2710
+ },
2711
+ {
2712
+ "epoch": 3.9918367346938775,
2713
+ "eval_loss": 1.1436331272125244,
2714
+ "eval_runtime": 18.2861,
2715
+ "eval_samples_per_second": 0.875,
2716
+ "eval_steps_per_second": 0.875,
2717
+ "step": 244
2718
+ },
2719
+ {
2720
+ "epoch": 4.0081632653061225,
2721
+ "grad_norm": 0.3620785176753998,
2722
+ "learning_rate": 6.642309668157873e-05,
2723
+ "loss": 0.0583,
2724
+ "step": 245
2725
+ },
2726
+ {
2727
+ "epoch": 4.024489795918368,
2728
+ "grad_norm": 0.1391618847846985,
2729
+ "learning_rate": 6.49334383757951e-05,
2730
+ "loss": 0.0322,
2731
+ "step": 246
2732
+ },
2733
+ {
2734
+ "epoch": 4.024489795918368,
2735
+ "eval_loss": 1.1510474681854248,
2736
+ "eval_runtime": 18.2582,
2737
+ "eval_samples_per_second": 0.876,
2738
+ "eval_steps_per_second": 0.876,
2739
+ "step": 246
2740
+ },
2741
+ {
2742
+ "epoch": 4.040816326530612,
2743
+ "grad_norm": 0.12477612495422363,
2744
+ "learning_rate": 6.345743042320471e-05,
2745
+ "loss": 0.0312,
2746
+ "step": 247
2747
+ },
2748
+ {
2749
+ "epoch": 4.057142857142857,
2750
+ "grad_norm": 0.13875025510787964,
2751
+ "learning_rate": 6.199522199492458e-05,
2752
+ "loss": 0.0265,
2753
+ "step": 248
2754
+ },
2755
+ {
2756
+ "epoch": 4.057142857142857,
2757
+ "eval_loss": 1.1840749979019165,
2758
+ "eval_runtime": 18.2575,
2759
+ "eval_samples_per_second": 0.876,
2760
+ "eval_steps_per_second": 0.876,
2761
+ "step": 248
2762
+ },
2763
+ {
2764
+ "epoch": 4.073469387755102,
2765
+ "grad_norm": 0.12535437941551208,
2766
+ "learning_rate": 6.0546960867437854e-05,
2767
+ "loss": 0.0202,
2768
+ "step": 249
2769
+ },
2770
+ {
2771
+ "epoch": 4.089795918367347,
2772
+ "grad_norm": 0.13667362928390503,
2773
+ "learning_rate": 5.911279340765941e-05,
2774
+ "loss": 0.0184,
2775
+ "step": 250
2776
+ },
2777
+ {
2778
+ "epoch": 4.089795918367347,
2779
+ "eval_loss": 1.2291345596313477,
2780
+ "eval_runtime": 18.2603,
2781
+ "eval_samples_per_second": 0.876,
2782
+ "eval_steps_per_second": 0.876,
2783
+ "step": 250
2784
+ },
2785
+ {
2786
+ "epoch": 4.106122448979592,
2787
+ "grad_norm": 0.14251337945461273,
2788
+ "learning_rate": 5.7692864558142934e-05,
2789
+ "loss": 0.0181,
2790
+ "step": 251
2791
+ },
2792
+ {
2793
+ "epoch": 4.122448979591836,
2794
+ "grad_norm": 0.1433674395084381,
2795
+ "learning_rate": 5.628731782243268e-05,
2796
+ "loss": 0.0214,
2797
+ "step": 252
2798
+ },
2799
+ {
2800
+ "epoch": 4.122448979591836,
2801
+ "eval_loss": 1.2775920629501343,
2802
+ "eval_runtime": 18.2768,
2803
+ "eval_samples_per_second": 0.875,
2804
+ "eval_steps_per_second": 0.875,
2805
+ "step": 252
2806
+ },
2807
+ {
2808
+ "epoch": 4.1387755102040815,
2809
+ "grad_norm": 0.15012766420841217,
2810
+ "learning_rate": 5.4896295250560434e-05,
2811
+ "loss": 0.0183,
2812
+ "step": 253
2813
+ },
2814
+ {
2815
+ "epoch": 4.155102040816327,
2816
+ "grad_norm": 0.17076925933361053,
2817
+ "learning_rate": 5.3519937424689394e-05,
2818
+ "loss": 0.019,
2819
+ "step": 254
2820
+ },
2821
+ {
2822
+ "epoch": 4.155102040816327,
2823
+ "eval_loss": 1.3157516717910767,
2824
+ "eval_runtime": 18.2837,
2825
+ "eval_samples_per_second": 0.875,
2826
+ "eval_steps_per_second": 0.875,
2827
+ "step": 254
2828
+ },
2829
+ {
2830
+ "epoch": 4.171428571428572,
2831
+ "grad_norm": 0.1613532155752182,
2832
+ "learning_rate": 5.215838344490631e-05,
2833
+ "loss": 0.0179,
2834
+ "step": 255
2835
+ },
2836
+ {
2837
+ "epoch": 4.187755102040816,
2838
+ "grad_norm": 0.1661355346441269,
2839
+ "learning_rate": 5.081177091516358e-05,
2840
+ "loss": 0.02,
2841
+ "step": 256
2842
+ },
2843
+ {
2844
+ "epoch": 4.187755102040816,
2845
+ "eval_loss": 1.3386974334716797,
2846
+ "eval_runtime": 18.2522,
2847
+ "eval_samples_per_second": 0.877,
2848
+ "eval_steps_per_second": 0.877,
2849
+ "step": 256
2850
+ },
2851
+ {
2852
+ "epoch": 4.204081632653061,
2853
+ "grad_norm": 0.15871840715408325,
2854
+ "learning_rate": 4.9480235929372434e-05,
2855
+ "loss": 0.0184,
2856
+ "step": 257
2857
+ },
2858
+ {
2859
+ "epoch": 4.220408163265306,
2860
+ "grad_norm": 0.17244984209537506,
2861
+ "learning_rate": 4.8163913057648714e-05,
2862
+ "loss": 0.0182,
2863
+ "step": 258
2864
+ },
2865
+ {
2866
+ "epoch": 4.220408163265306,
2867
+ "eval_loss": 1.3454052209854126,
2868
+ "eval_runtime": 18.2673,
2869
+ "eval_samples_per_second": 0.876,
2870
+ "eval_steps_per_second": 0.876,
2871
+ "step": 258
2872
+ },
2873
+ {
2874
+ "epoch": 4.236734693877551,
2875
+ "grad_norm": 0.15932978689670563,
2876
+ "learning_rate": 4.686293533271271e-05,
2877
+ "loss": 0.0181,
2878
+ "step": 259
2879
+ },
2880
+ {
2881
+ "epoch": 4.253061224489796,
2882
+ "grad_norm": 0.17341765761375427,
2883
+ "learning_rate": 4.5577434236444404e-05,
2884
+ "loss": 0.0176,
2885
+ "step": 260
2886
+ },
2887
+ {
2888
+ "epoch": 4.253061224489796,
2889
+ "eval_loss": 1.3430368900299072,
2890
+ "eval_runtime": 18.2538,
2891
+ "eval_samples_per_second": 0.877,
2892
+ "eval_steps_per_second": 0.877,
2893
+ "step": 260
2894
+ },
2895
+ {
2896
+ "epoch": 4.2693877551020405,
2897
+ "grad_norm": 0.16669811308383942,
2898
+ "learning_rate": 4.4307539686595334e-05,
2899
+ "loss": 0.0167,
2900
+ "step": 261
2901
+ },
2902
+ {
2903
+ "epoch": 4.285714285714286,
2904
+ "grad_norm": 0.13549935817718506,
2905
+ "learning_rate": 4.3053380023658595e-05,
2906
+ "loss": 0.0134,
2907
+ "step": 262
2908
+ },
2909
+ {
2910
+ "epoch": 4.285714285714286,
2911
+ "eval_loss": 1.3340528011322021,
2912
+ "eval_runtime": 18.2721,
2913
+ "eval_samples_per_second": 0.876,
2914
+ "eval_steps_per_second": 0.876,
2915
+ "step": 262
2916
+ },
2917
+ {
2918
+ "epoch": 4.302040816326531,
2919
+ "grad_norm": 0.14491026103496552,
2920
+ "learning_rate": 4.1815081997898345e-05,
2921
+ "loss": 0.0153,
2922
+ "step": 263
2923
+ },
2924
+ {
2925
+ "epoch": 4.318367346938776,
2926
+ "grad_norm": 0.13227814435958862,
2927
+ "learning_rate": 4.05927707565398e-05,
2928
+ "loss": 0.0162,
2929
+ "step": 264
2930
+ },
2931
+ {
2932
+ "epoch": 4.318367346938776,
2933
+ "eval_loss": 1.3255767822265625,
2934
+ "eval_runtime": 18.2895,
2935
+ "eval_samples_per_second": 0.875,
2936
+ "eval_steps_per_second": 0.875,
2937
+ "step": 264
2938
+ },
2939
+ {
2940
+ "epoch": 4.33469387755102,
2941
+ "grad_norm": 0.166014164686203,
2942
+ "learning_rate": 3.9386569831121476e-05,
2943
+ "loss": 0.0239,
2944
+ "step": 265
2945
+ },
2946
+ {
2947
+ "epoch": 4.351020408163265,
2948
+ "grad_norm": 0.13963960111141205,
2949
+ "learning_rate": 3.819660112501053e-05,
2950
+ "loss": 0.0167,
2951
+ "step": 266
2952
+ },
2953
+ {
2954
+ "epoch": 4.351020408163265,
2955
+ "eval_loss": 1.3155338764190674,
2956
+ "eval_runtime": 18.2671,
2957
+ "eval_samples_per_second": 0.876,
2958
+ "eval_steps_per_second": 0.876,
2959
+ "step": 266
2960
+ },
2961
+ {
2962
+ "epoch": 4.36734693877551,
2963
+ "grad_norm": 0.1515013724565506,
2964
+ "learning_rate": 3.702298490108276e-05,
2965
+ "loss": 0.0161,
2966
+ "step": 267
2967
+ },
2968
+ {
2969
+ "epoch": 4.383673469387755,
2970
+ "grad_norm": 0.16707275807857513,
2971
+ "learning_rate": 3.5865839769568435e-05,
2972
+ "loss": 0.0241,
2973
+ "step": 268
2974
+ },
2975
+ {
2976
+ "epoch": 4.383673469387755,
2977
+ "eval_loss": 1.306105375289917,
2978
+ "eval_runtime": 18.2749,
2979
+ "eval_samples_per_second": 0.876,
2980
+ "eval_steps_per_second": 0.876,
2981
+ "step": 268
2982
+ },
2983
+ {
2984
+ "epoch": 4.4,
2985
+ "grad_norm": 0.1421680599451065,
2986
+ "learning_rate": 3.472528267606492e-05,
2987
+ "loss": 0.0175,
2988
+ "step": 269
2989
+ },
2990
+ {
2991
+ "epoch": 4.416326530612245,
2992
+ "grad_norm": 0.144426167011261,
2993
+ "learning_rate": 3.360142888971789e-05,
2994
+ "loss": 0.0176,
2995
+ "step": 270
2996
+ },
2997
+ {
2998
+ "epoch": 4.416326530612245,
2999
+ "eval_loss": 1.2982478141784668,
3000
+ "eval_runtime": 18.287,
3001
+ "eval_samples_per_second": 0.875,
3002
+ "eval_steps_per_second": 0.875,
3003
+ "step": 270
3004
+ },
3005
+ {
3006
+ "epoch": 4.43265306122449,
3007
+ "grad_norm": 0.1484973430633545,
3008
+ "learning_rate": 3.249439199157167e-05,
3009
+ "loss": 0.0204,
3010
+ "step": 271
3011
+ },
3012
+ {
3013
+ "epoch": 4.448979591836735,
3014
+ "grad_norm": 0.15431199967861176,
3015
+ "learning_rate": 3.140428386309029e-05,
3016
+ "loss": 0.0256,
3017
+ "step": 272
3018
+ },
3019
+ {
3020
+ "epoch": 4.448979591836735,
3021
+ "eval_loss": 1.2938604354858398,
3022
+ "eval_runtime": 18.2628,
3023
+ "eval_samples_per_second": 0.876,
3024
+ "eval_steps_per_second": 0.876,
3025
+ "step": 272
3026
+ },
3027
+ {
3028
+ "epoch": 4.46530612244898,
3029
+ "grad_norm": 0.14612630009651184,
3030
+ "learning_rate": 3.0331214674850316e-05,
3031
+ "loss": 0.0205,
3032
+ "step": 273
3033
+ },
3034
+ {
3035
+ "epoch": 4.481632653061224,
3036
+ "grad_norm": 0.14046533405780792,
3037
+ "learning_rate": 2.927529287540667e-05,
3038
+ "loss": 0.0218,
3039
+ "step": 274
3040
+ },
3041
+ {
3042
+ "epoch": 4.481632653061224,
3043
+ "eval_loss": 1.2913928031921387,
3044
+ "eval_runtime": 18.2621,
3045
+ "eval_samples_per_second": 0.876,
3046
+ "eval_steps_per_second": 0.876,
3047
+ "step": 274
3048
+ },
3049
+ {
3050
+ "epoch": 4.497959183673469,
3051
+ "grad_norm": 0.14122799038887024,
3052
+ "learning_rate": 2.8236625180332256e-05,
3053
+ "loss": 0.0159,
3054
+ "step": 275
3055
+ },
3056
+ {
3057
+ "epoch": 4.514285714285714,
3058
+ "grad_norm": 0.1126718744635582,
3059
+ "learning_rate": 2.7215316561432947e-05,
3060
+ "loss": 0.0155,
3061
+ "step": 276
3062
+ },
3063
+ {
3064
+ "epoch": 4.514285714285714,
3065
+ "eval_loss": 1.2918992042541504,
3066
+ "eval_runtime": 16.7544,
3067
+ "eval_samples_per_second": 0.955,
3068
+ "eval_steps_per_second": 0.955,
3069
+ "step": 276
3070
+ },
3071
+ {
3072
+ "epoch": 4.530612244897959,
3073
+ "grad_norm": 0.1317344307899475,
3074
+ "learning_rate": 2.6211470236138748e-05,
3075
+ "loss": 0.0194,
3076
+ "step": 277
3077
+ },
3078
+ {
3079
+ "epoch": 4.546938775510204,
3080
+ "grad_norm": 0.13652952015399933,
3081
+ "learning_rate": 2.522518765707216e-05,
3082
+ "loss": 0.0184,
3083
+ "step": 278
3084
+ },
3085
+ {
3086
+ "epoch": 4.546938775510204,
3087
+ "eval_loss": 1.2949538230895996,
3088
+ "eval_runtime": 15.9544,
3089
+ "eval_samples_per_second": 1.003,
3090
+ "eval_steps_per_second": 1.003,
3091
+ "step": 278
3092
+ },
3093
+ {
3094
+ "epoch": 4.563265306122449,
3095
+ "grad_norm": 0.2611277103424072,
3096
+ "learning_rate": 2.425656850179505e-05,
3097
+ "loss": 0.0434,
3098
+ "step": 279
3099
+ },
3100
+ {
3101
+ "epoch": 4.579591836734694,
3102
+ "grad_norm": 0.13340182602405548,
3103
+ "learning_rate": 2.3305710662734858e-05,
3104
+ "loss": 0.0187,
3105
+ "step": 280
3106
+ },
3107
+ {
3108
+ "epoch": 4.579591836734694,
3109
+ "eval_loss": 1.2997756004333496,
3110
+ "eval_runtime": 15.9638,
3111
+ "eval_samples_per_second": 1.002,
3112
+ "eval_steps_per_second": 1.002,
3113
+ "step": 280
3114
+ },
3115
+ {
3116
+ "epoch": 4.595918367346939,
3117
+ "grad_norm": 0.13417263329029083,
3118
+ "learning_rate": 2.2372710237291107e-05,
3119
+ "loss": 0.0185,
3120
+ "step": 281
3121
+ },
3122
+ {
3123
+ "epoch": 4.612244897959184,
3124
+ "grad_norm": 0.1171732172369957,
3125
+ "learning_rate": 2.1457661518123562e-05,
3126
+ "loss": 0.015,
3127
+ "step": 282
3128
+ },
3129
+ {
3130
+ "epoch": 4.612244897959184,
3131
+ "eval_loss": 1.3039846420288086,
3132
+ "eval_runtime": 16.1058,
3133
+ "eval_samples_per_second": 0.993,
3134
+ "eval_steps_per_second": 0.993,
3135
+ "step": 282
3136
+ },
3137
+ {
3138
+ "epoch": 4.628571428571428,
3139
+ "grad_norm": 0.14753983914852142,
3140
+ "learning_rate": 2.0560656983622527e-05,
3141
+ "loss": 0.0189,
3142
+ "step": 283
3143
+ },
3144
+ {
3145
+ "epoch": 4.644897959183673,
3146
+ "grad_norm": 0.1579369455575943,
3147
+ "learning_rate": 1.968178728856269e-05,
3148
+ "loss": 0.0201,
3149
+ "step": 284
3150
+ },
3151
+ {
3152
+ "epoch": 4.644897959183673,
3153
+ "eval_loss": 1.307161808013916,
3154
+ "eval_runtime": 15.8569,
3155
+ "eval_samples_per_second": 1.009,
3156
+ "eval_steps_per_second": 1.009,
3157
+ "step": 284
3158
+ },
3159
+ {
3160
+ "epoch": 4.661224489795918,
3161
+ "grad_norm": 0.12243036180734634,
3162
+ "learning_rate": 1.8821141254941187e-05,
3163
+ "loss": 0.0147,
3164
+ "step": 285
3165
+ },
3166
+ {
3167
+ "epoch": 4.677551020408163,
3168
+ "grad_norm": 0.1257927268743515,
3169
+ "learning_rate": 1.797880586300087e-05,
3170
+ "loss": 0.0158,
3171
+ "step": 286
3172
+ },
3173
+ {
3174
+ "epoch": 4.677551020408163,
3175
+ "eval_loss": 1.3113857507705688,
3176
+ "eval_runtime": 15.8584,
3177
+ "eval_samples_per_second": 1.009,
3178
+ "eval_steps_per_second": 1.009,
3179
+ "step": 286
3180
+ },
3181
+ {
3182
+ "epoch": 4.6938775510204085,
3183
+ "grad_norm": 0.17673540115356445,
3184
+ "learning_rate": 1.7154866242439804e-05,
3185
+ "loss": 0.0269,
3186
+ "step": 287
3187
+ },
3188
+ {
3189
+ "epoch": 4.710204081632653,
3190
+ "grad_norm": 0.143116295337677,
3191
+ "learning_rate": 1.6349405663807673e-05,
3192
+ "loss": 0.0257,
3193
+ "step": 288
3194
+ },
3195
+ {
3196
+ "epoch": 4.710204081632653,
3197
+ "eval_loss": 1.3128083944320679,
3198
+ "eval_runtime": 15.883,
3199
+ "eval_samples_per_second": 1.007,
3200
+ "eval_steps_per_second": 1.007,
3201
+ "step": 288
3202
+ },
3203
+ {
3204
+ "epoch": 4.726530612244898,
3205
+ "grad_norm": 0.1345769762992859,
3206
+ "learning_rate": 1.5562505530090155e-05,
3207
+ "loss": 0.0198,
3208
+ "step": 289
3209
+ },
3210
+ {
3211
+ "epoch": 4.742857142857143,
3212
+ "grad_norm": 0.12065534293651581,
3213
+ "learning_rate": 1.4794245368481996e-05,
3214
+ "loss": 0.0173,
3215
+ "step": 290
3216
+ },
3217
+ {
3218
+ "epoch": 4.742857142857143,
3219
+ "eval_loss": 1.314129114151001,
3220
+ "eval_runtime": 15.8958,
3221
+ "eval_samples_per_second": 1.007,
3222
+ "eval_steps_per_second": 1.007,
3223
+ "step": 290
3224
+ },
3225
+ {
3226
+ "epoch": 4.759183673469388,
3227
+ "grad_norm": 0.12258104234933853,
3228
+ "learning_rate": 1.4044702822349731e-05,
3229
+ "loss": 0.0141,
3230
+ "step": 291
3231
+ },
3232
+ {
3233
+ "epoch": 4.775510204081632,
3234
+ "grad_norm": 0.12915143370628357,
3235
+ "learning_rate": 1.3313953643384747e-05,
3236
+ "loss": 0.0144,
3237
+ "step": 292
3238
+ },
3239
+ {
3240
+ "epoch": 4.775510204081632,
3241
+ "eval_loss": 1.31673264503479,
3242
+ "eval_runtime": 15.8895,
3243
+ "eval_samples_per_second": 1.007,
3244
+ "eval_steps_per_second": 1.007,
3245
+ "step": 292
3246
+ },
3247
+ {
3248
+ "epoch": 4.791836734693877,
3249
+ "grad_norm": 0.14802931249141693,
3250
+ "learning_rate": 1.2602071683947404e-05,
3251
+ "loss": 0.0186,
3252
+ "step": 293
3253
+ },
3254
+ {
3255
+ "epoch": 4.808163265306122,
3256
+ "grad_norm": 0.12036965042352676,
3257
+ "learning_rate": 1.1909128889603404e-05,
3258
+ "loss": 0.0176,
3259
+ "step": 294
3260
+ },
3261
+ {
3262
+ "epoch": 4.808163265306122,
3263
+ "eval_loss": 1.3176369667053223,
3264
+ "eval_runtime": 18.1713,
3265
+ "eval_samples_per_second": 0.881,
3266
+ "eval_steps_per_second": 0.881,
3267
+ "step": 294
3268
+ },
3269
+ {
3270
+ "epoch": 4.8244897959183675,
3271
+ "grad_norm": 0.1126311793923378,
3272
+ "learning_rate": 1.1235195291852529e-05,
3273
+ "loss": 0.0144,
3274
+ "step": 295
3275
+ },
3276
+ {
3277
+ "epoch": 4.840816326530613,
3278
+ "grad_norm": 0.13918578624725342,
3279
+ "learning_rate": 1.0580339001051154e-05,
3280
+ "loss": 0.0204,
3281
+ "step": 296
3282
+ },
3283
+ {
3284
+ "epoch": 4.840816326530613,
3285
+ "eval_loss": 1.3199832439422607,
3286
+ "eval_runtime": 18.2035,
3287
+ "eval_samples_per_second": 0.879,
3288
+ "eval_steps_per_second": 0.879,
3289
+ "step": 296
3290
+ },
3291
+ {
3292
+ "epoch": 4.857142857142857,
3293
+ "grad_norm": 0.1410403996706009,
3294
+ "learning_rate": 9.944626199528539e-06,
3295
+ "loss": 0.0175,
3296
+ "step": 297
3297
+ },
3298
+ {
3299
+ "epoch": 4.873469387755102,
3300
+ "grad_norm": 0.1490529477596283,
3301
+ "learning_rate": 9.328121134898337e-06,
3302
+ "loss": 0.0211,
3303
+ "step": 298
3304
+ },
3305
+ {
3306
+ "epoch": 4.873469387755102,
3307
+ "eval_loss": 1.320744276046753,
3308
+ "eval_runtime": 18.1887,
3309
+ "eval_samples_per_second": 0.88,
3310
+ "eval_steps_per_second": 0.88,
3311
+ "step": 298
3312
+ },
3313
+ {
3314
+ "epoch": 4.889795918367347,
3315
+ "grad_norm": 0.13268522918224335,
3316
+ "learning_rate": 8.730886113565473e-06,
3317
+ "loss": 0.0128,
3318
+ "step": 299
3319
+ },
3320
+ {
3321
+ "epoch": 4.906122448979592,
3322
+ "grad_norm": 0.143647238612175,
3323
+ "learning_rate": 8.152981494429135e-06,
3324
+ "loss": 0.0183,
3325
+ "step": 300
3326
+ },
3327
+ {
3328
+ "epoch": 4.906122448979592,
3329
+ "eval_loss": 1.3215551376342773,
3330
+ "eval_runtime": 18.2069,
3331
+ "eval_samples_per_second": 0.879,
3332
+ "eval_steps_per_second": 0.879,
3333
+ "step": 300
3334
+ }
3335
+ ],
3336
+ "logging_steps": 1,
3337
+ "max_steps": 305,
3338
+ "num_input_tokens_seen": 0,
3339
+ "num_train_epochs": 5,
3340
+ "save_steps": 30,
3341
+ "stateful_callbacks": {
3342
+ "TrainerControl": {
3343
+ "args": {
3344
+ "should_epoch_stop": false,
3345
+ "should_evaluate": false,
3346
+ "should_log": false,
3347
+ "should_save": true,
3348
+ "should_training_stop": false
3349
+ },
3350
+ "attributes": {}
3351
+ }
3352
+ },
3353
+ "total_flos": 3.627584723251538e+18,
3354
+ "train_batch_size": 1,
3355
+ "trial_name": null,
3356
+ "trial_params": null
3357
+ }
checkpoints/checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5208f4e9c07bb6bd2f0bc574a52273bdf74ca404d495a5bf559488089674f2f5
3
+ size 5624
checkpoints/checkpoint-60/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: /home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
checkpoints/checkpoint-60/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "/home/anon/AI-Models/LLM/Mistral-Small-24B-Instruct-2501/",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "gate_proj",
28
+ "down_proj",
29
+ "o_proj",
30
+ "v_proj",
31
+ "up_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
checkpoints/checkpoint-60/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786a23751362703625b5d84e669cad1fa7eba36ac879df6c2b2a343f55533238
3
+ size 739321784
checkpoints/checkpoint-60/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07233b688f5ed8469369520580b92686b5738fde4b8a819925559c1aa2f64d97
3
+ size 377514226
checkpoints/checkpoint-60/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea10b3bb66b8b27f44f2f960e6c5de5e4f3ad9ba367d567edbed1701a1afb9ca
3
+ size 14244