robiual-awal commited on
Commit
6cf81f6
·
verified ·
1 Parent(s): 7bf482f

End of training

Browse files
Files changed (1) hide show
  1. README.md +0 -187
README.md CHANGED
@@ -13,101 +13,6 @@ model-index:
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
- <details><summary>See axolotl config</summary>
18
-
19
- axolotl version: `0.4.1`
20
- ```yaml
21
- adapter: lora
22
- base_model: facebook/opt-125m
23
- bf16: auto
24
- chat_template: llama3
25
- dataset_prepared_path: null
26
- datasets:
27
- - data_files:
28
- - e9426b45bbc30495_train_data.json
29
- ds_type: json
30
- format: custom
31
- path: /workspace/input_data/e9426b45bbc30495_train_data.json
32
- type:
33
- field_input: original_version
34
- field_instruction: title
35
- field_output: french_version
36
- format: '{instruction} {input}'
37
- no_input_format: '{instruction}'
38
- system_format: '{system}'
39
- system_prompt: ''
40
- debug: null
41
- deepspeed: null
42
- device_map: auto
43
- do_eval: true
44
- early_stopping_patience: 3
45
- eval_batch_size: 4
46
- eval_max_new_tokens: 128
47
- eval_steps: 300
48
- eval_table_size: null
49
- evals_per_epoch: null
50
- flash_attention: true
51
- fp16: false
52
- fsdp: null
53
- fsdp_config: null
54
- gradient_accumulation_steps: 4
55
- gradient_checkpointing: false
56
- group_by_length: true
57
- hub_model_id: robiual-awal/31b2ce40-fe16-4b11-a7f2-c816733ae5bd
58
- hub_strategy: end
59
- learning_rate: 0.0002
60
- load_in_4bit: false
61
- load_in_8bit: false
62
- local_rank: null
63
- logging_steps: 50
64
- lora_alpha: 64
65
- lora_dropout: 0.05
66
- lora_fan_in_fan_out: null
67
- lora_model_dir: null
68
- lora_r: 32
69
- lora_target_linear: true
70
- lr_scheduler: constant
71
- max_grad_norm: 1.0
72
- max_memory:
73
- 0: 75GB
74
- max_steps: 20956
75
- micro_batch_size: 4
76
- mlflow_experiment_name: /tmp/e9426b45bbc30495_train_data.json
77
- model_type: AutoModelForCausalLM
78
- num_epochs: 10
79
- optim_args:
80
- adam_beta1: 0.9
81
- adam_beta2: 0.95
82
- adam_epsilon: 1e-5
83
- optimizer: adamw_bnb_8bit
84
- output_dir: miner_id_24
85
- pad_to_sequence_len: true
86
- resume_from_checkpoint: null
87
- s2_attention: null
88
- sample_packing: false
89
- save_steps: 300
90
- saves_per_epoch: null
91
- sequence_len: 512
92
- strict: false
93
- tf32: true
94
- tokenizer_type: AutoTokenizer
95
- train_on_inputs: false
96
- trust_remote_code: true
97
- val_set_size: 0.05
98
- wandb_entity: null
99
- wandb_mode: online
100
- wandb_name: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
101
- wandb_project: SN56-30
102
- wandb_run: your_name
103
- wandb_runid: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
104
- warmup_steps: 50
105
- weight_decay: 0.0
106
- xformers_attention: null
107
-
108
- ```
109
-
110
- </details><br>
111
 
112
  # 31b2ce40-fe16-4b11-a7f2-c816733ae5bd
113
 
@@ -127,98 +32,6 @@ More information needed
127
 
128
  More information needed
129
 
130
- ## Training procedure
131
-
132
- ### Training hyperparameters
133
-
134
- The following hyperparameters were used during training:
135
- - learning_rate: 0.0002
136
- - train_batch_size: 4
137
- - eval_batch_size: 4
138
- - seed: 42
139
- - gradient_accumulation_steps: 4
140
- - total_train_batch_size: 16
141
- - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
142
- - lr_scheduler_type: constant
143
- - lr_scheduler_warmup_steps: 50
144
- - training_steps: 20956
145
-
146
- ### Training results
147
-
148
- | Training Loss | Epoch | Step | Validation Loss |
149
- |:-------------:|:------:|:-----:|:---------------:|
150
- | No log | 0.0002 | 1 | 2.5746 |
151
- | 8.1108 | 0.0510 | 300 | 1.9106 |
152
- | 7.0989 | 0.1021 | 600 | 1.6791 |
153
- | 6.6679 | 0.1531 | 900 | 1.5726 |
154
- | 6.261 | 0.2042 | 1200 | 1.4999 |
155
- | 6.0721 | 0.2552 | 1500 | 1.4423 |
156
- | 5.8807 | 0.3063 | 1800 | 1.4126 |
157
- | 5.6805 | 0.3573 | 2100 | 1.3783 |
158
- | 5.5754 | 0.4083 | 2400 | 1.3535 |
159
- | 5.7266 | 0.4594 | 2700 | 1.3309 |
160
- | 5.5338 | 0.5104 | 3000 | 1.3168 |
161
- | 5.6379 | 0.5615 | 3300 | 1.2952 |
162
- | 5.5449 | 0.6125 | 3600 | 1.2839 |
163
- | 5.3335 | 0.6635 | 3900 | 1.2721 |
164
- | 5.3477 | 0.7146 | 4200 | 1.2623 |
165
- | 5.2752 | 0.7656 | 4500 | 1.2513 |
166
- | 5.1171 | 0.8167 | 4800 | 1.2466 |
167
- | 5.1925 | 0.8677 | 5100 | 1.2335 |
168
- | 5.3031 | 0.9188 | 5400 | 1.2284 |
169
- | 5.2691 | 0.9698 | 5700 | 1.2237 |
170
- | 5.2285 | 1.0208 | 6000 | 1.2107 |
171
- | 5.2817 | 1.0719 | 6300 | 1.2072 |
172
- | 5.0723 | 1.1229 | 6600 | 1.2032 |
173
- | 5.0179 | 1.1740 | 6900 | 1.1982 |
174
- | 4.8939 | 1.2250 | 7200 | 1.1965 |
175
- | 4.8136 | 1.2761 | 7500 | 1.1892 |
176
- | 4.9914 | 1.3271 | 7800 | 1.1828 |
177
- | 5.074 | 1.3781 | 8100 | 1.1815 |
178
- | 5.0051 | 1.4292 | 8400 | 1.1753 |
179
- | 4.9578 | 1.4802 | 8700 | 1.1743 |
180
- | 5.1432 | 1.5313 | 9000 | 1.1683 |
181
- | 4.7522 | 1.5823 | 9300 | 1.1685 |
182
- | 5.0689 | 1.6333 | 9600 | 1.1632 |
183
- | 4.8908 | 1.6844 | 9900 | 1.1638 |
184
- | 4.8675 | 1.7354 | 10200 | 1.1558 |
185
- | 4.8574 | 1.7865 | 10500 | 1.1557 |
186
- | 4.889 | 1.8375 | 10800 | 1.1522 |
187
- | 4.9843 | 1.8886 | 11100 | 1.1552 |
188
- | 4.6065 | 1.9396 | 11400 | 1.1506 |
189
- | 4.9163 | 1.9906 | 11700 | 1.1473 |
190
- | 4.8699 | 2.0417 | 12000 | 1.1422 |
191
- | 4.7492 | 2.0927 | 12300 | 1.1431 |
192
- | 4.7051 | 2.1438 | 12600 | 1.1392 |
193
- | 4.772 | 2.1948 | 12900 | 1.1397 |
194
- | 4.9571 | 2.2459 | 13200 | 1.1376 |
195
- | 4.5603 | 2.2969 | 13500 | 1.1356 |
196
- | 4.6664 | 2.3479 | 13800 | 1.1337 |
197
- | 4.876 | 2.3990 | 14100 | 1.1300 |
198
- | 4.5775 | 2.4500 | 14400 | 1.1301 |
199
- | 4.764 | 2.5011 | 14700 | 1.1275 |
200
- | 4.6266 | 2.5521 | 15000 | 1.1246 |
201
- | 4.7234 | 2.6031 | 15300 | 1.1250 |
202
- | 4.722 | 2.6542 | 15600 | 1.1211 |
203
- | 4.9044 | 2.7052 | 15900 | 1.1202 |
204
- | 4.8683 | 2.7563 | 16200 | 1.1217 |
205
- | 4.5523 | 2.8073 | 16500 | 1.1161 |
206
- | 4.6435 | 2.8584 | 16800 | 1.1191 |
207
- | 4.8074 | 2.9094 | 17100 | 1.1175 |
208
- | 4.6395 | 2.9604 | 17400 | 1.1156 |
209
- | 4.5781 | 3.0115 | 17700 | 1.1167 |
210
- | 4.4496 | 3.0625 | 18000 | 1.1188 |
211
- | 4.6846 | 3.1136 | 18300 | 1.1130 |
212
- | 4.5808 | 3.1646 | 18600 | 1.1168 |
213
- | 4.3914 | 3.2157 | 18900 | 1.1123 |
214
- | 4.6832 | 3.2667 | 19200 | 1.1118 |
215
- | 4.5798 | 3.3177 | 19500 | 1.1123 |
216
- | 4.966 | 3.3688 | 19800 | 1.1107 |
217
- | 4.6667 | 3.4198 | 20100 | 1.1098 |
218
- | 4.4912 | 3.4709 | 20400 | 1.1077 |
219
- | 4.749 | 3.5219 | 20700 | 1.1069 |
220
-
221
-
222
  ### Framework versions
223
 
224
  - PEFT 0.13.2
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
 
17
  # 31b2ce40-fe16-4b11-a7f2-c816733ae5bd
18
 
 
32
 
33
  More information needed
34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  ### Framework versions
36
 
37
  - PEFT 0.13.2