Aivesa commited on
Commit
b77cead
·
verified ·
1 Parent(s): 5d7d329

End of training

Browse files
Files changed (1) hide show
  1. README.md +16 -17
README.md CHANGED
@@ -1,14 +1,14 @@
1
  ---
2
  library_name: peft
3
  license: apache-2.0
4
- base_model: EleutherAI/pythia-160m
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
- - Aivesa/dataset_71c4d505-b734-4315-b4e8-1ed979528a1d
10
  model-index:
11
- - name: bbafd374-4aae-4af5-b2e8-6cd470f8d89f
12
  results: []
13
  ---
14
 
@@ -21,18 +21,17 @@ should probably proofread and complete it, then remove this comment. -->
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
- base_model: EleutherAI/pythia-160m
25
  bf16: auto
26
  chat_template: llama3
27
  dataset_prepared_path: /workspace/axolotl/data/prepared
28
  datasets:
29
  - ds_type: json
30
  format: custom
31
- path: Aivesa/dataset_71c4d505-b734-4315-b4e8-1ed979528a1d
32
  type:
33
- field_input: prompt_setting
34
- field_instruction: prompt
35
- field_output: completion
36
  system_format: '{system}'
37
  system_prompt: ''
38
  debug: null
@@ -48,7 +47,7 @@ fsdp_config: null
48
  gradient_accumulation_steps: 4
49
  gradient_checkpointing: false
50
  group_by_length: false
51
- hub_model_id: Aivesa/bbafd374-4aae-4af5-b2e8-6cd470f8d89f
52
  hub_private_repo: true
53
  hub_repo: null
54
  hub_strategy: checkpoint
@@ -90,10 +89,10 @@ use_accelerate: true
90
  val_set_size: 0.05
91
  wandb_entity: null
92
  wandb_mode: online
93
- wandb_name: 71c4d505-b734-4315-b4e8-1ed979528a1d
94
  wandb_project: Gradients-On-Demand
95
  wandb_run: your_name
96
- wandb_runid: 71c4d505-b734-4315-b4e8-1ed979528a1d
97
  warmup_steps: 10
98
  weight_decay: 0.0
99
  xformers_attention: null
@@ -102,11 +101,11 @@ xformers_attention: null
102
 
103
  </details><br>
104
 
105
- # bbafd374-4aae-4af5-b2e8-6cd470f8d89f
106
 
107
- This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on the Aivesa/dataset_71c4d505-b734-4315-b4e8-1ed979528a1d dataset.
108
  It achieves the following results on the evaluation set:
109
- - Loss: 2.4226
110
 
111
  ## Model description
112
 
@@ -140,9 +139,9 @@ The following hyperparameters were used during training:
140
 
141
  | Training Loss | Epoch | Step | Validation Loss |
142
  |:-------------:|:------:|:----:|:---------------:|
143
- | 6.2508 | 0.0053 | 3 | 2.4551 |
144
- | 9.0753 | 0.0105 | 6 | 2.4525 |
145
- | 14.6351 | 0.0158 | 9 | 2.4226 |
146
 
147
 
148
  ### Framework versions
 
1
  ---
2
  library_name: peft
3
  license: apache-2.0
4
+ base_model: EleutherAI/pythia-410m-deduped
5
  tags:
6
  - axolotl
7
  - generated_from_trainer
8
  datasets:
9
+ - Aivesa/dataset_8b4ee2ef-6f34-478c-b009-c74daaa5693c
10
  model-index:
11
+ - name: b0732ad0-1309-4d92-a6b8-78235a5a5912
12
  results: []
13
  ---
14
 
 
21
  axolotl version: `0.6.0`
22
  ```yaml
23
  adapter: lora
24
+ base_model: EleutherAI/pythia-410m-deduped
25
  bf16: auto
26
  chat_template: llama3
27
  dataset_prepared_path: /workspace/axolotl/data/prepared
28
  datasets:
29
  - ds_type: json
30
  format: custom
31
+ path: Aivesa/dataset_8b4ee2ef-6f34-478c-b009-c74daaa5693c
32
  type:
33
+ field_instruction: message_1
34
+ field_output: message_2
 
35
  system_format: '{system}'
36
  system_prompt: ''
37
  debug: null
 
47
  gradient_accumulation_steps: 4
48
  gradient_checkpointing: false
49
  group_by_length: false
50
+ hub_model_id: Aivesa/b0732ad0-1309-4d92-a6b8-78235a5a5912
51
  hub_private_repo: true
52
  hub_repo: null
53
  hub_strategy: checkpoint
 
89
  val_set_size: 0.05
90
  wandb_entity: null
91
  wandb_mode: online
92
+ wandb_name: 8b4ee2ef-6f34-478c-b009-c74daaa5693c
93
  wandb_project: Gradients-On-Demand
94
  wandb_run: your_name
95
+ wandb_runid: 8b4ee2ef-6f34-478c-b009-c74daaa5693c
96
  warmup_steps: 10
97
  weight_decay: 0.0
98
  xformers_attention: null
 
101
 
102
  </details><br>
103
 
104
+ # b0732ad0-1309-4d92-a6b8-78235a5a5912
105
 
106
+ This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped](https://huggingface.co/EleutherAI/pythia-410m-deduped) on the Aivesa/dataset_8b4ee2ef-6f34-478c-b009-c74daaa5693c dataset.
107
  It achieves the following results on the evaluation set:
108
+ - Loss: 1.5341
109
 
110
  ## Model description
111
 
 
139
 
140
  | Training Loss | Epoch | Step | Validation Loss |
141
  |:-------------:|:------:|:----:|:---------------:|
142
+ | 6.3369 | 0.0013 | 3 | 1.5670 |
143
+ | 6.3116 | 0.0026 | 6 | 1.5588 |
144
+ | 6.7369 | 0.0038 | 9 | 1.5341 |
145
 
146
 
147
  ### Framework versions