terry69 commited on
Commit
da952ce
1 Parent(s): c8797e8

End of training

Browse files
README.md CHANGED
@@ -3,9 +3,15 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.2
5
  tags:
 
6
  - trl
7
  - sft
8
  - generated_from_trainer
 
 
 
 
 
9
  model-index:
10
  - name: preference_p0.1_seed42_level3_stylemix
11
  results: []
@@ -16,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # preference_p0.1_seed42_level3_stylemix
18
 
19
- This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
20
 
21
  ## Model description
22
 
 
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.2
5
  tags:
6
+ - alignment-handbook
7
  - trl
8
  - sft
9
  - generated_from_trainer
10
+ - trl
11
+ - sft
12
+ - generated_from_trainer
13
+ datasets:
14
+ - preference-data
15
  model-index:
16
  - name: preference_p0.1_seed42_level3_stylemix
17
  results: []
 
22
 
23
  # preference_p0.1_seed42_level3_stylemix
24
 
25
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
26
 
27
  ## Model description
28
 
all_results.json CHANGED
@@ -1,5 +1,9 @@
1
  {
2
  "epoch": 0.9995872884853487,
 
 
 
 
3
  "total_flos": 6.266791881867264e+16,
4
  "train_loss": 0.5434653141299719,
5
  "train_runtime": 21156.3929,
 
1
  {
2
  "epoch": 0.9995872884853487,
3
+ "eval_runtime": 3.2341,
4
+ "eval_samples": 10,
5
+ "eval_samples_per_second": 3.092,
6
+ "eval_steps_per_second": 0.928,
7
  "total_flos": 6.266791881867264e+16,
8
  "train_loss": 0.5434653141299719,
9
  "train_runtime": 21156.3929,
config.json CHANGED
@@ -22,6 +22,6 @@
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.44.2",
25
- "use_cache": false,
26
  "vocab_size": 32000
27
  }
 
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.44.2",
25
+ "use_cache": true,
26
  "vocab_size": 32000
27
  }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9995872884853487,
3
+ "eval_runtime": 3.2341,
4
+ "eval_samples": 10,
5
+ "eval_samples_per_second": 3.092,
6
+ "eval_steps_per_second": 0.928
7
+ }
runs/Sep16_16-18-55_COE-CS-sv003/events.out.tfevents.1726525415.COE-CS-sv003.3494548.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971940f22fbc91f784bd33658a99ca25cd84f40a3c945a9a571c7a545991c667
3
+ size 311