terry69 commited on
Commit
a3f9c10
1 Parent(s): 02c39f8

End of training

Browse files
README.md CHANGED
@@ -3,10 +3,16 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: mistralai/Mistral-7B-Instruct-v0.2
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
  - alignment-handbook
9
  - generated_from_trainer
 
 
10
  model-index:
11
  - name: preference_p0.1_seed42_level2_syntaxdirtybatch16
12
  results: []
@@ -17,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # preference_p0.1_seed42_level2_syntaxdirtybatch16
19
 
20
- 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.
21
 
22
  ## Model description
23
 
 
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
  - alignment-handbook
13
  - generated_from_trainer
14
+ datasets:
15
+ - preference-data
16
  model-index:
17
  - name: preference_p0.1_seed42_level2_syntaxdirtybatch16
18
  results: []
 
23
 
24
  # preference_p0.1_seed42_level2_syntaxdirtybatch16
25
 
26
+ 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.
27
 
28
  ## Model description
29
 
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_runtime": 3.2433,
4
  "eval_samples": 10,
5
- "eval_samples_per_second": 3.083,
6
- "eval_steps_per_second": 0.925,
7
  "total_flos": 252302485094400.0,
8
  "train_loss": 0.0,
9
  "train_runtime": 0.0084,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_runtime": 4.2085,
4
  "eval_samples": 10,
5
+ "eval_samples_per_second": 2.376,
6
+ "eval_steps_per_second": 0.713,
7
  "total_flos": 252302485094400.0,
8
  "train_loss": 0.0,
9
  "train_runtime": 0.0084,
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 CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_runtime": 3.2433,
4
  "eval_samples": 10,
5
- "eval_samples_per_second": 3.083,
6
- "eval_steps_per_second": 0.925
7
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_runtime": 4.2085,
4
  "eval_samples": 10,
5
+ "eval_samples_per_second": 2.376,
6
+ "eval_steps_per_second": 0.713
7
  }
runs/Sep24_11-52-09_COE-CS-sv003/events.out.tfevents.1727178868.COE-CS-sv003.783277.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9da7b9824d4faeee5cf7535c6151f8bee2d371aa2f22bed94519a57914faf94
3
+ size 311