terry69 commited on
Commit
ba2b354
1 Parent(s): 698adaa

End of training

Browse files
README.md CHANGED
@@ -2,11 +2,15 @@
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-Instruct-v0.2
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  datasets:
9
- - generator
10
  model-index:
11
  - name: feedback_p0.1_seed42_level2_raremix
12
  results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # feedback_p0.1_seed42_level2_raremix
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 generator dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 0.3463
23
 
 
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-Instruct-v0.2
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
  - trl
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
+ - preference-data
14
  model-index:
15
  - name: feedback_p0.1_seed42_level2_raremix
16
  results: []
 
21
 
22
  # feedback_p0.1_seed42_level2_raremix
23
 
24
+ 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.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 0.3463
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 0.9997315436241611,
 
 
 
 
 
3
  "total_flos": 194880114524160.0,
4
  "train_loss": 0.5085661182086014,
5
  "train_runtime": 21123.8288,
 
1
  {
2
  "epoch": 0.9997315436241611,
3
+ "eval_loss": 0.3463418781757355,
4
+ "eval_runtime": 1.2868,
5
+ "eval_samples": 10,
6
+ "eval_samples_per_second": 1.554,
7
+ "eval_steps_per_second": 0.777,
8
  "total_flos": 194880114524160.0,
9
  "train_loss": 0.5085661182086014,
10
  "train_runtime": 21123.8288,
config.json CHANGED
@@ -22,6 +22,6 @@
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.43.4",
25
- "use_cache": false,
26
  "vocab_size": 32000
27
  }
 
22
  "tie_word_embeddings": false,
23
  "torch_dtype": "bfloat16",
24
  "transformers_version": "4.43.4",
25
+ "use_cache": true,
26
  "vocab_size": 32000
27
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.9997315436241611,
3
+ "eval_loss": 0.3463418781757355,
4
+ "eval_runtime": 1.2868,
5
+ "eval_samples": 10,
6
+ "eval_samples_per_second": 1.554,
7
+ "eval_steps_per_second": 0.777
8
+ }
runs/Sep09_09-31-09_COE-CS-sv003/events.out.tfevents.1725896266.COE-CS-sv003.742544.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2835759a115be28b412c319f22b0b65ce6d8574ee7ff57098f8dba2d2f72fb57
3
+ size 359