Minbyul commited on
Commit
0cc5eff
1 Parent(s): 743b07c

End of training

Browse files
Files changed (4) hide show
  1. README.md +6 -2
  2. all_results.json +5 -0
  3. config.json +1 -1
  4. eval_results.json +8 -0
README.md CHANGED
@@ -2,11 +2,15 @@
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-v0.1
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  datasets:
9
- - generator
10
  model-index:
11
  - name: mistral-7b-wo-live_qa-sft
12
  results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # mistral-7b-wo-live_qa-sft
19
 
20
- This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 1.6476
23
 
 
2
  license: apache-2.0
3
  base_model: mistralai/Mistral-7B-v0.1
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
  - trl
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
+ - HuggingFaceH4/deita-10k-v0-sft
14
  model-index:
15
  - name: mistral-7b-wo-live_qa-sft
16
  results: []
 
21
 
22
  # mistral-7b-wo-live_qa-sft
23
 
24
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/deita-10k-v0-sft dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 1.6476
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 2.77,
 
 
 
 
 
3
  "train_loss": 1.1346278654204474,
4
  "train_runtime": 313.3964,
5
  "train_samples": 4848,
 
1
  {
2
  "epoch": 2.77,
3
+ "eval_loss": 1.6476205587387085,
4
+ "eval_runtime": 1.3272,
5
+ "eval_samples": 100,
6
+ "eval_samples_per_second": 5.274,
7
+ "eval_steps_per_second": 0.753,
8
  "train_loss": 1.1346278654204474,
9
  "train_runtime": 313.3964,
10
  "train_samples": 4848,
config.json CHANGED
@@ -21,6 +21,6 @@
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.39.0.dev0",
24
- "use_cache": false,
25
  "vocab_size": 32000
26
  }
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
  "transformers_version": "4.39.0.dev0",
24
+ "use_cache": true,
25
  "vocab_size": 32000
26
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.77,
3
+ "eval_loss": 1.6476205587387085,
4
+ "eval_runtime": 1.3272,
5
+ "eval_samples": 100,
6
+ "eval_samples_per_second": 5.274,
7
+ "eval_steps_per_second": 0.753
8
+ }