Minbyul commited on
Commit
9ebae1f
1 Parent(s): a586bae

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
@@ -1,11 +1,15 @@
1
  ---
2
  base_model: dmis-lab/selfbiorag_7b
3
  tags:
 
 
 
 
4
  - trl
5
  - sft
6
  - generated_from_trainer
7
  datasets:
8
- - generator
9
  model-index:
10
  - name: selfbiorag-7b-5e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
11
  results: []
@@ -16,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # selfbiorag-7b-5e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
18
 
19
- This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the generator dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 1.2627
22
 
 
1
  ---
2
  base_model: dmis-lab/selfbiorag_7b
3
  tags:
4
+ - alignment-handbook
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
  - trl
9
  - sft
10
  - generated_from_trainer
11
  datasets:
12
+ - HuggingFaceH4/deita-10k-v0-sft
13
  model-index:
14
  - name: selfbiorag-7b-5e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
15
  results: []
 
20
 
21
  # selfbiorag-7b-5e-6-wo-kqa_silver_wogold-iter-sft-step1_lr
22
 
23
+ This model is a fine-tuned version of [dmis-lab/selfbiorag_7b](https://huggingface.co/dmis-lab/selfbiorag_7b) on the HuggingFaceH4/deita-10k-v0-sft dataset.
24
  It achieves the following results on the evaluation set:
25
  - Loss: 1.2627
26
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 2.53,
 
 
 
 
 
3
  "train_loss": 1.2326995531717937,
4
  "train_runtime": 212.4422,
5
  "train_samples": 4047,
 
1
  {
2
  "epoch": 2.53,
3
+ "eval_loss": 1.2627166509628296,
4
+ "eval_runtime": 5.5091,
5
+ "eval_samples": 904,
6
+ "eval_samples_per_second": 11.617,
7
+ "eval_steps_per_second": 0.726,
8
  "train_loss": 1.2326995531717937,
9
  "train_runtime": 212.4422,
10
  "train_samples": 4047,
config.json CHANGED
@@ -23,6 +23,6 @@
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.39.0.dev0",
26
- "use_cache": false,
27
  "vocab_size": 32016
28
  }
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.39.0.dev0",
26
+ "use_cache": true,
27
  "vocab_size": 32016
28
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.53,
3
+ "eval_loss": 1.2627166509628296,
4
+ "eval_runtime": 5.5091,
5
+ "eval_samples": 904,
6
+ "eval_samples_per_second": 11.617,
7
+ "eval_steps_per_second": 0.726
8
+ }