kykim0 commited on
Commit
3cce62a
1 Parent(s): 578c7d4

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: other
3
  base_model: google/gemma-2b
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  datasets:
9
- - generator
10
  model-index:
11
  - name: gemma-2b-ultrachat-sft
12
  results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # gemma-2b-ultrachat-sft
19
 
20
- This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 1.2072
23
 
 
2
  license: other
3
  base_model: google/gemma-2b
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/ultrachat_200k
14
  model-index:
15
  - name: gemma-2b-ultrachat-sft
16
  results: []
 
21
 
22
  # gemma-2b-ultrachat-sft
23
 
24
+ This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the HuggingFaceH4/ultrachat_200k dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 1.2072
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 3.0,
 
 
 
 
 
3
  "train_loss": 0.7671343510089264,
4
  "train_runtime": 16733.4448,
5
  "train_samples": 207864,
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_loss": 1.2072049379348755,
4
+ "eval_runtime": 241.8509,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 55.906,
7
+ "eval_steps_per_second": 3.498,
8
  "train_loss": 0.7671343510089264,
9
  "train_runtime": 16733.4448,
10
  "train_samples": 207864,
config.json CHANGED
@@ -23,6 +23,6 @@
23
  "rope_theta": 10000.0,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.39.0.dev0",
26
- "use_cache": false,
27
  "vocab_size": 256000
28
  }
 
23
  "rope_theta": 10000.0,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.39.0.dev0",
26
+ "use_cache": true,
27
  "vocab_size": 256000
28
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 1.2072049379348755,
4
+ "eval_runtime": 241.8509,
5
+ "eval_samples": 23109,
6
+ "eval_samples_per_second": 55.906,
7
+ "eval_steps_per_second": 3.498
8
+ }