Jennny commited on
Commit
022f7d5
1 Parent(s): c415291

End of training

Browse files
README.md CHANGED
@@ -2,11 +2,15 @@
2
  license: mit
3
  base_model: openai-community/gpt2-medium
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  datasets:
9
- - generator
10
  model-index:
11
  - name: gpt2-sft
12
  results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # gpt2-sft
19
 
20
- This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/gpt2-medium) on the generator dataset.
21
  It achieves the following results on the evaluation set:
22
  - Loss: 2.1977
23
 
 
2
  license: mit
3
  base_model: openai-community/gpt2-medium
4
  tags:
5
+ - alignment-handbook
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
  - trl
10
  - sft
11
  - generated_from_trainer
12
  datasets:
13
+ - Anthropic/hh-rlhf
14
  model-index:
15
  - name: gpt2-sft
16
  results: []
 
21
 
22
  # gpt2-sft
23
 
24
+ This model is a fine-tuned version of [openai-community/gpt2-medium](https://huggingface.co/openai-community/gpt2-medium) on the Anthropic/hh-rlhf dataset.
25
  It achieves the following results on the evaluation set:
26
  - Loss: 2.1977
27
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "train_loss": 0.6064129045034048,
4
  "train_runtime": 690.5421,
5
  "train_samples": 64320,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 2.1976709365844727,
4
+ "eval_runtime": 129.9307,
5
+ "eval_samples": 16080,
6
+ "eval_samples_per_second": 21.358,
7
+ "eval_steps_per_second": 2.671,
8
  "train_loss": 0.6064129045034048,
9
  "train_runtime": 690.5421,
10
  "train_samples": 64320,
config.json CHANGED
@@ -36,6 +36,6 @@
36
  },
37
  "torch_dtype": "bfloat16",
38
  "transformers_version": "4.39.0.dev0",
39
- "use_cache": false,
40
  "vocab_size": 50257
41
  }
 
36
  },
37
  "torch_dtype": "bfloat16",
38
  "transformers_version": "4.39.0.dev0",
39
+ "use_cache": true,
40
  "vocab_size": 50257
41
  }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 2.1976709365844727,
4
+ "eval_runtime": 129.9307,
5
+ "eval_samples": 16080,
6
+ "eval_samples_per_second": 21.358,
7
+ "eval_steps_per_second": 2.671
8
+ }
runs/Apr10_04-50-43_compsci-cluster-fitz-05/events.out.tfevents.1712739895.compsci-cluster-fitz-05.898746.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73e569f3154116e5d7f2e1b8a9b693057190052bc87d0a77e5b8b3003e7e4a5f
3
+ size 359