Hugging Face's logo

stevenjunliu
/
gpt2-cpt-white

Text Generation
Transformers
Safetensors
gpt2
alignment-handbook
trl
sft
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
stevenjunliu commited on
Commit
3f52b57
·
verified ·
1 Parent(s): d5911a4

Model save

Browse files
Files changed (6) hide show
  1. README.md +3 -6
  2. all_results.json +2 -2
  3. config.json +1 -1
  4. train_results.json +2 -2
  5. trainer_state.json +2 -2
  6. training_args.bin +1 -1
README.md CHANGED
@@ -2,15 +2,12 @@
2
  license: mit
3
  base_model: gpt2
4
  tags:
5
- - alignment-handbook
6
- - trl
7
- - sft
8
- - generated_from_trainer
9
  - trl
10
  - sft
 
11
  - generated_from_trainer
12
  datasets:
13
- - shahadalkhalifa/Crypto_Whitepaper_Labeled
14
  model-index:
15
  - name: gpt2-cpt-white
16
  results: []
@@ -21,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  # gpt2-cpt-white
23
 
24
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the shahadalkhalifa/Crypto_Whitepaper_Labeled dataset.
25
 
26
  ## Model description
27
 
 
2
  license: mit
3
  base_model: gpt2
4
  tags:
 
 
 
 
5
  - trl
6
  - sft
7
+ - alignment-handbook
8
  - generated_from_trainer
9
  datasets:
10
+ - generator
11
  model-index:
12
  - name: gpt2-cpt-white
13
  results: []
 
18
 
19
  # gpt2-cpt-white
20
 
21
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
22
 
23
  ## Model description
24
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
  "train_loss": 6.083620756864548,
4
- "train_runtime": 28.044,
5
  "train_samples": 91,
6
- "train_samples_per_second": 35.801,
7
  "train_steps_per_second": 0.571
8
  }
 
1
  {
2
  "epoch": 4.0,
3
  "train_loss": 6.083620756864548,
4
+ "train_runtime": 28.0153,
5
  "train_samples": 91,
6
+ "train_samples_per_second": 35.838,
7
  "train_steps_per_second": 0.571
8
  }
config.json CHANGED
@@ -34,6 +34,6 @@
34
  },
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.39.0.dev0",
37
- "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
34
  },
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.39.0.dev0",
37
+ "use_cache": false,
38
  "vocab_size": 50257
39
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.0,
3
  "train_loss": 6.083620756864548,
4
- "train_runtime": 28.044,
5
  "train_samples": 91,
6
- "train_samples_per_second": 35.801,
7
  "train_steps_per_second": 0.571
8
  }
 
1
  {
2
  "epoch": 4.0,
3
  "train_loss": 6.083620756864548,
4
+ "train_runtime": 28.0153,
5
  "train_samples": 91,
6
+ "train_samples_per_second": 35.838,
7
  "train_steps_per_second": 0.571
8
  }
trainer_state.json CHANGED
@@ -41,8 +41,8 @@
41
  "step": 16,
42
  "total_flos": 535126081536000.0,
43
  "train_loss": 6.083620756864548,
44
- "train_runtime": 28.044,
45
- "train_samples_per_second": 35.801,
46
  "train_steps_per_second": 0.571
47
  }
48
  ],
 
41
  "step": 16,
42
  "total_flos": 535126081536000.0,
43
  "train_loss": 6.083620756864548,
44
+ "train_runtime": 28.0153,
45
+ "train_samples_per_second": 35.838,
46
  "train_steps_per_second": 0.571
47
  }
48
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba7aad08f79b4b82f8d2e7069e009b925897569aebe186ceb0472cbbb86765b
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72678b2a88de20abefeb92c2713630bc7eb0c9a518ff85944dd79fb87d3dabb
3
  size 4984