Hugging Face's logo

siyangliu
/
gpt2-cpt-dutch

Text Generation
Transformers
Safetensors
gpt2
alignment-handbook
trl
sft
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
siyangliu commited on
Commit
acd3853
•
1 Parent(s): 2d8b5fb

Model save

Browse files
Files changed (6) hide show
  1. README.md +2 -6
  2. all_results.json +3 -3
  3. config.json +1 -1
  4. train_results.json +3 -3
  5. trainer_state.json +3 -3
  6. training_args.bin +1 -1
README.md CHANGED
@@ -2,16 +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
  - alignment-handbook
12
  - generated_from_trainer
13
  datasets:
14
- - siyangliu/Depression_Severity_Dataset
15
  model-index:
16
  - name: gpt2-cpt-dutch
17
  results: []
@@ -22,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
22
 
23
  # gpt2-cpt-dutch
24
 
25
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the siyangliu/Depression_Severity_Dataset dataset.
26
 
27
  ## Model description
28
 
 
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-dutch
13
  results: []
 
18
 
19
  # gpt2-cpt-dutch
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
@@ -2,8 +2,8 @@
2
  "epoch": 5.0,
3
  "total_flos": 1192860057600.0,
4
  "train_loss": 3.476953125,
5
- "train_runtime": 82.1231,
6
  "train_samples": 2842,
7
- "train_samples_per_second": 17.474,
8
- "train_steps_per_second": 0.304
9
  }
 
2
  "epoch": 5.0,
3
  "total_flos": 1192860057600.0,
4
  "train_loss": 3.476953125,
5
+ "train_runtime": 86.482,
6
  "train_samples": 2842,
7
+ "train_samples_per_second": 16.593,
8
+ "train_steps_per_second": 0.289
9
  }
config.json CHANGED
@@ -34,6 +34,6 @@
34
  },
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.40.2",
37
- "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
34
  },
35
  "torch_dtype": "bfloat16",
36
  "transformers_version": "4.40.2",
37
+ "use_cache": false,
38
  "vocab_size": 50257
39
  }
train_results.json CHANGED
@@ -2,8 +2,8 @@
2
  "epoch": 5.0,
3
  "total_flos": 1192860057600.0,
4
  "train_loss": 3.476953125,
5
- "train_runtime": 82.1231,
6
  "train_samples": 2842,
7
- "train_samples_per_second": 17.474,
8
- "train_steps_per_second": 0.304
9
  }
 
2
  "epoch": 5.0,
3
  "total_flos": 1192860057600.0,
4
  "train_loss": 3.476953125,
5
+ "train_runtime": 86.482,
6
  "train_samples": 2842,
7
+ "train_samples_per_second": 16.593,
8
+ "train_steps_per_second": 0.289
9
  }
trainer_state.json CHANGED
@@ -55,9 +55,9 @@
55
  "step": 25,
56
  "total_flos": 1192860057600.0,
57
  "train_loss": 3.476953125,
58
- "train_runtime": 82.1231,
59
- "train_samples_per_second": 17.474,
60
- "train_steps_per_second": 0.304
61
  }
62
  ],
63
  "logging_steps": 5,
 
55
  "step": 25,
56
  "total_flos": 1192860057600.0,
57
  "train_loss": 3.476953125,
58
+ "train_runtime": 86.482,
59
+ "train_samples_per_second": 16.593,
60
+ "train_steps_per_second": 0.289
61
  }
62
  ],
63
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79cbd345f17ffaee0fc38e86461190aba597a5d76f683cf8998dbee504e25fd0
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ca106782809be22ef2a6aa576588bc237bf896823712f4629e1fdae100e6016
3
  size 6200