Hugging Face's logo

wdli
/
gpt2-cpt-dutch

Text Generation
Transformers
Safetensors
gpt2
alignment-handbook
trl
sft
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
wdli commited on
Commit
0e512bc
•
1 Parent(s): 75904d1

Model save

Browse files
Files changed (6) hide show
  1. README.md +3 -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
@@ -2,15 +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
- - wdli/deptweet_dataset
14
  model-index:
15
  - name: gpt2-cpt-dutch
16
  results: []
@@ -21,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  # gpt2-cpt-dutch
23
 
24
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the wdli/deptweet_dataset 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-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": 1.0,
3
  "total_flos": 684585123840000.0,
4
  "train_loss": 4.120773559663354,
5
- "train_runtime": 120.6544,
6
  "train_samples": 32152,
7
- "train_samples_per_second": 10.857,
8
- "train_steps_per_second": 0.68
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 684585123840000.0,
4
  "train_loss": 4.120773559663354,
5
+ "train_runtime": 107.2282,
6
  "train_samples": 32152,
7
+ "train_samples_per_second": 12.217,
8
+ "train_steps_per_second": 0.765
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": 1.0,
3
  "total_flos": 684585123840000.0,
4
  "train_loss": 4.120773559663354,
5
- "train_runtime": 120.6544,
6
  "train_samples": 32152,
7
- "train_samples_per_second": 10.857,
8
- "train_steps_per_second": 0.68
9
  }
 
2
  "epoch": 1.0,
3
  "total_flos": 684585123840000.0,
4
  "train_loss": 4.120773559663354,
5
+ "train_runtime": 107.2282,
6
  "train_samples": 32152,
7
+ "train_samples_per_second": 12.217,
8
+ "train_steps_per_second": 0.765
9
  }
trainer_state.json CHANGED
@@ -132,9 +132,9 @@
132
  "step": 82,
133
  "total_flos": 684585123840000.0,
134
  "train_loss": 4.120773559663354,
135
- "train_runtime": 120.6544,
136
- "train_samples_per_second": 10.857,
137
- "train_steps_per_second": 0.68
138
  }
139
  ],
140
  "logging_steps": 5,
 
132
  "step": 82,
133
  "total_flos": 684585123840000.0,
134
  "train_loss": 4.120773559663354,
135
+ "train_runtime": 107.2282,
136
+ "train_samples_per_second": 12.217,
137
+ "train_steps_per_second": 0.765
138
  }
139
  ],
140
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14a58caf7cfe2d00aff9be0bbb296e554d9ad71d260085b3e7f500ade161affb
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a337a1ae977b8411a677046172f5a84e3d6421fa3a56e9e936c144a9743947d
3
  size 5048