Hugging Face's logo

HarshalH
/
output_dir

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
trl
sft
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
HarshalH commited on
Commit
2100b40
·
verified ·
1 Parent(s): f291697

HarshalH/OnlySFT

Browse files
Files changed (9) hide show
  1. README.md +15 -13
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
  5. runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728188604.40898b2f87bd.30.0 +3 -0
  6. runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728189041.40898b2f87bd.30.1 +3 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +1 -1
  9. training_args.bin +2 -2
README.md CHANGED
@@ -3,11 +3,9 @@ library_name: transformers
3
  license: mit
4
  base_model: gpt2
5
  tags:
6
- - trl
7
- - sft
8
  - generated_from_trainer
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: output_dir
13
  results: []
@@ -18,10 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # output_dir
20
 
21
- This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.4202
24
- - Model Preparation Time: 0.0039
25
 
26
  ## Model description
27
 
@@ -40,21 +37,26 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 0.0002
44
- - train_batch_size: 4
45
- - eval_batch_size: 8
46
  - seed: 42
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
- - num_epochs: 1
50
 
51
  ### Training results
52
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
56
 
57
- - Transformers 4.44.2
58
  - Pytorch 2.4.0
59
- - Datasets 3.0.0
60
- - Tokenizers 0.19.1
 
3
  license: mit
4
  base_model: gpt2
5
  tags:
 
 
6
  - generated_from_trainer
7
  datasets:
8
+ - scitldr
9
  model-index:
10
  - name: output_dir
11
  results: []
 
16
 
17
  # output_dir
18
 
19
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the scitldr dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.3648
 
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 16
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 3.0
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 125 | 3.4195 |
53
+ | No log | 2.0 | 250 | 3.3752 |
54
+ | No log | 3.0 | 375 | 3.3648 |
55
 
56
 
57
  ### Framework versions
58
 
59
+ - Transformers 4.45.1
60
  - Pytorch 2.4.0
61
+ - Datasets 3.0.1
62
+ - Tokenizers 0.20.0
config.json CHANGED
@@ -33,7 +33,7 @@
33
  }
34
  },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.44.2",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.45.1",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.44.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.45.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71ed609a2380b88caf4c1cd6b5a8b23ffe45d318b69c7234f2a9b3ca68930ba7
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d9ab37ac1418f598d273a6d8d27aaeffc53d4702e6ac0def9615308793d5386
3
  size 497774208
runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728188604.40898b2f87bd.30.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69d6458371251173f54403a3d9797da8042c06f4fa0a232dd04476858dc3cf8c
3
+ size 6361
runs/Oct06_04-23-21_40898b2f87bd/events.out.tfevents.1728189041.40898b2f87bd.30.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8869f39408e58cc12ce0675cead841db4b64a0e654a32c49110b30efb13f08fd
3
+ size 359
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -11,7 +11,7 @@
11
  }
12
  },
13
  "bos_token": "<|endoftext|>",
14
- "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",
 
11
  }
12
  },
13
  "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:001ed3f93051497be8912b177276192701edca05cdcd60f16d6c9519a42961f4
3
- size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed9f52ffddeb48fb2940c27b404e8f16eed53e637af8752e5a7ac9eb6df99acc
3
+ size 5240