Hugging Face's logo

ldm0612
/
lig_model_1

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
ldm0612 commited on
Commit
fd0635c
•
1 Parent(s): 782230e

End of training

Browse files
Files changed (10) hide show
  1. README.md +69 -29
  2. config.json +2 -2
  3. generation_config.json +1 -1
  4. merges.txt +0 -0
  5. model.safetensors +2 -2
  6. runs/May27_20-03-52_a770b5fedbe1/events.out.tfevents.1716840235.a770b5fedbe1.872.0 +3 -0
  7. runs/May27_20-03-52_a770b5fedbe1/events.out.tfevents.1716844080.a770b5fedbe1.872.1 +3 -0
  8. tokenizer.json +0 -0
  9. training_args.bin +2 -2
  10. vocab.json +0 -0
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 6.0053
19
 
20
  ## Model description
21
 
@@ -43,40 +43,80 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_steps: 10
46
- - num_epochs: 10
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:------:|:----:|:---------------:|
52
- | 8.5938 | 0.4129 | 8 | 8.2422 |
53
- | 7.2707 | 0.8258 | 16 | 7.1569 |
54
- | 7.0574 | 1.2387 | 24 | 7.0463 |
55
- | 6.8825 | 1.6516 | 32 | 6.8864 |
56
- | 6.7839 | 2.0645 | 40 | 6.7678 |
57
- | 6.631 | 2.4774 | 48 | 6.6710 |
58
- | 6.5484 | 2.8903 | 56 | 6.5532 |
59
- | 6.3611 | 3.3032 | 64 | 6.4609 |
60
- | 6.3755 | 3.7161 | 72 | 6.4121 |
61
- | 6.2088 | 4.1290 | 80 | 6.3268 |
62
- | 6.1636 | 4.5419 | 88 | 6.2846 |
63
- | 6.1312 | 4.9548 | 96 | 6.2282 |
64
- | 6.0123 | 5.3677 | 104 | 6.1946 |
65
- | 6.0009 | 5.7806 | 112 | 6.1529 |
66
- | 5.8959 | 6.1935 | 120 | 6.1212 |
67
- | 5.8683 | 6.6065 | 128 | 6.0844 |
68
- | 5.8714 | 7.0194 | 136 | 6.0617 |
69
- | 5.7793 | 7.4323 | 144 | 6.0414 |
70
- | 5.7765 | 7.8452 | 152 | 6.0233 |
71
- | 5.7313 | 8.2581 | 160 | 6.0146 |
72
- | 5.7357 | 8.6710 | 168 | 6.0096 |
73
- | 5.7303 | 9.0839 | 176 | 6.0060 |
74
- | 5.724 | 9.4968 | 184 | 6.0053 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.40.2
80
- - Pytorch 2.2.1+cu121
81
  - Datasets 2.19.1
82
  - Tokenizers 0.19.1
 
15
 
16
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.7688
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: cosine
45
  - lr_scheduler_warmup_steps: 10
46
+ - num_epochs: 15
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:-------:|:----:|:---------------:|
52
+ | 6.8679 | 0.2310 | 8 | 6.6211 |
53
+ | 6.3894 | 0.4621 | 16 | 6.3666 |
54
+ | 6.2641 | 0.6931 | 24 | 6.2481 |
55
+ | 6.1285 | 0.9242 | 32 | 6.0829 |
56
+ | 5.9436 | 1.1552 | 40 | 5.8900 |
57
+ | 5.8073 | 1.3863 | 48 | 5.7490 |
58
+ | 5.7164 | 1.6173 | 56 | 5.6617 |
59
+ | 5.6019 | 1.8484 | 64 | 5.5778 |
60
+ | 5.5427 | 2.0794 | 72 | 5.4886 |
61
+ | 5.454 | 2.3105 | 80 | 5.3954 |
62
+ | 5.3546 | 2.5415 | 88 | 5.3066 |
63
+ | 5.3014 | 2.7726 | 96 | 5.2124 |
64
+ | 5.2448 | 3.0036 | 104 | 5.1365 |
65
+ | 5.1185 | 3.2347 | 112 | 5.0765 |
66
+ | 5.0938 | 3.4657 | 120 | 5.0071 |
67
+ | 5.0347 | 3.6968 | 128 | 4.9339 |
68
+ | 4.9681 | 3.9278 | 136 | 4.8552 |
69
+ | 4.8323 | 4.1588 | 144 | 4.7821 |
70
+ | 4.7912 | 4.3899 | 152 | 4.7215 |
71
+ | 4.7225 | 4.6209 | 160 | 4.6431 |
72
+ | 4.6433 | 4.8520 | 168 | 4.5701 |
73
+ | 4.5309 | 5.0830 | 176 | 4.5002 |
74
+ | 4.4506 | 5.3141 | 184 | 4.4442 |
75
+ | 4.4097 | 5.5451 | 192 | 4.3820 |
76
+ | 4.3871 | 5.7762 | 200 | 4.3290 |
77
+ | 4.3345 | 6.0072 | 208 | 4.2869 |
78
+ | 4.2004 | 6.2383 | 216 | 4.2412 |
79
+ | 4.1716 | 6.4693 | 224 | 4.1978 |
80
+ | 4.1536 | 6.7004 | 232 | 4.1607 |
81
+ | 4.0975 | 6.9314 | 240 | 4.1294 |
82
+ | 3.9743 | 7.1625 | 248 | 4.1014 |
83
+ | 3.922 | 7.3935 | 256 | 4.0654 |
84
+ | 3.939 | 7.6245 | 264 | 4.0378 |
85
+ | 3.9208 | 7.8556 | 272 | 4.0102 |
86
+ | 3.8083 | 8.0866 | 280 | 3.9812 |
87
+ | 3.7611 | 8.3177 | 288 | 3.9630 |
88
+ | 3.7668 | 8.5487 | 296 | 3.9407 |
89
+ | 3.7285 | 8.7798 | 304 | 3.9183 |
90
+ | 3.6996 | 9.0108 | 312 | 3.8958 |
91
+ | 3.5754 | 9.2419 | 320 | 3.8825 |
92
+ | 3.5708 | 9.4729 | 328 | 3.8702 |
93
+ | 3.5607 | 9.7040 | 336 | 3.8510 |
94
+ | 3.5688 | 9.9350 | 344 | 3.8387 |
95
+ | 3.4188 | 10.1661 | 352 | 3.8350 |
96
+ | 3.432 | 10.3971 | 360 | 3.8261 |
97
+ | 3.4236 | 10.6282 | 368 | 3.8131 |
98
+ | 3.3985 | 10.8592 | 376 | 3.8026 |
99
+ | 3.306 | 11.0903 | 384 | 3.7934 |
100
+ | 3.3196 | 11.3213 | 392 | 3.7919 |
101
+ | 3.3031 | 11.5523 | 400 | 3.7908 |
102
+ | 3.2851 | 11.7834 | 408 | 3.7817 |
103
+ | 3.2703 | 12.0144 | 416 | 3.7789 |
104
+ | 3.2132 | 12.2455 | 424 | 3.7818 |
105
+ | 3.1829 | 12.4765 | 432 | 3.7778 |
106
+ | 3.1968 | 12.7076 | 440 | 3.7749 |
107
+ | 3.2206 | 12.9386 | 448 | 3.7711 |
108
+ | 3.1521 | 13.1697 | 456 | 3.7694 |
109
+ | 3.1412 | 13.4007 | 464 | 3.7700 |
110
+ | 3.1415 | 13.6318 | 472 | 3.7709 |
111
+ | 3.1402 | 13.8628 | 480 | 3.7694 |
112
+ | 3.129 | 14.0939 | 488 | 3.7689 |
113
+ | 3.1221 | 14.3249 | 496 | 3.7687 |
114
+ | 3.1576 | 14.5560 | 504 | 3.7688 |
115
 
116
 
117
  ### Framework versions
118
 
119
+ - Transformers 4.41.0
120
+ - Pytorch 2.3.0+cu121
121
  - Datasets 2.19.1
122
  - Tokenizers 0.19.1
config.json CHANGED
@@ -33,7 +33,7 @@
33
  }
34
  },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.40.2",
37
  "use_cache": true,
38
- "vocab_size": 25000
39
  }
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.41.0",
37
  "use_cache": true,
38
+ "vocab_size": 2500
39
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
- "transformers_version": "4.40.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 0,
4
  "eos_token_id": 0,
5
+ "transformers_version": "4.41.0"
6
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfb81b9eb766bdbc992801d16d2a3499ff4cd44245f1a40dbbc77591201ee388
3
- size 420184704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ace8794fd5e49d9fb2cd6dea87f4b70acf62d85f88a22e0d4470c31d2f48acb
3
+ size 351064704
runs/May27_20-03-52_a770b5fedbe1/events.out.tfevents.1716840235.a770b5fedbe1.872.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6884833a55dee994effe5ca7f2e733847bb98a27b2e42e08b160091da67ddf3
3
+ size 49042
runs/May27_20-03-52_a770b5fedbe1/events.out.tfevents.1716844080.a770b5fedbe1.872.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a0dae89ac562a95604707be938196471a8e80505de8b64385449174cd13bd39
3
+ size 359
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da5bd7f44ad86b20c765f11505e7afe276661660d969f1bf9393af26cd58c6de
3
- size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9718ad8627a3d80d82421ecf1e84eee7058e348eae4b3d45ce8175e85a60fb
3
+ size 5048
vocab.json CHANGED
The diff for this file is too large to render. See raw diff