Hugging Face's logo

MarkGG
/
Romance-cleaned-3

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
1
MarkGG commited on
Commit
3aff318
·
1 Parent(s): 26c4369

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +52 -22
README.md CHANGED
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 5.6216
18
 
19
  ## Model description
20
 
@@ -42,33 +42,63 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_steps: 1000
45
- - num_epochs: 20
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | No log | 1.0 | 16 | 9.9825 |
53
- | No log | 2.0 | 32 | 9.0942 |
54
- | No log | 3.0 | 48 | 8.5804 |
55
- | No log | 4.0 | 64 | 8.3083 |
56
- | No log | 5.0 | 80 | 8.0240 |
57
- | No log | 6.0 | 96 | 7.8109 |
58
- | No log | 7.0 | 112 | 7.5935 |
59
- | No log | 8.0 | 128 | 7.3827 |
60
- | No log | 9.0 | 144 | 7.2061 |
61
- | No log | 10.0 | 160 | 7.0479 |
62
- | No log | 11.0 | 176 | 6.8981 |
63
- | No log | 12.0 | 192 | 6.7452 |
64
- | No log | 13.0 | 208 | 6.5939 |
65
- | No log | 14.0 | 224 | 6.4373 |
66
- | No log | 15.0 | 240 | 6.2812 |
67
- | No log | 16.0 | 256 | 6.1414 |
68
- | No log | 17.0 | 272 | 5.9914 |
69
- | No log | 18.0 | 288 | 5.8628 |
70
- | No log | 19.0 | 304 | 5.7336 |
71
- | No log | 20.0 | 320 | 5.6216 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
72
 
73
 
74
  ### Framework versions
 
14
 
15
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 4.9593
18
 
19
  ## Model description
20
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: cosine
44
  - lr_scheduler_warmup_steps: 1000
45
+ - num_epochs: 50
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 1.0 | 16 | 10.0173 |
53
+ | No log | 2.0 | 32 | 9.1598 |
54
+ | No log | 3.0 | 48 | 8.6820 |
55
+ | No log | 4.0 | 64 | 8.3963 |
56
+ | No log | 5.0 | 80 | 8.1259 |
57
+ | No log | 6.0 | 96 | 7.9259 |
58
+ | No log | 7.0 | 112 | 7.6943 |
59
+ | No log | 8.0 | 128 | 7.4803 |
60
+ | No log | 9.0 | 144 | 7.2883 |
61
+ | No log | 10.0 | 160 | 7.1145 |
62
+ | No log | 11.0 | 176 | 6.9568 |
63
+ | No log | 12.0 | 192 | 6.8000 |
64
+ | No log | 13.0 | 208 | 6.6515 |
65
+ | No log | 14.0 | 224 | 6.5033 |
66
+ | No log | 15.0 | 240 | 6.3471 |
67
+ | No log | 16.0 | 256 | 6.2029 |
68
+ | No log | 17.0 | 272 | 6.0583 |
69
+ | No log | 18.0 | 288 | 5.9173 |
70
+ | No log | 19.0 | 304 | 5.7819 |
71
+ | No log | 20.0 | 320 | 5.6710 |
72
+ | No log | 21.0 | 336 | 5.5588 |
73
+ | No log | 22.0 | 352 | 5.4729 |
74
+ | No log | 23.0 | 368 | 5.3980 |
75
+ | No log | 24.0 | 384 | 5.3261 |
76
+ | No log | 25.0 | 400 | 5.2801 |
77
+ | No log | 26.0 | 416 | 5.2317 |
78
+ | No log | 27.0 | 432 | 5.1942 |
79
+ | No log | 28.0 | 448 | 5.1523 |
80
+ | No log | 29.0 | 464 | 5.1235 |
81
+ | No log | 30.0 | 480 | 5.1008 |
82
+ | No log | 31.0 | 496 | 5.0667 |
83
+ | No log | 32.0 | 512 | 5.0472 |
84
+ | No log | 33.0 | 528 | 5.0252 |
85
+ | No log | 34.0 | 544 | 5.0143 |
86
+ | No log | 35.0 | 560 | 5.0049 |
87
+ | No log | 36.0 | 576 | 4.9938 |
88
+ | No log | 37.0 | 592 | 4.9827 |
89
+ | No log | 38.0 | 608 | 4.9719 |
90
+ | No log | 39.0 | 624 | 4.9666 |
91
+ | No log | 40.0 | 640 | 4.9540 |
92
+ | No log | 41.0 | 656 | 4.9549 |
93
+ | No log | 42.0 | 672 | 4.9485 |
94
+ | No log | 43.0 | 688 | 4.9602 |
95
+ | No log | 44.0 | 704 | 4.9464 |
96
+ | No log | 45.0 | 720 | 4.9592 |
97
+ | No log | 46.0 | 736 | 4.9611 |
98
+ | No log | 47.0 | 752 | 4.9558 |
99
+ | No log | 48.0 | 768 | 4.9659 |
100
+ | No log | 49.0 | 784 | 4.9739 |
101
+ | No log | 50.0 | 800 | 4.9593 |
102
 
103
 
104
  ### Framework versions