Hugging Face's logo

MarkGG
/
Romance-baseline

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
MarkGG commited on
Commit
65b0b5a
·
1 Parent(s): c62d102

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -51
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: 10.0490
18
 
19
  ## Model description
20
 
@@ -49,56 +49,56 @@ The following hyperparameters were used during training:
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | No log | 1.0 | 1 | 11.0546 |
53
- | No log | 2.0 | 2 | 11.0524 |
54
- | No log | 3.0 | 3 | 11.0474 |
55
- | No log | 4.0 | 4 | 11.0406 |
56
- | No log | 5.0 | 5 | 11.0321 |
57
- | No log | 6.0 | 6 | 11.0205 |
58
- | No log | 7.0 | 7 | 11.0073 |
59
- | No log | 8.0 | 8 | 10.9917 |
60
- | No log | 9.0 | 9 | 10.9739 |
61
- | No log | 10.0 | 10 | 10.9532 |
62
- | No log | 11.0 | 11 | 10.9312 |
63
- | No log | 12.0 | 12 | 10.9074 |
64
- | No log | 13.0 | 13 | 10.8813 |
65
- | No log | 14.0 | 14 | 10.8541 |
66
- | No log | 15.0 | 15 | 10.8265 |
67
- | No log | 16.0 | 16 | 10.7961 |
68
- | No log | 17.0 | 17 | 10.7659 |
69
- | No log | 18.0 | 18 | 10.7354 |
70
- | No log | 19.0 | 19 | 10.7039 |
71
- | No log | 20.0 | 20 | 10.6732 |
72
- | No log | 21.0 | 21 | 10.6428 |
73
- | No log | 22.0 | 22 | 10.6126 |
74
- | No log | 23.0 | 23 | 10.5830 |
75
- | No log | 24.0 | 24 | 10.5539 |
76
- | No log | 25.0 | 25 | 10.5255 |
77
- | No log | 26.0 | 26 | 10.4978 |
78
- | No log | 27.0 | 27 | 10.4709 |
79
- | No log | 28.0 | 28 | 10.4451 |
80
- | No log | 29.0 | 29 | 10.4189 |
81
- | No log | 30.0 | 30 | 10.3938 |
82
- | No log | 31.0 | 31 | 10.3696 |
83
- | No log | 32.0 | 32 | 10.3450 |
84
- | No log | 33.0 | 33 | 10.3218 |
85
- | No log | 34.0 | 34 | 10.2993 |
86
- | No log | 35.0 | 35 | 10.2778 |
87
- | No log | 36.0 | 36 | 10.2565 |
88
- | No log | 37.0 | 37 | 10.2371 |
89
- | No log | 38.0 | 38 | 10.2175 |
90
- | No log | 39.0 | 39 | 10.1991 |
91
- | No log | 40.0 | 40 | 10.1822 |
92
- | No log | 41.0 | 41 | 10.1656 |
93
- | No log | 42.0 | 42 | 10.1501 |
94
- | No log | 43.0 | 43 | 10.1352 |
95
- | No log | 44.0 | 44 | 10.1210 |
96
- | No log | 45.0 | 45 | 10.1076 |
97
- | No log | 46.0 | 46 | 10.0949 |
98
- | No log | 47.0 | 47 | 10.0826 |
99
- | No log | 48.0 | 48 | 10.0709 |
100
- | No log | 49.0 | 49 | 10.0598 |
101
- | No log | 50.0 | 50 | 10.0490 |
102
 
103
 
104
  ### 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: 6.5909
18
 
19
  ## Model description
20
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | No log | 0.94 | 15 | 10.7009 |
53
+ | No log | 1.94 | 30 | 10.0799 |
54
+ | No log | 2.94 | 45 | 9.6627 |
55
+ | No log | 3.94 | 60 | 9.4619 |
56
+ | No log | 4.94 | 75 | 9.2970 |
57
+ | No log | 5.94 | 90 | 9.0919 |
58
+ | No log | 6.94 | 105 | 8.9071 |
59
+ | No log | 7.94 | 120 | 8.7240 |
60
+ | No log | 8.94 | 135 | 8.5485 |
61
+ | No log | 9.94 | 150 | 8.3952 |
62
+ | No log | 10.94 | 165 | 8.2469 |
63
+ | No log | 11.94 | 180 | 8.1193 |
64
+ | No log | 12.94 | 195 | 7.9918 |
65
+ | No log | 13.94 | 210 | 7.8662 |
66
+ | No log | 14.94 | 225 | 7.7394 |
67
+ | No log | 15.94 | 240 | 7.6219 |
68
+ | No log | 16.94 | 255 | 7.5135 |
69
+ | No log | 17.94 | 270 | 7.4110 |
70
+ | No log | 18.94 | 285 | 7.3021 |
71
+ | No log | 19.94 | 300 | 7.2021 |
72
+ | No log | 20.94 | 315 | 7.1276 |
73
+ | No log | 21.94 | 330 | 7.0278 |
74
+ | No log | 22.94 | 345 | 6.9627 |
75
+ | No log | 23.94 | 360 | 6.8806 |
76
+ | No log | 24.94 | 375 | 6.8214 |
77
+ | No log | 25.94 | 390 | 6.7725 |
78
+ | No log | 26.94 | 405 | 6.7101 |
79
+ | No log | 27.94 | 420 | 6.6792 |
80
+ | No log | 28.94 | 435 | 6.6361 |
81
+ | No log | 29.94 | 450 | 6.5950 |
82
+ | No log | 30.94 | 465 | 6.5745 |
83
+ | No log | 31.94 | 480 | 6.5469 |
84
+ | No log | 32.94 | 495 | 6.5520 |
85
+ | No log | 33.94 | 510 | 6.5121 |
86
+ | No log | 34.94 | 525 | 6.5255 |
87
+ | No log | 35.94 | 540 | 6.5179 |
88
+ | No log | 36.94 | 555 | 6.5079 |
89
+ | No log | 37.94 | 570 | 6.5138 |
90
+ | No log | 38.94 | 585 | 6.5170 |
91
+ | No log | 39.94 | 600 | 6.4807 |
92
+ | No log | 40.94 | 615 | 6.5338 |
93
+ | No log | 41.94 | 630 | 6.4960 |
94
+ | No log | 42.94 | 645 | 6.5342 |
95
+ | No log | 43.94 | 660 | 6.5119 |
96
+ | No log | 44.94 | 675 | 6.5614 |
97
+ | No log | 45.94 | 690 | 6.5235 |
98
+ | No log | 46.94 | 705 | 6.5388 |
99
+ | No log | 47.94 | 720 | 6.5574 |
100
+ | No log | 48.94 | 735 | 6.5581 |
101
+ | No log | 49.94 | 750 | 6.5909 |
102
 
103
 
104
  ### Framework versions