Hugging Face's logo

henryscheible
/
gpt2_crows_pairs_finetuned

Text Classification
Transformers
PyTorch
gpt2
Generated from Trainer
Eval Results
text-generation-inference
Model card Files Community
1
henryscheible commited on
Commit
5006896
·
1 Parent(s): fb72fff

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -37
README.md CHANGED
@@ -21,7 +21,7 @@ model-index:
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.6423841059602649
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,12 +31,12 @@ should probably proofread and complete it, then remove this comment. -->
31
 
32
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the crows_pairs dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 3.4639
35
- - Accuracy: 0.6424
36
- - Tp: 0.3344
37
- - Tn: 0.3079
38
- - Fp: 0.1656
39
- - Fn: 0.1921
40
 
41
  ## Model description
42
 
@@ -55,46 +55,65 @@ More information needed
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
- - learning_rate: 5e-05
59
  - train_batch_size: 64
60
  - eval_batch_size: 64
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
- - num_epochs: 30
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
70
- | 0.7226 | 1.05 | 20 | 0.7030 | 0.5265 | 0.5265 | 0.0 | 0.4735 | 0.0 |
71
- | 0.691 | 2.11 | 40 | 0.7176 | 0.5199 | 0.4503 | 0.0695 | 0.4040 | 0.0762 |
72
- | 0.7288 | 3.16 | 60 | 0.7409 | 0.5331 | 0.3146 | 0.2185 | 0.2550 | 0.2119 |
73
- | 0.403 | 4.21 | 80 | 0.8119 | 0.5563 | 0.2616 | 0.2947 | 0.1788 | 0.2649 |
74
- | 0.2029 | 5.26 | 100 | 1.2245 | 0.5960 | 0.4205 | 0.1755 | 0.2980 | 0.1060 |
75
- | 0.1727 | 6.32 | 120 | 1.3791 | 0.5795 | 0.4437 | 0.1358 | 0.3377 | 0.0828 |
76
- | 0.0907 | 7.37 | 140 | 1.6621 | 0.5960 | 0.3907 | 0.2053 | 0.2682 | 0.1358 |
77
- | 0.0566 | 8.42 | 160 | 2.7341 | 0.5960 | 0.3444 | 0.2517 | 0.2219 | 0.1821 |
78
- | 0.0616 | 9.47 | 180 | 2.4315 | 0.5861 | 0.2947 | 0.2914 | 0.1821 | 0.2318 |
79
- | 0.0794 | 10.53 | 200 | 2.3228 | 0.5795 | 0.4371 | 0.1424 | 0.3311 | 0.0894 |
80
- | 0.0329 | 11.58 | 220 | 2.4578 | 0.6026 | 0.2318 | 0.3709 | 0.1026 | 0.2947 |
81
- | 0.0788 | 12.63 | 240 | 2.5637 | 0.6026 | 0.3311 | 0.2715 | 0.2020 | 0.1954 |
82
- | 0.0164 | 13.68 | 260 | 2.4828 | 0.6159 | 0.3510 | 0.2649 | 0.2086 | 0.1755 |
83
- | 0.02 | 14.74 | 280 | 3.1787 | 0.5894 | 0.3046 | 0.2848 | 0.1887 | 0.2219 |
84
- | 0.0256 | 15.79 | 300 | 3.4015 | 0.6093 | 0.3212 | 0.2881 | 0.1854 | 0.2053 |
85
- | 0.0006 | 16.84 | 320 | 3.1505 | 0.6358 | 0.3411 | 0.2947 | 0.1788 | 0.1854 |
86
- | 0.0004 | 17.89 | 340 | 3.3157 | 0.6126 | 0.3642 | 0.2483 | 0.2252 | 0.1623 |
87
- | 0.0224 | 18.95 | 360 | 3.2259 | 0.6258 | 0.3113 | 0.3146 | 0.1589 | 0.2152 |
88
- | 0.0001 | 20.0 | 380 | 3.3545 | 0.6325 | 0.3576 | 0.2748 | 0.1987 | 0.1689 |
89
- | 0.0033 | 21.05 | 400 | 3.2960 | 0.6358 | 0.3377 | 0.2980 | 0.1755 | 0.1887 |
90
- | 0.0039 | 22.11 | 420 | 3.4235 | 0.6358 | 0.3642 | 0.2715 | 0.2020 | 0.1623 |
91
- | 0.0001 | 23.16 | 440 | 3.3855 | 0.6325 | 0.3311 | 0.3013 | 0.1722 | 0.1954 |
92
- | 0.0001 | 24.21 | 460 | 3.5120 | 0.6291 | 0.3709 | 0.2583 | 0.2152 | 0.1556 |
93
- | 0.0222 | 25.26 | 480 | 3.5530 | 0.6457 | 0.3278 | 0.3179 | 0.1556 | 0.1987 |
94
- | 0.0003 | 26.32 | 500 | 3.4705 | 0.6325 | 0.3477 | 0.2848 | 0.1887 | 0.1788 |
95
- | 0.0013 | 27.37 | 520 | 3.5134 | 0.6424 | 0.3411 | 0.3013 | 0.1722 | 0.1854 |
96
- | 0.017 | 28.42 | 540 | 3.4743 | 0.6424 | 0.3411 | 0.3013 | 0.1722 | 0.1854 |
97
- | 0.0069 | 29.47 | 560 | 3.4639 | 0.6424 | 0.3344 | 0.3079 | 0.1656 | 0.1921 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
 
99
 
100
  ### Framework versions
 
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.5033112582781457
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the crows_pairs dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 4.9930
35
+ - Accuracy: 0.5033
36
+ - Tp: 0.2550
37
+ - Tn: 0.2483
38
+ - Fp: 0.2483
39
+ - Fn: 0.2483
40
 
41
  ## Model description
42
 
 
55
  ### Training hyperparameters
56
 
57
  The following hyperparameters were used during training:
58
+ - learning_rate: 0.0001
59
  - train_batch_size: 64
60
  - eval_batch_size: 64
61
  - seed: 42
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
+ - num_epochs: 50
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
70
+ | 0.7446 | 1.05 | 20 | 0.6999 | 0.5033 | 0.5033 | 0.0 | 0.4967 | 0.0 |
71
+ | 0.7055 | 2.11 | 40 | 0.6967 | 0.5298 | 0.1060 | 0.4238 | 0.0728 | 0.3974 |
72
+ | 0.5364 | 3.16 | 60 | 1.1300 | 0.5232 | 0.1954 | 0.3278 | 0.1689 | 0.3079 |
73
+ | 0.2964 | 4.21 | 80 | 1.4674 | 0.5066 | 0.3444 | 0.1623 | 0.3344 | 0.1589 |
74
+ | 0.1457 | 5.26 | 100 | 2.1908 | 0.5066 | 0.3377 | 0.1689 | 0.3278 | 0.1656 |
75
+ | 0.046 | 6.32 | 120 | 3.5623 | 0.4768 | 0.2483 | 0.2285 | 0.2682 | 0.2550 |
76
+ | 0.0065 | 7.37 | 140 | 3.5099 | 0.5099 | 0.2483 | 0.2616 | 0.2351 | 0.2550 |
77
+ | 0.0418 | 8.42 | 160 | 3.2697 | 0.5199 | 0.2881 | 0.2318 | 0.2649 | 0.2152 |
78
+ | 0.0405 | 9.47 | 180 | 2.3453 | 0.5298 | 0.2616 | 0.2682 | 0.2285 | 0.2417 |
79
+ | 0.0399 | 10.53 | 200 | 4.0289 | 0.5397 | 0.3907 | 0.1490 | 0.3477 | 0.1126 |
80
+ | 0.01 | 11.58 | 220 | 3.3080 | 0.4834 | 0.2649 | 0.2185 | 0.2781 | 0.2384 |
81
+ | 0.0058 | 12.63 | 240 | 3.8782 | 0.5099 | 0.3013 | 0.2086 | 0.2881 | 0.2020 |
82
+ | 0.0052 | 13.68 | 260 | 4.5345 | 0.5066 | 0.2185 | 0.2881 | 0.2086 | 0.2848 |
83
+ | 0.026 | 14.74 | 280 | 4.9005 | 0.4967 | 0.2881 | 0.2086 | 0.2881 | 0.2152 |
84
+ | 0.0003 | 15.79 | 300 | 3.9885 | 0.5066 | 0.2914 | 0.2152 | 0.2815 | 0.2119 |
85
+ | 0.0159 | 16.84 | 320 | 3.1788 | 0.5298 | 0.2583 | 0.2715 | 0.2252 | 0.2450 |
86
+ | 0.0136 | 17.89 | 340 | 3.2487 | 0.5430 | 0.2517 | 0.2914 | 0.2053 | 0.2517 |
87
+ | 0.0039 | 18.95 | 360 | 4.0264 | 0.5166 | 0.2781 | 0.2384 | 0.2583 | 0.2252 |
88
+ | 0.0115 | 20.0 | 380 | 4.0050 | 0.5298 | 0.2815 | 0.2483 | 0.2483 | 0.2219 |
89
+ | 0.001 | 21.05 | 400 | 4.1541 | 0.5199 | 0.2947 | 0.2252 | 0.2715 | 0.2086 |
90
+ | 0.0139 | 22.11 | 420 | 4.2958 | 0.5232 | 0.2285 | 0.2947 | 0.2020 | 0.2748 |
91
+ | 0.0105 | 23.16 | 440 | 4.4861 | 0.5033 | 0.3013 | 0.2020 | 0.2947 | 0.2020 |
92
+ | 0.0 | 24.21 | 460 | 4.5776 | 0.5232 | 0.2583 | 0.2649 | 0.2318 | 0.2450 |
93
+ | 0.0002 | 25.26 | 480 | 4.7577 | 0.5265 | 0.2881 | 0.2384 | 0.2583 | 0.2152 |
94
+ | 0.0075 | 26.32 | 500 | 4.8050 | 0.5132 | 0.2417 | 0.2715 | 0.2252 | 0.2616 |
95
+ | 0.0016 | 27.37 | 520 | 4.9786 | 0.5132 | 0.2980 | 0.2152 | 0.2815 | 0.2053 |
96
+ | 0.0248 | 28.42 | 540 | 4.9352 | 0.5066 | 0.2980 | 0.2086 | 0.2881 | 0.2053 |
97
+ | 0.0191 | 29.47 | 560 | 4.4478 | 0.5265 | 0.2715 | 0.2550 | 0.2417 | 0.2318 |
98
+ | 0.0001 | 30.53 | 580 | 4.6225 | 0.5066 | 0.3146 | 0.1921 | 0.3046 | 0.1887 |
99
+ | 0.0 | 31.58 | 600 | 4.7652 | 0.5066 | 0.3079 | 0.1987 | 0.2980 | 0.1954 |
100
+ | 0.0 | 32.63 | 620 | 4.6810 | 0.5099 | 0.2483 | 0.2616 | 0.2351 | 0.2550 |
101
+ | 0.0 | 33.68 | 640 | 4.7454 | 0.5066 | 0.2351 | 0.2715 | 0.2252 | 0.2682 |
102
+ | 0.0 | 34.74 | 660 | 4.8393 | 0.5066 | 0.2351 | 0.2715 | 0.2252 | 0.2682 |
103
+ | 0.0 | 35.79 | 680 | 4.9037 | 0.5033 | 0.2351 | 0.2682 | 0.2285 | 0.2682 |
104
+ | 0.0063 | 36.84 | 700 | 4.9000 | 0.5033 | 0.2483 | 0.2550 | 0.2417 | 0.2550 |
105
+ | 0.0 | 37.89 | 720 | 4.8870 | 0.5199 | 0.2881 | 0.2318 | 0.2649 | 0.2152 |
106
+ | 0.0 | 38.95 | 740 | 4.9287 | 0.5166 | 0.2848 | 0.2318 | 0.2649 | 0.2185 |
107
+ | 0.0 | 40.0 | 760 | 4.9847 | 0.5166 | 0.2781 | 0.2384 | 0.2583 | 0.2252 |
108
+ | 0.0 | 41.05 | 780 | 5.0157 | 0.5166 | 0.2781 | 0.2384 | 0.2583 | 0.2252 |
109
+ | 0.0 | 42.11 | 800 | 5.0444 | 0.5166 | 0.2748 | 0.2417 | 0.2550 | 0.2285 |
110
+ | 0.0 | 43.16 | 820 | 5.0695 | 0.5099 | 0.2682 | 0.2417 | 0.2550 | 0.2351 |
111
+ | 0.0 | 44.21 | 840 | 5.0897 | 0.5066 | 0.2649 | 0.2417 | 0.2550 | 0.2384 |
112
+ | 0.0 | 45.26 | 860 | 5.1197 | 0.5066 | 0.2616 | 0.2450 | 0.2517 | 0.2417 |
113
+ | 0.0 | 46.32 | 880 | 5.1315 | 0.5066 | 0.2616 | 0.2450 | 0.2517 | 0.2417 |
114
+ | 0.0137 | 47.37 | 900 | 5.0644 | 0.5 | 0.2550 | 0.2450 | 0.2517 | 0.2483 |
115
+ | 0.0 | 48.42 | 920 | 4.9947 | 0.5033 | 0.2550 | 0.2483 | 0.2483 | 0.2483 |
116
+ | 0.0 | 49.47 | 940 | 4.9930 | 0.5033 | 0.2550 | 0.2483 | 0.2483 | 0.2483 |
117
 
118
 
119
  ### Framework versions