Commit ·
40882c4
1
Parent(s): b8d7c76
update model card README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,7 @@ model-index:
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
-
value: 0.
|
| 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: 0.
|
| 35 |
-
- Accuracy: 0.
|
| 36 |
- Tp: 0.1921
|
| 37 |
-
- Tn: 0.
|
| 38 |
-
- Fp: 0.
|
| 39 |
-
- Fn: 0.
|
| 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:
|
| 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:
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Tp | Tn | Fp | Fn |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.
|
| 97 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
|
| 99 |
|
| 100 |
### Framework versions
|
|
|
|
| 21 |
metrics:
|
| 22 |
- name: Accuracy
|
| 23 |
type: accuracy
|
| 24 |
+
value: 0.48344370860927155
|
| 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: 0.7153
|
| 35 |
+
- Accuracy: 0.4834
|
| 36 |
- Tp: 0.1921
|
| 37 |
+
- Tn: 0.2914
|
| 38 |
+
- Fp: 0.2450
|
| 39 |
+
- Fn: 0.2715
|
| 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 |
+
| 0.7312 | 1.05 | 20 | 0.7112 | 0.5397 | 0.2086 | 0.3311 | 0.2053 | 0.2550 |
|
| 71 |
+
| 0.7232 | 2.11 | 40 | 0.7120 | 0.5331 | 0.2318 | 0.3013 | 0.2351 | 0.2318 |
|
| 72 |
+
| 0.7222 | 3.16 | 60 | 0.7119 | 0.5364 | 0.2285 | 0.3079 | 0.2285 | 0.2351 |
|
| 73 |
+
| 0.7162 | 4.21 | 80 | 0.7138 | 0.5397 | 0.2550 | 0.2848 | 0.2517 | 0.2086 |
|
| 74 |
+
| 0.7086 | 5.26 | 100 | 0.7110 | 0.5033 | 0.1689 | 0.3344 | 0.2020 | 0.2947 |
|
| 75 |
+
| 0.6933 | 6.32 | 120 | 0.7139 | 0.5199 | 0.2417 | 0.2781 | 0.2583 | 0.2219 |
|
| 76 |
+
| 0.7015 | 7.37 | 140 | 0.7126 | 0.4967 | 0.1987 | 0.2980 | 0.2384 | 0.2649 |
|
| 77 |
+
| 0.7232 | 8.42 | 160 | 0.7116 | 0.5033 | 0.1921 | 0.3113 | 0.2252 | 0.2715 |
|
| 78 |
+
| 0.7061 | 9.47 | 180 | 0.7113 | 0.4934 | 0.1821 | 0.3113 | 0.2252 | 0.2815 |
|
| 79 |
+
| 0.6887 | 10.53 | 200 | 0.7106 | 0.5166 | 0.1623 | 0.3543 | 0.1821 | 0.3013 |
|
| 80 |
+
| 0.6904 | 11.58 | 220 | 0.7120 | 0.5033 | 0.2152 | 0.2881 | 0.2483 | 0.2483 |
|
| 81 |
+
| 0.6853 | 12.63 | 240 | 0.7111 | 0.4967 | 0.1854 | 0.3113 | 0.2252 | 0.2781 |
|
| 82 |
+
| 0.6826 | 13.68 | 260 | 0.7124 | 0.5066 | 0.1921 | 0.3146 | 0.2219 | 0.2715 |
|
| 83 |
+
| 0.6884 | 14.74 | 280 | 0.7123 | 0.5033 | 0.2053 | 0.2980 | 0.2384 | 0.2583 |
|
| 84 |
+
| 0.6688 | 15.79 | 300 | 0.7133 | 0.4934 | 0.1854 | 0.3079 | 0.2285 | 0.2781 |
|
| 85 |
+
| 0.6725 | 16.84 | 320 | 0.7152 | 0.4801 | 0.2119 | 0.2682 | 0.2682 | 0.2517 |
|
| 86 |
+
| 0.6867 | 17.89 | 340 | 0.7139 | 0.4934 | 0.1954 | 0.2980 | 0.2384 | 0.2682 |
|
| 87 |
+
| 0.6807 | 18.95 | 360 | 0.7143 | 0.4967 | 0.1987 | 0.2980 | 0.2384 | 0.2649 |
|
| 88 |
+
| 0.6878 | 20.0 | 380 | 0.7144 | 0.4901 | 0.1921 | 0.2980 | 0.2384 | 0.2715 |
|
| 89 |
+
| 0.6794 | 21.05 | 400 | 0.7149 | 0.4934 | 0.1954 | 0.2980 | 0.2384 | 0.2682 |
|
| 90 |
+
| 0.6648 | 22.11 | 420 | 0.7157 | 0.4868 | 0.2020 | 0.2848 | 0.2517 | 0.2616 |
|
| 91 |
+
| 0.6826 | 23.16 | 440 | 0.7147 | 0.5033 | 0.1821 | 0.3212 | 0.2152 | 0.2815 |
|
| 92 |
+
| 0.6943 | 24.21 | 460 | 0.7145 | 0.5099 | 0.1921 | 0.3179 | 0.2185 | 0.2715 |
|
| 93 |
+
| 0.6748 | 25.26 | 480 | 0.7146 | 0.5 | 0.1788 | 0.3212 | 0.2152 | 0.2848 |
|
| 94 |
+
| 0.6683 | 26.32 | 500 | 0.7152 | 0.4901 | 0.2020 | 0.2881 | 0.2483 | 0.2616 |
|
| 95 |
+
| 0.6785 | 27.37 | 520 | 0.7151 | 0.4934 | 0.1821 | 0.3113 | 0.2252 | 0.2815 |
|
| 96 |
+
| 0.69 | 28.42 | 540 | 0.7150 | 0.4868 | 0.1921 | 0.2947 | 0.2417 | 0.2715 |
|
| 97 |
+
| 0.6813 | 29.47 | 560 | 0.7155 | 0.4868 | 0.2053 | 0.2815 | 0.2550 | 0.2583 |
|
| 98 |
+
| 0.6793 | 30.53 | 580 | 0.7154 | 0.4834 | 0.1821 | 0.3013 | 0.2351 | 0.2815 |
|
| 99 |
+
| 0.6756 | 31.58 | 600 | 0.7161 | 0.4801 | 0.2020 | 0.2781 | 0.2583 | 0.2616 |
|
| 100 |
+
| 0.6764 | 32.63 | 620 | 0.7168 | 0.4868 | 0.2152 | 0.2715 | 0.2649 | 0.2483 |
|
| 101 |
+
| 0.6786 | 33.68 | 640 | 0.7165 | 0.4834 | 0.2053 | 0.2781 | 0.2583 | 0.2583 |
|
| 102 |
+
| 0.6804 | 34.74 | 660 | 0.7158 | 0.4768 | 0.1921 | 0.2848 | 0.2517 | 0.2715 |
|
| 103 |
+
| 0.6783 | 35.79 | 680 | 0.7150 | 0.4834 | 0.1722 | 0.3113 | 0.2252 | 0.2914 |
|
| 104 |
+
| 0.6773 | 36.84 | 700 | 0.7153 | 0.4768 | 0.1987 | 0.2781 | 0.2583 | 0.2649 |
|
| 105 |
+
| 0.6622 | 37.89 | 720 | 0.7155 | 0.4801 | 0.2053 | 0.2748 | 0.2616 | 0.2583 |
|
| 106 |
+
| 0.681 | 38.95 | 740 | 0.7152 | 0.4768 | 0.1987 | 0.2781 | 0.2583 | 0.2649 |
|
| 107 |
+
| 0.6694 | 40.0 | 760 | 0.7153 | 0.4768 | 0.1921 | 0.2848 | 0.2517 | 0.2715 |
|
| 108 |
+
| 0.6763 | 41.05 | 780 | 0.7150 | 0.4768 | 0.1788 | 0.2980 | 0.2384 | 0.2848 |
|
| 109 |
+
| 0.6805 | 42.11 | 800 | 0.7151 | 0.4801 | 0.1788 | 0.3013 | 0.2351 | 0.2848 |
|
| 110 |
+
| 0.6856 | 43.16 | 820 | 0.7151 | 0.4801 | 0.1788 | 0.3013 | 0.2351 | 0.2848 |
|
| 111 |
+
| 0.6698 | 44.21 | 840 | 0.7150 | 0.4801 | 0.1854 | 0.2947 | 0.2417 | 0.2781 |
|
| 112 |
+
| 0.671 | 45.26 | 860 | 0.7150 | 0.4834 | 0.1854 | 0.2980 | 0.2384 | 0.2781 |
|
| 113 |
+
| 0.6752 | 46.32 | 880 | 0.7151 | 0.4868 | 0.1921 | 0.2947 | 0.2417 | 0.2715 |
|
| 114 |
+
| 0.6656 | 47.37 | 900 | 0.7152 | 0.4834 | 0.1921 | 0.2914 | 0.2450 | 0.2715 |
|
| 115 |
+
| 0.6827 | 48.42 | 920 | 0.7153 | 0.4834 | 0.1921 | 0.2914 | 0.2450 | 0.2715 |
|
| 116 |
+
| 0.6679 | 49.47 | 940 | 0.7153 | 0.4834 | 0.1921 | 0.2914 | 0.2450 | 0.2715 |
|
| 117 |
|
| 118 |
|
| 119 |
### Framework versions
|