Commit
•
2c315ae
1
Parent(s):
a8e3fd2
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
|
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
31 |
|
32 |
This model is a fine-tuned version of [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the crows_pairs dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
-
- Loss:
|
35 |
-
- Accuracy: 0.
|
36 |
|
37 |
## Model description
|
38 |
|
@@ -51,7 +51,7 @@ More information needed
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
-
- learning_rate:
|
55 |
- train_batch_size: 64
|
56 |
- eval_batch_size: 64
|
57 |
- seed: 42
|
@@ -63,63 +63,63 @@ The following hyperparameters were used during training:
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
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 |
-
| 0.
|
99 |
-
| 0.
|
100 |
-
| 0.
|
101 |
-
| 0.
|
102 |
-
| 0.
|
103 |
-
| 0.
|
104 |
-
| 0.
|
105 |
-
| 0.
|
106 |
-
| 0.
|
107 |
-
| 0.
|
108 |
-
| 0.
|
109 |
-
| 0.
|
110 |
-
| 0.
|
111 |
-
| 0.
|
112 |
-
| 0.
|
113 |
-
| 0.
|
114 |
-
| 0.
|
115 |
-
| 0.
|
116 |
-
| 0.
|
117 |
-
| 0.
|
118 |
-
| 0.
|
119 |
-
| 0.
|
120 |
-
| 0.
|
121 |
-
| 0.
|
122 |
-
| 0.
|
123 |
|
124 |
|
125 |
### Framework versions
|
|
|
21 |
metrics:
|
22 |
- name: Accuracy
|
23 |
type: accuracy
|
24 |
+
value: 0.7119205298013245
|
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 [xlnet-base-cased](https://huggingface.co/xlnet-base-cased) on the crows_pairs dataset.
|
33 |
It achieves the following results on the evaluation set:
|
34 |
+
- Loss: 2.5652
|
35 |
+
- Accuracy: 0.7119
|
36 |
|
37 |
## Model description
|
38 |
|
|
|
51 |
### Training hyperparameters
|
52 |
|
53 |
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
- train_batch_size: 64
|
56 |
- eval_batch_size: 64
|
57 |
- seed: 42
|
|
|
63 |
|
64 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
65 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
66 |
+
| 0.728 | 0.53 | 10 | 0.6939 | 0.4901 |
|
67 |
+
| 0.6914 | 1.05 | 20 | 0.6939 | 0.4901 |
|
68 |
+
| 0.705 | 1.58 | 30 | 0.6925 | 0.5066 |
|
69 |
+
| 0.6993 | 2.11 | 40 | 0.6949 | 0.5066 |
|
70 |
+
| 0.6979 | 2.63 | 50 | 0.6996 | 0.5066 |
|
71 |
+
| 0.7152 | 3.16 | 60 | 0.6940 | 0.4901 |
|
72 |
+
| 0.7158 | 3.68 | 70 | 0.7007 | 0.4934 |
|
73 |
+
| 0.6968 | 4.21 | 80 | 0.6999 | 0.5066 |
|
74 |
+
| 0.7164 | 4.74 | 90 | 0.6977 | 0.4934 |
|
75 |
+
| 0.6698 | 5.26 | 100 | 0.7079 | 0.4536 |
|
76 |
+
| 0.611 | 5.79 | 110 | 0.8882 | 0.5099 |
|
77 |
+
| 0.6487 | 6.32 | 120 | 0.8360 | 0.5066 |
|
78 |
+
| 0.5223 | 6.84 | 130 | 0.8047 | 0.5728 |
|
79 |
+
| 0.2879 | 7.37 | 140 | 1.1483 | 0.5795 |
|
80 |
+
| 0.2369 | 7.89 | 150 | 1.1773 | 0.5993 |
|
81 |
+
| 0.2542 | 8.42 | 160 | 0.9170 | 0.6424 |
|
82 |
+
| 0.1743 | 8.95 | 170 | 1.3674 | 0.6424 |
|
83 |
+
| 0.1307 | 9.47 | 180 | 1.0740 | 0.7152 |
|
84 |
+
| 0.0718 | 10.0 | 190 | 1.4397 | 0.6424 |
|
85 |
+
| 0.0278 | 10.53 | 200 | 1.9821 | 0.6523 |
|
86 |
+
| 0.0519 | 11.05 | 210 | 1.6970 | 0.6755 |
|
87 |
+
| 0.0269 | 11.58 | 220 | 1.8299 | 0.6656 |
|
88 |
+
| 0.0556 | 12.11 | 230 | 1.9459 | 0.7086 |
|
89 |
+
| 0.0455 | 12.63 | 240 | 1.6443 | 0.6854 |
|
90 |
+
| 0.0665 | 13.16 | 250 | 1.9887 | 0.6821 |
|
91 |
+
| 0.009 | 13.68 | 260 | 2.0236 | 0.6788 |
|
92 |
+
| 0.0146 | 14.21 | 270 | 1.8515 | 0.7152 |
|
93 |
+
| 0.0034 | 14.74 | 280 | 1.9315 | 0.7252 |
|
94 |
+
| 0.0248 | 15.26 | 290 | 2.0754 | 0.7119 |
|
95 |
+
| 0.0536 | 15.79 | 300 | 2.0371 | 0.7053 |
|
96 |
+
| 0.0393 | 16.32 | 310 | 1.9381 | 0.6987 |
|
97 |
+
| 0.0255 | 16.84 | 320 | 1.9074 | 0.6788 |
|
98 |
+
| 0.0116 | 17.37 | 330 | 2.2182 | 0.6623 |
|
99 |
+
| 0.0128 | 17.89 | 340 | 2.3002 | 0.6689 |
|
100 |
+
| 0.0006 | 18.42 | 350 | 2.2353 | 0.6788 |
|
101 |
+
| 0.0053 | 18.95 | 360 | 2.4277 | 0.6755 |
|
102 |
+
| 0.0013 | 19.47 | 370 | 2.5156 | 0.6490 |
|
103 |
+
| 0.0004 | 20.0 | 380 | 2.5091 | 0.6689 |
|
104 |
+
| 0.0003 | 20.53 | 390 | 2.4096 | 0.6854 |
|
105 |
+
| 0.0017 | 21.05 | 400 | 2.3497 | 0.6921 |
|
106 |
+
| 0.0001 | 21.58 | 410 | 2.3376 | 0.6854 |
|
107 |
+
| 0.012 | 22.11 | 420 | 2.3832 | 0.6854 |
|
108 |
+
| 0.0002 | 22.63 | 430 | 2.4388 | 0.7053 |
|
109 |
+
| 0.0001 | 23.16 | 440 | 2.4821 | 0.7152 |
|
110 |
+
| 0.0001 | 23.68 | 450 | 2.5027 | 0.7119 |
|
111 |
+
| 0.0001 | 24.21 | 460 | 2.5105 | 0.7152 |
|
112 |
+
| 0.0001 | 24.74 | 470 | 2.5145 | 0.7152 |
|
113 |
+
| 0.0002 | 25.26 | 480 | 2.5143 | 0.6954 |
|
114 |
+
| 0.0001 | 25.79 | 490 | 2.5629 | 0.6821 |
|
115 |
+
| 0.0002 | 26.32 | 500 | 2.5414 | 0.6887 |
|
116 |
+
| 0.0001 | 26.84 | 510 | 2.5301 | 0.7119 |
|
117 |
+
| 0.0012 | 27.37 | 520 | 2.5360 | 0.7020 |
|
118 |
+
| 0.0 | 27.89 | 530 | 2.5428 | 0.6921 |
|
119 |
+
| 0.0117 | 28.42 | 540 | 2.5455 | 0.6954 |
|
120 |
+
| 0.0001 | 28.95 | 550 | 2.5598 | 0.7086 |
|
121 |
+
| 0.0001 | 29.47 | 560 | 2.5648 | 0.7119 |
|
122 |
+
| 0.0001 | 30.0 | 570 | 2.5652 | 0.7119 |
|
123 |
|
124 |
|
125 |
### Framework versions
|