update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,140 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- super_glue
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: '20230831092825'
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# 20230831092825
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the super_glue dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5298
|
22 |
+
- Accuracy: 0.6771
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 0.0003
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 8
|
44 |
+
- seed: 11
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: linear
|
47 |
+
- num_epochs: 80.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| No log | 1.0 | 340 | 0.4989 | 0.5 |
|
54 |
+
| 0.5076 | 2.0 | 680 | 0.4922 | 0.5 |
|
55 |
+
| 0.5029 | 3.0 | 1020 | 0.4980 | 0.5 |
|
56 |
+
| 0.5029 | 4.0 | 1360 | 0.4881 | 0.5125 |
|
57 |
+
| 0.4992 | 5.0 | 1700 | 0.5067 | 0.5 |
|
58 |
+
| 0.4818 | 6.0 | 2040 | 0.4919 | 0.5251 |
|
59 |
+
| 0.4818 | 7.0 | 2380 | 0.5045 | 0.5392 |
|
60 |
+
| 0.4719 | 8.0 | 2720 | 0.4695 | 0.5 |
|
61 |
+
| 0.4636 | 9.0 | 3060 | 0.4805 | 0.5 |
|
62 |
+
| 0.4636 | 10.0 | 3400 | 0.5002 | 0.5 |
|
63 |
+
| 0.4501 | 11.0 | 3740 | 0.5665 | 0.6646 |
|
64 |
+
| 0.4418 | 12.0 | 4080 | 0.5283 | 0.6897 |
|
65 |
+
| 0.4418 | 13.0 | 4420 | 0.4705 | 0.5 |
|
66 |
+
| 0.4352 | 14.0 | 4760 | 0.5644 | 0.6630 |
|
67 |
+
| 0.4302 | 15.0 | 5100 | 0.5080 | 0.6505 |
|
68 |
+
| 0.4302 | 16.0 | 5440 | 0.5084 | 0.6897 |
|
69 |
+
| 0.4305 | 17.0 | 5780 | 0.5006 | 0.6599 |
|
70 |
+
| 0.4203 | 18.0 | 6120 | 0.5246 | 0.6928 |
|
71 |
+
| 0.4203 | 19.0 | 6460 | 0.4958 | 0.6583 |
|
72 |
+
| 0.4166 | 20.0 | 6800 | 0.5595 | 0.6630 |
|
73 |
+
| 0.4117 | 21.0 | 7140 | 0.4796 | 0.5 |
|
74 |
+
| 0.4117 | 22.0 | 7480 | 0.4820 | 0.5 |
|
75 |
+
| 0.4131 | 23.0 | 7820 | 0.5158 | 0.6755 |
|
76 |
+
| 0.406 | 24.0 | 8160 | 0.4801 | 0.5 |
|
77 |
+
| 0.4062 | 25.0 | 8500 | 0.5471 | 0.6646 |
|
78 |
+
| 0.4062 | 26.0 | 8840 | 0.4904 | 0.5 |
|
79 |
+
| 0.4021 | 27.0 | 9180 | 0.4880 | 0.5 |
|
80 |
+
| 0.3971 | 28.0 | 9520 | 0.5019 | 0.6646 |
|
81 |
+
| 0.3971 | 29.0 | 9860 | 0.4825 | 0.5 |
|
82 |
+
| 0.3936 | 30.0 | 10200 | 0.5069 | 0.6693 |
|
83 |
+
| 0.3907 | 31.0 | 10540 | 0.5472 | 0.6693 |
|
84 |
+
| 0.3907 | 32.0 | 10880 | 0.4886 | 0.5 |
|
85 |
+
| 0.3906 | 33.0 | 11220 | 0.5531 | 0.6693 |
|
86 |
+
| 0.3888 | 34.0 | 11560 | 0.5023 | 0.5266 |
|
87 |
+
| 0.3888 | 35.0 | 11900 | 0.4896 | 0.5 |
|
88 |
+
| 0.387 | 36.0 | 12240 | 0.4985 | 0.5 |
|
89 |
+
| 0.3836 | 37.0 | 12580 | 0.5309 | 0.6834 |
|
90 |
+
| 0.3836 | 38.0 | 12920 | 0.5402 | 0.6818 |
|
91 |
+
| 0.3792 | 39.0 | 13260 | 0.4854 | 0.5 |
|
92 |
+
| 0.3789 | 40.0 | 13600 | 0.4971 | 0.5 |
|
93 |
+
| 0.3789 | 41.0 | 13940 | 0.5368 | 0.6803 |
|
94 |
+
| 0.3775 | 42.0 | 14280 | 0.4958 | 0.5047 |
|
95 |
+
| 0.3753 | 43.0 | 14620 | 0.5139 | 0.6897 |
|
96 |
+
| 0.3753 | 44.0 | 14960 | 0.5224 | 0.6834 |
|
97 |
+
| 0.3795 | 45.0 | 15300 | 0.5119 | 0.6865 |
|
98 |
+
| 0.3743 | 46.0 | 15640 | 0.5120 | 0.6740 |
|
99 |
+
| 0.3743 | 47.0 | 15980 | 0.5049 | 0.5204 |
|
100 |
+
| 0.3726 | 48.0 | 16320 | 0.5026 | 0.5 |
|
101 |
+
| 0.3683 | 49.0 | 16660 | 0.5137 | 0.6646 |
|
102 |
+
| 0.3707 | 50.0 | 17000 | 0.5088 | 0.6129 |
|
103 |
+
| 0.3707 | 51.0 | 17340 | 0.5608 | 0.6646 |
|
104 |
+
| 0.3654 | 52.0 | 17680 | 0.5217 | 0.6803 |
|
105 |
+
| 0.3684 | 53.0 | 18020 | 0.5236 | 0.6740 |
|
106 |
+
| 0.3684 | 54.0 | 18360 | 0.5135 | 0.5016 |
|
107 |
+
| 0.3663 | 55.0 | 18700 | 0.5192 | 0.6818 |
|
108 |
+
| 0.3669 | 56.0 | 19040 | 0.5212 | 0.6160 |
|
109 |
+
| 0.3669 | 57.0 | 19380 | 0.5320 | 0.6740 |
|
110 |
+
| 0.3641 | 58.0 | 19720 | 0.5344 | 0.6646 |
|
111 |
+
| 0.3628 | 59.0 | 20060 | 0.4991 | 0.5 |
|
112 |
+
| 0.3628 | 60.0 | 20400 | 0.5341 | 0.6661 |
|
113 |
+
| 0.3612 | 61.0 | 20740 | 0.5039 | 0.5 |
|
114 |
+
| 0.3608 | 62.0 | 21080 | 0.5267 | 0.6379 |
|
115 |
+
| 0.3608 | 63.0 | 21420 | 0.5249 | 0.6364 |
|
116 |
+
| 0.3599 | 64.0 | 21760 | 0.5226 | 0.6599 |
|
117 |
+
| 0.3616 | 65.0 | 22100 | 0.5370 | 0.6834 |
|
118 |
+
| 0.3616 | 66.0 | 22440 | 0.5109 | 0.5 |
|
119 |
+
| 0.3543 | 67.0 | 22780 | 0.5368 | 0.6740 |
|
120 |
+
| 0.3616 | 68.0 | 23120 | 0.5236 | 0.5690 |
|
121 |
+
| 0.3616 | 69.0 | 23460 | 0.5300 | 0.6693 |
|
122 |
+
| 0.3578 | 70.0 | 23800 | 0.5441 | 0.6583 |
|
123 |
+
| 0.3541 | 71.0 | 24140 | 0.5310 | 0.6724 |
|
124 |
+
| 0.3541 | 72.0 | 24480 | 0.5346 | 0.6693 |
|
125 |
+
| 0.354 | 73.0 | 24820 | 0.5338 | 0.6630 |
|
126 |
+
| 0.355 | 74.0 | 25160 | 0.5279 | 0.6599 |
|
127 |
+
| 0.3536 | 75.0 | 25500 | 0.5280 | 0.6552 |
|
128 |
+
| 0.3536 | 76.0 | 25840 | 0.5328 | 0.6693 |
|
129 |
+
| 0.3539 | 77.0 | 26180 | 0.5231 | 0.5376 |
|
130 |
+
| 0.3527 | 78.0 | 26520 | 0.5282 | 0.6646 |
|
131 |
+
| 0.3527 | 79.0 | 26860 | 0.5250 | 0.6364 |
|
132 |
+
| 0.3535 | 80.0 | 27200 | 0.5298 | 0.6771 |
|
133 |
+
|
134 |
+
|
135 |
+
### Framework versions
|
136 |
+
|
137 |
+
- Transformers 4.26.1
|
138 |
+
- Pytorch 2.0.1+cu118
|
139 |
+
- Datasets 2.12.0
|
140 |
+
- Tokenizers 0.13.3
|