update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 2_7e-3_1_0.1
|
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 |
+
# 2_7e-3_1_0.1
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [bert-large-uncased](https://huggingface.co/bert-large-uncased) on the super_glue dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6157
|
22 |
+
- Accuracy: 0.7196
|
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: 0.007
|
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: 60.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 1.0957 | 1.0 | 590 | 1.6286 | 0.6214 |
|
54 |
+
| 1.1171 | 2.0 | 1180 | 0.6747 | 0.6217 |
|
55 |
+
| 0.8947 | 3.0 | 1770 | 2.3203 | 0.3786 |
|
56 |
+
| 0.9598 | 4.0 | 2360 | 0.9842 | 0.6217 |
|
57 |
+
| 0.9065 | 5.0 | 2950 | 0.7703 | 0.3933 |
|
58 |
+
| 0.9278 | 6.0 | 3540 | 0.6835 | 0.6217 |
|
59 |
+
| 0.8667 | 7.0 | 4130 | 1.2649 | 0.3783 |
|
60 |
+
| 0.9028 | 8.0 | 4720 | 0.8041 | 0.4847 |
|
61 |
+
| 0.8376 | 9.0 | 5310 | 0.6376 | 0.6382 |
|
62 |
+
| 0.8633 | 10.0 | 5900 | 0.8873 | 0.6346 |
|
63 |
+
| 0.8114 | 11.0 | 6490 | 0.6563 | 0.6517 |
|
64 |
+
| 0.7774 | 12.0 | 7080 | 0.6721 | 0.5927 |
|
65 |
+
| 0.7993 | 13.0 | 7670 | 0.7169 | 0.5593 |
|
66 |
+
| 0.783 | 14.0 | 8260 | 0.8230 | 0.6217 |
|
67 |
+
| 0.7426 | 15.0 | 8850 | 0.8903 | 0.6471 |
|
68 |
+
| 0.7765 | 16.0 | 9440 | 0.6656 | 0.5972 |
|
69 |
+
| 0.7135 | 17.0 | 10030 | 0.6012 | 0.6835 |
|
70 |
+
| 0.7211 | 18.0 | 10620 | 0.7250 | 0.6263 |
|
71 |
+
| 0.6977 | 19.0 | 11210 | 0.6059 | 0.6942 |
|
72 |
+
| 0.7171 | 20.0 | 11800 | 0.6088 | 0.6746 |
|
73 |
+
| 0.6492 | 21.0 | 12390 | 0.6587 | 0.6529 |
|
74 |
+
| 0.6865 | 22.0 | 12980 | 0.7926 | 0.6306 |
|
75 |
+
| 0.6446 | 23.0 | 13570 | 0.7486 | 0.6373 |
|
76 |
+
| 0.6424 | 24.0 | 14160 | 0.5743 | 0.6920 |
|
77 |
+
| 0.6075 | 25.0 | 14750 | 0.6606 | 0.7116 |
|
78 |
+
| 0.5918 | 26.0 | 15340 | 0.9846 | 0.5734 |
|
79 |
+
| 0.6047 | 27.0 | 15930 | 0.7312 | 0.6327 |
|
80 |
+
| 0.5819 | 28.0 | 16520 | 0.6141 | 0.7131 |
|
81 |
+
| 0.5636 | 29.0 | 17110 | 0.6814 | 0.7061 |
|
82 |
+
| 0.5673 | 30.0 | 17700 | 0.6304 | 0.7208 |
|
83 |
+
| 0.5631 | 31.0 | 18290 | 0.5952 | 0.6994 |
|
84 |
+
| 0.5297 | 32.0 | 18880 | 0.6358 | 0.7055 |
|
85 |
+
| 0.5253 | 33.0 | 19470 | 0.6810 | 0.6801 |
|
86 |
+
| 0.5226 | 34.0 | 20060 | 0.6240 | 0.7196 |
|
87 |
+
| 0.5117 | 35.0 | 20650 | 0.6342 | 0.6966 |
|
88 |
+
| 0.5066 | 36.0 | 21240 | 0.5623 | 0.7177 |
|
89 |
+
| 0.4968 | 37.0 | 21830 | 0.5724 | 0.7153 |
|
90 |
+
| 0.4829 | 38.0 | 22420 | 0.6402 | 0.7257 |
|
91 |
+
| 0.4892 | 39.0 | 23010 | 0.6528 | 0.7266 |
|
92 |
+
| 0.4782 | 40.0 | 23600 | 0.9618 | 0.7003 |
|
93 |
+
| 0.4845 | 41.0 | 24190 | 0.7193 | 0.7205 |
|
94 |
+
| 0.4742 | 42.0 | 24780 | 0.6461 | 0.7089 |
|
95 |
+
| 0.4564 | 43.0 | 25370 | 0.5987 | 0.7260 |
|
96 |
+
| 0.4592 | 44.0 | 25960 | 0.6792 | 0.7031 |
|
97 |
+
| 0.4402 | 45.0 | 26550 | 0.6405 | 0.7187 |
|
98 |
+
| 0.4314 | 46.0 | 27140 | 0.6285 | 0.7193 |
|
99 |
+
| 0.4351 | 47.0 | 27730 | 0.6312 | 0.7217 |
|
100 |
+
| 0.4366 | 48.0 | 28320 | 0.6445 | 0.7177 |
|
101 |
+
| 0.4315 | 49.0 | 28910 | 0.5979 | 0.7281 |
|
102 |
+
| 0.4207 | 50.0 | 29500 | 0.6114 | 0.7232 |
|
103 |
+
| 0.4099 | 51.0 | 30090 | 0.6984 | 0.7083 |
|
104 |
+
| 0.4018 | 52.0 | 30680 | 0.6533 | 0.7125 |
|
105 |
+
| 0.3998 | 53.0 | 31270 | 0.6237 | 0.7174 |
|
106 |
+
| 0.3978 | 54.0 | 31860 | 0.6144 | 0.7214 |
|
107 |
+
| 0.3975 | 55.0 | 32450 | 0.6166 | 0.7245 |
|
108 |
+
| 0.396 | 56.0 | 33040 | 0.6707 | 0.7138 |
|
109 |
+
| 0.3958 | 57.0 | 33630 | 0.6091 | 0.7187 |
|
110 |
+
| 0.3901 | 58.0 | 34220 | 0.6157 | 0.7202 |
|
111 |
+
| 0.3816 | 59.0 | 34810 | 0.6077 | 0.7239 |
|
112 |
+
| 0.3754 | 60.0 | 35400 | 0.6157 | 0.7196 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.30.0
|
118 |
+
- Pytorch 2.0.1+cu117
|
119 |
+
- Datasets 2.14.4
|
120 |
+
- Tokenizers 0.13.3
|