update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: 1_1e-2_1_0.5
|
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 |
+
# 1_1e-2_1_0.5
|
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: 0.4701
|
22 |
+
- Accuracy: 0.7431
|
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: 0.01
|
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: 100.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 1.2311 | 1.0 | 590 | 1.5093 | 0.6217 |
|
54 |
+
| 1.0444 | 2.0 | 1180 | 0.5788 | 0.6196 |
|
55 |
+
| 0.9287 | 3.0 | 1770 | 1.3468 | 0.6217 |
|
56 |
+
| 0.8066 | 4.0 | 2360 | 0.7094 | 0.6217 |
|
57 |
+
| 0.6756 | 5.0 | 2950 | 0.5829 | 0.6486 |
|
58 |
+
| 0.5869 | 6.0 | 3540 | 0.5398 | 0.6670 |
|
59 |
+
| 0.5733 | 7.0 | 4130 | 0.6279 | 0.5716 |
|
60 |
+
| 0.5229 | 8.0 | 4720 | 0.4543 | 0.7061 |
|
61 |
+
| 0.4998 | 9.0 | 5310 | 0.4906 | 0.6685 |
|
62 |
+
| 0.476 | 10.0 | 5900 | 0.5972 | 0.6927 |
|
63 |
+
| 0.4498 | 11.0 | 6490 | 0.4602 | 0.7049 |
|
64 |
+
| 0.4082 | 12.0 | 7080 | 0.4432 | 0.7012 |
|
65 |
+
| 0.4072 | 13.0 | 7670 | 0.4585 | 0.6963 |
|
66 |
+
| 0.3746 | 14.0 | 8260 | 0.4281 | 0.7312 |
|
67 |
+
| 0.3652 | 15.0 | 8850 | 0.4691 | 0.7294 |
|
68 |
+
| 0.3505 | 16.0 | 9440 | 0.4156 | 0.7303 |
|
69 |
+
| 0.3375 | 17.0 | 10030 | 0.4299 | 0.7275 |
|
70 |
+
| 0.3298 | 18.0 | 10620 | 0.4948 | 0.7 |
|
71 |
+
| 0.3056 | 19.0 | 11210 | 0.4208 | 0.7275 |
|
72 |
+
| 0.2956 | 20.0 | 11800 | 0.4474 | 0.7324 |
|
73 |
+
| 0.2859 | 21.0 | 12390 | 0.5893 | 0.6746 |
|
74 |
+
| 0.2807 | 22.0 | 12980 | 0.4613 | 0.7291 |
|
75 |
+
| 0.2566 | 23.0 | 13570 | 0.4610 | 0.7235 |
|
76 |
+
| 0.249 | 24.0 | 14160 | 0.5434 | 0.7413 |
|
77 |
+
| 0.2391 | 25.0 | 14750 | 0.5110 | 0.7333 |
|
78 |
+
| 0.2421 | 26.0 | 15340 | 0.6915 | 0.6465 |
|
79 |
+
| 0.2556 | 27.0 | 15930 | 0.4759 | 0.7306 |
|
80 |
+
| 0.2271 | 28.0 | 16520 | 0.4690 | 0.7321 |
|
81 |
+
| 0.2295 | 29.0 | 17110 | 0.5012 | 0.7376 |
|
82 |
+
| 0.2283 | 30.0 | 17700 | 0.5150 | 0.7128 |
|
83 |
+
| 0.2054 | 31.0 | 18290 | 0.4737 | 0.7343 |
|
84 |
+
| 0.2157 | 32.0 | 18880 | 0.6032 | 0.7327 |
|
85 |
+
| 0.215 | 33.0 | 19470 | 0.4818 | 0.7297 |
|
86 |
+
| 0.196 | 34.0 | 20060 | 0.4894 | 0.7147 |
|
87 |
+
| 0.2001 | 35.0 | 20650 | 0.5326 | 0.7193 |
|
88 |
+
| 0.1955 | 36.0 | 21240 | 0.4826 | 0.7413 |
|
89 |
+
| 0.1947 | 37.0 | 21830 | 0.4625 | 0.7385 |
|
90 |
+
| 0.1912 | 38.0 | 22420 | 0.4764 | 0.7492 |
|
91 |
+
| 0.1946 | 39.0 | 23010 | 0.5615 | 0.7443 |
|
92 |
+
| 0.1898 | 40.0 | 23600 | 0.4870 | 0.7413 |
|
93 |
+
| 0.1789 | 41.0 | 24190 | 0.5526 | 0.7462 |
|
94 |
+
| 0.1803 | 42.0 | 24780 | 0.5021 | 0.7217 |
|
95 |
+
| 0.1708 | 43.0 | 25370 | 0.4751 | 0.7379 |
|
96 |
+
| 0.1835 | 44.0 | 25960 | 0.4738 | 0.7355 |
|
97 |
+
| 0.1738 | 45.0 | 26550 | 0.4759 | 0.7336 |
|
98 |
+
| 0.1726 | 46.0 | 27140 | 0.4928 | 0.7367 |
|
99 |
+
| 0.1756 | 47.0 | 27730 | 0.5380 | 0.7193 |
|
100 |
+
| 0.1617 | 48.0 | 28320 | 0.5119 | 0.7327 |
|
101 |
+
| 0.1725 | 49.0 | 28910 | 0.4884 | 0.7431 |
|
102 |
+
| 0.1643 | 50.0 | 29500 | 0.4968 | 0.7382 |
|
103 |
+
| 0.1593 | 51.0 | 30090 | 0.4708 | 0.7281 |
|
104 |
+
| 0.1645 | 52.0 | 30680 | 0.4943 | 0.7364 |
|
105 |
+
| 0.1566 | 53.0 | 31270 | 0.4820 | 0.7446 |
|
106 |
+
| 0.1555 | 54.0 | 31860 | 0.5117 | 0.7376 |
|
107 |
+
| 0.1584 | 55.0 | 32450 | 0.5269 | 0.7410 |
|
108 |
+
| 0.1587 | 56.0 | 33040 | 0.4650 | 0.7394 |
|
109 |
+
| 0.1527 | 57.0 | 33630 | 0.5007 | 0.7431 |
|
110 |
+
| 0.157 | 58.0 | 34220 | 0.4689 | 0.7413 |
|
111 |
+
| 0.1527 | 59.0 | 34810 | 0.4960 | 0.7306 |
|
112 |
+
| 0.1461 | 60.0 | 35400 | 0.5033 | 0.7416 |
|
113 |
+
| 0.1506 | 61.0 | 35990 | 0.4817 | 0.7459 |
|
114 |
+
| 0.153 | 62.0 | 36580 | 0.4782 | 0.7422 |
|
115 |
+
| 0.1417 | 63.0 | 37170 | 0.4808 | 0.7410 |
|
116 |
+
| 0.1477 | 64.0 | 37760 | 0.5090 | 0.7358 |
|
117 |
+
| 0.1467 | 65.0 | 38350 | 0.5180 | 0.7419 |
|
118 |
+
| 0.1416 | 66.0 | 38940 | 0.5055 | 0.7483 |
|
119 |
+
| 0.1407 | 67.0 | 39530 | 0.4779 | 0.7416 |
|
120 |
+
| 0.1407 | 68.0 | 40120 | 0.4661 | 0.7401 |
|
121 |
+
| 0.1379 | 69.0 | 40710 | 0.5172 | 0.7450 |
|
122 |
+
| 0.1432 | 70.0 | 41300 | 0.4883 | 0.7422 |
|
123 |
+
| 0.1455 | 71.0 | 41890 | 0.4853 | 0.7382 |
|
124 |
+
| 0.1348 | 72.0 | 42480 | 0.4934 | 0.7465 |
|
125 |
+
| 0.134 | 73.0 | 43070 | 0.4773 | 0.7462 |
|
126 |
+
| 0.1323 | 74.0 | 43660 | 0.5033 | 0.7428 |
|
127 |
+
| 0.1356 | 75.0 | 44250 | 0.5184 | 0.7483 |
|
128 |
+
| 0.1321 | 76.0 | 44840 | 0.4860 | 0.7382 |
|
129 |
+
| 0.1328 | 77.0 | 45430 | 0.4800 | 0.7422 |
|
130 |
+
| 0.1334 | 78.0 | 46020 | 0.4668 | 0.7489 |
|
131 |
+
| 0.128 | 79.0 | 46610 | 0.4930 | 0.7498 |
|
132 |
+
| 0.1315 | 80.0 | 47200 | 0.4808 | 0.7410 |
|
133 |
+
| 0.1236 | 81.0 | 47790 | 0.4718 | 0.7456 |
|
134 |
+
| 0.1286 | 82.0 | 48380 | 0.4723 | 0.7413 |
|
135 |
+
| 0.1264 | 83.0 | 48970 | 0.4987 | 0.7480 |
|
136 |
+
| 0.1273 | 84.0 | 49560 | 0.4582 | 0.7492 |
|
137 |
+
| 0.1243 | 85.0 | 50150 | 0.4713 | 0.7471 |
|
138 |
+
| 0.1286 | 86.0 | 50740 | 0.4913 | 0.7437 |
|
139 |
+
| 0.1186 | 87.0 | 51330 | 0.4953 | 0.7495 |
|
140 |
+
| 0.1194 | 88.0 | 51920 | 0.4805 | 0.7486 |
|
141 |
+
| 0.118 | 89.0 | 52510 | 0.4799 | 0.7474 |
|
142 |
+
| 0.1236 | 90.0 | 53100 | 0.4829 | 0.7471 |
|
143 |
+
| 0.1201 | 91.0 | 53690 | 0.4736 | 0.7474 |
|
144 |
+
| 0.1235 | 92.0 | 54280 | 0.4695 | 0.7431 |
|
145 |
+
| 0.1214 | 93.0 | 54870 | 0.4781 | 0.7446 |
|
146 |
+
| 0.1188 | 94.0 | 55460 | 0.4701 | 0.7456 |
|
147 |
+
| 0.1191 | 95.0 | 56050 | 0.4681 | 0.7456 |
|
148 |
+
| 0.1144 | 96.0 | 56640 | 0.4737 | 0.7453 |
|
149 |
+
| 0.1212 | 97.0 | 57230 | 0.4736 | 0.7446 |
|
150 |
+
| 0.1152 | 98.0 | 57820 | 0.4668 | 0.7410 |
|
151 |
+
| 0.1153 | 99.0 | 58410 | 0.4743 | 0.7437 |
|
152 |
+
| 0.1194 | 100.0 | 59000 | 0.4701 | 0.7431 |
|
153 |
+
|
154 |
+
|
155 |
+
### Framework versions
|
156 |
+
|
157 |
+
- Transformers 4.30.0
|
158 |
+
- Pytorch 2.0.1+cu117
|
159 |
+
- Datasets 2.14.4
|
160 |
+
- Tokenizers 0.13.3
|