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_7e-3_10_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_7e-3_10_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: 0.9382
|
22 |
+
- Accuracy: 0.7557
|
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: 100.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 2.7912 | 1.0 | 590 | 2.5545 | 0.3872 |
|
54 |
+
| 3.233 | 2.0 | 1180 | 2.8480 | 0.6217 |
|
55 |
+
| 2.7249 | 3.0 | 1770 | 2.7584 | 0.4037 |
|
56 |
+
| 2.5026 | 4.0 | 2360 | 1.8755 | 0.6113 |
|
57 |
+
| 2.235 | 5.0 | 2950 | 1.6668 | 0.6661 |
|
58 |
+
| 1.9303 | 6.0 | 3540 | 1.6441 | 0.6346 |
|
59 |
+
| 1.9491 | 7.0 | 4130 | 2.1352 | 0.5789 |
|
60 |
+
| 1.6294 | 8.0 | 4720 | 2.2811 | 0.6572 |
|
61 |
+
| 1.6591 | 9.0 | 5310 | 1.5834 | 0.6896 |
|
62 |
+
| 1.5251 | 10.0 | 5900 | 1.7600 | 0.6716 |
|
63 |
+
| 1.5112 | 11.0 | 6490 | 1.2400 | 0.6905 |
|
64 |
+
| 1.3972 | 12.0 | 7080 | 1.2023 | 0.7165 |
|
65 |
+
| 1.3804 | 13.0 | 7670 | 1.1972 | 0.7009 |
|
66 |
+
| 1.3085 | 14.0 | 8260 | 1.6154 | 0.7101 |
|
67 |
+
| 1.2559 | 15.0 | 8850 | 1.1741 | 0.7 |
|
68 |
+
| 1.2292 | 16.0 | 9440 | 1.1551 | 0.7028 |
|
69 |
+
| 1.1711 | 17.0 | 10030 | 1.9400 | 0.6242 |
|
70 |
+
| 1.1356 | 18.0 | 10620 | 1.1234 | 0.7165 |
|
71 |
+
| 1.0466 | 19.0 | 11210 | 1.0939 | 0.7312 |
|
72 |
+
| 1.1043 | 20.0 | 11800 | 1.2564 | 0.7183 |
|
73 |
+
| 0.9875 | 21.0 | 12390 | 1.1273 | 0.7135 |
|
74 |
+
| 0.9788 | 22.0 | 12980 | 1.0513 | 0.7187 |
|
75 |
+
| 0.9086 | 23.0 | 13570 | 1.0497 | 0.7312 |
|
76 |
+
| 0.9327 | 24.0 | 14160 | 1.1127 | 0.7046 |
|
77 |
+
| 0.8835 | 25.0 | 14750 | 1.3732 | 0.7235 |
|
78 |
+
| 0.8652 | 26.0 | 15340 | 1.6447 | 0.6511 |
|
79 |
+
| 0.843 | 27.0 | 15930 | 1.1686 | 0.7425 |
|
80 |
+
| 0.8072 | 28.0 | 16520 | 1.0110 | 0.7446 |
|
81 |
+
| 0.7735 | 29.0 | 17110 | 1.1610 | 0.7401 |
|
82 |
+
| 0.7717 | 30.0 | 17700 | 0.9851 | 0.7352 |
|
83 |
+
| 0.7746 | 31.0 | 18290 | 1.4960 | 0.7223 |
|
84 |
+
| 0.7439 | 32.0 | 18880 | 0.9772 | 0.7358 |
|
85 |
+
| 0.7534 | 33.0 | 19470 | 1.0034 | 0.7456 |
|
86 |
+
| 0.6874 | 34.0 | 20060 | 0.9894 | 0.7407 |
|
87 |
+
| 0.6877 | 35.0 | 20650 | 1.4460 | 0.6771 |
|
88 |
+
| 0.6816 | 36.0 | 21240 | 1.0221 | 0.7489 |
|
89 |
+
| 0.7158 | 37.0 | 21830 | 1.3579 | 0.7425 |
|
90 |
+
| 0.6694 | 38.0 | 22420 | 1.1472 | 0.7517 |
|
91 |
+
| 0.6586 | 39.0 | 23010 | 1.0499 | 0.7523 |
|
92 |
+
| 0.6418 | 40.0 | 23600 | 1.0344 | 0.7459 |
|
93 |
+
| 0.6366 | 41.0 | 24190 | 1.2582 | 0.7422 |
|
94 |
+
| 0.6289 | 42.0 | 24780 | 0.9833 | 0.7370 |
|
95 |
+
| 0.6065 | 43.0 | 25370 | 1.0209 | 0.7529 |
|
96 |
+
| 0.6053 | 44.0 | 25960 | 1.0147 | 0.7287 |
|
97 |
+
| 0.5958 | 45.0 | 26550 | 0.9454 | 0.7456 |
|
98 |
+
| 0.5637 | 46.0 | 27140 | 0.9789 | 0.7535 |
|
99 |
+
| 0.5818 | 47.0 | 27730 | 1.0014 | 0.7529 |
|
100 |
+
| 0.5743 | 48.0 | 28320 | 0.9380 | 0.7526 |
|
101 |
+
| 0.592 | 49.0 | 28910 | 0.9494 | 0.7385 |
|
102 |
+
| 0.5591 | 50.0 | 29500 | 0.9728 | 0.7523 |
|
103 |
+
| 0.5431 | 51.0 | 30090 | 0.9528 | 0.7502 |
|
104 |
+
| 0.5537 | 52.0 | 30680 | 0.9995 | 0.7410 |
|
105 |
+
| 0.5444 | 53.0 | 31270 | 0.9815 | 0.7538 |
|
106 |
+
| 0.5372 | 54.0 | 31860 | 0.9556 | 0.7517 |
|
107 |
+
| 0.5491 | 55.0 | 32450 | 0.9824 | 0.7459 |
|
108 |
+
| 0.5294 | 56.0 | 33040 | 0.9625 | 0.7391 |
|
109 |
+
| 0.5074 | 57.0 | 33630 | 0.9761 | 0.7538 |
|
110 |
+
| 0.5127 | 58.0 | 34220 | 1.1065 | 0.7587 |
|
111 |
+
| 0.5095 | 59.0 | 34810 | 0.9373 | 0.7434 |
|
112 |
+
| 0.5079 | 60.0 | 35400 | 0.9822 | 0.7532 |
|
113 |
+
| 0.4886 | 61.0 | 35990 | 1.0654 | 0.7627 |
|
114 |
+
| 0.5143 | 62.0 | 36580 | 0.9688 | 0.7520 |
|
115 |
+
| 0.4822 | 63.0 | 37170 | 0.9816 | 0.7373 |
|
116 |
+
| 0.4956 | 64.0 | 37760 | 0.9746 | 0.7477 |
|
117 |
+
| 0.4953 | 65.0 | 38350 | 0.9493 | 0.7544 |
|
118 |
+
| 0.4794 | 66.0 | 38940 | 1.0795 | 0.7532 |
|
119 |
+
| 0.4794 | 67.0 | 39530 | 0.9915 | 0.7575 |
|
120 |
+
| 0.48 | 68.0 | 40120 | 0.9385 | 0.7498 |
|
121 |
+
| 0.4633 | 69.0 | 40710 | 1.0949 | 0.7526 |
|
122 |
+
| 0.4749 | 70.0 | 41300 | 1.0207 | 0.7557 |
|
123 |
+
| 0.4657 | 71.0 | 41890 | 0.9383 | 0.7428 |
|
124 |
+
| 0.465 | 72.0 | 42480 | 1.0948 | 0.7581 |
|
125 |
+
| 0.4558 | 73.0 | 43070 | 0.9506 | 0.7492 |
|
126 |
+
| 0.4516 | 74.0 | 43660 | 1.0518 | 0.7606 |
|
127 |
+
| 0.4577 | 75.0 | 44250 | 1.0124 | 0.7575 |
|
128 |
+
| 0.4642 | 76.0 | 44840 | 0.9293 | 0.7526 |
|
129 |
+
| 0.4497 | 77.0 | 45430 | 0.9862 | 0.7541 |
|
130 |
+
| 0.4614 | 78.0 | 46020 | 0.9403 | 0.7566 |
|
131 |
+
| 0.4442 | 79.0 | 46610 | 0.9599 | 0.7581 |
|
132 |
+
| 0.4483 | 80.0 | 47200 | 0.9766 | 0.7593 |
|
133 |
+
| 0.4223 | 81.0 | 47790 | 0.9297 | 0.7547 |
|
134 |
+
| 0.4416 | 82.0 | 48380 | 0.9614 | 0.7587 |
|
135 |
+
| 0.4279 | 83.0 | 48970 | 0.9403 | 0.7587 |
|
136 |
+
| 0.4159 | 84.0 | 49560 | 1.0827 | 0.7569 |
|
137 |
+
| 0.4319 | 85.0 | 50150 | 0.9250 | 0.7505 |
|
138 |
+
| 0.427 | 86.0 | 50740 | 0.9475 | 0.7517 |
|
139 |
+
| 0.427 | 87.0 | 51330 | 0.9429 | 0.7523 |
|
140 |
+
| 0.4233 | 88.0 | 51920 | 0.9721 | 0.7581 |
|
141 |
+
| 0.4167 | 89.0 | 52510 | 0.9387 | 0.7557 |
|
142 |
+
| 0.4162 | 90.0 | 53100 | 0.9282 | 0.7544 |
|
143 |
+
| 0.4163 | 91.0 | 53690 | 0.9785 | 0.7566 |
|
144 |
+
| 0.4214 | 92.0 | 54280 | 0.9217 | 0.7517 |
|
145 |
+
| 0.4038 | 93.0 | 54870 | 0.9470 | 0.7584 |
|
146 |
+
| 0.4258 | 94.0 | 55460 | 0.9254 | 0.7550 |
|
147 |
+
| 0.4206 | 95.0 | 56050 | 0.9380 | 0.7569 |
|
148 |
+
| 0.4086 | 96.0 | 56640 | 0.9379 | 0.7578 |
|
149 |
+
| 0.3973 | 97.0 | 57230 | 0.9425 | 0.7557 |
|
150 |
+
| 0.3971 | 98.0 | 57820 | 0.9461 | 0.7572 |
|
151 |
+
| 0.3899 | 99.0 | 58410 | 0.9388 | 0.7557 |
|
152 |
+
| 0.4033 | 100.0 | 59000 | 0.9382 | 0.7557 |
|
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
|