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: '20230817123430'
|
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 |
+
# 20230817123430
|
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: 0.3373
|
22 |
+
- Accuracy: 0.7437
|
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: 0.003
|
42 |
+
- train_batch_size: 8
|
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 |
+
| No log | 1.0 | 312 | 0.3735 | 0.5054 |
|
54 |
+
| 0.5142 | 2.0 | 624 | 0.4848 | 0.5415 |
|
55 |
+
| 0.5142 | 3.0 | 936 | 0.3802 | 0.5379 |
|
56 |
+
| 0.4859 | 4.0 | 1248 | 0.4823 | 0.4729 |
|
57 |
+
| 0.4412 | 5.0 | 1560 | 0.3902 | 0.5379 |
|
58 |
+
| 0.4412 | 6.0 | 1872 | 0.3744 | 0.5596 |
|
59 |
+
| 0.4418 | 7.0 | 2184 | 0.4612 | 0.5487 |
|
60 |
+
| 0.4418 | 8.0 | 2496 | 0.4590 | 0.4729 |
|
61 |
+
| 0.4467 | 9.0 | 2808 | 0.4777 | 0.4729 |
|
62 |
+
| 0.4177 | 10.0 | 3120 | 0.3616 | 0.4838 |
|
63 |
+
| 0.4177 | 11.0 | 3432 | 0.3736 | 0.6245 |
|
64 |
+
| 0.3988 | 12.0 | 3744 | 0.3464 | 0.5993 |
|
65 |
+
| 0.3911 | 13.0 | 4056 | 0.3522 | 0.6282 |
|
66 |
+
| 0.3911 | 14.0 | 4368 | 0.3406 | 0.6859 |
|
67 |
+
| 0.3893 | 15.0 | 4680 | 0.4223 | 0.6570 |
|
68 |
+
| 0.3893 | 16.0 | 4992 | 0.6759 | 0.5415 |
|
69 |
+
| 0.38 | 17.0 | 5304 | 0.3631 | 0.6823 |
|
70 |
+
| 0.3772 | 18.0 | 5616 | 0.3434 | 0.6931 |
|
71 |
+
| 0.3772 | 19.0 | 5928 | 0.3344 | 0.6137 |
|
72 |
+
| 0.3639 | 20.0 | 6240 | 0.3670 | 0.6968 |
|
73 |
+
| 0.336 | 21.0 | 6552 | 0.3483 | 0.6895 |
|
74 |
+
| 0.336 | 22.0 | 6864 | 0.3485 | 0.7148 |
|
75 |
+
| 0.3369 | 23.0 | 7176 | 0.3541 | 0.7184 |
|
76 |
+
| 0.3369 | 24.0 | 7488 | 0.3346 | 0.7112 |
|
77 |
+
| 0.3291 | 25.0 | 7800 | 0.3387 | 0.7365 |
|
78 |
+
| 0.3228 | 26.0 | 8112 | 0.3492 | 0.7220 |
|
79 |
+
| 0.3228 | 27.0 | 8424 | 0.3334 | 0.7040 |
|
80 |
+
| 0.3206 | 28.0 | 8736 | 0.3388 | 0.7401 |
|
81 |
+
| 0.3189 | 29.0 | 9048 | 0.3304 | 0.7365 |
|
82 |
+
| 0.3189 | 30.0 | 9360 | 0.3566 | 0.7292 |
|
83 |
+
| 0.3148 | 31.0 | 9672 | 0.3370 | 0.7329 |
|
84 |
+
| 0.3148 | 32.0 | 9984 | 0.3328 | 0.7292 |
|
85 |
+
| 0.31 | 33.0 | 10296 | 0.3422 | 0.7437 |
|
86 |
+
| 0.306 | 34.0 | 10608 | 0.3339 | 0.7292 |
|
87 |
+
| 0.306 | 35.0 | 10920 | 0.3254 | 0.7292 |
|
88 |
+
| 0.3032 | 36.0 | 11232 | 0.3330 | 0.7473 |
|
89 |
+
| 0.3028 | 37.0 | 11544 | 0.3718 | 0.7184 |
|
90 |
+
| 0.3028 | 38.0 | 11856 | 0.3294 | 0.7473 |
|
91 |
+
| 0.3005 | 39.0 | 12168 | 0.3465 | 0.7329 |
|
92 |
+
| 0.3005 | 40.0 | 12480 | 0.3334 | 0.7292 |
|
93 |
+
| 0.2965 | 41.0 | 12792 | 0.3239 | 0.7256 |
|
94 |
+
| 0.2947 | 42.0 | 13104 | 0.3322 | 0.7329 |
|
95 |
+
| 0.2947 | 43.0 | 13416 | 0.3370 | 0.7401 |
|
96 |
+
| 0.2909 | 44.0 | 13728 | 0.3385 | 0.7473 |
|
97 |
+
| 0.2915 | 45.0 | 14040 | 0.3365 | 0.7329 |
|
98 |
+
| 0.2915 | 46.0 | 14352 | 0.3435 | 0.7365 |
|
99 |
+
| 0.29 | 47.0 | 14664 | 0.3301 | 0.7437 |
|
100 |
+
| 0.29 | 48.0 | 14976 | 0.3443 | 0.7401 |
|
101 |
+
| 0.2872 | 49.0 | 15288 | 0.3393 | 0.7437 |
|
102 |
+
| 0.2838 | 50.0 | 15600 | 0.3291 | 0.7437 |
|
103 |
+
| 0.2838 | 51.0 | 15912 | 0.3356 | 0.7401 |
|
104 |
+
| 0.2865 | 52.0 | 16224 | 0.3307 | 0.7365 |
|
105 |
+
| 0.2823 | 53.0 | 16536 | 0.3413 | 0.7401 |
|
106 |
+
| 0.2823 | 54.0 | 16848 | 0.3353 | 0.7437 |
|
107 |
+
| 0.28 | 55.0 | 17160 | 0.3315 | 0.7365 |
|
108 |
+
| 0.28 | 56.0 | 17472 | 0.3433 | 0.7365 |
|
109 |
+
| 0.2832 | 57.0 | 17784 | 0.3338 | 0.7401 |
|
110 |
+
| 0.2794 | 58.0 | 18096 | 0.3367 | 0.7401 |
|
111 |
+
| 0.2794 | 59.0 | 18408 | 0.3371 | 0.7401 |
|
112 |
+
| 0.2785 | 60.0 | 18720 | 0.3373 | 0.7437 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.30.0
|
118 |
+
- Pytorch 2.0.1
|
119 |
+
- Datasets 2.14.4
|
120 |
+
- Tokenizers 0.13.3
|