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: '20230824064444'
|
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 |
+
# 20230824064444
|
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: 0.0709
|
22 |
+
- Accuracy: 0.7329
|
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 | 0.4733 | 0.5307 |
|
54 |
+
| 0.3538 | 2.0 | 624 | 0.1917 | 0.5126 |
|
55 |
+
| 0.3538 | 3.0 | 936 | 0.1696 | 0.5560 |
|
56 |
+
| 0.2775 | 4.0 | 1248 | 0.1700 | 0.5271 |
|
57 |
+
| 0.2538 | 5.0 | 1560 | 0.3497 | 0.5343 |
|
58 |
+
| 0.2538 | 6.0 | 1872 | 0.2183 | 0.5632 |
|
59 |
+
| 0.259 | 7.0 | 2184 | 0.1783 | 0.5018 |
|
60 |
+
| 0.259 | 8.0 | 2496 | 0.2321 | 0.5848 |
|
61 |
+
| 0.2587 | 9.0 | 2808 | 0.2081 | 0.6101 |
|
62 |
+
| 0.2211 | 10.0 | 3120 | 0.1194 | 0.6715 |
|
63 |
+
| 0.2211 | 11.0 | 3432 | 0.1505 | 0.6390 |
|
64 |
+
| 0.198 | 12.0 | 3744 | 0.1130 | 0.7004 |
|
65 |
+
| 0.1939 | 13.0 | 4056 | 0.1187 | 0.6679 |
|
66 |
+
| 0.1939 | 14.0 | 4368 | 0.1175 | 0.6787 |
|
67 |
+
| 0.1687 | 15.0 | 4680 | 0.1092 | 0.7040 |
|
68 |
+
| 0.1687 | 16.0 | 4992 | 0.0984 | 0.7076 |
|
69 |
+
| 0.1511 | 17.0 | 5304 | 0.1032 | 0.7076 |
|
70 |
+
| 0.1448 | 18.0 | 5616 | 0.1024 | 0.7401 |
|
71 |
+
| 0.1448 | 19.0 | 5928 | 0.0902 | 0.7112 |
|
72 |
+
| 0.1392 | 20.0 | 6240 | 0.0972 | 0.7112 |
|
73 |
+
| 0.1283 | 21.0 | 6552 | 0.0880 | 0.7184 |
|
74 |
+
| 0.1283 | 22.0 | 6864 | 0.0892 | 0.7329 |
|
75 |
+
| 0.1257 | 23.0 | 7176 | 0.1156 | 0.7401 |
|
76 |
+
| 0.1257 | 24.0 | 7488 | 0.0940 | 0.7329 |
|
77 |
+
| 0.1215 | 25.0 | 7800 | 0.0876 | 0.7401 |
|
78 |
+
| 0.1184 | 26.0 | 8112 | 0.1289 | 0.7437 |
|
79 |
+
| 0.1184 | 27.0 | 8424 | 0.0808 | 0.7256 |
|
80 |
+
| 0.1112 | 28.0 | 8736 | 0.0823 | 0.7401 |
|
81 |
+
| 0.1139 | 29.0 | 9048 | 0.0838 | 0.7256 |
|
82 |
+
| 0.1139 | 30.0 | 9360 | 0.0855 | 0.7220 |
|
83 |
+
| 0.1095 | 31.0 | 9672 | 0.0813 | 0.7256 |
|
84 |
+
| 0.1095 | 32.0 | 9984 | 0.0765 | 0.7256 |
|
85 |
+
| 0.106 | 33.0 | 10296 | 0.0847 | 0.7365 |
|
86 |
+
| 0.1034 | 34.0 | 10608 | 0.0844 | 0.7509 |
|
87 |
+
| 0.1034 | 35.0 | 10920 | 0.0811 | 0.7184 |
|
88 |
+
| 0.0991 | 36.0 | 11232 | 0.0811 | 0.7292 |
|
89 |
+
| 0.0938 | 37.0 | 11544 | 0.0847 | 0.7365 |
|
90 |
+
| 0.0938 | 38.0 | 11856 | 0.0824 | 0.7256 |
|
91 |
+
| 0.0973 | 39.0 | 12168 | 0.0760 | 0.7292 |
|
92 |
+
| 0.0973 | 40.0 | 12480 | 0.0786 | 0.7220 |
|
93 |
+
| 0.0908 | 41.0 | 12792 | 0.0732 | 0.7473 |
|
94 |
+
| 0.0894 | 42.0 | 13104 | 0.0763 | 0.7401 |
|
95 |
+
| 0.0894 | 43.0 | 13416 | 0.0811 | 0.7365 |
|
96 |
+
| 0.0896 | 44.0 | 13728 | 0.0734 | 0.7473 |
|
97 |
+
| 0.0882 | 45.0 | 14040 | 0.0747 | 0.7329 |
|
98 |
+
| 0.0882 | 46.0 | 14352 | 0.0729 | 0.7401 |
|
99 |
+
| 0.0847 | 47.0 | 14664 | 0.0723 | 0.7329 |
|
100 |
+
| 0.0847 | 48.0 | 14976 | 0.0748 | 0.7401 |
|
101 |
+
| 0.0854 | 49.0 | 15288 | 0.0755 | 0.7292 |
|
102 |
+
| 0.0813 | 50.0 | 15600 | 0.0715 | 0.7329 |
|
103 |
+
| 0.0813 | 51.0 | 15912 | 0.0719 | 0.7292 |
|
104 |
+
| 0.0845 | 52.0 | 16224 | 0.0721 | 0.7401 |
|
105 |
+
| 0.0821 | 53.0 | 16536 | 0.0711 | 0.7292 |
|
106 |
+
| 0.0821 | 54.0 | 16848 | 0.0714 | 0.7437 |
|
107 |
+
| 0.0802 | 55.0 | 17160 | 0.0711 | 0.7401 |
|
108 |
+
| 0.0802 | 56.0 | 17472 | 0.0718 | 0.7329 |
|
109 |
+
| 0.0798 | 57.0 | 17784 | 0.0708 | 0.7220 |
|
110 |
+
| 0.0796 | 58.0 | 18096 | 0.0715 | 0.7365 |
|
111 |
+
| 0.0796 | 59.0 | 18408 | 0.0712 | 0.7329 |
|
112 |
+
| 0.0806 | 60.0 | 18720 | 0.0709 | 0.7329 |
|
113 |
+
|
114 |
+
|
115 |
+
### Framework versions
|
116 |
+
|
117 |
+
- Transformers 4.26.1
|
118 |
+
- Pytorch 2.0.1+cu118
|
119 |
+
- Datasets 2.12.0
|
120 |
+
- Tokenizers 0.13.3
|