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_5e-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 |
+
# 2_5e-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: 0.8743
|
22 |
+
- Accuracy: 0.7407
|
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: 0.005
|
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 |
+
| 2.0951 | 1.0 | 590 | 2.8478 | 0.6208 |
|
54 |
+
| 2.0966 | 2.0 | 1180 | 2.0402 | 0.6208 |
|
55 |
+
| 1.9864 | 3.0 | 1770 | 2.9563 | 0.4196 |
|
56 |
+
| 1.9962 | 4.0 | 2360 | 2.4148 | 0.4905 |
|
57 |
+
| 1.8743 | 5.0 | 2950 | 2.1057 | 0.6217 |
|
58 |
+
| 1.562 | 6.0 | 3540 | 1.6253 | 0.6636 |
|
59 |
+
| 1.4913 | 7.0 | 4130 | 1.4832 | 0.6734 |
|
60 |
+
| 1.4114 | 8.0 | 4720 | 1.4386 | 0.6560 |
|
61 |
+
| 1.3732 | 9.0 | 5310 | 1.4139 | 0.6508 |
|
62 |
+
| 1.3161 | 10.0 | 5900 | 1.3009 | 0.6893 |
|
63 |
+
| 1.2979 | 11.0 | 6490 | 1.2760 | 0.6963 |
|
64 |
+
| 1.1837 | 12.0 | 7080 | 1.2606 | 0.6737 |
|
65 |
+
| 1.2171 | 13.0 | 7670 | 1.2241 | 0.7040 |
|
66 |
+
| 1.1545 | 14.0 | 8260 | 1.2533 | 0.7086 |
|
67 |
+
| 1.1424 | 15.0 | 8850 | 1.1613 | 0.7061 |
|
68 |
+
| 1.1106 | 16.0 | 9440 | 1.1290 | 0.7018 |
|
69 |
+
| 1.0798 | 17.0 | 10030 | 1.1366 | 0.7049 |
|
70 |
+
| 1.0665 | 18.0 | 10620 | 1.1030 | 0.7147 |
|
71 |
+
| 1.0642 | 19.0 | 11210 | 1.1100 | 0.7168 |
|
72 |
+
| 1.0498 | 20.0 | 11800 | 1.1124 | 0.7235 |
|
73 |
+
| 0.9966 | 21.0 | 12390 | 1.1192 | 0.7211 |
|
74 |
+
| 1.0178 | 22.0 | 12980 | 1.0786 | 0.7211 |
|
75 |
+
| 0.9956 | 23.0 | 13570 | 1.0710 | 0.7024 |
|
76 |
+
| 0.9896 | 24.0 | 14160 | 1.0254 | 0.7211 |
|
77 |
+
| 0.9496 | 25.0 | 14750 | 1.0181 | 0.7217 |
|
78 |
+
| 0.9755 | 26.0 | 15340 | 1.0013 | 0.7211 |
|
79 |
+
| 0.9439 | 27.0 | 15930 | 1.0014 | 0.7153 |
|
80 |
+
| 0.9151 | 28.0 | 16520 | 0.9923 | 0.7336 |
|
81 |
+
| 0.8988 | 29.0 | 17110 | 0.9776 | 0.7318 |
|
82 |
+
| 0.8962 | 30.0 | 17700 | 0.9625 | 0.7401 |
|
83 |
+
| 0.8825 | 31.0 | 18290 | 0.9702 | 0.7346 |
|
84 |
+
| 0.8734 | 32.0 | 18880 | 0.9766 | 0.7394 |
|
85 |
+
| 0.8651 | 33.0 | 19470 | 0.9443 | 0.7394 |
|
86 |
+
| 0.8404 | 34.0 | 20060 | 0.9665 | 0.7364 |
|
87 |
+
| 0.8312 | 35.0 | 20650 | 0.9290 | 0.7370 |
|
88 |
+
| 0.8401 | 36.0 | 21240 | 0.9546 | 0.7309 |
|
89 |
+
| 0.8121 | 37.0 | 21830 | 0.9287 | 0.7391 |
|
90 |
+
| 0.8162 | 38.0 | 22420 | 0.9171 | 0.7278 |
|
91 |
+
| 0.8096 | 39.0 | 23010 | 0.9196 | 0.7428 |
|
92 |
+
| 0.7901 | 40.0 | 23600 | 0.9168 | 0.7422 |
|
93 |
+
| 0.8011 | 41.0 | 24190 | 0.9136 | 0.7297 |
|
94 |
+
| 0.7908 | 42.0 | 24780 | 0.9080 | 0.7385 |
|
95 |
+
| 0.7755 | 43.0 | 25370 | 0.9270 | 0.7446 |
|
96 |
+
| 0.786 | 44.0 | 25960 | 0.8954 | 0.7333 |
|
97 |
+
| 0.7664 | 45.0 | 26550 | 0.9038 | 0.7410 |
|
98 |
+
| 0.7725 | 46.0 | 27140 | 0.8874 | 0.7431 |
|
99 |
+
| 0.7607 | 47.0 | 27730 | 0.9019 | 0.7416 |
|
100 |
+
| 0.7683 | 48.0 | 28320 | 0.9069 | 0.7456 |
|
101 |
+
| 0.7594 | 49.0 | 28910 | 0.9003 | 0.7318 |
|
102 |
+
| 0.7317 | 50.0 | 29500 | 0.8860 | 0.7428 |
|
103 |
+
| 0.7306 | 51.0 | 30090 | 0.8862 | 0.7434 |
|
104 |
+
| 0.736 | 52.0 | 30680 | 0.8952 | 0.7471 |
|
105 |
+
| 0.7343 | 53.0 | 31270 | 0.8761 | 0.7419 |
|
106 |
+
| 0.7248 | 54.0 | 31860 | 0.8876 | 0.7309 |
|
107 |
+
| 0.7334 | 55.0 | 32450 | 0.8841 | 0.7431 |
|
108 |
+
| 0.7458 | 56.0 | 33040 | 0.8817 | 0.7434 |
|
109 |
+
| 0.727 | 57.0 | 33630 | 0.8743 | 0.7431 |
|
110 |
+
| 0.7077 | 58.0 | 34220 | 0.8741 | 0.7422 |
|
111 |
+
| 0.7158 | 59.0 | 34810 | 0.8768 | 0.7446 |
|
112 |
+
| 0.7061 | 60.0 | 35400 | 0.8743 | 0.7407 |
|
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
|