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_5e-3_5_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_5e-3_5_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: 0.9516
|
22 |
+
- Accuracy: 0.7450
|
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: 100.0
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
52 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
53 |
+
| 2.4372 | 1.0 | 590 | 1.8593 | 0.6177 |
|
54 |
+
| 2.3953 | 2.0 | 1180 | 3.6910 | 0.3786 |
|
55 |
+
| 2.3694 | 3.0 | 1770 | 2.1033 | 0.4694 |
|
56 |
+
| 2.0494 | 4.0 | 2360 | 1.7694 | 0.6006 |
|
57 |
+
| 2.034 | 5.0 | 2950 | 1.7949 | 0.6355 |
|
58 |
+
| 1.8146 | 6.0 | 3540 | 1.7374 | 0.6159 |
|
59 |
+
| 1.896 | 7.0 | 4130 | 1.8850 | 0.5624 |
|
60 |
+
| 1.7794 | 8.0 | 4720 | 2.8405 | 0.6245 |
|
61 |
+
| 1.8298 | 9.0 | 5310 | 2.6985 | 0.4349 |
|
62 |
+
| 1.7892 | 10.0 | 5900 | 2.2049 | 0.6352 |
|
63 |
+
| 1.6916 | 11.0 | 6490 | 1.6606 | 0.6272 |
|
64 |
+
| 1.6384 | 12.0 | 7080 | 1.5955 | 0.6394 |
|
65 |
+
| 1.6382 | 13.0 | 7670 | 1.6722 | 0.6596 |
|
66 |
+
| 1.6078 | 14.0 | 8260 | 1.4874 | 0.6587 |
|
67 |
+
| 1.5373 | 15.0 | 8850 | 1.4382 | 0.6642 |
|
68 |
+
| 1.4655 | 16.0 | 9440 | 1.4120 | 0.6700 |
|
69 |
+
| 1.4354 | 17.0 | 10030 | 2.0067 | 0.6532 |
|
70 |
+
| 1.4021 | 18.0 | 10620 | 1.7860 | 0.5875 |
|
71 |
+
| 1.3537 | 19.0 | 11210 | 1.4043 | 0.6853 |
|
72 |
+
| 1.3638 | 20.0 | 11800 | 1.3726 | 0.6875 |
|
73 |
+
| 1.3061 | 21.0 | 12390 | 1.3332 | 0.6740 |
|
74 |
+
| 1.3052 | 22.0 | 12980 | 1.2831 | 0.6939 |
|
75 |
+
| 1.4056 | 23.0 | 13570 | 1.4235 | 0.6835 |
|
76 |
+
| 1.3389 | 24.0 | 14160 | 1.5395 | 0.6817 |
|
77 |
+
| 1.2294 | 25.0 | 14750 | 1.2364 | 0.6994 |
|
78 |
+
| 1.2213 | 26.0 | 15340 | 1.1806 | 0.7012 |
|
79 |
+
| 1.203 | 27.0 | 15930 | 1.3771 | 0.6538 |
|
80 |
+
| 1.1667 | 28.0 | 16520 | 1.3193 | 0.6820 |
|
81 |
+
| 1.1516 | 29.0 | 17110 | 1.3490 | 0.6621 |
|
82 |
+
| 1.1657 | 30.0 | 17700 | 1.1866 | 0.7015 |
|
83 |
+
| 1.1212 | 31.0 | 18290 | 1.2403 | 0.6991 |
|
84 |
+
| 1.0632 | 32.0 | 18880 | 1.1608 | 0.7138 |
|
85 |
+
| 1.0702 | 33.0 | 19470 | 1.3606 | 0.6642 |
|
86 |
+
| 1.0609 | 34.0 | 20060 | 1.1448 | 0.6972 |
|
87 |
+
| 1.0407 | 35.0 | 20650 | 1.2761 | 0.6838 |
|
88 |
+
| 1.0151 | 36.0 | 21240 | 2.0245 | 0.6862 |
|
89 |
+
| 1.0246 | 37.0 | 21830 | 1.0999 | 0.7012 |
|
90 |
+
| 0.9971 | 38.0 | 22420 | 1.1661 | 0.6997 |
|
91 |
+
| 0.9732 | 39.0 | 23010 | 1.1978 | 0.7187 |
|
92 |
+
| 0.9642 | 40.0 | 23600 | 1.0760 | 0.7245 |
|
93 |
+
| 0.9628 | 41.0 | 24190 | 1.2119 | 0.7223 |
|
94 |
+
| 0.9605 | 42.0 | 24780 | 1.0589 | 0.7245 |
|
95 |
+
| 0.9297 | 43.0 | 25370 | 1.0496 | 0.7297 |
|
96 |
+
| 0.9282 | 44.0 | 25960 | 1.0384 | 0.7324 |
|
97 |
+
| 0.8927 | 45.0 | 26550 | 1.0954 | 0.7284 |
|
98 |
+
| 0.8753 | 46.0 | 27140 | 1.0344 | 0.7343 |
|
99 |
+
| 0.8787 | 47.0 | 27730 | 1.0238 | 0.7162 |
|
100 |
+
| 0.8397 | 48.0 | 28320 | 1.0650 | 0.7162 |
|
101 |
+
| 0.9109 | 49.0 | 28910 | 1.0901 | 0.7297 |
|
102 |
+
| 0.8609 | 50.0 | 29500 | 1.0152 | 0.7300 |
|
103 |
+
| 0.823 | 51.0 | 30090 | 1.1109 | 0.7128 |
|
104 |
+
| 0.8029 | 52.0 | 30680 | 1.0899 | 0.7113 |
|
105 |
+
| 0.8142 | 53.0 | 31270 | 1.0185 | 0.7339 |
|
106 |
+
| 0.7967 | 54.0 | 31860 | 0.9917 | 0.7336 |
|
107 |
+
| 0.7919 | 55.0 | 32450 | 1.0096 | 0.7352 |
|
108 |
+
| 0.7883 | 56.0 | 33040 | 1.0033 | 0.7355 |
|
109 |
+
| 0.7794 | 57.0 | 33630 | 1.0478 | 0.7336 |
|
110 |
+
| 0.7444 | 58.0 | 34220 | 1.0485 | 0.7284 |
|
111 |
+
| 0.7646 | 59.0 | 34810 | 1.0046 | 0.7242 |
|
112 |
+
| 0.7493 | 60.0 | 35400 | 0.9997 | 0.7300 |
|
113 |
+
| 0.7126 | 61.0 | 35990 | 0.9838 | 0.7398 |
|
114 |
+
| 0.7303 | 62.0 | 36580 | 0.9983 | 0.7300 |
|
115 |
+
| 0.7184 | 63.0 | 37170 | 1.1151 | 0.7156 |
|
116 |
+
| 0.711 | 64.0 | 37760 | 1.0758 | 0.7220 |
|
117 |
+
| 0.6963 | 65.0 | 38350 | 0.9884 | 0.7281 |
|
118 |
+
| 0.6972 | 66.0 | 38940 | 0.9688 | 0.7336 |
|
119 |
+
| 0.6927 | 67.0 | 39530 | 0.9794 | 0.7339 |
|
120 |
+
| 0.6923 | 68.0 | 40120 | 0.9681 | 0.7379 |
|
121 |
+
| 0.6829 | 69.0 | 40710 | 1.0167 | 0.7440 |
|
122 |
+
| 0.6705 | 70.0 | 41300 | 0.9709 | 0.7358 |
|
123 |
+
| 0.6717 | 71.0 | 41890 | 1.0276 | 0.7226 |
|
124 |
+
| 0.6683 | 72.0 | 42480 | 0.9858 | 0.7324 |
|
125 |
+
| 0.6405 | 73.0 | 43070 | 0.9954 | 0.7336 |
|
126 |
+
| 0.6423 | 74.0 | 43660 | 0.9730 | 0.7339 |
|
127 |
+
| 0.6628 | 75.0 | 44250 | 1.0100 | 0.7388 |
|
128 |
+
| 0.6528 | 76.0 | 44840 | 0.9663 | 0.7398 |
|
129 |
+
| 0.6327 | 77.0 | 45430 | 0.9619 | 0.7358 |
|
130 |
+
| 0.6434 | 78.0 | 46020 | 0.9671 | 0.7361 |
|
131 |
+
| 0.6261 | 79.0 | 46610 | 0.9778 | 0.7248 |
|
132 |
+
| 0.6312 | 80.0 | 47200 | 0.9802 | 0.7343 |
|
133 |
+
| 0.6098 | 81.0 | 47790 | 0.9736 | 0.7431 |
|
134 |
+
| 0.6221 | 82.0 | 48380 | 0.9820 | 0.7330 |
|
135 |
+
| 0.6166 | 83.0 | 48970 | 0.9587 | 0.7431 |
|
136 |
+
| 0.6072 | 84.0 | 49560 | 0.9671 | 0.7370 |
|
137 |
+
| 0.5986 | 85.0 | 50150 | 0.9629 | 0.7385 |
|
138 |
+
| 0.5959 | 86.0 | 50740 | 0.9576 | 0.7407 |
|
139 |
+
| 0.5858 | 87.0 | 51330 | 0.9793 | 0.7428 |
|
140 |
+
| 0.5846 | 88.0 | 51920 | 0.9722 | 0.7404 |
|
141 |
+
| 0.5879 | 89.0 | 52510 | 0.9822 | 0.7394 |
|
142 |
+
| 0.582 | 90.0 | 53100 | 0.9625 | 0.7422 |
|
143 |
+
| 0.5805 | 91.0 | 53690 | 0.9856 | 0.7443 |
|
144 |
+
| 0.5767 | 92.0 | 54280 | 0.9560 | 0.7404 |
|
145 |
+
| 0.5711 | 93.0 | 54870 | 0.9629 | 0.7440 |
|
146 |
+
| 0.5769 | 94.0 | 55460 | 0.9560 | 0.7431 |
|
147 |
+
| 0.557 | 95.0 | 56050 | 0.9562 | 0.7434 |
|
148 |
+
| 0.5706 | 96.0 | 56640 | 0.9565 | 0.7440 |
|
149 |
+
| 0.5691 | 97.0 | 57230 | 0.9515 | 0.7425 |
|
150 |
+
| 0.5496 | 98.0 | 57820 | 0.9570 | 0.7410 |
|
151 |
+
| 0.5643 | 99.0 | 58410 | 0.9512 | 0.7434 |
|
152 |
+
| 0.5539 | 100.0 | 59000 | 0.9516 | 0.7450 |
|
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
|