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_1_0.9
|
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_1_0.9
|
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: 0.2534
|
22 |
+
- Accuracy: 0.7483
|
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 |
+
| 0.959 | 1.0 | 590 | 0.8539 | 0.6217 |
|
54 |
+
| 0.7269 | 2.0 | 1180 | 0.5087 | 0.6211 |
|
55 |
+
| 0.7153 | 3.0 | 1770 | 0.6070 | 0.4086 |
|
56 |
+
| 0.6861 | 4.0 | 2360 | 0.7139 | 0.6217 |
|
57 |
+
| 0.6453 | 5.0 | 2950 | 0.4409 | 0.6584 |
|
58 |
+
| 0.5962 | 6.0 | 3540 | 0.4496 | 0.5887 |
|
59 |
+
| 0.5361 | 7.0 | 4130 | 0.5527 | 0.5122 |
|
60 |
+
| 0.5468 | 8.0 | 4720 | 0.3969 | 0.6850 |
|
61 |
+
| 0.4902 | 9.0 | 5310 | 0.3556 | 0.6878 |
|
62 |
+
| 0.4794 | 10.0 | 5900 | 0.4762 | 0.6657 |
|
63 |
+
| 0.4719 | 11.0 | 6490 | 0.3936 | 0.6450 |
|
64 |
+
| 0.4317 | 12.0 | 7080 | 0.3662 | 0.7037 |
|
65 |
+
| 0.4179 | 13.0 | 7670 | 0.3144 | 0.6884 |
|
66 |
+
| 0.3817 | 14.0 | 8260 | 0.3086 | 0.7061 |
|
67 |
+
| 0.3867 | 15.0 | 8850 | 0.3868 | 0.7131 |
|
68 |
+
| 0.3573 | 16.0 | 9440 | 0.3145 | 0.7156 |
|
69 |
+
| 0.3413 | 17.0 | 10030 | 0.3493 | 0.6667 |
|
70 |
+
| 0.3458 | 18.0 | 10620 | 0.3274 | 0.6758 |
|
71 |
+
| 0.3212 | 19.0 | 11210 | 0.2809 | 0.7211 |
|
72 |
+
| 0.3182 | 20.0 | 11800 | 0.3024 | 0.7294 |
|
73 |
+
| 0.2971 | 21.0 | 12390 | 0.2963 | 0.6991 |
|
74 |
+
| 0.297 | 22.0 | 12980 | 0.2757 | 0.7089 |
|
75 |
+
| 0.276 | 23.0 | 13570 | 0.2705 | 0.7245 |
|
76 |
+
| 0.2741 | 24.0 | 14160 | 0.2971 | 0.6924 |
|
77 |
+
| 0.2651 | 25.0 | 14750 | 0.3400 | 0.7327 |
|
78 |
+
| 0.2635 | 26.0 | 15340 | 0.3080 | 0.6859 |
|
79 |
+
| 0.2578 | 27.0 | 15930 | 0.2861 | 0.7083 |
|
80 |
+
| 0.2479 | 28.0 | 16520 | 0.2751 | 0.7398 |
|
81 |
+
| 0.2466 | 29.0 | 17110 | 0.2798 | 0.7385 |
|
82 |
+
| 0.2461 | 30.0 | 17700 | 0.2627 | 0.7266 |
|
83 |
+
| 0.2355 | 31.0 | 18290 | 0.3146 | 0.7309 |
|
84 |
+
| 0.2315 | 32.0 | 18880 | 0.4802 | 0.7159 |
|
85 |
+
| 0.2258 | 33.0 | 19470 | 0.2626 | 0.7327 |
|
86 |
+
| 0.2192 | 34.0 | 20060 | 0.2806 | 0.7385 |
|
87 |
+
| 0.2217 | 35.0 | 20650 | 0.2837 | 0.7040 |
|
88 |
+
| 0.2126 | 36.0 | 21240 | 0.2950 | 0.7434 |
|
89 |
+
| 0.21 | 37.0 | 21830 | 0.3081 | 0.7419 |
|
90 |
+
| 0.2086 | 38.0 | 22420 | 0.2490 | 0.7343 |
|
91 |
+
| 0.2071 | 39.0 | 23010 | 0.2674 | 0.7437 |
|
92 |
+
| 0.2052 | 40.0 | 23600 | 0.3063 | 0.7413 |
|
93 |
+
| 0.2027 | 41.0 | 24190 | 0.2926 | 0.7410 |
|
94 |
+
| 0.2035 | 42.0 | 24780 | 0.2712 | 0.7398 |
|
95 |
+
| 0.1945 | 43.0 | 25370 | 0.2639 | 0.7367 |
|
96 |
+
| 0.1988 | 44.0 | 25960 | 0.2570 | 0.7370 |
|
97 |
+
| 0.1909 | 45.0 | 26550 | 0.2635 | 0.7361 |
|
98 |
+
| 0.1891 | 46.0 | 27140 | 0.2565 | 0.7358 |
|
99 |
+
| 0.1878 | 47.0 | 27730 | 0.2588 | 0.7367 |
|
100 |
+
| 0.1861 | 48.0 | 28320 | 0.2511 | 0.7294 |
|
101 |
+
| 0.1932 | 49.0 | 28910 | 0.2632 | 0.7422 |
|
102 |
+
| 0.1835 | 50.0 | 29500 | 0.2599 | 0.7398 |
|
103 |
+
| 0.1803 | 51.0 | 30090 | 0.2641 | 0.7379 |
|
104 |
+
| 0.1808 | 52.0 | 30680 | 0.2586 | 0.7355 |
|
105 |
+
| 0.174 | 53.0 | 31270 | 0.2502 | 0.7394 |
|
106 |
+
| 0.1774 | 54.0 | 31860 | 0.2650 | 0.7361 |
|
107 |
+
| 0.1804 | 55.0 | 32450 | 0.2486 | 0.7330 |
|
108 |
+
| 0.1814 | 56.0 | 33040 | 0.2919 | 0.7422 |
|
109 |
+
| 0.1679 | 57.0 | 33630 | 0.2837 | 0.7398 |
|
110 |
+
| 0.1665 | 58.0 | 34220 | 0.2751 | 0.7391 |
|
111 |
+
| 0.1732 | 59.0 | 34810 | 0.2575 | 0.7315 |
|
112 |
+
| 0.1666 | 60.0 | 35400 | 0.2518 | 0.7349 |
|
113 |
+
| 0.1667 | 61.0 | 35990 | 0.2582 | 0.7407 |
|
114 |
+
| 0.172 | 62.0 | 36580 | 0.2512 | 0.7373 |
|
115 |
+
| 0.1657 | 63.0 | 37170 | 0.2500 | 0.7364 |
|
116 |
+
| 0.1687 | 64.0 | 37760 | 0.2589 | 0.7419 |
|
117 |
+
| 0.1605 | 65.0 | 38350 | 0.2833 | 0.7434 |
|
118 |
+
| 0.1635 | 66.0 | 38940 | 0.2536 | 0.7343 |
|
119 |
+
| 0.1583 | 67.0 | 39530 | 0.2554 | 0.7416 |
|
120 |
+
| 0.1638 | 68.0 | 40120 | 0.2598 | 0.7462 |
|
121 |
+
| 0.1615 | 69.0 | 40710 | 0.3022 | 0.7407 |
|
122 |
+
| 0.16 | 70.0 | 41300 | 0.2653 | 0.7459 |
|
123 |
+
| 0.1601 | 71.0 | 41890 | 0.2593 | 0.7456 |
|
124 |
+
| 0.1567 | 72.0 | 42480 | 0.2564 | 0.7446 |
|
125 |
+
| 0.1503 | 73.0 | 43070 | 0.2788 | 0.7465 |
|
126 |
+
| 0.1531 | 74.0 | 43660 | 0.2518 | 0.7446 |
|
127 |
+
| 0.1536 | 75.0 | 44250 | 0.3032 | 0.7440 |
|
128 |
+
| 0.1549 | 76.0 | 44840 | 0.2513 | 0.7370 |
|
129 |
+
| 0.1543 | 77.0 | 45430 | 0.2647 | 0.7486 |
|
130 |
+
| 0.1516 | 78.0 | 46020 | 0.2511 | 0.7471 |
|
131 |
+
| 0.1512 | 79.0 | 46610 | 0.2562 | 0.7431 |
|
132 |
+
| 0.1493 | 80.0 | 47200 | 0.2568 | 0.7474 |
|
133 |
+
| 0.1443 | 81.0 | 47790 | 0.2650 | 0.7492 |
|
134 |
+
| 0.1487 | 82.0 | 48380 | 0.2488 | 0.7492 |
|
135 |
+
| 0.1453 | 83.0 | 48970 | 0.2444 | 0.7431 |
|
136 |
+
| 0.1465 | 84.0 | 49560 | 0.2665 | 0.7443 |
|
137 |
+
| 0.1444 | 85.0 | 50150 | 0.2531 | 0.7456 |
|
138 |
+
| 0.1487 | 86.0 | 50740 | 0.2475 | 0.7431 |
|
139 |
+
| 0.1425 | 87.0 | 51330 | 0.2774 | 0.7453 |
|
140 |
+
| 0.145 | 88.0 | 51920 | 0.2636 | 0.7465 |
|
141 |
+
| 0.1399 | 89.0 | 52510 | 0.2552 | 0.7459 |
|
142 |
+
| 0.1429 | 90.0 | 53100 | 0.2611 | 0.7443 |
|
143 |
+
| 0.1453 | 91.0 | 53690 | 0.2558 | 0.7468 |
|
144 |
+
| 0.1473 | 92.0 | 54280 | 0.2467 | 0.7413 |
|
145 |
+
| 0.1433 | 93.0 | 54870 | 0.2712 | 0.7474 |
|
146 |
+
| 0.1445 | 94.0 | 55460 | 0.2591 | 0.7465 |
|
147 |
+
| 0.1432 | 95.0 | 56050 | 0.2604 | 0.7486 |
|
148 |
+
| 0.1397 | 96.0 | 56640 | 0.2618 | 0.7492 |
|
149 |
+
| 0.1412 | 97.0 | 57230 | 0.2550 | 0.7483 |
|
150 |
+
| 0.1327 | 98.0 | 57820 | 0.2512 | 0.7471 |
|
151 |
+
| 0.136 | 99.0 | 58410 | 0.2525 | 0.7489 |
|
152 |
+
| 0.145 | 100.0 | 59000 | 0.2534 | 0.7483 |
|
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
|