🚀 wav2vec2-conformer-rel-pos-large-960h-ft-intent-classification-ori
該模型是基於facebook/wav2vec2-conformer-rel-pos-large-960h-ft在None數據集上進行微調的版本。在評估集上取得了以下結果：
📚 詳細文檔
模型描述
更多信息待補充。
預期用途與限制
更多信息待補充。
訓練和評估數據
更多信息待補充。
訓練過程
訓練超參數
訓練過程中使用了以下超參數：
- 學習率：3e-05
- 訓練批次大小：1
- 評估批次大小：1
- 隨機種子：42
- 梯度累積步數：4
- 總訓練批次大小：4
- 優化器：Adam（β1=0.9，β2=0.999，ε=1e-08）
- 學習率調度器類型：線性
- 學習率調度器熱身比例：0.1
- 訓練輪數：45
訓練結果
| 訓練損失 |
輪數 |
步數 |
驗證損失 |
準確率 |
| 2.2018 |
1.0 |
28 |
2.1963 |
0.125 |
| 2.1871 |
2.0 |
56 |
2.1715 |
0.3333 |
| 2.1499 |
3.0 |
84 |
2.1349 |
0.3333 |
| 2.1236 |
4.0 |
112 |
2.0749 |
0.3333 |
| 2.0814 |
5.0 |
140 |
2.0232 |
0.3333 |
| 2.0905 |
6.0 |
168 |
1.9028 |
0.375 |
| 1.9167 |
7.0 |
196 |
1.8469 |
0.3958 |
| 1.7048 |
8.0 |
224 |
1.6481 |
0.4583 |
| 1.4723 |
9.0 |
252 |
1.5350 |
0.4583 |
| 1.5265 |
10.0 |
280 |
1.4526 |
0.5 |
| 1.2621 |
11.0 |
308 |
1.4451 |
0.4583 |
| 1.5083 |
12.0 |
336 |
1.3296 |
0.4792 |
| 1.1857 |
13.0 |
364 |
1.2983 |
0.4792 |
| 1.3449 |
14.0 |
392 |
1.3026 |
0.4792 |
| 1.2061 |
15.0 |
420 |
1.3181 |
0.4792 |
| 1.2544 |
16.0 |
448 |
1.2603 |
0.4792 |
| 1.0731 |
17.0 |
476 |
1.2607 |
0.4792 |
| 0.8836 |
18.0 |
504 |
1.2644 |
0.4792 |
| 1.0917 |
19.0 |
532 |
1.2345 |
0.4792 |
| 1.0786 |
20.0 |
560 |
1.2791 |
0.4792 |
| 1.1616 |
21.0 |
588 |
1.2238 |
0.4792 |
| 1.0614 |
22.0 |
616 |
1.2305 |
0.4583 |
| 0.9617 |
23.0 |
644 |
1.2315 |
0.4792 |
| 0.9652 |
24.0 |
672 |
1.2931 |
0.4792 |
| 0.9042 |
25.0 |
700 |
1.1246 |
0.5 |
| 1.0865 |
26.0 |
728 |
1.1490 |
0.4792 |
| 0.9653 |
27.0 |
756 |
1.1713 |
0.5 |
| 0.858 |
28.0 |
784 |
1.1726 |
0.5208 |
| 0.8364 |
29.0 |
812 |
1.2142 |
0.5 |
| 0.6798 |
30.0 |
840 |
1.2163 |
0.5208 |
| 0.9284 |
31.0 |
868 |
1.1398 |
0.4792 |
| 0.7383 |
32.0 |
896 |
1.2418 |
0.5208 |
| 0.651 |
33.0 |
924 |
1.1734 |
0.5 |
| 0.7416 |
34.0 |
952 |
1.2285 |
0.5 |
| 0.6287 |
35.0 |
980 |
1.1467 |
0.5833 |
| 0.6806 |
36.0 |
1008 |
1.1589 |
0.5625 |
| 0.6148 |
37.0 |
1036 |
1.1373 |
0.5833 |
| 0.7174 |
38.0 |
1064 |
1.2118 |
0.5625 |
| 0.6056 |
39.0 |
1092 |
1.2205 |
0.5833 |
| 0.7041 |
40.0 |
1120 |
1.2408 |
0.5833 |
| 0.631 |
41.0 |
1148 |
1.2350 |
0.5833 |
| 0.6028 |
42.0 |
1176 |
1.2787 |
0.5833 |
| 0.5942 |
43.0 |
1204 |
1.2463 |
0.5833 |
| 0.5441 |
44.0 |
1232 |
1.2496 |
0.5833 |
| 0.5042 |
45.0 |
1260 |
1.2518 |
0.5833 |
框架版本
- Transformers 4.20.1
- Pytorch 1.11.0
- Datasets 2.1.0
- Tokenizers 0.12.1
📄 許可證
該模型採用Apache-2.0許可證。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
PyTorch
Transformers 支持多種語言