🚀 wiki_42
wiki_42 是在未知數據集上對 進行微調後的模型版本。該模型在評估集上取得了一定的效果，例如損失率為 2.1322。
🚀 快速開始
此模型是在未知數據集上對 進行微調後的版本，在評估集上的損失為 2.1322。
🔧 技術細節
訓練超參數
訓練過程中使用了以下超參數：
- 學習率：0.0001
- 訓練批次大小：16
- 評估批次大小：16
- 隨機種子：42
- 梯度累積步數：2
- 總訓練批次大小：32
- 優化器：Adam（β1=0.9，β2=0.999，ε=1e - 08）
- 學習率調度器類型：線性
- 學習率調度器熱身步數：40000
- 訓練步數：100000
訓練結果
| 訓練損失 |
輪數 |
步數 |
驗證損失 |
| 無日誌 |
1.5662 |
2000 |
7.6634 |
| 7.6907 |
3.1323 |
4000 |
6.6436 |
| 7.6907 |
4.6985 |
6000 |
6.5194 |
| 6.5174 |
6.2647 |
8000 |
6.4353 |
| 6.5174 |
7.8309 |
10000 |
6.3850 |
| 6.3619 |
9.3970 |
12000 |
6.3224 |
| 6.3619 |
10.9632 |
14000 |
6.2452 |
| 6.2364 |
12.5294 |
16000 |
6.2350 |
| 6.2364 |
14.0955 |
18000 |
6.1499 |
| 6.1142 |
15.6617 |
20000 |
6.1037 |
| 6.1142 |
17.2279 |
22000 |
5.9377 |
| 5.8469 |
18.7940 |
24000 |
5.4239 |
| 5.8469 |
20.3602 |
26000 |
4.9251 |
| 4.9884 |
21.9264 |
28000 |
4.3860 |
| 4.9884 |
23.4926 |
30000 |
3.9695 |
| 4.0613 |
25.0587 |
32000 |
3.6959 |
| 4.0613 |
26.6249 |
34000 |
3.4763 |
| 3.5095 |
28.1911 |
36000 |
3.3151 |
| 3.5095 |
29.7572 |
38000 |
3.1737 |
| 3.1643 |
31.3234 |
40000 |
3.0445 |
| 3.1643 |
32.8896 |
42000 |
2.9430 |
| 2.9042 |
34.4558 |
44000 |
2.8326 |
| 2.9042 |
36.0219 |
46000 |
2.7730 |
| 2.6997 |
37.5881 |
48000 |
2.7106 |
| 2.6997 |
39.1543 |
50000 |
2.6288 |
| 2.5476 |
40.7204 |
52000 |
2.5801 |
| 2.5476 |
42.2866 |
54000 |
2.5604 |
| 2.4341 |
43.8528 |
56000 |
2.4778 |
| 2.4341 |
45.4190 |
58000 |
2.4722 |
| 2.3354 |
46.9851 |
60000 |
2.4329 |
| 2.3354 |
48.5513 |
62000 |
2.3689 |
| 2.2574 |
50.1175 |
64000 |
2.3834 |
| 2.2574 |
51.6836 |
66000 |
2.3362 |
| 2.1901 |
53.2498 |
68000 |
2.3154 |
| 2.1901 |
54.8160 |
70000 |
2.3113 |
| 2.1297 |
56.3821 |
72000 |
2.2685 |
| 2.1297 |
57.9483 |
74000 |
2.2540 |
| 2.0848 |
59.5145 |
76000 |
2.2351 |
| 2.0848 |
61.0807 |
78000 |
2.2405 |
| 2.0416 |
62.6468 |
80000 |
2.2016 |
| 2.0416 |
64.2130 |
82000 |
2.2054 |
| 2.004 |
65.7792 |
84000 |
2.1990 |
| 2.004 |
67.3453 |
86000 |
2.1745 |
| 1.9701 |
68.9115 |
88000 |
2.1781 |
| 1.9701 |
70.4777 |
90000 |
2.1825 |
| 1.9457 |
72.0439 |
92000 |
2.1373 |
| 1.9457 |
73.6100 |
94000 |
2.1161 |
| 1.9247 |
75.1762 |
96000 |
2.1504 |
| 1.9247 |
76.7424 |
98000 |
2.1297 |
| 1.9142 |
78.3085 |
100000 |
2.1322 |
框架版本
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1
%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)
Transformers 支持多種語言