🚀 wiki_13
このモデルは、 を未知のデータセットでファインチューニングしたバージョンです。評価セットでは以下の結果を達成しています。
🚀 クイックスタート
このセクションでは、このモデルの基本的な使い方を説明します。
🔧 技術詳細
学習ハイパーパラメータ
学習中に使用されたハイパーパラメータは以下の通りです。
| パラメータ |
値 |
| learning_rate |
0.0001 |
| train_batch_size |
16 |
| eval_batch_size |
16 |
| seed |
13 |
| gradient_accumulation_steps |
2 |
| total_train_batch_size |
32 |
| optimizer |
Adam (betas=(0.9,0.999), epsilon=1e-08) |
| lr_scheduler_type |
linear |
| lr_scheduler_warmup_steps |
40000 |
| training_steps |
100000 |
学習結果
| 学習損失 |
エポック |
ステップ |
検証損失 |
| No log |
1.5662 |
2000 |
7.6811 |
| 7.6872 |
3.1323 |
4000 |
6.6323 |
| 7.6872 |
4.6985 |
6000 |
6.5117 |
| 6.5145 |
6.2647 |
8000 |
6.4461 |
| 6.5145 |
7.8309 |
10000 |
6.3755 |
| 6.3572 |
9.3970 |
12000 |
6.3094 |
| 6.3572 |
10.9632 |
14000 |
6.2737 |
| 6.2339 |
12.5294 |
16000 |
6.2091 |
| 6.2339 |
14.0955 |
18000 |
6.1964 |
| 6.1124 |
15.6617 |
20000 |
6.1261 |
| 6.1124 |
17.2279 |
22000 |
5.9661 |
| 5.9136 |
18.7940 |
24000 |
5.5933 |
| 5.9136 |
20.3602 |
26000 |
5.0449 |
| 5.109 |
21.9264 |
28000 |
4.4819 |
| 5.109 |
23.4926 |
30000 |
4.0711 |
| 4.1502 |
25.0587 |
32000 |
3.7598 |
| 4.1502 |
26.6249 |
34000 |
3.4685 |
| 3.5347 |
28.1911 |
36000 |
3.3009 |
| 3.5347 |
29.7572 |
38000 |
3.1496 |
| 3.1576 |
31.3234 |
40000 |
3.0139 |
| 3.1576 |
32.8896 |
42000 |
2.9557 |
| 2.8847 |
34.4558 |
44000 |
2.8395 |
| 2.8847 |
36.0219 |
46000 |
2.7659 |
| 2.6809 |
37.5881 |
48000 |
2.6953 |
| 2.6809 |
39.1543 |
50000 |
2.6246 |
| 2.5261 |
40.7204 |
52000 |
2.5583 |
| 2.5261 |
42.2866 |
54000 |
2.5142 |
| 2.4073 |
43.8528 |
56000 |
2.4925 |
| 2.4073 |
45.4190 |
58000 |
2.4343 |
| 2.3129 |
46.9851 |
60000 |
2.4278 |
| 2.3129 |
48.5513 |
62000 |
2.3707 |
| 2.23 |
50.1175 |
64000 |
2.3806 |
| 2.23 |
51.6836 |
66000 |
2.3299 |
| 2.1662 |
53.2498 |
68000 |
2.3031 |
| 2.1662 |
54.8160 |
70000 |
2.2718 |
| 2.1093 |
56.3821 |
72000 |
2.2745 |
| 2.1093 |
57.9483 |
74000 |
2.2610 |
| 2.0596 |
59.5145 |
76000 |
2.2490 |
| 2.0596 |
61.0807 |
78000 |
2.1928 |
| 2.0165 |
62.6468 |
80000 |
2.1660 |
| 2.0165 |
64.2130 |
82000 |
2.1797 |
| 1.9818 |
65.7792 |
84000 |
2.1873 |
| 1.9818 |
67.3453 |
86000 |
2.1384 |
| 1.9505 |
68.9115 |
88000 |
2.1419 |
| 1.9505 |
70.4777 |
90000 |
2.1471 |
| 1.9231 |
72.0439 |
92000 |
2.1419 |
| 1.9231 |
73.6100 |
94000 |
2.1390 |
| 1.9072 |
75.1762 |
96000 |
2.1414 |
| 1.9072 |
76.7424 |
98000 |
2.1240 |
| 1.8894 |
78.3085 |
100000 |
2.1200 |
フレームワークのバージョン
- 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 複数言語対応