Language Modeling on WikiText2 (train)
14.6401Final Train Loss
QKV111
Updated 4d ago
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
2025.12 | 14.6401 | - | 0 | - | - | - | |
2025.12 | 14.8002 | - | -1.093 | - | - | - | |
2025.12 | 14.8139 | - | -1.186 | - | - | - | |
2025.12 | 15.0499 | - | -2.799 | - | - | - | |
2025.12 | 15.1213 | - | 0.8328 | - | - | - | |
2025.12 | 15.2483 | - | 0 | - | - | - | |
2025.12 | 15.3293 | - | -0.531 | - | - | - | |
2025.12 | 16.4084 | - | 0.241 | - | - | - | |
2025.12 | 16.4481 | - | 0 | - | - | - | |
2025.12 | 16.4519 | - | -0.023 | - | - | - | |
2025.12 | 16.5034 | - | -0.336 | - | - | - | |
2022.06 | - | 3.8 | - | - | - | - | |
2022.06 | - | 4.1 | - | - | - | - | |
2022.06 | - | 3 | - | - | - | - | |
2026.02 | - | - | - | 360.8 | 0.68 | - | |
2026.02 | - | - | - | 243 | 0.51 | 33 | |
2026.02 | - | - | - | 136.2 | 0.86 | 62 | |
2026.02 | - | - | - | 516.2 | 1.66 | - | |
2026.02 | - | - | - | 376 | 1.21 | 27 | |
2026.02 | - | - | - | 262.6 | 2.17 | 49 | |
2026.02 | - | - | - | 637.6 | 3.21 | - | |
2026.02 | - | - | - | 479.2 | 2.24 | 25 | |
2026.02 | - | - | - | 368.4 | 4.09 | 42 |