Causal Language Modeling on WikiText-103 GPT-2 (124M) (train)
4.4614Train Loss
GEM (N = 2)
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.04 | 4.4614 | |
2026.04 | 4.4727 | |
2026.04 | 4.4833 | |
2026.04 | 4.4833 | |
2026.04 | 4.5341 | |
2026.04 | 4.5967 |
GEM (N = 2)
| Method | Links | |
|---|---|---|
2026.04 | 4.4614 | |
2026.04 | 4.4727 | |
2026.04 | 4.4833 | |
2026.04 | 4.4833 | |
2026.04 | 4.5341 | |
2026.04 | 4.5967 |