"HOM2" GPT2 (base) and GPT2Moe
Collection
Trained on fra_latn, glg_latn, spa_latn, por_latn, and ita_latn (homogeneous set 2) โข 6 items โข Updated
GPT2Moe (custom) trained on a balanced set of languages Balanced model training set (1000mb with byte premium scaling for each language) Balanced tokenizer training set (100mb with byte premium scaling for each language)
Based on 2 W&B runs named gpt2moe_hom2_1000mb in sjzahra-ri-se/huggingface.
Loss: 1 run(s); warmup: 1; GPU telemetry: 1 run(s).
Training hardware: Trained on a single H100 GPU.
French, Spanish, Portuguese, Italian, Galician
| Parameter | Value |
|---|---|
| Runs included | 2 |
| Training hardware | Trained on a single H100 GPU |
| Total epochs | 9.99981 |
| Total training steps | 375,482 |
| Total training FLOPs | 1.2559e+19 |
| Learning rate | 0.0001 |
| Train batch size | 8 |
| Eval batch size | 4 |
| Gradient accumulation | 8 |
| Weight decay | 0.01 |
| Warmup steps | 37548 |
| Warmup ratio | 0 |
| Optimizer | adamw_torch_fused |
| Scheduler | linear |
| Max sequence length | 20 |
| Precision | False |
| Seed | 42 |
| GPU utilization | mean 57.1%, peak 100.0% |
Generated 2026-11-17T17:21:56+00:00.