gptbase_dom_het3_tok_1000mb
GPT2 (base) trained on a set of languages where French dominates the model and tokenizer training data sets French is dominant in the model training set (3000mb of French and 500mb (both with byte premium scaling) for all other languages) French is dominant in the tokenizer training set (300mb of French and 50mb (both with byte premium scaling) for all other languages)
Training results
Based on 1 W&B runs named gptbase_dom_het3_tok_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.
Languages
Greek, Turkish, Estonian, French, Arabic
Training metadata
| Parameter | Value |
|---|---|
| Runs included | 1 |
| Training hardware | Trained on a single H100 GPU |
| Total epochs | 9.99975 |
| Total training steps | 400,200 |
| Total training FLOPs | 6.6923e+18 |
| Learning rate | 0.0001 |
| Train batch size | 64 |
| Eval batch size | 64 |
| Gradient accumulation | 1 |
| Weight decay | 0.01 |
| Warmup steps | 40020 |
| Warmup ratio | 0 |
| Optimizer | adamw_torch_fused |
| Scheduler | linear |
| Max sequence length | 20 |
| Precision | False |
| Seed | 43 |
| GPU utilization | mean 98.1%, peak 100.0% |
W&B runs: 0nyl3z6u
Generated 2026-11-17T17:22:44+00:00.
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Collection including NLP-RISE/gptbase_dom_het3_tok_1000mb
Collection
Trained on est_latn, arb_arab, ell_grek, tur_latn, and fra_latn (heterogeneous set 3). โข 6 items โข Updated
