| { | |
| "n_layers_quantized": 128, | |
| "n_layers_skipped": 0, | |
| "avg_error": 0.004986405004168977, | |
| "max_error": 0.015271722124009159, | |
| "compression_ratio": 1.4412203733458264, | |
| "format": "qoperator_w8a8", | |
| "alpha": 0.5, | |
| "base_model": "v13.9.2-finetune-v4", | |
| "canonical_source": "step 20 best checkpoint (loss 6.23, ppl 507.81)", | |
| "datasets": [ | |
| "orion-research/translations-en_US-pt_BR", | |
| "cnmoro/Instruct-PTBR-10M", | |
| "strak2005/corpus-ptbr-v1" | |
| ], | |
| "format_standardization": "### Instruction:/### Response: template aplicado a orion e cnmoro", | |
| "training_note": "v4 training: 500 samples × 3 datasets × 40 opt steps × 16 grad_accum = 640 micro-batches. Best stable loss at step 20 (loss 6.23, ppl 507.81). Step 35+ showed loss spike (likely bad batch in cnmoro range). Final-step (40) model was worse, so canonical = step 20 checkpoint." | |
| } |