| { |
| "model": { |
| "vocab_size": 32768, |
| "max_seq_len": 512, |
| "d_model": 1024, |
| "n_layers": 24, |
| "n_heads": 16, |
| "d_ff": 4096, |
| "dropout": 0.1, |
| "attention_dropout": 0.1, |
| "layer_norm_eps": 1e-05, |
| "pad_token_id": 0, |
| "tie_mlm_head": true, |
| "grad_checkpointing": false, |
| "num_labels": 2 |
| }, |
| "tokenizer": "tokenizer.json", |
| "training": { |
| "run_name": "large-24L", |
| "status": "complete", |
| "source_checkpoint": "step-0009552", |
| "steps": 9552, |
| "total_steps_planned": 9552, |
| "steps_per_epoch": 796, |
| "epochs_planned": 12, |
| "epochs_completed": 12.0, |
| "tokens_seen": 1291124736, |
| "total_training_seconds": 54185.9, |
| "total_training_time": "15h 03m 05s", |
| "final_loss": 1.523698394948786, |
| "val_loss": 1.9862932266429436, |
| "val_masked_acc": 0.6291136684837473, |
| "peak_vram_reserved_gb": 17.939, |
| "peak_vram_allocated_gb": 17.494, |
| "micro_batch": 24, |
| "grad_accumulation": 11, |
| "effective_batch": 264, |
| "precision": "bf16_autocast", |
| "optimizer": "AdamW(fused) {\"lr\": 0.00015, \"betas\": [0.9, 0.98], \"eps\": 1e-06, \"weight_decay\": 0.01, \"grad_clip\": 1.0, \"mlm_probability\": 0.15, \"mask_replace_probs\": [0.8, 0.1, 0.1], \"schedule\": \"cosine_to_10pct\", \"effective_batch_sequences\": 256}", |
| "schedule": { |
| "kind": "cosine", |
| "peak_lr": 0.00015, |
| "warmup_steps": 573, |
| "total_steps": 9552, |
| "floor_ratio": 0.1 |
| }, |
| "mean_tokens_per_s": 23889, |
| "data": { |
| "n_windows": 210368, |
| "n_val_windows": 1999, |
| "tokenizer_sha1": "9f50c5e775089d2ca3efc82e100cd6b3396ed7e7", |
| "n_docs": 226273, |
| "limit_docs": null, |
| "window": "[CLS] + 511 stream tokens" |
| }, |
| "weights_dtype": "float32", |
| "exported_at": "2026-10-09T03:31:14" |
| } |
| } |
|
|
