| { | |
| "arm": "causal", | |
| "attn_impl": "flex", | |
| "qk_norm": true, | |
| "output_dir": "/scratch/11079/antonxue/tridlm-runs/20260829-1047-qk1-lr1e-4-causal", | |
| "learning_rate": 0.0001, | |
| "warmup_steps": 1000, | |
| "stable_steps": 89000, | |
| "decay_steps": 10000, | |
| "min_lr_ratio": 0.0, | |
| "weight_decay": 0.1, | |
| "batch_size": 64, | |
| "gradient_accumulation_steps": 1, | |
| "logging_steps": 5, | |
| "save_steps": 1000, | |
| "save_total_limit": 5, | |
| "keep_every": 5000, | |
| "seed": 1, | |
| "dataloader_num_workers": 4, | |
| "compile": true, | |
| "resume_from_checkpoint": null, | |
| "tiny": false, | |
| "synthetic_rows": 0, | |
| "max_train_rows": 0 | |
| } |