| { | |
| "step": 503, | |
| "val_bpb": 0.4306600049435095, | |
| "model_config": { | |
| "sequence_len": 2048, | |
| "vocab_size": 32768, | |
| "n_layer": 18, | |
| "n_head": 9, | |
| "n_kv_head": 9, | |
| "n_embd": 1152, | |
| "window_pattern": "L", | |
| "use_mla": false, | |
| "kv_lora_rank": 512, | |
| "qk_lora_rank": 1536, | |
| "qk_nope_head_dim": 128, | |
| "qk_rope_head_dim": 64, | |
| "v_head_dim": 128, | |
| "use_ssa": true | |
| }, | |
| "user_config": { | |
| "run": "nanochat", | |
| "device_type": "", | |
| "model_tag": "picochat_long", | |
| "model_step": null, | |
| "load_optimizer": 1, | |
| "num_iterations": -1, | |
| "max_seq_len": null, | |
| "device_batch_size": 32, | |
| "total_batch_size": null, | |
| "embedding_lr": null, | |
| "unembedding_lr": null, | |
| "matrix_lr": null, | |
| "init_lr_frac": 0.8, | |
| "warmup_ratio": 0.0, | |
| "warmdown_ratio": 0.5, | |
| "final_lr_frac": 0.0, | |
| "no_muon": false, | |
| "eval_every": 200, | |
| "eval_tokens": 20971520, | |
| "chatcore_every": 200, | |
| "chatcore_max_cat": -1, | |
| "chatcore_max_sample": 24, | |
| "mmlu_epochs": 3, | |
| "gsm8k_epochs": 4 | |
| } | |
| } |