| { | |
| "step": 21400, | |
| "val_bpb": 0.8120380958080629, | |
| "model_config": { | |
| "sequence_len": 2048, | |
| "vocab_size": 65536, | |
| "n_layer": 20, | |
| "n_head": 10, | |
| "n_kv_head": 10, | |
| "n_embd": 1280 | |
| }, | |
| "user_config": { | |
| "run": "d20", | |
| "device_type": "", | |
| "depth": 20, | |
| "max_seq_len": 2048, | |
| "num_iterations": -1, | |
| "target_flops": -1.0, | |
| "target_param_data_ratio": 20, | |
| "device_batch_size": 32, | |
| "total_batch_size": 524288, | |
| "embedding_lr": 0.2, | |
| "unembedding_lr": 0.004, | |
| "weight_decay": 0.0, | |
| "matrix_lr": 0.02, | |
| "grad_clip": 1.0, | |
| "warmup_ratio": 0.0, | |
| "warmdown_ratio": 0.2, | |
| "final_lr_frac": 0.0, | |
| "resume_from_step": -1, | |
| "eval_every": 250, | |
| "eval_tokens": 10485760, | |
| "core_metric_every": 2000, | |
| "core_metric_max_per_task": 500, | |
| "sample_every": 2000, | |
| "save_every": -1, | |
| "model_tag": "" | |
| }, | |
| "device_batch_size": 32, | |
| "max_seq_len": 2048, | |
| "dataloader_state_dict": { | |
| "pq_idx": 198, | |
| "rg_idx": 40 | |
| }, | |
| "loop_state": { | |
| "min_val_bpb": 0.8120380958080629, | |
| "smooth_train_loss": 2.7197287798216516, | |
| "total_training_time": 11182.78338599205 | |
| } | |
| } |