Spaces:
Sleeping
Sleeping
| { | |
| "step": 971, | |
| "val_bpb": 0.36456499504385426, | |
| "model_config": { | |
| "sequence_len": 2048, | |
| "vocab_size": 32768, | |
| "n_layer": 12, | |
| "n_head": 6, | |
| "n_kv_head": 6, | |
| "n_embd": 768, | |
| "window_pattern": "L" | |
| }, | |
| "user_config": { | |
| "run": "d12_climbmix_sft_v1", | |
| "device_type": "", | |
| "model_tag": "d12_climbmix_v1", | |
| "model_step": 2205, | |
| "load_optimizer": 1, | |
| "num_iterations": -1, | |
| "max_seq_len": null, | |
| "device_batch_size": 2, | |
| "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, | |
| "eval_every": -1, | |
| "eval_tokens": 20971520, | |
| "chatcore_every": 200, | |
| "chatcore_max_cat": -1, | |
| "chatcore_max_sample": 24, | |
| "mmlu_epochs": 3, | |
| "gsm8k_epochs": 4 | |
| } | |
| } |