| { |
| "params_total": 1095845888, |
| "n_tensors": 143, |
| "dtype": "bf16", |
| "vocab_size": 32000, |
| "d_model": 2048, |
| "n_blocks": 20, |
| "tensor_keys_sample": [ |
| "blocks.0.attn.out_proj.weight", |
| "blocks.0.attn.qkv.weight", |
| "blocks.0.attn_norm.scale", |
| "blocks.0.ffn.down.weight", |
| "blocks.0.ffn.gate.weight", |
| "blocks.0.ffn.up.weight", |
| "blocks.0.ffn_norm.scale", |
| "blocks.1.attn.out_proj.weight" |
| ], |
| "source_checkpoint": "<workspace>/1B WSM/fine-tuning/ckpt_1b_mix42_merged/best_val/checkpoint.pt", |
| "source_checkpoint_relative": "fine-tuning/ckpt_1b_mix42_merged/best_val/checkpoint.pt", |
| "source_keys": [ |
| "model", |
| "optimizer", |
| "scheduler", |
| "config", |
| "training_state", |
| "timestamp" |
| ], |
| "source_config": { |
| "vocab_size": 32000, |
| "d_model": 2048, |
| "num_layers": 20, |
| "num_heads": 16, |
| "d_ff": 5120, |
| "max_seq_len": 1024, |
| "rope_theta": 500000.0, |
| "dropout_rate": 0.0 |
| }, |
| "config_note": "use_fp8 absent from the raw checkpoint config (plain nn.Linear build); none was added.", |
| "checkpoint_step": 2000, |
| "checkpoint_timestamp": "2026-10-13T23:27:36.964113", |
| "training_state": { |
| "step": 2000, |
| "total_tokens": 65536000, |
| "epoch": 0, |
| "best_val_loss": 0.6519121726595375, |
| "max_tokens": 31013881856, |
| "round_start_tokens": 0, |
| "data_position": { |
| "source_type": "bin", |
| "file_index": 0, |
| "files_total": 0, |
| "rows_skipped": 0, |
| "bin_path": "data_mix_gold/sft_train.bin", |
| "token_offset": 68812800 |
| } |
| }, |
| "nonfinite_after_cast": [], |
| "created_utc": "2026-10-23T11:01:58Z" |
| } |
|
|
