| { | |
| "name": "hypernix.3-mini", | |
| "params": 48706048, | |
| "config": { | |
| "vocab_size": 32000, | |
| "n_layers": 8, | |
| "n_heads": 8, | |
| "n_kv_heads": 2, | |
| "d_model": 512, | |
| "d_ff": 2203, | |
| "max_seq_len": 512, | |
| "rope_theta": 100000.0, | |
| "norm_eps": 1e-05, | |
| "dropout": 0.0, | |
| "tie_embeddings": true, | |
| "use_sliding_window": false, | |
| "sliding_window_size": 512, | |
| "attention_type": "gqa", | |
| "name": "hypernix.3-mini" | |
| }, | |
| "tokens_trained": 873660416, | |
| "steps": 18464, | |
| "total_steps": 18464, | |
| "best_val_loss": 7.839838576316834, | |
| "best_val_ppl": 2539.7948177006024, | |
| "elapsed_seconds": 1047820.9095537663, | |
| "elapsed_human": "12d03h03m", | |
| "deadline_hours": 9999.0, | |
| "within_deadline": true, | |
| "final_ladder": { | |
| "micro_batch": 8, | |
| "accum": 8, | |
| "ce_chunk": 2048, | |
| "grad_ckpt": false, | |
| "rung": 1 | |
| }, | |
| "dataset_bytes": 2422007338, | |
| "optimizer": "pcv6", | |
| "sources": [ | |
| { | |
| "repo": "HuggingFaceFW/fineweb-edu", | |
| "config": "sample-10BT", | |
| "split": "train", | |
| "weight": 1.0, | |
| "text_key": "text" | |
| } | |
| ] | |
| } |