| { | |
| "meta": { | |
| "model": "bdh", | |
| "size_m": 150, | |
| "steps": 30000, | |
| "seq_len": 2048, | |
| "warmup": 1000, | |
| "seed": 0, | |
| "config": { | |
| "arch": "bdh", | |
| "size_m": 150, | |
| "mult": 768, | |
| "checkpointed": 1 | |
| }, | |
| "data": "research-mix-v1 970M tok byte-level (80%EN fineweb-edu / 20%PL speakleash)", | |
| "optimizer": "AdamW lr=1e-3 wd=0.1 cos->1e-4 warmup1000", | |
| "clip": "ZClip", | |
| "world": 1, | |
| "rank": 0 | |
| } | |
| } |