TransWave / training_result.json
Angshul's picture
Release TransWave 96.13M C4 checkpoint
ea51a3d verified
Raw History Blame Contribute Delete
746 Bytes
{
"release": "TransWave-Meyer-96M-C4",
"architecture": "causal_transwave_blocklifting_meyer_byte_lm_g4_v2",
"source_commit": "5cae31b81e15160379ded79f32bcbb443d7db9f7",
"parameters": 96130040,
"dataset": "allenai/c4:en",
"context_tokens": 20480,
"physical_batch": 280,
"tokens_per_full_step": 5734400,
"usable_training_tokens": 4499988480,
"tokens_seen": 4499988480,
"steps": 785,
"target_ppl": 3.0,
"best_full_validation_nll": 2.228725892720205,
"best_full_validation_ppl": 9.288024597671594,
"final_validation": {
"nll": 2.228725892720205,
"ppl": 9.288024597671594,
"tokens": 16773120,
"contexts": 819
},
"stop_reason": "maximum_4p5B_token_budget_exhausted",
"wall_hours": 2.553788356317414
}