{ "parameters": 34999041, "matmul_parameters": 34975744, "training_percent": 100, "step": 72479, "total_steps": 72479, "tokens_seen": 37999869952, "target_tokens": 38000000000, "trained_token_target": 37999869952, "tokens_per_step": 524288, "world_size": 8, "gpu_name": "NVIDIA RTX PRO 6000 Blackwell Server Edition", "peak_lr": 0.0023, "solo_lambda": 0.3, "architecture_revision": "a0f30efc480e2c298dc7e779d714338ecf031eaa", "dataset_revisions": { "fineweb_hq": "e58199cdd52438d94405df1a4d8630cc5f13bf84", "dclm": "a3b142c183aebe5af344955ae20836eb34dcf69b", "cosmopedia_v2": "3ba9d605774198c5868892d7a8deda78031a781f", "finemath": "e92b25a616738fe95dc186b64dfb19f9c8525594" }, "source_tokens": { "fineweb_hq": 19363528704, "dclm": 7891058688, "cosmopedia_v2": 7616331776, "finemath": 3128950784 }, "mix": { "fineweb_hq": 0.50957, "dclm": 0.20766, "cosmopedia_v2": 0.20043, "finemath": 0.08234 }, "elapsed_seconds": 27405.331552505493 }