{ "effective_tokens_per_sec": 7286.899729026163, "epoch": 4.0, "total_flos": 3.4175049861232067e+18, "train_loss": 0.7562091423920304, "train_runtime": 9085.3052, "train_samples_per_second": 5.957, "train_steps_per_second": 0.199 }