{ "effective_tokens_per_sec": 330.74608278063124, "epoch": 3.0, "total_flos": 5.409409894396723e+17, "train_loss": 0.06834091498837834, "train_runtime": 761.1394, "train_samples_per_second": 28.694, "train_steps_per_second": 0.225 }