{"train/loss": 0.1199, "train/grad_norm": 1.1583800315856934, "train/learning_rate": 7.722007722007723e-09, "train/epoch": 9.971126082771896, "train/global_step": 2590, "_timestamp": 1726573085.5001044, "_runtime": 638.6713645458221, "_step": 22, "eval/loss": 0.25901132822036743, "eval/f1": 0.7609269081317186, "eval/precision": 0.7112407211028632, "eval/recall": 0.8180764774044033, "eval/accuracy": 0.9229162898531661, "eval/runtime": 8.311, "eval/samples_per_second": 463.961, "eval/steps_per_second": 57.995, "train_runtime": 624.2924, "train_samples_per_second": 266.205, "train_steps_per_second": 4.149, "total_flos": 4413788351238426.0, "train_loss": 0.181362230160982} |