{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.16, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.008, "grad_norm": 0.8485889434814453, "learning_rate": 0.0001999964908278481, "loss": 1.2049, "step": 5 }, { "epoch": 0.016, "grad_norm": 0.47789862751960754, "learning_rate": 0.00019998596355767805, "loss": 0.9333, "step": 10 }, { "epoch": 0.024, "grad_norm": 1.017558217048645, "learning_rate": 0.00019996841892833, "loss": 0.8671, "step": 15 }, { "epoch": 0.032, "grad_norm": 0.6610977053642273, "learning_rate": 0.00019994385817114646, "loss": 0.7979, "step": 20 }, { "epoch": 0.04, "grad_norm": 0.6075429320335388, "learning_rate": 0.00019991228300988585, "loss": 0.7662, "step": 25 }, { "epoch": 0.048, "grad_norm": 0.6595763564109802, "learning_rate": 0.00019987369566060176, "loss": 0.7929, "step": 30 }, { "epoch": 0.056, "grad_norm": 0.6968618035316467, "learning_rate": 0.00019982809883148722, "loss": 0.7683, "step": 35 }, { "epoch": 0.064, "grad_norm": 0.4889592230319977, "learning_rate": 0.00019977549572268468, "loss": 0.8667, "step": 40 }, { "epoch": 0.072, "grad_norm": 0.6651108264923096, "learning_rate": 0.0001997158900260614, "loss": 0.8446, "step": 45 }, { "epoch": 0.08, "grad_norm": 0.5898510217666626, "learning_rate": 0.00019964928592495045, "loss": 0.9051, "step": 50 }, { "epoch": 0.088, "grad_norm": 0.4398016035556793, "learning_rate": 0.00019957568809385694, "loss": 0.7235, "step": 55 }, { "epoch": 0.096, "grad_norm": 0.6901968121528625, "learning_rate": 0.00019949510169813003, "loss": 0.8169, "step": 60 }, { "epoch": 0.104, "grad_norm": 0.6267213225364685, "learning_rate": 0.00019940753239360047, "loss": 0.8266, "step": 65 }, { "epoch": 0.112, "grad_norm": 0.48524895310401917, "learning_rate": 0.00019931298632618356, "loss": 0.758, "step": 70 }, { "epoch": 0.12, "grad_norm": 0.5294132232666016, "learning_rate": 0.0001992114701314478, "loss": 0.7759, "step": 75 }, { "epoch": 0.128, "grad_norm": 0.48957982659339905, "learning_rate": 0.0001991029909341493, "loss": 0.7797, "step": 80 }, { "epoch": 0.136, "grad_norm": 0.645412802696228, "learning_rate": 0.00019898755634773158, "loss": 0.7437, "step": 85 }, { "epoch": 0.144, "grad_norm": 0.43297675251960754, "learning_rate": 0.0001988651744737914, "loss": 0.8043, "step": 90 }, { "epoch": 0.152, "grad_norm": 0.5513920783996582, "learning_rate": 0.00019873585390151003, "loss": 0.7701, "step": 95 }, { "epoch": 0.16, "grad_norm": 0.8462435007095337, "learning_rate": 0.0001985996037070505, "loss": 0.709, "step": 100 } ], "logging_steps": 5, "max_steps": 1875, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 6310561256570880.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }