{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.28486646884273, "eval_steps": 6, "global_step": 6, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.04747774480712166, "grad_norm": 0.10393894463777542, "learning_rate": 1e-05, "loss": 10.3853, "step": 1 }, { "epoch": 0.04747774480712166, "eval_loss": 10.38197135925293, "eval_runtime": 10.9858, "eval_samples_per_second": 3.277, "eval_steps_per_second": 1.638, "step": 1 }, { "epoch": 0.09495548961424333, "grad_norm": 0.10695062577724457, "learning_rate": 2e-05, "loss": 10.3893, "step": 2 }, { "epoch": 0.142433234421365, "grad_norm": 0.10071176290512085, "learning_rate": 3e-05, "loss": 10.3815, "step": 3 }, { "epoch": 0.18991097922848665, "grad_norm": 0.104220911860466, "learning_rate": 4e-05, "loss": 10.3825, "step": 4 }, { "epoch": 0.23738872403560832, "grad_norm": 0.11204732209444046, "learning_rate": 5e-05, "loss": 10.3846, "step": 5 }, { "epoch": 0.28486646884273, "grad_norm": 0.11993242055177689, "learning_rate": 6e-05, "loss": 10.3843, "step": 6 }, { "epoch": 0.28486646884273, "eval_loss": 10.381671905517578, "eval_runtime": 0.075, "eval_samples_per_second": 480.233, "eval_steps_per_second": 240.117, "step": 6 } ], "logging_steps": 1, "max_steps": 22, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 6, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 481676328960.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }