{ "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 120, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.0, "grad_norm": 1.9622077941894531, "learning_rate": 1.3333333333333333e-05, "loss": 0.7054, "step": 40 }, { "epoch": 1.0, "eval_accuracy": 0.39436619718309857, "eval_loss": 0.7037611603736877, "eval_runtime": 0.3115, "eval_samples_per_second": 227.899, "eval_steps_per_second": 28.889, "step": 40 }, { "epoch": 2.0, "grad_norm": 2.4183990955352783, "learning_rate": 6.666666666666667e-06, "loss": 0.7017, "step": 80 }, { "epoch": 2.0, "eval_accuracy": 0.4225352112676056, "eval_loss": 0.7019116878509521, "eval_runtime": 0.3114, "eval_samples_per_second": 228.007, "eval_steps_per_second": 28.902, "step": 80 }, { "epoch": 3.0, "grad_norm": 3.7433464527130127, "learning_rate": 0.0, "loss": 0.6947, "step": 120 }, { "epoch": 3.0, "eval_accuracy": 0.5211267605633803, "eval_loss": 0.7029412984848022, "eval_runtime": 0.3126, "eval_samples_per_second": 227.111, "eval_steps_per_second": 28.789, "step": 120 }, { "epoch": 3.0, "step": 120, "total_flos": 501226560460800.0, "train_loss": 0.700636609395345, "train_runtime": 43.2665, "train_samples_per_second": 44.029, "train_steps_per_second": 2.774 } ], "logging_steps": 500, "max_steps": 120, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 501226560460800.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }