{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00040945010850427875, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.189002170085576e-06, "eval_loss": NaN, "eval_runtime": 3688.7091, "eval_samples_per_second": 3.679, "eval_steps_per_second": 3.679, "step": 1 }, { "epoch": 4.094501085042788e-05, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 8.189002170085576e-05, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.00012283503255128362, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.0001637800434017115, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.00020472505425213938, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 0.0, "step": 25 }, { "epoch": 0.00020472505425213938, "eval_loss": NaN, "eval_runtime": 3706.1532, "eval_samples_per_second": 3.661, "eval_steps_per_second": 3.661, "step": 25 }, { "epoch": 0.00024567006510256724, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 30 }, { "epoch": 0.00028661507595299513, "grad_norm": NaN, "learning_rate": 3.086582838174551e-05, "loss": 0.0, "step": 35 }, { "epoch": 0.000327560086803423, "grad_norm": NaN, "learning_rate": 1.4644660940672627e-05, "loss": 0.0, "step": 40 }, { "epoch": 0.00036850509765385086, "grad_norm": NaN, "learning_rate": 3.8060233744356633e-06, "loss": 0.0, "step": 45 }, { "epoch": 0.00040945010850427875, "grad_norm": NaN, "learning_rate": 0.0, "loss": 0.0, "step": 50 }, { "epoch": 0.00040945010850427875, "eval_loss": NaN, "eval_runtime": 3698.3758, "eval_samples_per_second": 3.669, "eval_steps_per_second": 3.669, "step": 50 } ], "logging_steps": 5, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 25, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4368991833292800.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }