{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0008284231999917158, "eval_steps": 10, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 8.284231999917157e-05, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 1 }, { "epoch": 8.284231999917157e-05, "eval_loss": NaN, "eval_runtime": 1482.1917, "eval_samples_per_second": 6.859, "eval_steps_per_second": 3.429, "step": 1 }, { "epoch": 0.00016568463999834315, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 2 }, { "epoch": 0.00024852695999751475, "grad_norm": NaN, "learning_rate": 9.924038765061042e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0003313692799966863, "grad_norm": NaN, "learning_rate": 9.698463103929542e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0004142115999958579, "grad_norm": NaN, "learning_rate": 9.330127018922194e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0004970539199950295, "grad_norm": NaN, "learning_rate": 8.83022221559489e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.000579896239994201, "grad_norm": NaN, "learning_rate": 8.213938048432697e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.0006627385599933726, "grad_norm": NaN, "learning_rate": 7.500000000000001e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.0007455808799925441, "grad_norm": NaN, "learning_rate": 6.710100716628344e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.0008284231999917158, "grad_norm": NaN, "learning_rate": 5.868240888334653e-05, "loss": 0.0, "step": 10 }, { "epoch": 0.0008284231999917158, "eval_loss": NaN, "eval_runtime": 1482.4697, "eval_samples_per_second": 6.857, "eval_steps_per_second": 3.429, "step": 10 } ], "logging_steps": 1, "max_steps": 20, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1.4321866512531456e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }