{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.003328340822100183, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003328340822100183, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0003328340822100183, "eval_loss": NaN, "eval_runtime": 70.5457, "eval_samples_per_second": 17.932, "eval_steps_per_second": 8.973, "step": 1 }, { "epoch": 0.0006656681644200366, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.000998502246630055, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.000998502246630055, "eval_loss": NaN, "eval_runtime": 68.3813, "eval_samples_per_second": 18.499, "eval_steps_per_second": 9.257, "step": 3 }, { "epoch": 0.0013313363288400732, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0016641704110500915, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.00199700449326011, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.00199700449326011, "eval_loss": NaN, "eval_runtime": 68.6135, "eval_samples_per_second": 18.437, "eval_steps_per_second": 9.226, "step": 6 }, { "epoch": 0.002329838575470128, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.0026626726576801465, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0029955067398901645, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0029955067398901645, "eval_loss": NaN, "eval_runtime": 68.5945, "eval_samples_per_second": 18.442, "eval_steps_per_second": 9.228, "step": 9 }, { "epoch": 0.003328340822100183, "grad_norm": NaN, "learning_rate": 0.0002, "loss": 0.0, "step": 10 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3238750071029760.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }