{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00032447647748336044, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.489529549667209e-05, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 6.489529549667209e-05, "eval_loss": NaN, "eval_runtime": 980.943, "eval_samples_per_second": 26.457, "eval_steps_per_second": 13.229, "step": 1 }, { "epoch": 0.00012979059099334418, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.00012979059099334418, "eval_loss": NaN, "eval_runtime": 1323.3876, "eval_samples_per_second": 19.611, "eval_steps_per_second": 9.806, "step": 2 }, { "epoch": 0.00019468588649001627, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.00025958118198668835, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00025958118198668835, "eval_loss": NaN, "eval_runtime": 1845.7076, "eval_samples_per_second": 14.061, "eval_steps_per_second": 7.031, "step": 4 }, { "epoch": 0.00032447647748336044, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 3769902192132096.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }