{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.004340748779164406, "eval_steps": 3, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0004340748779164406, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0004340748779164406, "eval_loss": NaN, "eval_runtime": 154.9634, "eval_samples_per_second": 6.26, "eval_steps_per_second": 3.13, "step": 1 }, { "epoch": 0.0008681497558328812, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0013022246337493217, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0013022246337493217, "eval_loss": NaN, "eval_runtime": 157.0354, "eval_samples_per_second": 6.177, "eval_steps_per_second": 3.088, "step": 3 }, { "epoch": 0.0017362995116657625, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.002170374389582203, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.0026044492674986435, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0026044492674986435, "eval_loss": NaN, "eval_runtime": 156.8835, "eval_samples_per_second": 6.183, "eval_steps_per_second": 3.091, "step": 6 }, { "epoch": 0.003038524145415084, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.003472599023331525, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.003906673901247965, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.003906673901247965, "eval_loss": NaN, "eval_runtime": 156.9349, "eval_samples_per_second": 6.181, "eval_steps_per_second": 3.09, "step": 9 }, { "epoch": 0.004340748779164406, "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": 2959302797033472.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }