{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0006505122784192552, "eval_steps": 8, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.505122784192551e-05, "eval_loss": NaN, "eval_runtime": 492.5828, "eval_samples_per_second": 13.141, "eval_steps_per_second": 6.571, "step": 1 }, { "epoch": 0.00019515368352577655, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0003903073670515531, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.0005204098227354041, "eval_loss": NaN, "eval_runtime": 491.4977, "eval_samples_per_second": 13.17, "eval_steps_per_second": 6.586, "step": 8 }, { "epoch": 0.0005854610505773297, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 } ], "logging_steps": 3, "max_steps": 30, "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": 3515651519938560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }