{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.05187319884726225, "eval_steps": 9, "global_step": 9, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.005763688760806916, "eval_loss": NaN, "eval_runtime": 30.7478, "eval_samples_per_second": 9.529, "eval_steps_per_second": 1.203, "step": 1 }, { "epoch": 0.01729106628242075, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0345821325648415, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.05187319884726225, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.05187319884726225, "eval_loss": NaN, "eval_runtime": 30.7379, "eval_samples_per_second": 9.532, "eval_steps_per_second": 1.204, "step": 9 } ], "logging_steps": 3, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 9, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 2.088819058802688e+16, "train_batch_size": 8, "trial_name": null, "trial_params": null }