{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9256198347107438, "eval_steps": 30, "global_step": 7, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.1322314049586777, "grad_norm": 1.7038763761520386, "learning_rate": 0.00017142857142857143, "loss": 10.0955, "step": 1 }, { "epoch": 0.2644628099173554, "grad_norm": 1.7832878828048706, "learning_rate": 0.00014285714285714287, "loss": 10.0281, "step": 2 }, { "epoch": 0.39669421487603307, "grad_norm": 2.6710143089294434, "learning_rate": 0.00011428571428571428, "loss": 9.5219, "step": 3 }, { "epoch": 0.5289256198347108, "grad_norm": 3.564816951751709, "learning_rate": 8.571428571428571e-05, "loss": 9.0921, "step": 4 }, { "epoch": 0.6611570247933884, "grad_norm": 3.5809993743896484, "learning_rate": 5.714285714285714e-05, "loss": 8.6465, "step": 5 }, { "epoch": 0.7933884297520661, "grad_norm": 2.9257972240448, "learning_rate": 2.857142857142857e-05, "loss": 8.3989, "step": 6 }, { "epoch": 0.9256198347107438, "grad_norm": 3.141226291656494, "learning_rate": 0.0, "loss": 8.2718, "step": 7 }, { "epoch": 0.9256198347107438, "step": 7, "total_flos": 12275755601088.0, "train_loss": 9.150690759931292, "train_runtime": 313.5661, "train_samples_per_second": 0.386, "train_steps_per_second": 0.022 } ], "logging_steps": 1.0, "max_steps": 7, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 12275755601088.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }