{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.0, "eval_steps": 100, "global_step": 84, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.47619047619047616, "grad_norm": 2.757856845855713, "learning_rate": 0.0001761904761904762, "loss": 0.5843, "step": 10 }, { "epoch": 0.9523809523809523, "grad_norm": 3.4689693450927734, "learning_rate": 0.00015238095238095237, "loss": 0.5473, "step": 20 }, { "epoch": 1.4285714285714286, "grad_norm": 0.5666776299476624, "learning_rate": 0.00012857142857142858, "loss": 0.1833, "step": 30 }, { "epoch": 1.9047619047619047, "grad_norm": 0.2773081362247467, "learning_rate": 0.00010476190476190477, "loss": 0.1073, "step": 40 }, { "epoch": 2.380952380952381, "grad_norm": 0.14523948729038239, "learning_rate": 8.095238095238096e-05, "loss": 0.0217, "step": 50 }, { "epoch": 2.857142857142857, "grad_norm": 0.10562175512313843, "learning_rate": 5.714285714285714e-05, "loss": 0.0158, "step": 60 }, { "epoch": 3.3333333333333335, "grad_norm": 0.09110253304243088, "learning_rate": 3.3333333333333335e-05, "loss": 0.0125, "step": 70 }, { "epoch": 3.8095238095238093, "grad_norm": 0.09965213388204575, "learning_rate": 9.523809523809523e-06, "loss": 0.0116, "step": 80 }, { "epoch": 4.0, "step": 84, "total_flos": 2.5417372593586176e+16, "train_loss": 0.17717325119745164, "train_runtime": 30.5569, "train_samples_per_second": 10.734, "train_steps_per_second": 2.749 } ], "logging_steps": 10, "max_steps": 84, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.5417372593586176e+16, "train_batch_size": 4, "trial_name": null, "trial_params": null }