{ "best_metric": null, "best_model_checkpoint": null, "epoch": 50.0, "eval_steps": 500, "global_step": 3850, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.4935064935064934, "grad_norm": 17.624969482421875, "learning_rate": 4.3506493506493503e-05, "loss": 1.7452, "step": 500 }, { "epoch": 12.987012987012987, "grad_norm": 15.936542510986328, "learning_rate": 3.701298701298702e-05, "loss": 1.1727, "step": 1000 }, { "epoch": 19.48051948051948, "grad_norm": 22.365955352783203, "learning_rate": 3.051948051948052e-05, "loss": 0.8119, "step": 1500 }, { "epoch": 25.974025974025974, "grad_norm": 19.36739730834961, "learning_rate": 2.4025974025974027e-05, "loss": 0.5254, "step": 2000 }, { "epoch": 32.467532467532465, "grad_norm": 4.489462852478027, "learning_rate": 1.7532467532467535e-05, "loss": 0.3811, "step": 2500 }, { "epoch": 38.96103896103896, "grad_norm": 0.12353431433439255, "learning_rate": 1.103896103896104e-05, "loss": 0.2244, "step": 3000 }, { "epoch": 45.45454545454545, "grad_norm": 4.508783340454102, "learning_rate": 4.5454545454545455e-06, "loss": 0.1191, "step": 3500 }, { "epoch": 50.0, "step": 3850, "total_flos": 1779910137759600.0, "train_loss": 0.6525665847976486, "train_runtime": 847.6015, "train_samples_per_second": 36.102, "train_steps_per_second": 4.542 } ], "logging_steps": 500, "max_steps": 3850, "num_input_tokens_seen": 0, "num_train_epochs": 50, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1779910137759600.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }