{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.888888888888889, "eval_steps": 500, "global_step": 8, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.4444444444444444, "grad_norm": 1.1740930080413818, "learning_rate": 0.000175, "loss": 8.9875, "step": 1 }, { "epoch": 0.8888888888888888, "grad_norm": 1.2762857675552368, "learning_rate": 0.00015000000000000001, "loss": 8.9379, "step": 2 }, { "epoch": 1.0, "grad_norm": 0.6354243159294128, "learning_rate": 0.000125, "loss": 2.2202, "step": 3 }, { "epoch": 1.4444444444444444, "grad_norm": 2.7923552989959717, "learning_rate": 0.0001, "loss": 8.8081, "step": 4 }, { "epoch": 1.8888888888888888, "grad_norm": 3.2708566188812256, "learning_rate": 7.500000000000001e-05, "loss": 8.7649, "step": 5 }, { "epoch": 2.0, "grad_norm": 1.0620002746582031, "learning_rate": 5e-05, "loss": 2.1849, "step": 6 }, { "epoch": 2.4444444444444446, "grad_norm": 3.5511021614074707, "learning_rate": 2.5e-05, "loss": 8.6598, "step": 7 }, { "epoch": 2.888888888888889, "grad_norm": 3.999887466430664, "learning_rate": 0.0, "loss": 8.615, "step": 8 }, { "epoch": 2.888888888888889, "step": 8, "total_flos": 16781863634496.0, "train_loss": 7.147286474704742, "train_runtime": 50.3802, "train_samples_per_second": 2.779, "train_steps_per_second": 0.159 } ], "logging_steps": 1, "max_steps": 8, "num_input_tokens_seen": 0, "num_train_epochs": 4, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 16781863634496.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }