{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.9230769230769231, "eval_steps": 25, "global_step": 50, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.19230769230769232, "grad_norm": 0.5569552183151245, "learning_rate": 0.0001, "loss": 4.6128, "step": 5 }, { "epoch": 0.38461538461538464, "grad_norm": 0.7635518312454224, "learning_rate": 0.00019714285714285716, "loss": 4.4768, "step": 10 }, { "epoch": 0.5769230769230769, "grad_norm": 1.002182126045227, "learning_rate": 0.00018285714285714286, "loss": 4.3935, "step": 15 }, { "epoch": 0.7692307692307693, "grad_norm": 0.7686426043510437, "learning_rate": 0.00016857142857142857, "loss": 4.1717, "step": 20 }, { "epoch": 0.9615384615384616, "grad_norm": 0.9222117066383362, "learning_rate": 0.0001542857142857143, "loss": 3.7154, "step": 25 }, { "epoch": 1.1538461538461537, "grad_norm": 1.0059330463409424, "learning_rate": 0.00014, "loss": 3.6302, "step": 30 }, { "epoch": 1.3461538461538463, "grad_norm": 1.1044957637786865, "learning_rate": 0.00012571428571428572, "loss": 3.617, "step": 35 }, { "epoch": 1.5384615384615383, "grad_norm": 1.1102561950683594, "learning_rate": 0.00011142857142857144, "loss": 3.3122, "step": 40 }, { "epoch": 1.7307692307692308, "grad_norm": 1.1488291025161743, "learning_rate": 9.714285714285715e-05, "loss": 3.473, "step": 45 }, { "epoch": 1.9230769230769231, "grad_norm": 1.1239038705825806, "learning_rate": 8.285714285714287e-05, "loss": 3.2339, "step": 50 } ], "logging_steps": 5, "max_steps": 78, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 50, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 26425362087936.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }