{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.972972972972973, "eval_steps": 500, "global_step": 9, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.10810810810810811, "grad_norm": NaN, "learning_rate": 1.0000000000000002e-06, "loss": 0.0, "step": 1 }, { "epoch": 0.21621621621621623, "grad_norm": NaN, "learning_rate": 2.0000000000000003e-06, "loss": 0.0, "step": 2 }, { "epoch": 0.32432432432432434, "grad_norm": NaN, "learning_rate": 3e-06, "loss": 0.0, "step": 3 }, { "epoch": 0.43243243243243246, "grad_norm": NaN, "learning_rate": 4.000000000000001e-06, "loss": 0.0, "step": 4 }, { "epoch": 0.5405405405405406, "grad_norm": NaN, "learning_rate": 5e-06, "loss": 0.0, "step": 5 }, { "epoch": 0.6486486486486487, "grad_norm": NaN, "learning_rate": 6e-06, "loss": 0.0, "step": 6 }, { "epoch": 0.7567567567567568, "grad_norm": NaN, "learning_rate": 7.000000000000001e-06, "loss": 0.0, "step": 7 }, { "epoch": 0.8648648648648649, "grad_norm": NaN, "learning_rate": 8.000000000000001e-06, "loss": 0.0, "step": 8 }, { "epoch": 0.972972972972973, "grad_norm": NaN, "learning_rate": 9e-06, "loss": 0.0, "step": 9 } ], "logging_steps": 1, "max_steps": 9, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 239, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 14514483363840.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }