{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0006980205881172466, "eval_steps": 500, "global_step": 100, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 6.980205881172465e-05, "grad_norm": NaN, "learning_rate": 0.0001981178176898239, "loss": 0.0, "step": 10 }, { "epoch": 0.0001396041176234493, "grad_norm": NaN, "learning_rate": 0.00018687117365181512, "loss": 0.0, "step": 20 }, { "epoch": 0.00020940617643517396, "grad_norm": NaN, "learning_rate": 0.00016659152250116812, "loss": 0.0, "step": 30 }, { "epoch": 0.0002792082352468986, "grad_norm": NaN, "learning_rate": 0.00013938757562492873, "loss": 0.0, "step": 40 }, { "epoch": 0.0003490102940586233, "grad_norm": NaN, "learning_rate": 0.00010808804403614043, "loss": 0.0, "step": 50 }, { "epoch": 0.0004188123528703479, "grad_norm": NaN, "learning_rate": 7.594750436337467e-05, "loss": 0.0, "step": 60 }, { "epoch": 0.0004886144116820726, "grad_norm": NaN, "learning_rate": 4.630798263510162e-05, "loss": 0.0, "step": 70 }, { "epoch": 0.0005584164704937972, "grad_norm": NaN, "learning_rate": 2.2251444932035094e-05, "loss": 0.0, "step": 80 }, { "epoch": 0.0006282185293055219, "grad_norm": NaN, "learning_rate": 6.2793294993656494e-06, "loss": 0.0, "step": 90 }, { "epoch": 0.0006980205881172466, "grad_norm": NaN, "learning_rate": 5.2443095448506674e-08, "loss": 0.0, "step": 100 } ], "logging_steps": 10, "max_steps": 100, "num_input_tokens_seen": 0, "num_train_epochs": 1, "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": 522113463091200.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }