{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.2157676348547718, "eval_steps": 13, "global_step": 13, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.016597510373443983, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.016597510373443983, "eval_loss": NaN, "eval_runtime": 63.7392, "eval_samples_per_second": 1.6, "eval_steps_per_second": 0.8, "step": 1 }, { "epoch": 0.03319502074688797, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.04979253112033195, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.06639004149377593, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.08298755186721991, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.0995850622406639, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 6 }, { "epoch": 0.11618257261410789, "grad_norm": NaN, "learning_rate": 7e-05, "loss": 0.0, "step": 7 }, { "epoch": 0.13278008298755187, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 8 }, { "epoch": 0.14937759336099585, "grad_norm": NaN, "learning_rate": 9e-05, "loss": 0.0, "step": 9 }, { "epoch": 0.16597510373443983, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.1825726141078838, "grad_norm": NaN, "learning_rate": 9.98458666866564e-05, "loss": 0.0, "step": 11 }, { "epoch": 0.1991701244813278, "grad_norm": NaN, "learning_rate": 9.938441702975689e-05, "loss": 0.0, "step": 12 }, { "epoch": 0.2157676348547718, "grad_norm": NaN, "learning_rate": 9.861849601988383e-05, "loss": 0.0, "step": 13 }, { "epoch": 0.2157676348547718, "eval_loss": NaN, "eval_runtime": 15.2066, "eval_samples_per_second": 6.708, "eval_steps_per_second": 3.354, "step": 13 } ], "logging_steps": 1, "max_steps": 50, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 13, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3.836374444670976e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }