{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.05702066999287242, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.011404133998574484, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 446.0754, "step": 1 }, { "epoch": 0.011404133998574484, "eval_loss": NaN, "eval_runtime": 143.8707, "eval_samples_per_second": 1.029, "eval_steps_per_second": 0.514, "step": 1 }, { "epoch": 0.022808267997148968, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 39.3452, "step": 2 }, { "epoch": 0.022808267997148968, "eval_loss": NaN, "eval_runtime": 7.412, "eval_samples_per_second": 19.968, "eval_steps_per_second": 9.984, "step": 2 }, { "epoch": 0.03421240199572345, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.045616535994297935, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.045616535994297935, "eval_loss": NaN, "eval_runtime": 7.4188, "eval_samples_per_second": 19.949, "eval_steps_per_second": 9.975, "step": 4 }, { "epoch": 0.05702066999287242, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 1946.2954, "step": 5 } ], "logging_steps": 1, "max_steps": 5, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 2, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 8703670952656896.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }