{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0011073583965450417, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00022147167930900837, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 931.3442, "step": 1 }, { "epoch": 0.00022147167930900837, "eval_loss": NaN, "eval_runtime": 443.204, "eval_samples_per_second": 17.159, "eval_steps_per_second": 8.581, "step": 1 }, { "epoch": 0.00044294335861801674, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 14.921, "step": 2 }, { "epoch": 0.00044294335861801674, "eval_loss": NaN, "eval_runtime": 557.9975, "eval_samples_per_second": 13.629, "eval_steps_per_second": 6.815, "step": 2 }, { "epoch": 0.000664415037927025, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0008858867172360335, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 480.5198, "step": 4 }, { "epoch": 0.0008858867172360335, "eval_loss": NaN, "eval_runtime": 612.6889, "eval_samples_per_second": 12.412, "eval_steps_per_second": 6.207, "step": 4 }, { "epoch": 0.0011073583965450417, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 63.2643, "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": 5750698952097792.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }