{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.007665772326561901, "eval_steps": 8, "global_step": 10, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0007665772326561902, "eval_loss": 1.4402562379837036, "eval_runtime": 111.3354, "eval_samples_per_second": 4.94, "eval_steps_per_second": 2.47, "step": 1 }, { "epoch": 0.0022997316979685703, "grad_norm": 2.2092761993408203, "learning_rate": 6e-05, "loss": 5.8138, "step": 3 }, { "epoch": 0.0045994633959371405, "grad_norm": 1.861556887626648, "learning_rate": 0.00012, "loss": 5.6808, "step": 6 }, { "epoch": 0.006132617861249521, "eval_loss": 1.2501766681671143, "eval_runtime": 112.2324, "eval_samples_per_second": 4.901, "eval_steps_per_second": 2.45, "step": 8 }, { "epoch": 0.006899195093905711, "grad_norm": 2.0317749977111816, "learning_rate": 0.00018, "loss": 5.2817, "step": 9 } ], "logging_steps": 3, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 10, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1842091508367360.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }