{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0013686911890504706, "eval_steps": 2, "global_step": 5, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0002737382378100941, "grad_norm": NaN, "learning_rate": 1e-05, "loss": 0.0, "step": 1 }, { "epoch": 0.0002737382378100941, "eval_loss": NaN, "eval_runtime": 409.9835, "eval_samples_per_second": 15.008, "eval_steps_per_second": 7.505, "step": 1 }, { "epoch": 0.0005474764756201882, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 2 }, { "epoch": 0.0005474764756201882, "eval_loss": NaN, "eval_runtime": 202.0635, "eval_samples_per_second": 30.451, "eval_steps_per_second": 15.228, "step": 2 }, { "epoch": 0.0008212147134302823, "grad_norm": NaN, "learning_rate": 3e-05, "loss": 0.0, "step": 3 }, { "epoch": 0.0010949529512403763, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.0010949529512403763, "eval_loss": NaN, "eval_runtime": 202.6282, "eval_samples_per_second": 30.366, "eval_steps_per_second": 15.185, "step": 4 }, { "epoch": 0.0013686911890504706, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "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": 1837066396631040.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }