{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.029928057553956836, "eval_steps": 10, "global_step": 26, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0011510791366906475, "eval_loss": NaN, "eval_runtime": 19.145, "eval_samples_per_second": 19.117, "eval_steps_per_second": 9.559, "step": 1 }, { "epoch": 0.0057553956834532375, "grad_norm": NaN, "learning_rate": 5e-05, "loss": 0.0, "step": 5 }, { "epoch": 0.011510791366906475, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 10 }, { "epoch": 0.011510791366906475, "eval_loss": NaN, "eval_runtime": 18.0771, "eval_samples_per_second": 20.247, "eval_steps_per_second": 10.123, "step": 10 }, { "epoch": 0.017266187050359712, "grad_norm": NaN, "learning_rate": 9.619397662556435e-05, "loss": 0.0, "step": 15 }, { "epoch": 0.02302158273381295, "grad_norm": NaN, "learning_rate": 8.535533905932738e-05, "loss": 0.0, "step": 20 }, { "epoch": 0.02302158273381295, "eval_loss": NaN, "eval_runtime": 18.2152, "eval_samples_per_second": 20.093, "eval_steps_per_second": 10.047, "step": 20 }, { "epoch": 0.02877697841726619, "grad_norm": NaN, "learning_rate": 6.91341716182545e-05, "loss": 1.2632, "step": 25 } ], "logging_steps": 5, "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": 3260792854020096.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }