{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0009643201542912247, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003214400514304082, "grad_norm": 2.2572340965270996, "learning_rate": 2e-05, "loss": 8.2829, "step": 1 }, { "epoch": 0.0003214400514304082, "eval_loss": 2.0177955627441406, "eval_runtime": 60.9708, "eval_samples_per_second": 21.486, "eval_steps_per_second": 10.743, "step": 1 }, { "epoch": 0.0006428801028608164, "grad_norm": 2.169924736022949, "learning_rate": 4e-05, "loss": 7.2637, "step": 2 }, { "epoch": 0.0009643201542912247, "grad_norm": 1.8544375896453857, "learning_rate": 6e-05, "loss": 7.9408, "step": 3 }, { "epoch": 0.0009643201542912247, "eval_loss": 2.0139975547790527, "eval_runtime": 59.6992, "eval_samples_per_second": 21.943, "eval_steps_per_second": 10.972, "step": 3 } ], "logging_steps": 1, "max_steps": 10, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 3, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 1212442277314560.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }