{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0009354536950420954, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0003118178983473651, "grad_norm": 0.6566165685653687, "learning_rate": 2e-05, "loss": 1.8957, "step": 1 }, { "epoch": 0.0003118178983473651, "eval_loss": 1.8035469055175781, "eval_runtime": 57.7332, "eval_samples_per_second": 23.401, "eval_steps_per_second": 11.709, "step": 1 }, { "epoch": 0.0006236357966947302, "grad_norm": 0.7361301183700562, "learning_rate": 4e-05, "loss": 1.8645, "step": 2 }, { "epoch": 0.0009354536950420954, "grad_norm": 0.5800981521606445, "learning_rate": 6e-05, "loss": 1.7754, "step": 3 }, { "epoch": 0.0009354536950420954, "eval_loss": 1.79875910282135, "eval_runtime": 55.7045, "eval_samples_per_second": 24.253, "eval_steps_per_second": 12.135, "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": 786064805462016.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }