{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0002771618625277162, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 9.238728750923873e-05, "grad_norm": 1.9452441930770874, "learning_rate": 2e-05, "loss": 2.8965, "step": 1 }, { "epoch": 9.238728750923873e-05, "eval_loss": 2.72082257270813, "eval_runtime": 193.625, "eval_samples_per_second": 23.54, "eval_steps_per_second": 11.77, "step": 1 }, { "epoch": 0.00018477457501847746, "grad_norm": 1.5764484405517578, "learning_rate": 4e-05, "loss": 2.3501, "step": 2 }, { "epoch": 0.0002771618625277162, "grad_norm": 1.4889730215072632, "learning_rate": 6e-05, "loss": 2.3164, "step": 3 }, { "epoch": 0.0002771618625277162, "eval_loss": 2.713813066482544, "eval_runtime": 192.3994, "eval_samples_per_second": 23.69, "eval_steps_per_second": 11.845, "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 }