{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.00046511627906976747, "eval_steps": 3, "global_step": 3, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0001550387596899225, "grad_norm": 0.6437714695930481, "learning_rate": 2e-05, "loss": 1.2098, "step": 1 }, { "epoch": 0.0001550387596899225, "eval_loss": 1.2846004962921143, "eval_runtime": 144.5256, "eval_samples_per_second": 18.793, "eval_steps_per_second": 9.396, "step": 1 }, { "epoch": 0.000310077519379845, "grad_norm": 0.5917322635650635, "learning_rate": 4e-05, "loss": 1.1567, "step": 2 }, { "epoch": 0.00046511627906976747, "grad_norm": 0.6734963655471802, "learning_rate": 6e-05, "loss": 1.1999, "step": 3 }, { "epoch": 0.00046511627906976747, "eval_loss": 1.2787954807281494, "eval_runtime": 140.0314, "eval_samples_per_second": 19.396, "eval_steps_per_second": 9.698, "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": 1017260336480256.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }