{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.0002742815347575656, "eval_steps": 3, "global_step": 9, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 3.0475726084173955e-05, "grad_norm": NaN, "learning_rate": 2e-05, "loss": 0.0, "step": 1 }, { "epoch": 3.0475726084173955e-05, "eval_loss": NaN, "eval_runtime": 469.0526, "eval_samples_per_second": 29.455, "eval_steps_per_second": 14.728, "step": 1 }, { "epoch": 6.095145216834791e-05, "grad_norm": NaN, "learning_rate": 4e-05, "loss": 0.0, "step": 2 }, { "epoch": 9.142717825252186e-05, "grad_norm": NaN, "learning_rate": 6e-05, "loss": 0.0, "step": 3 }, { "epoch": 9.142717825252186e-05, "eval_loss": NaN, "eval_runtime": 467.7547, "eval_samples_per_second": 29.537, "eval_steps_per_second": 14.768, "step": 3 }, { "epoch": 0.00012190290433669582, "grad_norm": NaN, "learning_rate": 8e-05, "loss": 0.0, "step": 4 }, { "epoch": 0.00015237863042086977, "grad_norm": NaN, "learning_rate": 0.0001, "loss": 0.0, "step": 5 }, { "epoch": 0.00018285435650504373, "grad_norm": NaN, "learning_rate": 0.00012, "loss": 0.0, "step": 6 }, { "epoch": 0.00018285435650504373, "eval_loss": NaN, "eval_runtime": 467.8566, "eval_samples_per_second": 29.53, "eval_steps_per_second": 14.765, "step": 6 }, { "epoch": 0.00021333008258921768, "grad_norm": NaN, "learning_rate": 0.00014, "loss": 0.0, "step": 7 }, { "epoch": 0.00024380580867339164, "grad_norm": NaN, "learning_rate": 0.00016, "loss": 0.0, "step": 8 }, { "epoch": 0.0002742815347575656, "grad_norm": NaN, "learning_rate": 0.00018, "loss": 0.0, "step": 9 }, { "epoch": 0.0002742815347575656, "eval_loss": NaN, "eval_runtime": 467.9084, "eval_samples_per_second": 29.527, "eval_steps_per_second": 14.764, "step": 9 } ], "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": 2091163255308288.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }