{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9473684210526314, "eval_steps": 500, "global_step": 42, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.7017543859649122, "grad_norm": 16.393852597636165, "learning_rate": 5e-06, "loss": 1.1132, "step": 10 }, { "epoch": 0.9824561403508771, "eval_loss": 1.012129306793213, "eval_runtime": 15.1228, "eval_samples_per_second": 25.326, "eval_steps_per_second": 0.397, "step": 14 }, { "epoch": 1.4035087719298245, "grad_norm": 2.5938261902095183, "learning_rate": 5e-06, "loss": 1.0732, "step": 20 }, { "epoch": 1.9649122807017543, "eval_loss": 0.9422828555107117, "eval_runtime": 15.0756, "eval_samples_per_second": 25.405, "eval_steps_per_second": 0.398, "step": 28 }, { "epoch": 2.1052631578947367, "grad_norm": 2.090076312551718, "learning_rate": 5e-06, "loss": 1.0059, "step": 30 }, { "epoch": 2.807017543859649, "grad_norm": 1.336744771215339, "learning_rate": 5e-06, "loss": 0.8793, "step": 40 }, { "epoch": 2.9473684210526314, "eval_loss": 0.91075199842453, "eval_runtime": 14.4837, "eval_samples_per_second": 26.444, "eval_steps_per_second": 0.414, "step": 42 }, { "epoch": 2.9473684210526314, "step": 42, "total_flos": 70142184652800.0, "train_loss": 1.0100621836526054, "train_runtime": 2763.4228, "train_samples_per_second": 7.884, "train_steps_per_second": 0.015 } ], "logging_steps": 10, "max_steps": 42, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 70142184652800.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }