{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 30, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.03333333333333333, "grad_norm": 2887.1779646766117, "learning_rate": 6.666666666666667e-06, "loss": 51.8008, "step": 1 }, { "epoch": 0.16666666666666666, "grad_norm": 160.2012999619403, "learning_rate": 1.973044870579824e-05, "loss": 35.3031, "step": 5 }, { "epoch": 0.3333333333333333, "grad_norm": 174.9205998746732, "learning_rate": 1.686241637868734e-05, "loss": 23.3777, "step": 10 }, { "epoch": 0.5, "grad_norm": 59.723271817506884, "learning_rate": 1.1736481776669307e-05, "loss": 4.8098, "step": 15 }, { "epoch": 0.6666666666666666, "grad_norm": 59.24049980030896, "learning_rate": 6.039202339608432e-06, "loss": 3.6963, "step": 20 }, { "epoch": 0.8333333333333334, "grad_norm": 24.651667124483836, "learning_rate": 1.6451218858706374e-06, "loss": 2.7203, "step": 25 }, { "epoch": 1.0, "grad_norm": 8.885240913602228, "learning_rate": 0.0, "loss": 2.3447, "step": 30 }, { "epoch": 1.0, "eval_loss": 2.876784563064575, "eval_runtime": 0.8467, "eval_samples_per_second": 4.724, "eval_steps_per_second": 1.181, "step": 30 }, { "epoch": 1.0, "step": 30, "total_flos": 8193589641216.0, "train_loss": 12.591909694671632, "train_runtime": 386.7747, "train_samples_per_second": 39.579, "train_steps_per_second": 0.078 } ], "logging_steps": 5, "max_steps": 30, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": false, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8193589641216.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }