{ "best_metric": 0.5364909768104553, "best_model_checkpoint": "autotrain-ecb-uncertainty-deberta-v3-large/checkpoint-120", "epoch": 1.0, "eval_steps": 500, "global_step": 120, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05, "grad_norm": 4.925415992736816, "learning_rate": 1.6666666666666667e-06, "loss": 0.7077, "step": 6 }, { "epoch": 0.1, "grad_norm": 4.121665954589844, "learning_rate": 3.3333333333333333e-06, "loss": 0.6967, "step": 12 }, { "epoch": 0.15, "grad_norm": 3.579362630844116, "learning_rate": 5e-06, "loss": 0.6732, "step": 18 }, { "epoch": 0.2, "grad_norm": 3.409770965576172, "learning_rate": 6.666666666666667e-06, "loss": 0.6812, "step": 24 }, { "epoch": 0.25, "grad_norm": 3.262946128845215, "learning_rate": 8.333333333333334e-06, "loss": 0.7021, "step": 30 }, { "epoch": 0.3, "grad_norm": 1.882023572921753, "learning_rate": 1e-05, "loss": 0.6861, "step": 36 }, { "epoch": 0.35, "grad_norm": 2.0393922328948975, "learning_rate": 9.814814814814815e-06, "loss": 0.6689, "step": 42 }, { "epoch": 0.4, "grad_norm": 2.3638412952423096, "learning_rate": 9.62962962962963e-06, "loss": 0.6781, "step": 48 }, { "epoch": 0.45, "grad_norm": 1.785644769668579, "learning_rate": 9.444444444444445e-06, "loss": 0.6817, "step": 54 }, { "epoch": 0.5, "grad_norm": 5.820407390594482, "learning_rate": 9.25925925925926e-06, "loss": 0.63, "step": 60 }, { "epoch": 0.55, "grad_norm": 2.0294086933135986, "learning_rate": 9.074074074074075e-06, "loss": 0.629, "step": 66 }, { "epoch": 0.6, "grad_norm": 7.212940692901611, "learning_rate": 8.888888888888888e-06, "loss": 0.7502, "step": 72 }, { "epoch": 0.65, "grad_norm": 5.35235071182251, "learning_rate": 8.703703703703705e-06, "loss": 0.6315, "step": 78 }, { "epoch": 0.7, "grad_norm": 3.978393077850342, "learning_rate": 8.518518518518519e-06, "loss": 0.6373, "step": 84 }, { "epoch": 0.75, "grad_norm": 6.702513694763184, "learning_rate": 8.333333333333334e-06, "loss": 0.573, "step": 90 }, { "epoch": 0.8, "grad_norm": 10.61103630065918, "learning_rate": 8.148148148148148e-06, "loss": 0.6378, "step": 96 }, { "epoch": 0.85, "grad_norm": 8.387734413146973, "learning_rate": 7.962962962962963e-06, "loss": 0.4785, "step": 102 }, { "epoch": 0.9, "grad_norm": 10.877920150756836, "learning_rate": 7.808641975308642e-06, "loss": 0.5362, "step": 108 }, { "epoch": 0.95, "grad_norm": 8.344444274902344, "learning_rate": 7.623456790123458e-06, "loss": 0.6228, "step": 114 }, { "epoch": 1.0, "grad_norm": 4.364614009857178, "learning_rate": 7.438271604938272e-06, "loss": 0.5578, "step": 120 }, { "epoch": 1.0, "eval_accuracy": 0.7566666666666667, "eval_auc": 0.8095903592375367, "eval_f1": 0.7044534412955465, "eval_loss": 0.5364909768104553, "eval_precision": 0.7073170731707317, "eval_recall": 0.7016129032258065, "eval_runtime": 2.8168, "eval_samples_per_second": 106.505, "eval_steps_per_second": 5.325, "step": 120 } ], "logging_steps": 6, "max_steps": 360, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "stateful_callbacks": { "EarlyStoppingCallback": { "args": { "early_stopping_patience": 5, "early_stopping_threshold": 0.01 }, "attributes": { "early_stopping_patience_counter": 0 } }, "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 559162592870400.0, "train_batch_size": 10, "trial_name": null, "trial_params": null }