{ "best_metric": 0.06852502375841141, "best_model_checkpoint": "/content/cyner_deberta/checkpoint-1000", "epoch": 10.0, "eval_steps": 500, "global_step": 3520, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 1.42, "learning_rate": 1.715909090909091e-05, "loss": 0.1285, "step": 500 }, { "epoch": 1.42, "eval_accuracy": 0.982345393892738, "eval_f1": 0.7652068126520681, "eval_loss": 0.0761805921792984, "eval_precision": 0.7305458768873403, "eval_recall": 0.8033205619412516, "eval_runtime": 4.9018, "eval_samples_per_second": 165.652, "eval_steps_per_second": 20.809, "step": 500 }, { "epoch": 2.84, "learning_rate": 1.431818181818182e-05, "loss": 0.041, "step": 1000 }, { "epoch": 2.84, "eval_accuracy": 0.9838850397741853, "eval_f1": 0.7952410770194114, "eval_loss": 0.06852502375841141, "eval_precision": 0.7800982800982801, "eval_recall": 0.8109833971902938, "eval_runtime": 4.9191, "eval_samples_per_second": 165.071, "eval_steps_per_second": 20.735, "step": 1000 }, { "epoch": 4.26, "learning_rate": 1.1477272727272729e-05, "loss": 0.024, "step": 1500 }, { "epoch": 4.26, "eval_accuracy": 0.9855273287143956, "eval_f1": 0.7982176957352005, "eval_loss": 0.07960831373929977, "eval_precision": 0.7956852791878173, "eval_recall": 0.8007662835249042, "eval_runtime": 5.1215, "eval_samples_per_second": 158.547, "eval_steps_per_second": 19.916, "step": 1500 }, { "epoch": 5.68, "learning_rate": 8.636363636363637e-06, "loss": 0.0156, "step": 2000 }, { "epoch": 5.68, "eval_accuracy": 0.9858352578906852, "eval_f1": 0.8049689440993788, "eval_loss": 0.07465782761573792, "eval_precision": 0.7835550181378477, "eval_recall": 0.8275862068965517, "eval_runtime": 4.9527, "eval_samples_per_second": 163.952, "eval_steps_per_second": 20.595, "step": 2000 }, { "epoch": 7.1, "learning_rate": 5.795454545454546e-06, "loss": 0.0106, "step": 2500 }, { "epoch": 7.1, "eval_accuracy": 0.9859379009494483, "eval_f1": 0.8139825218476903, "eval_loss": 0.08166122436523438, "eval_precision": 0.796092796092796, "eval_recall": 0.8326947637292464, "eval_runtime": 4.9286, "eval_samples_per_second": 164.753, "eval_steps_per_second": 20.696, "step": 2500 }, { "epoch": 8.52, "learning_rate": 2.954545454545455e-06, "loss": 0.0064, "step": 3000 }, { "epoch": 8.52, "eval_accuracy": 0.9864511162432641, "eval_f1": 0.8178438661710037, "eval_loss": 0.08277998119592667, "eval_precision": 0.7942238267148014, "eval_recall": 0.842911877394636, "eval_runtime": 4.9237, "eval_samples_per_second": 164.917, "eval_steps_per_second": 20.716, "step": 3000 }, { "epoch": 9.94, "learning_rate": 1.1363636363636364e-07, "loss": 0.0049, "step": 3500 }, { "epoch": 9.94, "eval_accuracy": 0.9865024377726457, "eval_f1": 0.8159700561447287, "eval_loss": 0.0857752189040184, "eval_precision": 0.7975609756097561, "eval_recall": 0.8352490421455939, "eval_runtime": 5.5982, "eval_samples_per_second": 145.045, "eval_steps_per_second": 18.22, "step": 3500 }, { "epoch": 10.0, "step": 3520, "total_flos": 1097378896882380.0, "train_loss": 0.03283687870610844, "train_runtime": 907.3969, "train_samples_per_second": 30.968, "train_steps_per_second": 3.879 } ], "logging_steps": 500, "max_steps": 3520, "num_train_epochs": 10, "save_steps": 500, "total_flos": 1097378896882380.0, "trial_name": null, "trial_params": null }