| { | |
| "best_metric": 0.8778576539129843, | |
| "best_model_checkpoint": "./fields_classification/checkpoint-4610", | |
| "epoch": 9.98916576381365, | |
| "eval_steps": 500, | |
| "global_step": 4610, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.1747, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.38636055803873764, | |
| "eval_f1": 0.5336014591030258, | |
| "eval_loss": 0.08355075865983963, | |
| "eval_precision": 0.8621731902674928, | |
| "eval_recall": 0.38636055803873764, | |
| "eval_roc_auc": 0.6919450088040092, | |
| "eval_runtime": 116.991, | |
| "eval_samples_per_second": 126.215, | |
| "eval_steps_per_second": 1.975, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0684, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.769944467018827, | |
| "eval_f1": 0.8073713737883038, | |
| "eval_loss": 0.05430687218904495, | |
| "eval_precision": 0.8486228260058222, | |
| "eval_recall": 0.769944467018827, | |
| "eval_roc_auc": 0.8822253826357849, | |
| "eval_runtime": 117.0652, | |
| "eval_samples_per_second": 126.135, | |
| "eval_steps_per_second": 1.973, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0498, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8040769334958688, | |
| "eval_f1": 0.8276895206243033, | |
| "eval_loss": 0.04519835114479065, | |
| "eval_precision": 0.8522743578705697, | |
| "eval_recall": 0.8044832723825004, | |
| "eval_roc_auc": 0.8994527969660029, | |
| "eval_runtime": 116.7477, | |
| "eval_samples_per_second": 126.478, | |
| "eval_steps_per_second": 1.979, | |
| "step": 1384 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0407, | |
| "step": 1846 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8289990518759311, | |
| "eval_f1": 0.8456551724137932, | |
| "eval_loss": 0.039659492671489716, | |
| "eval_precision": 0.8614584796965014, | |
| "eval_recall": 0.8304212379791412, | |
| "eval_roc_auc": 0.9125396180414465, | |
| "eval_runtime": 117.5369, | |
| "eval_samples_per_second": 125.629, | |
| "eval_steps_per_second": 1.965, | |
| "step": 1846 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.035, | |
| "step": 2307 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8405119869971557, | |
| "eval_f1": 0.8543429844097995, | |
| "eval_loss": 0.03649652376770973, | |
| "eval_precision": 0.8646230667868784, | |
| "eval_recall": 0.8443044832723825, | |
| "eval_roc_auc": 0.919508329947176, | |
| "eval_runtime": 117.0597, | |
| "eval_samples_per_second": 126.141, | |
| "eval_steps_per_second": 1.973, | |
| "step": 2307 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0303, | |
| "step": 2769 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8518217526750643, | |
| "eval_f1": 0.8653773746363169, | |
| "eval_loss": 0.0338783822953701, | |
| "eval_precision": 0.8748702332341338, | |
| "eval_recall": 0.8560883109846946, | |
| "eval_roc_auc": 0.9255952864689151, | |
| "eval_runtime": 116.7614, | |
| "eval_samples_per_second": 126.463, | |
| "eval_steps_per_second": 1.978, | |
| "step": 2769 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0268, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8566300961668698, | |
| "eval_f1": 0.8697338868849113, | |
| "eval_loss": 0.03237078711390495, | |
| "eval_precision": 0.8740766073871409, | |
| "eval_recall": 0.865434105377218, | |
| "eval_roc_auc": 0.9302234863876474, | |
| "eval_runtime": 117.0283, | |
| "eval_samples_per_second": 126.175, | |
| "eval_steps_per_second": 1.974, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0237, | |
| "step": 3692 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8580522822700799, | |
| "eval_f1": 0.8707677634716261, | |
| "eval_loss": 0.03161860257387161, | |
| "eval_precision": 0.8759594298245614, | |
| "eval_recall": 0.8656372748205337, | |
| "eval_roc_auc": 0.9303670594609237, | |
| "eval_runtime": 116.6155, | |
| "eval_samples_per_second": 126.621, | |
| "eval_steps_per_second": 1.981, | |
| "step": 3692 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0211, | |
| "step": 4153 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.8651632127861303, | |
| "eval_f1": 0.8777002891648241, | |
| "eval_loss": 0.030687741935253143, | |
| "eval_precision": 0.8818101032196323, | |
| "eval_recall": 0.8736286062576188, | |
| "eval_roc_auc": 0.9344724366788568, | |
| "eval_runtime": 116.7518, | |
| "eval_samples_per_second": 126.473, | |
| "eval_steps_per_second": 1.979, | |
| "step": 4153 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0188, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 9.99, | |
| "eval_accuracy": 0.8656372748205337, | |
| "eval_f1": 0.8778576539129843, | |
| "eval_loss": 0.03020327538251877, | |
| "eval_precision": 0.8833047651696949, | |
| "eval_recall": 0.8724773127454964, | |
| "eval_roc_auc": 0.9339333604225925, | |
| "eval_runtime": 117.271, | |
| "eval_samples_per_second": 125.914, | |
| "eval_steps_per_second": 1.97, | |
| "step": 4610 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 4610, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.5527107913529754e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |