| { | |
| "best_metric": 0.7976659536361694, | |
| "best_model_checkpoint": "sbert-ru-huawei-rureviews-no-duplicates/checkpoint-589", | |
| "epoch": 0.9987282746926663, | |
| "eval_steps": 500, | |
| "global_step": 589, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0423908435777872, | |
| "grad_norm": 18.781570434570312, | |
| "learning_rate": 7.062146892655368e-06, | |
| "loss": 1.5601, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0847816871555744, | |
| "grad_norm": 12.51102066040039, | |
| "learning_rate": 1.4124293785310736e-05, | |
| "loss": 1.0521, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1271725307333616, | |
| "grad_norm": 24.600730895996094, | |
| "learning_rate": 2.1186440677966103e-05, | |
| "loss": 0.8671, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.1695633743111488, | |
| "grad_norm": 14.450693130493164, | |
| "learning_rate": 2.8248587570621472e-05, | |
| "loss": 0.8607, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21195421788893598, | |
| "grad_norm": 15.730051040649414, | |
| "learning_rate": 3.531073446327684e-05, | |
| "loss": 0.8658, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.2543450614667232, | |
| "grad_norm": 15.596332550048828, | |
| "learning_rate": 4.2372881355932206e-05, | |
| "loss": 0.8358, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.29673590504451036, | |
| "grad_norm": 14.379067420959473, | |
| "learning_rate": 4.9435028248587575e-05, | |
| "loss": 0.8535, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.3391267486222976, | |
| "grad_norm": 14.174772262573242, | |
| "learning_rate": 4.927672955974843e-05, | |
| "loss": 0.8428, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.3815175922000848, | |
| "grad_norm": 15.868408203125, | |
| "learning_rate": 4.849056603773585e-05, | |
| "loss": 0.8436, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.42390843577787196, | |
| "grad_norm": 12.947571754455566, | |
| "learning_rate": 4.7704402515723276e-05, | |
| "loss": 0.8498, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.4662992793556592, | |
| "grad_norm": 12.922489166259766, | |
| "learning_rate": 4.691823899371069e-05, | |
| "loss": 0.8728, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.5086901229334464, | |
| "grad_norm": 16.116744995117188, | |
| "learning_rate": 4.616352201257862e-05, | |
| "loss": 0.8058, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5510809665112336, | |
| "grad_norm": 13.213577270507812, | |
| "learning_rate": 4.537735849056604e-05, | |
| "loss": 0.8092, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.5934718100890207, | |
| "grad_norm": 13.749724388122559, | |
| "learning_rate": 4.459119496855346e-05, | |
| "loss": 0.8277, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.6358626536668079, | |
| "grad_norm": 14.099920272827148, | |
| "learning_rate": 4.3805031446540885e-05, | |
| "loss": 0.8172, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.6782534972445952, | |
| "grad_norm": 11.363203048706055, | |
| "learning_rate": 4.301886792452831e-05, | |
| "loss": 0.8397, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.7206443408223824, | |
| "grad_norm": 13.129080772399902, | |
| "learning_rate": 4.2232704402515726e-05, | |
| "loss": 0.8768, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.7630351844001696, | |
| "grad_norm": 13.105059623718262, | |
| "learning_rate": 4.1477987421383654e-05, | |
| "loss": 0.8453, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.8054260279779568, | |
| "grad_norm": 17.31393814086914, | |
| "learning_rate": 4.069182389937107e-05, | |
| "loss": 0.8207, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.8478168715557439, | |
| "grad_norm": 15.73338794708252, | |
| "learning_rate": 3.9905660377358494e-05, | |
| "loss": 0.8093, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.8902077151335311, | |
| "grad_norm": 10.630894660949707, | |
| "learning_rate": 3.911949685534592e-05, | |
| "loss": 0.7984, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.9325985587113184, | |
| "grad_norm": 14.764472961425781, | |
| "learning_rate": 3.8333333333333334e-05, | |
| "loss": 0.7914, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.9749894022891056, | |
| "grad_norm": 14.726776123046875, | |
| "learning_rate": 3.754716981132076e-05, | |
| "loss": 0.7818, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.9987282746926663, | |
| "eval_accuracy": 0.6771595124536302, | |
| "eval_f1_macro": 0.47781142535236576, | |
| "eval_f1_micro": 0.6771595124536302, | |
| "eval_f1_weighted": 0.6542674498710257, | |
| "eval_loss": 0.7976659536361694, | |
| "eval_precision_macro": 0.6650293707575838, | |
| "eval_precision_micro": 0.6771595124536302, | |
| "eval_precision_weighted": 0.6930699230580497, | |
| "eval_recall_macro": 0.5021643205507915, | |
| "eval_recall_micro": 0.6771595124536302, | |
| "eval_recall_weighted": 0.6771595124536302, | |
| "eval_runtime": 60.5427, | |
| "eval_samples_per_second": 155.84, | |
| "eval_steps_per_second": 4.873, | |
| "step": 589 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1767, | |
| "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": 1.7587586671312896e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |