{ "best_metric": 0.8592572635193997, "best_model_checkpoint": "result/my-sup-simcse-roberta-large_filtered_final_nli_pos_neg", "epoch": 3.0, "global_step": 1542, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.05, "eval_avg_sts": 0.38903997598842077, "eval_sickr_spearman": 0.3422475345413293, "eval_stsb_spearman": 0.4358324174355123, "step": 25 }, { "epoch": 0.1, "eval_avg_sts": 0.7948315851126678, "eval_sickr_spearman": 0.7633529637036648, "eval_stsb_spearman": 0.8263102065216709, "step": 50 }, { "epoch": 0.15, "eval_avg_sts": 0.832614438173249, "eval_sickr_spearman": 0.8162565802271669, "eval_stsb_spearman": 0.848972296119331, "step": 75 }, { "epoch": 0.19, "eval_avg_sts": 0.837867574586473, "eval_sickr_spearman": 0.8242750363945497, "eval_stsb_spearman": 0.8514601127783963, "step": 100 }, { "epoch": 0.24, "eval_avg_sts": 0.8359050915516192, "eval_sickr_spearman": 0.8232498125343531, "eval_stsb_spearman": 0.8485603705688852, "step": 125 }, { "epoch": 0.29, "eval_avg_sts": 0.8396735422853538, "eval_sickr_spearman": 0.8239864175060081, "eval_stsb_spearman": 0.8553606670646995, "step": 150 }, { "epoch": 0.34, "eval_avg_sts": 0.8406033233672054, "eval_sickr_spearman": 0.8250130822992476, "eval_stsb_spearman": 0.8561935644351634, "step": 175 }, { "epoch": 0.39, "eval_avg_sts": 0.8400202980074645, "eval_sickr_spearman": 0.8286637822262545, "eval_stsb_spearman": 0.8513768137886746, "step": 200 }, { "epoch": 0.44, "eval_avg_sts": 0.8503413783622236, "eval_sickr_spearman": 0.8387088626877169, "eval_stsb_spearman": 0.8619738940367302, "step": 225 }, { "epoch": 0.49, "eval_avg_sts": 0.8511101105456758, "eval_sickr_spearman": 0.8356727207036109, "eval_stsb_spearman": 0.8665475003877408, "step": 250 }, { "epoch": 0.54, "eval_avg_sts": 0.8567862839908125, "eval_sickr_spearman": 0.8444381565605592, "eval_stsb_spearman": 0.8691344114210658, "step": 275 }, { "epoch": 0.58, "eval_avg_sts": 0.8538836668779227, "eval_sickr_spearman": 0.841704130204499, "eval_stsb_spearman": 0.8660632035513465, "step": 300 }, { "epoch": 0.63, "eval_avg_sts": 0.8545681159942804, "eval_sickr_spearman": 0.8441892593929071, "eval_stsb_spearman": 0.8649469725956536, "step": 325 }, { "epoch": 0.68, "eval_avg_sts": 0.8511207304405305, "eval_sickr_spearman": 0.8412596503917908, "eval_stsb_spearman": 0.8609818104892701, "step": 350 }, { "epoch": 0.73, "eval_avg_sts": 0.8536184034220342, "eval_sickr_spearman": 0.8376980001268504, "eval_stsb_spearman": 0.869538806717218, "step": 375 }, { "epoch": 0.78, "eval_avg_sts": 0.8525588625627976, "eval_sickr_spearman": 0.8385172185929789, "eval_stsb_spearman": 0.8666005065326163, "step": 400 }, { "epoch": 0.83, "eval_avg_sts": 0.855131044041153, "eval_sickr_spearman": 0.845190419671283, "eval_stsb_spearman": 0.8650716684110231, "step": 425 }, { "epoch": 0.88, "eval_avg_sts": 0.8541681429669479, "eval_sickr_spearman": 0.8433326727298597, "eval_stsb_spearman": 0.8650036132040362, "step": 450 }, { "epoch": 0.92, "eval_avg_sts": 0.8558873351170334, "eval_sickr_spearman": 0.8422996678312301, "eval_stsb_spearman": 0.8694750024028367, "step": 475 }, { "epoch": 0.97, "learning_rate": 6.7574578469520115e-06, "loss": 0.6522, "step": 500 }, { "epoch": 0.97, "eval_avg_sts": 0.8545521189776211, "eval_sickr_spearman": 0.8421153724950121, "eval_stsb_spearman": 0.8669888654602301, "step": 500 }, { "epoch": 1.02, "eval_avg_sts": 0.8572413202932077, "eval_sickr_spearman": 0.8456393663764249, "eval_stsb_spearman": 0.8688432742099903, "step": 525 }, { "epoch": 1.07, "eval_avg_sts": 0.8530206397139759, "eval_sickr_spearman": 0.8416999514986739, "eval_stsb_spearman": 0.8643413279292779, "step": 550 }, { "epoch": 1.12, "eval_avg_sts": 0.8539449812014897, "eval_sickr_spearman": 0.8428747442087487, "eval_stsb_spearman": 0.8650152181942306, "step": 575 }, { "epoch": 1.17, "eval_avg_sts": 0.8554613984004424, "eval_sickr_spearman": 0.8447085236305545, "eval_stsb_spearman": 0.8662142731703305, "step": 600 }, { "epoch": 1.22, "eval_avg_sts": 0.8558245678668116, "eval_sickr_spearman": 0.846121406510458, "eval_stsb_spearman": 0.8655277292231652, "step": 625 }, { "epoch": 1.26, "eval_avg_sts": 0.8548715982555288, "eval_sickr_spearman": 0.8424131172928271, "eval_stsb_spearman": 0.8673300792182305, "step": 650 }, { "epoch": 1.31, "eval_avg_sts": 0.8578462484095313, "eval_sickr_spearman": 0.8463831279821943, "eval_stsb_spearman": 0.8693093688368684, "step": 675 }, { "epoch": 1.36, "eval_avg_sts": 0.8569757520330985, "eval_sickr_spearman": 0.8444606831471337, "eval_stsb_spearman": 0.8694908209190633, "step": 700 }, { "epoch": 1.41, "eval_avg_sts": 0.8566543148971089, "eval_sickr_spearman": 0.8443323440440912, "eval_stsb_spearman": 0.8689762857501264, "step": 725 }, { "epoch": 1.46, "eval_avg_sts": 0.8559571122998568, "eval_sickr_spearman": 0.843302221011548, "eval_stsb_spearman": 0.8686120035881657, "step": 750 }, { "epoch": 1.51, "eval_avg_sts": 0.8564558623479355, "eval_sickr_spearman": 0.8421180142055913, "eval_stsb_spearman": 0.8707937104902796, "step": 775 }, { "epoch": 1.56, "eval_avg_sts": 0.858434934817754, "eval_sickr_spearman": 0.8465295267793775, "eval_stsb_spearman": 0.8703403428561304, "step": 800 }, { "epoch": 1.61, "eval_avg_sts": 0.8568722246962146, "eval_sickr_spearman": 0.8450603514485886, "eval_stsb_spearman": 0.8686840979438405, "step": 825 }, { "epoch": 1.65, "eval_avg_sts": 0.8549889262613304, "eval_sickr_spearman": 0.8409472080769357, "eval_stsb_spearman": 0.869030644445725, "step": 850 }, { "epoch": 1.7, "eval_avg_sts": 0.8573504810509991, "eval_sickr_spearman": 0.8454733228587534, "eval_stsb_spearman": 0.8692276392432446, "step": 875 }, { "epoch": 1.75, "eval_avg_sts": 0.8559678018004105, "eval_sickr_spearman": 0.8426885276284731, "eval_stsb_spearman": 0.869247075972348, "step": 900 }, { "epoch": 1.8, "eval_avg_sts": 0.8592572635193997, "eval_sickr_spearman": 0.8466042631732152, "eval_stsb_spearman": 0.8719102638655841, "step": 925 }, { "epoch": 1.85, "eval_avg_sts": 0.8565383373902099, "eval_sickr_spearman": 0.8425774316908469, "eval_stsb_spearman": 0.8704992430895729, "step": 950 }, { "epoch": 1.9, "eval_avg_sts": 0.8575761402637414, "eval_sickr_spearman": 0.843271529137729, "eval_stsb_spearman": 0.8718807513897538, "step": 975 }, { "epoch": 1.95, "learning_rate": 3.5149156939040206e-06, "loss": 0.2665, "step": 1000 }, { "epoch": 1.95, "eval_avg_sts": 0.8545158625377212, "eval_sickr_spearman": 0.842564943604473, "eval_stsb_spearman": 0.8664667814709694, "step": 1000 }, { "epoch": 1.99, "eval_avg_sts": 0.8591698955083712, "eval_sickr_spearman": 0.8463661249722851, "eval_stsb_spearman": 0.8719736660444573, "step": 1025 }, { "epoch": 2.04, "eval_avg_sts": 0.8581627640843799, "eval_sickr_spearman": 0.8440300843227411, "eval_stsb_spearman": 0.8722954438460186, "step": 1050 }, { "epoch": 2.09, "eval_avg_sts": 0.8582253078870739, "eval_sickr_spearman": 0.84485866885365, "eval_stsb_spearman": 0.8715919469204976, "step": 1075 }, { "epoch": 2.14, "eval_avg_sts": 0.8584444810228428, "eval_sickr_spearman": 0.8451566057758707, "eval_stsb_spearman": 0.8717323562698148, "step": 1100 }, { "epoch": 2.19, "eval_avg_sts": 0.8579360448028752, "eval_sickr_spearman": 0.845280862235291, "eval_stsb_spearman": 0.8705912273704595, "step": 1125 }, { "epoch": 2.24, "eval_avg_sts": 0.8587806706442964, "eval_sickr_spearman": 0.8453484900261158, "eval_stsb_spearman": 0.8722128512624772, "step": 1150 }, { "epoch": 2.29, "eval_avg_sts": 0.8587164541843216, "eval_sickr_spearman": 0.8441751862801856, "eval_stsb_spearman": 0.8732577220884576, "step": 1175 }, { "epoch": 2.33, "eval_avg_sts": 0.8553970686859056, "eval_sickr_spearman": 0.8400229936230637, "eval_stsb_spearman": 0.8707711437487474, "step": 1200 }, { "epoch": 2.38, "eval_avg_sts": 0.8582483701862629, "eval_sickr_spearman": 0.844513421296513, "eval_stsb_spearman": 0.8719833190760128, "step": 1225 }, { "epoch": 2.43, "eval_avg_sts": 0.8590849115354441, "eval_sickr_spearman": 0.8454768291291586, "eval_stsb_spearman": 0.8726929939417296, "step": 1250 }, { "epoch": 2.48, "eval_avg_sts": 0.8568280119545071, "eval_sickr_spearman": 0.8431880991145311, "eval_stsb_spearman": 0.870467924794483, "step": 1275 }, { "epoch": 2.53, "eval_avg_sts": 0.8571144935641057, "eval_sickr_spearman": 0.8426291131559942, "eval_stsb_spearman": 0.8715998739722173, "step": 1300 }, { "epoch": 2.58, "eval_avg_sts": 0.8560020316748019, "eval_sickr_spearman": 0.8417059073552523, "eval_stsb_spearman": 0.8702981559943516, "step": 1325 }, { "epoch": 2.63, "eval_avg_sts": 0.8565539872110424, "eval_sickr_spearman": 0.8419177245125944, "eval_stsb_spearman": 0.8711902499094905, "step": 1350 }, { "epoch": 2.68, "eval_avg_sts": 0.8583649723369124, "eval_sickr_spearman": 0.8444052552560741, "eval_stsb_spearman": 0.8723246894177509, "step": 1375 }, { "epoch": 2.72, "eval_avg_sts": 0.8579980787413095, "eval_sickr_spearman": 0.8443179827447611, "eval_stsb_spearman": 0.871678174737858, "step": 1400 }, { "epoch": 2.77, "eval_avg_sts": 0.8568025047431966, "eval_sickr_spearman": 0.8429390098224729, "eval_stsb_spearman": 0.8706659996639204, "step": 1425 }, { "epoch": 2.82, "eval_avg_sts": 0.8568593888645377, "eval_sickr_spearman": 0.8429925645005764, "eval_stsb_spearman": 0.8707262132284992, "step": 1450 }, { "epoch": 2.87, "eval_avg_sts": 0.8568385750256056, "eval_sickr_spearman": 0.8429098549439, "eval_stsb_spearman": 0.870767295107311, "step": 1475 }, { "epoch": 2.92, "learning_rate": 2.7237354085603116e-07, "loss": 0.2438, "step": 1500 }, { "epoch": 2.92, "eval_avg_sts": 0.8568328584730116, "eval_sickr_spearman": 0.8430229681877869, "eval_stsb_spearman": 0.8706427487582363, "step": 1500 }, { "epoch": 2.97, "eval_avg_sts": 0.8572096542762062, "eval_sickr_spearman": 0.8438662022046343, "eval_stsb_spearman": 0.8705531063477782, "step": 1525 }, { "epoch": 3.0, "step": 1542, "train_runtime": 3580.3029, "train_samples_per_second": 0.431 } ], "max_steps": 1542, "num_train_epochs": 3, "total_flos": 370635120359073792, "trial_name": null, "trial_params": null }