{ "best_metric": 0.8561129573607319, "best_model_checkpoint": "result/my-unsup-simcse-roberta-large-d0.1-rs192-std0.5-t0.05", "epoch": 1.0, "global_step": 7813, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02, "eval_avg_sts": 0.778341475975213, "eval_sickr_spearman": 0.7418720622385991, "eval_stsb_spearman": 0.8148108897118267, "step": 125 }, { "epoch": 0.03, "eval_avg_sts": 0.7780892042897212, "eval_sickr_spearman": 0.7348078399634872, "eval_stsb_spearman": 0.8213705686159553, "step": 250 }, { "epoch": 0.05, "eval_avg_sts": 0.7907877208360297, "eval_sickr_spearman": 0.7455401974554278, "eval_stsb_spearman": 0.8360352442166316, "step": 375 }, { "epoch": 0.06, "learning_rate": 1.872008191475746e-05, "loss": 0.1943, "step": 500 }, { "epoch": 0.06, "eval_avg_sts": 0.7955144537705907, "eval_sickr_spearman": 0.753126085523259, "eval_stsb_spearman": 0.8379028220179224, "step": 500 }, { "epoch": 0.08, "eval_avg_sts": 0.7917299175053137, "eval_sickr_spearman": 0.747866055511467, "eval_stsb_spearman": 0.8355937794991605, "step": 625 }, { "epoch": 0.1, "eval_avg_sts": 0.8016064223978117, "eval_sickr_spearman": 0.7573344745690636, "eval_stsb_spearman": 0.8458783702265597, "step": 750 }, { "epoch": 0.11, "eval_avg_sts": 0.8037483952735749, "eval_sickr_spearman": 0.7601063676756831, "eval_stsb_spearman": 0.8473904228714668, "step": 875 }, { "epoch": 0.13, "learning_rate": 1.7440163829514915e-05, "loss": 0.0005, "step": 1000 }, { "epoch": 0.13, "eval_avg_sts": 0.7957627833498355, "eval_sickr_spearman": 0.7503112228234783, "eval_stsb_spearman": 0.8412143438761926, "step": 1000 }, { "epoch": 0.14, "eval_avg_sts": 0.7961233391304097, "eval_sickr_spearman": 0.7518578723208871, "eval_stsb_spearman": 0.8403888059399321, "step": 1125 }, { "epoch": 0.16, "eval_avg_sts": 0.8051272481365592, "eval_sickr_spearman": 0.7633100719300806, "eval_stsb_spearman": 0.8469444243430378, "step": 1250 }, { "epoch": 0.18, "eval_avg_sts": 0.8057468354082986, "eval_sickr_spearman": 0.7553807134558654, "eval_stsb_spearman": 0.8561129573607319, "step": 1375 }, { "epoch": 0.19, "learning_rate": 1.616024574427237e-05, "loss": 0.0004, "step": 1500 }, { "epoch": 0.19, "eval_avg_sts": 0.8123723555741679, "eval_sickr_spearman": 0.7723355962013163, "eval_stsb_spearman": 0.8524091149470194, "step": 1500 }, { "epoch": 0.21, "eval_avg_sts": 0.8035895611478845, "eval_sickr_spearman": 0.7606879100092697, "eval_stsb_spearman": 0.8464912122864992, "step": 1625 }, { "epoch": 0.22, "eval_avg_sts": 0.7991717974519061, "eval_sickr_spearman": 0.7465859786270398, "eval_stsb_spearman": 0.8517576162767726, "step": 1750 }, { "epoch": 0.24, "eval_avg_sts": 0.7964600696271789, "eval_sickr_spearman": 0.7422818155649676, "eval_stsb_spearman": 0.8506383236893902, "step": 1875 }, { "epoch": 0.26, "learning_rate": 1.4880327659029823e-05, "loss": 0.0007, "step": 2000 }, { "epoch": 0.26, "eval_avg_sts": 0.8044429784441518, "eval_sickr_spearman": 0.7591500982345256, "eval_stsb_spearman": 0.8497358586537781, "step": 2000 }, { "epoch": 0.27, "eval_avg_sts": 0.80058268060333, "eval_sickr_spearman": 0.7487337853900479, "eval_stsb_spearman": 0.8524315758166123, "step": 2125 }, { "epoch": 0.29, "eval_avg_sts": 0.8019106027671927, "eval_sickr_spearman": 0.7506407822258964, "eval_stsb_spearman": 0.853180423308489, "step": 2250 }, { "epoch": 0.3, "eval_avg_sts": 0.8040000758463681, "eval_sickr_spearman": 0.7559858573028843, "eval_stsb_spearman": 0.852014294389852, "step": 2375 }, { "epoch": 0.32, "learning_rate": 1.3600409573787278e-05, "loss": 0.0004, "step": 2500 }, { "epoch": 0.32, "eval_avg_sts": 0.8026474310995677, "eval_sickr_spearman": 0.7573420154519893, "eval_stsb_spearman": 0.847952846747146, "step": 2500 }, { "epoch": 0.34, "eval_avg_sts": 0.7924131853036531, "eval_sickr_spearman": 0.7428461810068655, "eval_stsb_spearman": 0.8419801896004406, "step": 2625 }, { "epoch": 0.35, "eval_avg_sts": 0.7950751062581133, "eval_sickr_spearman": 0.7408404502419113, "eval_stsb_spearman": 0.8493097622743153, "step": 2750 }, { "epoch": 0.37, "eval_avg_sts": 0.7999799876999598, "eval_sickr_spearman": 0.749456173155677, "eval_stsb_spearman": 0.8505038022442425, "step": 2875 }, { "epoch": 0.38, "learning_rate": 1.2320491488544735e-05, "loss": 0.0004, "step": 3000 }, { "epoch": 0.38, "eval_avg_sts": 0.7937458509139534, "eval_sickr_spearman": 0.7430877294159979, "eval_stsb_spearman": 0.8444039724119089, "step": 3000 }, { "epoch": 0.4, "eval_avg_sts": 0.7856063441760408, "eval_sickr_spearman": 0.7330642149190809, "eval_stsb_spearman": 0.8381484734330007, "step": 3125 }, { "epoch": 0.42, "eval_avg_sts": 0.7909319347148922, "eval_sickr_spearman": 0.7362177449151016, "eval_stsb_spearman": 0.8456461245146829, "step": 3250 }, { "epoch": 0.43, "eval_avg_sts": 0.7875482454299103, "eval_sickr_spearman": 0.7297334021276521, "eval_stsb_spearman": 0.8453630887321684, "step": 3375 }, { "epoch": 0.45, "learning_rate": 1.104057340330219e-05, "loss": 0.0004, "step": 3500 }, { "epoch": 0.45, "eval_avg_sts": 0.7857444621535814, "eval_sickr_spearman": 0.7371294712825999, "eval_stsb_spearman": 0.8343594530245628, "step": 3500 }, { "epoch": 0.46, "eval_avg_sts": 0.790497235297885, "eval_sickr_spearman": 0.7411372344176974, "eval_stsb_spearman": 0.8398572361780724, "step": 3625 }, { "epoch": 0.48, "eval_avg_sts": 0.7912227836878545, "eval_sickr_spearman": 0.7381786146313126, "eval_stsb_spearman": 0.8442669527443964, "step": 3750 }, { "epoch": 0.5, "eval_avg_sts": 0.7960570924578971, "eval_sickr_spearman": 0.7468062972893365, "eval_stsb_spearman": 0.8453078876264578, "step": 3875 }, { "epoch": 0.51, "learning_rate": 9.760655318059645e-06, "loss": 0.0004, "step": 4000 }, { "epoch": 0.51, "eval_avg_sts": 0.7975689873245354, "eval_sickr_spearman": 0.7517150278252102, "eval_stsb_spearman": 0.8434229468238607, "step": 4000 }, { "epoch": 0.53, "eval_avg_sts": 0.7971877757425163, "eval_sickr_spearman": 0.7490601086932185, "eval_stsb_spearman": 0.8453154427918141, "step": 4125 }, { "epoch": 0.54, "eval_avg_sts": 0.799856091040363, "eval_sickr_spearman": 0.7506221281430873, "eval_stsb_spearman": 0.8490900539376388, "step": 4250 }, { "epoch": 0.56, "eval_avg_sts": 0.8009276979255495, "eval_sickr_spearman": 0.7507006589939387, "eval_stsb_spearman": 0.8511547368571605, "step": 4375 }, { "epoch": 0.58, "learning_rate": 8.4807372328171e-06, "loss": 0.0002, "step": 4500 }, { "epoch": 0.58, "eval_avg_sts": 0.8015427695250972, "eval_sickr_spearman": 0.752485398661176, "eval_stsb_spearman": 0.8506001403890182, "step": 4500 }, { "epoch": 0.59, "eval_avg_sts": 0.7931466450868088, "eval_sickr_spearman": 0.7451727595294263, "eval_stsb_spearman": 0.8411205306441913, "step": 4625 }, { "epoch": 0.61, "eval_avg_sts": 0.8009401798756712, "eval_sickr_spearman": 0.7592960647517961, "eval_stsb_spearman": 0.8425842949995465, "step": 4750 }, { "epoch": 0.62, "eval_avg_sts": 0.7902486823800228, "eval_sickr_spearman": 0.7485647639440872, "eval_stsb_spearman": 0.8319326008159583, "step": 4875 }, { "epoch": 0.64, "learning_rate": 7.200819147574556e-06, "loss": 0.0004, "step": 5000 }, { "epoch": 0.64, "eval_avg_sts": 0.7865346213104021, "eval_sickr_spearman": 0.7400579275372816, "eval_stsb_spearman": 0.8330113150835224, "step": 5000 }, { "epoch": 0.66, "eval_avg_sts": 0.7872787939204771, "eval_sickr_spearman": 0.7410168684774935, "eval_stsb_spearman": 0.8335407193634606, "step": 5125 }, { "epoch": 0.67, "eval_avg_sts": 0.7881510784701646, "eval_sickr_spearman": 0.7505857685992987, "eval_stsb_spearman": 0.8257163883410304, "step": 5250 }, { "epoch": 0.69, "eval_avg_sts": 0.7945145118810497, "eval_sickr_spearman": 0.7558576142620445, "eval_stsb_spearman": 0.833171409500055, "step": 5375 }, { "epoch": 0.7, "learning_rate": 5.920901062332012e-06, "loss": 0.0002, "step": 5500 }, { "epoch": 0.7, "eval_avg_sts": 0.7979814354987071, "eval_sickr_spearman": 0.7559497379146027, "eval_stsb_spearman": 0.8400131330828116, "step": 5500 }, { "epoch": 0.72, "eval_avg_sts": 0.7982480461082944, "eval_sickr_spearman": 0.7554273996864633, "eval_stsb_spearman": 0.8410686925301255, "step": 5625 }, { "epoch": 0.74, "eval_avg_sts": 0.798189926599052, "eval_sickr_spearman": 0.7587051861419044, "eval_stsb_spearman": 0.8376746670561996, "step": 5750 }, { "epoch": 0.75, "eval_avg_sts": 0.7966011989359767, "eval_sickr_spearman": 0.756065973180083, "eval_stsb_spearman": 0.8371364246918704, "step": 5875 }, { "epoch": 0.77, "learning_rate": 4.640982977089467e-06, "loss": 0.0004, "step": 6000 }, { "epoch": 0.77, "eval_avg_sts": 0.7984593901137271, "eval_sickr_spearman": 0.7602338720073751, "eval_stsb_spearman": 0.8366849082200791, "step": 6000 }, { "epoch": 0.78, "eval_avg_sts": 0.7952611257249883, "eval_sickr_spearman": 0.7563395583338746, "eval_stsb_spearman": 0.834182693116102, "step": 6125 }, { "epoch": 0.8, "eval_avg_sts": 0.7946186448265642, "eval_sickr_spearman": 0.7567510888109963, "eval_stsb_spearman": 0.832486200842132, "step": 6250 }, { "epoch": 0.82, "eval_avg_sts": 0.7938673811911408, "eval_sickr_spearman": 0.756815306393619, "eval_stsb_spearman": 0.8309194559886626, "step": 6375 }, { "epoch": 0.83, "learning_rate": 3.3610648918469217e-06, "loss": 0.0003, "step": 6500 }, { "epoch": 0.83, "eval_avg_sts": 0.7941658649824449, "eval_sickr_spearman": 0.7582097933616717, "eval_stsb_spearman": 0.8301219366032181, "step": 6500 }, { "epoch": 0.85, "eval_avg_sts": 0.7899228636738962, "eval_sickr_spearman": 0.7538527000258148, "eval_stsb_spearman": 0.8259930273219777, "step": 6625 }, { "epoch": 0.86, "eval_avg_sts": 0.7908249597888872, "eval_sickr_spearman": 0.7529101376911932, "eval_stsb_spearman": 0.8287397818865813, "step": 6750 }, { "epoch": 0.88, "eval_avg_sts": 0.7913431181790619, "eval_sickr_spearman": 0.7534930911693477, "eval_stsb_spearman": 0.8291931451887761, "step": 6875 }, { "epoch": 0.9, "learning_rate": 2.0811468066043775e-06, "loss": 0.0004, "step": 7000 }, { "epoch": 0.9, "eval_avg_sts": 0.7932583890535982, "eval_sickr_spearman": 0.7548152913297359, "eval_stsb_spearman": 0.8317014867774606, "step": 7000 }, { "epoch": 0.91, "eval_avg_sts": 0.7936961629213847, "eval_sickr_spearman": 0.7550173581734861, "eval_stsb_spearman": 0.8323749676692832, "step": 7125 }, { "epoch": 0.93, "eval_avg_sts": 0.7943097969110002, "eval_sickr_spearman": 0.7551339296566764, "eval_stsb_spearman": 0.8334856641653241, "step": 7250 }, { "epoch": 0.94, "eval_avg_sts": 0.7952534760489661, "eval_sickr_spearman": 0.7558418120296713, "eval_stsb_spearman": 0.834665140068261, "step": 7375 }, { "epoch": 0.96, "learning_rate": 8.012287213618329e-07, "loss": 0.0003, "step": 7500 }, { "epoch": 0.96, "eval_avg_sts": 0.7950213976361764, "eval_sickr_spearman": 0.7561205845424182, "eval_stsb_spearman": 0.8339222107299348, "step": 7500 }, { "epoch": 0.98, "eval_avg_sts": 0.7959169977411076, "eval_sickr_spearman": 0.7571501312017441, "eval_stsb_spearman": 0.834683864280471, "step": 7625 }, { "epoch": 0.99, "eval_avg_sts": 0.7962776415425221, "eval_sickr_spearman": 0.75766166243206, "eval_stsb_spearman": 0.8348936206529841, "step": 7750 }, { "epoch": 1.0, "step": 7813, "train_runtime": 6281.3522, "train_samples_per_second": 1.244 } ], "max_steps": 7813, "num_train_epochs": 1, "total_flos": 136861324957188096, "trial_name": null, "trial_params": null }