{ "best_metric": 0.8323569009206506, "best_model_checkpoint": "checkpoints/bert-base-uncased", "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": 0.8091205074434157, "eval_sickr_spearman": 0.7855689811762409, "eval_stsb_spearman": 0.8326720337105905, "step": 25 }, { "epoch": 0.1, "eval_avg_sts": 0.8102784124545166, "eval_sickr_spearman": 0.7833337578086155, "eval_stsb_spearman": 0.8372230671004176, "step": 50 }, { "epoch": 0.15, "eval_avg_sts": 0.8185920801302614, "eval_sickr_spearman": 0.7990731655010734, "eval_stsb_spearman": 0.8381109947594494, "step": 75 }, { "epoch": 0.19, "eval_avg_sts": 0.8235606132721098, "eval_sickr_spearman": 0.802081545508548, "eval_stsb_spearman": 0.8450396810356716, "step": 100 }, { "epoch": 0.24, "eval_avg_sts": 0.8261107797978882, "eval_sickr_spearman": 0.8095936578045705, "eval_stsb_spearman": 0.8426279017912058, "step": 125 }, { "epoch": 0.29, "eval_avg_sts": 0.8298711381476593, "eval_sickr_spearman": 0.8175562057698793, "eval_stsb_spearman": 0.8421860705254393, "step": 150 }, { "epoch": 0.34, "eval_avg_sts": 0.8268735580135445, "eval_sickr_spearman": 0.809783716872961, "eval_stsb_spearman": 0.843963399154128, "step": 175 }, { "epoch": 0.39, "eval_avg_sts": 0.8269969778164787, "eval_sickr_spearman": 0.8097261275823368, "eval_stsb_spearman": 0.8442678280506208, "step": 200 }, { "epoch": 0.44, "eval_avg_sts": 0.8286377864730684, "eval_sickr_spearman": 0.8138642471267373, "eval_stsb_spearman": 0.8434113258193995, "step": 225 }, { "epoch": 0.49, "eval_avg_sts": 0.8311901085527629, "eval_sickr_spearman": 0.8156780936414463, "eval_stsb_spearman": 0.8467021234640796, "step": 250 }, { "epoch": 0.54, "eval_avg_sts": 0.8239986377138246, "eval_sickr_spearman": 0.8047907397851649, "eval_stsb_spearman": 0.8432065356424845, "step": 275 }, { "epoch": 0.58, "eval_avg_sts": 0.828722661892037, "eval_sickr_spearman": 0.8108316114130363, "eval_stsb_spearman": 0.8466137123710378, "step": 300 }, { "epoch": 0.63, "eval_avg_sts": 0.8283282637029816, "eval_sickr_spearman": 0.8147261652420443, "eval_stsb_spearman": 0.8419303621639188, "step": 325 }, { "epoch": 0.68, "eval_avg_sts": 0.8300155790519733, "eval_sickr_spearman": 0.8170386706518836, "eval_stsb_spearman": 0.842992487452063, "step": 350 }, { "epoch": 0.73, "eval_avg_sts": 0.8283238508507671, "eval_sickr_spearman": 0.8139993586150827, "eval_stsb_spearman": 0.8426483430864515, "step": 375 }, { "epoch": 0.78, "eval_avg_sts": 0.8320405612243372, "eval_sickr_spearman": 0.8164555730804248, "eval_stsb_spearman": 0.8476255493682496, "step": 400 }, { "epoch": 0.83, "eval_avg_sts": 0.8285288492675393, "eval_sickr_spearman": 0.8121700941168123, "eval_stsb_spearman": 0.8448876044182664, "step": 425 }, { "epoch": 0.88, "eval_avg_sts": 0.8323569009206506, "eval_sickr_spearman": 0.8193010796229231, "eval_stsb_spearman": 0.8454127222183782, "step": 450 }, { "epoch": 0.92, "eval_avg_sts": 0.825475145325371, "eval_sickr_spearman": 0.8101125858245077, "eval_stsb_spearman": 0.8408377048262344, "step": 475 }, { "epoch": 0.97, "learning_rate": 3.378728923476006e-05, "loss": 0.4728, "step": 500 }, { "epoch": 0.97, "eval_avg_sts": 0.8271573597477266, "eval_sickr_spearman": 0.8153802527814284, "eval_stsb_spearman": 0.8389344667140248, "step": 500 }, { "epoch": 1.02, "eval_avg_sts": 0.825308678275509, "eval_sickr_spearman": 0.8106034636812054, "eval_stsb_spearman": 0.8400138928698127, "step": 525 }, { "epoch": 1.07, "eval_avg_sts": 0.8267825462568358, "eval_sickr_spearman": 0.8081616105151932, "eval_stsb_spearman": 0.8454034819984784, "step": 550 }, { "epoch": 1.12, "eval_avg_sts": 0.8292667339957281, "eval_sickr_spearman": 0.8131185642769106, "eval_stsb_spearman": 0.8454149037145456, "step": 575 }, { "epoch": 1.17, "eval_avg_sts": 0.8282847493542007, "eval_sickr_spearman": 0.8099082134878887, "eval_stsb_spearman": 0.8466612852205128, "step": 600 }, { "epoch": 1.22, "eval_avg_sts": 0.8284726818422365, "eval_sickr_spearman": 0.8136914792548644, "eval_stsb_spearman": 0.8432538844296088, "step": 625 }, { "epoch": 1.26, "eval_avg_sts": 0.8264807699499799, "eval_sickr_spearman": 0.8101471201864417, "eval_stsb_spearman": 0.8428144197135181, "step": 650 }, { "epoch": 1.31, "eval_avg_sts": 0.825789312158798, "eval_sickr_spearman": 0.8071726981676838, "eval_stsb_spearman": 0.8444059261499122, "step": 675 }, { "epoch": 1.36, "eval_avg_sts": 0.8263077667234103, "eval_sickr_spearman": 0.809834918027094, "eval_stsb_spearman": 0.8427806154197267, "step": 700 }, { "epoch": 1.41, "eval_avg_sts": 0.8269124521441422, "eval_sickr_spearman": 0.8103127314242003, "eval_stsb_spearman": 0.8435121728640842, "step": 725 }, { "epoch": 1.46, "eval_avg_sts": 0.8284054639641667, "eval_sickr_spearman": 0.812405014233946, "eval_stsb_spearman": 0.8444059136943874, "step": 750 }, { "epoch": 1.51, "eval_avg_sts": 0.82848047976913, "eval_sickr_spearman": 0.8127376776425065, "eval_stsb_spearman": 0.8442232818957535, "step": 775 }, { "epoch": 1.56, "eval_avg_sts": 0.827488956868254, "eval_sickr_spearman": 0.8100566776224338, "eval_stsb_spearman": 0.844921236114074, "step": 800 }, { "epoch": 1.61, "eval_avg_sts": 0.8279657581459612, "eval_sickr_spearman": 0.8108479419875253, "eval_stsb_spearman": 0.845083574304397, "step": 825 }, { "epoch": 1.65, "eval_avg_sts": 0.8273853394613049, "eval_sickr_spearman": 0.8107756071487595, "eval_stsb_spearman": 0.8439950717738504, "step": 850 }, { "epoch": 1.7, "eval_avg_sts": 0.8313352689680793, "eval_sickr_spearman": 0.8172410737133439, "eval_stsb_spearman": 0.8454294642228147, "step": 875 }, { "epoch": 1.75, "eval_avg_sts": 0.8319193188081185, "eval_sickr_spearman": 0.8177730661928723, "eval_stsb_spearman": 0.8460655714233648, "step": 900 }, { "epoch": 1.8, "eval_avg_sts": 0.8290710541535955, "eval_sickr_spearman": 0.8117156718661062, "eval_stsb_spearman": 0.8464264364410848, "step": 925 }, { "epoch": 1.85, "eval_avg_sts": 0.8304411183144629, "eval_sickr_spearman": 0.8173339178324237, "eval_stsb_spearman": 0.8435483187965022, "step": 950 }, { "epoch": 1.9, "eval_avg_sts": 0.8278597990068485, "eval_sickr_spearman": 0.8122580390635454, "eval_stsb_spearman": 0.8434615589501515, "step": 975 }, { "epoch": 1.95, "learning_rate": 1.7574578469520103e-05, "loss": 0.2979, "step": 1000 }, { "epoch": 1.95, "eval_avg_sts": 0.8302680866123784, "eval_sickr_spearman": 0.8155675260459356, "eval_stsb_spearman": 0.8449686471788213, "step": 1000 }, { "epoch": 1.99, "eval_avg_sts": 0.8254828270469559, "eval_sickr_spearman": 0.8089062366807882, "eval_stsb_spearman": 0.8420594174131236, "step": 1025 }, { "epoch": 2.04, "eval_avg_sts": 0.828821293584806, "eval_sickr_spearman": 0.8119630800696138, "eval_stsb_spearman": 0.8456795070999983, "step": 1050 }, { "epoch": 2.09, "eval_avg_sts": 0.828469666832049, "eval_sickr_spearman": 0.8131763937230422, "eval_stsb_spearman": 0.8437629399410558, "step": 1075 }, { "epoch": 2.14, "eval_avg_sts": 0.8282850923377056, "eval_sickr_spearman": 0.8126665916123781, "eval_stsb_spearman": 0.8439035930630331, "step": 1100 }, { "epoch": 2.19, "eval_avg_sts": 0.8305188158369109, "eval_sickr_spearman": 0.8153585427235783, "eval_stsb_spearman": 0.8456790889502435, "step": 1125 }, { "epoch": 2.24, "eval_avg_sts": 0.827633691614419, "eval_sickr_spearman": 0.8116303205988508, "eval_stsb_spearman": 0.8436370626299873, "step": 1150 }, { "epoch": 2.29, "eval_avg_sts": 0.8282905337553752, "eval_sickr_spearman": 0.8129372468689818, "eval_stsb_spearman": 0.8436438206417686, "step": 1175 }, { "epoch": 2.33, "eval_avg_sts": 0.8284000990759287, "eval_sickr_spearman": 0.8133387388459029, "eval_stsb_spearman": 0.8434614593059545, "step": 1200 }, { "epoch": 2.38, "eval_avg_sts": 0.8281162332936303, "eval_sickr_spearman": 0.8138668123079954, "eval_stsb_spearman": 0.8423656542792651, "step": 1225 }, { "epoch": 2.43, "eval_avg_sts": 0.8294468108598559, "eval_sickr_spearman": 0.8161867430056757, "eval_stsb_spearman": 0.8427068787140362, "step": 1250 }, { "epoch": 2.48, "eval_avg_sts": 0.8283226082193897, "eval_sickr_spearman": 0.813798972859883, "eval_stsb_spearman": 0.8428462435788966, "step": 1275 }, { "epoch": 2.53, "eval_avg_sts": 0.8292589856543454, "eval_sickr_spearman": 0.8143020025852442, "eval_stsb_spearman": 0.8442159687234466, "step": 1300 }, { "epoch": 2.58, "eval_avg_sts": 0.8276816481179423, "eval_sickr_spearman": 0.8122173567206272, "eval_stsb_spearman": 0.8431459395152573, "step": 1325 }, { "epoch": 2.63, "eval_avg_sts": 0.828135742102698, "eval_sickr_spearman": 0.8131700536176523, "eval_stsb_spearman": 0.8431014305877439, "step": 1350 }, { "epoch": 2.68, "eval_avg_sts": 0.8272048038824943, "eval_sickr_spearman": 0.8118982380826725, "eval_stsb_spearman": 0.8425113696823161, "step": 1375 }, { "epoch": 2.72, "eval_avg_sts": 0.8277882199813771, "eval_sickr_spearman": 0.8125238431789039, "eval_stsb_spearman": 0.8430525967838501, "step": 1400 }, { "epoch": 2.77, "eval_avg_sts": 0.8280258441957502, "eval_sickr_spearman": 0.8130684198070092, "eval_stsb_spearman": 0.8429832685844911, "step": 1425 }, { "epoch": 2.82, "eval_avg_sts": 0.8283991403128114, "eval_sickr_spearman": 0.8137915280391601, "eval_stsb_spearman": 0.8430067525864626, "step": 1450 }, { "epoch": 2.87, "eval_avg_sts": 0.8277659521731837, "eval_sickr_spearman": 0.8129026644759463, "eval_stsb_spearman": 0.842629239870421, "step": 1475 }, { "epoch": 2.92, "learning_rate": 1.3618677042801557e-06, "loss": 0.2608, "step": 1500 }, { "epoch": 2.92, "eval_avg_sts": 0.8277817426384378, "eval_sickr_spearman": 0.812730280852885, "eval_stsb_spearman": 0.8428332044239907, "step": 1500 }, { "epoch": 2.97, "eval_avg_sts": 0.8276246266790095, "eval_sickr_spearman": 0.8125702892539944, "eval_stsb_spearman": 0.8426789641040247, "step": 1525 }, { "epoch": 3.0, "step": 1542, "train_runtime": 2256.7501, "train_samples_per_second": 0.683 } ], "max_steps": 1542, "num_train_epochs": 3, "total_flos": 121335504616820736, "trial_name": null, "trial_params": null }