| { | |
| "best_metric": 0.18472303450107574, | |
| "best_model_checkpoint": "frost-vision-v2-google_vit-base-patch16-384-v2024-11-10/checkpoint-500", | |
| "epoch": 30.0, | |
| "eval_steps": 100, | |
| "global_step": 2130, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14084507042253522, | |
| "grad_norm": 1.9532430171966553, | |
| "learning_rate": 9.389671361502347e-06, | |
| "loss": 0.7081, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28169014084507044, | |
| "grad_norm": 1.4905153512954712, | |
| "learning_rate": 1.8779342723004694e-05, | |
| "loss": 0.5966, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4225352112676056, | |
| "grad_norm": 1.0629397630691528, | |
| "learning_rate": 2.8169014084507046e-05, | |
| "loss": 0.4634, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5633802816901409, | |
| "grad_norm": 1.1944268941879272, | |
| "learning_rate": 3.755868544600939e-05, | |
| "loss": 0.4103, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.704225352112676, | |
| "grad_norm": 1.0600364208221436, | |
| "learning_rate": 4.694835680751174e-05, | |
| "loss": 0.3456, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8450704225352113, | |
| "grad_norm": 0.9409961700439453, | |
| "learning_rate": 5.633802816901409e-05, | |
| "loss": 0.2917, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9859154929577465, | |
| "grad_norm": 0.9866936206817627, | |
| "learning_rate": 6.572769953051644e-05, | |
| "loss": 0.2536, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1267605633802817, | |
| "grad_norm": 0.8040021657943726, | |
| "learning_rate": 7.511737089201878e-05, | |
| "loss": 0.236, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.267605633802817, | |
| "grad_norm": 0.7174156904220581, | |
| "learning_rate": 8.450704225352113e-05, | |
| "loss": 0.2305, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "grad_norm": 1.468618631362915, | |
| "learning_rate": 9.389671361502347e-05, | |
| "loss": 0.2243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.408450704225352, | |
| "eval_accuracy": 0.9242957746478874, | |
| "eval_f1": 0.7981220657276995, | |
| "eval_loss": 0.20880411565303802, | |
| "eval_precision": 0.8534136546184738, | |
| "eval_recall": 0.7495590828924162, | |
| "eval_runtime": 4.7453, | |
| "eval_samples_per_second": 59.848, | |
| "eval_steps_per_second": 7.586, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5492957746478875, | |
| "grad_norm": 1.7064496278762817, | |
| "learning_rate": 0.00010328638497652582, | |
| "loss": 0.2272, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.6901408450704225, | |
| "grad_norm": 0.8617244362831116, | |
| "learning_rate": 0.00011267605633802819, | |
| "loss": 0.2142, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8309859154929577, | |
| "grad_norm": 0.8898526430130005, | |
| "learning_rate": 0.00012206572769953053, | |
| "loss": 0.2208, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.971830985915493, | |
| "grad_norm": 1.2177144289016724, | |
| "learning_rate": 0.00013145539906103288, | |
| "loss": 0.2147, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.112676056338028, | |
| "grad_norm": 1.7734003067016602, | |
| "learning_rate": 0.00014084507042253522, | |
| "loss": 0.1993, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.2535211267605635, | |
| "grad_norm": 0.9507364630699158, | |
| "learning_rate": 0.00015023474178403755, | |
| "loss": 0.1806, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.3943661971830985, | |
| "grad_norm": 0.9511057734489441, | |
| "learning_rate": 0.00015962441314553992, | |
| "loss": 0.1913, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.535211267605634, | |
| "grad_norm": 1.419704556465149, | |
| "learning_rate": 0.00016901408450704225, | |
| "loss": 0.1949, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.676056338028169, | |
| "grad_norm": 0.8608860373497009, | |
| "learning_rate": 0.00017840375586854461, | |
| "loss": 0.1907, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "grad_norm": 1.1266043186187744, | |
| "learning_rate": 0.00018779342723004695, | |
| "loss": 0.2438, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.816901408450704, | |
| "eval_accuracy": 0.9299295774647888, | |
| "eval_f1": 0.8102955195424214, | |
| "eval_loss": 0.18185150623321533, | |
| "eval_precision": 0.8817427385892116, | |
| "eval_recall": 0.7495590828924162, | |
| "eval_runtime": 4.6977, | |
| "eval_samples_per_second": 60.455, | |
| "eval_steps_per_second": 7.663, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.9577464788732395, | |
| "grad_norm": 0.9358466267585754, | |
| "learning_rate": 0.0001971830985915493, | |
| "loss": 0.1805, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.0985915492957745, | |
| "grad_norm": 0.5238935351371765, | |
| "learning_rate": 0.00019926969222743872, | |
| "loss": 0.1614, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.23943661971831, | |
| "grad_norm": 0.8152980208396912, | |
| "learning_rate": 0.00019822639540949402, | |
| "loss": 0.1632, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.380281690140845, | |
| "grad_norm": 0.8670392036437988, | |
| "learning_rate": 0.0001971830985915493, | |
| "loss": 0.17, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.52112676056338, | |
| "grad_norm": 0.719203531742096, | |
| "learning_rate": 0.0001961398017736046, | |
| "loss": 0.1843, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.6619718309859155, | |
| "grad_norm": 1.1024322509765625, | |
| "learning_rate": 0.0001950965049556599, | |
| "loss": 0.1843, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.802816901408451, | |
| "grad_norm": 1.002933382987976, | |
| "learning_rate": 0.0001940532081377152, | |
| "loss": 0.1657, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.943661971830986, | |
| "grad_norm": 0.6921798586845398, | |
| "learning_rate": 0.0001930099113197705, | |
| "loss": 0.1881, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.084507042253521, | |
| "grad_norm": 0.5872893333435059, | |
| "learning_rate": 0.0001919666145018258, | |
| "loss": 0.1775, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.225352112676056, | |
| "grad_norm": 0.7991660833358765, | |
| "learning_rate": 0.0001909233176838811, | |
| "loss": 0.1338, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.225352112676056, | |
| "eval_accuracy": 0.9376760563380282, | |
| "eval_f1": 0.8448729184925504, | |
| "eval_loss": 0.1607813537120819, | |
| "eval_precision": 0.8397212543554007, | |
| "eval_recall": 0.8500881834215167, | |
| "eval_runtime": 4.716, | |
| "eval_samples_per_second": 60.22, | |
| "eval_steps_per_second": 7.634, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.366197183098592, | |
| "grad_norm": 0.3925558030605316, | |
| "learning_rate": 0.00018988002086593636, | |
| "loss": 0.1397, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.507042253521127, | |
| "grad_norm": 0.9107651114463806, | |
| "learning_rate": 0.00018883672404799165, | |
| "loss": 0.1328, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.647887323943662, | |
| "grad_norm": 0.6482114791870117, | |
| "learning_rate": 0.00018779342723004695, | |
| "loss": 0.1343, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.788732394366197, | |
| "grad_norm": 0.8836609125137329, | |
| "learning_rate": 0.00018675013041210225, | |
| "loss": 0.1527, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 4.929577464788732, | |
| "grad_norm": 0.8424317240715027, | |
| "learning_rate": 0.00018570683359415754, | |
| "loss": 0.1338, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.070422535211268, | |
| "grad_norm": 0.824109673500061, | |
| "learning_rate": 0.00018466353677621284, | |
| "loss": 0.1455, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.211267605633803, | |
| "grad_norm": 0.7583167552947998, | |
| "learning_rate": 0.00018362023995826813, | |
| "loss": 0.1045, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.352112676056338, | |
| "grad_norm": 0.9834734797477722, | |
| "learning_rate": 0.00018257694314032343, | |
| "loss": 0.1297, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.492957746478873, | |
| "grad_norm": 0.6775982975959778, | |
| "learning_rate": 0.00018153364632237873, | |
| "loss": 0.1382, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.633802816901408, | |
| "grad_norm": 0.4346470236778259, | |
| "learning_rate": 0.00018049034950443402, | |
| "loss": 0.1224, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.633802816901408, | |
| "eval_accuracy": 0.9271126760563381, | |
| "eval_f1": 0.8179419525065963, | |
| "eval_loss": 0.17346476018428802, | |
| "eval_precision": 0.8157894736842105, | |
| "eval_recall": 0.8201058201058201, | |
| "eval_runtime": 4.3151, | |
| "eval_samples_per_second": 65.816, | |
| "eval_steps_per_second": 8.343, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.774647887323944, | |
| "grad_norm": 0.6250389218330383, | |
| "learning_rate": 0.00017944705268648932, | |
| "loss": 0.1535, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 5.915492957746479, | |
| "grad_norm": 0.7581302523612976, | |
| "learning_rate": 0.00017840375586854461, | |
| "loss": 0.1217, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.056338028169014, | |
| "grad_norm": 1.0700663328170776, | |
| "learning_rate": 0.0001773604590505999, | |
| "loss": 0.1206, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.197183098591549, | |
| "grad_norm": 0.9656069278717041, | |
| "learning_rate": 0.0001763171622326552, | |
| "loss": 0.1063, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.338028169014084, | |
| "grad_norm": 0.8910039067268372, | |
| "learning_rate": 0.0001752738654147105, | |
| "loss": 0.1105, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.47887323943662, | |
| "grad_norm": 1.0498372316360474, | |
| "learning_rate": 0.0001742305685967658, | |
| "loss": 0.1064, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.619718309859155, | |
| "grad_norm": 0.8038674592971802, | |
| "learning_rate": 0.00017318727177882107, | |
| "loss": 0.1048, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.76056338028169, | |
| "grad_norm": 0.5430222749710083, | |
| "learning_rate": 0.00017214397496087636, | |
| "loss": 0.1081, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 6.901408450704225, | |
| "grad_norm": 0.6888221502304077, | |
| "learning_rate": 0.00017110067814293166, | |
| "loss": 0.1176, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.042253521126761, | |
| "grad_norm": 0.5913430452346802, | |
| "learning_rate": 0.00017005738132498696, | |
| "loss": 0.1065, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.042253521126761, | |
| "eval_accuracy": 0.9274647887323944, | |
| "eval_f1": 0.8186619718309859, | |
| "eval_loss": 0.18472303450107574, | |
| "eval_precision": 0.8172231985940246, | |
| "eval_recall": 0.8201058201058201, | |
| "eval_runtime": 4.2833, | |
| "eval_samples_per_second": 66.305, | |
| "eval_steps_per_second": 8.405, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.183098591549296, | |
| "grad_norm": 0.7211888432502747, | |
| "learning_rate": 0.00016901408450704225, | |
| "loss": 0.0907, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.323943661971831, | |
| "grad_norm": 0.9712802767753601, | |
| "learning_rate": 0.00016797078768909755, | |
| "loss": 0.1174, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.464788732394366, | |
| "grad_norm": 0.5647371411323547, | |
| "learning_rate": 0.00016692749087115284, | |
| "loss": 0.1188, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.605633802816901, | |
| "grad_norm": 0.8738060593605042, | |
| "learning_rate": 0.00016588419405320814, | |
| "loss": 0.1261, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.746478873239437, | |
| "grad_norm": 0.4535655081272125, | |
| "learning_rate": 0.00016484089723526344, | |
| "loss": 0.0865, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 7.887323943661972, | |
| "grad_norm": 0.4072222411632538, | |
| "learning_rate": 0.00016379760041731873, | |
| "loss": 0.0974, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.028169014084508, | |
| "grad_norm": 0.36978864669799805, | |
| "learning_rate": 0.00016275430359937403, | |
| "loss": 0.0989, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.169014084507042, | |
| "grad_norm": 0.6507691740989685, | |
| "learning_rate": 0.00016171100678142932, | |
| "loss": 0.0989, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.309859154929578, | |
| "grad_norm": 0.8923565149307251, | |
| "learning_rate": 0.00016066770996348462, | |
| "loss": 0.0901, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.450704225352112, | |
| "grad_norm": 0.8466383814811707, | |
| "learning_rate": 0.00015962441314553992, | |
| "loss": 0.1008, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.450704225352112, | |
| "eval_accuracy": 0.9404929577464789, | |
| "eval_f1": 0.8505747126436781, | |
| "eval_loss": 0.17097999155521393, | |
| "eval_precision": 0.8528368794326241, | |
| "eval_recall": 0.8483245149911817, | |
| "eval_runtime": 3.9495, | |
| "eval_samples_per_second": 71.908, | |
| "eval_steps_per_second": 9.115, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.591549295774648, | |
| "grad_norm": 0.568720817565918, | |
| "learning_rate": 0.0001585811163275952, | |
| "loss": 0.084, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.732394366197184, | |
| "grad_norm": 0.6025291085243225, | |
| "learning_rate": 0.0001575378195096505, | |
| "loss": 0.1059, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 8.873239436619718, | |
| "grad_norm": 0.6547625660896301, | |
| "learning_rate": 0.0001564945226917058, | |
| "loss": 0.0871, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.014084507042254, | |
| "grad_norm": 0.46392133831977844, | |
| "learning_rate": 0.00015545122587376107, | |
| "loss": 0.0856, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.154929577464788, | |
| "grad_norm": 0.29296088218688965, | |
| "learning_rate": 0.00015440792905581637, | |
| "loss": 0.0883, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.295774647887324, | |
| "grad_norm": 0.6499446630477905, | |
| "learning_rate": 0.00015336463223787167, | |
| "loss": 0.0632, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.43661971830986, | |
| "grad_norm": 0.27808037400245667, | |
| "learning_rate": 0.00015232133541992696, | |
| "loss": 0.0731, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.577464788732394, | |
| "grad_norm": 0.6585447788238525, | |
| "learning_rate": 0.00015127803860198226, | |
| "loss": 0.073, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.71830985915493, | |
| "grad_norm": 0.5550310611724854, | |
| "learning_rate": 0.00015023474178403755, | |
| "loss": 0.0762, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 9.859154929577464, | |
| "grad_norm": 0.8603278398513794, | |
| "learning_rate": 0.00014919144496609285, | |
| "loss": 0.1005, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 9.859154929577464, | |
| "eval_accuracy": 0.9383802816901409, | |
| "eval_f1": 0.8404740200546946, | |
| "eval_loss": 0.18234650790691376, | |
| "eval_precision": 0.869811320754717, | |
| "eval_recall": 0.8130511463844797, | |
| "eval_runtime": 4.0053, | |
| "eval_samples_per_second": 70.906, | |
| "eval_steps_per_second": 8.988, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.5497912168502808, | |
| "learning_rate": 0.00014814814814814815, | |
| "loss": 0.0828, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.140845070422536, | |
| "grad_norm": 0.5562108755111694, | |
| "learning_rate": 0.00014710485133020344, | |
| "loss": 0.0771, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.28169014084507, | |
| "grad_norm": 0.5177081823348999, | |
| "learning_rate": 0.00014606155451225874, | |
| "loss": 0.0699, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.422535211267606, | |
| "grad_norm": 1.1959189176559448, | |
| "learning_rate": 0.00014501825769431403, | |
| "loss": 0.0706, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.56338028169014, | |
| "grad_norm": 0.41302013397216797, | |
| "learning_rate": 0.00014397496087636933, | |
| "loss": 0.0562, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.704225352112676, | |
| "grad_norm": 0.8963214159011841, | |
| "learning_rate": 0.00014293166405842463, | |
| "loss": 0.0795, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 10.845070422535212, | |
| "grad_norm": 0.5553390979766846, | |
| "learning_rate": 0.00014188836724047992, | |
| "loss": 0.0841, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 10.985915492957746, | |
| "grad_norm": 0.5120792984962463, | |
| "learning_rate": 0.00014084507042253522, | |
| "loss": 0.0571, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.126760563380282, | |
| "grad_norm": 0.8299622535705566, | |
| "learning_rate": 0.00013980177360459051, | |
| "loss": 0.0674, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.267605633802816, | |
| "grad_norm": 0.8283889889717102, | |
| "learning_rate": 0.00013875847678664578, | |
| "loss": 0.0756, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.267605633802816, | |
| "eval_accuracy": 0.9415492957746479, | |
| "eval_f1": 0.8520499108734403, | |
| "eval_loss": 0.1770765483379364, | |
| "eval_precision": 0.8612612612612612, | |
| "eval_recall": 0.8430335097001763, | |
| "eval_runtime": 3.9753, | |
| "eval_samples_per_second": 71.441, | |
| "eval_steps_per_second": 9.056, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.408450704225352, | |
| "grad_norm": 0.7964696288108826, | |
| "learning_rate": 0.00013771517996870108, | |
| "loss": 0.0674, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.549295774647888, | |
| "grad_norm": 0.5819689631462097, | |
| "learning_rate": 0.00013667188315075638, | |
| "loss": 0.0744, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.690140845070422, | |
| "grad_norm": 0.4807089865207672, | |
| "learning_rate": 0.0001356285863328117, | |
| "loss": 0.09, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 11.830985915492958, | |
| "grad_norm": 0.4166727364063263, | |
| "learning_rate": 0.000134585289514867, | |
| "loss": 0.057, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 11.971830985915492, | |
| "grad_norm": 0.5973660349845886, | |
| "learning_rate": 0.0001335419926969223, | |
| "loss": 0.0678, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 12.112676056338028, | |
| "grad_norm": 0.8271676898002625, | |
| "learning_rate": 0.0001324986958789776, | |
| "loss": 0.0676, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.253521126760564, | |
| "grad_norm": 0.4148211181163788, | |
| "learning_rate": 0.00013145539906103288, | |
| "loss": 0.0724, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.394366197183098, | |
| "grad_norm": 0.8119566440582275, | |
| "learning_rate": 0.00013041210224308818, | |
| "loss": 0.0513, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.535211267605634, | |
| "grad_norm": 0.3651484549045563, | |
| "learning_rate": 0.00012936880542514348, | |
| "loss": 0.0681, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.676056338028168, | |
| "grad_norm": 0.5199844241142273, | |
| "learning_rate": 0.00012832550860719877, | |
| "loss": 0.0653, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.676056338028168, | |
| "eval_accuracy": 0.9323943661971831, | |
| "eval_f1": 0.8309859154929577, | |
| "eval_loss": 0.1971179097890854, | |
| "eval_precision": 0.8295254833040422, | |
| "eval_recall": 0.8324514991181657, | |
| "eval_runtime": 4.0066, | |
| "eval_samples_per_second": 70.884, | |
| "eval_steps_per_second": 8.985, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 12.816901408450704, | |
| "grad_norm": 0.5670329332351685, | |
| "learning_rate": 0.00012728221178925407, | |
| "loss": 0.0619, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 12.95774647887324, | |
| "grad_norm": 0.5461100935935974, | |
| "learning_rate": 0.00012623891497130936, | |
| "loss": 0.0411, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 13.098591549295774, | |
| "grad_norm": 0.5733127593994141, | |
| "learning_rate": 0.00012519561815336466, | |
| "loss": 0.0544, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.23943661971831, | |
| "grad_norm": 1.001535177230835, | |
| "learning_rate": 0.00012415232133541993, | |
| "loss": 0.0723, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.380281690140846, | |
| "grad_norm": 0.4734277129173279, | |
| "learning_rate": 0.00012310902451747523, | |
| "loss": 0.0457, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.52112676056338, | |
| "grad_norm": 0.41569235920906067, | |
| "learning_rate": 0.00012206572769953053, | |
| "loss": 0.0611, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.661971830985916, | |
| "grad_norm": 0.656200110912323, | |
| "learning_rate": 0.00012102243088158583, | |
| "loss": 0.0578, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 13.80281690140845, | |
| "grad_norm": 0.4374938905239105, | |
| "learning_rate": 0.00011997913406364111, | |
| "loss": 0.0493, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 13.943661971830986, | |
| "grad_norm": 0.4476602077484131, | |
| "learning_rate": 0.00011893583724569641, | |
| "loss": 0.0645, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.084507042253522, | |
| "grad_norm": 0.4841475784778595, | |
| "learning_rate": 0.0001178925404277517, | |
| "loss": 0.0367, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.084507042253522, | |
| "eval_accuracy": 0.9295774647887324, | |
| "eval_f1": 0.8220640569395018, | |
| "eval_loss": 0.2123415768146515, | |
| "eval_precision": 0.829443447037702, | |
| "eval_recall": 0.8148148148148148, | |
| "eval_runtime": 3.9803, | |
| "eval_samples_per_second": 71.351, | |
| "eval_steps_per_second": 9.045, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.225352112676056, | |
| "grad_norm": 0.36940839886665344, | |
| "learning_rate": 0.000116849243609807, | |
| "loss": 0.0583, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.366197183098592, | |
| "grad_norm": 0.360748291015625, | |
| "learning_rate": 0.0001158059467918623, | |
| "loss": 0.0557, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.507042253521126, | |
| "grad_norm": 0.5215537548065186, | |
| "learning_rate": 0.0001147626499739176, | |
| "loss": 0.0687, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.647887323943662, | |
| "grad_norm": 0.504537045955658, | |
| "learning_rate": 0.00011371935315597289, | |
| "loss": 0.07, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 14.788732394366198, | |
| "grad_norm": 0.6165650486946106, | |
| "learning_rate": 0.00011267605633802819, | |
| "loss": 0.0527, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 14.929577464788732, | |
| "grad_norm": 0.4196755588054657, | |
| "learning_rate": 0.00011163275952008347, | |
| "loss": 0.039, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 15.070422535211268, | |
| "grad_norm": 0.789492130279541, | |
| "learning_rate": 0.00011058946270213876, | |
| "loss": 0.0518, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.211267605633802, | |
| "grad_norm": 0.3040258288383484, | |
| "learning_rate": 0.00010954616588419406, | |
| "loss": 0.0426, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.352112676056338, | |
| "grad_norm": 0.5353887677192688, | |
| "learning_rate": 0.00010850286906624936, | |
| "loss": 0.06, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.492957746478874, | |
| "grad_norm": 0.4748779833316803, | |
| "learning_rate": 0.00010745957224830465, | |
| "loss": 0.0459, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.492957746478874, | |
| "eval_accuracy": 0.9334507042253521, | |
| "eval_f1": 0.832, | |
| "eval_loss": 0.20056356489658356, | |
| "eval_precision": 0.8387096774193549, | |
| "eval_recall": 0.8253968253968254, | |
| "eval_runtime": 3.8873, | |
| "eval_samples_per_second": 73.058, | |
| "eval_steps_per_second": 9.261, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.633802816901408, | |
| "grad_norm": 1.0769853591918945, | |
| "learning_rate": 0.00010641627543035995, | |
| "loss": 0.0564, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 15.774647887323944, | |
| "grad_norm": 0.2092517763376236, | |
| "learning_rate": 0.00010537297861241524, | |
| "loss": 0.037, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 15.915492957746478, | |
| "grad_norm": 0.4689568877220154, | |
| "learning_rate": 0.00010432968179447054, | |
| "loss": 0.0401, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 16.056338028169016, | |
| "grad_norm": 0.2354661524295807, | |
| "learning_rate": 0.00010328638497652582, | |
| "loss": 0.0459, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 16.197183098591548, | |
| "grad_norm": 0.11875198781490326, | |
| "learning_rate": 0.00010224308815858112, | |
| "loss": 0.0369, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.338028169014084, | |
| "grad_norm": 0.5551555156707764, | |
| "learning_rate": 0.00010119979134063642, | |
| "loss": 0.034, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.47887323943662, | |
| "grad_norm": 0.35518983006477356, | |
| "learning_rate": 0.00010015649452269171, | |
| "loss": 0.0523, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.619718309859156, | |
| "grad_norm": 0.6546155214309692, | |
| "learning_rate": 9.911319770474701e-05, | |
| "loss": 0.0472, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 16.760563380281692, | |
| "grad_norm": 1.1401140689849854, | |
| "learning_rate": 9.80699008868023e-05, | |
| "loss": 0.0565, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 16.901408450704224, | |
| "grad_norm": 0.5762555599212646, | |
| "learning_rate": 9.70266040688576e-05, | |
| "loss": 0.0559, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 16.901408450704224, | |
| "eval_accuracy": 0.9313380281690141, | |
| "eval_f1": 0.8232094288304623, | |
| "eval_loss": 0.20966318249702454, | |
| "eval_precision": 0.8470149253731343, | |
| "eval_recall": 0.800705467372134, | |
| "eval_runtime": 3.9873, | |
| "eval_samples_per_second": 71.227, | |
| "eval_steps_per_second": 9.029, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 17.04225352112676, | |
| "grad_norm": 0.5705350637435913, | |
| "learning_rate": 9.59833072509129e-05, | |
| "loss": 0.0455, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 17.183098591549296, | |
| "grad_norm": 0.08219115436077118, | |
| "learning_rate": 9.494001043296818e-05, | |
| "loss": 0.029, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.323943661971832, | |
| "grad_norm": 0.41505807638168335, | |
| "learning_rate": 9.389671361502347e-05, | |
| "loss": 0.05, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.464788732394368, | |
| "grad_norm": 0.5585283637046814, | |
| "learning_rate": 9.285341679707877e-05, | |
| "loss": 0.0424, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.6056338028169, | |
| "grad_norm": 0.4773949980735779, | |
| "learning_rate": 9.181011997913407e-05, | |
| "loss": 0.043, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 17.746478873239436, | |
| "grad_norm": 0.5886436700820923, | |
| "learning_rate": 9.076682316118936e-05, | |
| "loss": 0.043, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 17.887323943661972, | |
| "grad_norm": 0.45917659997940063, | |
| "learning_rate": 8.972352634324466e-05, | |
| "loss": 0.0444, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 18.028169014084508, | |
| "grad_norm": 0.5295466780662537, | |
| "learning_rate": 8.868022952529996e-05, | |
| "loss": 0.0385, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 18.169014084507044, | |
| "grad_norm": 0.24455229938030243, | |
| "learning_rate": 8.763693270735525e-05, | |
| "loss": 0.0263, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 18.309859154929576, | |
| "grad_norm": 0.34424206614494324, | |
| "learning_rate": 8.659363588941053e-05, | |
| "loss": 0.0382, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.309859154929576, | |
| "eval_accuracy": 0.9352112676056338, | |
| "eval_f1": 0.8371681415929203, | |
| "eval_loss": 0.2055191993713379, | |
| "eval_precision": 0.8401420959147424, | |
| "eval_recall": 0.8342151675485009, | |
| "eval_runtime": 4.0365, | |
| "eval_samples_per_second": 70.358, | |
| "eval_steps_per_second": 8.919, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 18.450704225352112, | |
| "grad_norm": 0.10903073102235794, | |
| "learning_rate": 8.555033907146583e-05, | |
| "loss": 0.0276, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 18.591549295774648, | |
| "grad_norm": 0.4288780987262726, | |
| "learning_rate": 8.450704225352113e-05, | |
| "loss": 0.0457, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 18.732394366197184, | |
| "grad_norm": 0.9041640758514404, | |
| "learning_rate": 8.346374543557642e-05, | |
| "loss": 0.0404, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 18.87323943661972, | |
| "grad_norm": 0.3118440806865692, | |
| "learning_rate": 8.242044861763172e-05, | |
| "loss": 0.0404, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 19.014084507042252, | |
| "grad_norm": 0.39209580421447754, | |
| "learning_rate": 8.137715179968701e-05, | |
| "loss": 0.029, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 19.154929577464788, | |
| "grad_norm": 0.6325451731681824, | |
| "learning_rate": 8.033385498174231e-05, | |
| "loss": 0.0299, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 19.295774647887324, | |
| "grad_norm": 0.33151936531066895, | |
| "learning_rate": 7.92905581637976e-05, | |
| "loss": 0.0277, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 19.43661971830986, | |
| "grad_norm": 0.40647652745246887, | |
| "learning_rate": 7.82472613458529e-05, | |
| "loss": 0.0285, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 19.577464788732396, | |
| "grad_norm": 0.3072868585586548, | |
| "learning_rate": 7.720396452790818e-05, | |
| "loss": 0.0314, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 19.718309859154928, | |
| "grad_norm": 0.6823632121086121, | |
| "learning_rate": 7.616066770996348e-05, | |
| "loss": 0.0361, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.718309859154928, | |
| "eval_accuracy": 0.9334507042253521, | |
| "eval_f1": 0.8304932735426009, | |
| "eval_loss": 0.20700237154960632, | |
| "eval_precision": 0.8448905109489051, | |
| "eval_recall": 0.8165784832451499, | |
| "eval_runtime": 4.3433, | |
| "eval_samples_per_second": 65.388, | |
| "eval_steps_per_second": 8.289, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 19.859154929577464, | |
| "grad_norm": 0.4812707006931305, | |
| "learning_rate": 7.511737089201878e-05, | |
| "loss": 0.0515, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 0.9425677061080933, | |
| "learning_rate": 7.407407407407407e-05, | |
| "loss": 0.0408, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 20.140845070422536, | |
| "grad_norm": 0.23266366124153137, | |
| "learning_rate": 7.303077725612937e-05, | |
| "loss": 0.033, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 20.281690140845072, | |
| "grad_norm": 0.6943417191505432, | |
| "learning_rate": 7.198748043818467e-05, | |
| "loss": 0.0371, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 20.422535211267604, | |
| "grad_norm": 0.5533664226531982, | |
| "learning_rate": 7.094418362023996e-05, | |
| "loss": 0.0333, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 20.56338028169014, | |
| "grad_norm": 0.3414551913738251, | |
| "learning_rate": 6.990088680229526e-05, | |
| "loss": 0.0344, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 20.704225352112676, | |
| "grad_norm": 0.21747425198554993, | |
| "learning_rate": 6.885758998435054e-05, | |
| "loss": 0.0507, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 20.845070422535212, | |
| "grad_norm": 0.10106892138719559, | |
| "learning_rate": 6.781429316640585e-05, | |
| "loss": 0.0336, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 20.985915492957748, | |
| "grad_norm": 0.11431819200515747, | |
| "learning_rate": 6.677099634846115e-05, | |
| "loss": 0.0349, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 21.12676056338028, | |
| "grad_norm": 0.24515172839164734, | |
| "learning_rate": 6.572769953051644e-05, | |
| "loss": 0.0358, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 21.12676056338028, | |
| "eval_accuracy": 0.9397887323943662, | |
| "eval_f1": 0.8458070333633905, | |
| "eval_loss": 0.1959269642829895, | |
| "eval_precision": 0.8653136531365314, | |
| "eval_recall": 0.8271604938271605, | |
| "eval_runtime": 4.6741, | |
| "eval_samples_per_second": 60.76, | |
| "eval_steps_per_second": 7.702, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 21.267605633802816, | |
| "grad_norm": 0.1288166046142578, | |
| "learning_rate": 6.468440271257174e-05, | |
| "loss": 0.0319, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 21.408450704225352, | |
| "grad_norm": 0.3846772611141205, | |
| "learning_rate": 6.364110589462703e-05, | |
| "loss": 0.0292, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 21.549295774647888, | |
| "grad_norm": 0.8348280191421509, | |
| "learning_rate": 6.259780907668233e-05, | |
| "loss": 0.0408, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 21.690140845070424, | |
| "grad_norm": 0.24261720478534698, | |
| "learning_rate": 6.155451225873761e-05, | |
| "loss": 0.0279, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 21.830985915492956, | |
| "grad_norm": 0.5973533391952515, | |
| "learning_rate": 6.0511215440792915e-05, | |
| "loss": 0.0363, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 21.971830985915492, | |
| "grad_norm": 0.3994261622428894, | |
| "learning_rate": 5.9467918622848205e-05, | |
| "loss": 0.0294, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 22.112676056338028, | |
| "grad_norm": 0.2752346992492676, | |
| "learning_rate": 5.84246218049035e-05, | |
| "loss": 0.0355, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 22.253521126760564, | |
| "grad_norm": 0.0635056421160698, | |
| "learning_rate": 5.73813249869588e-05, | |
| "loss": 0.0192, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 22.3943661971831, | |
| "grad_norm": 0.4133341908454895, | |
| "learning_rate": 5.633802816901409e-05, | |
| "loss": 0.0412, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 22.535211267605632, | |
| "grad_norm": 0.30646753311157227, | |
| "learning_rate": 5.529473135106938e-05, | |
| "loss": 0.0382, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 22.535211267605632, | |
| "eval_accuracy": 0.9320422535211268, | |
| "eval_f1": 0.8269058295964126, | |
| "eval_loss": 0.20972707867622375, | |
| "eval_precision": 0.8412408759124088, | |
| "eval_recall": 0.8130511463844797, | |
| "eval_runtime": 4.7317, | |
| "eval_samples_per_second": 60.021, | |
| "eval_steps_per_second": 7.608, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 22.676056338028168, | |
| "grad_norm": 1.3331828117370605, | |
| "learning_rate": 5.425143453312468e-05, | |
| "loss": 0.0331, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 22.816901408450704, | |
| "grad_norm": 0.5091800093650818, | |
| "learning_rate": 5.3208137715179974e-05, | |
| "loss": 0.0187, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 22.95774647887324, | |
| "grad_norm": 0.1486244797706604, | |
| "learning_rate": 5.216484089723527e-05, | |
| "loss": 0.02, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 23.098591549295776, | |
| "grad_norm": 0.07892175763845444, | |
| "learning_rate": 5.112154407929056e-05, | |
| "loss": 0.0254, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 23.239436619718308, | |
| "grad_norm": 0.7007431387901306, | |
| "learning_rate": 5.0078247261345856e-05, | |
| "loss": 0.0179, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 23.380281690140844, | |
| "grad_norm": 0.4025111496448517, | |
| "learning_rate": 4.903495044340115e-05, | |
| "loss": 0.0256, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 23.52112676056338, | |
| "grad_norm": 0.30540022253990173, | |
| "learning_rate": 4.799165362545645e-05, | |
| "loss": 0.0254, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 23.661971830985916, | |
| "grad_norm": 0.45088985562324524, | |
| "learning_rate": 4.694835680751174e-05, | |
| "loss": 0.0326, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 23.802816901408452, | |
| "grad_norm": 0.15087296068668365, | |
| "learning_rate": 4.5905059989567033e-05, | |
| "loss": 0.0229, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 23.943661971830984, | |
| "grad_norm": 0.419587641954422, | |
| "learning_rate": 4.486176317162233e-05, | |
| "loss": 0.0285, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 23.943661971830984, | |
| "eval_accuracy": 0.9415492957746479, | |
| "eval_f1": 0.851520572450805, | |
| "eval_loss": 0.20160087943077087, | |
| "eval_precision": 0.8638838475499092, | |
| "eval_recall": 0.8395061728395061, | |
| "eval_runtime": 4.681, | |
| "eval_samples_per_second": 60.671, | |
| "eval_steps_per_second": 7.691, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 24.08450704225352, | |
| "grad_norm": 0.2833576202392578, | |
| "learning_rate": 4.3818466353677626e-05, | |
| "loss": 0.0136, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 24.225352112676056, | |
| "grad_norm": 0.13959386944770813, | |
| "learning_rate": 4.2775169535732915e-05, | |
| "loss": 0.0195, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 24.366197183098592, | |
| "grad_norm": 0.27296531200408936, | |
| "learning_rate": 4.173187271778821e-05, | |
| "loss": 0.0283, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 24.507042253521128, | |
| "grad_norm": 0.21670201420783997, | |
| "learning_rate": 4.068857589984351e-05, | |
| "loss": 0.0196, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 24.647887323943664, | |
| "grad_norm": 0.5724736452102661, | |
| "learning_rate": 3.96452790818988e-05, | |
| "loss": 0.031, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 24.788732394366196, | |
| "grad_norm": 0.5493142604827881, | |
| "learning_rate": 3.860198226395409e-05, | |
| "loss": 0.0265, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 24.929577464788732, | |
| "grad_norm": 0.21168898046016693, | |
| "learning_rate": 3.755868544600939e-05, | |
| "loss": 0.0224, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 25.070422535211268, | |
| "grad_norm": 0.5312497019767761, | |
| "learning_rate": 3.6515388628064685e-05, | |
| "loss": 0.024, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 25.211267605633804, | |
| "grad_norm": 0.5924656391143799, | |
| "learning_rate": 3.547209181011998e-05, | |
| "loss": 0.0151, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 25.352112676056336, | |
| "grad_norm": 0.05471556633710861, | |
| "learning_rate": 3.442879499217527e-05, | |
| "loss": 0.0141, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.352112676056336, | |
| "eval_accuracy": 0.9366197183098591, | |
| "eval_f1": 0.8384201077199281, | |
| "eval_loss": 0.2161274552345276, | |
| "eval_precision": 0.8537477148080439, | |
| "eval_recall": 0.8236331569664903, | |
| "eval_runtime": 4.5245, | |
| "eval_samples_per_second": 62.77, | |
| "eval_steps_per_second": 7.957, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 25.492957746478872, | |
| "grad_norm": 0.2500435709953308, | |
| "learning_rate": 3.338549817423057e-05, | |
| "loss": 0.0177, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 25.633802816901408, | |
| "grad_norm": 0.2633652985095978, | |
| "learning_rate": 3.234220135628587e-05, | |
| "loss": 0.0372, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 25.774647887323944, | |
| "grad_norm": 0.2851497232913971, | |
| "learning_rate": 3.1298904538341165e-05, | |
| "loss": 0.0253, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 25.91549295774648, | |
| "grad_norm": 0.13328520953655243, | |
| "learning_rate": 3.0255607720396458e-05, | |
| "loss": 0.0311, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 26.056338028169016, | |
| "grad_norm": 0.5192949771881104, | |
| "learning_rate": 2.921231090245175e-05, | |
| "loss": 0.0155, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 26.197183098591548, | |
| "grad_norm": 0.16768410801887512, | |
| "learning_rate": 2.8169014084507046e-05, | |
| "loss": 0.0282, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 26.338028169014084, | |
| "grad_norm": 0.045551054179668427, | |
| "learning_rate": 2.712571726656234e-05, | |
| "loss": 0.0194, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 26.47887323943662, | |
| "grad_norm": 0.33393070101737976, | |
| "learning_rate": 2.6082420448617635e-05, | |
| "loss": 0.0139, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 26.619718309859156, | |
| "grad_norm": 0.2400021106004715, | |
| "learning_rate": 2.5039123630672928e-05, | |
| "loss": 0.0111, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 26.760563380281692, | |
| "grad_norm": 0.5022717118263245, | |
| "learning_rate": 2.3995826812728224e-05, | |
| "loss": 0.0179, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 26.760563380281692, | |
| "eval_accuracy": 0.9376760563380282, | |
| "eval_f1": 0.8426666666666667, | |
| "eval_loss": 0.2072737216949463, | |
| "eval_precision": 0.8494623655913979, | |
| "eval_recall": 0.8359788359788359, | |
| "eval_runtime": 4.0574, | |
| "eval_samples_per_second": 69.995, | |
| "eval_steps_per_second": 8.873, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 26.901408450704224, | |
| "grad_norm": 0.41647252440452576, | |
| "learning_rate": 2.2952529994783517e-05, | |
| "loss": 0.0285, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 27.04225352112676, | |
| "grad_norm": 0.3066710829734802, | |
| "learning_rate": 2.1909233176838813e-05, | |
| "loss": 0.0225, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 27.183098591549296, | |
| "grad_norm": 0.09687885642051697, | |
| "learning_rate": 2.0865936358894105e-05, | |
| "loss": 0.0109, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 27.323943661971832, | |
| "grad_norm": 0.25405797362327576, | |
| "learning_rate": 1.98226395409494e-05, | |
| "loss": 0.0204, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 27.464788732394368, | |
| "grad_norm": 0.06933202594518661, | |
| "learning_rate": 1.8779342723004694e-05, | |
| "loss": 0.0274, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 27.6056338028169, | |
| "grad_norm": 0.13852407038211823, | |
| "learning_rate": 1.773604590505999e-05, | |
| "loss": 0.0194, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 27.746478873239436, | |
| "grad_norm": 0.1922004669904709, | |
| "learning_rate": 1.6692749087115286e-05, | |
| "loss": 0.0228, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 27.887323943661972, | |
| "grad_norm": 0.2851165235042572, | |
| "learning_rate": 1.5649452269170582e-05, | |
| "loss": 0.022, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 28.028169014084508, | |
| "grad_norm": 0.30591297149658203, | |
| "learning_rate": 1.4606155451225875e-05, | |
| "loss": 0.0179, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 28.169014084507044, | |
| "grad_norm": 0.9221152067184448, | |
| "learning_rate": 1.356285863328117e-05, | |
| "loss": 0.0263, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 28.169014084507044, | |
| "eval_accuracy": 0.9390845070422535, | |
| "eval_f1": 0.8456735057983943, | |
| "eval_loss": 0.20973354578018188, | |
| "eval_precision": 0.855595667870036, | |
| "eval_recall": 0.8359788359788359, | |
| "eval_runtime": 3.8982, | |
| "eval_samples_per_second": 72.853, | |
| "eval_steps_per_second": 9.235, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 28.309859154929576, | |
| "grad_norm": 0.2080974280834198, | |
| "learning_rate": 1.2519561815336464e-05, | |
| "loss": 0.0223, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 28.450704225352112, | |
| "grad_norm": 0.265176385641098, | |
| "learning_rate": 1.1476264997391758e-05, | |
| "loss": 0.0156, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 28.591549295774648, | |
| "grad_norm": 0.6490623950958252, | |
| "learning_rate": 1.0432968179447053e-05, | |
| "loss": 0.0143, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 28.732394366197184, | |
| "grad_norm": 0.08013524860143661, | |
| "learning_rate": 9.389671361502347e-06, | |
| "loss": 0.0175, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 28.87323943661972, | |
| "grad_norm": 0.24310840666294098, | |
| "learning_rate": 8.346374543557643e-06, | |
| "loss": 0.0208, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 29.014084507042252, | |
| "grad_norm": 0.21826568245887756, | |
| "learning_rate": 7.303077725612938e-06, | |
| "loss": 0.0209, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 29.154929577464788, | |
| "grad_norm": 0.10844382643699646, | |
| "learning_rate": 6.259780907668232e-06, | |
| "loss": 0.0122, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 29.295774647887324, | |
| "grad_norm": 0.1837497502565384, | |
| "learning_rate": 5.216484089723526e-06, | |
| "loss": 0.0155, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 29.43661971830986, | |
| "grad_norm": 0.8813931941986084, | |
| "learning_rate": 4.173187271778822e-06, | |
| "loss": 0.0229, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 29.577464788732396, | |
| "grad_norm": 0.10835859924554825, | |
| "learning_rate": 3.129890453834116e-06, | |
| "loss": 0.0191, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 29.577464788732396, | |
| "eval_accuracy": 0.9376760563380282, | |
| "eval_f1": 0.8415398388540735, | |
| "eval_loss": 0.21010643243789673, | |
| "eval_precision": 0.8545454545454545, | |
| "eval_recall": 0.8289241622574955, | |
| "eval_runtime": 4.0827, | |
| "eval_samples_per_second": 69.561, | |
| "eval_steps_per_second": 8.818, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 29.718309859154928, | |
| "grad_norm": 0.5981993079185486, | |
| "learning_rate": 2.086593635889411e-06, | |
| "loss": 0.024, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 29.859154929577464, | |
| "grad_norm": 0.029736319556832314, | |
| "learning_rate": 1.0432968179447054e-06, | |
| "loss": 0.0147, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "grad_norm": 0.1090225800871849, | |
| "learning_rate": 0.0, | |
| "loss": 0.0163, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "step": 2130, | |
| "total_flos": 7.774335248148726e+18, | |
| "train_loss": 0.08187752739294595, | |
| "train_runtime": 1287.2767, | |
| "train_samples_per_second": 26.428, | |
| "train_steps_per_second": 1.655 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2130, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.774335248148726e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |