| { | |
| "best_metric": 0.855129650507328, | |
| "best_model_checkpoint": "swinv2-tiny-patch4-window16-256-finetuned-galaxy10-decals/checkpoint-1750", | |
| "epoch": 29.76, | |
| "eval_steps": 500, | |
| "global_step": 1860, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 2.3867, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 2.3023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 2.2058, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 2.0987, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 1.9414, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 1.723, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.48027057497181513, | |
| "eval_f1": 0.43586397572183194, | |
| "eval_loss": 1.463147759437561, | |
| "eval_precision": 0.5151716306960038, | |
| "eval_recall": 0.48027057497181513, | |
| "eval_runtime": 12.0594, | |
| "eval_samples_per_second": 147.105, | |
| "eval_steps_per_second": 2.322, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 1.5803, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 1.47, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 1.3504, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 1.2957, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.76, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 1.1976, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 1.1597, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.6758737316798196, | |
| "eval_f1": 0.6656604563894376, | |
| "eval_loss": 0.9497688412666321, | |
| "eval_precision": 0.6941863699672675, | |
| "eval_recall": 0.6758737316798196, | |
| "eval_runtime": 12.4298, | |
| "eval_samples_per_second": 142.721, | |
| "eval_steps_per_second": 2.253, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.08, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 1.0812, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 1.0358, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.9995, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.56, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.984, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.9713, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.9305, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.7728297632468997, | |
| "eval_f1": 0.7620341432725858, | |
| "eval_loss": 0.6600359678268433, | |
| "eval_precision": 0.7591548542854433, | |
| "eval_recall": 0.7728297632468997, | |
| "eval_runtime": 12.6126, | |
| "eval_samples_per_second": 140.653, | |
| "eval_steps_per_second": 2.22, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 3.04, | |
| "learning_rate": 4.98805256869773e-05, | |
| "loss": 0.9489, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 3.2, | |
| "learning_rate": 4.9581839904420555e-05, | |
| "loss": 0.8829, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 4.92831541218638e-05, | |
| "loss": 0.8387, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.52, | |
| "learning_rate": 4.898446833930705e-05, | |
| "loss": 0.862, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.68, | |
| "learning_rate": 4.86857825567503e-05, | |
| "loss": 0.7964, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.84, | |
| "learning_rate": 4.8387096774193554e-05, | |
| "loss": 0.799, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "learning_rate": 4.80884109916368e-05, | |
| "loss": 0.7634, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.7874859075535513, | |
| "eval_f1": 0.7764587142625603, | |
| "eval_loss": 0.6276313662528992, | |
| "eval_precision": 0.783142587836459, | |
| "eval_recall": 0.7874859075535513, | |
| "eval_runtime": 12.5792, | |
| "eval_samples_per_second": 141.026, | |
| "eval_steps_per_second": 2.226, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 4.16, | |
| "learning_rate": 4.778972520908005e-05, | |
| "loss": 0.8211, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "learning_rate": 4.74910394265233e-05, | |
| "loss": 0.7618, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 4.7192353643966546e-05, | |
| "loss": 0.761, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "learning_rate": 4.6893667861409805e-05, | |
| "loss": 0.7428, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.8, | |
| "learning_rate": 4.659498207885305e-05, | |
| "loss": 0.7787, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.6924, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.794250281848929, | |
| "eval_f1": 0.7934025148468361, | |
| "eval_loss": 0.5762449502944946, | |
| "eval_precision": 0.7972124708156384, | |
| "eval_recall": 0.794250281848929, | |
| "eval_runtime": 12.5491, | |
| "eval_samples_per_second": 141.364, | |
| "eval_steps_per_second": 2.231, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 5.12, | |
| "learning_rate": 4.5997610513739546e-05, | |
| "loss": 0.7261, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "learning_rate": 4.56989247311828e-05, | |
| "loss": 0.7497, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.44, | |
| "learning_rate": 4.540023894862604e-05, | |
| "loss": 0.6948, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 4.51015531660693e-05, | |
| "loss": 0.7092, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.76, | |
| "learning_rate": 4.4802867383512545e-05, | |
| "loss": 0.6681, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "learning_rate": 4.4504181600955796e-05, | |
| "loss": 0.6992, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8122886133032694, | |
| "eval_f1": 0.8058543425880699, | |
| "eval_loss": 0.5421018600463867, | |
| "eval_precision": 0.8128418371203046, | |
| "eval_recall": 0.8122886133032694, | |
| "eval_runtime": 12.0745, | |
| "eval_samples_per_second": 146.921, | |
| "eval_steps_per_second": 2.319, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 6.08, | |
| "learning_rate": 4.420549581839905e-05, | |
| "loss": 0.6817, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "learning_rate": 4.390681003584229e-05, | |
| "loss": 0.7155, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 6.4, | |
| "learning_rate": 4.360812425328555e-05, | |
| "loss": 0.6519, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "learning_rate": 4.3309438470728796e-05, | |
| "loss": 0.6672, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 4.301075268817205e-05, | |
| "loss": 0.6326, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "learning_rate": 4.271206690561529e-05, | |
| "loss": 0.6731, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.99, | |
| "eval_accuracy": 0.8128523111612176, | |
| "eval_f1": 0.8108013365786323, | |
| "eval_loss": 0.524404764175415, | |
| "eval_precision": 0.8152866766453654, | |
| "eval_recall": 0.8128523111612176, | |
| "eval_runtime": 12.2249, | |
| "eval_samples_per_second": 145.114, | |
| "eval_steps_per_second": 2.29, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 7.04, | |
| "learning_rate": 4.241338112305854e-05, | |
| "loss": 0.6926, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "learning_rate": 4.2114695340501795e-05, | |
| "loss": 0.662, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 7.36, | |
| "learning_rate": 4.1816009557945046e-05, | |
| "loss": 0.627, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "learning_rate": 4.15173237753883e-05, | |
| "loss": 0.6601, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.68, | |
| "learning_rate": 4.121863799283154e-05, | |
| "loss": 0.6332, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.0919952210274794e-05, | |
| "loss": 0.6323, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "learning_rate": 4.062126642771804e-05, | |
| "loss": 0.6274, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8055242390078917, | |
| "eval_f1": 0.8018609003788845, | |
| "eval_loss": 0.5278695225715637, | |
| "eval_precision": 0.8140213900969322, | |
| "eval_recall": 0.8055242390078917, | |
| "eval_runtime": 12.7959, | |
| "eval_samples_per_second": 138.638, | |
| "eval_steps_per_second": 2.188, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.16, | |
| "learning_rate": 4.032258064516129e-05, | |
| "loss": 0.6149, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "learning_rate": 4.002389486260454e-05, | |
| "loss": 0.6023, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 8.48, | |
| "learning_rate": 3.972520908004779e-05, | |
| "loss": 0.6354, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "learning_rate": 3.9426523297491045e-05, | |
| "loss": 0.6199, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.8, | |
| "learning_rate": 3.912783751493429e-05, | |
| "loss": 0.6421, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.882915173237754e-05, | |
| "loss": 0.6096, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "eval_accuracy": 0.8354002254791432, | |
| "eval_f1": 0.8321131246589322, | |
| "eval_loss": 0.47367918491363525, | |
| "eval_precision": 0.8336138678707014, | |
| "eval_recall": 0.8354002254791432, | |
| "eval_runtime": 12.2091, | |
| "eval_samples_per_second": 145.301, | |
| "eval_steps_per_second": 2.293, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 9.12, | |
| "learning_rate": 3.8530465949820786e-05, | |
| "loss": 0.6106, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 9.28, | |
| "learning_rate": 3.8231780167264044e-05, | |
| "loss": 0.5893, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 9.44, | |
| "learning_rate": 3.793309438470729e-05, | |
| "loss": 0.5924, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 9.6, | |
| "learning_rate": 3.763440860215054e-05, | |
| "loss": 0.6316, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.76, | |
| "learning_rate": 3.7335722819593785e-05, | |
| "loss": 0.5708, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.92, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.5906, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8382187147688839, | |
| "eval_f1": 0.8356686320601805, | |
| "eval_loss": 0.47918501496315, | |
| "eval_precision": 0.8381581586399207, | |
| "eval_recall": 0.8382187147688839, | |
| "eval_runtime": 12.6953, | |
| "eval_samples_per_second": 139.737, | |
| "eval_steps_per_second": 2.206, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 10.08, | |
| "learning_rate": 3.673835125448029e-05, | |
| "loss": 0.5816, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 10.24, | |
| "learning_rate": 3.643966547192354e-05, | |
| "loss": 0.6022, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 10.4, | |
| "learning_rate": 3.614097968936679e-05, | |
| "loss": 0.6111, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 10.56, | |
| "learning_rate": 3.5842293906810036e-05, | |
| "loss": 0.5935, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 10.72, | |
| "learning_rate": 3.554360812425329e-05, | |
| "loss": 0.5732, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.88, | |
| "learning_rate": 3.524492234169653e-05, | |
| "loss": 0.5839, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.99, | |
| "eval_accuracy": 0.822435174746336, | |
| "eval_f1": 0.8198839842783593, | |
| "eval_loss": 0.5092853903770447, | |
| "eval_precision": 0.832233741136264, | |
| "eval_recall": 0.822435174746336, | |
| "eval_runtime": 12.5736, | |
| "eval_samples_per_second": 141.089, | |
| "eval_steps_per_second": 2.227, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 3.494623655913979e-05, | |
| "loss": 0.5442, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 11.2, | |
| "learning_rate": 3.4647550776583035e-05, | |
| "loss": 0.5468, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 11.36, | |
| "learning_rate": 3.4348864994026287e-05, | |
| "loss": 0.5331, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 11.52, | |
| "learning_rate": 3.405017921146954e-05, | |
| "loss": 0.5448, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 11.68, | |
| "learning_rate": 3.375149342891278e-05, | |
| "loss": 0.5835, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 11.84, | |
| "learning_rate": 3.3452807646356034e-05, | |
| "loss": 0.5686, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "learning_rate": 3.3154121863799286e-05, | |
| "loss": 0.5478, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8432919954904171, | |
| "eval_f1": 0.84111751350394, | |
| "eval_loss": 0.46005183458328247, | |
| "eval_precision": 0.8428747917086379, | |
| "eval_recall": 0.8432919954904171, | |
| "eval_runtime": 12.454, | |
| "eval_samples_per_second": 142.444, | |
| "eval_steps_per_second": 2.248, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 3.285543608124254e-05, | |
| "loss": 0.5372, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 12.32, | |
| "learning_rate": 3.255675029868578e-05, | |
| "loss": 0.5204, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 12.48, | |
| "learning_rate": 3.2258064516129034e-05, | |
| "loss": 0.5426, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 12.64, | |
| "learning_rate": 3.195937873357228e-05, | |
| "loss": 0.567, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 12.8, | |
| "learning_rate": 3.1660692951015537e-05, | |
| "loss": 0.5446, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.96, | |
| "learning_rate": 3.136200716845878e-05, | |
| "loss": 0.5678, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "eval_accuracy": 0.826944757609921, | |
| "eval_f1": 0.823334784762628, | |
| "eval_loss": 0.5018390417098999, | |
| "eval_precision": 0.832241199269988, | |
| "eval_recall": 0.826944757609921, | |
| "eval_runtime": 12.8358, | |
| "eval_samples_per_second": 138.207, | |
| "eval_steps_per_second": 2.181, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 13.12, | |
| "learning_rate": 3.106332138590203e-05, | |
| "loss": 0.5366, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 3.0764635603345284e-05, | |
| "loss": 0.5299, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 13.44, | |
| "learning_rate": 3.046594982078853e-05, | |
| "loss": 0.5724, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 13.6, | |
| "learning_rate": 3.016726403823178e-05, | |
| "loss": 0.5284, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 13.76, | |
| "learning_rate": 2.9868578255675032e-05, | |
| "loss": 0.5602, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 13.92, | |
| "learning_rate": 2.9569892473118284e-05, | |
| "loss": 0.5586, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8438556933483653, | |
| "eval_f1": 0.8423489554185123, | |
| "eval_loss": 0.45030543208122253, | |
| "eval_precision": 0.8444016206511684, | |
| "eval_recall": 0.8438556933483653, | |
| "eval_runtime": 12.3871, | |
| "eval_samples_per_second": 143.214, | |
| "eval_steps_per_second": 2.26, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 14.08, | |
| "learning_rate": 2.9271206690561532e-05, | |
| "loss": 0.5111, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 14.24, | |
| "learning_rate": 2.897252090800478e-05, | |
| "loss": 0.5022, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.8673835125448028e-05, | |
| "loss": 0.5325, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 14.56, | |
| "learning_rate": 2.8375149342891276e-05, | |
| "loss": 0.5369, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 14.72, | |
| "learning_rate": 2.807646356033453e-05, | |
| "loss": 0.5464, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 14.88, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5267, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 14.99, | |
| "eval_accuracy": 0.8444193912063134, | |
| "eval_f1": 0.8423664554530824, | |
| "eval_loss": 0.4492391049861908, | |
| "eval_precision": 0.8415641336709727, | |
| "eval_recall": 0.8444193912063134, | |
| "eval_runtime": 12.4534, | |
| "eval_samples_per_second": 142.451, | |
| "eval_steps_per_second": 2.248, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 15.04, | |
| "learning_rate": 2.747909199522103e-05, | |
| "loss": 0.5125, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 15.2, | |
| "learning_rate": 2.718040621266428e-05, | |
| "loss": 0.4894, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 15.36, | |
| "learning_rate": 2.6881720430107527e-05, | |
| "loss": 0.5091, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 2.6583034647550775e-05, | |
| "loss": 0.5181, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 15.68, | |
| "learning_rate": 2.628434886499403e-05, | |
| "loss": 0.4984, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 15.84, | |
| "learning_rate": 2.5985663082437278e-05, | |
| "loss": 0.5181, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "learning_rate": 2.5686977299880526e-05, | |
| "loss": 0.5143, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8483652762119503, | |
| "eval_f1": 0.844154366160951, | |
| "eval_loss": 0.45428839325904846, | |
| "eval_precision": 0.845796346600765, | |
| "eval_recall": 0.8483652762119503, | |
| "eval_runtime": 12.1953, | |
| "eval_samples_per_second": 145.466, | |
| "eval_steps_per_second": 2.296, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 16.16, | |
| "learning_rate": 2.5388291517323774e-05, | |
| "loss": 0.4989, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 16.32, | |
| "learning_rate": 2.5089605734767026e-05, | |
| "loss": 0.471, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 16.48, | |
| "learning_rate": 2.4790919952210277e-05, | |
| "loss": 0.4896, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 16.64, | |
| "learning_rate": 2.4492234169653525e-05, | |
| "loss": 0.5324, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 16.8, | |
| "learning_rate": 2.4193548387096777e-05, | |
| "loss": 0.5097, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 16.96, | |
| "learning_rate": 2.3894862604540025e-05, | |
| "loss": 0.4608, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 16.99, | |
| "eval_accuracy": 0.842728297632469, | |
| "eval_f1": 0.8397872059697985, | |
| "eval_loss": 0.4615502953529358, | |
| "eval_precision": 0.8418539907290827, | |
| "eval_recall": 0.842728297632469, | |
| "eval_runtime": 12.0709, | |
| "eval_samples_per_second": 146.965, | |
| "eval_steps_per_second": 2.32, | |
| "step": 1062 | |
| }, | |
| { | |
| "epoch": 17.12, | |
| "learning_rate": 2.3596176821983273e-05, | |
| "loss": 0.4787, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 17.28, | |
| "learning_rate": 2.3297491039426525e-05, | |
| "loss": 0.4864, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 17.44, | |
| "learning_rate": 2.2998805256869773e-05, | |
| "loss": 0.5195, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 17.6, | |
| "learning_rate": 2.270011947431302e-05, | |
| "loss": 0.5127, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 17.76, | |
| "learning_rate": 2.2401433691756272e-05, | |
| "loss": 0.4907, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 17.92, | |
| "learning_rate": 2.2102747909199524e-05, | |
| "loss": 0.4914, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8500563697857948, | |
| "eval_f1": 0.8478805448558889, | |
| "eval_loss": 0.4476957321166992, | |
| "eval_precision": 0.8501152530032781, | |
| "eval_recall": 0.8500563697857948, | |
| "eval_runtime": 12.2539, | |
| "eval_samples_per_second": 144.771, | |
| "eval_steps_per_second": 2.285, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 18.08, | |
| "learning_rate": 2.1804062126642775e-05, | |
| "loss": 0.4733, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 18.24, | |
| "learning_rate": 2.1505376344086024e-05, | |
| "loss": 0.4717, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 18.4, | |
| "learning_rate": 2.120669056152927e-05, | |
| "loss": 0.4814, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 18.56, | |
| "learning_rate": 2.0908004778972523e-05, | |
| "loss": 0.4759, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 18.72, | |
| "learning_rate": 2.060931899641577e-05, | |
| "loss": 0.4735, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 18.88, | |
| "learning_rate": 2.031063321385902e-05, | |
| "loss": 0.4889, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 18.99, | |
| "eval_accuracy": 0.8337091319052987, | |
| "eval_f1": 0.8309994416840022, | |
| "eval_loss": 0.4738193154335022, | |
| "eval_precision": 0.8383422217934622, | |
| "eval_recall": 0.8337091319052987, | |
| "eval_runtime": 12.0406, | |
| "eval_samples_per_second": 147.335, | |
| "eval_steps_per_second": 2.325, | |
| "step": 1187 | |
| }, | |
| { | |
| "epoch": 19.04, | |
| "learning_rate": 2.001194743130227e-05, | |
| "loss": 0.491, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 19.2, | |
| "learning_rate": 1.9713261648745522e-05, | |
| "loss": 0.4481, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 19.36, | |
| "learning_rate": 1.941457586618877e-05, | |
| "loss": 0.4704, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 19.52, | |
| "learning_rate": 1.9115890083632022e-05, | |
| "loss": 0.4893, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 19.68, | |
| "learning_rate": 1.881720430107527e-05, | |
| "loss": 0.4685, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 19.84, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.4936, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "learning_rate": 1.821983273596177e-05, | |
| "loss": 0.4943, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8387824126268321, | |
| "eval_f1": 0.8352385955918987, | |
| "eval_loss": 0.4757649898529053, | |
| "eval_precision": 0.837337549123484, | |
| "eval_recall": 0.8387824126268321, | |
| "eval_runtime": 12.479, | |
| "eval_samples_per_second": 142.159, | |
| "eval_steps_per_second": 2.244, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 20.16, | |
| "learning_rate": 1.7921146953405018e-05, | |
| "loss": 0.452, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 20.32, | |
| "learning_rate": 1.7622461170848266e-05, | |
| "loss": 0.4755, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 20.48, | |
| "learning_rate": 1.7323775388291518e-05, | |
| "loss": 0.454, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 20.64, | |
| "learning_rate": 1.702508960573477e-05, | |
| "loss": 0.4267, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 20.8, | |
| "learning_rate": 1.6726403823178017e-05, | |
| "loss": 0.4787, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 20.96, | |
| "learning_rate": 1.642771804062127e-05, | |
| "loss": 0.4759, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 20.99, | |
| "eval_accuracy": 0.8478015783540023, | |
| "eval_f1": 0.8455888112946022, | |
| "eval_loss": 0.45496803522109985, | |
| "eval_precision": 0.8483696922558357, | |
| "eval_recall": 0.8478015783540023, | |
| "eval_runtime": 12.8996, | |
| "eval_samples_per_second": 137.523, | |
| "eval_steps_per_second": 2.171, | |
| "step": 1312 | |
| }, | |
| { | |
| "epoch": 21.12, | |
| "learning_rate": 1.6129032258064517e-05, | |
| "loss": 0.4409, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 21.28, | |
| "learning_rate": 1.5830346475507768e-05, | |
| "loss": 0.4618, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 21.44, | |
| "learning_rate": 1.5531660692951016e-05, | |
| "loss": 0.4426, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 21.6, | |
| "learning_rate": 1.5232974910394265e-05, | |
| "loss": 0.4595, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 21.76, | |
| "learning_rate": 1.4934289127837516e-05, | |
| "loss": 0.4569, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 21.92, | |
| "learning_rate": 1.4635603345280766e-05, | |
| "loss": 0.49, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8511837655016911, | |
| "eval_f1": 0.8488711109995941, | |
| "eval_loss": 0.4529497027397156, | |
| "eval_precision": 0.8520223099800657, | |
| "eval_recall": 0.8511837655016911, | |
| "eval_runtime": 12.6187, | |
| "eval_samples_per_second": 140.585, | |
| "eval_steps_per_second": 2.219, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 22.08, | |
| "learning_rate": 1.4336917562724014e-05, | |
| "loss": 0.4496, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 22.24, | |
| "learning_rate": 1.4038231780167265e-05, | |
| "loss": 0.4085, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 22.4, | |
| "learning_rate": 1.3739545997610515e-05, | |
| "loss": 0.44, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 22.56, | |
| "learning_rate": 1.3440860215053763e-05, | |
| "loss": 0.4496, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 22.72, | |
| "learning_rate": 1.3142174432497015e-05, | |
| "loss": 0.4672, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 22.88, | |
| "learning_rate": 1.2843488649940263e-05, | |
| "loss": 0.4546, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 22.99, | |
| "eval_accuracy": 0.8472378804960541, | |
| "eval_f1": 0.8447498091306326, | |
| "eval_loss": 0.45672544836997986, | |
| "eval_precision": 0.8455778427961377, | |
| "eval_recall": 0.8472378804960541, | |
| "eval_runtime": 12.4744, | |
| "eval_samples_per_second": 142.211, | |
| "eval_steps_per_second": 2.245, | |
| "step": 1437 | |
| }, | |
| { | |
| "epoch": 23.04, | |
| "learning_rate": 1.2544802867383513e-05, | |
| "loss": 0.458, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 23.2, | |
| "learning_rate": 1.2246117084826763e-05, | |
| "loss": 0.4388, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 23.36, | |
| "learning_rate": 1.1947431302270013e-05, | |
| "loss": 0.4351, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 23.52, | |
| "learning_rate": 1.1648745519713262e-05, | |
| "loss": 0.4426, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 23.68, | |
| "learning_rate": 1.135005973715651e-05, | |
| "loss": 0.4818, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 23.84, | |
| "learning_rate": 1.1051373954599762e-05, | |
| "loss": 0.4129, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "learning_rate": 1.0752688172043012e-05, | |
| "loss": 0.4638, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8449830890642616, | |
| "eval_f1": 0.8431202612399936, | |
| "eval_loss": 0.4597967863082886, | |
| "eval_precision": 0.8437884301770292, | |
| "eval_recall": 0.8449830890642616, | |
| "eval_runtime": 12.8591, | |
| "eval_samples_per_second": 137.956, | |
| "eval_steps_per_second": 2.177, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 24.16, | |
| "learning_rate": 1.0454002389486262e-05, | |
| "loss": 0.4742, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 24.32, | |
| "learning_rate": 1.015531660692951e-05, | |
| "loss": 0.4419, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 24.48, | |
| "learning_rate": 9.856630824372761e-06, | |
| "loss": 0.437, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 24.64, | |
| "learning_rate": 9.557945041816011e-06, | |
| "loss": 0.442, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 24.8, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.45, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 24.96, | |
| "learning_rate": 8.960573476702509e-06, | |
| "loss": 0.4591, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 24.99, | |
| "eval_accuracy": 0.8528748590755355, | |
| "eval_f1": 0.8507379545847151, | |
| "eval_loss": 0.4654536843299866, | |
| "eval_precision": 0.8539198039435939, | |
| "eval_recall": 0.8528748590755355, | |
| "eval_runtime": 12.4122, | |
| "eval_samples_per_second": 142.924, | |
| "eval_steps_per_second": 2.256, | |
| "step": 1562 | |
| }, | |
| { | |
| "epoch": 25.12, | |
| "learning_rate": 8.661887694145759e-06, | |
| "loss": 0.4101, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 25.28, | |
| "learning_rate": 8.363201911589009e-06, | |
| "loss": 0.4295, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 25.44, | |
| "learning_rate": 8.064516129032258e-06, | |
| "loss": 0.4206, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 25.6, | |
| "learning_rate": 7.765830346475508e-06, | |
| "loss": 0.4421, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 25.76, | |
| "learning_rate": 7.467144563918758e-06, | |
| "loss": 0.4256, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 25.92, | |
| "learning_rate": 7.168458781362007e-06, | |
| "loss": 0.413, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.85456595264938, | |
| "eval_f1": 0.851427482739825, | |
| "eval_loss": 0.4512122571468353, | |
| "eval_precision": 0.8526202227777903, | |
| "eval_recall": 0.85456595264938, | |
| "eval_runtime": 12.0942, | |
| "eval_samples_per_second": 146.682, | |
| "eval_steps_per_second": 2.315, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 26.08, | |
| "learning_rate": 6.869772998805258e-06, | |
| "loss": 0.4169, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 26.24, | |
| "learning_rate": 6.5710872162485075e-06, | |
| "loss": 0.425, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 26.4, | |
| "learning_rate": 6.2724014336917564e-06, | |
| "loss": 0.432, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 26.56, | |
| "learning_rate": 5.973715651135006e-06, | |
| "loss": 0.4187, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 26.72, | |
| "learning_rate": 5.675029868578255e-06, | |
| "loss": 0.4282, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 26.88, | |
| "learning_rate": 5.376344086021506e-06, | |
| "loss": 0.4268, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 26.99, | |
| "eval_accuracy": 0.8517474633596392, | |
| "eval_f1": 0.8496240747782253, | |
| "eval_loss": 0.4510926604270935, | |
| "eval_precision": 0.8505750842630703, | |
| "eval_recall": 0.8517474633596392, | |
| "eval_runtime": 12.8047, | |
| "eval_samples_per_second": 138.543, | |
| "eval_steps_per_second": 2.187, | |
| "step": 1687 | |
| }, | |
| { | |
| "epoch": 27.04, | |
| "learning_rate": 5.077658303464755e-06, | |
| "loss": 0.4294, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 27.2, | |
| "learning_rate": 4.7789725209080055e-06, | |
| "loss": 0.4402, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 27.36, | |
| "learning_rate": 4.4802867383512545e-06, | |
| "loss": 0.4496, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 27.52, | |
| "learning_rate": 4.181600955794504e-06, | |
| "loss": 0.4312, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 27.68, | |
| "learning_rate": 3.882915173237754e-06, | |
| "loss": 0.3903, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 27.84, | |
| "learning_rate": 3.5842293906810035e-06, | |
| "loss": 0.4291, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "learning_rate": 3.2855436081242537e-06, | |
| "loss": 0.4497, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.855129650507328, | |
| "eval_f1": 0.8517741167024618, | |
| "eval_loss": 0.4594862163066864, | |
| "eval_precision": 0.853570788548253, | |
| "eval_recall": 0.855129650507328, | |
| "eval_runtime": 12.3974, | |
| "eval_samples_per_second": 143.095, | |
| "eval_steps_per_second": 2.259, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 28.16, | |
| "learning_rate": 2.986857825567503e-06, | |
| "loss": 0.4143, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 28.32, | |
| "learning_rate": 2.688172043010753e-06, | |
| "loss": 0.438, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 28.48, | |
| "learning_rate": 2.3894862604540028e-06, | |
| "loss": 0.429, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 28.64, | |
| "learning_rate": 2.090800477897252e-06, | |
| "loss": 0.4248, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 28.8, | |
| "learning_rate": 1.7921146953405017e-06, | |
| "loss": 0.4295, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 28.96, | |
| "learning_rate": 1.4934289127837516e-06, | |
| "loss": 0.4183, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 28.99, | |
| "eval_accuracy": 0.8540022547914318, | |
| "eval_f1": 0.8512321886354705, | |
| "eval_loss": 0.45555904507637024, | |
| "eval_precision": 0.8532475786105113, | |
| "eval_recall": 0.8540022547914318, | |
| "eval_runtime": 12.7702, | |
| "eval_samples_per_second": 138.917, | |
| "eval_steps_per_second": 2.193, | |
| "step": 1812 | |
| }, | |
| { | |
| "epoch": 29.12, | |
| "learning_rate": 1.1947431302270014e-06, | |
| "loss": 0.4302, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 29.28, | |
| "learning_rate": 8.960573476702509e-07, | |
| "loss": 0.4056, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 29.44, | |
| "learning_rate": 5.973715651135007e-07, | |
| "loss": 0.408, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 29.6, | |
| "learning_rate": 2.9868578255675034e-07, | |
| "loss": 0.4049, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "learning_rate": 0.0, | |
| "loss": 0.4211, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "eval_accuracy": 0.8528748590755355, | |
| "eval_f1": 0.8502571819421584, | |
| "eval_loss": 0.45673882961273193, | |
| "eval_precision": 0.8522521708294911, | |
| "eval_recall": 0.8528748590755355, | |
| "eval_runtime": 12.5344, | |
| "eval_samples_per_second": 141.531, | |
| "eval_steps_per_second": 2.234, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 29.76, | |
| "step": 1860, | |
| "total_flos": 1.5459140620853969e+19, | |
| "train_loss": 0.628424834948714, | |
| "train_runtime": 5258.9548, | |
| "train_samples_per_second": 91.056, | |
| "train_steps_per_second": 0.354 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1860, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 500, | |
| "total_flos": 1.5459140620853969e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |