| { | |
| "best_metric": 0.23673731088638306, | |
| "best_model_checkpoint": "/mnt/disk_victorlebos/data/datarmor/models/dinov2-large-2024_05_23-drone_batch-size512_epochs50_freeze/checkpoint-1400", | |
| "epoch": 50.0, | |
| "eval_steps": 500, | |
| "global_step": 1400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.012405938580435224, | |
| "eval_f1_macro": 0.40667627783698285, | |
| "eval_f1_micro": 0.5738973203699311, | |
| "eval_loss": 0.5951732397079468, | |
| "eval_roc_auc": 0.752833094536879, | |
| "eval_runtime": 32.6366, | |
| "eval_samples_per_second": 150.659, | |
| "eval_steps_per_second": 0.306, | |
| "learning_rate": 0.001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.06975798250966037, | |
| "eval_f1_macro": 0.4367882492755507, | |
| "eval_f1_micro": 0.7307120964254151, | |
| "eval_loss": 0.4730209410190582, | |
| "eval_roc_auc": 0.8401493620198748, | |
| "eval_runtime": 32.801, | |
| "eval_samples_per_second": 149.904, | |
| "eval_steps_per_second": 0.305, | |
| "learning_rate": 0.001, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.10738255033557047, | |
| "eval_f1_macro": 0.37702459211637257, | |
| "eval_f1_micro": 0.7498981835953409, | |
| "eval_loss": 0.3240152895450592, | |
| "eval_roc_auc": 0.8377639463906806, | |
| "eval_runtime": 33.9297, | |
| "eval_samples_per_second": 144.917, | |
| "eval_steps_per_second": 0.295, | |
| "learning_rate": 0.001, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.11795810453528574, | |
| "eval_f1_macro": 0.3710481900670742, | |
| "eval_f1_micro": 0.7521195160095482, | |
| "eval_loss": 0.2770342230796814, | |
| "eval_roc_auc": 0.8371968879000634, | |
| "eval_runtime": 33.1578, | |
| "eval_samples_per_second": 148.291, | |
| "eval_steps_per_second": 0.302, | |
| "learning_rate": 0.001, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.11958511287370348, | |
| "eval_f1_macro": 0.3714736793659693, | |
| "eval_f1_micro": 0.7507292550220328, | |
| "eval_loss": 0.25879302620887756, | |
| "eval_roc_auc": 0.8353003094576528, | |
| "eval_runtime": 33.1064, | |
| "eval_samples_per_second": 148.521, | |
| "eval_steps_per_second": 0.302, | |
| "learning_rate": 0.001, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.12182224933902787, | |
| "eval_f1_macro": 0.36304822534346387, | |
| "eval_f1_micro": 0.7520252586099456, | |
| "eval_loss": 0.25328728556632996, | |
| "eval_roc_auc": 0.8353620986749458, | |
| "eval_runtime": 33.4017, | |
| "eval_samples_per_second": 147.208, | |
| "eval_steps_per_second": 0.299, | |
| "learning_rate": 0.001, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.11531421598535692, | |
| "eval_f1_macro": 0.3646331511607325, | |
| "eval_f1_micro": 0.7517183920016662, | |
| "eval_loss": 0.25132349133491516, | |
| "eval_roc_auc": 0.834652371152471, | |
| "eval_runtime": 33.338, | |
| "eval_samples_per_second": 147.489, | |
| "eval_steps_per_second": 0.3, | |
| "learning_rate": 0.001, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.12283912955053895, | |
| "eval_f1_macro": 0.38940077262215617, | |
| "eval_f1_micro": 0.7576399892988702, | |
| "eval_loss": 0.2507544159889221, | |
| "eval_roc_auc": 0.8407135898239845, | |
| "eval_runtime": 33.4587, | |
| "eval_samples_per_second": 146.957, | |
| "eval_steps_per_second": 0.299, | |
| "learning_rate": 0.001, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.12751677852348994, | |
| "eval_f1_macro": 0.38290945223752887, | |
| "eval_f1_micro": 0.7549859932265752, | |
| "eval_loss": 0.24785615503787994, | |
| "eval_roc_auc": 0.8360210323976333, | |
| "eval_runtime": 34.4389, | |
| "eval_samples_per_second": 142.775, | |
| "eval_steps_per_second": 0.29, | |
| "learning_rate": 0.001, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.12649989831197886, | |
| "eval_f1_macro": 0.37973264961121395, | |
| "eval_f1_micro": 0.7583163191651716, | |
| "eval_loss": 0.2480766475200653, | |
| "eval_roc_auc": 0.8407307602236042, | |
| "eval_runtime": 34.0205, | |
| "eval_samples_per_second": 144.531, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.12426276184665447, | |
| "eval_f1_macro": 0.3964288145693209, | |
| "eval_f1_micro": 0.7600958878849345, | |
| "eval_loss": 0.24667006731033325, | |
| "eval_roc_auc": 0.8431424613547966, | |
| "eval_runtime": 34.2677, | |
| "eval_samples_per_second": 143.488, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.12507626601586333, | |
| "eval_f1_macro": 0.3733203958034908, | |
| "eval_f1_micro": 0.7564640698455339, | |
| "eval_loss": 0.2459569126367569, | |
| "eval_roc_auc": 0.836213120741293, | |
| "eval_runtime": 34.8153, | |
| "eval_samples_per_second": 141.231, | |
| "eval_steps_per_second": 0.287, | |
| "learning_rate": 0.001, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.1297539149888143, | |
| "eval_f1_macro": 0.38618999344086086, | |
| "eval_f1_micro": 0.7581923944769908, | |
| "eval_loss": 0.245611771941185, | |
| "eval_roc_auc": 0.839925579714772, | |
| "eval_runtime": 34.1156, | |
| "eval_samples_per_second": 144.128, | |
| "eval_steps_per_second": 0.293, | |
| "learning_rate": 0.001, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.13707545251169412, | |
| "eval_f1_macro": 0.37084554766098704, | |
| "eval_f1_micro": 0.7526021832952525, | |
| "eval_loss": 0.24649737775325775, | |
| "eval_roc_auc": 0.8323046017083424, | |
| "eval_runtime": 34.0576, | |
| "eval_samples_per_second": 144.373, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.1271100264388855, | |
| "eval_f1_macro": 0.37953234953900117, | |
| "eval_f1_micro": 0.7540528606572888, | |
| "eval_loss": 0.24523988366127014, | |
| "eval_roc_auc": 0.8343517118764396, | |
| "eval_runtime": 34.2408, | |
| "eval_samples_per_second": 143.601, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.1293471629042099, | |
| "eval_f1_macro": 0.39042586476441543, | |
| "eval_f1_micro": 0.7597242635642867, | |
| "eval_loss": 0.24370642006397247, | |
| "eval_roc_auc": 0.8408989171069663, | |
| "eval_runtime": 34.1492, | |
| "eval_samples_per_second": 143.986, | |
| "eval_steps_per_second": 0.293, | |
| "learning_rate": 0.001, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.13158429936953428, | |
| "eval_f1_macro": 0.38542350135117487, | |
| "eval_f1_micro": 0.7525727259224682, | |
| "eval_loss": 0.24466517567634583, | |
| "eval_roc_auc": 0.8317419799054098, | |
| "eval_runtime": 33.8536, | |
| "eval_samples_per_second": 145.243, | |
| "eval_steps_per_second": 0.295, | |
| "learning_rate": 0.001, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 17.857142857142858, | |
| "grad_norm": 0.09434398263692856, | |
| "learning_rate": 0.001, | |
| "loss": 0.3126, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.133211307707952, | |
| "eval_f1_macro": 0.35783734462173733, | |
| "eval_f1_micro": 0.7534316217590239, | |
| "eval_loss": 0.24544650316238403, | |
| "eval_roc_auc": 0.8325846543647923, | |
| "eval_runtime": 33.8618, | |
| "eval_samples_per_second": 145.208, | |
| "eval_steps_per_second": 0.295, | |
| "learning_rate": 0.001, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.13239780353874314, | |
| "eval_f1_macro": 0.3694145346248099, | |
| "eval_f1_micro": 0.7568417082268136, | |
| "eval_loss": 0.2440878450870514, | |
| "eval_roc_auc": 0.8367437261179794, | |
| "eval_runtime": 33.9612, | |
| "eval_samples_per_second": 144.783, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.13605857230018303, | |
| "eval_f1_macro": 0.3768127127776539, | |
| "eval_f1_micro": 0.750895096799091, | |
| "eval_loss": 0.2453632354736328, | |
| "eval_roc_auc": 0.8288096279784166, | |
| "eval_runtime": 33.6713, | |
| "eval_samples_per_second": 146.03, | |
| "eval_steps_per_second": 0.297, | |
| "learning_rate": 0.001, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.12487288997356112, | |
| "eval_f1_macro": 0.38961590782494593, | |
| "eval_f1_micro": 0.760243826841616, | |
| "eval_loss": 0.24377579987049103, | |
| "eval_roc_auc": 0.8415825201166579, | |
| "eval_runtime": 33.7544, | |
| "eval_samples_per_second": 145.67, | |
| "eval_steps_per_second": 0.296, | |
| "learning_rate": 0.001, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.13016066707341875, | |
| "eval_f1_macro": 0.3715634230883189, | |
| "eval_f1_micro": 0.7576183975637929, | |
| "eval_loss": 0.24192409217357635, | |
| "eval_roc_auc": 0.8368051515288276, | |
| "eval_runtime": 33.7095, | |
| "eval_samples_per_second": 145.864, | |
| "eval_steps_per_second": 0.297, | |
| "learning_rate": 0.001, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.12649989831197886, | |
| "eval_f1_macro": 0.3880375815747224, | |
| "eval_f1_micro": 0.7628996647313762, | |
| "eval_loss": 0.24348826706409454, | |
| "eval_roc_auc": 0.845384034822261, | |
| "eval_runtime": 33.9782, | |
| "eval_samples_per_second": 144.711, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.1342281879194631, | |
| "eval_f1_macro": 0.3896884130115941, | |
| "eval_f1_micro": 0.7561114991428027, | |
| "eval_loss": 0.2413305789232254, | |
| "eval_roc_auc": 0.8344032230752988, | |
| "eval_runtime": 34.4343, | |
| "eval_samples_per_second": 142.794, | |
| "eval_steps_per_second": 0.29, | |
| "learning_rate": 0.001, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.1297539149888143, | |
| "eval_f1_macro": 0.38267978517684004, | |
| "eval_f1_micro": 0.7599182173024102, | |
| "eval_loss": 0.24189460277557373, | |
| "eval_roc_auc": 0.8414795784567333, | |
| "eval_runtime": 34.3901, | |
| "eval_samples_per_second": 142.977, | |
| "eval_steps_per_second": 0.291, | |
| "learning_rate": 0.001, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.12670327435428105, | |
| "eval_f1_macro": 0.3971421437602147, | |
| "eval_f1_micro": 0.7593076827294236, | |
| "eval_loss": 0.2437727451324463, | |
| "eval_roc_auc": 0.8401496844846781, | |
| "eval_runtime": 34.2926, | |
| "eval_samples_per_second": 143.384, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.1309741712426276, | |
| "eval_f1_macro": 0.38383597863653807, | |
| "eval_f1_micro": 0.761437908496732, | |
| "eval_loss": 0.24182096123695374, | |
| "eval_roc_auc": 0.8421530853512137, | |
| "eval_runtime": 34.6404, | |
| "eval_samples_per_second": 141.944, | |
| "eval_steps_per_second": 0.289, | |
| "learning_rate": 0.001, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.13341468375025423, | |
| "eval_f1_macro": 0.3792682503180625, | |
| "eval_f1_micro": 0.7498440155769273, | |
| "eval_loss": 0.24316559731960297, | |
| "eval_roc_auc": 0.8275284660741716, | |
| "eval_runtime": 33.9704, | |
| "eval_samples_per_second": 144.743, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.1366687004270897, | |
| "eval_f1_macro": 0.39596794972011545, | |
| "eval_f1_micro": 0.7621594930458399, | |
| "eval_loss": 0.24201267957687378, | |
| "eval_roc_auc": 0.8436467097327637, | |
| "eval_runtime": 34.1508, | |
| "eval_samples_per_second": 143.979, | |
| "eval_steps_per_second": 0.293, | |
| "learning_rate": 0.001, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.14236322961155176, | |
| "eval_f1_macro": 0.38596411111358153, | |
| "eval_f1_micro": 0.7619565217391304, | |
| "eval_loss": 0.2406790852546692, | |
| "eval_roc_auc": 0.840430919512073, | |
| "eval_runtime": 34.2312, | |
| "eval_samples_per_second": 143.641, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.13280455562334756, | |
| "eval_f1_macro": 0.3928781445591724, | |
| "eval_f1_micro": 0.7611869607298037, | |
| "eval_loss": 0.24222084879875183, | |
| "eval_roc_auc": 0.8428517162907542, | |
| "eval_runtime": 34.0721, | |
| "eval_samples_per_second": 144.311, | |
| "eval_steps_per_second": 0.293, | |
| "learning_rate": 0.001, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.13117754728492984, | |
| "eval_f1_macro": 0.3912203123758987, | |
| "eval_f1_micro": 0.7516135926480015, | |
| "eval_loss": 0.24304261803627014, | |
| "eval_roc_auc": 0.8298242087648536, | |
| "eval_runtime": 33.969, | |
| "eval_samples_per_second": 144.75, | |
| "eval_steps_per_second": 0.294, | |
| "learning_rate": 0.001, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.13016066707341875, | |
| "eval_f1_macro": 0.38844227395152936, | |
| "eval_f1_micro": 0.758885526453094, | |
| "eval_loss": 0.24139608442783356, | |
| "eval_roc_auc": 0.838798415911255, | |
| "eval_runtime": 34.3634, | |
| "eval_samples_per_second": 143.088, | |
| "eval_steps_per_second": 0.291, | |
| "learning_rate": 0.001, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.1354484441732764, | |
| "eval_f1_macro": 0.4037409737349212, | |
| "eval_f1_micro": 0.7624706542289075, | |
| "eval_loss": 0.24039919674396515, | |
| "eval_roc_auc": 0.8419399356299166, | |
| "eval_runtime": 34.2464, | |
| "eval_samples_per_second": 143.577, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.12995729103111653, | |
| "eval_f1_macro": 0.3973020120442106, | |
| "eval_f1_micro": 0.7601615858737297, | |
| "eval_loss": 0.24134761095046997, | |
| "eval_roc_auc": 0.8400403455705201, | |
| "eval_runtime": 34.3251, | |
| "eval_samples_per_second": 143.248, | |
| "eval_steps_per_second": 0.291, | |
| "learning_rate": 0.001, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 35.714285714285715, | |
| "grad_norm": 0.08046075701713562, | |
| "learning_rate": 0.001, | |
| "loss": 0.2465, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.13565182021557862, | |
| "eval_f1_macro": 0.38761085480429286, | |
| "eval_f1_micro": 0.7622066694112803, | |
| "eval_loss": 0.24192169308662415, | |
| "eval_roc_auc": 0.8435798471665079, | |
| "eval_runtime": 34.1038, | |
| "eval_samples_per_second": 144.177, | |
| "eval_steps_per_second": 0.293, | |
| "learning_rate": 0.001, | |
| "step": 1008 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.1342281879194631, | |
| "eval_f1_macro": 0.3992187594370792, | |
| "eval_f1_micro": 0.7598352387357096, | |
| "eval_loss": 0.2399486005306244, | |
| "eval_roc_auc": 0.8380691834023499, | |
| "eval_runtime": 34.6394, | |
| "eval_samples_per_second": 141.948, | |
| "eval_steps_per_second": 0.289, | |
| "learning_rate": 0.001, | |
| "step": 1036 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.13300793166564978, | |
| "eval_f1_macro": 0.3932700433432016, | |
| "eval_f1_micro": 0.7607364527387098, | |
| "eval_loss": 0.24004822969436646, | |
| "eval_roc_auc": 0.8397074475961233, | |
| "eval_runtime": 34.2918, | |
| "eval_samples_per_second": 143.387, | |
| "eval_steps_per_second": 0.292, | |
| "learning_rate": 0.001, | |
| "step": 1064 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.13890583689241406, | |
| "eval_f1_macro": 0.4007929579258356, | |
| "eval_f1_micro": 0.7619087275149901, | |
| "eval_loss": 0.24091550707817078, | |
| "eval_roc_auc": 0.8411762713701608, | |
| "eval_runtime": 34.4221, | |
| "eval_samples_per_second": 142.844, | |
| "eval_steps_per_second": 0.291, | |
| "learning_rate": 0.001, | |
| "step": 1092 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.1354484441732764, | |
| "eval_f1_macro": 0.39250375468507387, | |
| "eval_f1_micro": 0.76, | |
| "eval_loss": 0.23991511762142181, | |
| "eval_roc_auc": 0.8378351644204551, | |
| "eval_runtime": 35.4899, | |
| "eval_samples_per_second": 138.546, | |
| "eval_steps_per_second": 0.282, | |
| "learning_rate": 0.001, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.12487288997356112, | |
| "eval_f1_macro": 0.40608061408264917, | |
| "eval_f1_micro": 0.7639710985018574, | |
| "eval_loss": 0.2422637641429901, | |
| "eval_roc_auc": 0.8463905306427496, | |
| "eval_runtime": 35.0605, | |
| "eval_samples_per_second": 140.243, | |
| "eval_steps_per_second": 0.285, | |
| "learning_rate": 0.001, | |
| "step": 1148 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.1309741712426276, | |
| "eval_f1_macro": 0.4005098857996497, | |
| "eval_f1_micro": 0.7568840806286871, | |
| "eval_loss": 0.24256455898284912, | |
| "eval_roc_auc": 0.8377674429208019, | |
| "eval_runtime": 35.1895, | |
| "eval_samples_per_second": 139.729, | |
| "eval_steps_per_second": 0.284, | |
| "learning_rate": 0.001, | |
| "step": 1176 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.13361805979255645, | |
| "eval_f1_macro": 0.4007981173529554, | |
| "eval_f1_micro": 0.7594289817122102, | |
| "eval_loss": 0.23922023177146912, | |
| "eval_roc_auc": 0.8368935200169594, | |
| "eval_runtime": 34.9621, | |
| "eval_samples_per_second": 140.638, | |
| "eval_steps_per_second": 0.286, | |
| "learning_rate": 0.001, | |
| "step": 1204 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.13036404311572097, | |
| "eval_f1_macro": 0.40641694858015515, | |
| "eval_f1_micro": 0.7576905272903253, | |
| "eval_loss": 0.24184103310108185, | |
| "eval_roc_auc": 0.8364958212082838, | |
| "eval_runtime": 35.0243, | |
| "eval_samples_per_second": 140.388, | |
| "eval_steps_per_second": 0.286, | |
| "learning_rate": 0.001, | |
| "step": 1232 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.13788895668090298, | |
| "eval_f1_macro": 0.39055068831340933, | |
| "eval_f1_micro": 0.7591085068536151, | |
| "eval_loss": 0.24105145037174225, | |
| "eval_roc_auc": 0.8384187060666997, | |
| "eval_runtime": 34.7759, | |
| "eval_samples_per_second": 141.391, | |
| "eval_steps_per_second": 0.288, | |
| "learning_rate": 0.001, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.13626194834248526, | |
| "eval_f1_macro": 0.4106196361694743, | |
| "eval_f1_micro": 0.7653508320819534, | |
| "eval_loss": 0.23963303864002228, | |
| "eval_roc_auc": 0.8457236836435186, | |
| "eval_runtime": 34.9314, | |
| "eval_samples_per_second": 140.762, | |
| "eval_steps_per_second": 0.286, | |
| "learning_rate": 0.001, | |
| "step": 1288 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.13260117958104536, | |
| "eval_f1_macro": 0.3967990889217657, | |
| "eval_f1_micro": 0.7575076348829317, | |
| "eval_loss": 0.23957742750644684, | |
| "eval_roc_auc": 0.8348926760093537, | |
| "eval_runtime": 35.1971, | |
| "eval_samples_per_second": 139.699, | |
| "eval_steps_per_second": 0.284, | |
| "learning_rate": 0.001, | |
| "step": 1316 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.12873703477730322, | |
| "eval_f1_macro": 0.38777990454974365, | |
| "eval_f1_micro": 0.7563947423325684, | |
| "eval_loss": 0.24231907725334167, | |
| "eval_roc_auc": 0.8372881264708554, | |
| "eval_runtime": 106.544, | |
| "eval_samples_per_second": 46.15, | |
| "eval_steps_per_second": 0.094, | |
| "learning_rate": 0.001, | |
| "step": 1344 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.13300793166564978, | |
| "eval_f1_macro": 0.40266317126303974, | |
| "eval_f1_micro": 0.7608376348147216, | |
| "eval_loss": 0.23978127539157867, | |
| "eval_roc_auc": 0.8389943850191152, | |
| "eval_runtime": 103.5302, | |
| "eval_samples_per_second": 47.493, | |
| "eval_steps_per_second": 0.097, | |
| "learning_rate": 0.001, | |
| "step": 1372 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.14236322961155176, | |
| "eval_f1_macro": 0.4087415721658059, | |
| "eval_f1_micro": 0.7652267908369019, | |
| "eval_loss": 0.23673731088638306, | |
| "eval_roc_auc": 0.8435746322832197, | |
| "eval_runtime": 102.3756, | |
| "eval_samples_per_second": 48.029, | |
| "eval_steps_per_second": 0.098, | |
| "learning_rate": 0.0001, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "learning_rate": 0.0001, | |
| "step": 1400, | |
| "total_flos": 9.998216165993483e+19, | |
| "train_loss": 0.2689315250941685, | |
| "train_runtime": 8372.8151, | |
| "train_samples_per_second": 84.762, | |
| "train_steps_per_second": 0.167 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 1400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 50, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 10, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.998216165993483e+19, | |
| "train_batch_size": 512, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |