| { | |
| "best_metric": 0.9049755301794453, | |
| "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-lora-medmnistv2/checkpoint-2180", | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 2180, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 5.959507465362549, | |
| "learning_rate": 0.004977064220183487, | |
| "loss": 1.9585, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 3.8976335525512695, | |
| "learning_rate": 0.004954128440366973, | |
| "loss": 1.3768, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 2.9822118282318115, | |
| "learning_rate": 0.004931192660550459, | |
| "loss": 1.4236, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 3.5010669231414795, | |
| "learning_rate": 0.004908256880733945, | |
| "loss": 1.2595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 4.538541793823242, | |
| "learning_rate": 0.004887614678899083, | |
| "loss": 1.4165, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 3.172377586364746, | |
| "learning_rate": 0.004864678899082569, | |
| "loss": 1.1823, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 2.388909101486206, | |
| "learning_rate": 0.004841743119266055, | |
| "loss": 1.1399, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 2.9836621284484863, | |
| "learning_rate": 0.004818807339449541, | |
| "loss": 1.1484, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 2.9791626930236816, | |
| "learning_rate": 0.004795871559633028, | |
| "loss": 1.1652, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 2.8931291103363037, | |
| "learning_rate": 0.004772935779816514, | |
| "loss": 1.0614, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 4.281805515289307, | |
| "learning_rate": 0.00475, | |
| "loss": 1.1816, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 1.8973846435546875, | |
| "learning_rate": 0.0047270642201834865, | |
| "loss": 1.0441, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 2.476250648498535, | |
| "learning_rate": 0.004704128440366973, | |
| "loss": 1.1724, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 3.405545711517334, | |
| "learning_rate": 0.004681192660550459, | |
| "loss": 1.1089, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 3.545285940170288, | |
| "learning_rate": 0.0046582568807339445, | |
| "loss": 0.9702, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 2.000765085220337, | |
| "learning_rate": 0.004635321100917431, | |
| "loss": 1.0029, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 3.3316946029663086, | |
| "learning_rate": 0.004612385321100918, | |
| "loss": 1.003, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 2.2348740100860596, | |
| "learning_rate": 0.004589449541284404, | |
| "loss": 1.0428, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 2.1600568294525146, | |
| "learning_rate": 0.00456651376146789, | |
| "loss": 1.0674, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 3.6075286865234375, | |
| "learning_rate": 0.0045435779816513765, | |
| "loss": 1.0286, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 1.731745719909668, | |
| "learning_rate": 0.004520642201834862, | |
| "loss": 0.9608, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7765089722675367, | |
| "eval_f1": 0.7007285514340752, | |
| "eval_loss": 0.6055155992507935, | |
| "eval_precision": 0.7235333775207775, | |
| "eval_recall": 0.7232886628310071, | |
| "eval_runtime": 20.7254, | |
| "eval_samples_per_second": 118.309, | |
| "eval_steps_per_second": 7.43, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 2.186959981918335, | |
| "learning_rate": 0.004497706422018349, | |
| "loss": 1.0296, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 1.06, | |
| "grad_norm": 2.0718557834625244, | |
| "learning_rate": 0.0044747706422018346, | |
| "loss": 0.9602, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "grad_norm": 2.098830461502075, | |
| "learning_rate": 0.004451834862385321, | |
| "loss": 0.9453, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "grad_norm": 2.486630439758301, | |
| "learning_rate": 0.004428899082568808, | |
| "loss": 0.9209, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "grad_norm": 2.0856552124023438, | |
| "learning_rate": 0.0044059633027522934, | |
| "loss": 1.0935, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "grad_norm": 1.6093757152557373, | |
| "learning_rate": 0.00438302752293578, | |
| "loss": 1.0387, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.28, | |
| "grad_norm": 1.9845185279846191, | |
| "learning_rate": 0.004360091743119266, | |
| "loss": 0.9536, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "grad_norm": 2.10725474357605, | |
| "learning_rate": 0.004337155963302752, | |
| "loss": 0.8167, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "grad_norm": 2.1504321098327637, | |
| "learning_rate": 0.004314220183486239, | |
| "loss": 0.9638, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "grad_norm": 1.8799842596054077, | |
| "learning_rate": 0.004291284403669725, | |
| "loss": 0.9503, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "grad_norm": 2.466273069381714, | |
| "learning_rate": 0.004268348623853211, | |
| "loss": 0.9487, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.51, | |
| "grad_norm": 1.635208249092102, | |
| "learning_rate": 0.004245412844036698, | |
| "loss": 0.9618, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "grad_norm": 1.8513455390930176, | |
| "learning_rate": 0.0042224770642201835, | |
| "loss": 0.9647, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.61, | |
| "grad_norm": 2.562163829803467, | |
| "learning_rate": 0.004199541284403669, | |
| "loss": 0.9159, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.65, | |
| "grad_norm": 3.5535786151885986, | |
| "learning_rate": 0.004176605504587156, | |
| "loss": 1.109, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "grad_norm": 2.6485819816589355, | |
| "learning_rate": 0.004153669724770642, | |
| "loss": 1.0044, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.74, | |
| "grad_norm": 2.7095954418182373, | |
| "learning_rate": 0.004130733944954129, | |
| "loss": 0.9123, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "grad_norm": 1.9968432188034058, | |
| "learning_rate": 0.004107798165137615, | |
| "loss": 0.9469, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "grad_norm": 2.2975969314575195, | |
| "learning_rate": 0.004084862385321101, | |
| "loss": 0.9568, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.88, | |
| "grad_norm": 3.4922454357147217, | |
| "learning_rate": 0.004061926605504587, | |
| "loss": 0.9636, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "grad_norm": 1.8210103511810303, | |
| "learning_rate": 0.004038990825688074, | |
| "loss": 0.9296, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "grad_norm": 2.032224655151367, | |
| "learning_rate": 0.004016055045871559, | |
| "loss": 0.9984, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8066884176182708, | |
| "eval_f1": 0.7113876383080939, | |
| "eval_loss": 0.4811672270298004, | |
| "eval_precision": 0.7265273055775476, | |
| "eval_recall": 0.7320681182395002, | |
| "eval_runtime": 20.7162, | |
| "eval_samples_per_second": 118.362, | |
| "eval_steps_per_second": 7.434, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 2.02, | |
| "grad_norm": 1.7719513177871704, | |
| "learning_rate": 0.003995412844036697, | |
| "loss": 0.9865, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 2.06, | |
| "grad_norm": 2.115173578262329, | |
| "learning_rate": 0.003972477064220183, | |
| "loss": 0.9227, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "grad_norm": 1.707400918006897, | |
| "learning_rate": 0.00394954128440367, | |
| "loss": 0.9195, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "grad_norm": 2.7709805965423584, | |
| "learning_rate": 0.0039266055045871565, | |
| "loss": 0.8792, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 2.2, | |
| "grad_norm": 2.1106033325195312, | |
| "learning_rate": 0.003903669724770642, | |
| "loss": 0.9282, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.25, | |
| "grad_norm": 2.2281219959259033, | |
| "learning_rate": 0.0038807339449541283, | |
| "loss": 0.8242, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 2.29, | |
| "grad_norm": 1.9189764261245728, | |
| "learning_rate": 0.003857798165137615, | |
| "loss": 0.8428, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "grad_norm": 2.04294753074646, | |
| "learning_rate": 0.003834862385321101, | |
| "loss": 0.8726, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "grad_norm": 2.139575481414795, | |
| "learning_rate": 0.003811926605504587, | |
| "loss": 0.9184, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 2.43, | |
| "grad_norm": 2.527928113937378, | |
| "learning_rate": 0.0037889908256880734, | |
| "loss": 0.934, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "grad_norm": 1.9021204710006714, | |
| "learning_rate": 0.00376605504587156, | |
| "loss": 0.9117, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.52, | |
| "grad_norm": 2.099567174911499, | |
| "learning_rate": 0.003743119266055046, | |
| "loss": 0.7403, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.57, | |
| "grad_norm": 1.6857088804244995, | |
| "learning_rate": 0.003720183486238532, | |
| "loss": 0.8173, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "grad_norm": 2.216789960861206, | |
| "learning_rate": 0.0036972477064220184, | |
| "loss": 0.9077, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 2.66, | |
| "grad_norm": 1.2876479625701904, | |
| "learning_rate": 0.0036743119266055045, | |
| "loss": 0.8218, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 2.71, | |
| "grad_norm": 1.7834821939468384, | |
| "learning_rate": 0.003651376146788991, | |
| "loss": 0.8954, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "grad_norm": 2.3635175228118896, | |
| "learning_rate": 0.003628440366972477, | |
| "loss": 0.8818, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 1.9978779554367065, | |
| "learning_rate": 0.0036055045871559634, | |
| "loss": 0.9062, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "grad_norm": 2.9038476943969727, | |
| "learning_rate": 0.0035825688073394496, | |
| "loss": 0.8452, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "grad_norm": 1.843595027923584, | |
| "learning_rate": 0.003559633027522936, | |
| "loss": 0.8291, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 2.94, | |
| "grad_norm": 2.618366241455078, | |
| "learning_rate": 0.003536697247706422, | |
| "loss": 0.8661, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 2.98, | |
| "grad_norm": 1.8442063331604004, | |
| "learning_rate": 0.003513761467889908, | |
| "loss": 0.8265, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.851957585644372, | |
| "eval_f1": 0.768301171782241, | |
| "eval_loss": 0.3725639581680298, | |
| "eval_precision": 0.800477076178721, | |
| "eval_recall": 0.771278337679668, | |
| "eval_runtime": 20.7103, | |
| "eval_samples_per_second": 118.395, | |
| "eval_steps_per_second": 7.436, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 3.03, | |
| "grad_norm": 2.050394058227539, | |
| "learning_rate": 0.0034908256880733946, | |
| "loss": 0.7888, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 3.07, | |
| "grad_norm": 2.184720993041992, | |
| "learning_rate": 0.003467889908256881, | |
| "loss": 0.8631, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 3.12, | |
| "grad_norm": 1.606249213218689, | |
| "learning_rate": 0.003444954128440367, | |
| "loss": 0.7822, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 3.17, | |
| "grad_norm": 2.3371753692626953, | |
| "learning_rate": 0.003422018348623853, | |
| "loss": 0.7497, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "grad_norm": 2.1213464736938477, | |
| "learning_rate": 0.0033990825688073397, | |
| "loss": 0.8359, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.26, | |
| "grad_norm": 2.4342410564422607, | |
| "learning_rate": 0.003376146788990826, | |
| "loss": 0.8393, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 3.3, | |
| "grad_norm": 2.252201557159424, | |
| "learning_rate": 0.003353211009174312, | |
| "loss": 0.771, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.35, | |
| "grad_norm": 2.0991744995117188, | |
| "learning_rate": 0.003330275229357798, | |
| "loss": 0.8322, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 3.39, | |
| "grad_norm": 1.4995887279510498, | |
| "learning_rate": 0.0033073394495412847, | |
| "loss": 0.8652, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 3.44, | |
| "grad_norm": 1.8054556846618652, | |
| "learning_rate": 0.003284403669724771, | |
| "loss": 0.8594, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.49, | |
| "grad_norm": 1.846091389656067, | |
| "learning_rate": 0.0032614678899082566, | |
| "loss": 0.8507, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 3.53, | |
| "grad_norm": 2.486276149749756, | |
| "learning_rate": 0.003238532110091743, | |
| "loss": 0.8608, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "grad_norm": 1.9299883842468262, | |
| "learning_rate": 0.0032155963302752293, | |
| "loss": 0.7887, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.62, | |
| "grad_norm": 1.7495784759521484, | |
| "learning_rate": 0.003192660550458716, | |
| "loss": 0.8364, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 3.67, | |
| "grad_norm": 1.4023948907852173, | |
| "learning_rate": 0.0031697247706422016, | |
| "loss": 0.8239, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.72, | |
| "grad_norm": 2.4405996799468994, | |
| "learning_rate": 0.003146788990825688, | |
| "loss": 0.7324, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 3.76, | |
| "grad_norm": 2.8213984966278076, | |
| "learning_rate": 0.0031238532110091743, | |
| "loss": 0.8305, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "grad_norm": 1.9884538650512695, | |
| "learning_rate": 0.003100917431192661, | |
| "loss": 0.823, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "grad_norm": 1.3576688766479492, | |
| "learning_rate": 0.0030779816513761466, | |
| "loss": 0.7203, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.9, | |
| "grad_norm": 1.8440253734588623, | |
| "learning_rate": 0.0030550458715596328, | |
| "loss": 0.7564, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.94, | |
| "grad_norm": 1.383427381515503, | |
| "learning_rate": 0.0030321100917431194, | |
| "loss": 0.7679, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 3.99, | |
| "grad_norm": 2.3057126998901367, | |
| "learning_rate": 0.003009174311926606, | |
| "loss": 0.7938, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8507340946166395, | |
| "eval_f1": 0.7554407269192587, | |
| "eval_loss": 0.39133650064468384, | |
| "eval_precision": 0.7811773459124496, | |
| "eval_recall": 0.7830608562256607, | |
| "eval_runtime": 20.8094, | |
| "eval_samples_per_second": 117.831, | |
| "eval_steps_per_second": 7.4, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 4.04, | |
| "grad_norm": 1.3315050601959229, | |
| "learning_rate": 0.0029862385321100917, | |
| "loss": 0.7701, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 4.08, | |
| "grad_norm": 2.4050934314727783, | |
| "learning_rate": 0.002963302752293578, | |
| "loss": 0.7967, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 4.13, | |
| "grad_norm": 1.3627427816390991, | |
| "learning_rate": 0.0029403669724770644, | |
| "loss": 0.8184, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 4.17, | |
| "grad_norm": 2.152087688446045, | |
| "learning_rate": 0.0029174311926605506, | |
| "loss": 0.7987, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 4.22, | |
| "grad_norm": 2.42413067817688, | |
| "learning_rate": 0.0028944954128440367, | |
| "loss": 0.7772, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 4.27, | |
| "grad_norm": 1.8017699718475342, | |
| "learning_rate": 0.002871559633027523, | |
| "loss": 0.7587, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 4.31, | |
| "grad_norm": 1.805237889289856, | |
| "learning_rate": 0.0028486238532110094, | |
| "loss": 0.7326, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 4.36, | |
| "grad_norm": 2.2268106937408447, | |
| "learning_rate": 0.0028256880733944956, | |
| "loss": 0.7293, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "grad_norm": 2.386366605758667, | |
| "learning_rate": 0.0028027522935779813, | |
| "loss": 0.7396, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.45, | |
| "grad_norm": 2.0315840244293213, | |
| "learning_rate": 0.002779816513761468, | |
| "loss": 0.7131, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 4.5, | |
| "grad_norm": 2.1899399757385254, | |
| "learning_rate": 0.002756880733944954, | |
| "loss": 0.8073, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 4.54, | |
| "grad_norm": 1.614035725593567, | |
| "learning_rate": 0.0027339449541284406, | |
| "loss": 0.7168, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 4.59, | |
| "grad_norm": 2.4006643295288086, | |
| "learning_rate": 0.0027110091743119263, | |
| "loss": 0.7774, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "grad_norm": 2.3257529735565186, | |
| "learning_rate": 0.002688073394495413, | |
| "loss": 0.7808, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 4.68, | |
| "grad_norm": 1.6664689779281616, | |
| "learning_rate": 0.002665137614678899, | |
| "loss": 0.717, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.72, | |
| "grad_norm": 1.7779196500778198, | |
| "learning_rate": 0.0026422018348623857, | |
| "loss": 0.7697, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 4.77, | |
| "grad_norm": 1.8458689451217651, | |
| "learning_rate": 0.0026192660550458714, | |
| "loss": 0.7384, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 4.82, | |
| "grad_norm": 1.5530970096588135, | |
| "learning_rate": 0.0025963302752293575, | |
| "loss": 0.7411, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 4.86, | |
| "grad_norm": 2.550743341445923, | |
| "learning_rate": 0.002573394495412844, | |
| "loss": 0.6985, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 4.91, | |
| "grad_norm": 1.284894347190857, | |
| "learning_rate": 0.0025504587155963303, | |
| "loss": 0.7961, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 4.95, | |
| "grad_norm": 1.5528652667999268, | |
| "learning_rate": 0.0025275229357798164, | |
| "loss": 0.8198, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 2.2907180786132812, | |
| "learning_rate": 0.0025045871559633026, | |
| "loss": 0.8149, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8531810766721044, | |
| "eval_f1": 0.7701622667658707, | |
| "eval_loss": 0.3675837218761444, | |
| "eval_precision": 0.7686624499292936, | |
| "eval_recall": 0.8001667562361665, | |
| "eval_runtime": 20.7465, | |
| "eval_samples_per_second": 118.189, | |
| "eval_steps_per_second": 7.423, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 5.05, | |
| "grad_norm": 1.3846713304519653, | |
| "learning_rate": 0.002481651376146789, | |
| "loss": 0.6938, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 5.09, | |
| "grad_norm": 1.6576237678527832, | |
| "learning_rate": 0.0024587155963302753, | |
| "loss": 0.7169, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 5.14, | |
| "grad_norm": 1.8432438373565674, | |
| "learning_rate": 0.0024357798165137614, | |
| "loss": 0.7242, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 5.18, | |
| "grad_norm": 1.9799226522445679, | |
| "learning_rate": 0.002412844036697248, | |
| "loss": 0.6667, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 5.23, | |
| "grad_norm": 1.92507004737854, | |
| "learning_rate": 0.002389908256880734, | |
| "loss": 0.6681, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 5.28, | |
| "grad_norm": 1.4437962770462036, | |
| "learning_rate": 0.0023669724770642203, | |
| "loss": 0.6618, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "grad_norm": 1.565990924835205, | |
| "learning_rate": 0.0023440366972477065, | |
| "loss": 0.7162, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "grad_norm": 1.7609509229660034, | |
| "learning_rate": 0.0023211009174311926, | |
| "loss": 0.6953, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 5.41, | |
| "grad_norm": 1.402076005935669, | |
| "learning_rate": 0.002298165137614679, | |
| "loss": 0.7114, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 5.46, | |
| "grad_norm": 1.542944312095642, | |
| "learning_rate": 0.0022752293577981654, | |
| "loss": 0.7695, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 5.5, | |
| "grad_norm": 1.3250664472579956, | |
| "learning_rate": 0.0022522935779816515, | |
| "loss": 0.6984, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.55, | |
| "grad_norm": 1.790968894958496, | |
| "learning_rate": 0.0022293577981651377, | |
| "loss": 0.7457, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "grad_norm": 1.8708348274230957, | |
| "learning_rate": 0.002206422018348624, | |
| "loss": 0.6854, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 1.3669894933700562, | |
| "learning_rate": 0.0021834862385321104, | |
| "loss": 0.7601, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 5.69, | |
| "grad_norm": 1.6164820194244385, | |
| "learning_rate": 0.0021605504587155966, | |
| "loss": 0.7015, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 5.73, | |
| "grad_norm": 2.5344796180725098, | |
| "learning_rate": 0.0021376146788990827, | |
| "loss": 0.6816, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 5.78, | |
| "grad_norm": 1.8224860429763794, | |
| "learning_rate": 0.002114678899082569, | |
| "loss": 0.7091, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 5.83, | |
| "grad_norm": 2.3349053859710693, | |
| "learning_rate": 0.002091743119266055, | |
| "loss": 0.69, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 5.87, | |
| "grad_norm": 1.742497444152832, | |
| "learning_rate": 0.002068807339449541, | |
| "loss": 0.6835, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 5.92, | |
| "grad_norm": 1.6536716222763062, | |
| "learning_rate": 0.0020458715596330277, | |
| "loss": 0.6827, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "grad_norm": 1.6461354494094849, | |
| "learning_rate": 0.002022935779816514, | |
| "loss": 0.6737, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8674551386623165, | |
| "eval_f1": 0.7933729473887552, | |
| "eval_loss": 0.3304790258407593, | |
| "eval_precision": 0.8306122822846135, | |
| "eval_recall": 0.8116698887283952, | |
| "eval_runtime": 20.7895, | |
| "eval_samples_per_second": 117.944, | |
| "eval_steps_per_second": 7.408, | |
| "step": 1308 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "grad_norm": 1.2140992879867554, | |
| "learning_rate": 0.002, | |
| "loss": 0.6921, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 6.06, | |
| "grad_norm": 2.1813745498657227, | |
| "learning_rate": 0.001977064220183486, | |
| "loss": 0.7078, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 6.1, | |
| "grad_norm": 1.2994489669799805, | |
| "learning_rate": 0.0019541284403669728, | |
| "loss": 0.6949, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "grad_norm": 1.4426566362380981, | |
| "learning_rate": 0.0019311926605504587, | |
| "loss": 0.6685, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "grad_norm": 1.5542079210281372, | |
| "learning_rate": 0.001908256880733945, | |
| "loss": 0.6823, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 6.24, | |
| "grad_norm": 1.5096594095230103, | |
| "learning_rate": 0.0018853211009174312, | |
| "loss": 0.6203, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 6.28, | |
| "grad_norm": 2.132112979888916, | |
| "learning_rate": 0.0018623853211009176, | |
| "loss": 0.6942, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 6.33, | |
| "grad_norm": 2.1632845401763916, | |
| "learning_rate": 0.0018394495412844037, | |
| "loss": 0.5899, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 6.38, | |
| "grad_norm": 1.6782176494598389, | |
| "learning_rate": 0.0018165137614678901, | |
| "loss": 0.6316, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "grad_norm": 1.1974135637283325, | |
| "learning_rate": 0.001793577981651376, | |
| "loss": 0.609, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 6.47, | |
| "grad_norm": 1.8140075206756592, | |
| "learning_rate": 0.0017706422018348624, | |
| "loss": 0.65, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 6.51, | |
| "grad_norm": 1.5135620832443237, | |
| "learning_rate": 0.0017477064220183486, | |
| "loss": 0.6201, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 6.56, | |
| "grad_norm": 1.6838016510009766, | |
| "learning_rate": 0.001724770642201835, | |
| "loss": 0.6044, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 6.61, | |
| "grad_norm": 1.55550217628479, | |
| "learning_rate": 0.001701834862385321, | |
| "loss": 0.6753, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 6.65, | |
| "grad_norm": 1.8122529983520508, | |
| "learning_rate": 0.0016788990825688074, | |
| "loss": 0.6608, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 6.7, | |
| "grad_norm": 2.207045555114746, | |
| "learning_rate": 0.0016559633027522936, | |
| "loss": 0.6132, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 6.74, | |
| "grad_norm": 0.9892495274543762, | |
| "learning_rate": 0.00163302752293578, | |
| "loss": 0.6177, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "grad_norm": 2.4809529781341553, | |
| "learning_rate": 0.0016100917431192661, | |
| "loss": 0.5607, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 6.83, | |
| "grad_norm": 1.430293083190918, | |
| "learning_rate": 0.0015871559633027525, | |
| "loss": 0.6822, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 6.88, | |
| "grad_norm": 1.6523278951644897, | |
| "learning_rate": 0.0015642201834862384, | |
| "loss": 0.6486, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.93, | |
| "grad_norm": 1.5746197700500488, | |
| "learning_rate": 0.0015412844036697248, | |
| "loss": 0.5902, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "grad_norm": 1.5833261013031006, | |
| "learning_rate": 0.001518348623853211, | |
| "loss": 0.5695, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.9029363784665579, | |
| "eval_f1": 0.8321123007962286, | |
| "eval_loss": 0.24805299937725067, | |
| "eval_precision": 0.8545669814728453, | |
| "eval_recall": 0.8469225407396054, | |
| "eval_runtime": 20.7317, | |
| "eval_samples_per_second": 118.273, | |
| "eval_steps_per_second": 7.428, | |
| "step": 1526 | |
| }, | |
| { | |
| "epoch": 7.02, | |
| "grad_norm": 1.8044548034667969, | |
| "learning_rate": 0.0014954128440366973, | |
| "loss": 0.5888, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 7.06, | |
| "grad_norm": 1.9052773714065552, | |
| "learning_rate": 0.0014724770642201835, | |
| "loss": 0.5968, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 7.11, | |
| "grad_norm": 1.835716962814331, | |
| "learning_rate": 0.0014495412844036698, | |
| "loss": 0.642, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "grad_norm": 1.3683079481124878, | |
| "learning_rate": 0.001426605504587156, | |
| "loss": 0.6627, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 7.2, | |
| "grad_norm": 1.9506031274795532, | |
| "learning_rate": 0.0014036697247706423, | |
| "loss": 0.6054, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 7.25, | |
| "grad_norm": 1.300554871559143, | |
| "learning_rate": 0.0013807339449541285, | |
| "loss": 0.6375, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 7.29, | |
| "grad_norm": 2.0933167934417725, | |
| "learning_rate": 0.0013577981651376149, | |
| "loss": 0.5603, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 7.34, | |
| "grad_norm": 1.0951093435287476, | |
| "learning_rate": 0.0013348623853211008, | |
| "loss": 0.5836, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "grad_norm": 1.186511516571045, | |
| "learning_rate": 0.0013119266055045872, | |
| "loss": 0.5877, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 7.43, | |
| "grad_norm": 1.5988391637802124, | |
| "learning_rate": 0.0012889908256880733, | |
| "loss": 0.5868, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 7.48, | |
| "grad_norm": 2.0407028198242188, | |
| "learning_rate": 0.0012660550458715597, | |
| "loss": 0.564, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 7.52, | |
| "grad_norm": 1.4676613807678223, | |
| "learning_rate": 0.001243119266055046, | |
| "loss": 0.6205, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 7.57, | |
| "grad_norm": 1.1794471740722656, | |
| "learning_rate": 0.0012201834862385322, | |
| "loss": 0.581, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "grad_norm": 1.7204222679138184, | |
| "learning_rate": 0.0011972477064220183, | |
| "loss": 0.6433, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 7.66, | |
| "grad_norm": 1.7347933053970337, | |
| "learning_rate": 0.0011743119266055047, | |
| "loss": 0.6132, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 7.71, | |
| "grad_norm": 1.0963069200515747, | |
| "learning_rate": 0.0011513761467889909, | |
| "loss": 0.5961, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 7.75, | |
| "grad_norm": 1.0383723974227905, | |
| "learning_rate": 0.0011284403669724772, | |
| "loss": 0.5934, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 7.8, | |
| "grad_norm": 1.314132809638977, | |
| "learning_rate": 0.0011055045871559634, | |
| "loss": 0.5667, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "grad_norm": 1.8448032140731812, | |
| "learning_rate": 0.0010825688073394495, | |
| "loss": 0.5999, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 7.89, | |
| "grad_norm": 1.187971591949463, | |
| "learning_rate": 0.001059633027522936, | |
| "loss": 0.5668, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 7.94, | |
| "grad_norm": 1.451027512550354, | |
| "learning_rate": 0.001036697247706422, | |
| "loss": 0.5928, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 7.98, | |
| "grad_norm": 1.5274406671524048, | |
| "learning_rate": 0.0010137614678899084, | |
| "loss": 0.5857, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8923327895595432, | |
| "eval_f1": 0.8339907958679574, | |
| "eval_loss": 0.2911706566810608, | |
| "eval_precision": 0.8463533280759077, | |
| "eval_recall": 0.8356417778568457, | |
| "eval_runtime": 20.8398, | |
| "eval_samples_per_second": 117.66, | |
| "eval_steps_per_second": 7.39, | |
| "step": 1744 | |
| }, | |
| { | |
| "epoch": 8.03, | |
| "grad_norm": 1.254504919052124, | |
| "learning_rate": 0.0009908256880733946, | |
| "loss": 0.5059, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 8.07, | |
| "grad_norm": 1.3762636184692383, | |
| "learning_rate": 0.0009678899082568808, | |
| "loss": 0.578, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 8.12, | |
| "grad_norm": 1.472004771232605, | |
| "learning_rate": 0.0009449541284403671, | |
| "loss": 0.5216, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 8.17, | |
| "grad_norm": 1.5876396894454956, | |
| "learning_rate": 0.0009220183486238532, | |
| "loss": 0.5689, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "grad_norm": 1.2409037351608276, | |
| "learning_rate": 0.0008990825688073395, | |
| "loss": 0.5571, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 8.26, | |
| "grad_norm": 1.2082581520080566, | |
| "learning_rate": 0.0008761467889908258, | |
| "loss": 0.5809, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 8.3, | |
| "grad_norm": 1.7171647548675537, | |
| "learning_rate": 0.000853211009174312, | |
| "loss": 0.5626, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 8.35, | |
| "grad_norm": 1.3834128379821777, | |
| "learning_rate": 0.0008302752293577983, | |
| "loss": 0.5362, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 8.39, | |
| "grad_norm": 1.424574375152588, | |
| "learning_rate": 0.0008073394495412844, | |
| "loss": 0.5418, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 8.44, | |
| "grad_norm": 1.5661699771881104, | |
| "learning_rate": 0.0007844036697247707, | |
| "loss": 0.5609, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 8.49, | |
| "grad_norm": 1.9551769495010376, | |
| "learning_rate": 0.0007614678899082569, | |
| "loss": 0.564, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 8.53, | |
| "grad_norm": 1.084270715713501, | |
| "learning_rate": 0.0007385321100917432, | |
| "loss": 0.5121, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "grad_norm": 1.446973204612732, | |
| "learning_rate": 0.0007155963302752295, | |
| "loss": 0.569, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 8.62, | |
| "grad_norm": 1.3539941310882568, | |
| "learning_rate": 0.0006926605504587156, | |
| "loss": 0.525, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 8.67, | |
| "grad_norm": 1.413223147392273, | |
| "learning_rate": 0.0006697247706422019, | |
| "loss": 0.4403, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 8.72, | |
| "grad_norm": 1.3614115715026855, | |
| "learning_rate": 0.0006467889908256881, | |
| "loss": 0.553, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 8.76, | |
| "grad_norm": 1.2185453176498413, | |
| "learning_rate": 0.0006238532110091744, | |
| "loss": 0.5498, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "grad_norm": 1.3884397745132446, | |
| "learning_rate": 0.0006009174311926606, | |
| "loss": 0.5092, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 8.85, | |
| "grad_norm": 1.2725589275360107, | |
| "learning_rate": 0.0005779816513761468, | |
| "loss": 0.5695, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "grad_norm": 1.2434947490692139, | |
| "learning_rate": 0.000555045871559633, | |
| "loss": 0.4998, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 8.94, | |
| "grad_norm": 1.378146767616272, | |
| "learning_rate": 0.0005321100917431193, | |
| "loss": 0.5091, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 8.99, | |
| "grad_norm": 1.3200100660324097, | |
| "learning_rate": 0.0005091743119266056, | |
| "loss": 0.4834, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.899673735725938, | |
| "eval_f1": 0.8285783762787183, | |
| "eval_loss": 0.2657569944858551, | |
| "eval_precision": 0.8428024691807685, | |
| "eval_recall": 0.8409794358062922, | |
| "eval_runtime": 20.7116, | |
| "eval_samples_per_second": 118.388, | |
| "eval_steps_per_second": 7.435, | |
| "step": 1962 | |
| }, | |
| { | |
| "epoch": 9.04, | |
| "grad_norm": 1.1076021194458008, | |
| "learning_rate": 0.0004862385321100918, | |
| "loss": 0.5164, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 9.08, | |
| "grad_norm": 1.50495445728302, | |
| "learning_rate": 0.00046330275229357804, | |
| "loss": 0.4388, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 9.13, | |
| "grad_norm": 1.4007256031036377, | |
| "learning_rate": 0.00044036697247706424, | |
| "loss": 0.4761, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 9.17, | |
| "grad_norm": 1.226333737373352, | |
| "learning_rate": 0.0004174311926605505, | |
| "loss": 0.4861, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.22, | |
| "grad_norm": 1.937953233718872, | |
| "learning_rate": 0.0003944954128440367, | |
| "loss": 0.4604, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 9.27, | |
| "grad_norm": 1.35695219039917, | |
| "learning_rate": 0.00037155963302752296, | |
| "loss": 0.4633, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 9.31, | |
| "grad_norm": 1.521087884902954, | |
| "learning_rate": 0.0003486238532110092, | |
| "loss": 0.4512, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 9.36, | |
| "grad_norm": 1.4338667392730713, | |
| "learning_rate": 0.0003256880733944954, | |
| "loss": 0.5439, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "grad_norm": 1.7897557020187378, | |
| "learning_rate": 0.0003027522935779817, | |
| "loss": 0.5278, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 9.45, | |
| "grad_norm": 1.0933929681777954, | |
| "learning_rate": 0.0002798165137614679, | |
| "loss": 0.4592, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 9.5, | |
| "grad_norm": 1.2754806280136108, | |
| "learning_rate": 0.00025688073394495415, | |
| "loss": 0.476, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 9.54, | |
| "grad_norm": 1.724406361579895, | |
| "learning_rate": 0.00023394495412844038, | |
| "loss": 0.4963, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 9.59, | |
| "grad_norm": 1.5604366064071655, | |
| "learning_rate": 0.0002110091743119266, | |
| "loss": 0.4926, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "grad_norm": 1.2408415079116821, | |
| "learning_rate": 0.00018807339449541287, | |
| "loss": 0.4954, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 9.68, | |
| "grad_norm": 0.8950926065444946, | |
| "learning_rate": 0.0001651376146788991, | |
| "loss": 0.4444, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 9.72, | |
| "grad_norm": 1.2199152708053589, | |
| "learning_rate": 0.00014220183486238534, | |
| "loss": 0.4606, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 9.77, | |
| "grad_norm": 1.1516410112380981, | |
| "learning_rate": 0.00011926605504587157, | |
| "loss": 0.4691, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 9.82, | |
| "grad_norm": 2.192310333251953, | |
| "learning_rate": 9.63302752293578e-05, | |
| "loss": 0.5306, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 9.86, | |
| "grad_norm": 1.2649255990982056, | |
| "learning_rate": 7.339449541284404e-05, | |
| "loss": 0.5238, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 9.91, | |
| "grad_norm": 1.5681147575378418, | |
| "learning_rate": 5.0458715596330276e-05, | |
| "loss": 0.4631, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 9.95, | |
| "grad_norm": 1.3230477571487427, | |
| "learning_rate": 2.7522935779816515e-05, | |
| "loss": 0.4716, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 1.0949994325637817, | |
| "learning_rate": 4.587155963302753e-06, | |
| "loss": 0.5287, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.9049755301794453, | |
| "eval_f1": 0.8468363122524573, | |
| "eval_loss": 0.2590215504169464, | |
| "eval_precision": 0.8523921546408058, | |
| "eval_recall": 0.8468399455092634, | |
| "eval_runtime": 20.6801, | |
| "eval_samples_per_second": 118.568, | |
| "eval_steps_per_second": 7.447, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 2180, | |
| "total_flos": 1.087396245164114e+19, | |
| "train_loss": 0.7537981033325195, | |
| "train_runtime": 2484.6922, | |
| "train_samples_per_second": 56.104, | |
| "train_steps_per_second": 0.877 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8239891267414203, | |
| "eval_f1": 0.7852027158639473, | |
| "eval_loss": 0.4609430432319641, | |
| "eval_precision": 0.7894503286617733, | |
| "eval_recall": 0.7820860597039324, | |
| "eval_runtime": 74.5465, | |
| "eval_samples_per_second": 118.436, | |
| "eval_steps_per_second": 7.405, | |
| "step": 2180 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2180, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "total_flos": 1.087396245164114e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |