| { |
| "best_metric": 0.2933545410633087, |
| "best_model_checkpoint": "./vit-large-binary-isic-sharpened-patch-16/checkpoint-2500", |
| "epoch": 4.0, |
| "global_step": 4328, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01, |
| "learning_rate": 0.00019953789279112755, |
| "loss": 0.8082, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.02, |
| "learning_rate": 0.00019912199630314236, |
| "loss": 0.6929, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.03, |
| "learning_rate": 0.0001986598890942699, |
| "loss": 0.6865, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.04, |
| "learning_rate": 0.0001981977818853974, |
| "loss": 0.9436, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.05, |
| "learning_rate": 0.00019773567467652495, |
| "loss": 0.6843, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019727356746765252, |
| "loss": 0.5735, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.06, |
| "learning_rate": 0.00019681146025878006, |
| "loss": 0.6261, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.07, |
| "learning_rate": 0.00019634935304990757, |
| "loss": 0.5538, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.08, |
| "learning_rate": 0.00019588724584103511, |
| "loss": 0.5933, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.09, |
| "learning_rate": 0.00019542513863216268, |
| "loss": 0.5213, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.09, |
| "eval_accuracy": 0.7638390568939005, |
| "eval_f1": 0.7638390568939006, |
| "eval_loss": 0.44594600796699524, |
| "eval_precision": 0.7638390568939005, |
| "eval_recall": 0.7638390568939005, |
| "eval_runtime": 82.3787, |
| "eval_samples_per_second": 94.733, |
| "eval_steps_per_second": 11.848, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.1, |
| "learning_rate": 0.00019496303142329022, |
| "loss": 0.4627, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.11, |
| "learning_rate": 0.00019450092421441774, |
| "loss": 0.6127, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.12, |
| "learning_rate": 0.0001940388170055453, |
| "loss": 0.5404, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.13, |
| "learning_rate": 0.00019357670979667284, |
| "loss": 0.5488, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.14, |
| "learning_rate": 0.00019311460258780039, |
| "loss": 0.4643, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.15, |
| "learning_rate": 0.0001926524953789279, |
| "loss": 0.524, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.16, |
| "learning_rate": 0.00019219038817005547, |
| "loss": 0.5372, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.17, |
| "learning_rate": 0.000191728280961183, |
| "loss": 0.4095, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.00019126617375231055, |
| "loss": 0.4569, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.18, |
| "learning_rate": 0.0001908040665434381, |
| "loss": 0.4388, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.18, |
| "eval_accuracy": 0.7869041517170682, |
| "eval_f1": 0.7869041517170682, |
| "eval_loss": 0.5328742861747742, |
| "eval_precision": 0.7869041517170682, |
| "eval_recall": 0.7869041517170682, |
| "eval_runtime": 83.9617, |
| "eval_samples_per_second": 92.947, |
| "eval_steps_per_second": 11.624, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.19, |
| "learning_rate": 0.00019034195933456563, |
| "loss": 0.3869, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.2, |
| "learning_rate": 0.00018987985212569317, |
| "loss": 0.5303, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.21, |
| "learning_rate": 0.0001894177449168207, |
| "loss": 0.3612, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.22, |
| "learning_rate": 0.00018895563770794825, |
| "loss": 0.4922, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.23, |
| "learning_rate": 0.0001884935304990758, |
| "loss": 0.5435, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.24, |
| "learning_rate": 0.00018803142329020333, |
| "loss": 0.5545, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.25, |
| "learning_rate": 0.00018756931608133087, |
| "loss": 0.3933, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.26, |
| "learning_rate": 0.00018710720887245841, |
| "loss": 0.5536, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.27, |
| "learning_rate": 0.00018664510166358596, |
| "loss": 0.4346, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.28, |
| "learning_rate": 0.0001861829944547135, |
| "loss": 0.4157, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.28, |
| "eval_accuracy": 0.7712711430035879, |
| "eval_f1": 0.7712711430035878, |
| "eval_loss": 0.4437919855117798, |
| "eval_precision": 0.7712711430035879, |
| "eval_recall": 0.7712711430035879, |
| "eval_runtime": 83.2116, |
| "eval_samples_per_second": 93.785, |
| "eval_steps_per_second": 11.729, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.29, |
| "learning_rate": 0.00018572088724584104, |
| "loss": 0.4296, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.0001852587800369686, |
| "loss": 0.3737, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.3, |
| "learning_rate": 0.00018479667282809612, |
| "loss": 0.5117, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.31, |
| "learning_rate": 0.00018433456561922366, |
| "loss": 0.481, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.32, |
| "learning_rate": 0.0001838724584103512, |
| "loss": 0.3608, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.33, |
| "learning_rate": 0.00018341035120147877, |
| "loss": 0.5656, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.34, |
| "learning_rate": 0.00018294824399260628, |
| "loss": 0.3464, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.35, |
| "learning_rate": 0.00018248613678373382, |
| "loss": 0.4749, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.36, |
| "learning_rate": 0.0001820240295748614, |
| "loss": 0.4352, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.37, |
| "learning_rate": 0.00018156192236598893, |
| "loss": 0.4578, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.37, |
| "eval_accuracy": 0.7652485904664275, |
| "eval_f1": 0.7652485904664275, |
| "eval_loss": 0.43274176120758057, |
| "eval_precision": 0.7652485904664275, |
| "eval_recall": 0.7652485904664275, |
| "eval_runtime": 83.447, |
| "eval_samples_per_second": 93.52, |
| "eval_steps_per_second": 11.696, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.38, |
| "learning_rate": 0.00018109981515711647, |
| "loss": 0.4351, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.39, |
| "learning_rate": 0.00018063770794824399, |
| "loss": 0.4204, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.4, |
| "learning_rate": 0.00018017560073937155, |
| "loss": 0.4808, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 0.0001797134935304991, |
| "loss": 0.4456, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.42, |
| "learning_rate": 0.00017925138632162663, |
| "loss": 0.4193, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00017878927911275415, |
| "loss": 0.4122, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.43, |
| "learning_rate": 0.00017832717190388172, |
| "loss": 0.3472, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.44, |
| "learning_rate": 0.00017786506469500926, |
| "loss": 0.4757, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.45, |
| "learning_rate": 0.0001774029574861368, |
| "loss": 0.4282, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.46, |
| "learning_rate": 0.00017694085027726434, |
| "loss": 0.4322, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.46, |
| "eval_accuracy": 0.7897232188621219, |
| "eval_f1": 0.7897232188621218, |
| "eval_loss": 0.41786515712738037, |
| "eval_precision": 0.7897232188621219, |
| "eval_recall": 0.7897232188621219, |
| "eval_runtime": 82.8608, |
| "eval_samples_per_second": 94.182, |
| "eval_steps_per_second": 11.779, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.47, |
| "learning_rate": 0.00017647874306839188, |
| "loss": 0.3439, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.48, |
| "learning_rate": 0.00017601663585951942, |
| "loss": 0.4745, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.49, |
| "learning_rate": 0.00017555452865064696, |
| "loss": 0.3952, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.5, |
| "learning_rate": 0.0001750924214417745, |
| "loss": 0.4404, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.51, |
| "learning_rate": 0.00017463031423290204, |
| "loss": 0.3986, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.52, |
| "learning_rate": 0.00017416820702402958, |
| "loss": 0.3229, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.53, |
| "learning_rate": 0.00017370609981515712, |
| "loss": 0.3817, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.54, |
| "learning_rate": 0.0001732439926062847, |
| "loss": 0.3598, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.0001727818853974122, |
| "loss": 0.3485, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.55, |
| "learning_rate": 0.00017231977818853975, |
| "loss": 0.4258, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.55, |
| "eval_accuracy": 0.797924141465915, |
| "eval_f1": 0.797924141465915, |
| "eval_loss": 0.4318617284297943, |
| "eval_precision": 0.797924141465915, |
| "eval_recall": 0.797924141465915, |
| "eval_runtime": 83.3645, |
| "eval_samples_per_second": 93.613, |
| "eval_steps_per_second": 11.708, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.56, |
| "learning_rate": 0.00017185767097966729, |
| "loss": 0.4918, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.57, |
| "learning_rate": 0.00017139556377079485, |
| "loss": 0.3992, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.58, |
| "learning_rate": 0.00017093345656192237, |
| "loss": 0.3479, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.59, |
| "learning_rate": 0.0001704713493530499, |
| "loss": 0.4309, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.6, |
| "learning_rate": 0.00017000924214417745, |
| "loss": 0.3343, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 0.00016954713493530502, |
| "loss": 0.4232, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.62, |
| "learning_rate": 0.00016908502772643253, |
| "loss": 0.3481, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.63, |
| "learning_rate": 0.00016862292051756007, |
| "loss": 0.3571, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.64, |
| "learning_rate": 0.00016816081330868764, |
| "loss": 0.3539, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.65, |
| "learning_rate": 0.00016769870609981518, |
| "loss": 0.3156, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.65, |
| "eval_accuracy": 0.7729369554074833, |
| "eval_f1": 0.7729369554074833, |
| "eval_loss": 0.44701671600341797, |
| "eval_precision": 0.7729369554074833, |
| "eval_recall": 0.7729369554074833, |
| "eval_runtime": 82.9893, |
| "eval_samples_per_second": 94.036, |
| "eval_steps_per_second": 11.761, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.66, |
| "learning_rate": 0.0001672365988909427, |
| "loss": 0.3531, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.00016677449168207023, |
| "loss": 0.3733, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.67, |
| "learning_rate": 0.0001663123844731978, |
| "loss": 0.4025, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.68, |
| "learning_rate": 0.00016585027726432534, |
| "loss": 0.3557, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.69, |
| "learning_rate": 0.00016538817005545286, |
| "loss": 0.3355, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.7, |
| "learning_rate": 0.0001649260628465804, |
| "loss": 0.4307, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.71, |
| "learning_rate": 0.00016446395563770796, |
| "loss": 0.3081, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.72, |
| "learning_rate": 0.0001640018484288355, |
| "loss": 0.2495, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.73, |
| "learning_rate": 0.00016353974121996305, |
| "loss": 0.7359, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.74, |
| "learning_rate": 0.0001630776340110906, |
| "loss": 0.449, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.74, |
| "eval_accuracy": 0.8035622757560226, |
| "eval_f1": 0.8035622757560226, |
| "eval_loss": 0.4222868084907532, |
| "eval_precision": 0.8035622757560226, |
| "eval_recall": 0.8035622757560226, |
| "eval_runtime": 83.1321, |
| "eval_samples_per_second": 93.875, |
| "eval_steps_per_second": 11.74, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.75, |
| "learning_rate": 0.00016261552680221813, |
| "loss": 0.4488, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.76, |
| "learning_rate": 0.00016215341959334567, |
| "loss": 0.3456, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.77, |
| "learning_rate": 0.0001616913123844732, |
| "loss": 0.3863, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.78, |
| "learning_rate": 0.00016122920517560075, |
| "loss": 0.6473, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.0001607670979667283, |
| "loss": 0.3917, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.79, |
| "learning_rate": 0.00016030499075785583, |
| "loss": 0.3228, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.8, |
| "learning_rate": 0.00015984288354898337, |
| "loss": 0.357, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.81, |
| "learning_rate": 0.0001593807763401109, |
| "loss": 0.4173, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 0.00015891866913123845, |
| "loss": 0.4865, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.83, |
| "learning_rate": 0.000158456561922366, |
| "loss": 0.464, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.83, |
| "eval_accuracy": 0.7813941568426448, |
| "eval_f1": 0.7813941568426448, |
| "eval_loss": 0.43043768405914307, |
| "eval_precision": 0.7813941568426448, |
| "eval_recall": 0.7813941568426448, |
| "eval_runtime": 83.0934, |
| "eval_samples_per_second": 93.918, |
| "eval_steps_per_second": 11.746, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.84, |
| "learning_rate": 0.00015799445471349353, |
| "loss": 0.3436, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.85, |
| "learning_rate": 0.00015753234750462108, |
| "loss": 0.3055, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.86, |
| "learning_rate": 0.00015707024029574862, |
| "loss": 0.416, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.87, |
| "learning_rate": 0.00015660813308687616, |
| "loss": 0.3808, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.88, |
| "learning_rate": 0.0001561460258780037, |
| "loss": 0.4386, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.89, |
| "learning_rate": 0.00015568391866913127, |
| "loss": 0.3534, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.9, |
| "learning_rate": 0.00015522181146025878, |
| "loss": 0.3438, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.00015475970425138632, |
| "loss": 0.4168, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.91, |
| "learning_rate": 0.0001542975970425139, |
| "loss": 0.3478, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.92, |
| "learning_rate": 0.00015383548983364143, |
| "loss": 0.2522, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.92, |
| "eval_accuracy": 0.8068939005638134, |
| "eval_f1": 0.8068939005638134, |
| "eval_loss": 0.47550439834594727, |
| "eval_precision": 0.8068939005638134, |
| "eval_recall": 0.8068939005638134, |
| "eval_runtime": 84.382, |
| "eval_samples_per_second": 92.484, |
| "eval_steps_per_second": 11.566, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.93, |
| "learning_rate": 0.00015337338262476894, |
| "loss": 0.4115, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.94, |
| "learning_rate": 0.00015291127541589648, |
| "loss": 0.3326, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.95, |
| "learning_rate": 0.00015244916820702405, |
| "loss": 0.3685, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.96, |
| "learning_rate": 0.0001519870609981516, |
| "loss": 0.3352, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.97, |
| "learning_rate": 0.0001515249537892791, |
| "loss": 0.3781, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.98, |
| "learning_rate": 0.00015106284658040665, |
| "loss": 0.3695, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.99, |
| "learning_rate": 0.00015060073937153421, |
| "loss": 0.3506, |
| "step": 1070 |
| }, |
| { |
| "epoch": 1.0, |
| "learning_rate": 0.00015013863216266175, |
| "loss": 0.3365, |
| "step": 1080 |
| }, |
| { |
| "epoch": 1.01, |
| "learning_rate": 0.00014967652495378927, |
| "loss": 0.3824, |
| "step": 1090 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 0.00014921441774491684, |
| "loss": 0.3268, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.02, |
| "eval_accuracy": 0.8118913377754997, |
| "eval_f1": 0.8118913377754997, |
| "eval_loss": 0.3677738308906555, |
| "eval_precision": 0.8118913377754997, |
| "eval_recall": 0.8118913377754997, |
| "eval_runtime": 82.9889, |
| "eval_samples_per_second": 94.037, |
| "eval_steps_per_second": 11.761, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.03, |
| "learning_rate": 0.00014875231053604438, |
| "loss": 0.2994, |
| "step": 1110 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00014829020332717192, |
| "loss": 0.3662, |
| "step": 1120 |
| }, |
| { |
| "epoch": 1.04, |
| "learning_rate": 0.00014782809611829943, |
| "loss": 0.3251, |
| "step": 1130 |
| }, |
| { |
| "epoch": 1.05, |
| "learning_rate": 0.000147365988909427, |
| "loss": 0.3474, |
| "step": 1140 |
| }, |
| { |
| "epoch": 1.06, |
| "learning_rate": 0.00014690388170055454, |
| "loss": 0.3311, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.07, |
| "learning_rate": 0.00014644177449168208, |
| "loss": 0.2867, |
| "step": 1160 |
| }, |
| { |
| "epoch": 1.08, |
| "learning_rate": 0.00014597966728280962, |
| "loss": 0.3252, |
| "step": 1170 |
| }, |
| { |
| "epoch": 1.09, |
| "learning_rate": 0.00014551756007393716, |
| "loss": 0.3454, |
| "step": 1180 |
| }, |
| { |
| "epoch": 1.1, |
| "learning_rate": 0.0001450554528650647, |
| "loss": 0.4511, |
| "step": 1190 |
| }, |
| { |
| "epoch": 1.11, |
| "learning_rate": 0.00014459334565619224, |
| "loss": 0.3374, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.11, |
| "eval_accuracy": 0.8323936442849821, |
| "eval_f1": 0.8323936442849821, |
| "eval_loss": 0.3609340190887451, |
| "eval_precision": 0.8323936442849821, |
| "eval_recall": 0.8323936442849821, |
| "eval_runtime": 83.0459, |
| "eval_samples_per_second": 93.972, |
| "eval_steps_per_second": 11.753, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.12, |
| "learning_rate": 0.00014413123844731978, |
| "loss": 0.3587, |
| "step": 1210 |
| }, |
| { |
| "epoch": 1.13, |
| "learning_rate": 0.00014366913123844732, |
| "loss": 0.3456, |
| "step": 1220 |
| }, |
| { |
| "epoch": 1.14, |
| "learning_rate": 0.00014320702402957487, |
| "loss": 0.3165, |
| "step": 1230 |
| }, |
| { |
| "epoch": 1.15, |
| "learning_rate": 0.0001427449168207024, |
| "loss": 0.2648, |
| "step": 1240 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.00014228280961182995, |
| "loss": 0.3565, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.16, |
| "learning_rate": 0.0001418207024029575, |
| "loss": 0.3545, |
| "step": 1260 |
| }, |
| { |
| "epoch": 1.17, |
| "learning_rate": 0.00014135859519408503, |
| "loss": 0.2751, |
| "step": 1270 |
| }, |
| { |
| "epoch": 1.18, |
| "learning_rate": 0.00014089648798521257, |
| "loss": 0.2633, |
| "step": 1280 |
| }, |
| { |
| "epoch": 1.19, |
| "learning_rate": 0.00014043438077634014, |
| "loss": 0.388, |
| "step": 1290 |
| }, |
| { |
| "epoch": 1.2, |
| "learning_rate": 0.00013997227356746765, |
| "loss": 0.3814, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.2, |
| "eval_accuracy": 0.8393131727319323, |
| "eval_f1": 0.8393131727319323, |
| "eval_loss": 0.3524097204208374, |
| "eval_precision": 0.8393131727319323, |
| "eval_recall": 0.8393131727319323, |
| "eval_runtime": 82.9575, |
| "eval_samples_per_second": 94.072, |
| "eval_steps_per_second": 11.765, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.21, |
| "learning_rate": 0.0001395101663585952, |
| "loss": 0.3347, |
| "step": 1310 |
| }, |
| { |
| "epoch": 1.22, |
| "learning_rate": 0.00013904805914972273, |
| "loss": 0.3734, |
| "step": 1320 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 0.0001385859519408503, |
| "loss": 0.3307, |
| "step": 1330 |
| }, |
| { |
| "epoch": 1.24, |
| "learning_rate": 0.00013812384473197784, |
| "loss": 0.3689, |
| "step": 1340 |
| }, |
| { |
| "epoch": 1.25, |
| "learning_rate": 0.00013766173752310535, |
| "loss": 0.3188, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.26, |
| "learning_rate": 0.0001371996303142329, |
| "loss": 0.3658, |
| "step": 1360 |
| }, |
| { |
| "epoch": 1.27, |
| "learning_rate": 0.00013673752310536046, |
| "loss": 0.3124, |
| "step": 1370 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.000136275415896488, |
| "loss": 0.3679, |
| "step": 1380 |
| }, |
| { |
| "epoch": 1.28, |
| "learning_rate": 0.00013581330868761552, |
| "loss": 0.2349, |
| "step": 1390 |
| }, |
| { |
| "epoch": 1.29, |
| "learning_rate": 0.00013535120147874308, |
| "loss": 0.4162, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.29, |
| "eval_accuracy": 0.831368528959508, |
| "eval_f1": 0.8313685289595081, |
| "eval_loss": 0.36000585556030273, |
| "eval_precision": 0.831368528959508, |
| "eval_recall": 0.831368528959508, |
| "eval_runtime": 83.2807, |
| "eval_samples_per_second": 93.707, |
| "eval_steps_per_second": 11.719, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.3, |
| "learning_rate": 0.00013488909426987063, |
| "loss": 0.2992, |
| "step": 1410 |
| }, |
| { |
| "epoch": 1.31, |
| "learning_rate": 0.00013442698706099817, |
| "loss": 0.3341, |
| "step": 1420 |
| }, |
| { |
| "epoch": 1.32, |
| "learning_rate": 0.00013396487985212568, |
| "loss": 0.4084, |
| "step": 1430 |
| }, |
| { |
| "epoch": 1.33, |
| "learning_rate": 0.00013350277264325325, |
| "loss": 0.2804, |
| "step": 1440 |
| }, |
| { |
| "epoch": 1.34, |
| "learning_rate": 0.0001330406654343808, |
| "loss": 0.3436, |
| "step": 1450 |
| }, |
| { |
| "epoch": 1.35, |
| "learning_rate": 0.00013257855822550833, |
| "loss": 0.2991, |
| "step": 1460 |
| }, |
| { |
| "epoch": 1.36, |
| "learning_rate": 0.00013211645101663584, |
| "loss": 0.3522, |
| "step": 1470 |
| }, |
| { |
| "epoch": 1.37, |
| "learning_rate": 0.0001316543438077634, |
| "loss": 0.2607, |
| "step": 1480 |
| }, |
| { |
| "epoch": 1.38, |
| "learning_rate": 0.00013119223659889095, |
| "loss": 0.3095, |
| "step": 1490 |
| }, |
| { |
| "epoch": 1.39, |
| "learning_rate": 0.0001307301293900185, |
| "loss": 0.3096, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.39, |
| "eval_accuracy": 0.8404664274730907, |
| "eval_f1": 0.8404664274730907, |
| "eval_loss": 0.35373032093048096, |
| "eval_precision": 0.8404664274730907, |
| "eval_recall": 0.8404664274730907, |
| "eval_runtime": 83.2107, |
| "eval_samples_per_second": 93.786, |
| "eval_steps_per_second": 11.729, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00013026802218114603, |
| "loss": 0.3398, |
| "step": 1510 |
| }, |
| { |
| "epoch": 1.4, |
| "learning_rate": 0.00012980591497227357, |
| "loss": 0.3616, |
| "step": 1520 |
| }, |
| { |
| "epoch": 1.41, |
| "learning_rate": 0.00012934380776340111, |
| "loss": 0.3308, |
| "step": 1530 |
| }, |
| { |
| "epoch": 1.42, |
| "learning_rate": 0.00012888170055452866, |
| "loss": 0.3405, |
| "step": 1540 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 0.0001284195933456562, |
| "loss": 0.3674, |
| "step": 1550 |
| }, |
| { |
| "epoch": 1.44, |
| "learning_rate": 0.00012795748613678374, |
| "loss": 0.3469, |
| "step": 1560 |
| }, |
| { |
| "epoch": 1.45, |
| "learning_rate": 0.00012749537892791128, |
| "loss": 0.3249, |
| "step": 1570 |
| }, |
| { |
| "epoch": 1.46, |
| "learning_rate": 0.00012703327171903882, |
| "loss": 0.3027, |
| "step": 1580 |
| }, |
| { |
| "epoch": 1.47, |
| "learning_rate": 0.00012657116451016639, |
| "loss": 0.3378, |
| "step": 1590 |
| }, |
| { |
| "epoch": 1.48, |
| "learning_rate": 0.0001261090573012939, |
| "loss": 0.285, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.48, |
| "eval_accuracy": 0.8234238851870835, |
| "eval_f1": 0.8234238851870836, |
| "eval_loss": 0.38117510080337524, |
| "eval_precision": 0.8234238851870835, |
| "eval_recall": 0.8234238851870835, |
| "eval_runtime": 82.7683, |
| "eval_samples_per_second": 94.287, |
| "eval_steps_per_second": 11.792, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.49, |
| "learning_rate": 0.00012564695009242144, |
| "loss": 0.2934, |
| "step": 1610 |
| }, |
| { |
| "epoch": 1.5, |
| "learning_rate": 0.00012518484288354898, |
| "loss": 0.3616, |
| "step": 1620 |
| }, |
| { |
| "epoch": 1.51, |
| "learning_rate": 0.00012472273567467655, |
| "loss": 0.3436, |
| "step": 1630 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.00012426062846580406, |
| "loss": 0.3223, |
| "step": 1640 |
| }, |
| { |
| "epoch": 1.52, |
| "learning_rate": 0.0001237985212569316, |
| "loss": 0.3983, |
| "step": 1650 |
| }, |
| { |
| "epoch": 1.53, |
| "learning_rate": 0.00012333641404805914, |
| "loss": 0.3771, |
| "step": 1660 |
| }, |
| { |
| "epoch": 1.54, |
| "learning_rate": 0.0001228743068391867, |
| "loss": 0.2622, |
| "step": 1670 |
| }, |
| { |
| "epoch": 1.55, |
| "learning_rate": 0.00012241219963031423, |
| "loss": 0.3511, |
| "step": 1680 |
| }, |
| { |
| "epoch": 1.56, |
| "learning_rate": 0.00012195009242144178, |
| "loss": 0.3802, |
| "step": 1690 |
| }, |
| { |
| "epoch": 1.57, |
| "learning_rate": 0.00012148798521256932, |
| "loss": 0.3039, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.57, |
| "eval_accuracy": 0.8258585340850846, |
| "eval_f1": 0.8258585340850846, |
| "eval_loss": 0.44907084107398987, |
| "eval_precision": 0.8258585340850846, |
| "eval_recall": 0.8258585340850846, |
| "eval_runtime": 83.5438, |
| "eval_samples_per_second": 93.412, |
| "eval_steps_per_second": 11.682, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.58, |
| "learning_rate": 0.00012102587800369687, |
| "loss": 0.3883, |
| "step": 1710 |
| }, |
| { |
| "epoch": 1.59, |
| "learning_rate": 0.00012056377079482442, |
| "loss": 0.4093, |
| "step": 1720 |
| }, |
| { |
| "epoch": 1.6, |
| "learning_rate": 0.00012010166358595194, |
| "loss": 0.3599, |
| "step": 1730 |
| }, |
| { |
| "epoch": 1.61, |
| "learning_rate": 0.00011963955637707948, |
| "loss": 0.3568, |
| "step": 1740 |
| }, |
| { |
| "epoch": 1.62, |
| "learning_rate": 0.00011917744916820704, |
| "loss": 0.3132, |
| "step": 1750 |
| }, |
| { |
| "epoch": 1.63, |
| "learning_rate": 0.00011871534195933458, |
| "loss": 0.4369, |
| "step": 1760 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 0.0001182532347504621, |
| "loss": 0.2406, |
| "step": 1770 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.00011779112754158965, |
| "loss": 0.2356, |
| "step": 1780 |
| }, |
| { |
| "epoch": 1.65, |
| "learning_rate": 0.0001173290203327172, |
| "loss": 0.4487, |
| "step": 1790 |
| }, |
| { |
| "epoch": 1.66, |
| "learning_rate": 0.00011686691312384474, |
| "loss": 0.3026, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.66, |
| "eval_accuracy": 0.8154792414146591, |
| "eval_f1": 0.8154792414146591, |
| "eval_loss": 0.37932685017585754, |
| "eval_precision": 0.8154792414146591, |
| "eval_recall": 0.8154792414146591, |
| "eval_runtime": 83.4604, |
| "eval_samples_per_second": 93.505, |
| "eval_steps_per_second": 11.694, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.67, |
| "learning_rate": 0.00011640480591497227, |
| "loss": 0.2803, |
| "step": 1810 |
| }, |
| { |
| "epoch": 1.68, |
| "learning_rate": 0.00011594269870609982, |
| "loss": 0.3341, |
| "step": 1820 |
| }, |
| { |
| "epoch": 1.69, |
| "learning_rate": 0.00011548059149722736, |
| "loss": 0.2738, |
| "step": 1830 |
| }, |
| { |
| "epoch": 1.7, |
| "learning_rate": 0.0001150184842883549, |
| "loss": 0.2745, |
| "step": 1840 |
| }, |
| { |
| "epoch": 1.71, |
| "learning_rate": 0.00011455637707948243, |
| "loss": 0.2923, |
| "step": 1850 |
| }, |
| { |
| "epoch": 1.72, |
| "learning_rate": 0.00011409426987060999, |
| "loss": 0.2751, |
| "step": 1860 |
| }, |
| { |
| "epoch": 1.73, |
| "learning_rate": 0.00011363216266173753, |
| "loss": 0.3123, |
| "step": 1870 |
| }, |
| { |
| "epoch": 1.74, |
| "learning_rate": 0.00011317005545286508, |
| "loss": 0.2117, |
| "step": 1880 |
| }, |
| { |
| "epoch": 1.75, |
| "learning_rate": 0.00011270794824399262, |
| "loss": 0.4266, |
| "step": 1890 |
| }, |
| { |
| "epoch": 1.76, |
| "learning_rate": 0.00011224584103512015, |
| "loss": 0.2304, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.76, |
| "eval_accuracy": 0.8175294720656073, |
| "eval_f1": 0.8175294720656073, |
| "eval_loss": 0.34882843494415283, |
| "eval_precision": 0.8175294720656073, |
| "eval_recall": 0.8175294720656073, |
| "eval_runtime": 83.2606, |
| "eval_samples_per_second": 93.73, |
| "eval_steps_per_second": 11.722, |
| "step": 1900 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.00011178373382624769, |
| "loss": 0.3104, |
| "step": 1910 |
| }, |
| { |
| "epoch": 1.77, |
| "learning_rate": 0.00011132162661737524, |
| "loss": 0.2913, |
| "step": 1920 |
| }, |
| { |
| "epoch": 1.78, |
| "learning_rate": 0.00011085951940850278, |
| "loss": 0.2877, |
| "step": 1930 |
| }, |
| { |
| "epoch": 1.79, |
| "learning_rate": 0.00011039741219963031, |
| "loss": 0.2993, |
| "step": 1940 |
| }, |
| { |
| "epoch": 1.8, |
| "learning_rate": 0.00010993530499075787, |
| "loss": 0.3001, |
| "step": 1950 |
| }, |
| { |
| "epoch": 1.81, |
| "learning_rate": 0.0001094731977818854, |
| "loss": 0.2604, |
| "step": 1960 |
| }, |
| { |
| "epoch": 1.82, |
| "learning_rate": 0.00010901109057301295, |
| "loss": 0.2376, |
| "step": 1970 |
| }, |
| { |
| "epoch": 1.83, |
| "learning_rate": 0.00010854898336414047, |
| "loss": 0.3068, |
| "step": 1980 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 0.00010808687615526803, |
| "loss": 0.2837, |
| "step": 1990 |
| }, |
| { |
| "epoch": 1.85, |
| "learning_rate": 0.00010762476894639557, |
| "loss": 0.2454, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.85, |
| "eval_accuracy": 0.8357252690927729, |
| "eval_f1": 0.8357252690927729, |
| "eval_loss": 0.34422409534454346, |
| "eval_precision": 0.8357252690927729, |
| "eval_recall": 0.8357252690927729, |
| "eval_runtime": 83.1104, |
| "eval_samples_per_second": 93.899, |
| "eval_steps_per_second": 11.743, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.86, |
| "learning_rate": 0.00010716266173752312, |
| "loss": 0.2813, |
| "step": 2010 |
| }, |
| { |
| "epoch": 1.87, |
| "learning_rate": 0.00010670055452865064, |
| "loss": 0.3136, |
| "step": 2020 |
| }, |
| { |
| "epoch": 1.88, |
| "learning_rate": 0.00010623844731977819, |
| "loss": 0.3534, |
| "step": 2030 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.00010577634011090573, |
| "loss": 0.2866, |
| "step": 2040 |
| }, |
| { |
| "epoch": 1.89, |
| "learning_rate": 0.00010531423290203329, |
| "loss": 0.2329, |
| "step": 2050 |
| }, |
| { |
| "epoch": 1.9, |
| "learning_rate": 0.00010485212569316081, |
| "loss": 0.2623, |
| "step": 2060 |
| }, |
| { |
| "epoch": 1.91, |
| "learning_rate": 0.00010439001848428835, |
| "loss": 0.3563, |
| "step": 2070 |
| }, |
| { |
| "epoch": 1.92, |
| "learning_rate": 0.0001039279112754159, |
| "loss": 0.2561, |
| "step": 2080 |
| }, |
| { |
| "epoch": 1.93, |
| "learning_rate": 0.00010346580406654345, |
| "loss": 0.2701, |
| "step": 2090 |
| }, |
| { |
| "epoch": 1.94, |
| "learning_rate": 0.00010300369685767099, |
| "loss": 0.314, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.94, |
| "eval_accuracy": 0.8370066632496156, |
| "eval_f1": 0.8370066632496156, |
| "eval_loss": 0.34697625041007996, |
| "eval_precision": 0.8370066632496156, |
| "eval_recall": 0.8370066632496156, |
| "eval_runtime": 83.0388, |
| "eval_samples_per_second": 93.98, |
| "eval_steps_per_second": 11.754, |
| "step": 2100 |
| }, |
| { |
| "epoch": 1.95, |
| "learning_rate": 0.00010254158964879852, |
| "loss": 0.2527, |
| "step": 2110 |
| }, |
| { |
| "epoch": 1.96, |
| "learning_rate": 0.00010207948243992607, |
| "loss": 0.4185, |
| "step": 2120 |
| }, |
| { |
| "epoch": 1.97, |
| "learning_rate": 0.00010161737523105361, |
| "loss": 0.2779, |
| "step": 2130 |
| }, |
| { |
| "epoch": 1.98, |
| "learning_rate": 0.00010115526802218117, |
| "loss": 0.2264, |
| "step": 2140 |
| }, |
| { |
| "epoch": 1.99, |
| "learning_rate": 0.00010069316081330868, |
| "loss": 0.2755, |
| "step": 2150 |
| }, |
| { |
| "epoch": 2.0, |
| "learning_rate": 0.00010023105360443623, |
| "loss": 0.2602, |
| "step": 2160 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 9.976894639556378e-05, |
| "loss": 0.2639, |
| "step": 2170 |
| }, |
| { |
| "epoch": 2.01, |
| "learning_rate": 9.930683918669132e-05, |
| "loss": 0.3943, |
| "step": 2180 |
| }, |
| { |
| "epoch": 2.02, |
| "learning_rate": 9.884473197781886e-05, |
| "loss": 0.3857, |
| "step": 2190 |
| }, |
| { |
| "epoch": 2.03, |
| "learning_rate": 9.83826247689464e-05, |
| "loss": 0.3015, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.03, |
| "eval_accuracy": 0.8500768836494106, |
| "eval_f1": 0.8500768836494106, |
| "eval_loss": 0.32626640796661377, |
| "eval_precision": 0.8500768836494106, |
| "eval_recall": 0.8500768836494106, |
| "eval_runtime": 83.2219, |
| "eval_samples_per_second": 93.773, |
| "eval_steps_per_second": 11.728, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.04, |
| "learning_rate": 9.792051756007394e-05, |
| "loss": 0.263, |
| "step": 2210 |
| }, |
| { |
| "epoch": 2.05, |
| "learning_rate": 9.745841035120148e-05, |
| "loss": 0.2313, |
| "step": 2220 |
| }, |
| { |
| "epoch": 2.06, |
| "learning_rate": 9.699630314232902e-05, |
| "loss": 0.2466, |
| "step": 2230 |
| }, |
| { |
| "epoch": 2.07, |
| "learning_rate": 9.653419593345656e-05, |
| "loss": 0.3537, |
| "step": 2240 |
| }, |
| { |
| "epoch": 2.08, |
| "learning_rate": 9.607208872458411e-05, |
| "loss": 0.2296, |
| "step": 2250 |
| }, |
| { |
| "epoch": 2.09, |
| "learning_rate": 9.560998151571166e-05, |
| "loss": 0.1974, |
| "step": 2260 |
| }, |
| { |
| "epoch": 2.1, |
| "learning_rate": 9.51478743068392e-05, |
| "loss": 0.2216, |
| "step": 2270 |
| }, |
| { |
| "epoch": 2.11, |
| "learning_rate": 9.468576709796674e-05, |
| "loss": 0.3016, |
| "step": 2280 |
| }, |
| { |
| "epoch": 2.12, |
| "learning_rate": 9.422365988909428e-05, |
| "loss": 0.2648, |
| "step": 2290 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 9.376155268022182e-05, |
| "loss": 0.2595, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.13, |
| "eval_accuracy": 0.842516658124039, |
| "eval_f1": 0.842516658124039, |
| "eval_loss": 0.3540014326572418, |
| "eval_precision": 0.842516658124039, |
| "eval_recall": 0.842516658124039, |
| "eval_runtime": 82.854, |
| "eval_samples_per_second": 94.19, |
| "eval_steps_per_second": 11.78, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.13, |
| "learning_rate": 9.329944547134936e-05, |
| "loss": 0.1862, |
| "step": 2310 |
| }, |
| { |
| "epoch": 2.14, |
| "learning_rate": 9.28373382624769e-05, |
| "loss": 0.2549, |
| "step": 2320 |
| }, |
| { |
| "epoch": 2.15, |
| "learning_rate": 9.237523105360444e-05, |
| "loss": 0.2497, |
| "step": 2330 |
| }, |
| { |
| "epoch": 2.16, |
| "learning_rate": 9.191312384473198e-05, |
| "loss": 0.3169, |
| "step": 2340 |
| }, |
| { |
| "epoch": 2.17, |
| "learning_rate": 9.145101663585952e-05, |
| "loss": 0.299, |
| "step": 2350 |
| }, |
| { |
| "epoch": 2.18, |
| "learning_rate": 9.098890942698706e-05, |
| "loss": 0.2912, |
| "step": 2360 |
| }, |
| { |
| "epoch": 2.19, |
| "learning_rate": 9.05268022181146e-05, |
| "loss": 0.2363, |
| "step": 2370 |
| }, |
| { |
| "epoch": 2.2, |
| "learning_rate": 9.006469500924214e-05, |
| "loss": 0.2762, |
| "step": 2380 |
| }, |
| { |
| "epoch": 2.21, |
| "learning_rate": 8.960258780036968e-05, |
| "loss": 0.1996, |
| "step": 2390 |
| }, |
| { |
| "epoch": 2.22, |
| "learning_rate": 8.914048059149724e-05, |
| "loss": 0.2901, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.22, |
| "eval_accuracy": 0.8577652485904664, |
| "eval_f1": 0.8577652485904664, |
| "eval_loss": 0.3567024767398834, |
| "eval_precision": 0.8577652485904664, |
| "eval_recall": 0.8577652485904664, |
| "eval_runtime": 82.9736, |
| "eval_samples_per_second": 94.054, |
| "eval_steps_per_second": 11.763, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.23, |
| "learning_rate": 8.867837338262477e-05, |
| "loss": 0.2183, |
| "step": 2410 |
| }, |
| { |
| "epoch": 2.24, |
| "learning_rate": 8.821626617375232e-05, |
| "loss": 0.3484, |
| "step": 2420 |
| }, |
| { |
| "epoch": 2.25, |
| "learning_rate": 8.775415896487985e-05, |
| "loss": 0.2335, |
| "step": 2430 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 8.72920517560074e-05, |
| "loss": 0.2727, |
| "step": 2440 |
| }, |
| { |
| "epoch": 2.26, |
| "learning_rate": 8.682994454713494e-05, |
| "loss": 0.2093, |
| "step": 2450 |
| }, |
| { |
| "epoch": 2.27, |
| "learning_rate": 8.636783733826248e-05, |
| "loss": 0.2919, |
| "step": 2460 |
| }, |
| { |
| "epoch": 2.28, |
| "learning_rate": 8.590573012939002e-05, |
| "loss": 0.2532, |
| "step": 2470 |
| }, |
| { |
| "epoch": 2.29, |
| "learning_rate": 8.544362292051756e-05, |
| "loss": 0.2433, |
| "step": 2480 |
| }, |
| { |
| "epoch": 2.3, |
| "learning_rate": 8.49815157116451e-05, |
| "loss": 0.2603, |
| "step": 2490 |
| }, |
| { |
| "epoch": 2.31, |
| "learning_rate": 8.451940850277265e-05, |
| "loss": 0.1825, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.31, |
| "eval_accuracy": 0.858534085084572, |
| "eval_f1": 0.8585340850845719, |
| "eval_loss": 0.2933545410633087, |
| "eval_precision": 0.858534085084572, |
| "eval_recall": 0.858534085084572, |
| "eval_runtime": 83.1432, |
| "eval_samples_per_second": 93.862, |
| "eval_steps_per_second": 11.739, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.32, |
| "learning_rate": 8.405730129390019e-05, |
| "loss": 0.2932, |
| "step": 2510 |
| }, |
| { |
| "epoch": 2.33, |
| "learning_rate": 8.359519408502773e-05, |
| "loss": 0.237, |
| "step": 2520 |
| }, |
| { |
| "epoch": 2.34, |
| "learning_rate": 8.313308687615527e-05, |
| "loss": 0.2803, |
| "step": 2530 |
| }, |
| { |
| "epoch": 2.35, |
| "learning_rate": 8.267097966728281e-05, |
| "loss": 0.2615, |
| "step": 2540 |
| }, |
| { |
| "epoch": 2.36, |
| "learning_rate": 8.220887245841036e-05, |
| "loss": 0.3773, |
| "step": 2550 |
| }, |
| { |
| "epoch": 2.37, |
| "learning_rate": 8.174676524953789e-05, |
| "loss": 0.2332, |
| "step": 2560 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 8.128465804066544e-05, |
| "loss": 0.1964, |
| "step": 2570 |
| }, |
| { |
| "epoch": 2.38, |
| "learning_rate": 8.082255083179297e-05, |
| "loss": 0.2671, |
| "step": 2580 |
| }, |
| { |
| "epoch": 2.39, |
| "learning_rate": 8.036044362292053e-05, |
| "loss": 0.2849, |
| "step": 2590 |
| }, |
| { |
| "epoch": 2.4, |
| "learning_rate": 7.989833641404805e-05, |
| "loss": 0.2558, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.4, |
| "eval_accuracy": 0.8377754997437211, |
| "eval_f1": 0.8377754997437211, |
| "eval_loss": 0.32812419533729553, |
| "eval_precision": 0.8377754997437211, |
| "eval_recall": 0.8377754997437211, |
| "eval_runtime": 83.4244, |
| "eval_samples_per_second": 93.546, |
| "eval_steps_per_second": 11.699, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.41, |
| "learning_rate": 7.943622920517561e-05, |
| "loss": 0.2514, |
| "step": 2610 |
| }, |
| { |
| "epoch": 2.42, |
| "learning_rate": 7.897412199630314e-05, |
| "loss": 0.2943, |
| "step": 2620 |
| }, |
| { |
| "epoch": 2.43, |
| "learning_rate": 7.851201478743069e-05, |
| "loss": 0.2335, |
| "step": 2630 |
| }, |
| { |
| "epoch": 2.44, |
| "learning_rate": 7.804990757855823e-05, |
| "loss": 0.1907, |
| "step": 2640 |
| }, |
| { |
| "epoch": 2.45, |
| "learning_rate": 7.758780036968577e-05, |
| "loss": 0.2308, |
| "step": 2650 |
| }, |
| { |
| "epoch": 2.46, |
| "learning_rate": 7.712569316081331e-05, |
| "loss": 0.2706, |
| "step": 2660 |
| }, |
| { |
| "epoch": 2.47, |
| "learning_rate": 7.666358595194085e-05, |
| "loss": 0.2988, |
| "step": 2670 |
| }, |
| { |
| "epoch": 2.48, |
| "learning_rate": 7.620147874306839e-05, |
| "loss": 0.2063, |
| "step": 2680 |
| }, |
| { |
| "epoch": 2.49, |
| "learning_rate": 7.573937153419593e-05, |
| "loss": 0.2314, |
| "step": 2690 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 7.527726432532349e-05, |
| "loss": 0.2553, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.5, |
| "eval_accuracy": 0.8305996924654023, |
| "eval_f1": 0.8305996924654023, |
| "eval_loss": 0.38693130016326904, |
| "eval_precision": 0.8305996924654023, |
| "eval_recall": 0.8305996924654023, |
| "eval_runtime": 83.2337, |
| "eval_samples_per_second": 93.76, |
| "eval_steps_per_second": 11.726, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.5, |
| "learning_rate": 7.481515711645102e-05, |
| "loss": 0.4367, |
| "step": 2710 |
| }, |
| { |
| "epoch": 2.51, |
| "learning_rate": 7.435304990757857e-05, |
| "loss": 0.2324, |
| "step": 2720 |
| }, |
| { |
| "epoch": 2.52, |
| "learning_rate": 7.38909426987061e-05, |
| "loss": 0.2025, |
| "step": 2730 |
| }, |
| { |
| "epoch": 2.53, |
| "learning_rate": 7.342883548983365e-05, |
| "loss": 0.2587, |
| "step": 2740 |
| }, |
| { |
| "epoch": 2.54, |
| "learning_rate": 7.296672828096118e-05, |
| "loss": 0.3039, |
| "step": 2750 |
| }, |
| { |
| "epoch": 2.55, |
| "learning_rate": 7.250462107208873e-05, |
| "loss": 0.211, |
| "step": 2760 |
| }, |
| { |
| "epoch": 2.56, |
| "learning_rate": 7.204251386321626e-05, |
| "loss": 0.2925, |
| "step": 2770 |
| }, |
| { |
| "epoch": 2.57, |
| "learning_rate": 7.158040665434381e-05, |
| "loss": 0.2267, |
| "step": 2780 |
| }, |
| { |
| "epoch": 2.58, |
| "learning_rate": 7.111829944547135e-05, |
| "loss": 0.2621, |
| "step": 2790 |
| }, |
| { |
| "epoch": 2.59, |
| "learning_rate": 7.06561922365989e-05, |
| "loss": 0.1911, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.59, |
| "eval_accuracy": 0.8340594566888775, |
| "eval_f1": 0.8340594566888775, |
| "eval_loss": 0.3585541546344757, |
| "eval_precision": 0.8340594566888775, |
| "eval_recall": 0.8340594566888775, |
| "eval_runtime": 83.9924, |
| "eval_samples_per_second": 92.913, |
| "eval_steps_per_second": 11.62, |
| "step": 2800 |
| }, |
| { |
| "epoch": 2.6, |
| "learning_rate": 7.019408502772644e-05, |
| "loss": 0.1907, |
| "step": 2810 |
| }, |
| { |
| "epoch": 2.61, |
| "learning_rate": 6.973197781885398e-05, |
| "loss": 0.2851, |
| "step": 2820 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 6.926987060998153e-05, |
| "loss": 0.1846, |
| "step": 2830 |
| }, |
| { |
| "epoch": 2.62, |
| "learning_rate": 6.880776340110906e-05, |
| "loss": 0.2278, |
| "step": 2840 |
| }, |
| { |
| "epoch": 2.63, |
| "learning_rate": 6.834565619223661e-05, |
| "loss": 0.2496, |
| "step": 2850 |
| }, |
| { |
| "epoch": 2.64, |
| "learning_rate": 6.788354898336414e-05, |
| "loss": 0.1906, |
| "step": 2860 |
| }, |
| { |
| "epoch": 2.65, |
| "learning_rate": 6.74214417744917e-05, |
| "loss": 0.1721, |
| "step": 2870 |
| }, |
| { |
| "epoch": 2.66, |
| "learning_rate": 6.695933456561922e-05, |
| "loss": 0.221, |
| "step": 2880 |
| }, |
| { |
| "epoch": 2.67, |
| "learning_rate": 6.649722735674678e-05, |
| "loss": 0.2934, |
| "step": 2890 |
| }, |
| { |
| "epoch": 2.68, |
| "learning_rate": 6.60351201478743e-05, |
| "loss": 0.1705, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.68, |
| "eval_accuracy": 0.8576371091747822, |
| "eval_f1": 0.8576371091747822, |
| "eval_loss": 0.3363144099712372, |
| "eval_precision": 0.8576371091747822, |
| "eval_recall": 0.8576371091747822, |
| "eval_runtime": 82.6805, |
| "eval_samples_per_second": 94.387, |
| "eval_steps_per_second": 11.804, |
| "step": 2900 |
| }, |
| { |
| "epoch": 2.69, |
| "learning_rate": 6.557301293900186e-05, |
| "loss": 0.3019, |
| "step": 2910 |
| }, |
| { |
| "epoch": 2.7, |
| "learning_rate": 6.511090573012938e-05, |
| "loss": 0.3116, |
| "step": 2920 |
| }, |
| { |
| "epoch": 2.71, |
| "learning_rate": 6.464879852125694e-05, |
| "loss": 0.1549, |
| "step": 2930 |
| }, |
| { |
| "epoch": 2.72, |
| "learning_rate": 6.418669131238448e-05, |
| "loss": 0.2972, |
| "step": 2940 |
| }, |
| { |
| "epoch": 2.73, |
| "learning_rate": 6.372458410351202e-05, |
| "loss": 0.2639, |
| "step": 2950 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 6.326247689463956e-05, |
| "loss": 0.2287, |
| "step": 2960 |
| }, |
| { |
| "epoch": 2.74, |
| "learning_rate": 6.28003696857671e-05, |
| "loss": 0.2893, |
| "step": 2970 |
| }, |
| { |
| "epoch": 2.75, |
| "learning_rate": 6.233826247689464e-05, |
| "loss": 0.2132, |
| "step": 2980 |
| }, |
| { |
| "epoch": 2.76, |
| "learning_rate": 6.187615526802218e-05, |
| "loss": 0.1585, |
| "step": 2990 |
| }, |
| { |
| "epoch": 2.77, |
| "learning_rate": 6.141404805914972e-05, |
| "loss": 0.2686, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.77, |
| "eval_accuracy": 0.8535366478728857, |
| "eval_f1": 0.8535366478728857, |
| "eval_loss": 0.33777493238449097, |
| "eval_precision": 0.8535366478728857, |
| "eval_recall": 0.8535366478728857, |
| "eval_runtime": 83.4535, |
| "eval_samples_per_second": 93.513, |
| "eval_steps_per_second": 11.695, |
| "step": 3000 |
| }, |
| { |
| "epoch": 2.78, |
| "learning_rate": 6.0951940850277264e-05, |
| "loss": 0.2497, |
| "step": 3010 |
| }, |
| { |
| "epoch": 2.79, |
| "learning_rate": 6.048983364140481e-05, |
| "loss": 0.2184, |
| "step": 3020 |
| }, |
| { |
| "epoch": 2.8, |
| "learning_rate": 6.002772643253235e-05, |
| "loss": 0.1742, |
| "step": 3030 |
| }, |
| { |
| "epoch": 2.81, |
| "learning_rate": 5.956561922365989e-05, |
| "loss": 0.3367, |
| "step": 3040 |
| }, |
| { |
| "epoch": 2.82, |
| "learning_rate": 5.9103512014787434e-05, |
| "loss": 0.2488, |
| "step": 3050 |
| }, |
| { |
| "epoch": 2.83, |
| "learning_rate": 5.864140480591498e-05, |
| "loss": 0.1905, |
| "step": 3060 |
| }, |
| { |
| "epoch": 2.84, |
| "learning_rate": 5.8179297597042515e-05, |
| "loss": 0.2274, |
| "step": 3070 |
| }, |
| { |
| "epoch": 2.85, |
| "learning_rate": 5.771719038817006e-05, |
| "loss": 0.1707, |
| "step": 3080 |
| }, |
| { |
| "epoch": 2.86, |
| "learning_rate": 5.72550831792976e-05, |
| "loss": 0.1783, |
| "step": 3090 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 5.6792975970425144e-05, |
| "loss": 0.2136, |
| "step": 3100 |
| }, |
| { |
| "epoch": 2.87, |
| "eval_accuracy": 0.8676319835981547, |
| "eval_f1": 0.8676319835981547, |
| "eval_loss": 0.331231951713562, |
| "eval_precision": 0.8676319835981547, |
| "eval_recall": 0.8676319835981547, |
| "eval_runtime": 84.7186, |
| "eval_samples_per_second": 92.117, |
| "eval_steps_per_second": 11.52, |
| "step": 3100 |
| }, |
| { |
| "epoch": 2.87, |
| "learning_rate": 5.633086876155268e-05, |
| "loss": 0.2459, |
| "step": 3110 |
| }, |
| { |
| "epoch": 2.88, |
| "learning_rate": 5.5868761552680226e-05, |
| "loss": 0.4273, |
| "step": 3120 |
| }, |
| { |
| "epoch": 2.89, |
| "learning_rate": 5.540665434380776e-05, |
| "loss": 0.2554, |
| "step": 3130 |
| }, |
| { |
| "epoch": 2.9, |
| "learning_rate": 5.494454713493531e-05, |
| "loss": 0.1924, |
| "step": 3140 |
| }, |
| { |
| "epoch": 2.91, |
| "learning_rate": 5.448243992606285e-05, |
| "loss": 0.2888, |
| "step": 3150 |
| }, |
| { |
| "epoch": 2.92, |
| "learning_rate": 5.402033271719039e-05, |
| "loss": 0.2182, |
| "step": 3160 |
| }, |
| { |
| "epoch": 2.93, |
| "learning_rate": 5.355822550831793e-05, |
| "loss": 0.2181, |
| "step": 3170 |
| }, |
| { |
| "epoch": 2.94, |
| "learning_rate": 5.309611829944548e-05, |
| "loss": 0.1726, |
| "step": 3180 |
| }, |
| { |
| "epoch": 2.95, |
| "learning_rate": 5.263401109057301e-05, |
| "loss": 0.2143, |
| "step": 3190 |
| }, |
| { |
| "epoch": 2.96, |
| "learning_rate": 5.217190388170056e-05, |
| "loss": 0.1913, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.96, |
| "eval_accuracy": 0.8559712967708867, |
| "eval_f1": 0.8559712967708867, |
| "eval_loss": 0.3304664194583893, |
| "eval_precision": 0.8559712967708867, |
| "eval_recall": 0.8559712967708867, |
| "eval_runtime": 83.4271, |
| "eval_samples_per_second": 93.543, |
| "eval_steps_per_second": 11.699, |
| "step": 3200 |
| }, |
| { |
| "epoch": 2.97, |
| "learning_rate": 5.1709796672828106e-05, |
| "loss": 0.2562, |
| "step": 3210 |
| }, |
| { |
| "epoch": 2.98, |
| "learning_rate": 5.124768946395564e-05, |
| "loss": 0.2153, |
| "step": 3220 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 5.078558225508319e-05, |
| "loss": 0.233, |
| "step": 3230 |
| }, |
| { |
| "epoch": 2.99, |
| "learning_rate": 5.032347504621072e-05, |
| "loss": 0.2605, |
| "step": 3240 |
| }, |
| { |
| "epoch": 3.0, |
| "learning_rate": 4.986136783733826e-05, |
| "loss": 0.2078, |
| "step": 3250 |
| }, |
| { |
| "epoch": 3.01, |
| "learning_rate": 4.93992606284658e-05, |
| "loss": 0.1473, |
| "step": 3260 |
| }, |
| { |
| "epoch": 3.02, |
| "learning_rate": 4.893715341959334e-05, |
| "loss": 0.0867, |
| "step": 3270 |
| }, |
| { |
| "epoch": 3.03, |
| "learning_rate": 4.8475046210720884e-05, |
| "loss": 0.189, |
| "step": 3280 |
| }, |
| { |
| "epoch": 3.04, |
| "learning_rate": 4.801293900184843e-05, |
| "loss": 0.1112, |
| "step": 3290 |
| }, |
| { |
| "epoch": 3.05, |
| "learning_rate": 4.755083179297597e-05, |
| "loss": 0.3307, |
| "step": 3300 |
| }, |
| { |
| "epoch": 3.05, |
| "eval_accuracy": 0.8675038441824705, |
| "eval_f1": 0.8675038441824704, |
| "eval_loss": 0.3613434433937073, |
| "eval_precision": 0.8675038441824705, |
| "eval_recall": 0.8675038441824705, |
| "eval_runtime": 84.0129, |
| "eval_samples_per_second": 92.891, |
| "eval_steps_per_second": 11.617, |
| "step": 3300 |
| }, |
| { |
| "epoch": 3.06, |
| "learning_rate": 4.708872458410351e-05, |
| "loss": 0.2285, |
| "step": 3310 |
| }, |
| { |
| "epoch": 3.07, |
| "learning_rate": 4.662661737523106e-05, |
| "loss": 0.1865, |
| "step": 3320 |
| }, |
| { |
| "epoch": 3.08, |
| "learning_rate": 4.61645101663586e-05, |
| "loss": 0.2364, |
| "step": 3330 |
| }, |
| { |
| "epoch": 3.09, |
| "learning_rate": 4.570240295748614e-05, |
| "loss": 0.2601, |
| "step": 3340 |
| }, |
| { |
| "epoch": 3.1, |
| "learning_rate": 4.524029574861368e-05, |
| "loss": 0.2584, |
| "step": 3350 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 4.4778188539741223e-05, |
| "loss": 0.1929, |
| "step": 3360 |
| }, |
| { |
| "epoch": 3.11, |
| "learning_rate": 4.4316081330868764e-05, |
| "loss": 0.1556, |
| "step": 3370 |
| }, |
| { |
| "epoch": 3.12, |
| "learning_rate": 4.3853974121996305e-05, |
| "loss": 0.1246, |
| "step": 3380 |
| }, |
| { |
| "epoch": 3.13, |
| "learning_rate": 4.3391866913123846e-05, |
| "loss": 0.172, |
| "step": 3390 |
| }, |
| { |
| "epoch": 3.14, |
| "learning_rate": 4.2929759704251386e-05, |
| "loss": 0.2204, |
| "step": 3400 |
| }, |
| { |
| "epoch": 3.14, |
| "eval_accuracy": 0.8651973347001538, |
| "eval_f1": 0.8651973347001538, |
| "eval_loss": 0.3567483425140381, |
| "eval_precision": 0.8651973347001538, |
| "eval_recall": 0.8651973347001538, |
| "eval_runtime": 83.4884, |
| "eval_samples_per_second": 93.474, |
| "eval_steps_per_second": 11.69, |
| "step": 3400 |
| }, |
| { |
| "epoch": 3.15, |
| "learning_rate": 4.246765249537893e-05, |
| "loss": 0.1677, |
| "step": 3410 |
| }, |
| { |
| "epoch": 3.16, |
| "learning_rate": 4.200554528650647e-05, |
| "loss": 0.1818, |
| "step": 3420 |
| }, |
| { |
| "epoch": 3.17, |
| "learning_rate": 4.154343807763401e-05, |
| "loss": 0.2236, |
| "step": 3430 |
| }, |
| { |
| "epoch": 3.18, |
| "learning_rate": 4.1081330868761556e-05, |
| "loss": 0.1512, |
| "step": 3440 |
| }, |
| { |
| "epoch": 3.19, |
| "learning_rate": 4.06192236598891e-05, |
| "loss": 0.164, |
| "step": 3450 |
| }, |
| { |
| "epoch": 3.2, |
| "learning_rate": 4.015711645101664e-05, |
| "loss": 0.1624, |
| "step": 3460 |
| }, |
| { |
| "epoch": 3.21, |
| "learning_rate": 3.969500924214418e-05, |
| "loss": 0.2389, |
| "step": 3470 |
| }, |
| { |
| "epoch": 3.22, |
| "learning_rate": 3.9232902033271726e-05, |
| "loss": 0.1191, |
| "step": 3480 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 3.8770794824399266e-05, |
| "loss": 0.2061, |
| "step": 3490 |
| }, |
| { |
| "epoch": 3.23, |
| "learning_rate": 3.830868761552681e-05, |
| "loss": 0.2149, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.23, |
| "eval_accuracy": 0.8705791901588928, |
| "eval_f1": 0.870579190158893, |
| "eval_loss": 0.31783682107925415, |
| "eval_precision": 0.8705791901588928, |
| "eval_recall": 0.8705791901588928, |
| "eval_runtime": 83.1514, |
| "eval_samples_per_second": 93.853, |
| "eval_steps_per_second": 11.738, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.24, |
| "learning_rate": 3.784658040665435e-05, |
| "loss": 0.2526, |
| "step": 3510 |
| }, |
| { |
| "epoch": 3.25, |
| "learning_rate": 3.738447319778189e-05, |
| "loss": 0.2039, |
| "step": 3520 |
| }, |
| { |
| "epoch": 3.26, |
| "learning_rate": 3.692236598890943e-05, |
| "loss": 0.2152, |
| "step": 3530 |
| }, |
| { |
| "epoch": 3.27, |
| "learning_rate": 3.646025878003697e-05, |
| "loss": 0.1966, |
| "step": 3540 |
| }, |
| { |
| "epoch": 3.28, |
| "learning_rate": 3.599815157116451e-05, |
| "loss": 0.2337, |
| "step": 3550 |
| }, |
| { |
| "epoch": 3.29, |
| "learning_rate": 3.553604436229205e-05, |
| "loss": 0.1461, |
| "step": 3560 |
| }, |
| { |
| "epoch": 3.3, |
| "learning_rate": 3.507393715341959e-05, |
| "loss": 0.1895, |
| "step": 3570 |
| }, |
| { |
| "epoch": 3.31, |
| "learning_rate": 3.461182994454713e-05, |
| "loss": 0.2539, |
| "step": 3580 |
| }, |
| { |
| "epoch": 3.32, |
| "learning_rate": 3.414972273567468e-05, |
| "loss": 0.1795, |
| "step": 3590 |
| }, |
| { |
| "epoch": 3.33, |
| "learning_rate": 3.368761552680222e-05, |
| "loss": 0.1389, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.33, |
| "eval_accuracy": 0.8705791901588928, |
| "eval_f1": 0.870579190158893, |
| "eval_loss": 0.31231769919395447, |
| "eval_precision": 0.8705791901588928, |
| "eval_recall": 0.8705791901588928, |
| "eval_runtime": 82.8775, |
| "eval_samples_per_second": 94.163, |
| "eval_steps_per_second": 11.776, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.34, |
| "learning_rate": 3.322550831792976e-05, |
| "loss": 0.1735, |
| "step": 3610 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 3.27634011090573e-05, |
| "loss": 0.2483, |
| "step": 3620 |
| }, |
| { |
| "epoch": 3.35, |
| "learning_rate": 3.2301293900184843e-05, |
| "loss": 0.1655, |
| "step": 3630 |
| }, |
| { |
| "epoch": 3.36, |
| "learning_rate": 3.1839186691312384e-05, |
| "loss": 0.1921, |
| "step": 3640 |
| }, |
| { |
| "epoch": 3.37, |
| "learning_rate": 3.1377079482439925e-05, |
| "loss": 0.213, |
| "step": 3650 |
| }, |
| { |
| "epoch": 3.38, |
| "learning_rate": 3.091497227356747e-05, |
| "loss": 0.1803, |
| "step": 3660 |
| }, |
| { |
| "epoch": 3.39, |
| "learning_rate": 3.0452865064695013e-05, |
| "loss": 0.2075, |
| "step": 3670 |
| }, |
| { |
| "epoch": 3.4, |
| "learning_rate": 2.9990757855822554e-05, |
| "loss": 0.1324, |
| "step": 3680 |
| }, |
| { |
| "epoch": 3.41, |
| "learning_rate": 2.9528650646950095e-05, |
| "loss": 0.1569, |
| "step": 3690 |
| }, |
| { |
| "epoch": 3.42, |
| "learning_rate": 2.9066543438077635e-05, |
| "loss": 0.1567, |
| "step": 3700 |
| }, |
| { |
| "epoch": 3.42, |
| "eval_accuracy": 0.8668631471040492, |
| "eval_f1": 0.8668631471040492, |
| "eval_loss": 0.3373697102069855, |
| "eval_precision": 0.8668631471040492, |
| "eval_recall": 0.8668631471040492, |
| "eval_runtime": 82.8609, |
| "eval_samples_per_second": 94.182, |
| "eval_steps_per_second": 11.779, |
| "step": 3700 |
| }, |
| { |
| "epoch": 3.43, |
| "learning_rate": 2.860443622920518e-05, |
| "loss": 0.1987, |
| "step": 3710 |
| }, |
| { |
| "epoch": 3.44, |
| "learning_rate": 2.814232902033272e-05, |
| "loss": 0.2211, |
| "step": 3720 |
| }, |
| { |
| "epoch": 3.45, |
| "learning_rate": 2.768022181146026e-05, |
| "loss": 0.16, |
| "step": 3730 |
| }, |
| { |
| "epoch": 3.46, |
| "learning_rate": 2.72181146025878e-05, |
| "loss": 0.1842, |
| "step": 3740 |
| }, |
| { |
| "epoch": 3.47, |
| "learning_rate": 2.6756007393715342e-05, |
| "loss": 0.123, |
| "step": 3750 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 2.6293900184842883e-05, |
| "loss": 0.1428, |
| "step": 3760 |
| }, |
| { |
| "epoch": 3.48, |
| "learning_rate": 2.5831792975970427e-05, |
| "loss": 0.2821, |
| "step": 3770 |
| }, |
| { |
| "epoch": 3.49, |
| "learning_rate": 2.5369685767097968e-05, |
| "loss": 0.179, |
| "step": 3780 |
| }, |
| { |
| "epoch": 3.5, |
| "learning_rate": 2.490757855822551e-05, |
| "loss": 0.1674, |
| "step": 3790 |
| }, |
| { |
| "epoch": 3.51, |
| "learning_rate": 2.4445471349353053e-05, |
| "loss": 0.1871, |
| "step": 3800 |
| }, |
| { |
| "epoch": 3.51, |
| "eval_accuracy": 0.8700666324961558, |
| "eval_f1": 0.8700666324961558, |
| "eval_loss": 0.34498330950737, |
| "eval_precision": 0.8700666324961558, |
| "eval_recall": 0.8700666324961558, |
| "eval_runtime": 83.543, |
| "eval_samples_per_second": 93.413, |
| "eval_steps_per_second": 11.683, |
| "step": 3800 |
| }, |
| { |
| "epoch": 3.52, |
| "learning_rate": 2.3983364140480594e-05, |
| "loss": 0.1245, |
| "step": 3810 |
| }, |
| { |
| "epoch": 3.53, |
| "learning_rate": 2.3521256931608134e-05, |
| "loss": 0.1481, |
| "step": 3820 |
| }, |
| { |
| "epoch": 3.54, |
| "learning_rate": 2.3059149722735675e-05, |
| "loss": 0.1474, |
| "step": 3830 |
| }, |
| { |
| "epoch": 3.55, |
| "learning_rate": 2.259704251386322e-05, |
| "loss": 0.1258, |
| "step": 3840 |
| }, |
| { |
| "epoch": 3.56, |
| "learning_rate": 2.213493530499076e-05, |
| "loss": 0.2297, |
| "step": 3850 |
| }, |
| { |
| "epoch": 3.57, |
| "learning_rate": 2.16728280961183e-05, |
| "loss": 0.153, |
| "step": 3860 |
| }, |
| { |
| "epoch": 3.58, |
| "learning_rate": 2.121072088724584e-05, |
| "loss": 0.1238, |
| "step": 3870 |
| }, |
| { |
| "epoch": 3.59, |
| "learning_rate": 2.0748613678373382e-05, |
| "loss": 0.1478, |
| "step": 3880 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 2.0286506469500923e-05, |
| "loss": 0.0582, |
| "step": 3890 |
| }, |
| { |
| "epoch": 3.6, |
| "learning_rate": 1.9824399260628467e-05, |
| "loss": 0.1616, |
| "step": 3900 |
| }, |
| { |
| "epoch": 3.6, |
| "eval_accuracy": 0.8608405945668888, |
| "eval_f1": 0.8608405945668888, |
| "eval_loss": 0.3869592547416687, |
| "eval_precision": 0.8608405945668888, |
| "eval_recall": 0.8608405945668888, |
| "eval_runtime": 83.1131, |
| "eval_samples_per_second": 93.896, |
| "eval_steps_per_second": 11.743, |
| "step": 3900 |
| }, |
| { |
| "epoch": 3.61, |
| "learning_rate": 1.9362292051756008e-05, |
| "loss": 0.2838, |
| "step": 3910 |
| }, |
| { |
| "epoch": 3.62, |
| "learning_rate": 1.890018484288355e-05, |
| "loss": 0.1526, |
| "step": 3920 |
| }, |
| { |
| "epoch": 3.63, |
| "learning_rate": 1.8438077634011092e-05, |
| "loss": 0.2089, |
| "step": 3930 |
| }, |
| { |
| "epoch": 3.64, |
| "learning_rate": 1.7975970425138633e-05, |
| "loss": 0.1879, |
| "step": 3940 |
| }, |
| { |
| "epoch": 3.65, |
| "learning_rate": 1.7513863216266174e-05, |
| "loss": 0.0983, |
| "step": 3950 |
| }, |
| { |
| "epoch": 3.66, |
| "learning_rate": 1.7051756007393715e-05, |
| "loss": 0.1382, |
| "step": 3960 |
| }, |
| { |
| "epoch": 3.67, |
| "learning_rate": 1.6589648798521255e-05, |
| "loss": 0.1314, |
| "step": 3970 |
| }, |
| { |
| "epoch": 3.68, |
| "learning_rate": 1.61275415896488e-05, |
| "loss": 0.1829, |
| "step": 3980 |
| }, |
| { |
| "epoch": 3.69, |
| "learning_rate": 1.5665434380776344e-05, |
| "loss": 0.219, |
| "step": 3990 |
| }, |
| { |
| "epoch": 3.7, |
| "learning_rate": 1.5203327171903883e-05, |
| "loss": 0.1582, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.7, |
| "eval_accuracy": 0.8655817529472065, |
| "eval_f1": 0.8655817529472065, |
| "eval_loss": 0.3489628732204437, |
| "eval_precision": 0.8655817529472065, |
| "eval_recall": 0.8655817529472065, |
| "eval_runtime": 83.2496, |
| "eval_samples_per_second": 93.742, |
| "eval_steps_per_second": 11.724, |
| "step": 4000 |
| }, |
| { |
| "epoch": 3.71, |
| "learning_rate": 1.4741219963031425e-05, |
| "loss": 0.1748, |
| "step": 4010 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 1.4279112754158966e-05, |
| "loss": 0.1501, |
| "step": 4020 |
| }, |
| { |
| "epoch": 3.72, |
| "learning_rate": 1.3817005545286506e-05, |
| "loss": 0.1524, |
| "step": 4030 |
| }, |
| { |
| "epoch": 3.73, |
| "learning_rate": 1.3354898336414049e-05, |
| "loss": 0.1592, |
| "step": 4040 |
| }, |
| { |
| "epoch": 3.74, |
| "learning_rate": 1.289279112754159e-05, |
| "loss": 0.1496, |
| "step": 4050 |
| }, |
| { |
| "epoch": 3.75, |
| "learning_rate": 1.2430683918669132e-05, |
| "loss": 0.1155, |
| "step": 4060 |
| }, |
| { |
| "epoch": 3.76, |
| "learning_rate": 1.1968576709796673e-05, |
| "loss": 0.202, |
| "step": 4070 |
| }, |
| { |
| "epoch": 3.77, |
| "learning_rate": 1.1506469500924215e-05, |
| "loss": 0.242, |
| "step": 4080 |
| }, |
| { |
| "epoch": 3.78, |
| "learning_rate": 1.1044362292051756e-05, |
| "loss": 0.1616, |
| "step": 4090 |
| }, |
| { |
| "epoch": 3.79, |
| "learning_rate": 1.0582255083179297e-05, |
| "loss": 0.1199, |
| "step": 4100 |
| }, |
| { |
| "epoch": 3.79, |
| "eval_accuracy": 0.8684008200922604, |
| "eval_f1": 0.8684008200922604, |
| "eval_loss": 0.34080585837364197, |
| "eval_precision": 0.8684008200922604, |
| "eval_recall": 0.8684008200922604, |
| "eval_runtime": 82.9018, |
| "eval_samples_per_second": 94.135, |
| "eval_steps_per_second": 11.773, |
| "step": 4100 |
| }, |
| { |
| "epoch": 3.8, |
| "learning_rate": 1.012014787430684e-05, |
| "loss": 0.1014, |
| "step": 4110 |
| }, |
| { |
| "epoch": 3.81, |
| "learning_rate": 9.658040665434381e-06, |
| "loss": 0.1887, |
| "step": 4120 |
| }, |
| { |
| "epoch": 3.82, |
| "learning_rate": 9.195933456561922e-06, |
| "loss": 0.1606, |
| "step": 4130 |
| }, |
| { |
| "epoch": 3.83, |
| "learning_rate": 8.733826247689465e-06, |
| "loss": 0.1815, |
| "step": 4140 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 8.271719038817007e-06, |
| "loss": 0.0654, |
| "step": 4150 |
| }, |
| { |
| "epoch": 3.84, |
| "learning_rate": 7.809611829944548e-06, |
| "loss": 0.0818, |
| "step": 4160 |
| }, |
| { |
| "epoch": 3.85, |
| "learning_rate": 7.393715341959336e-06, |
| "loss": 0.2116, |
| "step": 4170 |
| }, |
| { |
| "epoch": 3.86, |
| "learning_rate": 6.931608133086876e-06, |
| "loss": 0.1685, |
| "step": 4180 |
| }, |
| { |
| "epoch": 3.87, |
| "learning_rate": 6.469500924214418e-06, |
| "loss": 0.2356, |
| "step": 4190 |
| }, |
| { |
| "epoch": 3.88, |
| "learning_rate": 6.0073937153419595e-06, |
| "loss": 0.1563, |
| "step": 4200 |
| }, |
| { |
| "epoch": 3.88, |
| "eval_accuracy": 0.8668631471040492, |
| "eval_f1": 0.8668631471040492, |
| "eval_loss": 0.34982988238334656, |
| "eval_precision": 0.8668631471040492, |
| "eval_recall": 0.8668631471040492, |
| "eval_runtime": 82.8915, |
| "eval_samples_per_second": 94.147, |
| "eval_steps_per_second": 11.774, |
| "step": 4200 |
| }, |
| { |
| "epoch": 3.89, |
| "learning_rate": 5.545286506469501e-06, |
| "loss": 0.1676, |
| "step": 4210 |
| }, |
| { |
| "epoch": 3.9, |
| "learning_rate": 5.083179297597043e-06, |
| "loss": 0.2368, |
| "step": 4220 |
| }, |
| { |
| "epoch": 3.91, |
| "learning_rate": 4.621072088724584e-06, |
| "loss": 0.1144, |
| "step": 4230 |
| }, |
| { |
| "epoch": 3.92, |
| "learning_rate": 4.158964879852126e-06, |
| "loss": 0.1205, |
| "step": 4240 |
| }, |
| { |
| "epoch": 3.93, |
| "learning_rate": 3.696857670979668e-06, |
| "loss": 0.1361, |
| "step": 4250 |
| }, |
| { |
| "epoch": 3.94, |
| "learning_rate": 3.234750462107209e-06, |
| "loss": 0.1127, |
| "step": 4260 |
| }, |
| { |
| "epoch": 3.95, |
| "learning_rate": 2.7726432532347505e-06, |
| "loss": 0.1775, |
| "step": 4270 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 2.310536044362292e-06, |
| "loss": 0.1007, |
| "step": 4280 |
| }, |
| { |
| "epoch": 3.96, |
| "learning_rate": 1.848428835489834e-06, |
| "loss": 0.1032, |
| "step": 4290 |
| }, |
| { |
| "epoch": 3.97, |
| "learning_rate": 1.3863216266173753e-06, |
| "loss": 0.1544, |
| "step": 4300 |
| }, |
| { |
| "epoch": 3.97, |
| "eval_accuracy": 0.8708354689902614, |
| "eval_f1": 0.8708354689902614, |
| "eval_loss": 0.3397839665412903, |
| "eval_precision": 0.8708354689902614, |
| "eval_recall": 0.8708354689902614, |
| "eval_runtime": 82.9372, |
| "eval_samples_per_second": 94.095, |
| "eval_steps_per_second": 11.768, |
| "step": 4300 |
| }, |
| { |
| "epoch": 3.98, |
| "learning_rate": 9.24214417744917e-07, |
| "loss": 0.1174, |
| "step": 4310 |
| }, |
| { |
| "epoch": 3.99, |
| "learning_rate": 4.621072088724585e-07, |
| "loss": 0.1329, |
| "step": 4320 |
| }, |
| { |
| "epoch": 4.0, |
| "step": 4328, |
| "total_flos": 1.8960628193506492e+19, |
| "train_loss": 0.2956196453952525, |
| "train_runtime": 6421.7635, |
| "train_samples_per_second": 10.778, |
| "train_steps_per_second": 0.674 |
| } |
| ], |
| "max_steps": 4328, |
| "num_train_epochs": 4, |
| "total_flos": 1.8960628193506492e+19, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
