| { | |
| "best_metric": 0.9049823782519661, | |
| "best_model_checkpoint": "./results/checkpoint-3145", | |
| "epoch": 8.998569384835479, | |
| "eval_steps": 500, | |
| "global_step": 3145, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02861230329041488, | |
| "grad_norm": 6.876509666442871, | |
| "learning_rate": 5.730659025787966e-07, | |
| "loss": 2.4197, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05722460658082976, | |
| "grad_norm": 7.476705074310303, | |
| "learning_rate": 1.1461318051575932e-06, | |
| "loss": 2.4492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08583690987124463, | |
| "grad_norm": 7.696058750152588, | |
| "learning_rate": 1.7191977077363897e-06, | |
| "loss": 2.4148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.11444921316165951, | |
| "grad_norm": 7.015161514282227, | |
| "learning_rate": 2.2922636103151864e-06, | |
| "loss": 2.3494, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1430615164520744, | |
| "grad_norm": 12.62998104095459, | |
| "learning_rate": 2.865329512893983e-06, | |
| "loss": 2.2623, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.17167381974248927, | |
| "grad_norm": 14.117810249328613, | |
| "learning_rate": 3.3810888252149e-06, | |
| "loss": 2.098, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.20028612303290416, | |
| "grad_norm": 9.416646957397461, | |
| "learning_rate": 3.954154727793696e-06, | |
| "loss": 1.9519, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22889842632331903, | |
| "grad_norm": 8.700328826904297, | |
| "learning_rate": 4.527220630372493e-06, | |
| "loss": 1.7806, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2575107296137339, | |
| "grad_norm": 10.860468864440918, | |
| "learning_rate": 5.10028653295129e-06, | |
| "loss": 1.8199, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.2861230329041488, | |
| "grad_norm": 9.035737037658691, | |
| "learning_rate": 5.673352435530086e-06, | |
| "loss": 1.7734, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3147353361945637, | |
| "grad_norm": 8.161845207214355, | |
| "learning_rate": 6.246418338108883e-06, | |
| "loss": 1.7332, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.34334763948497854, | |
| "grad_norm": 9.786896705627441, | |
| "learning_rate": 6.819484240687679e-06, | |
| "loss": 1.6379, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.3719599427753934, | |
| "grad_norm": 8.398969650268555, | |
| "learning_rate": 7.392550143266476e-06, | |
| "loss": 1.5716, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4005722460658083, | |
| "grad_norm": 10.114533424377441, | |
| "learning_rate": 7.965616045845273e-06, | |
| "loss": 1.6692, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.4291845493562232, | |
| "grad_norm": 9.715279579162598, | |
| "learning_rate": 8.53868194842407e-06, | |
| "loss": 1.562, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.45779685264663805, | |
| "grad_norm": 9.378506660461426, | |
| "learning_rate": 9.111747851002865e-06, | |
| "loss": 1.495, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.4864091559370529, | |
| "grad_norm": 10.23122787475586, | |
| "learning_rate": 9.684813753581662e-06, | |
| "loss": 1.5594, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.5150214592274678, | |
| "grad_norm": 9.27610969543457, | |
| "learning_rate": 1.0257879656160459e-05, | |
| "loss": 1.3837, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.5436337625178826, | |
| "grad_norm": 7.880237579345703, | |
| "learning_rate": 1.0830945558739256e-05, | |
| "loss": 1.5223, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.5722460658082976, | |
| "grad_norm": 9.665934562683105, | |
| "learning_rate": 1.1404011461318051e-05, | |
| "loss": 1.5726, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6008583690987125, | |
| "grad_norm": 10.41831111907959, | |
| "learning_rate": 1.197707736389685e-05, | |
| "loss": 1.3886, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.6294706723891274, | |
| "grad_norm": 10.866052627563477, | |
| "learning_rate": 1.2550143266475645e-05, | |
| "loss": 1.2832, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.6580829756795422, | |
| "grad_norm": 8.700434684753418, | |
| "learning_rate": 1.3123209169054444e-05, | |
| "loss": 1.3478, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.6866952789699571, | |
| "grad_norm": 9.831547737121582, | |
| "learning_rate": 1.3696275071633239e-05, | |
| "loss": 1.3709, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.7153075822603719, | |
| "grad_norm": 8.401679992675781, | |
| "learning_rate": 1.4269340974212036e-05, | |
| "loss": 1.1379, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.7439198855507868, | |
| "grad_norm": 8.623452186584473, | |
| "learning_rate": 1.4842406876790831e-05, | |
| "loss": 1.1539, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.7725321888412017, | |
| "grad_norm": 8.327902793884277, | |
| "learning_rate": 1.541547277936963e-05, | |
| "loss": 1.2316, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.8011444921316166, | |
| "grad_norm": 7.682071208953857, | |
| "learning_rate": 1.5988538681948423e-05, | |
| "loss": 1.0331, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.8297567954220315, | |
| "grad_norm": 11.49991512298584, | |
| "learning_rate": 1.6561604584527223e-05, | |
| "loss": 1.0284, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.8583690987124464, | |
| "grad_norm": 12.24896240234375, | |
| "learning_rate": 1.7134670487106017e-05, | |
| "loss": 0.9963, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.8869814020028612, | |
| "grad_norm": 11.292716979980469, | |
| "learning_rate": 1.7707736389684814e-05, | |
| "loss": 1.0393, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.9155937052932761, | |
| "grad_norm": 12.811381340026855, | |
| "learning_rate": 1.828080229226361e-05, | |
| "loss": 0.9775, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.944206008583691, | |
| "grad_norm": 10.303635597229004, | |
| "learning_rate": 1.8853868194842408e-05, | |
| "loss": 0.9981, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.9728183118741058, | |
| "grad_norm": 8.658745765686035, | |
| "learning_rate": 1.9426934097421205e-05, | |
| "loss": 0.8987, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.9985693848354793, | |
| "eval_avg_f1": 0.628490484052183, | |
| "eval_avg_macro_f1": 0.42788465867275915, | |
| "eval_hazard_accuracy": 0.825589706933524, | |
| "eval_hazard_f1": 0.8033759184058155, | |
| "eval_hazard_macro_f1": 0.5331731123201242, | |
| "eval_hazard_precision": 0.8219654012602551, | |
| "eval_hazard_recall": 0.825589706933524, | |
| "eval_loss": 0.8228468298912048, | |
| "eval_product_accuracy": 0.5160829163688349, | |
| "eval_product_f1": 0.4536050496985506, | |
| "eval_product_macro_f1": 0.3225962050253941, | |
| "eval_product_precision": 0.5171642919697715, | |
| "eval_product_recall": 0.5160829163688349, | |
| "eval_runtime": 129.8116, | |
| "eval_samples_per_second": 10.777, | |
| "eval_steps_per_second": 5.392, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 1.0014306151645207, | |
| "grad_norm": 18.984487533569336, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8162, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.0300429184549356, | |
| "grad_norm": 11.077680587768555, | |
| "learning_rate": 1.993632601082458e-05, | |
| "loss": 0.8289, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.0586552217453504, | |
| "grad_norm": 8.779168128967285, | |
| "learning_rate": 1.9872652021649158e-05, | |
| "loss": 0.7518, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.0872675250357653, | |
| "grad_norm": 11.665291786193848, | |
| "learning_rate": 1.9808978032473735e-05, | |
| "loss": 0.8352, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.1158798283261802, | |
| "grad_norm": 10.888090133666992, | |
| "learning_rate": 1.9745304043298315e-05, | |
| "loss": 0.7818, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.144492131616595, | |
| "grad_norm": 7.827507495880127, | |
| "learning_rate": 1.9681630054122895e-05, | |
| "loss": 0.7133, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.17310443490701, | |
| "grad_norm": 9.694169044494629, | |
| "learning_rate": 1.961795606494747e-05, | |
| "loss": 0.7354, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.201716738197425, | |
| "grad_norm": 9.30434513092041, | |
| "learning_rate": 1.9554282075772048e-05, | |
| "loss": 0.7404, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.2303290414878398, | |
| "grad_norm": 9.60873031616211, | |
| "learning_rate": 1.9490608086596628e-05, | |
| "loss": 0.6384, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.2589413447782547, | |
| "grad_norm": 8.565361022949219, | |
| "learning_rate": 1.9426934097421205e-05, | |
| "loss": 0.5877, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.2875536480686696, | |
| "grad_norm": 6.860024452209473, | |
| "learning_rate": 1.936326010824578e-05, | |
| "loss": 0.5608, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.3161659513590844, | |
| "grad_norm": 10.23735523223877, | |
| "learning_rate": 1.929958611907036e-05, | |
| "loss": 0.5611, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.3447782546494993, | |
| "grad_norm": 9.30553913116455, | |
| "learning_rate": 1.923591212989494e-05, | |
| "loss": 0.6389, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.3733905579399142, | |
| "grad_norm": 10.408185005187988, | |
| "learning_rate": 1.9172238140719518e-05, | |
| "loss": 0.5982, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.402002861230329, | |
| "grad_norm": 7.272457122802734, | |
| "learning_rate": 1.9114931550461637e-05, | |
| "loss": 0.6152, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.4306151645207439, | |
| "grad_norm": 14.093036651611328, | |
| "learning_rate": 1.9051257561286217e-05, | |
| "loss": 0.5622, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.4592274678111588, | |
| "grad_norm": 9.175661087036133, | |
| "learning_rate": 1.8987583572110794e-05, | |
| "loss": 0.5649, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.4878397711015736, | |
| "grad_norm": 9.00843620300293, | |
| "learning_rate": 1.892390958293537e-05, | |
| "loss": 0.497, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.5164520743919887, | |
| "grad_norm": 12.909320831298828, | |
| "learning_rate": 1.886023559375995e-05, | |
| "loss": 0.5668, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.5450643776824036, | |
| "grad_norm": 8.075855255126953, | |
| "learning_rate": 1.879656160458453e-05, | |
| "loss": 0.4738, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.5736766809728184, | |
| "grad_norm": 8.01660442352295, | |
| "learning_rate": 1.8732887615409107e-05, | |
| "loss": 0.5215, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.6022889842632333, | |
| "grad_norm": 8.67613697052002, | |
| "learning_rate": 1.8669213626233684e-05, | |
| "loss": 0.402, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.6309012875536482, | |
| "grad_norm": 12.167224884033203, | |
| "learning_rate": 1.8605539637058264e-05, | |
| "loss": 0.5239, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.659513590844063, | |
| "grad_norm": 8.326301574707031, | |
| "learning_rate": 1.854186564788284e-05, | |
| "loss": 0.4593, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.688125894134478, | |
| "grad_norm": 8.792169570922852, | |
| "learning_rate": 1.847819165870742e-05, | |
| "loss": 0.4246, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.7167381974248928, | |
| "grad_norm": 5.764039993286133, | |
| "learning_rate": 1.8414517669531997e-05, | |
| "loss": 0.4653, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.7453505007153076, | |
| "grad_norm": 9.632957458496094, | |
| "learning_rate": 1.8350843680356577e-05, | |
| "loss": 0.4983, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.7739628040057225, | |
| "grad_norm": 5.234284400939941, | |
| "learning_rate": 1.8287169691181154e-05, | |
| "loss": 0.437, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.8025751072961373, | |
| "grad_norm": 9.065439224243164, | |
| "learning_rate": 1.822349570200573e-05, | |
| "loss": 0.4994, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.8311874105865522, | |
| "grad_norm": 8.478631019592285, | |
| "learning_rate": 1.815982171283031e-05, | |
| "loss": 0.4488, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.859799713876967, | |
| "grad_norm": 9.906896591186523, | |
| "learning_rate": 1.809614772365489e-05, | |
| "loss": 0.4591, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.888412017167382, | |
| "grad_norm": 8.688902854919434, | |
| "learning_rate": 1.8032473734479467e-05, | |
| "loss": 0.3987, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.9170243204577968, | |
| "grad_norm": 8.751792907714844, | |
| "learning_rate": 1.7968799745304043e-05, | |
| "loss": 0.3636, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.9456366237482117, | |
| "grad_norm": 8.234392166137695, | |
| "learning_rate": 1.7905125756128623e-05, | |
| "loss": 0.38, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.9742489270386265, | |
| "grad_norm": 11.33198070526123, | |
| "learning_rate": 1.7841451766953203e-05, | |
| "loss": 0.4105, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_avg_f1": 0.8280098465171617, | |
| "eval_avg_macro_f1": 0.74927766614807, | |
| "eval_hazard_accuracy": 0.8956397426733381, | |
| "eval_hazard_f1": 0.8909842147196562, | |
| "eval_hazard_macro_f1": 0.7504887189330472, | |
| "eval_hazard_precision": 0.8943267421662421, | |
| "eval_hazard_recall": 0.8956397426733381, | |
| "eval_loss": 0.4124191701412201, | |
| "eval_product_accuracy": 0.7684060042887777, | |
| "eval_product_f1": 0.7650354783146672, | |
| "eval_product_macro_f1": 0.7480666133630927, | |
| "eval_product_precision": 0.7938898073346229, | |
| "eval_product_recall": 0.7684060042887777, | |
| "eval_runtime": 129.9333, | |
| "eval_samples_per_second": 10.767, | |
| "eval_steps_per_second": 5.387, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 2.0028612303290414, | |
| "grad_norm": 8.635429382324219, | |
| "learning_rate": 1.7777777777777777e-05, | |
| "loss": 0.4702, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.0314735336194563, | |
| "grad_norm": 8.250715255737305, | |
| "learning_rate": 1.7714103788602357e-05, | |
| "loss": 0.3381, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 2.060085836909871, | |
| "grad_norm": 9.375146865844727, | |
| "learning_rate": 1.7650429799426937e-05, | |
| "loss": 0.25, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 2.088698140200286, | |
| "grad_norm": 8.349605560302734, | |
| "learning_rate": 1.7586755810251513e-05, | |
| "loss": 0.2904, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 2.117310443490701, | |
| "grad_norm": 5.922322750091553, | |
| "learning_rate": 1.752308182107609e-05, | |
| "loss": 0.2953, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 2.1459227467811157, | |
| "grad_norm": 9.073394775390625, | |
| "learning_rate": 1.745940783190067e-05, | |
| "loss": 0.4012, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 2.1745350500715306, | |
| "grad_norm": 5.899810791015625, | |
| "learning_rate": 1.739573384272525e-05, | |
| "loss": 0.2627, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 2.2031473533619454, | |
| "grad_norm": 8.413034439086914, | |
| "learning_rate": 1.7332059853549826e-05, | |
| "loss": 0.2664, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 2.2317596566523603, | |
| "grad_norm": 5.280710697174072, | |
| "learning_rate": 1.7268385864374403e-05, | |
| "loss": 0.2687, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 2.260371959942775, | |
| "grad_norm": 4.636008262634277, | |
| "learning_rate": 1.7204711875198983e-05, | |
| "loss": 0.3354, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 2.28898426323319, | |
| "grad_norm": 7.188244819641113, | |
| "learning_rate": 1.7141037886023563e-05, | |
| "loss": 0.3449, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.317596566523605, | |
| "grad_norm": 8.121512413024902, | |
| "learning_rate": 1.707736389684814e-05, | |
| "loss": 0.3, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 2.34620886981402, | |
| "grad_norm": 8.199843406677246, | |
| "learning_rate": 1.7013689907672716e-05, | |
| "loss": 0.2975, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 2.374821173104435, | |
| "grad_norm": 4.355212211608887, | |
| "learning_rate": 1.6950015918497296e-05, | |
| "loss": 0.3658, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 2.40343347639485, | |
| "grad_norm": 4.755102634429932, | |
| "learning_rate": 1.6886341929321873e-05, | |
| "loss": 0.2632, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 2.432045779685265, | |
| "grad_norm": 7.069221496582031, | |
| "learning_rate": 1.682266794014645e-05, | |
| "loss": 0.2625, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 2.4606580829756797, | |
| "grad_norm": 5.802147388458252, | |
| "learning_rate": 1.675899395097103e-05, | |
| "loss": 0.2629, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 2.4892703862660945, | |
| "grad_norm": 9.528565406799316, | |
| "learning_rate": 1.669531996179561e-05, | |
| "loss": 0.3839, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 2.5178826895565094, | |
| "grad_norm": 5.615097999572754, | |
| "learning_rate": 1.6631645972620186e-05, | |
| "loss": 0.2388, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 2.5464949928469243, | |
| "grad_norm": 6.9182209968566895, | |
| "learning_rate": 1.6567971983444763e-05, | |
| "loss": 0.2958, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.575107296137339, | |
| "grad_norm": 12.66451644897461, | |
| "learning_rate": 1.6504297994269343e-05, | |
| "loss": 0.2204, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.603719599427754, | |
| "grad_norm": 6.674743175506592, | |
| "learning_rate": 1.6440624005093923e-05, | |
| "loss": 0.2877, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.632331902718169, | |
| "grad_norm": 5.2552289962768555, | |
| "learning_rate": 1.63769500159185e-05, | |
| "loss": 0.2812, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.6609442060085837, | |
| "grad_norm": 7.143093585968018, | |
| "learning_rate": 1.6313276026743076e-05, | |
| "loss": 0.232, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.6895565092989986, | |
| "grad_norm": 6.480932235717773, | |
| "learning_rate": 1.6249602037567656e-05, | |
| "loss": 0.2833, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.7181688125894135, | |
| "grad_norm": 4.548788547515869, | |
| "learning_rate": 1.6185928048392233e-05, | |
| "loss": 0.303, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.7467811158798283, | |
| "grad_norm": 6.597518444061279, | |
| "learning_rate": 1.612225405921681e-05, | |
| "loss": 0.226, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.775393419170243, | |
| "grad_norm": 5.480116844177246, | |
| "learning_rate": 1.605858007004139e-05, | |
| "loss": 0.2969, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.804005722460658, | |
| "grad_norm": 7.167335510253906, | |
| "learning_rate": 1.599490608086597e-05, | |
| "loss": 0.291, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.832618025751073, | |
| "grad_norm": 7.781642436981201, | |
| "learning_rate": 1.5931232091690546e-05, | |
| "loss": 0.3327, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.8612303290414878, | |
| "grad_norm": 6.379146575927734, | |
| "learning_rate": 1.5867558102515122e-05, | |
| "loss": 0.2287, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.8898426323319026, | |
| "grad_norm": 4.854823589324951, | |
| "learning_rate": 1.5803884113339702e-05, | |
| "loss": 0.2949, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.9184549356223175, | |
| "grad_norm": 8.530597686767578, | |
| "learning_rate": 1.574021012416428e-05, | |
| "loss": 0.2513, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.9470672389127324, | |
| "grad_norm": 3.9975430965423584, | |
| "learning_rate": 1.567653613498886e-05, | |
| "loss": 0.241, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.9756795422031472, | |
| "grad_norm": 7.5502495765686035, | |
| "learning_rate": 1.5612862145813436e-05, | |
| "loss": 0.2415, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.9985693848354793, | |
| "eval_avg_f1": 0.8646060311796574, | |
| "eval_avg_macro_f1": 0.8202031937507945, | |
| "eval_hazard_accuracy": 0.9242315939957112, | |
| "eval_hazard_f1": 0.9209214047945541, | |
| "eval_hazard_macro_f1": 0.8335196381848966, | |
| "eval_hazard_precision": 0.922656067429271, | |
| "eval_hazard_recall": 0.9242315939957112, | |
| "eval_loss": 0.31081312894821167, | |
| "eval_product_accuracy": 0.8091493924231594, | |
| "eval_product_f1": 0.8082906575647607, | |
| "eval_product_macro_f1": 0.8068867493166926, | |
| "eval_product_precision": 0.821048045009564, | |
| "eval_product_recall": 0.8091493924231594, | |
| "eval_runtime": 129.7873, | |
| "eval_samples_per_second": 10.779, | |
| "eval_steps_per_second": 5.393, | |
| "step": 1048 | |
| }, | |
| { | |
| "epoch": 3.004291845493562, | |
| "grad_norm": 7.4025726318359375, | |
| "learning_rate": 1.5549188156638016e-05, | |
| "loss": 0.2662, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 3.032904148783977, | |
| "grad_norm": 3.517706871032715, | |
| "learning_rate": 1.5485514167462592e-05, | |
| "loss": 0.1339, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 3.061516452074392, | |
| "grad_norm": 7.23236083984375, | |
| "learning_rate": 1.5421840178287172e-05, | |
| "loss": 0.1601, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 3.0901287553648067, | |
| "grad_norm": 8.8353853225708, | |
| "learning_rate": 1.535816618911175e-05, | |
| "loss": 0.1327, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 3.1187410586552216, | |
| "grad_norm": 7.725401878356934, | |
| "learning_rate": 1.529449219993633e-05, | |
| "loss": 0.1812, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 3.1473533619456364, | |
| "grad_norm": 7.550207138061523, | |
| "learning_rate": 1.5230818210760905e-05, | |
| "loss": 0.1994, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.1759656652360517, | |
| "grad_norm": 9.055293083190918, | |
| "learning_rate": 1.5167144221585484e-05, | |
| "loss": 0.1645, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 3.2045779685264666, | |
| "grad_norm": 3.738288640975952, | |
| "learning_rate": 1.5103470232410062e-05, | |
| "loss": 0.167, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 3.2331902718168815, | |
| "grad_norm": 4.433919906616211, | |
| "learning_rate": 1.5039796243234639e-05, | |
| "loss": 0.2408, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 3.2618025751072963, | |
| "grad_norm": 7.696563243865967, | |
| "learning_rate": 1.4976122254059217e-05, | |
| "loss": 0.1636, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 3.290414878397711, | |
| "grad_norm": 3.678316354751587, | |
| "learning_rate": 1.4912448264883797e-05, | |
| "loss": 0.1288, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 3.319027181688126, | |
| "grad_norm": 5.206940174102783, | |
| "learning_rate": 1.4848774275708375e-05, | |
| "loss": 0.1615, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 3.347639484978541, | |
| "grad_norm": 6.231516361236572, | |
| "learning_rate": 1.4785100286532952e-05, | |
| "loss": 0.203, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 3.376251788268956, | |
| "grad_norm": 6.873571395874023, | |
| "learning_rate": 1.472142629735753e-05, | |
| "loss": 0.145, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 3.4048640915593706, | |
| "grad_norm": 8.790820121765137, | |
| "learning_rate": 1.4657752308182109e-05, | |
| "loss": 0.1287, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 3.4334763948497855, | |
| "grad_norm": 3.0134575366973877, | |
| "learning_rate": 1.4594078319006685e-05, | |
| "loss": 0.1526, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.4620886981402004, | |
| "grad_norm": 3.7933926582336426, | |
| "learning_rate": 1.4530404329831265e-05, | |
| "loss": 0.1477, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 3.4907010014306152, | |
| "grad_norm": 5.385199546813965, | |
| "learning_rate": 1.4466730340655843e-05, | |
| "loss": 0.1924, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 3.51931330472103, | |
| "grad_norm": 4.563629627227783, | |
| "learning_rate": 1.4403056351480422e-05, | |
| "loss": 0.1599, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 3.547925608011445, | |
| "grad_norm": 4.976149559020996, | |
| "learning_rate": 1.4339382362304998e-05, | |
| "loss": 0.1056, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 3.57653791130186, | |
| "grad_norm": 7.8397369384765625, | |
| "learning_rate": 1.4275708373129578e-05, | |
| "loss": 0.1606, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 3.6051502145922747, | |
| "grad_norm": 4.005160808563232, | |
| "learning_rate": 1.4212034383954157e-05, | |
| "loss": 0.1435, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 3.6337625178826896, | |
| "grad_norm": 4.652032375335693, | |
| "learning_rate": 1.4148360394778735e-05, | |
| "loss": 0.1331, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 3.6623748211731044, | |
| "grad_norm": 5.29043436050415, | |
| "learning_rate": 1.4084686405603312e-05, | |
| "loss": 0.2153, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 3.6909871244635193, | |
| "grad_norm": 3.634098529815674, | |
| "learning_rate": 1.402101241642789e-05, | |
| "loss": 0.1544, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 3.719599427753934, | |
| "grad_norm": 8.322735786437988, | |
| "learning_rate": 1.395733842725247e-05, | |
| "loss": 0.1972, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.748211731044349, | |
| "grad_norm": 7.596883773803711, | |
| "learning_rate": 1.3893664438077047e-05, | |
| "loss": 0.0944, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 3.776824034334764, | |
| "grad_norm": 7.210901737213135, | |
| "learning_rate": 1.3829990448901625e-05, | |
| "loss": 0.2145, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 3.8054363376251787, | |
| "grad_norm": 2.7890021800994873, | |
| "learning_rate": 1.3766316459726203e-05, | |
| "loss": 0.1598, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 3.8340486409155936, | |
| "grad_norm": 5.991145133972168, | |
| "learning_rate": 1.3702642470550781e-05, | |
| "loss": 0.1237, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 3.8626609442060085, | |
| "grad_norm": 9.527064323425293, | |
| "learning_rate": 1.3638968481375358e-05, | |
| "loss": 0.2123, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 3.8912732474964233, | |
| "grad_norm": 7.581963062286377, | |
| "learning_rate": 1.3575294492199938e-05, | |
| "loss": 0.1112, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 3.919885550786838, | |
| "grad_norm": 3.083259344100952, | |
| "learning_rate": 1.3511620503024516e-05, | |
| "loss": 0.1645, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 3.948497854077253, | |
| "grad_norm": 5.185080051422119, | |
| "learning_rate": 1.3447946513849093e-05, | |
| "loss": 0.1617, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 3.977110157367668, | |
| "grad_norm": 3.8500514030456543, | |
| "learning_rate": 1.3384272524673671e-05, | |
| "loss": 0.1992, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_avg_f1": 0.8851622412902382, | |
| "eval_avg_macro_f1": 0.8655477884160602, | |
| "eval_hazard_accuracy": 0.9306647605432452, | |
| "eval_hazard_f1": 0.9291664035270353, | |
| "eval_hazard_macro_f1": 0.8679930988825365, | |
| "eval_hazard_precision": 0.9299572534743619, | |
| "eval_hazard_recall": 0.9306647605432452, | |
| "eval_loss": 0.27699437737464905, | |
| "eval_product_accuracy": 0.8391708363116511, | |
| "eval_product_f1": 0.8411580790534411, | |
| "eval_product_macro_f1": 0.8631024779495838, | |
| "eval_product_precision": 0.8488249750983786, | |
| "eval_product_recall": 0.8391708363116511, | |
| "eval_runtime": 130.3572, | |
| "eval_samples_per_second": 10.732, | |
| "eval_steps_per_second": 5.37, | |
| "step": 1398 | |
| }, | |
| { | |
| "epoch": 4.005722460658083, | |
| "grad_norm": 0.853125274181366, | |
| "learning_rate": 1.332059853549825e-05, | |
| "loss": 0.1052, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 4.034334763948498, | |
| "grad_norm": 4.933560371398926, | |
| "learning_rate": 1.325692454632283e-05, | |
| "loss": 0.0654, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 4.0629470672389125, | |
| "grad_norm": 3.6680829524993896, | |
| "learning_rate": 1.3193250557147406e-05, | |
| "loss": 0.1259, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 4.091559370529327, | |
| "grad_norm": 6.895246982574463, | |
| "learning_rate": 1.3129576567971985e-05, | |
| "loss": 0.1075, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 4.120171673819742, | |
| "grad_norm": 1.8694907426834106, | |
| "learning_rate": 1.3065902578796563e-05, | |
| "loss": 0.0468, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 4.148783977110157, | |
| "grad_norm": 3.379357099533081, | |
| "learning_rate": 1.300222858962114e-05, | |
| "loss": 0.1315, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 4.177396280400572, | |
| "grad_norm": 7.892834186553955, | |
| "learning_rate": 1.2938554600445718e-05, | |
| "loss": 0.1094, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 4.206008583690987, | |
| "grad_norm": 1.6634479761123657, | |
| "learning_rate": 1.2874880611270298e-05, | |
| "loss": 0.0958, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 4.234620886981402, | |
| "grad_norm": 3.4273829460144043, | |
| "learning_rate": 1.2811206622094876e-05, | |
| "loss": 0.0919, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 4.263233190271817, | |
| "grad_norm": 3.1847472190856934, | |
| "learning_rate": 1.2747532632919453e-05, | |
| "loss": 0.119, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 4.291845493562231, | |
| "grad_norm": 6.2553815841674805, | |
| "learning_rate": 1.2683858643744031e-05, | |
| "loss": 0.0607, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.320457796852646, | |
| "grad_norm": 4.419532775878906, | |
| "learning_rate": 1.2620184654568611e-05, | |
| "loss": 0.0674, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 4.349070100143061, | |
| "grad_norm": 0.7810031771659851, | |
| "learning_rate": 1.255651066539319e-05, | |
| "loss": 0.0714, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 4.377682403433476, | |
| "grad_norm": 5.215312480926514, | |
| "learning_rate": 1.2492836676217766e-05, | |
| "loss": 0.1047, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 4.406294706723891, | |
| "grad_norm": 3.8974525928497314, | |
| "learning_rate": 1.2429162687042344e-05, | |
| "loss": 0.1382, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 4.434907010014306, | |
| "grad_norm": 2.479971408843994, | |
| "learning_rate": 1.2365488697866923e-05, | |
| "loss": 0.1178, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 4.463519313304721, | |
| "grad_norm": 6.309189319610596, | |
| "learning_rate": 1.23018147086915e-05, | |
| "loss": 0.1058, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 4.492131616595136, | |
| "grad_norm": 5.032012462615967, | |
| "learning_rate": 1.223814071951608e-05, | |
| "loss": 0.1014, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 4.52074391988555, | |
| "grad_norm": 3.660862684249878, | |
| "learning_rate": 1.2174466730340657e-05, | |
| "loss": 0.1059, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 4.549356223175966, | |
| "grad_norm": 4.471796035766602, | |
| "learning_rate": 1.2110792741165236e-05, | |
| "loss": 0.1342, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 4.57796852646638, | |
| "grad_norm": 1.652951717376709, | |
| "learning_rate": 1.2047118751989812e-05, | |
| "loss": 0.0819, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.606580829756796, | |
| "grad_norm": 10.334088325500488, | |
| "learning_rate": 1.198344476281439e-05, | |
| "loss": 0.126, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 4.63519313304721, | |
| "grad_norm": 2.5108392238616943, | |
| "learning_rate": 1.191977077363897e-05, | |
| "loss": 0.06, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 4.663805436337626, | |
| "grad_norm": 1.85515558719635, | |
| "learning_rate": 1.1856096784463547e-05, | |
| "loss": 0.1013, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 4.69241773962804, | |
| "grad_norm": 3.7234935760498047, | |
| "learning_rate": 1.1792422795288126e-05, | |
| "loss": 0.118, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 4.721030042918455, | |
| "grad_norm": 1.4880505800247192, | |
| "learning_rate": 1.1728748806112704e-05, | |
| "loss": 0.1033, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 4.74964234620887, | |
| "grad_norm": 0.767953097820282, | |
| "learning_rate": 1.1665074816937282e-05, | |
| "loss": 0.0686, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 4.778254649499285, | |
| "grad_norm": 6.8715643882751465, | |
| "learning_rate": 1.1601400827761859e-05, | |
| "loss": 0.1569, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 4.8068669527897, | |
| "grad_norm": 4.068518161773682, | |
| "learning_rate": 1.1537726838586439e-05, | |
| "loss": 0.1418, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 4.835479256080115, | |
| "grad_norm": 4.682926654815674, | |
| "learning_rate": 1.1474052849411017e-05, | |
| "loss": 0.0648, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 4.86409155937053, | |
| "grad_norm": 7.655228614807129, | |
| "learning_rate": 1.1410378860235594e-05, | |
| "loss": 0.0663, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.8927038626609445, | |
| "grad_norm": 3.970196485519409, | |
| "learning_rate": 1.1346704871060172e-05, | |
| "loss": 0.0987, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 4.921316165951359, | |
| "grad_norm": 5.761990070343018, | |
| "learning_rate": 1.128303088188475e-05, | |
| "loss": 0.1427, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 4.949928469241774, | |
| "grad_norm": 4.295167922973633, | |
| "learning_rate": 1.121935689270933e-05, | |
| "loss": 0.0823, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 4.978540772532189, | |
| "grad_norm": 4.116291046142578, | |
| "learning_rate": 1.1155682903533907e-05, | |
| "loss": 0.1385, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 4.998569384835479, | |
| "eval_avg_f1": 0.8941948349225115, | |
| "eval_avg_macro_f1": 0.8878550329309804, | |
| "eval_hazard_accuracy": 0.9435310936383131, | |
| "eval_hazard_f1": 0.9425641782349181, | |
| "eval_hazard_macro_f1": 0.9097795857611878, | |
| "eval_hazard_precision": 0.9426745513555169, | |
| "eval_hazard_recall": 0.9435310936383131, | |
| "eval_loss": 0.28357216715812683, | |
| "eval_product_accuracy": 0.8456040028591851, | |
| "eval_product_f1": 0.8458254916101048, | |
| "eval_product_macro_f1": 0.8659304801007732, | |
| "eval_product_precision": 0.8482459261870001, | |
| "eval_product_recall": 0.8456040028591851, | |
| "eval_runtime": 130.0777, | |
| "eval_samples_per_second": 10.755, | |
| "eval_steps_per_second": 5.381, | |
| "step": 1747 | |
| }, | |
| { | |
| "epoch": 5.007153075822604, | |
| "grad_norm": 0.7914103269577026, | |
| "learning_rate": 1.1092008914358485e-05, | |
| "loss": 0.103, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 5.035765379113019, | |
| "grad_norm": 1.690512776374817, | |
| "learning_rate": 1.1028334925183064e-05, | |
| "loss": 0.0496, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 5.064377682403434, | |
| "grad_norm": 2.9918479919433594, | |
| "learning_rate": 1.0964660936007644e-05, | |
| "loss": 0.0575, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 5.0929899856938485, | |
| "grad_norm": 4.817768573760986, | |
| "learning_rate": 1.0900986946832219e-05, | |
| "loss": 0.0352, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 5.121602288984263, | |
| "grad_norm": 4.413773059844971, | |
| "learning_rate": 1.0837312957656799e-05, | |
| "loss": 0.0619, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 5.150214592274678, | |
| "grad_norm": 5.848459243774414, | |
| "learning_rate": 1.0773638968481377e-05, | |
| "loss": 0.0832, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.178826895565093, | |
| "grad_norm": 1.7106515169143677, | |
| "learning_rate": 1.0709964979305953e-05, | |
| "loss": 0.0364, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 5.207439198855508, | |
| "grad_norm": 0.5961392521858215, | |
| "learning_rate": 1.0646290990130532e-05, | |
| "loss": 0.059, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 5.236051502145923, | |
| "grad_norm": 6.867336750030518, | |
| "learning_rate": 1.0582617000955112e-05, | |
| "loss": 0.1284, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 5.264663805436338, | |
| "grad_norm": 2.6260428428649902, | |
| "learning_rate": 1.051894301177969e-05, | |
| "loss": 0.0571, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 5.293276108726753, | |
| "grad_norm": 4.524204730987549, | |
| "learning_rate": 1.0455269022604267e-05, | |
| "loss": 0.0271, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 5.3218884120171674, | |
| "grad_norm": 0.2257910519838333, | |
| "learning_rate": 1.0391595033428845e-05, | |
| "loss": 0.0412, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 5.350500715307582, | |
| "grad_norm": 2.122143268585205, | |
| "learning_rate": 1.0327921044253423e-05, | |
| "loss": 0.0523, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 5.379113018597997, | |
| "grad_norm": 3.099912643432617, | |
| "learning_rate": 1.0264247055078e-05, | |
| "loss": 0.0956, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 5.407725321888412, | |
| "grad_norm": 1.7758303880691528, | |
| "learning_rate": 1.020057306590258e-05, | |
| "loss": 0.0505, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 5.436337625178827, | |
| "grad_norm": 0.38635560870170593, | |
| "learning_rate": 1.0136899076727158e-05, | |
| "loss": 0.0337, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.464949928469242, | |
| "grad_norm": 1.2298860549926758, | |
| "learning_rate": 1.0073225087551737e-05, | |
| "loss": 0.0366, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 5.493562231759657, | |
| "grad_norm": 3.3369784355163574, | |
| "learning_rate": 1.0009551098376313e-05, | |
| "loss": 0.077, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 5.5221745350500715, | |
| "grad_norm": 3.413776397705078, | |
| "learning_rate": 9.945877109200891e-06, | |
| "loss": 0.064, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 5.550786838340486, | |
| "grad_norm": 8.428875923156738, | |
| "learning_rate": 9.882203120025471e-06, | |
| "loss": 0.0546, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 5.579399141630901, | |
| "grad_norm": 3.4294254779815674, | |
| "learning_rate": 9.818529130850048e-06, | |
| "loss": 0.0712, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 5.608011444921316, | |
| "grad_norm": 6.573678970336914, | |
| "learning_rate": 9.754855141674626e-06, | |
| "loss": 0.0693, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 5.636623748211731, | |
| "grad_norm": 2.1921682357788086, | |
| "learning_rate": 9.691181152499205e-06, | |
| "loss": 0.0433, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 5.665236051502146, | |
| "grad_norm": 4.298460006713867, | |
| "learning_rate": 9.627507163323783e-06, | |
| "loss": 0.0624, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 5.693848354792561, | |
| "grad_norm": 0.3570319712162018, | |
| "learning_rate": 9.563833174148361e-06, | |
| "loss": 0.0354, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 5.7224606580829755, | |
| "grad_norm": 0.37695419788360596, | |
| "learning_rate": 9.50015918497294e-06, | |
| "loss": 0.0354, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.75107296137339, | |
| "grad_norm": 3.561854362487793, | |
| "learning_rate": 9.436485195797518e-06, | |
| "loss": 0.0616, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 5.779685264663805, | |
| "grad_norm": 4.1541900634765625, | |
| "learning_rate": 9.372811206622096e-06, | |
| "loss": 0.0536, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 5.80829756795422, | |
| "grad_norm": 1.080567717552185, | |
| "learning_rate": 9.309137217446675e-06, | |
| "loss": 0.0245, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 5.836909871244635, | |
| "grad_norm": 6.586161136627197, | |
| "learning_rate": 9.245463228271251e-06, | |
| "loss": 0.0332, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 5.86552217453505, | |
| "grad_norm": 3.8174326419830322, | |
| "learning_rate": 9.18178923909583e-06, | |
| "loss": 0.0959, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 5.894134477825465, | |
| "grad_norm": 1.1422789096832275, | |
| "learning_rate": 9.118115249920408e-06, | |
| "loss": 0.0333, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 5.92274678111588, | |
| "grad_norm": 2.6852996349334717, | |
| "learning_rate": 9.054441260744986e-06, | |
| "loss": 0.0747, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 5.9513590844062945, | |
| "grad_norm": 2.938167095184326, | |
| "learning_rate": 8.990767271569564e-06, | |
| "loss": 0.0546, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 5.979971387696709, | |
| "grad_norm": 4.585486888885498, | |
| "learning_rate": 8.927093282394143e-06, | |
| "loss": 0.0743, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_avg_f1": 0.899039326351045, | |
| "eval_avg_macro_f1": 0.8991573960541488, | |
| "eval_hazard_accuracy": 0.9485346676197284, | |
| "eval_hazard_f1": 0.9484425225873391, | |
| "eval_hazard_macro_f1": 0.9204644489900575, | |
| "eval_hazard_precision": 0.9486631245033109, | |
| "eval_hazard_recall": 0.9485346676197284, | |
| "eval_loss": 0.3084051012992859, | |
| "eval_product_accuracy": 0.8470335954253038, | |
| "eval_product_f1": 0.849636130114751, | |
| "eval_product_macro_f1": 0.8778503431182402, | |
| "eval_product_precision": 0.8553543990148441, | |
| "eval_product_recall": 0.8470335954253038, | |
| "eval_runtime": 130.815, | |
| "eval_samples_per_second": 10.694, | |
| "eval_steps_per_second": 5.351, | |
| "step": 2097 | |
| }, | |
| { | |
| "epoch": 6.008583690987124, | |
| "grad_norm": 2.7679495811462402, | |
| "learning_rate": 8.863419293218721e-06, | |
| "loss": 0.0518, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 6.037195994277539, | |
| "grad_norm": 3.5409038066864014, | |
| "learning_rate": 8.7997453040433e-06, | |
| "loss": 0.0344, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 6.065808297567954, | |
| "grad_norm": 0.5573897957801819, | |
| "learning_rate": 8.736071314867878e-06, | |
| "loss": 0.0116, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 6.094420600858369, | |
| "grad_norm": 3.2066051959991455, | |
| "learning_rate": 8.672397325692456e-06, | |
| "loss": 0.0145, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 6.123032904148784, | |
| "grad_norm": 2.6980865001678467, | |
| "learning_rate": 8.608723336517033e-06, | |
| "loss": 0.0319, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 6.1516452074391985, | |
| "grad_norm": 3.0440590381622314, | |
| "learning_rate": 8.545049347341613e-06, | |
| "loss": 0.0327, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 6.180257510729613, | |
| "grad_norm": 0.7029679417610168, | |
| "learning_rate": 8.481375358166189e-06, | |
| "loss": 0.0361, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 6.208869814020028, | |
| "grad_norm": 1.076248288154602, | |
| "learning_rate": 8.417701368990769e-06, | |
| "loss": 0.0219, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 6.237482117310443, | |
| "grad_norm": 0.21603639423847198, | |
| "learning_rate": 8.354027379815346e-06, | |
| "loss": 0.0254, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 6.266094420600858, | |
| "grad_norm": 1.9013558626174927, | |
| "learning_rate": 8.290353390639924e-06, | |
| "loss": 0.0463, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 6.294706723891273, | |
| "grad_norm": 5.441349983215332, | |
| "learning_rate": 8.226679401464502e-06, | |
| "loss": 0.024, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.323319027181688, | |
| "grad_norm": 5.063304901123047, | |
| "learning_rate": 8.16300541228908e-06, | |
| "loss": 0.0637, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 6.3519313304721035, | |
| "grad_norm": 1.4071033000946045, | |
| "learning_rate": 8.099331423113659e-06, | |
| "loss": 0.0517, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 6.380543633762517, | |
| "grad_norm": 1.1152009963989258, | |
| "learning_rate": 8.035657433938237e-06, | |
| "loss": 0.0389, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 6.409155937052933, | |
| "grad_norm": 0.7116595506668091, | |
| "learning_rate": 7.971983444762816e-06, | |
| "loss": 0.0189, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 6.437768240343348, | |
| "grad_norm": 0.37217339873313904, | |
| "learning_rate": 7.908309455587392e-06, | |
| "loss": 0.0474, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 6.466380543633763, | |
| "grad_norm": 4.032446384429932, | |
| "learning_rate": 7.844635466411972e-06, | |
| "loss": 0.0192, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 6.494992846924178, | |
| "grad_norm": 1.627589464187622, | |
| "learning_rate": 7.780961477236549e-06, | |
| "loss": 0.0287, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 6.523605150214593, | |
| "grad_norm": 4.680599689483643, | |
| "learning_rate": 7.717287488061129e-06, | |
| "loss": 0.0266, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 6.5522174535050075, | |
| "grad_norm": 2.4412145614624023, | |
| "learning_rate": 7.653613498885705e-06, | |
| "loss": 0.0359, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 6.580829756795422, | |
| "grad_norm": 7.0371994972229, | |
| "learning_rate": 7.589939509710284e-06, | |
| "loss": 0.0444, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.609442060085837, | |
| "grad_norm": 1.9186558723449707, | |
| "learning_rate": 7.526265520534862e-06, | |
| "loss": 0.0464, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 6.638054363376252, | |
| "grad_norm": 5.816532135009766, | |
| "learning_rate": 7.4625915313594395e-06, | |
| "loss": 0.0326, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 0.9704585075378418, | |
| "learning_rate": 7.398917542184019e-06, | |
| "loss": 0.0509, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 6.695278969957082, | |
| "grad_norm": 0.7912341356277466, | |
| "learning_rate": 7.335243553008596e-06, | |
| "loss": 0.0271, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 6.723891273247497, | |
| "grad_norm": 1.4395134449005127, | |
| "learning_rate": 7.271569563833175e-06, | |
| "loss": 0.0116, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 6.752503576537912, | |
| "grad_norm": 1.1446588039398193, | |
| "learning_rate": 7.207895574657753e-06, | |
| "loss": 0.0144, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 6.781115879828326, | |
| "grad_norm": 9.389579772949219, | |
| "learning_rate": 7.144221585482332e-06, | |
| "loss": 0.0501, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 6.809728183118741, | |
| "grad_norm": 0.7342149615287781, | |
| "learning_rate": 7.080547596306909e-06, | |
| "loss": 0.0423, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 6.838340486409156, | |
| "grad_norm": 0.45319071412086487, | |
| "learning_rate": 7.016873607131487e-06, | |
| "loss": 0.0166, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 6.866952789699571, | |
| "grad_norm": 1.0449373722076416, | |
| "learning_rate": 6.953199617956066e-06, | |
| "loss": 0.0334, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.895565092989986, | |
| "grad_norm": 2.302659034729004, | |
| "learning_rate": 6.889525628780643e-06, | |
| "loss": 0.0245, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 6.924177396280401, | |
| "grad_norm": 4.263031005859375, | |
| "learning_rate": 6.825851639605222e-06, | |
| "loss": 0.0471, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 6.952789699570816, | |
| "grad_norm": 1.7275855541229248, | |
| "learning_rate": 6.7621776504298e-06, | |
| "loss": 0.0398, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 6.9814020028612305, | |
| "grad_norm": 7.692391872406006, | |
| "learning_rate": 6.698503661254378e-06, | |
| "loss": 0.0518, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 6.998569384835479, | |
| "eval_avg_f1": 0.898106190665952, | |
| "eval_avg_macro_f1": 0.8971876250415056, | |
| "eval_hazard_accuracy": 0.9449606862044317, | |
| "eval_hazard_f1": 0.9433007151966496, | |
| "eval_hazard_macro_f1": 0.9137195353650875, | |
| "eval_hazard_precision": 0.9454855478200699, | |
| "eval_hazard_recall": 0.9449606862044317, | |
| "eval_loss": 0.316262811422348, | |
| "eval_product_accuracy": 0.8491779842744818, | |
| "eval_product_f1": 0.8529116661352544, | |
| "eval_product_macro_f1": 0.8806557147179237, | |
| "eval_product_precision": 0.8601471328543786, | |
| "eval_product_recall": 0.8491779842744818, | |
| "eval_runtime": 130.6421, | |
| "eval_samples_per_second": 10.709, | |
| "eval_steps_per_second": 5.358, | |
| "step": 2446 | |
| }, | |
| { | |
| "epoch": 7.010014306151645, | |
| "grad_norm": 0.39778342843055725, | |
| "learning_rate": 6.634829672078957e-06, | |
| "loss": 0.0237, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 7.03862660944206, | |
| "grad_norm": 0.2173616886138916, | |
| "learning_rate": 6.571155682903534e-06, | |
| "loss": 0.0126, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 7.067238912732475, | |
| "grad_norm": 0.37986260652542114, | |
| "learning_rate": 6.507481693728112e-06, | |
| "loss": 0.0175, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 7.09585121602289, | |
| "grad_norm": 0.17169423401355743, | |
| "learning_rate": 6.443807704552691e-06, | |
| "loss": 0.0084, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 7.124463519313305, | |
| "grad_norm": 0.15883368253707886, | |
| "learning_rate": 6.380133715377269e-06, | |
| "loss": 0.0113, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 7.15307582260372, | |
| "grad_norm": 0.38070613145828247, | |
| "learning_rate": 6.3164597262018465e-06, | |
| "loss": 0.0158, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 7.1816881258941345, | |
| "grad_norm": 1.6812623739242554, | |
| "learning_rate": 6.252785737026426e-06, | |
| "loss": 0.0058, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 7.210300429184549, | |
| "grad_norm": 0.9641416668891907, | |
| "learning_rate": 6.189111747851003e-06, | |
| "loss": 0.0164, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 7.238912732474964, | |
| "grad_norm": 0.4583294689655304, | |
| "learning_rate": 6.125437758675582e-06, | |
| "loss": 0.0276, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 7.267525035765379, | |
| "grad_norm": 0.13083776831626892, | |
| "learning_rate": 6.06176376950016e-06, | |
| "loss": 0.0218, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 7.296137339055794, | |
| "grad_norm": 1.4103626012802124, | |
| "learning_rate": 5.998089780324737e-06, | |
| "loss": 0.0125, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 7.324749642346209, | |
| "grad_norm": 0.144416943192482, | |
| "learning_rate": 5.934415791149316e-06, | |
| "loss": 0.0107, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 7.353361945636624, | |
| "grad_norm": 0.27716395258903503, | |
| "learning_rate": 5.870741801973894e-06, | |
| "loss": 0.0134, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 7.381974248927039, | |
| "grad_norm": 1.8152793645858765, | |
| "learning_rate": 5.807067812798473e-06, | |
| "loss": 0.0082, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 7.410586552217453, | |
| "grad_norm": 0.464851438999176, | |
| "learning_rate": 5.74339382362305e-06, | |
| "loss": 0.0205, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 7.439198855507868, | |
| "grad_norm": 0.06875355541706085, | |
| "learning_rate": 5.679719834447629e-06, | |
| "loss": 0.0139, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.467811158798283, | |
| "grad_norm": 3.882838487625122, | |
| "learning_rate": 5.616045845272207e-06, | |
| "loss": 0.0231, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 7.496423462088698, | |
| "grad_norm": 1.3986179828643799, | |
| "learning_rate": 5.552371856096785e-06, | |
| "loss": 0.0107, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 7.525035765379113, | |
| "grad_norm": 0.6413142085075378, | |
| "learning_rate": 5.488697866921363e-06, | |
| "loss": 0.0209, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 7.553648068669528, | |
| "grad_norm": 0.40927574038505554, | |
| "learning_rate": 5.425023877745941e-06, | |
| "loss": 0.0069, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 7.582260371959943, | |
| "grad_norm": 0.2263065129518509, | |
| "learning_rate": 5.361349888570519e-06, | |
| "loss": 0.0178, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 7.6108726752503575, | |
| "grad_norm": 0.36000296473503113, | |
| "learning_rate": 5.30404329831264e-06, | |
| "loss": 0.0169, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 7.639484978540772, | |
| "grad_norm": 4.618471622467041, | |
| "learning_rate": 5.240369309137218e-06, | |
| "loss": 0.031, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 7.668097281831187, | |
| "grad_norm": 0.1742757260799408, | |
| "learning_rate": 5.176695319961796e-06, | |
| "loss": 0.0067, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 7.696709585121602, | |
| "grad_norm": 4.546988487243652, | |
| "learning_rate": 5.1130213307863745e-06, | |
| "loss": 0.0262, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 7.725321888412017, | |
| "grad_norm": 0.41645824909210205, | |
| "learning_rate": 5.049347341610953e-06, | |
| "loss": 0.0171, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.753934191702432, | |
| "grad_norm": 1.6162680387496948, | |
| "learning_rate": 4.98567335243553e-06, | |
| "loss": 0.0366, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 7.782546494992847, | |
| "grad_norm": 0.5289233922958374, | |
| "learning_rate": 4.9219993632601085e-06, | |
| "loss": 0.0229, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 7.8111587982832615, | |
| "grad_norm": 1.002968430519104, | |
| "learning_rate": 4.858325374084687e-06, | |
| "loss": 0.0148, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 7.839771101573676, | |
| "grad_norm": 0.32215040922164917, | |
| "learning_rate": 4.794651384909265e-06, | |
| "loss": 0.0438, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 7.868383404864091, | |
| "grad_norm": 0.2097528576850891, | |
| "learning_rate": 4.730977395733843e-06, | |
| "loss": 0.0234, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 7.896995708154506, | |
| "grad_norm": 0.3217938542366028, | |
| "learning_rate": 4.667303406558421e-06, | |
| "loss": 0.0256, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 7.925608011444921, | |
| "grad_norm": 0.6360646486282349, | |
| "learning_rate": 4.603629417382999e-06, | |
| "loss": 0.0417, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 7.954220314735336, | |
| "grad_norm": 2.2907752990722656, | |
| "learning_rate": 4.5399554282075775e-06, | |
| "loss": 0.0146, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 7.982832618025751, | |
| "grad_norm": 0.6704244613647461, | |
| "learning_rate": 4.476281439032156e-06, | |
| "loss": 0.0203, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_avg_f1": 0.9009805609498489, | |
| "eval_avg_macro_f1": 0.8958663202550365, | |
| "eval_hazard_accuracy": 0.9449606862044317, | |
| "eval_hazard_f1": 0.9442059444799251, | |
| "eval_hazard_macro_f1": 0.90671634348049, | |
| "eval_hazard_precision": 0.9452464738608288, | |
| "eval_hazard_recall": 0.9449606862044317, | |
| "eval_loss": 0.31793642044067383, | |
| "eval_product_accuracy": 0.8556111508220158, | |
| "eval_product_f1": 0.8577551774197726, | |
| "eval_product_macro_f1": 0.885016297029583, | |
| "eval_product_precision": 0.8628350198223755, | |
| "eval_product_recall": 0.8556111508220158, | |
| "eval_runtime": 130.7407, | |
| "eval_samples_per_second": 10.701, | |
| "eval_steps_per_second": 5.354, | |
| "step": 2796 | |
| }, | |
| { | |
| "epoch": 8.011444921316166, | |
| "grad_norm": 0.2047724425792694, | |
| "learning_rate": 4.412607449856734e-06, | |
| "loss": 0.0064, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 8.040057224606581, | |
| "grad_norm": 0.07871759682893753, | |
| "learning_rate": 4.3489334606813125e-06, | |
| "loss": 0.0138, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 8.068669527896995, | |
| "grad_norm": 1.8063669204711914, | |
| "learning_rate": 4.285259471505891e-06, | |
| "loss": 0.0043, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 8.097281831187411, | |
| "grad_norm": 0.4856473505496979, | |
| "learning_rate": 4.221585482330468e-06, | |
| "loss": 0.0062, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 8.125894134477825, | |
| "grad_norm": 0.5017396807670593, | |
| "learning_rate": 4.1579114931550465e-06, | |
| "loss": 0.0263, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 8.15450643776824, | |
| "grad_norm": 2.501828193664551, | |
| "learning_rate": 4.094237503979625e-06, | |
| "loss": 0.0295, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 8.183118741058655, | |
| "grad_norm": 0.36499956250190735, | |
| "learning_rate": 4.030563514804202e-06, | |
| "loss": 0.0218, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 8.21173104434907, | |
| "grad_norm": 1.9966788291931152, | |
| "learning_rate": 3.966889525628781e-06, | |
| "loss": 0.0108, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 8.240343347639485, | |
| "grad_norm": 2.827831983566284, | |
| "learning_rate": 3.903215536453359e-06, | |
| "loss": 0.0123, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 8.2689556509299, | |
| "grad_norm": 0.40095698833465576, | |
| "learning_rate": 3.839541547277937e-06, | |
| "loss": 0.0014, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 8.297567954220314, | |
| "grad_norm": 0.21733756363391876, | |
| "learning_rate": 3.7758675581025155e-06, | |
| "loss": 0.0231, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 8.32618025751073, | |
| "grad_norm": 0.2822847366333008, | |
| "learning_rate": 3.712193568927094e-06, | |
| "loss": 0.0027, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 8.354792560801144, | |
| "grad_norm": 0.19272436201572418, | |
| "learning_rate": 3.6485195797516713e-06, | |
| "loss": 0.0015, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 8.38340486409156, | |
| "grad_norm": 0.49634698033332825, | |
| "learning_rate": 3.5848455905762496e-06, | |
| "loss": 0.0074, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 8.412017167381974, | |
| "grad_norm": 0.06298165023326874, | |
| "learning_rate": 3.521171601400828e-06, | |
| "loss": 0.0218, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 8.44062947067239, | |
| "grad_norm": 0.0625123679637909, | |
| "learning_rate": 3.4574976122254062e-06, | |
| "loss": 0.0051, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 8.469241773962803, | |
| "grad_norm": 0.0806524008512497, | |
| "learning_rate": 3.3938236230499845e-06, | |
| "loss": 0.003, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 8.49785407725322, | |
| "grad_norm": 0.1726488322019577, | |
| "learning_rate": 3.3301496338745624e-06, | |
| "loss": 0.0038, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 8.526466380543633, | |
| "grad_norm": 2.4908065795898438, | |
| "learning_rate": 3.2664756446991407e-06, | |
| "loss": 0.0124, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 8.555078683834049, | |
| "grad_norm": 0.015561264008283615, | |
| "learning_rate": 3.202801655523719e-06, | |
| "loss": 0.0132, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 8.583690987124463, | |
| "grad_norm": 0.09347698092460632, | |
| "learning_rate": 3.1391276663482973e-06, | |
| "loss": 0.0094, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.612303290414879, | |
| "grad_norm": 0.6292846202850342, | |
| "learning_rate": 3.075453677172875e-06, | |
| "loss": 0.0047, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 8.640915593705293, | |
| "grad_norm": 0.0815897285938263, | |
| "learning_rate": 3.011779687997453e-06, | |
| "loss": 0.0028, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 8.669527896995708, | |
| "grad_norm": 0.4412260055541992, | |
| "learning_rate": 2.9481056988220314e-06, | |
| "loss": 0.0066, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 8.698140200286122, | |
| "grad_norm": 6.015453815460205, | |
| "learning_rate": 2.8844317096466097e-06, | |
| "loss": 0.0351, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 8.726752503576538, | |
| "grad_norm": 3.0399041175842285, | |
| "learning_rate": 2.8207577204711876e-06, | |
| "loss": 0.0049, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 8.755364806866952, | |
| "grad_norm": 0.5966952443122864, | |
| "learning_rate": 2.757083731295766e-06, | |
| "loss": 0.0153, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 8.783977110157368, | |
| "grad_norm": 0.6676664352416992, | |
| "learning_rate": 2.693409742120344e-06, | |
| "loss": 0.0079, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 8.812589413447782, | |
| "grad_norm": 1.2754206657409668, | |
| "learning_rate": 2.6297357529449225e-06, | |
| "loss": 0.0028, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 8.841201716738198, | |
| "grad_norm": 0.17587369680404663, | |
| "learning_rate": 2.5660617637695e-06, | |
| "loss": 0.0148, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 8.869814020028612, | |
| "grad_norm": 1.2772883176803589, | |
| "learning_rate": 2.5023877745940783e-06, | |
| "loss": 0.005, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.898426323319027, | |
| "grad_norm": 1.0710519552230835, | |
| "learning_rate": 2.4387137854186566e-06, | |
| "loss": 0.0109, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 8.927038626609441, | |
| "grad_norm": 0.30399370193481445, | |
| "learning_rate": 2.375039796243235e-06, | |
| "loss": 0.0029, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 8.955650929899857, | |
| "grad_norm": 0.3177274167537689, | |
| "learning_rate": 2.3113658070678128e-06, | |
| "loss": 0.0057, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 8.984263233190273, | |
| "grad_norm": 0.523124635219574, | |
| "learning_rate": 2.247691817892391e-06, | |
| "loss": 0.0058, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 8.998569384835479, | |
| "eval_avg_f1": 0.9074990725453154, | |
| "eval_avg_macro_f1": 0.9049823782519661, | |
| "eval_hazard_accuracy": 0.949964260185847, | |
| "eval_hazard_f1": 0.9494646211249262, | |
| "eval_hazard_macro_f1": 0.9187490461241665, | |
| "eval_hazard_precision": 0.9503361146795187, | |
| "eval_hazard_recall": 0.949964260185847, | |
| "eval_loss": 0.32502511143684387, | |
| "eval_product_accuracy": 0.8649035025017869, | |
| "eval_product_f1": 0.8655335239657044, | |
| "eval_product_macro_f1": 0.8912157103797657, | |
| "eval_product_precision": 0.8676022686098708, | |
| "eval_product_recall": 0.8649035025017869, | |
| "eval_runtime": 130.924, | |
| "eval_samples_per_second": 10.686, | |
| "eval_steps_per_second": 5.347, | |
| "step": 3145 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 3490, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |