{ "best_metric": 0.955865295904617, "best_model_checkpoint": "output_classification_768/hazard/checkpoint-5714", "epoch": 8.0, "eval_steps": 500, "global_step": 5714, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01400070003500175, "grad_norm": 18.827600479125977, "learning_rate": 8.403361344537815e-08, "loss": 1.9841, "step": 10 }, { "epoch": 0.0280014000700035, "grad_norm": 18.72251319885254, "learning_rate": 1.680672268907563e-07, "loss": 2.0361, "step": 20 }, { "epoch": 0.04200210010500525, "grad_norm": 19.22981071472168, "learning_rate": 2.6143790849673207e-07, "loss": 2.0152, "step": 30 }, { "epoch": 0.056002800140007, "grad_norm": 29.57445526123047, "learning_rate": 3.548085901027078e-07, "loss": 1.9341, "step": 40 }, { "epoch": 0.07000350017500875, "grad_norm": 22.95323944091797, "learning_rate": 4.481792717086835e-07, "loss": 1.886, "step": 50 }, { "epoch": 0.0840042002100105, "grad_norm": 19.979074478149414, "learning_rate": 5.415499533146593e-07, "loss": 1.956, "step": 60 }, { "epoch": 0.09800490024501225, "grad_norm": 20.88674545288086, "learning_rate": 6.255835667600374e-07, "loss": 1.8046, "step": 70 }, { "epoch": 0.112005600280014, "grad_norm": 29.573392868041992, "learning_rate": 7.189542483660131e-07, "loss": 1.6156, "step": 80 }, { "epoch": 0.12600630031501575, "grad_norm": 51.34833908081055, "learning_rate": 8.123249299719889e-07, "loss": 1.4696, "step": 90 }, { "epoch": 0.1400070003500175, "grad_norm": 25.478782653808594, "learning_rate": 9.056956115779646e-07, "loss": 1.3458, "step": 100 }, { "epoch": 0.15400770038501926, "grad_norm": 26.403230667114258, "learning_rate": 9.897292250233428e-07, "loss": 1.2287, "step": 110 }, { "epoch": 0.168008400420021, "grad_norm": 32.914329528808594, "learning_rate": 1.0830999066293185e-06, "loss": 1.373, "step": 120 }, { "epoch": 0.18200910045502275, "grad_norm": 27.074459075927734, "learning_rate": 1.1764705882352942e-06, "loss": 1.1883, "step": 130 }, { "epoch": 0.1960098004900245, "grad_norm": 30.801422119140625, "learning_rate": 1.26984126984127e-06, "loss": 1.1013, "step": 140 }, { "epoch": 0.21001050052502626, "grad_norm": 28.34015655517578, "learning_rate": 1.3632119514472457e-06, "loss": 1.2526, "step": 150 }, { "epoch": 0.224011200560028, "grad_norm": 25.3271541595459, "learning_rate": 1.4565826330532216e-06, "loss": 1.1301, "step": 160 }, { "epoch": 0.23801190059502975, "grad_norm": 39.82203674316406, "learning_rate": 1.5499533146591973e-06, "loss": 1.257, "step": 170 }, { "epoch": 0.2520126006300315, "grad_norm": 30.389141082763672, "learning_rate": 1.6433239962651728e-06, "loss": 1.1949, "step": 180 }, { "epoch": 0.26601330066503326, "grad_norm": Infinity, "learning_rate": 1.727357609710551e-06, "loss": 1.1192, "step": 190 }, { "epoch": 0.280014000700035, "grad_norm": 20.167753219604492, "learning_rate": 1.8207282913165267e-06, "loss": 1.1671, "step": 200 }, { "epoch": 0.29401470073503677, "grad_norm": 35.408851623535156, "learning_rate": 1.914098972922503e-06, "loss": 1.0633, "step": 210 }, { "epoch": 0.3080154007700385, "grad_norm": 27.517133712768555, "learning_rate": 2.0074696545284783e-06, "loss": 1.2556, "step": 220 }, { "epoch": 0.32201610080504023, "grad_norm": 28.972402572631836, "learning_rate": 2.100840336134454e-06, "loss": 0.9785, "step": 230 }, { "epoch": 0.336016800840042, "grad_norm": 27.440292358398438, "learning_rate": 2.1942110177404298e-06, "loss": 1.0198, "step": 240 }, { "epoch": 0.35001750087504374, "grad_norm": 48.26941680908203, "learning_rate": 2.278244631185808e-06, "loss": 1.2617, "step": 250 }, { "epoch": 0.3640182009100455, "grad_norm": 24.725189208984375, "learning_rate": 2.3716153127917835e-06, "loss": 1.0211, "step": 260 }, { "epoch": 0.37801890094504725, "grad_norm": 23.73585319519043, "learning_rate": 2.4649859943977594e-06, "loss": 1.0714, "step": 270 }, { "epoch": 0.392019600980049, "grad_norm": 26.64818000793457, "learning_rate": 2.558356676003735e-06, "loss": 0.7989, "step": 280 }, { "epoch": 0.40602030101505077, "grad_norm": 14.705005645751953, "learning_rate": 2.651727357609711e-06, "loss": 0.7878, "step": 290 }, { "epoch": 0.4200210010500525, "grad_norm": 14.422958374023438, "learning_rate": 2.7450980392156867e-06, "loss": 0.8429, "step": 300 }, { "epoch": 0.4340217010850543, "grad_norm": 33.29634475708008, "learning_rate": 2.8384687208216622e-06, "loss": 0.7312, "step": 310 }, { "epoch": 0.448022401120056, "grad_norm": 33.81440353393555, "learning_rate": 2.931839402427638e-06, "loss": 0.6694, "step": 320 }, { "epoch": 0.46202310115505774, "grad_norm": 24.78529167175293, "learning_rate": 3.0252100840336137e-06, "loss": 0.4384, "step": 330 }, { "epoch": 0.4760238011900595, "grad_norm": 12.186172485351562, "learning_rate": 3.1185807656395896e-06, "loss": 0.6493, "step": 340 }, { "epoch": 0.49002450122506125, "grad_norm": 21.81092071533203, "learning_rate": 3.2119514472455655e-06, "loss": 0.6262, "step": 350 }, { "epoch": 0.504025201260063, "grad_norm": 32.27071762084961, "learning_rate": 3.305322128851541e-06, "loss": 0.5861, "step": 360 }, { "epoch": 0.5180259012950648, "grad_norm": 25.360836029052734, "learning_rate": 3.398692810457517e-06, "loss": 0.4615, "step": 370 }, { "epoch": 0.5320266013300665, "grad_norm": 4.028536796569824, "learning_rate": 3.492063492063492e-06, "loss": 0.3756, "step": 380 }, { "epoch": 0.5460273013650683, "grad_norm": 23.051633834838867, "learning_rate": 3.585434173669468e-06, "loss": 0.4682, "step": 390 }, { "epoch": 0.56002800140007, "grad_norm": 16.828521728515625, "learning_rate": 3.678804855275444e-06, "loss": 0.3575, "step": 400 }, { "epoch": 0.5740287014350718, "grad_norm": 14.486180305480957, "learning_rate": 3.7721755368814194e-06, "loss": 0.3074, "step": 410 }, { "epoch": 0.5880294014700735, "grad_norm": 20.30696678161621, "learning_rate": 3.865546218487396e-06, "loss": 0.3504, "step": 420 }, { "epoch": 0.6020301015050753, "grad_norm": 11.418947219848633, "learning_rate": 3.958916900093371e-06, "loss": 0.421, "step": 430 }, { "epoch": 0.616030801540077, "grad_norm": 22.60586929321289, "learning_rate": 4.052287581699347e-06, "loss": 0.4654, "step": 440 }, { "epoch": 0.6300315015750787, "grad_norm": 11.261972427368164, "learning_rate": 4.145658263305323e-06, "loss": 0.3997, "step": 450 }, { "epoch": 0.6440322016100805, "grad_norm": 28.590770721435547, "learning_rate": 4.239028944911298e-06, "loss": 0.41, "step": 460 }, { "epoch": 0.6580329016450822, "grad_norm": 19.348529815673828, "learning_rate": 4.332399626517274e-06, "loss": 0.3127, "step": 470 }, { "epoch": 0.672033601680084, "grad_norm": 11.520312309265137, "learning_rate": 4.4257703081232496e-06, "loss": 0.2414, "step": 480 }, { "epoch": 0.6860343017150857, "grad_norm": 12.15475082397461, "learning_rate": 4.519140989729225e-06, "loss": 0.3494, "step": 490 }, { "epoch": 0.7000350017500875, "grad_norm": 25.96927833557129, "learning_rate": 4.612511671335201e-06, "loss": 0.3013, "step": 500 }, { "epoch": 0.7140357017850892, "grad_norm": 6.085643291473389, "learning_rate": 4.705882352941177e-06, "loss": 0.2011, "step": 510 }, { "epoch": 0.728036401820091, "grad_norm": 44.394142150878906, "learning_rate": 4.799253034547152e-06, "loss": 0.3666, "step": 520 }, { "epoch": 0.7420371018550928, "grad_norm": 17.268661499023438, "learning_rate": 4.892623716153128e-06, "loss": 0.4868, "step": 530 }, { "epoch": 0.7560378018900945, "grad_norm": 4.370459079742432, "learning_rate": 4.985994397759104e-06, "loss": 0.2099, "step": 540 }, { "epoch": 0.7700385019250963, "grad_norm": 18.326570510864258, "learning_rate": 5.07936507936508e-06, "loss": 0.1579, "step": 550 }, { "epoch": 0.784039201960098, "grad_norm": 15.142720222473145, "learning_rate": 5.172735760971056e-06, "loss": 0.366, "step": 560 }, { "epoch": 0.7980399019950998, "grad_norm": 18.712690353393555, "learning_rate": 5.266106442577032e-06, "loss": 0.2947, "step": 570 }, { "epoch": 0.8120406020301015, "grad_norm": 17.141977310180664, "learning_rate": 5.359477124183007e-06, "loss": 0.3521, "step": 580 }, { "epoch": 0.8260413020651033, "grad_norm": 25.074716567993164, "learning_rate": 5.452847805788983e-06, "loss": 0.3515, "step": 590 }, { "epoch": 0.840042002100105, "grad_norm": 39.856689453125, "learning_rate": 5.546218487394959e-06, "loss": 0.2407, "step": 600 }, { "epoch": 0.8540427021351068, "grad_norm": 27.31299591064453, "learning_rate": 5.6395891690009344e-06, "loss": 0.3806, "step": 610 }, { "epoch": 0.8680434021701086, "grad_norm": 23.94294548034668, "learning_rate": 5.732959850606909e-06, "loss": 0.247, "step": 620 }, { "epoch": 0.8820441022051102, "grad_norm": 18.762691497802734, "learning_rate": 5.826330532212886e-06, "loss": 0.227, "step": 630 }, { "epoch": 0.896044802240112, "grad_norm": 1.3951778411865234, "learning_rate": 5.919701213818862e-06, "loss": 0.2068, "step": 640 }, { "epoch": 0.9100455022751137, "grad_norm": 0.5448408126831055, "learning_rate": 6.0130718954248365e-06, "loss": 0.1872, "step": 650 }, { "epoch": 0.9240462023101155, "grad_norm": 15.129274368286133, "learning_rate": 6.106442577030814e-06, "loss": 0.2704, "step": 660 }, { "epoch": 0.9380469023451172, "grad_norm": 14.669654846191406, "learning_rate": 6.199813258636789e-06, "loss": 0.2402, "step": 670 }, { "epoch": 0.952047602380119, "grad_norm": 12.849870681762695, "learning_rate": 6.293183940242764e-06, "loss": 0.3798, "step": 680 }, { "epoch": 0.9660483024151207, "grad_norm": 3.6425814628601074, "learning_rate": 6.386554621848739e-06, "loss": 0.1084, "step": 690 }, { "epoch": 0.9800490024501225, "grad_norm": 22.52290153503418, "learning_rate": 6.479925303454716e-06, "loss": 0.2555, "step": 700 }, { "epoch": 0.9940497024851243, "grad_norm": 21.555450439453125, "learning_rate": 6.573295985060691e-06, "loss": 0.0919, "step": 710 }, { "epoch": 0.999649982499125, "eval_f1": 0.8955208020599833, "eval_loss": 0.22013917565345764, "eval_precision": 0.8902907982202399, "eval_recall": 0.8957312806158153, "eval_runtime": 85.7223, "eval_samples_per_second": 16.67, "eval_steps_per_second": 8.341, "step": 714 }, { "epoch": 1.008050402520126, "grad_norm": 50.78132247924805, "learning_rate": 6.666666666666667e-06, "loss": 0.1955, "step": 720 }, { "epoch": 1.0220511025551278, "grad_norm": 10.807790756225586, "learning_rate": 6.760037348272643e-06, "loss": 0.2093, "step": 730 }, { "epoch": 1.0360518025901295, "grad_norm": 13.804763793945312, "learning_rate": 6.8534080298786185e-06, "loss": 0.1498, "step": 740 }, { "epoch": 1.0500525026251313, "grad_norm": 177.36477661132812, "learning_rate": 6.946778711484594e-06, "loss": 0.0677, "step": 750 }, { "epoch": 1.064053202660133, "grad_norm": 33.29927062988281, "learning_rate": 7.04014939309057e-06, "loss": 0.1319, "step": 760 }, { "epoch": 1.0780539026951348, "grad_norm": 50.21918869018555, "learning_rate": 7.133520074696546e-06, "loss": 0.1975, "step": 770 }, { "epoch": 1.0920546027301365, "grad_norm": 20.914047241210938, "learning_rate": 7.226890756302521e-06, "loss": 0.1184, "step": 780 }, { "epoch": 1.1060553027651383, "grad_norm": 25.241579055786133, "learning_rate": 7.320261437908497e-06, "loss": 0.2089, "step": 790 }, { "epoch": 1.12005600280014, "grad_norm": 30.187185287475586, "learning_rate": 7.413632119514473e-06, "loss": 0.1561, "step": 800 }, { "epoch": 1.1340567028351418, "grad_norm": 57.18680953979492, "learning_rate": 7.507002801120449e-06, "loss": 0.1638, "step": 810 }, { "epoch": 1.1480574028701436, "grad_norm": 27.371370315551758, "learning_rate": 7.600373482726424e-06, "loss": 0.1526, "step": 820 }, { "epoch": 1.1620581029051453, "grad_norm": 3.447115659713745, "learning_rate": 7.6937441643324e-06, "loss": 0.1566, "step": 830 }, { "epoch": 1.176058802940147, "grad_norm": 47.86556625366211, "learning_rate": 7.787114845938376e-06, "loss": 0.0942, "step": 840 }, { "epoch": 1.1900595029751488, "grad_norm": 1.0057041645050049, "learning_rate": 7.880485527544352e-06, "loss": 0.1284, "step": 850 }, { "epoch": 1.2040602030101506, "grad_norm": 1.5863021612167358, "learning_rate": 7.973856209150329e-06, "loss": 0.0242, "step": 860 }, { "epoch": 1.2180609030451524, "grad_norm": 37.52120590209961, "learning_rate": 8.067226890756303e-06, "loss": 0.1856, "step": 870 }, { "epoch": 1.232061603080154, "grad_norm": 0.7147373557090759, "learning_rate": 8.151260504201681e-06, "loss": 0.1503, "step": 880 }, { "epoch": 1.2460623031151559, "grad_norm": 15.735259056091309, "learning_rate": 8.244631185807657e-06, "loss": 0.1443, "step": 890 }, { "epoch": 1.2600630031501576, "grad_norm": 28.31800651550293, "learning_rate": 8.338001867413634e-06, "loss": 0.2344, "step": 900 }, { "epoch": 1.2740637031851594, "grad_norm": 29.48625946044922, "learning_rate": 8.43137254901961e-06, "loss": 0.0729, "step": 910 }, { "epoch": 1.2880644032201611, "grad_norm": 18.03072166442871, "learning_rate": 8.524743230625583e-06, "loss": 0.2843, "step": 920 }, { "epoch": 1.302065103255163, "grad_norm": 7.900409698486328, "learning_rate": 8.61811391223156e-06, "loss": 0.1405, "step": 930 }, { "epoch": 1.3160658032901644, "grad_norm": 9.55482006072998, "learning_rate": 8.711484593837536e-06, "loss": 0.3472, "step": 940 }, { "epoch": 1.3300665033251662, "grad_norm": 1.0517637729644775, "learning_rate": 8.804855275443511e-06, "loss": 0.1811, "step": 950 }, { "epoch": 1.344067203360168, "grad_norm": 21.067020416259766, "learning_rate": 8.898225957049487e-06, "loss": 0.101, "step": 960 }, { "epoch": 1.3580679033951697, "grad_norm": 2.4087302684783936, "learning_rate": 8.991596638655462e-06, "loss": 0.1637, "step": 970 }, { "epoch": 1.3720686034301715, "grad_norm": 0.5226989388465881, "learning_rate": 9.084967320261438e-06, "loss": 0.1412, "step": 980 }, { "epoch": 1.3860693034651732, "grad_norm": 1.7105305194854736, "learning_rate": 9.178338001867413e-06, "loss": 0.0549, "step": 990 }, { "epoch": 1.400070003500175, "grad_norm": 1.5454177856445312, "learning_rate": 9.27170868347339e-06, "loss": 0.1198, "step": 1000 }, { "epoch": 1.4140707035351767, "grad_norm": 0.15765634179115295, "learning_rate": 9.365079365079366e-06, "loss": 0.1376, "step": 1010 }, { "epoch": 1.4280714035701785, "grad_norm": 1.46312415599823, "learning_rate": 9.458450046685342e-06, "loss": 0.0745, "step": 1020 }, { "epoch": 1.4420721036051802, "grad_norm": 5.383272647857666, "learning_rate": 9.551820728291317e-06, "loss": 0.1296, "step": 1030 }, { "epoch": 1.456072803640182, "grad_norm": 27.422487258911133, "learning_rate": 9.645191409897293e-06, "loss": 0.2348, "step": 1040 }, { "epoch": 1.4700735036751837, "grad_norm": 4.522994041442871, "learning_rate": 9.738562091503268e-06, "loss": 0.2962, "step": 1050 }, { "epoch": 1.4840742037101855, "grad_norm": 1.4947142601013184, "learning_rate": 9.831932773109244e-06, "loss": 0.2838, "step": 1060 }, { "epoch": 1.4980749037451873, "grad_norm": 5.711818695068359, "learning_rate": 9.92530345471522e-06, "loss": 0.0891, "step": 1070 }, { "epoch": 1.512075603780189, "grad_norm": 49.88716125488281, "learning_rate": 9.999998937727915e-06, "loss": 0.1245, "step": 1080 }, { "epoch": 1.5260763038151908, "grad_norm": 31.99099349975586, "learning_rate": 9.999961758252293e-06, "loss": 0.0667, "step": 1090 }, { "epoch": 1.5400770038501925, "grad_norm": 0.10951868444681168, "learning_rate": 9.999871465623728e-06, "loss": 0.2052, "step": 1100 }, { "epoch": 1.5540777038851943, "grad_norm": 44.73365783691406, "learning_rate": 9.999728060801377e-06, "loss": 0.2205, "step": 1110 }, { "epoch": 1.568078403920196, "grad_norm": 4.195182800292969, "learning_rate": 9.999531545308584e-06, "loss": 0.1455, "step": 1120 }, { "epoch": 1.5820791039551978, "grad_norm": 16.288776397705078, "learning_rate": 9.99928192123288e-06, "loss": 0.1029, "step": 1130 }, { "epoch": 1.5960798039901996, "grad_norm": 2.2979979515075684, "learning_rate": 9.998979191225946e-06, "loss": 0.3084, "step": 1140 }, { "epoch": 1.6100805040252013, "grad_norm": 6.856667995452881, "learning_rate": 9.998623358503599e-06, "loss": 0.1179, "step": 1150 }, { "epoch": 1.624081204060203, "grad_norm": 0.1702626645565033, "learning_rate": 9.998214426845745e-06, "loss": 0.0635, "step": 1160 }, { "epoch": 1.6380819040952046, "grad_norm": 3.6995737552642822, "learning_rate": 9.997752400596348e-06, "loss": 0.3362, "step": 1170 }, { "epoch": 1.6520826041302064, "grad_norm": 49.20168685913086, "learning_rate": 9.99723728466338e-06, "loss": 0.193, "step": 1180 }, { "epoch": 1.6660833041652081, "grad_norm": 0.09634213149547577, "learning_rate": 9.996669084518767e-06, "loss": 0.1294, "step": 1190 }, { "epoch": 1.6800840042002099, "grad_norm": 31.4400577545166, "learning_rate": 9.996047806198338e-06, "loss": 0.1319, "step": 1200 }, { "epoch": 1.6940847042352116, "grad_norm": 28.559484481811523, "learning_rate": 9.995373456301755e-06, "loss": 0.1419, "step": 1210 }, { "epoch": 1.7080854042702134, "grad_norm": 20.74497413635254, "learning_rate": 9.99464604199244e-06, "loss": 0.0486, "step": 1220 }, { "epoch": 1.7220861043052151, "grad_norm": 1.08584725856781, "learning_rate": 9.993865570997504e-06, "loss": 0.106, "step": 1230 }, { "epoch": 1.736086804340217, "grad_norm": 28.463891983032227, "learning_rate": 9.99303205160767e-06, "loss": 0.2637, "step": 1240 }, { "epoch": 1.7500875043752186, "grad_norm": 0.8130584359169006, "learning_rate": 9.99214549267717e-06, "loss": 0.0446, "step": 1250 }, { "epoch": 1.7640882044102204, "grad_norm": 1.0180484056472778, "learning_rate": 9.991205903623666e-06, "loss": 0.0494, "step": 1260 }, { "epoch": 1.7780889044452222, "grad_norm": 45.445831298828125, "learning_rate": 9.990213294428141e-06, "loss": 0.228, "step": 1270 }, { "epoch": 1.792089604480224, "grad_norm": 50.22725296020508, "learning_rate": 9.9891676756348e-06, "loss": 0.1444, "step": 1280 }, { "epoch": 1.8060903045152257, "grad_norm": 78.8548583984375, "learning_rate": 9.988069058350945e-06, "loss": 0.2021, "step": 1290 }, { "epoch": 1.8200910045502274, "grad_norm": 58.68122482299805, "learning_rate": 9.986917454246872e-06, "loss": 0.2497, "step": 1300 }, { "epoch": 1.8340917045852292, "grad_norm": 0.021190036088228226, "learning_rate": 9.985712875555743e-06, "loss": 0.1506, "step": 1310 }, { "epoch": 1.848092404620231, "grad_norm": 63.01392364501953, "learning_rate": 9.984455335073445e-06, "loss": 0.1217, "step": 1320 }, { "epoch": 1.8620931046552327, "grad_norm": 19.447858810424805, "learning_rate": 9.983144846158472e-06, "loss": 0.2588, "step": 1330 }, { "epoch": 1.8760938046902345, "grad_norm": 15.400856018066406, "learning_rate": 9.981781422731772e-06, "loss": 0.1024, "step": 1340 }, { "epoch": 1.8900945047252362, "grad_norm": 1.073379397392273, "learning_rate": 9.980365079276593e-06, "loss": 0.1605, "step": 1350 }, { "epoch": 1.904095204760238, "grad_norm": 31.710058212280273, "learning_rate": 9.978895830838348e-06, "loss": 0.0748, "step": 1360 }, { "epoch": 1.9180959047952397, "grad_norm": 0.05758415535092354, "learning_rate": 9.977373693024437e-06, "loss": 0.1769, "step": 1370 }, { "epoch": 1.9320966048302415, "grad_norm": 13.29843521118164, "learning_rate": 9.975798682004095e-06, "loss": 0.0806, "step": 1380 }, { "epoch": 1.9460973048652432, "grad_norm": 0.0567200742661953, "learning_rate": 9.974170814508207e-06, "loss": 0.1365, "step": 1390 }, { "epoch": 1.960098004900245, "grad_norm": 28.02842140197754, "learning_rate": 9.972490107829142e-06, "loss": 0.2761, "step": 1400 }, { "epoch": 1.9740987049352468, "grad_norm": 2.56071400642395, "learning_rate": 9.970756579820562e-06, "loss": 0.1046, "step": 1410 }, { "epoch": 1.9880994049702485, "grad_norm": 0.15937501192092896, "learning_rate": 9.968970248897233e-06, "loss": 0.1141, "step": 1420 }, { "epoch": 1.99929996499825, "eval_f1": 0.9405169889195438, "eval_loss": 0.16149015724658966, "eval_precision": 0.9404955962490559, "eval_recall": 0.940517844646606, "eval_runtime": 85.7404, "eval_samples_per_second": 16.667, "eval_steps_per_second": 8.339, "step": 1428 }, { "epoch": 2.0021001050052503, "grad_norm": 0.22882509231567383, "learning_rate": 9.96713113403484e-06, "loss": 0.0945, "step": 1430 }, { "epoch": 2.016100805040252, "grad_norm": 9.80128288269043, "learning_rate": 9.965239254769764e-06, "loss": 0.0908, "step": 1440 }, { "epoch": 2.0301015050752538, "grad_norm": 4.904554843902588, "learning_rate": 9.963294631198897e-06, "loss": 0.0313, "step": 1450 }, { "epoch": 2.0441022051102555, "grad_norm": 30.783597946166992, "learning_rate": 9.961297283979413e-06, "loss": 0.1126, "step": 1460 }, { "epoch": 2.0581029051452573, "grad_norm": 17.089374542236328, "learning_rate": 9.959247234328556e-06, "loss": 0.1442, "step": 1470 }, { "epoch": 2.072103605180259, "grad_norm": 0.05348501354455948, "learning_rate": 9.957144504023413e-06, "loss": 0.0121, "step": 1480 }, { "epoch": 2.086104305215261, "grad_norm": 2.584078550338745, "learning_rate": 9.954989115400684e-06, "loss": 0.1215, "step": 1490 }, { "epoch": 2.1001050052502626, "grad_norm": 0.12374909967184067, "learning_rate": 9.952781091356439e-06, "loss": 0.0125, "step": 1500 }, { "epoch": 2.1141057052852643, "grad_norm": 73.67182922363281, "learning_rate": 9.95052045534588e-06, "loss": 0.2536, "step": 1510 }, { "epoch": 2.128106405320266, "grad_norm": 27.475414276123047, "learning_rate": 9.948207231383094e-06, "loss": 0.3477, "step": 1520 }, { "epoch": 2.142107105355268, "grad_norm": 0.2636147141456604, "learning_rate": 9.945841444040793e-06, "loss": 0.041, "step": 1530 }, { "epoch": 2.1561078053902696, "grad_norm": 35.20915985107422, "learning_rate": 9.943423118450051e-06, "loss": 0.0535, "step": 1540 }, { "epoch": 2.1701085054252713, "grad_norm": 0.16824166476726532, "learning_rate": 9.940952280300049e-06, "loss": 0.0332, "step": 1550 }, { "epoch": 2.184109205460273, "grad_norm": 0.11545979231595993, "learning_rate": 9.938428955837785e-06, "loss": 0.0857, "step": 1560 }, { "epoch": 2.198109905495275, "grad_norm": 0.8021575808525085, "learning_rate": 9.935853171867807e-06, "loss": 0.0974, "step": 1570 }, { "epoch": 2.2121106055302766, "grad_norm": 2.349532127380371, "learning_rate": 9.933224955751929e-06, "loss": 0.0452, "step": 1580 }, { "epoch": 2.2261113055652784, "grad_norm": 0.620644211769104, "learning_rate": 9.930544335408931e-06, "loss": 0.0929, "step": 1590 }, { "epoch": 2.24011200560028, "grad_norm": 0.02595665119588375, "learning_rate": 9.927811339314272e-06, "loss": 0.1078, "step": 1600 }, { "epoch": 2.254112705635282, "grad_norm": 31.513547897338867, "learning_rate": 9.92502599649978e-06, "loss": 0.336, "step": 1610 }, { "epoch": 2.2681134056702836, "grad_norm": 8.418824195861816, "learning_rate": 9.922188336553351e-06, "loss": 0.1468, "step": 1620 }, { "epoch": 2.2821141057052854, "grad_norm": 0.19196270406246185, "learning_rate": 9.919298389618628e-06, "loss": 0.0518, "step": 1630 }, { "epoch": 2.296114805740287, "grad_norm": 86.77196502685547, "learning_rate": 9.916356186394684e-06, "loss": 0.0622, "step": 1640 }, { "epoch": 2.310115505775289, "grad_norm": 12.014430046081543, "learning_rate": 9.913361758135697e-06, "loss": 0.186, "step": 1650 }, { "epoch": 2.3241162058102907, "grad_norm": 4.975588321685791, "learning_rate": 9.910315136650614e-06, "loss": 0.1345, "step": 1660 }, { "epoch": 2.3381169058452924, "grad_norm": 0.15552039444446564, "learning_rate": 9.90721635430282e-06, "loss": 0.0215, "step": 1670 }, { "epoch": 2.352117605880294, "grad_norm": 24.961191177368164, "learning_rate": 9.904065444009785e-06, "loss": 0.1216, "step": 1680 }, { "epoch": 2.366118305915296, "grad_norm": 4.592883110046387, "learning_rate": 9.900862439242719e-06, "loss": 0.1366, "step": 1690 }, { "epoch": 2.3801190059502977, "grad_norm": 0.4605049192905426, "learning_rate": 9.897607374026223e-06, "loss": 0.0946, "step": 1700 }, { "epoch": 2.3941197059852994, "grad_norm": 1.254657506942749, "learning_rate": 9.894300282937915e-06, "loss": 0.042, "step": 1710 }, { "epoch": 2.408120406020301, "grad_norm": 0.14538034796714783, "learning_rate": 9.890941201108069e-06, "loss": 0.0559, "step": 1720 }, { "epoch": 2.422121106055303, "grad_norm": 3.5109119415283203, "learning_rate": 9.887530164219246e-06, "loss": 0.1131, "step": 1730 }, { "epoch": 2.4361218060903047, "grad_norm": 3.36604380607605, "learning_rate": 9.884067208505905e-06, "loss": 0.0274, "step": 1740 }, { "epoch": 2.4501225061253065, "grad_norm": 37.22677993774414, "learning_rate": 9.88055237075403e-06, "loss": 0.0846, "step": 1750 }, { "epoch": 2.464123206160308, "grad_norm": 4.4809651374816895, "learning_rate": 9.876985688300724e-06, "loss": 0.0349, "step": 1760 }, { "epoch": 2.47812390619531, "grad_norm": 85.08074951171875, "learning_rate": 9.873367199033834e-06, "loss": 0.1417, "step": 1770 }, { "epoch": 2.4921246062303117, "grad_norm": 16.589052200317383, "learning_rate": 9.869696941391525e-06, "loss": 0.1312, "step": 1780 }, { "epoch": 2.5061253062653135, "grad_norm": 15.452710151672363, "learning_rate": 9.865974954361885e-06, "loss": 0.0609, "step": 1790 }, { "epoch": 2.5201260063003152, "grad_norm": 0.2092599719762802, "learning_rate": 9.862201277482513e-06, "loss": 0.0776, "step": 1800 }, { "epoch": 2.534126706335317, "grad_norm": 0.01015313621610403, "learning_rate": 9.85837595084009e-06, "loss": 0.0674, "step": 1810 }, { "epoch": 2.5481274063703188, "grad_norm": 0.03218379244208336, "learning_rate": 9.854499015069955e-06, "loss": 0.037, "step": 1820 }, { "epoch": 2.5621281064053205, "grad_norm": 13.874772071838379, "learning_rate": 9.850570511355686e-06, "loss": 0.0864, "step": 1830 }, { "epoch": 2.5761288064403223, "grad_norm": 0.4755847752094269, "learning_rate": 9.846590481428639e-06, "loss": 0.0984, "step": 1840 }, { "epoch": 2.590129506475324, "grad_norm": 0.3224013149738312, "learning_rate": 9.842558967567531e-06, "loss": 0.0818, "step": 1850 }, { "epoch": 2.604130206510326, "grad_norm": 0.0649426281452179, "learning_rate": 9.838476012597969e-06, "loss": 0.0538, "step": 1860 }, { "epoch": 2.6181309065453275, "grad_norm": 14.650222778320312, "learning_rate": 9.834341659892007e-06, "loss": 0.1298, "step": 1870 }, { "epoch": 2.632131606580329, "grad_norm": 0.07487118244171143, "learning_rate": 9.830155953367684e-06, "loss": 0.0178, "step": 1880 }, { "epoch": 2.6461323066153306, "grad_norm": 0.08998718857765198, "learning_rate": 9.82591893748855e-06, "loss": 0.1297, "step": 1890 }, { "epoch": 2.6601330066503324, "grad_norm": 1.421534538269043, "learning_rate": 9.821630657263211e-06, "loss": 0.1277, "step": 1900 }, { "epoch": 2.674133706685334, "grad_norm": 0.007493593730032444, "learning_rate": 9.817291158244825e-06, "loss": 0.0734, "step": 1910 }, { "epoch": 2.688134406720336, "grad_norm": 7.475185394287109, "learning_rate": 9.812900486530643e-06, "loss": 0.0623, "step": 1920 }, { "epoch": 2.7021351067553376, "grad_norm": 23.813947677612305, "learning_rate": 9.808458688761507e-06, "loss": 0.1739, "step": 1930 }, { "epoch": 2.7161358067903394, "grad_norm": 0.08445608615875244, "learning_rate": 9.80396581212135e-06, "loss": 0.0465, "step": 1940 }, { "epoch": 2.730136506825341, "grad_norm": 0.16602131724357605, "learning_rate": 9.799421904336709e-06, "loss": 0.1728, "step": 1950 }, { "epoch": 2.744137206860343, "grad_norm": 5.605527877807617, "learning_rate": 9.794827013676206e-06, "loss": 0.0888, "step": 1960 }, { "epoch": 2.7581379068953447, "grad_norm": 0.016257012262940407, "learning_rate": 9.790181188950043e-06, "loss": 0.021, "step": 1970 }, { "epoch": 2.7721386069303464, "grad_norm": 0.015474709682166576, "learning_rate": 9.785484479509472e-06, "loss": 0.1041, "step": 1980 }, { "epoch": 2.786139306965348, "grad_norm": 0.18694552779197693, "learning_rate": 9.780736935246292e-06, "loss": 0.2925, "step": 1990 }, { "epoch": 2.80014000700035, "grad_norm": 0.2058991640806198, "learning_rate": 9.775938606592287e-06, "loss": 0.09, "step": 2000 }, { "epoch": 2.8141407070353517, "grad_norm": 0.6892361640930176, "learning_rate": 9.771089544518729e-06, "loss": 0.0446, "step": 2010 }, { "epoch": 2.8281414070703534, "grad_norm": 0.04991542920470238, "learning_rate": 9.766189800535803e-06, "loss": 0.089, "step": 2020 }, { "epoch": 2.842142107105355, "grad_norm": 3.87736439704895, "learning_rate": 9.761239426692077e-06, "loss": 0.0798, "step": 2030 }, { "epoch": 2.856142807140357, "grad_norm": 0.036107420921325684, "learning_rate": 9.756238475573947e-06, "loss": 0.0641, "step": 2040 }, { "epoch": 2.8701435071753587, "grad_norm": 0.6231482625007629, "learning_rate": 9.751187000305076e-06, "loss": 0.071, "step": 2050 }, { "epoch": 2.8841442072103605, "grad_norm": 0.014469561167061329, "learning_rate": 9.746085054545829e-06, "loss": 0.0645, "step": 2060 }, { "epoch": 2.8981449072453622, "grad_norm": 0.029857950285077095, "learning_rate": 9.740932692492705e-06, "loss": 0.0221, "step": 2070 }, { "epoch": 2.912145607280364, "grad_norm": 0.03372916206717491, "learning_rate": 9.735729968877763e-06, "loss": 0.099, "step": 2080 }, { "epoch": 2.9261463073153657, "grad_norm": 40.68704605102539, "learning_rate": 9.730476938968037e-06, "loss": 0.0539, "step": 2090 }, { "epoch": 2.9401470073503675, "grad_norm": 0.22137188911437988, "learning_rate": 9.725173658564948e-06, "loss": 0.0521, "step": 2100 }, { "epoch": 2.9541477073853692, "grad_norm": 0.17224650084972382, "learning_rate": 9.719820184003716e-06, "loss": 0.0558, "step": 2110 }, { "epoch": 2.968148407420371, "grad_norm": 0.216918483376503, "learning_rate": 9.714416572152758e-06, "loss": 0.0414, "step": 2120 }, { "epoch": 2.9821491074553728, "grad_norm": 6.288044452667236, "learning_rate": 9.708962880413088e-06, "loss": 0.0984, "step": 2130 }, { "epoch": 2.9961498074903745, "grad_norm": 0.015979696065187454, "learning_rate": 9.703459166717701e-06, "loss": 0.0483, "step": 2140 }, { "epoch": 2.998949947497375, "eval_f1": 0.9439567208197156, "eval_loss": 0.16459082067012787, "eval_precision": 0.9424573482270827, "eval_recall": 0.9440167949615116, "eval_runtime": 85.5476, "eval_samples_per_second": 16.704, "eval_steps_per_second": 8.358, "step": 2142 }, { "epoch": 3.0101505075253763, "grad_norm": 0.030147364363074303, "learning_rate": 9.697905489530962e-06, "loss": 0.0517, "step": 2150 }, { "epoch": 3.024151207560378, "grad_norm": 0.12278366088867188, "learning_rate": 9.692301907847981e-06, "loss": 0.0017, "step": 2160 }, { "epoch": 3.03815190759538, "grad_norm": 1.394048810005188, "learning_rate": 9.686648481193994e-06, "loss": 0.0195, "step": 2170 }, { "epoch": 3.0521526076303815, "grad_norm": 0.3854627013206482, "learning_rate": 9.68094526962372e-06, "loss": 0.0932, "step": 2180 }, { "epoch": 3.0661533076653833, "grad_norm": 0.019702697172760963, "learning_rate": 9.675192333720735e-06, "loss": 0.1094, "step": 2190 }, { "epoch": 3.080154007700385, "grad_norm": 0.032759979367256165, "learning_rate": 9.669389734596819e-06, "loss": 0.1292, "step": 2200 }, { "epoch": 3.094154707735387, "grad_norm": 73.04602813720703, "learning_rate": 9.66353753389131e-06, "loss": 0.0889, "step": 2210 }, { "epoch": 3.1081554077703886, "grad_norm": 1.0851781368255615, "learning_rate": 9.65763579377045e-06, "loss": 0.0102, "step": 2220 }, { "epoch": 3.1221561078053903, "grad_norm": 0.02348620630800724, "learning_rate": 9.651684576926721e-06, "loss": 0.0526, "step": 2230 }, { "epoch": 3.136156807840392, "grad_norm": 0.0017571039497852325, "learning_rate": 9.645683946578189e-06, "loss": 0.0792, "step": 2240 }, { "epoch": 3.150157507875394, "grad_norm": 0.04782587289810181, "learning_rate": 9.639633966467817e-06, "loss": 0.0505, "step": 2250 }, { "epoch": 3.1641582079103956, "grad_norm": 0.854295551776886, "learning_rate": 9.633534700862804e-06, "loss": 0.011, "step": 2260 }, { "epoch": 3.1781589079453973, "grad_norm": 29.275421142578125, "learning_rate": 9.627386214553886e-06, "loss": 0.0132, "step": 2270 }, { "epoch": 3.192159607980399, "grad_norm": 7.652329444885254, "learning_rate": 9.621188572854668e-06, "loss": 0.0817, "step": 2280 }, { "epoch": 3.206160308015401, "grad_norm": 0.05205431953072548, "learning_rate": 9.614941841600905e-06, "loss": 0.064, "step": 2290 }, { "epoch": 3.2201610080504026, "grad_norm": 0.006069015711545944, "learning_rate": 9.608646087149826e-06, "loss": 0.1078, "step": 2300 }, { "epoch": 3.2341617080854044, "grad_norm": 0.04892052710056305, "learning_rate": 9.60230137637942e-06, "loss": 0.0643, "step": 2310 }, { "epoch": 3.248162408120406, "grad_norm": 7.19106388092041, "learning_rate": 9.595907776687715e-06, "loss": 0.0014, "step": 2320 }, { "epoch": 3.262163108155408, "grad_norm": 10.295150756835938, "learning_rate": 9.58946535599208e-06, "loss": 0.0847, "step": 2330 }, { "epoch": 3.2761638081904096, "grad_norm": 111.84056854248047, "learning_rate": 9.582974182728497e-06, "loss": 0.1459, "step": 2340 }, { "epoch": 3.2901645082254114, "grad_norm": 4.704950332641602, "learning_rate": 9.576434325850824e-06, "loss": 0.0405, "step": 2350 }, { "epoch": 3.304165208260413, "grad_norm": 0.4798479676246643, "learning_rate": 9.56984585483008e-06, "loss": 0.0535, "step": 2360 }, { "epoch": 3.318165908295415, "grad_norm": 0.06830032169818878, "learning_rate": 9.56320883965369e-06, "loss": 0.1739, "step": 2370 }, { "epoch": 3.3321666083304167, "grad_norm": 1.7860515117645264, "learning_rate": 9.556523350824759e-06, "loss": 0.0327, "step": 2380 }, { "epoch": 3.3461673083654184, "grad_norm": 0.03282421454787254, "learning_rate": 9.549789459361303e-06, "loss": 0.0985, "step": 2390 }, { "epoch": 3.36016800840042, "grad_norm": 0.0977889746427536, "learning_rate": 9.543007236795513e-06, "loss": 0.0634, "step": 2400 }, { "epoch": 3.374168708435422, "grad_norm": 0.7682515382766724, "learning_rate": 9.536176755172988e-06, "loss": 0.1193, "step": 2410 }, { "epoch": 3.3881694084704237, "grad_norm": 0.010290628299117088, "learning_rate": 9.52929808705196e-06, "loss": 0.0047, "step": 2420 }, { "epoch": 3.4021701085054254, "grad_norm": 0.04401390254497528, "learning_rate": 9.522371305502542e-06, "loss": 0.0266, "step": 2430 }, { "epoch": 3.416170808540427, "grad_norm": 18.24448013305664, "learning_rate": 9.515396484105938e-06, "loss": 0.2168, "step": 2440 }, { "epoch": 3.430171508575429, "grad_norm": 3.006004571914673, "learning_rate": 9.508373696953664e-06, "loss": 0.0812, "step": 2450 }, { "epoch": 3.4441722086104303, "grad_norm": 0.4662695527076721, "learning_rate": 9.501303018646766e-06, "loss": 0.001, "step": 2460 }, { "epoch": 3.458172908645432, "grad_norm": 0.026914849877357483, "learning_rate": 9.494184524295023e-06, "loss": 0.0834, "step": 2470 }, { "epoch": 3.472173608680434, "grad_norm": 31.83331298828125, "learning_rate": 9.487018289516146e-06, "loss": 0.0091, "step": 2480 }, { "epoch": 3.4861743087154355, "grad_norm": 0.003149577882140875, "learning_rate": 9.479804390434983e-06, "loss": 0.0109, "step": 2490 }, { "epoch": 3.5001750087504373, "grad_norm": 24.41321563720703, "learning_rate": 9.472542903682708e-06, "loss": 0.0085, "step": 2500 }, { "epoch": 3.514175708785439, "grad_norm": 0.015754742547869682, "learning_rate": 9.465233906395998e-06, "loss": 0.0667, "step": 2510 }, { "epoch": 3.528176408820441, "grad_norm": 0.012419297359883785, "learning_rate": 9.457877476216228e-06, "loss": 0.0599, "step": 2520 }, { "epoch": 3.5421771088554426, "grad_norm": 65.708984375, "learning_rate": 9.450473691288637e-06, "loss": 0.0873, "step": 2530 }, { "epoch": 3.5561778088904443, "grad_norm": 0.09007327258586884, "learning_rate": 9.443022630261495e-06, "loss": 0.0203, "step": 2540 }, { "epoch": 3.570178508925446, "grad_norm": 1.3261775970458984, "learning_rate": 9.435524372285279e-06, "loss": 0.0507, "step": 2550 }, { "epoch": 3.584179208960448, "grad_norm": 0.07640054076910019, "learning_rate": 9.42797899701182e-06, "loss": 0.0875, "step": 2560 }, { "epoch": 3.5981799089954496, "grad_norm": 0.007880746386945248, "learning_rate": 9.420386584593469e-06, "loss": 0.0329, "step": 2570 }, { "epoch": 3.6121806090304514, "grad_norm": 0.0786275640130043, "learning_rate": 9.412747215682231e-06, "loss": 0.089, "step": 2580 }, { "epoch": 3.626181309065453, "grad_norm": 0.0043255346827209, "learning_rate": 9.405060971428924e-06, "loss": 0.0878, "step": 2590 }, { "epoch": 3.640182009100455, "grad_norm": 0.3558666408061981, "learning_rate": 9.397327933482303e-06, "loss": 0.0578, "step": 2600 }, { "epoch": 3.6541827091354566, "grad_norm": 13.108118057250977, "learning_rate": 9.389548183988204e-06, "loss": 0.0592, "step": 2610 }, { "epoch": 3.6681834091704584, "grad_norm": 0.004170840140432119, "learning_rate": 9.381721805588663e-06, "loss": 0.0787, "step": 2620 }, { "epoch": 3.68218410920546, "grad_norm": 3.8345985412597656, "learning_rate": 9.373848881421045e-06, "loss": 0.0259, "step": 2630 }, { "epoch": 3.696184809240462, "grad_norm": 0.04699714854359627, "learning_rate": 9.36592949511715e-06, "loss": 0.0474, "step": 2640 }, { "epoch": 3.7101855092754636, "grad_norm": 0.024606017395853996, "learning_rate": 9.35796373080234e-06, "loss": 0.0043, "step": 2650 }, { "epoch": 3.7241862093104654, "grad_norm": 0.39088472723960876, "learning_rate": 9.349951673094633e-06, "loss": 0.0471, "step": 2660 }, { "epoch": 3.738186909345467, "grad_norm": 0.029532933607697487, "learning_rate": 9.341893407103808e-06, "loss": 0.061, "step": 2670 }, { "epoch": 3.752187609380469, "grad_norm": 6.01865816116333, "learning_rate": 9.333789018430505e-06, "loss": 0.038, "step": 2680 }, { "epoch": 3.7661883094154707, "grad_norm": 0.9192459583282471, "learning_rate": 9.325638593165308e-06, "loss": 0.0417, "step": 2690 }, { "epoch": 3.7801890094504724, "grad_norm": 0.4111453890800476, "learning_rate": 9.317442217887835e-06, "loss": 0.0358, "step": 2700 }, { "epoch": 3.794189709485474, "grad_norm": 0.17047695815563202, "learning_rate": 9.309199979665821e-06, "loss": 0.0528, "step": 2710 }, { "epoch": 3.808190409520476, "grad_norm": 0.09648007899522781, "learning_rate": 9.300911966054184e-06, "loss": 0.0862, "step": 2720 }, { "epoch": 3.8221911095554777, "grad_norm": 61.79411315917969, "learning_rate": 9.292578265094109e-06, "loss": 0.0682, "step": 2730 }, { "epoch": 3.8361918095904795, "grad_norm": 0.0917210653424263, "learning_rate": 9.284198965312096e-06, "loss": 0.0035, "step": 2740 }, { "epoch": 3.850192509625481, "grad_norm": 4.736217498779297, "learning_rate": 9.275774155719032e-06, "loss": 0.0184, "step": 2750 }, { "epoch": 3.864193209660483, "grad_norm": 0.051652390509843826, "learning_rate": 9.267303925809246e-06, "loss": 0.0562, "step": 2760 }, { "epoch": 3.8781939096954847, "grad_norm": 4.532809257507324, "learning_rate": 9.258788365559543e-06, "loss": 0.0089, "step": 2770 }, { "epoch": 3.8921946097304865, "grad_norm": 0.05398925766348839, "learning_rate": 9.25022756542827e-06, "loss": 0.0032, "step": 2780 }, { "epoch": 3.9061953097654882, "grad_norm": 49.33939743041992, "learning_rate": 9.24162161635434e-06, "loss": 0.1271, "step": 2790 }, { "epoch": 3.92019600980049, "grad_norm": 0.09320775419473648, "learning_rate": 9.232970609756267e-06, "loss": 0.1672, "step": 2800 }, { "epoch": 3.9341967098354917, "grad_norm": 109.32254791259766, "learning_rate": 9.224274637531204e-06, "loss": 0.1793, "step": 2810 }, { "epoch": 3.9481974098704935, "grad_norm": 0.11961990594863892, "learning_rate": 9.215533792053957e-06, "loss": 0.0838, "step": 2820 }, { "epoch": 3.9621981099054953, "grad_norm": 2.1533560752868652, "learning_rate": 9.20674816617601e-06, "loss": 0.0522, "step": 2830 }, { "epoch": 3.976198809940497, "grad_norm": 0.02157438173890114, "learning_rate": 9.197917853224531e-06, "loss": 0.0747, "step": 2840 }, { "epoch": 3.9901995099754988, "grad_norm": 0.005027266219258308, "learning_rate": 9.189042947001395e-06, "loss": 0.056, "step": 2850 }, { "epoch": 4.0, "eval_f1": 0.9502738893213575, "eval_loss": 0.1555524319410324, "eval_precision": 0.9492496335924279, "eval_recall": 0.9503149055283415, "eval_runtime": 85.5789, "eval_samples_per_second": 16.698, "eval_steps_per_second": 8.355, "step": 2857 }, { "epoch": 4.0042002100105005, "grad_norm": 2.6012561321258545, "learning_rate": 9.180123541782172e-06, "loss": 0.0626, "step": 2860 }, { "epoch": 4.018200910045502, "grad_norm": 0.03805302456021309, "learning_rate": 9.171159732315129e-06, "loss": 0.0306, "step": 2870 }, { "epoch": 4.032201610080504, "grad_norm": 0.02099209651350975, "learning_rate": 9.162151613820236e-06, "loss": 0.005, "step": 2880 }, { "epoch": 4.046202310115506, "grad_norm": 6.755284786224365, "learning_rate": 9.153099281988138e-06, "loss": 0.0276, "step": 2890 }, { "epoch": 4.0602030101505076, "grad_norm": 0.10712507367134094, "learning_rate": 9.144002832979149e-06, "loss": 0.0385, "step": 2900 }, { "epoch": 4.074203710185509, "grad_norm": 0.017589423805475235, "learning_rate": 9.134862363422223e-06, "loss": 0.0196, "step": 2910 }, { "epoch": 4.088204410220511, "grad_norm": 1.701547384262085, "learning_rate": 9.125677970413935e-06, "loss": 0.0195, "step": 2920 }, { "epoch": 4.102205110255513, "grad_norm": 0.546120285987854, "learning_rate": 9.116449751517448e-06, "loss": 0.029, "step": 2930 }, { "epoch": 4.116205810290515, "grad_norm": 0.008883952163159847, "learning_rate": 9.107177804761468e-06, "loss": 0.0012, "step": 2940 }, { "epoch": 4.130206510325516, "grad_norm": 0.0017636914271861315, "learning_rate": 9.097862228639216e-06, "loss": 0.0006, "step": 2950 }, { "epoch": 4.144207210360518, "grad_norm": 0.03372401371598244, "learning_rate": 9.088503122107371e-06, "loss": 0.0002, "step": 2960 }, { "epoch": 4.15820791039552, "grad_norm": 0.03106401488184929, "learning_rate": 9.079100584585027e-06, "loss": 0.0606, "step": 2970 }, { "epoch": 4.172208610430522, "grad_norm": 6.889786720275879, "learning_rate": 9.06965471595263e-06, "loss": 0.0372, "step": 2980 }, { "epoch": 4.186209310465523, "grad_norm": 0.10271060466766357, "learning_rate": 9.060165616550918e-06, "loss": 0.0517, "step": 2990 }, { "epoch": 4.200210010500525, "grad_norm": 0.1456887125968933, "learning_rate": 9.050633387179861e-06, "loss": 0.0289, "step": 3000 }, { "epoch": 4.214210710535527, "grad_norm": 1.0142897367477417, "learning_rate": 9.041058129097586e-06, "loss": 0.0866, "step": 3010 }, { "epoch": 4.228211410570529, "grad_norm": 0.005523073021322489, "learning_rate": 9.031439944019302e-06, "loss": 0.1116, "step": 3020 }, { "epoch": 4.24221211060553, "grad_norm": 36.47334289550781, "learning_rate": 9.021778934116212e-06, "loss": 0.0188, "step": 3030 }, { "epoch": 4.256212810640532, "grad_norm": 0.0005946714081801474, "learning_rate": 9.012075202014444e-06, "loss": 0.0291, "step": 3040 }, { "epoch": 4.270213510675534, "grad_norm": 0.0017927681328728795, "learning_rate": 9.002328850793946e-06, "loss": 0.0002, "step": 3050 }, { "epoch": 4.284214210710536, "grad_norm": 0.015693560242652893, "learning_rate": 8.992539983987401e-06, "loss": 0.0528, "step": 3060 }, { "epoch": 4.298214910745537, "grad_norm": 0.028800832107663155, "learning_rate": 8.982708705579119e-06, "loss": 0.0598, "step": 3070 }, { "epoch": 4.312215610780539, "grad_norm": 0.012344347313046455, "learning_rate": 8.972835120003936e-06, "loss": 0.0687, "step": 3080 }, { "epoch": 4.326216310815541, "grad_norm": 0.6642976403236389, "learning_rate": 8.962919332146107e-06, "loss": 0.0349, "step": 3090 }, { "epoch": 4.340217010850543, "grad_norm": 0.03467980772256851, "learning_rate": 8.952961447338192e-06, "loss": 0.0012, "step": 3100 }, { "epoch": 4.354217710885544, "grad_norm": 0.023241745308041573, "learning_rate": 8.942961571359927e-06, "loss": 0.0905, "step": 3110 }, { "epoch": 4.368218410920546, "grad_norm": 65.47942352294922, "learning_rate": 8.932919810437117e-06, "loss": 0.1127, "step": 3120 }, { "epoch": 4.382219110955548, "grad_norm": 0.06475795060396194, "learning_rate": 8.92283627124049e-06, "loss": 0.0241, "step": 3130 }, { "epoch": 4.39621981099055, "grad_norm": 0.0579422190785408, "learning_rate": 8.912711060884585e-06, "loss": 0.0002, "step": 3140 }, { "epoch": 4.4102205110255515, "grad_norm": 0.030872151255607605, "learning_rate": 8.902544286926585e-06, "loss": 0.0002, "step": 3150 }, { "epoch": 4.424221211060553, "grad_norm": 0.020232750102877617, "learning_rate": 8.892336057365204e-06, "loss": 0.0917, "step": 3160 }, { "epoch": 4.438221911095555, "grad_norm": 0.010859241709113121, "learning_rate": 8.882086480639526e-06, "loss": 0.1093, "step": 3170 }, { "epoch": 4.452222611130557, "grad_norm": 0.030299527570605278, "learning_rate": 8.871795665627845e-06, "loss": 0.0634, "step": 3180 }, { "epoch": 4.4662233111655585, "grad_norm": 1.2195743322372437, "learning_rate": 8.861463721646528e-06, "loss": 0.0005, "step": 3190 }, { "epoch": 4.48022401120056, "grad_norm": 0.06468135863542557, "learning_rate": 8.851090758448836e-06, "loss": 0.0717, "step": 3200 }, { "epoch": 4.494224711235562, "grad_norm": 0.1307636797428131, "learning_rate": 8.840676886223768e-06, "loss": 0.0716, "step": 3210 }, { "epoch": 4.508225411270564, "grad_norm": 0.06059357896447182, "learning_rate": 8.83022221559489e-06, "loss": 0.0375, "step": 3220 }, { "epoch": 4.5222261113055655, "grad_norm": 0.013207100331783295, "learning_rate": 8.819726857619156e-06, "loss": 0.0492, "step": 3230 }, { "epoch": 4.536226811340567, "grad_norm": 0.020494362339377403, "learning_rate": 8.809190923785724e-06, "loss": 0.0175, "step": 3240 }, { "epoch": 4.550227511375569, "grad_norm": 0.04863560572266579, "learning_rate": 8.798614526014786e-06, "loss": 0.1044, "step": 3250 }, { "epoch": 4.564228211410571, "grad_norm": 0.000641553255263716, "learning_rate": 8.78799777665637e-06, "loss": 0.0706, "step": 3260 }, { "epoch": 4.5782289114455725, "grad_norm": 0.1729791760444641, "learning_rate": 8.777340788489145e-06, "loss": 0.0544, "step": 3270 }, { "epoch": 4.592229611480574, "grad_norm": 0.32355839014053345, "learning_rate": 8.76664367471922e-06, "loss": 0.0785, "step": 3280 }, { "epoch": 4.606230311515576, "grad_norm": 1.423351526260376, "learning_rate": 8.755906548978957e-06, "loss": 0.0126, "step": 3290 }, { "epoch": 4.620231011550578, "grad_norm": 15.19318962097168, "learning_rate": 8.745129525325746e-06, "loss": 0.0809, "step": 3300 }, { "epoch": 4.63423171158558, "grad_norm": 24.36188316345215, "learning_rate": 8.734312718240807e-06, "loss": 0.0907, "step": 3310 }, { "epoch": 4.648232411620581, "grad_norm": 0.013152498751878738, "learning_rate": 8.723456242627961e-06, "loss": 0.0869, "step": 3320 }, { "epoch": 4.662233111655583, "grad_norm": 0.017324671149253845, "learning_rate": 8.712560213812421e-06, "loss": 0.0513, "step": 3330 }, { "epoch": 4.676233811690585, "grad_norm": 0.044183555990457535, "learning_rate": 8.701624747539563e-06, "loss": 0.0209, "step": 3340 }, { "epoch": 4.690234511725587, "grad_norm": 0.001150390598922968, "learning_rate": 8.690649959973693e-06, "loss": 0.0266, "step": 3350 }, { "epoch": 4.704235211760588, "grad_norm": 0.005500374361872673, "learning_rate": 8.679635967696815e-06, "loss": 0.0332, "step": 3360 }, { "epoch": 4.71823591179559, "grad_norm": 0.07724996656179428, "learning_rate": 8.6685828877074e-06, "loss": 0.0403, "step": 3370 }, { "epoch": 4.732236611830592, "grad_norm": 0.20006419718265533, "learning_rate": 8.657490837419124e-06, "loss": 0.0808, "step": 3380 }, { "epoch": 4.746237311865594, "grad_norm": 1.35878324508667, "learning_rate": 8.646359934659648e-06, "loss": 0.0544, "step": 3390 }, { "epoch": 4.760238011900595, "grad_norm": 4.547935962677002, "learning_rate": 8.63519029766934e-06, "loss": 0.0756, "step": 3400 }, { "epoch": 4.774238711935597, "grad_norm": 0.7724612951278687, "learning_rate": 8.623982045100037e-06, "loss": 0.0283, "step": 3410 }, { "epoch": 4.788239411970599, "grad_norm": 0.037291232496500015, "learning_rate": 8.612735296013777e-06, "loss": 0.0903, "step": 3420 }, { "epoch": 4.802240112005601, "grad_norm": 4.7362565994262695, "learning_rate": 8.601450169881533e-06, "loss": 0.0344, "step": 3430 }, { "epoch": 4.816240812040602, "grad_norm": 3.896909713745117, "learning_rate": 8.590126786581948e-06, "loss": 0.0117, "step": 3440 }, { "epoch": 4.830241512075604, "grad_norm": 0.0022337951231747866, "learning_rate": 8.57876526640006e-06, "loss": 0.1031, "step": 3450 }, { "epoch": 4.844242212110606, "grad_norm": 11.048283576965332, "learning_rate": 8.567365730026025e-06, "loss": 0.0687, "step": 3460 }, { "epoch": 4.858242912145608, "grad_norm": 0.5430986285209656, "learning_rate": 8.55592829855383e-06, "loss": 0.0284, "step": 3470 }, { "epoch": 4.872243612180609, "grad_norm": 10.159993171691895, "learning_rate": 8.544453093480017e-06, "loss": 0.0261, "step": 3480 }, { "epoch": 4.886244312215611, "grad_norm": 0.057509321719408035, "learning_rate": 8.53294023670238e-06, "loss": 0.0031, "step": 3490 }, { "epoch": 4.900245012250613, "grad_norm": 28.648855209350586, "learning_rate": 8.521389850518682e-06, "loss": 0.0544, "step": 3500 }, { "epoch": 4.914245712285615, "grad_norm": 3.066316604614258, "learning_rate": 8.509802057625345e-06, "loss": 0.0143, "step": 3510 }, { "epoch": 4.928246412320616, "grad_norm": 0.005794500466436148, "learning_rate": 8.498176981116152e-06, "loss": 0.0044, "step": 3520 }, { "epoch": 4.942247112355618, "grad_norm": 33.897499084472656, "learning_rate": 8.486514744480946e-06, "loss": 0.103, "step": 3530 }, { "epoch": 4.95624781239062, "grad_norm": 18.55446434020996, "learning_rate": 8.474815471604303e-06, "loss": 0.0672, "step": 3540 }, { "epoch": 4.970248512425622, "grad_norm": 0.018390638753771782, "learning_rate": 8.463079286764224e-06, "loss": 0.0698, "step": 3550 }, { "epoch": 4.9842492124606235, "grad_norm": 14.878451347351074, "learning_rate": 8.451306314630825e-06, "loss": 0.0149, "step": 3560 }, { "epoch": 4.998249912495625, "grad_norm": 0.10592308640480042, "learning_rate": 8.439496680264993e-06, "loss": 0.0257, "step": 3570 }, { "epoch": 4.999649982499125, "eval_f1": 0.9530601608778744, "eval_loss": 0.1417933851480484, "eval_precision": 0.9517145171612903, "eval_recall": 0.9531140657802659, "eval_runtime": 85.6287, "eval_samples_per_second": 16.688, "eval_steps_per_second": 8.35, "step": 3571 }, { "epoch": 5.012250612530626, "grad_norm": 0.3304142653942108, "learning_rate": 8.42765050911707e-06, "loss": 0.002, "step": 3580 }, { "epoch": 5.026251312565628, "grad_norm": 0.0006598730105906725, "learning_rate": 8.41576792702552e-06, "loss": 0.0491, "step": 3590 }, { "epoch": 5.04025201260063, "grad_norm": 5.164649486541748, "learning_rate": 8.403849060215587e-06, "loss": 0.0065, "step": 3600 }, { "epoch": 5.054252712635631, "grad_norm": 0.1107124462723732, "learning_rate": 8.391894035297962e-06, "loss": 0.0118, "step": 3610 }, { "epoch": 5.068253412670633, "grad_norm": 0.0056930468417704105, "learning_rate": 8.379902979267424e-06, "loss": 0.0151, "step": 3620 }, { "epoch": 5.082254112705635, "grad_norm": 0.004092092160135508, "learning_rate": 8.367876019501512e-06, "loss": 0.0005, "step": 3630 }, { "epoch": 5.096254812740637, "grad_norm": 0.008662878535687923, "learning_rate": 8.35581328375915e-06, "loss": 0.001, "step": 3640 }, { "epoch": 5.110255512775638, "grad_norm": 0.002947417553514242, "learning_rate": 8.343714900179304e-06, "loss": 0.0244, "step": 3650 }, { "epoch": 5.12425621281064, "grad_norm": 32.711063385009766, "learning_rate": 8.331580997279616e-06, "loss": 0.0394, "step": 3660 }, { "epoch": 5.138256912845642, "grad_norm": 21.720970153808594, "learning_rate": 8.319411703955042e-06, "loss": 0.0487, "step": 3670 }, { "epoch": 5.152257612880644, "grad_norm": 6.737855434417725, "learning_rate": 8.307207149476478e-06, "loss": 0.0527, "step": 3680 }, { "epoch": 5.166258312915645, "grad_norm": 0.01580864191055298, "learning_rate": 8.294967463489387e-06, "loss": 0.029, "step": 3690 }, { "epoch": 5.180259012950647, "grad_norm": 0.054978061467409134, "learning_rate": 8.282692776012429e-06, "loss": 0.0261, "step": 3700 }, { "epoch": 5.194259712985649, "grad_norm": 0.001470154500566423, "learning_rate": 8.27038321743607e-06, "loss": 0.0204, "step": 3710 }, { "epoch": 5.208260413020651, "grad_norm": 0.005747316405177116, "learning_rate": 8.258038918521203e-06, "loss": 0.0466, "step": 3720 }, { "epoch": 5.222261113055652, "grad_norm": 0.10529675334692001, "learning_rate": 8.24566001039776e-06, "loss": 0.0019, "step": 3730 }, { "epoch": 5.236261813090654, "grad_norm": 3.1363236904144287, "learning_rate": 8.233246624563315e-06, "loss": 0.0235, "step": 3740 }, { "epoch": 5.250262513125656, "grad_norm": 0.280477911233902, "learning_rate": 8.220798892881686e-06, "loss": 0.054, "step": 3750 }, { "epoch": 5.264263213160658, "grad_norm": 35.494441986083984, "learning_rate": 8.208316947581543e-06, "loss": 0.0547, "step": 3760 }, { "epoch": 5.2782639131956595, "grad_norm": 2.8686635494232178, "learning_rate": 8.19580092125499e-06, "loss": 0.0051, "step": 3770 }, { "epoch": 5.292264613230661, "grad_norm": 0.020721808075904846, "learning_rate": 8.183250946856173e-06, "loss": 0.0408, "step": 3780 }, { "epoch": 5.306265313265663, "grad_norm": 9.166502952575684, "learning_rate": 8.17066715769985e-06, "loss": 0.0636, "step": 3790 }, { "epoch": 5.320266013300665, "grad_norm": 28.179536819458008, "learning_rate": 8.158049687459986e-06, "loss": 0.044, "step": 3800 }, { "epoch": 5.3342667133356665, "grad_norm": 0.19162550568580627, "learning_rate": 8.145398670168336e-06, "loss": 0.0283, "step": 3810 }, { "epoch": 5.348267413370668, "grad_norm": 0.9183430671691895, "learning_rate": 8.132714240213009e-06, "loss": 0.0002, "step": 3820 }, { "epoch": 5.36226811340567, "grad_norm": 0.1281927078962326, "learning_rate": 8.119996532337047e-06, "loss": 0.0229, "step": 3830 }, { "epoch": 5.376268813440672, "grad_norm": 0.011076876893639565, "learning_rate": 8.107245681636997e-06, "loss": 0.0252, "step": 3840 }, { "epoch": 5.3902695134756735, "grad_norm": 4.825412750244141, "learning_rate": 8.094461823561473e-06, "loss": 0.0624, "step": 3850 }, { "epoch": 5.404270213510675, "grad_norm": 0.024655018001794815, "learning_rate": 8.081645093909715e-06, "loss": 0.0536, "step": 3860 }, { "epoch": 5.418270913545677, "grad_norm": 0.002414155751466751, "learning_rate": 8.068795628830148e-06, "loss": 0.0163, "step": 3870 }, { "epoch": 5.432271613580679, "grad_norm": 0.4145294725894928, "learning_rate": 8.055913564818938e-06, "loss": 0.0282, "step": 3880 }, { "epoch": 5.4462723136156805, "grad_norm": 82.75165557861328, "learning_rate": 8.042999038718538e-06, "loss": 0.0065, "step": 3890 }, { "epoch": 5.460273013650682, "grad_norm": 0.1588965505361557, "learning_rate": 8.030052187716238e-06, "loss": 0.0546, "step": 3900 }, { "epoch": 5.474273713685684, "grad_norm": 0.04659806191921234, "learning_rate": 8.017073149342703e-06, "loss": 0.0289, "step": 3910 }, { "epoch": 5.488274413720686, "grad_norm": 0.0054337154142558575, "learning_rate": 8.004062061470519e-06, "loss": 0.0267, "step": 3920 }, { "epoch": 5.502275113755688, "grad_norm": 0.01362488605082035, "learning_rate": 7.991019062312723e-06, "loss": 0.0156, "step": 3930 }, { "epoch": 5.516275813790689, "grad_norm": 0.01387427095323801, "learning_rate": 7.97794429042134e-06, "loss": 0.0756, "step": 3940 }, { "epoch": 5.530276513825691, "grad_norm": 0.1007440835237503, "learning_rate": 7.9648378846859e-06, "loss": 0.0348, "step": 3950 }, { "epoch": 5.544277213860693, "grad_norm": 0.1274271011352539, "learning_rate": 7.951699984331973e-06, "loss": 0.0352, "step": 3960 }, { "epoch": 5.558277913895695, "grad_norm": 0.13830313086509705, "learning_rate": 7.93853072891969e-06, "loss": 0.1726, "step": 3970 }, { "epoch": 5.572278613930696, "grad_norm": 0.11423526704311371, "learning_rate": 7.925330258342261e-06, "loss": 0.0695, "step": 3980 }, { "epoch": 5.586279313965698, "grad_norm": 0.07872703671455383, "learning_rate": 7.912098712824474e-06, "loss": 0.0003, "step": 3990 }, { "epoch": 5.6002800140007, "grad_norm": 0.15258124470710754, "learning_rate": 7.89883623292123e-06, "loss": 0.0314, "step": 4000 }, { "epoch": 5.614280714035702, "grad_norm": 0.14406810700893402, "learning_rate": 7.885542959516027e-06, "loss": 0.0538, "step": 4010 }, { "epoch": 5.628281414070703, "grad_norm": 12.04726505279541, "learning_rate": 7.872219033819479e-06, "loss": 0.1207, "step": 4020 }, { "epoch": 5.642282114105705, "grad_norm": 0.028468133881688118, "learning_rate": 7.85886459736781e-06, "loss": 0.0025, "step": 4030 }, { "epoch": 5.656282814140707, "grad_norm": 0.06600043177604675, "learning_rate": 7.84547979202135e-06, "loss": 0.0302, "step": 4040 }, { "epoch": 5.670283514175709, "grad_norm": 6.3559160232543945, "learning_rate": 7.832064759963028e-06, "loss": 0.0434, "step": 4050 }, { "epoch": 5.68428421421071, "grad_norm": 64.54084014892578, "learning_rate": 7.818619643696863e-06, "loss": 0.0091, "step": 4060 }, { "epoch": 5.698284914245712, "grad_norm": 0.014282717369496822, "learning_rate": 7.805144586046454e-06, "loss": 0.0004, "step": 4070 }, { "epoch": 5.712285614280714, "grad_norm": 0.034424930810928345, "learning_rate": 7.791639730153453e-06, "loss": 0.0048, "step": 4080 }, { "epoch": 5.726286314315716, "grad_norm": 0.039621662348508835, "learning_rate": 7.778105219476053e-06, "loss": 0.1063, "step": 4090 }, { "epoch": 5.740287014350717, "grad_norm": 0.03727049380540848, "learning_rate": 7.764541197787462e-06, "loss": 0.0783, "step": 4100 }, { "epoch": 5.754287714385719, "grad_norm": 0.0016835929127410054, "learning_rate": 7.750947809174372e-06, "loss": 0.0315, "step": 4110 }, { "epoch": 5.768288414420721, "grad_norm": 0.0010269766207784414, "learning_rate": 7.737325198035435e-06, "loss": 0.0002, "step": 4120 }, { "epoch": 5.782289114455723, "grad_norm": 0.18126137554645538, "learning_rate": 7.723673509079718e-06, "loss": 0.0325, "step": 4130 }, { "epoch": 5.7962898144907244, "grad_norm": 7.939001560211182, "learning_rate": 7.709992887325187e-06, "loss": 0.0374, "step": 4140 }, { "epoch": 5.810290514525726, "grad_norm": 0.024497386068105698, "learning_rate": 7.69628347809714e-06, "loss": 0.0008, "step": 4150 }, { "epoch": 5.824291214560728, "grad_norm": 3.9139621257781982, "learning_rate": 7.68254542702668e-06, "loss": 0.0015, "step": 4160 }, { "epoch": 5.83829191459573, "grad_norm": 0.0018668597331270576, "learning_rate": 7.668778880049167e-06, "loss": 0.0245, "step": 4170 }, { "epoch": 5.8522926146307315, "grad_norm": 15.285141944885254, "learning_rate": 7.654983983402662e-06, "loss": 0.0633, "step": 4180 }, { "epoch": 5.866293314665733, "grad_norm": 0.036636680364608765, "learning_rate": 7.641160883626374e-06, "loss": 0.0015, "step": 4190 }, { "epoch": 5.880294014700735, "grad_norm": 0.025609202682971954, "learning_rate": 7.627309727559114e-06, "loss": 0.019, "step": 4200 }, { "epoch": 5.894294714735737, "grad_norm": 7.280523777008057, "learning_rate": 7.613430662337715e-06, "loss": 0.0796, "step": 4210 }, { "epoch": 5.9082954147707385, "grad_norm": 0.04838598519563675, "learning_rate": 7.599523835395493e-06, "loss": 0.0288, "step": 4220 }, { "epoch": 5.92229611480574, "grad_norm": 0.0003251319285482168, "learning_rate": 7.585589394460661e-06, "loss": 0.0007, "step": 4230 }, { "epoch": 5.936296814840742, "grad_norm": 0.007616756483912468, "learning_rate": 7.571627487554769e-06, "loss": 0.075, "step": 4240 }, { "epoch": 5.950297514875744, "grad_norm": 0.12283679097890854, "learning_rate": 7.5576382629911306e-06, "loss": 0.0505, "step": 4250 }, { "epoch": 5.9642982149107455, "grad_norm": 0.017637204378843307, "learning_rate": 7.543621869373249e-06, "loss": 0.0872, "step": 4260 }, { "epoch": 5.978298914945747, "grad_norm": 0.00048005758435465395, "learning_rate": 7.529578455593232e-06, "loss": 0.0234, "step": 4270 }, { "epoch": 5.992299614980749, "grad_norm": 0.5085453391075134, "learning_rate": 7.515508170830221e-06, "loss": 0.1398, "step": 4280 }, { "epoch": 5.99929996499825, "eval_f1": 0.9488872841236063, "eval_loss": 0.16063901782035828, "eval_precision": 0.948186790375482, "eval_recall": 0.9489153254023793, "eval_runtime": 85.1915, "eval_samples_per_second": 16.774, "eval_steps_per_second": 8.393, "step": 4285 }, { "epoch": 6.006300315015751, "grad_norm": 0.041102755814790726, "learning_rate": 7.501411164548792e-06, "loss": 0.0006, "step": 4290 }, { "epoch": 6.0203010150507525, "grad_norm": 5.220290660858154, "learning_rate": 7.487287586497384e-06, "loss": 0.001, "step": 4300 }, { "epoch": 6.034301715085754, "grad_norm": 10.654687881469727, "learning_rate": 7.473137586706693e-06, "loss": 0.0228, "step": 4310 }, { "epoch": 6.048302415120756, "grad_norm": 0.5803616046905518, "learning_rate": 7.458961315488095e-06, "loss": 0.0472, "step": 4320 }, { "epoch": 6.062303115155758, "grad_norm": 0.04721968621015549, "learning_rate": 7.444758923432028e-06, "loss": 0.0109, "step": 4330 }, { "epoch": 6.07630381519076, "grad_norm": 0.033405423164367676, "learning_rate": 7.4305305614064145e-06, "loss": 0.0006, "step": 4340 }, { "epoch": 6.090304515225761, "grad_norm": 0.0014901540707796812, "learning_rate": 7.416276380555041e-06, "loss": 0.0093, "step": 4350 }, { "epoch": 6.104305215260763, "grad_norm": 0.026062890887260437, "learning_rate": 7.401996532295965e-06, "loss": 0.0022, "step": 4360 }, { "epoch": 6.118305915295765, "grad_norm": 0.26311179995536804, "learning_rate": 7.3876911683198995e-06, "loss": 0.0345, "step": 4370 }, { "epoch": 6.132306615330767, "grad_norm": 0.013148613274097443, "learning_rate": 7.373360440588604e-06, "loss": 0.0011, "step": 4380 }, { "epoch": 6.146307315365768, "grad_norm": 1.30440354347229, "learning_rate": 7.359004501333267e-06, "loss": 0.0012, "step": 4390 }, { "epoch": 6.16030801540077, "grad_norm": 0.0015283781103789806, "learning_rate": 7.344623503052898e-06, "loss": 0.0096, "step": 4400 }, { "epoch": 6.174308715435772, "grad_norm": 2.4098916053771973, "learning_rate": 7.330217598512696e-06, "loss": 0.0698, "step": 4410 }, { "epoch": 6.188309415470774, "grad_norm": 0.06899107992649078, "learning_rate": 7.315786940742432e-06, "loss": 0.0917, "step": 4420 }, { "epoch": 6.202310115505775, "grad_norm": 22.4434757232666, "learning_rate": 7.301331683034827e-06, "loss": 0.0104, "step": 4430 }, { "epoch": 6.216310815540777, "grad_norm": 0.0014025595737621188, "learning_rate": 7.286851978943919e-06, "loss": 0.054, "step": 4440 }, { "epoch": 6.230311515575779, "grad_norm": 0.36593034863471985, "learning_rate": 7.2723479822834295e-06, "loss": 0.0003, "step": 4450 }, { "epoch": 6.244312215610781, "grad_norm": 5.852354049682617, "learning_rate": 7.257819847125136e-06, "loss": 0.0498, "step": 4460 }, { "epoch": 6.258312915645782, "grad_norm": 0.009837552905082703, "learning_rate": 7.243267727797235e-06, "loss": 0.0148, "step": 4470 }, { "epoch": 6.272313615680784, "grad_norm": 0.712465226650238, "learning_rate": 7.2286917788826926e-06, "loss": 0.0009, "step": 4480 }, { "epoch": 6.286314315715786, "grad_norm": 0.007876602001488209, "learning_rate": 7.214092155217614e-06, "loss": 0.0129, "step": 4490 }, { "epoch": 6.300315015750788, "grad_norm": 0.06980904191732407, "learning_rate": 7.199469011889598e-06, "loss": 0.0611, "step": 4500 }, { "epoch": 6.314315715785789, "grad_norm": 0.0010226389858871698, "learning_rate": 7.18482250423608e-06, "loss": 0.001, "step": 4510 }, { "epoch": 6.328316415820791, "grad_norm": 0.016090035438537598, "learning_rate": 7.170152787842689e-06, "loss": 0.0081, "step": 4520 }, { "epoch": 6.342317115855793, "grad_norm": 0.0010334812104701996, "learning_rate": 7.155460018541597e-06, "loss": 0.0258, "step": 4530 }, { "epoch": 6.356317815890795, "grad_norm": 0.0009966572979465127, "learning_rate": 7.140744352409856e-06, "loss": 0.0243, "step": 4540 }, { "epoch": 6.3703185159257965, "grad_norm": 27.122793197631836, "learning_rate": 7.12600594576775e-06, "loss": 0.0202, "step": 4550 }, { "epoch": 6.384319215960798, "grad_norm": 8.17154598236084, "learning_rate": 7.1112449551771225e-06, "loss": 0.0069, "step": 4560 }, { "epoch": 6.3983199159958, "grad_norm": 0.0030006226152181625, "learning_rate": 7.096461537439725e-06, "loss": 0.0005, "step": 4570 }, { "epoch": 6.412320616030802, "grad_norm": 28.31182289123535, "learning_rate": 7.0816558495955435e-06, "loss": 0.0367, "step": 4580 }, { "epoch": 6.4263213160658035, "grad_norm": 0.0193657074123621, "learning_rate": 7.066828048921133e-06, "loss": 0.0076, "step": 4590 }, { "epoch": 6.440322016100805, "grad_norm": 0.0019821927417069674, "learning_rate": 7.051978292927947e-06, "loss": 0.0011, "step": 4600 }, { "epoch": 6.454322716135807, "grad_norm": 0.003565513761714101, "learning_rate": 7.0371067393606665e-06, "loss": 0.0118, "step": 4610 }, { "epoch": 6.468323416170809, "grad_norm": 0.7763420939445496, "learning_rate": 7.022213546195516e-06, "loss": 0.0565, "step": 4620 }, { "epoch": 6.4823241162058105, "grad_norm": 0.005166476126760244, "learning_rate": 7.007298871638597e-06, "loss": 0.0081, "step": 4630 }, { "epoch": 6.496324816240812, "grad_norm": 0.0027893453370779753, "learning_rate": 6.9923628741242e-06, "loss": 0.0197, "step": 4640 }, { "epoch": 6.510325516275814, "grad_norm": 0.010828179307281971, "learning_rate": 6.97740571231312e-06, "loss": 0.0002, "step": 4650 }, { "epoch": 6.524326216310816, "grad_norm": 1.695597767829895, "learning_rate": 6.96242754509098e-06, "loss": 0.0102, "step": 4660 }, { "epoch": 6.5383269163458175, "grad_norm": 0.03126674145460129, "learning_rate": 6.947428531566531e-06, "loss": 0.0252, "step": 4670 }, { "epoch": 6.552327616380819, "grad_norm": 2.710430145263672, "learning_rate": 6.9324088310699745e-06, "loss": 0.0297, "step": 4680 }, { "epoch": 6.566328316415821, "grad_norm": 0.0005242613842710853, "learning_rate": 6.9173686031512595e-06, "loss": 0.0127, "step": 4690 }, { "epoch": 6.580329016450823, "grad_norm": 0.12270841002464294, "learning_rate": 6.902308007578392e-06, "loss": 0.0048, "step": 4700 }, { "epoch": 6.5943297164858246, "grad_norm": 0.5776433944702148, "learning_rate": 6.887227204335739e-06, "loss": 0.0012, "step": 4710 }, { "epoch": 6.608330416520826, "grad_norm": 0.004722943529486656, "learning_rate": 6.8721263536223295e-06, "loss": 0.0388, "step": 4720 }, { "epoch": 6.622331116555828, "grad_norm": 27.21036148071289, "learning_rate": 6.857005615850148e-06, "loss": 0.0208, "step": 4730 }, { "epoch": 6.63633181659083, "grad_norm": 0.00167378771584481, "learning_rate": 6.841865151642434e-06, "loss": 0.0056, "step": 4740 }, { "epoch": 6.650332516625832, "grad_norm": 54.31971740722656, "learning_rate": 6.8267051218319766e-06, "loss": 0.0165, "step": 4750 }, { "epoch": 6.664333216660833, "grad_norm": 0.0031642315443605185, "learning_rate": 6.8115256874594015e-06, "loss": 0.0066, "step": 4760 }, { "epoch": 6.678333916695835, "grad_norm": 0.0017562637804076076, "learning_rate": 6.7963270097714705e-06, "loss": 0.0004, "step": 4770 }, { "epoch": 6.692334616730837, "grad_norm": 0.0005346941761672497, "learning_rate": 6.781109250219353e-06, "loss": 0.0021, "step": 4780 }, { "epoch": 6.706335316765839, "grad_norm": 0.001608767081052065, "learning_rate": 6.765872570456926e-06, "loss": 0.0147, "step": 4790 }, { "epoch": 6.72033601680084, "grad_norm": 0.000481385737657547, "learning_rate": 6.750617132339045e-06, "loss": 0.0535, "step": 4800 }, { "epoch": 6.734336716835842, "grad_norm": 0.3291676938533783, "learning_rate": 6.735343097919838e-06, "loss": 0.092, "step": 4810 }, { "epoch": 6.748337416870844, "grad_norm": 18.21904754638672, "learning_rate": 6.720050629450963e-06, "loss": 0.0278, "step": 4820 }, { "epoch": 6.762338116905846, "grad_norm": 15.501587867736816, "learning_rate": 6.704739889379914e-06, "loss": 0.0919, "step": 4830 }, { "epoch": 6.776338816940847, "grad_norm": 0.0905318409204483, "learning_rate": 6.689411040348267e-06, "loss": 0.0201, "step": 4840 }, { "epoch": 6.790339516975849, "grad_norm": 0.034947771579027176, "learning_rate": 6.674064245189969e-06, "loss": 0.0616, "step": 4850 }, { "epoch": 6.804340217010851, "grad_norm": 0.007598557509481907, "learning_rate": 6.6586996669296014e-06, "loss": 0.0272, "step": 4860 }, { "epoch": 6.818340917045853, "grad_norm": 38.44027328491211, "learning_rate": 6.6433174687806525e-06, "loss": 0.0331, "step": 4870 }, { "epoch": 6.832341617080854, "grad_norm": 0.016838544979691505, "learning_rate": 6.62791781414378e-06, "loss": 0.0036, "step": 4880 }, { "epoch": 6.846342317115856, "grad_norm": 0.11778023093938828, "learning_rate": 6.612500866605078e-06, "loss": 0.059, "step": 4890 }, { "epoch": 6.860343017150858, "grad_norm": 0.002434186404570937, "learning_rate": 6.597066789934336e-06, "loss": 0.0687, "step": 4900 }, { "epoch": 6.87434371718586, "grad_norm": 1.2733291387557983, "learning_rate": 6.581615748083306e-06, "loss": 0.0171, "step": 4910 }, { "epoch": 6.8883444172208605, "grad_norm": 0.05777943879365921, "learning_rate": 6.56614790518395e-06, "loss": 0.0092, "step": 4920 }, { "epoch": 6.902345117255862, "grad_norm": 0.00835686456412077, "learning_rate": 6.5506634255467085e-06, "loss": 0.0003, "step": 4930 }, { "epoch": 6.916345817290864, "grad_norm": 0.5090736746788025, "learning_rate": 6.5351624736587446e-06, "loss": 0.0296, "step": 4940 }, { "epoch": 6.930346517325866, "grad_norm": 0.007250604685395956, "learning_rate": 6.5196452141822045e-06, "loss": 0.002, "step": 4950 }, { "epoch": 6.944347217360868, "grad_norm": 0.0013252092758193612, "learning_rate": 6.504111811952463e-06, "loss": 0.0005, "step": 4960 }, { "epoch": 6.958347917395869, "grad_norm": 9.083790064323694e-05, "learning_rate": 6.488562431976376e-06, "loss": 0.0491, "step": 4970 }, { "epoch": 6.972348617430871, "grad_norm": 0.534872829914093, "learning_rate": 6.472997239430529e-06, "loss": 0.0572, "step": 4980 }, { "epoch": 6.986349317465873, "grad_norm": 0.11519961804151535, "learning_rate": 6.457416399659472e-06, "loss": 0.0593, "step": 4990 }, { "epoch": 6.998949947497374, "eval_f1": 0.9509583006631868, "eval_loss": 0.16305629909038544, "eval_precision": 0.9495505979751435, "eval_recall": 0.9510146955913226, "eval_runtime": 85.3445, "eval_samples_per_second": 16.744, "eval_steps_per_second": 8.378, "step": 4999 }, { "epoch": 7.000350017500875, "grad_norm": 0.2292632907629013, "learning_rate": 6.441820078173979e-06, "loss": 0.0009, "step": 5000 }, { "epoch": 7.014350717535876, "grad_norm": 0.05339179188013077, "learning_rate": 6.426208440649278e-06, "loss": 0.0393, "step": 5010 }, { "epoch": 7.028351417570878, "grad_norm": 0.36590057611465454, "learning_rate": 6.410581652923298e-06, "loss": 0.0127, "step": 5020 }, { "epoch": 7.04235211760588, "grad_norm": 0.01245095580816269, "learning_rate": 6.394939880994899e-06, "loss": 0.0001, "step": 5030 }, { "epoch": 7.056352817640882, "grad_norm": 0.010753228329122066, "learning_rate": 6.379283291022118e-06, "loss": 0.0011, "step": 5040 }, { "epoch": 7.070353517675883, "grad_norm": 0.0007269814377650619, "learning_rate": 6.363612049320398e-06, "loss": 0.0282, "step": 5050 }, { "epoch": 7.084354217710885, "grad_norm": 0.004665072076022625, "learning_rate": 6.347926322360825e-06, "loss": 0.0003, "step": 5060 }, { "epoch": 7.098354917745887, "grad_norm": 0.06511039286851883, "learning_rate": 6.3322262767683564e-06, "loss": 0.0009, "step": 5070 }, { "epoch": 7.112355617780889, "grad_norm": 0.17725107073783875, "learning_rate": 6.31651207932005e-06, "loss": 0.0152, "step": 5080 }, { "epoch": 7.12635631781589, "grad_norm": 0.026116928085684776, "learning_rate": 6.300783896943299e-06, "loss": 0.0037, "step": 5090 }, { "epoch": 7.140357017850892, "grad_norm": 0.0030039288103580475, "learning_rate": 6.285041896714052e-06, "loss": 0.0203, "step": 5100 }, { "epoch": 7.154357717885894, "grad_norm": 0.0004382748156785965, "learning_rate": 6.269286245855039e-06, "loss": 0.009, "step": 5110 }, { "epoch": 7.168358417920896, "grad_norm": 0.12300131469964981, "learning_rate": 6.253517111734004e-06, "loss": 0.0014, "step": 5120 }, { "epoch": 7.182359117955897, "grad_norm": 0.01677461341023445, "learning_rate": 6.237734661861909e-06, "loss": 0.0416, "step": 5130 }, { "epoch": 7.196359817990899, "grad_norm": 0.264602929353714, "learning_rate": 6.221939063891176e-06, "loss": 0.0007, "step": 5140 }, { "epoch": 7.210360518025901, "grad_norm": 5.225741188041866e-05, "learning_rate": 6.206130485613887e-06, "loss": 0.0588, "step": 5150 }, { "epoch": 7.224361218060903, "grad_norm": 0.0019231714541092515, "learning_rate": 6.1903090949600144e-06, "loss": 0.0081, "step": 5160 }, { "epoch": 7.2383619180959045, "grad_norm": 0.33081698417663574, "learning_rate": 6.1744750599956315e-06, "loss": 0.0002, "step": 5170 }, { "epoch": 7.252362618130906, "grad_norm": 0.04602145031094551, "learning_rate": 6.158628548921132e-06, "loss": 0.0376, "step": 5180 }, { "epoch": 7.266363318165908, "grad_norm": 0.006785963661968708, "learning_rate": 6.142769730069431e-06, "loss": 0.0003, "step": 5190 }, { "epoch": 7.28036401820091, "grad_norm": 0.051581576466560364, "learning_rate": 6.126898771904197e-06, "loss": 0.0003, "step": 5200 }, { "epoch": 7.2943647182359115, "grad_norm": 0.0003680915688164532, "learning_rate": 6.11101584301804e-06, "loss": 0.017, "step": 5210 }, { "epoch": 7.308365418270913, "grad_norm": 0.26525017619132996, "learning_rate": 6.095121112130742e-06, "loss": 0.0282, "step": 5220 }, { "epoch": 7.322366118305915, "grad_norm": 0.0712617039680481, "learning_rate": 6.079214748087444e-06, "loss": 0.0004, "step": 5230 }, { "epoch": 7.336366818340917, "grad_norm": 0.022503864020109177, "learning_rate": 6.063296919856872e-06, "loss": 0.0437, "step": 5240 }, { "epoch": 7.3503675183759185, "grad_norm": 0.005461391061544418, "learning_rate": 6.047367796529523e-06, "loss": 0.0008, "step": 5250 }, { "epoch": 7.36436821841092, "grad_norm": 0.013845465146005154, "learning_rate": 6.031427547315889e-06, "loss": 0.0241, "step": 5260 }, { "epoch": 7.378368918445922, "grad_norm": 0.0006676681223325431, "learning_rate": 6.0154763415446395e-06, "loss": 0.0478, "step": 5270 }, { "epoch": 7.392369618480924, "grad_norm": 0.001390443299897015, "learning_rate": 5.9995143486608406e-06, "loss": 0.0007, "step": 5280 }, { "epoch": 7.4063703185159255, "grad_norm": 0.0034175976179540157, "learning_rate": 5.983541738224141e-06, "loss": 0.0005, "step": 5290 }, { "epoch": 7.420371018550927, "grad_norm": 0.08463763445615768, "learning_rate": 5.967558679906981e-06, "loss": 0.0008, "step": 5300 }, { "epoch": 7.434371718585929, "grad_norm": 0.00045262128696776927, "learning_rate": 5.951565343492779e-06, "loss": 0.0001, "step": 5310 }, { "epoch": 7.448372418620931, "grad_norm": 35.275489807128906, "learning_rate": 5.935561898874142e-06, "loss": 0.0477, "step": 5320 }, { "epoch": 7.462373118655933, "grad_norm": 0.0014428936410695314, "learning_rate": 5.91954851605105e-06, "loss": 0.0001, "step": 5330 }, { "epoch": 7.476373818690934, "grad_norm": 0.002006105612963438, "learning_rate": 5.9035253651290555e-06, "loss": 0.0003, "step": 5340 }, { "epoch": 7.490374518725936, "grad_norm": 0.08378235995769501, "learning_rate": 5.887492616317471e-06, "loss": 0.0001, "step": 5350 }, { "epoch": 7.504375218760938, "grad_norm": 0.006655500736087561, "learning_rate": 5.87145043992757e-06, "loss": 0.0023, "step": 5360 }, { "epoch": 7.51837591879594, "grad_norm": 0.0004303493769839406, "learning_rate": 5.855399006370766e-06, "loss": 0.0001, "step": 5370 }, { "epoch": 7.532376618830941, "grad_norm": 0.029720665886998177, "learning_rate": 5.839338486156812e-06, "loss": 0.0127, "step": 5380 }, { "epoch": 7.546377318865943, "grad_norm": 0.0001170751202153042, "learning_rate": 5.8232690498919906e-06, "loss": 0.0003, "step": 5390 }, { "epoch": 7.560378018900945, "grad_norm": 0.0037085022777318954, "learning_rate": 5.80719086827729e-06, "loss": 0.0004, "step": 5400 }, { "epoch": 7.574378718935947, "grad_norm": 0.003970707766711712, "learning_rate": 5.7911041121066e-06, "loss": 0.0065, "step": 5410 }, { "epoch": 7.588379418970948, "grad_norm": 0.013814202509820461, "learning_rate": 5.775008952264897e-06, "loss": 0.0712, "step": 5420 }, { "epoch": 7.60238011900595, "grad_norm": 0.003518168581649661, "learning_rate": 5.7589055597264235e-06, "loss": 0.0026, "step": 5430 }, { "epoch": 7.616380819040952, "grad_norm": 0.07790637761354446, "learning_rate": 5.742794105552879e-06, "loss": 0.0389, "step": 5440 }, { "epoch": 7.630381519075954, "grad_norm": 0.0029561452101916075, "learning_rate": 5.726674760891599e-06, "loss": 0.0371, "step": 5450 }, { "epoch": 7.644382219110955, "grad_norm": 0.006337731145322323, "learning_rate": 5.71054769697374e-06, "loss": 0.0302, "step": 5460 }, { "epoch": 7.658382919145957, "grad_norm": 0.3749936521053314, "learning_rate": 5.694413085112448e-06, "loss": 0.0032, "step": 5470 }, { "epoch": 7.672383619180959, "grad_norm": 0.03626039996743202, "learning_rate": 5.678271096701059e-06, "loss": 0.0646, "step": 5480 }, { "epoch": 7.686384319215961, "grad_norm": 0.014318865723907948, "learning_rate": 5.662121903211265e-06, "loss": 0.0007, "step": 5490 }, { "epoch": 7.700385019250962, "grad_norm": 0.005021099466830492, "learning_rate": 5.645965676191294e-06, "loss": 0.0003, "step": 5500 }, { "epoch": 7.714385719285964, "grad_norm": 0.004436223302036524, "learning_rate": 5.62980258726409e-06, "loss": 0.0004, "step": 5510 }, { "epoch": 7.728386419320966, "grad_norm": 0.000860211905092001, "learning_rate": 5.6136328081254874e-06, "loss": 0.0, "step": 5520 }, { "epoch": 7.742387119355968, "grad_norm": 0.0007738994318060577, "learning_rate": 5.597456510542395e-06, "loss": 0.0266, "step": 5530 }, { "epoch": 7.756387819390969, "grad_norm": 0.003178725950419903, "learning_rate": 5.581273866350955e-06, "loss": 0.0001, "step": 5540 }, { "epoch": 7.770388519425971, "grad_norm": 0.0775187537074089, "learning_rate": 5.565085047454737e-06, "loss": 0.0298, "step": 5550 }, { "epoch": 7.784389219460973, "grad_norm": 0.07989465445280075, "learning_rate": 5.548890225822896e-06, "loss": 0.0162, "step": 5560 }, { "epoch": 7.798389919495975, "grad_norm": 1.2074592113494873, "learning_rate": 5.53268957348836e-06, "loss": 0.0013, "step": 5570 }, { "epoch": 7.8123906195309765, "grad_norm": 0.0009719234658405185, "learning_rate": 5.5164832625459865e-06, "loss": 0.0187, "step": 5580 }, { "epoch": 7.826391319565978, "grad_norm": 0.0023037681821733713, "learning_rate": 5.500271465150748e-06, "loss": 0.009, "step": 5590 }, { "epoch": 7.84039201960098, "grad_norm": 9.558547973632812, "learning_rate": 5.484054353515896e-06, "loss": 0.1276, "step": 5600 }, { "epoch": 7.854392719635982, "grad_norm": 20.879596710205078, "learning_rate": 5.467832099911135e-06, "loss": 0.0327, "step": 5610 }, { "epoch": 7.8683934196709835, "grad_norm": 0.022236233577132225, "learning_rate": 5.451604876660787e-06, "loss": 0.0006, "step": 5620 }, { "epoch": 7.882394119705985, "grad_norm": 0.005190831143409014, "learning_rate": 5.435372856141975e-06, "loss": 0.0117, "step": 5630 }, { "epoch": 7.896394819740987, "grad_norm": 24.173221588134766, "learning_rate": 5.4191362107827704e-06, "loss": 0.003, "step": 5640 }, { "epoch": 7.910395519775989, "grad_norm": 0.0021344611886888742, "learning_rate": 5.402895113060379e-06, "loss": 0.035, "step": 5650 }, { "epoch": 7.9243962198109905, "grad_norm": 0.045800287276506424, "learning_rate": 5.3866497354993e-06, "loss": 0.0004, "step": 5660 }, { "epoch": 7.938396919845992, "grad_norm": 0.05233141407370567, "learning_rate": 5.370400250669504e-06, "loss": 0.0445, "step": 5670 }, { "epoch": 7.952397619880994, "grad_norm": 0.005411333404481411, "learning_rate": 5.354146831184579e-06, "loss": 0.0006, "step": 5680 }, { "epoch": 7.966398319915996, "grad_norm": 0.002824575873091817, "learning_rate": 5.337889649699921e-06, "loss": 0.0006, "step": 5690 }, { "epoch": 7.9803990199509975, "grad_norm": 0.0004603438137564808, "learning_rate": 5.3216288789108805e-06, "loss": 0.0, "step": 5700 }, { "epoch": 7.994399719985999, "grad_norm": 0.17578007280826569, "learning_rate": 5.305364691550944e-06, "loss": 0.001, "step": 5710 }, { "epoch": 8.0, "eval_f1": 0.955865295904617, "eval_loss": 0.17154428362846375, "eval_precision": 0.9546686028711965, "eval_recall": 0.9559132260321903, "eval_runtime": 85.2061, "eval_samples_per_second": 16.771, "eval_steps_per_second": 8.391, "step": 5714 } ], "logging_steps": 10, "max_steps": 10710, "num_input_tokens_seen": 0, "num_train_epochs": 15, "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": 3.602886153473369e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }