{ "best_metric": 0.8035092246161786, "best_model_checkpoint": "videomae-base-finetuned-ucf101-newone/checkpoint-23742", "epoch": 19.049279210925643, "global_step": 26360, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.8968133535660094e-07, "loss": 4.607, "step": 10 }, { "epoch": 0.0, "learning_rate": 3.793626707132019e-07, "loss": 4.6321, "step": 20 }, { "epoch": 0.0, "learning_rate": 5.690440060698028e-07, "loss": 4.6528, "step": 30 }, { "epoch": 0.0, "learning_rate": 7.587253414264037e-07, "loss": 4.6371, "step": 40 }, { "epoch": 0.0, "learning_rate": 9.484066767830046e-07, "loss": 4.6886, "step": 50 }, { "epoch": 0.0, "learning_rate": 1.1380880121396055e-06, "loss": 4.6727, "step": 60 }, { "epoch": 0.0, "learning_rate": 1.3277693474962064e-06, "loss": 4.6135, "step": 70 }, { "epoch": 0.0, "learning_rate": 1.5174506828528075e-06, "loss": 4.6389, "step": 80 }, { "epoch": 0.0, "learning_rate": 1.7071320182094082e-06, "loss": 4.6206, "step": 90 }, { "epoch": 0.0, "learning_rate": 1.8968133535660093e-06, "loss": 4.6663, "step": 100 }, { "epoch": 0.0, "learning_rate": 2.0864946889226104e-06, "loss": 4.6393, "step": 110 }, { "epoch": 0.0, "learning_rate": 2.276176024279211e-06, "loss": 4.5888, "step": 120 }, { "epoch": 0.0, "learning_rate": 2.465857359635812e-06, "loss": 4.6612, "step": 130 }, { "epoch": 0.01, "learning_rate": 2.655538694992413e-06, "loss": 4.6547, "step": 140 }, { "epoch": 0.01, "learning_rate": 2.845220030349014e-06, "loss": 4.7248, "step": 150 }, { "epoch": 0.01, "learning_rate": 3.034901365705615e-06, "loss": 4.6031, "step": 160 }, { "epoch": 0.01, "learning_rate": 3.2245827010622157e-06, "loss": 4.6511, "step": 170 }, { "epoch": 0.01, "learning_rate": 3.4142640364188163e-06, "loss": 4.5547, "step": 180 }, { "epoch": 0.01, "learning_rate": 3.6039453717754174e-06, "loss": 4.6374, "step": 190 }, { "epoch": 0.01, "learning_rate": 3.7936267071320185e-06, "loss": 4.6197, "step": 200 }, { "epoch": 0.01, "learning_rate": 3.983308042488619e-06, "loss": 4.6185, "step": 210 }, { "epoch": 0.01, "learning_rate": 4.172989377845221e-06, "loss": 4.6046, "step": 220 }, { "epoch": 0.01, "learning_rate": 4.362670713201821e-06, "loss": 4.6074, "step": 230 }, { "epoch": 0.01, "learning_rate": 4.552352048558422e-06, "loss": 4.5464, "step": 240 }, { "epoch": 0.01, "learning_rate": 4.742033383915024e-06, "loss": 4.6256, "step": 250 }, { "epoch": 0.01, "learning_rate": 4.931714719271624e-06, "loss": 4.6597, "step": 260 }, { "epoch": 0.01, "learning_rate": 5.121396054628225e-06, "loss": 4.5796, "step": 270 }, { "epoch": 0.01, "learning_rate": 5.311077389984826e-06, "loss": 4.5694, "step": 280 }, { "epoch": 0.01, "learning_rate": 5.500758725341427e-06, "loss": 4.659, "step": 290 }, { "epoch": 0.01, "learning_rate": 5.690440060698028e-06, "loss": 4.6983, "step": 300 }, { "epoch": 0.01, "learning_rate": 5.8801213960546285e-06, "loss": 4.5705, "step": 310 }, { "epoch": 0.01, "learning_rate": 6.06980273141123e-06, "loss": 4.5639, "step": 320 }, { "epoch": 0.01, "learning_rate": 6.259484066767831e-06, "loss": 4.6241, "step": 330 }, { "epoch": 0.01, "learning_rate": 6.449165402124431e-06, "loss": 4.628, "step": 340 }, { "epoch": 0.01, "learning_rate": 6.638846737481032e-06, "loss": 4.5883, "step": 350 }, { "epoch": 0.01, "learning_rate": 6.828528072837633e-06, "loss": 4.6048, "step": 360 }, { "epoch": 0.01, "learning_rate": 7.018209408194234e-06, "loss": 4.6584, "step": 370 }, { "epoch": 0.01, "learning_rate": 7.207890743550835e-06, "loss": 4.6752, "step": 380 }, { "epoch": 0.01, "learning_rate": 7.3975720789074356e-06, "loss": 4.5767, "step": 390 }, { "epoch": 0.02, "learning_rate": 7.587253414264037e-06, "loss": 4.642, "step": 400 }, { "epoch": 0.02, "learning_rate": 7.776934749620638e-06, "loss": 4.5667, "step": 410 }, { "epoch": 0.02, "learning_rate": 7.966616084977238e-06, "loss": 4.5188, "step": 420 }, { "epoch": 0.02, "learning_rate": 8.15629742033384e-06, "loss": 4.5286, "step": 430 }, { "epoch": 0.02, "learning_rate": 8.345978755690441e-06, "loss": 4.5154, "step": 440 }, { "epoch": 0.02, "learning_rate": 8.535660091047042e-06, "loss": 4.5849, "step": 450 }, { "epoch": 0.02, "learning_rate": 8.725341426403643e-06, "loss": 4.5663, "step": 460 }, { "epoch": 0.02, "learning_rate": 8.915022761760243e-06, "loss": 4.5194, "step": 470 }, { "epoch": 0.02, "learning_rate": 9.104704097116844e-06, "loss": 4.496, "step": 480 }, { "epoch": 0.02, "learning_rate": 9.294385432473445e-06, "loss": 4.4427, "step": 490 }, { "epoch": 0.02, "learning_rate": 9.484066767830047e-06, "loss": 4.5888, "step": 500 }, { "epoch": 0.02, "learning_rate": 9.673748103186648e-06, "loss": 4.5173, "step": 510 }, { "epoch": 0.02, "learning_rate": 9.863429438543249e-06, "loss": 4.5703, "step": 520 }, { "epoch": 0.02, "learning_rate": 1.005311077389985e-05, "loss": 4.466, "step": 530 }, { "epoch": 0.02, "learning_rate": 1.024279210925645e-05, "loss": 4.5249, "step": 540 }, { "epoch": 0.02, "learning_rate": 1.043247344461305e-05, "loss": 4.4186, "step": 550 }, { "epoch": 0.02, "learning_rate": 1.0622154779969651e-05, "loss": 4.5121, "step": 560 }, { "epoch": 0.02, "learning_rate": 1.0811836115326254e-05, "loss": 4.5683, "step": 570 }, { "epoch": 0.02, "learning_rate": 1.1001517450682854e-05, "loss": 4.4585, "step": 580 }, { "epoch": 0.02, "learning_rate": 1.1191198786039455e-05, "loss": 4.476, "step": 590 }, { "epoch": 0.02, "learning_rate": 1.1380880121396056e-05, "loss": 4.3856, "step": 600 }, { "epoch": 0.02, "learning_rate": 1.1570561456752656e-05, "loss": 4.4231, "step": 610 }, { "epoch": 0.02, "learning_rate": 1.1760242792109257e-05, "loss": 4.375, "step": 620 }, { "epoch": 0.02, "learning_rate": 1.194992412746586e-05, "loss": 4.3542, "step": 630 }, { "epoch": 0.02, "learning_rate": 1.213960546282246e-05, "loss": 4.4062, "step": 640 }, { "epoch": 0.02, "learning_rate": 1.232928679817906e-05, "loss": 4.2902, "step": 650 }, { "epoch": 0.03, "learning_rate": 1.2518968133535661e-05, "loss": 4.3666, "step": 660 }, { "epoch": 0.03, "learning_rate": 1.2708649468892262e-05, "loss": 4.2456, "step": 670 }, { "epoch": 0.03, "learning_rate": 1.2898330804248863e-05, "loss": 4.2609, "step": 680 }, { "epoch": 0.03, "learning_rate": 1.3088012139605463e-05, "loss": 4.3389, "step": 690 }, { "epoch": 0.03, "learning_rate": 1.3277693474962064e-05, "loss": 4.1807, "step": 700 }, { "epoch": 0.03, "learning_rate": 1.3467374810318665e-05, "loss": 4.2172, "step": 710 }, { "epoch": 0.03, "learning_rate": 1.3657056145675265e-05, "loss": 4.1309, "step": 720 }, { "epoch": 0.03, "learning_rate": 1.3846737481031868e-05, "loss": 4.1794, "step": 730 }, { "epoch": 0.03, "learning_rate": 1.4036418816388468e-05, "loss": 4.0394, "step": 740 }, { "epoch": 0.03, "learning_rate": 1.4226100151745069e-05, "loss": 4.1463, "step": 750 }, { "epoch": 0.03, "learning_rate": 1.441578148710167e-05, "loss": 4.1361, "step": 760 }, { "epoch": 0.03, "learning_rate": 1.460546282245827e-05, "loss": 4.0293, "step": 770 }, { "epoch": 0.03, "learning_rate": 1.4795144157814871e-05, "loss": 4.0575, "step": 780 }, { "epoch": 0.03, "learning_rate": 1.4984825493171473e-05, "loss": 3.9758, "step": 790 }, { "epoch": 0.03, "learning_rate": 1.5174506828528074e-05, "loss": 3.9138, "step": 800 }, { "epoch": 0.03, "learning_rate": 1.5364188163884675e-05, "loss": 3.9409, "step": 810 }, { "epoch": 0.03, "learning_rate": 1.5553869499241275e-05, "loss": 3.9833, "step": 820 }, { "epoch": 0.03, "learning_rate": 1.5743550834597876e-05, "loss": 3.8194, "step": 830 }, { "epoch": 0.03, "learning_rate": 1.5933232169954477e-05, "loss": 3.9143, "step": 840 }, { "epoch": 0.03, "learning_rate": 1.6122913505311078e-05, "loss": 3.7833, "step": 850 }, { "epoch": 0.03, "learning_rate": 1.631259484066768e-05, "loss": 3.7316, "step": 860 }, { "epoch": 0.03, "learning_rate": 1.6502276176024282e-05, "loss": 4.0113, "step": 870 }, { "epoch": 0.03, "learning_rate": 1.6691957511380883e-05, "loss": 3.8137, "step": 880 }, { "epoch": 0.03, "learning_rate": 1.6881638846737484e-05, "loss": 4.0983, "step": 890 }, { "epoch": 0.03, "learning_rate": 1.7071320182094084e-05, "loss": 3.7786, "step": 900 }, { "epoch": 0.03, "learning_rate": 1.7261001517450685e-05, "loss": 3.8001, "step": 910 }, { "epoch": 0.03, "learning_rate": 1.7450682852807286e-05, "loss": 3.6232, "step": 920 }, { "epoch": 0.04, "learning_rate": 1.7640364188163886e-05, "loss": 3.5918, "step": 930 }, { "epoch": 0.04, "learning_rate": 1.7830045523520487e-05, "loss": 3.5412, "step": 940 }, { "epoch": 0.04, "learning_rate": 1.8019726858877088e-05, "loss": 3.6586, "step": 950 }, { "epoch": 0.04, "learning_rate": 1.8209408194233688e-05, "loss": 3.6789, "step": 960 }, { "epoch": 0.04, "learning_rate": 1.839908952959029e-05, "loss": 3.6056, "step": 970 }, { "epoch": 0.04, "learning_rate": 1.858877086494689e-05, "loss": 3.6297, "step": 980 }, { "epoch": 0.04, "learning_rate": 1.8778452200303494e-05, "loss": 3.6031, "step": 990 }, { "epoch": 0.04, "learning_rate": 1.8968133535660094e-05, "loss": 3.4693, "step": 1000 }, { "epoch": 0.04, "learning_rate": 1.9157814871016695e-05, "loss": 3.3267, "step": 1010 }, { "epoch": 0.04, "learning_rate": 1.9347496206373296e-05, "loss": 3.5468, "step": 1020 }, { "epoch": 0.04, "learning_rate": 1.9537177541729896e-05, "loss": 3.3226, "step": 1030 }, { "epoch": 0.04, "learning_rate": 1.9726858877086497e-05, "loss": 3.4241, "step": 1040 }, { "epoch": 0.04, "learning_rate": 1.9916540212443098e-05, "loss": 3.4421, "step": 1050 }, { "epoch": 0.04, "learning_rate": 2.01062215477997e-05, "loss": 3.2474, "step": 1060 }, { "epoch": 0.04, "learning_rate": 2.02959028831563e-05, "loss": 3.1911, "step": 1070 }, { "epoch": 0.04, "learning_rate": 2.04855842185129e-05, "loss": 3.2751, "step": 1080 }, { "epoch": 0.04, "learning_rate": 2.06752655538695e-05, "loss": 3.1756, "step": 1090 }, { "epoch": 0.04, "learning_rate": 2.08649468892261e-05, "loss": 3.2812, "step": 1100 }, { "epoch": 0.04, "learning_rate": 2.1054628224582702e-05, "loss": 3.1802, "step": 1110 }, { "epoch": 0.04, "learning_rate": 2.1244309559939302e-05, "loss": 3.1993, "step": 1120 }, { "epoch": 0.04, "learning_rate": 2.1433990895295907e-05, "loss": 3.1135, "step": 1130 }, { "epoch": 0.04, "learning_rate": 2.1623672230652507e-05, "loss": 3.0828, "step": 1140 }, { "epoch": 0.04, "learning_rate": 2.1813353566009108e-05, "loss": 3.0259, "step": 1150 }, { "epoch": 0.04, "learning_rate": 2.200303490136571e-05, "loss": 3.0233, "step": 1160 }, { "epoch": 0.04, "learning_rate": 2.219271623672231e-05, "loss": 3.0618, "step": 1170 }, { "epoch": 0.04, "learning_rate": 2.238239757207891e-05, "loss": 2.9612, "step": 1180 }, { "epoch": 0.05, "learning_rate": 2.257207890743551e-05, "loss": 2.9724, "step": 1190 }, { "epoch": 0.05, "learning_rate": 2.276176024279211e-05, "loss": 2.7964, "step": 1200 }, { "epoch": 0.05, "learning_rate": 2.2951441578148712e-05, "loss": 2.9328, "step": 1210 }, { "epoch": 0.05, "learning_rate": 2.3141122913505313e-05, "loss": 3.0828, "step": 1220 }, { "epoch": 0.05, "learning_rate": 2.3330804248861913e-05, "loss": 2.8538, "step": 1230 }, { "epoch": 0.05, "learning_rate": 2.3520485584218514e-05, "loss": 2.836, "step": 1240 }, { "epoch": 0.05, "learning_rate": 2.3710166919575115e-05, "loss": 2.8984, "step": 1250 }, { "epoch": 0.05, "learning_rate": 2.389984825493172e-05, "loss": 3.1944, "step": 1260 }, { "epoch": 0.05, "learning_rate": 2.408952959028832e-05, "loss": 2.8113, "step": 1270 }, { "epoch": 0.05, "learning_rate": 2.427921092564492e-05, "loss": 2.9952, "step": 1280 }, { "epoch": 0.05, "learning_rate": 2.446889226100152e-05, "loss": 2.6015, "step": 1290 }, { "epoch": 0.05, "learning_rate": 2.465857359635812e-05, "loss": 2.7598, "step": 1300 }, { "epoch": 0.05, "learning_rate": 2.4848254931714722e-05, "loss": 2.7691, "step": 1310 }, { "epoch": 0.05, "eval_accuracy": 0.3723390530254161, "eval_loss": 2.8224644660949707, "eval_runtime": 614.2909, "eval_samples_per_second": 12.618, "eval_steps_per_second": 2.103, "step": 1319 }, { "epoch": 1.0, "learning_rate": 2.5037936267071323e-05, "loss": 2.6302, "step": 1320 }, { "epoch": 1.0, "learning_rate": 2.5227617602427923e-05, "loss": 2.5674, "step": 1330 }, { "epoch": 1.0, "learning_rate": 2.5417298937784524e-05, "loss": 2.6626, "step": 1340 }, { "epoch": 1.0, "learning_rate": 2.5606980273141125e-05, "loss": 2.6131, "step": 1350 }, { "epoch": 1.0, "learning_rate": 2.5796661608497725e-05, "loss": 2.4377, "step": 1360 }, { "epoch": 1.0, "learning_rate": 2.5986342943854326e-05, "loss": 2.6046, "step": 1370 }, { "epoch": 1.0, "learning_rate": 2.6176024279210927e-05, "loss": 2.4089, "step": 1380 }, { "epoch": 1.0, "learning_rate": 2.6365705614567527e-05, "loss": 2.407, "step": 1390 }, { "epoch": 1.0, "learning_rate": 2.6555386949924128e-05, "loss": 2.3953, "step": 1400 }, { "epoch": 1.0, "learning_rate": 2.674506828528073e-05, "loss": 2.5839, "step": 1410 }, { "epoch": 1.0, "learning_rate": 2.693474962063733e-05, "loss": 2.3647, "step": 1420 }, { "epoch": 1.0, "learning_rate": 2.712443095599393e-05, "loss": 2.3187, "step": 1430 }, { "epoch": 1.0, "learning_rate": 2.731411229135053e-05, "loss": 2.2226, "step": 1440 }, { "epoch": 1.0, "learning_rate": 2.7503793626707135e-05, "loss": 1.9446, "step": 1450 }, { "epoch": 1.01, "learning_rate": 2.7693474962063735e-05, "loss": 2.1345, "step": 1460 }, { "epoch": 1.01, "learning_rate": 2.7883156297420336e-05, "loss": 2.3025, "step": 1470 }, { "epoch": 1.01, "learning_rate": 2.8072837632776937e-05, "loss": 2.2535, "step": 1480 }, { "epoch": 1.01, "learning_rate": 2.8262518968133538e-05, "loss": 2.2146, "step": 1490 }, { "epoch": 1.01, "learning_rate": 2.8452200303490138e-05, "loss": 2.3776, "step": 1500 }, { "epoch": 1.01, "learning_rate": 2.864188163884674e-05, "loss": 2.3834, "step": 1510 }, { "epoch": 1.01, "learning_rate": 2.883156297420334e-05, "loss": 2.1672, "step": 1520 }, { "epoch": 1.01, "learning_rate": 2.902124430955994e-05, "loss": 2.2496, "step": 1530 }, { "epoch": 1.01, "learning_rate": 2.921092564491654e-05, "loss": 2.1976, "step": 1540 }, { "epoch": 1.01, "learning_rate": 2.940060698027314e-05, "loss": 2.2141, "step": 1550 }, { "epoch": 1.01, "learning_rate": 2.9590288315629742e-05, "loss": 1.846, "step": 1560 }, { "epoch": 1.01, "learning_rate": 2.9779969650986346e-05, "loss": 1.9342, "step": 1570 }, { "epoch": 1.01, "learning_rate": 2.9969650986342947e-05, "loss": 2.2097, "step": 1580 }, { "epoch": 1.01, "learning_rate": 3.0159332321699548e-05, "loss": 1.9857, "step": 1590 }, { "epoch": 1.01, "learning_rate": 3.0349013657056148e-05, "loss": 2.2405, "step": 1600 }, { "epoch": 1.01, "learning_rate": 3.0538694992412746e-05, "loss": 2.018, "step": 1610 }, { "epoch": 1.01, "learning_rate": 3.072837632776935e-05, "loss": 2.0661, "step": 1620 }, { "epoch": 1.01, "learning_rate": 3.091805766312595e-05, "loss": 1.8737, "step": 1630 }, { "epoch": 1.01, "learning_rate": 3.110773899848255e-05, "loss": 2.2663, "step": 1640 }, { "epoch": 1.01, "learning_rate": 3.129742033383915e-05, "loss": 2.1111, "step": 1650 }, { "epoch": 1.01, "learning_rate": 3.148710166919575e-05, "loss": 2.1449, "step": 1660 }, { "epoch": 1.01, "learning_rate": 3.167678300455235e-05, "loss": 2.0595, "step": 1670 }, { "epoch": 1.01, "learning_rate": 3.1866464339908954e-05, "loss": 1.8436, "step": 1680 }, { "epoch": 1.01, "learning_rate": 3.205614567526555e-05, "loss": 1.865, "step": 1690 }, { "epoch": 1.01, "learning_rate": 3.2245827010622155e-05, "loss": 1.8625, "step": 1700 }, { "epoch": 1.01, "learning_rate": 3.243550834597875e-05, "loss": 1.6873, "step": 1710 }, { "epoch": 1.02, "learning_rate": 3.262518968133536e-05, "loss": 1.8459, "step": 1720 }, { "epoch": 1.02, "learning_rate": 3.281487101669196e-05, "loss": 1.9889, "step": 1730 }, { "epoch": 1.02, "learning_rate": 3.3004552352048564e-05, "loss": 1.5985, "step": 1740 }, { "epoch": 1.02, "learning_rate": 3.319423368740516e-05, "loss": 1.7511, "step": 1750 }, { "epoch": 1.02, "learning_rate": 3.3383915022761766e-05, "loss": 1.7906, "step": 1760 }, { "epoch": 1.02, "learning_rate": 3.357359635811836e-05, "loss": 1.8873, "step": 1770 }, { "epoch": 1.02, "learning_rate": 3.376327769347497e-05, "loss": 1.6878, "step": 1780 }, { "epoch": 1.02, "learning_rate": 3.3952959028831564e-05, "loss": 1.9693, "step": 1790 }, { "epoch": 1.02, "learning_rate": 3.414264036418817e-05, "loss": 1.6615, "step": 1800 }, { "epoch": 1.02, "learning_rate": 3.4332321699544766e-05, "loss": 1.9915, "step": 1810 }, { "epoch": 1.02, "learning_rate": 3.452200303490137e-05, "loss": 1.6995, "step": 1820 }, { "epoch": 1.02, "learning_rate": 3.471168437025797e-05, "loss": 1.8022, "step": 1830 }, { "epoch": 1.02, "learning_rate": 3.490136570561457e-05, "loss": 1.6636, "step": 1840 }, { "epoch": 1.02, "learning_rate": 3.509104704097117e-05, "loss": 1.7474, "step": 1850 }, { "epoch": 1.02, "learning_rate": 3.528072837632777e-05, "loss": 1.8256, "step": 1860 }, { "epoch": 1.02, "learning_rate": 3.547040971168437e-05, "loss": 1.81, "step": 1870 }, { "epoch": 1.02, "learning_rate": 3.5660091047040974e-05, "loss": 1.9152, "step": 1880 }, { "epoch": 1.02, "learning_rate": 3.584977238239757e-05, "loss": 1.8167, "step": 1890 }, { "epoch": 1.02, "learning_rate": 3.6039453717754175e-05, "loss": 1.6653, "step": 1900 }, { "epoch": 1.02, "learning_rate": 3.622913505311077e-05, "loss": 1.7355, "step": 1910 }, { "epoch": 1.02, "learning_rate": 3.6418816388467377e-05, "loss": 1.751, "step": 1920 }, { "epoch": 1.02, "learning_rate": 3.6608497723823974e-05, "loss": 1.7103, "step": 1930 }, { "epoch": 1.02, "learning_rate": 3.679817905918058e-05, "loss": 1.7756, "step": 1940 }, { "epoch": 1.02, "learning_rate": 3.6987860394537175e-05, "loss": 1.7528, "step": 1950 }, { "epoch": 1.02, "learning_rate": 3.717754172989378e-05, "loss": 1.5338, "step": 1960 }, { "epoch": 1.02, "learning_rate": 3.7367223065250377e-05, "loss": 1.55, "step": 1970 }, { "epoch": 1.03, "learning_rate": 3.755690440060699e-05, "loss": 1.5246, "step": 1980 }, { "epoch": 1.03, "learning_rate": 3.7746585735963585e-05, "loss": 1.5441, "step": 1990 }, { "epoch": 1.03, "learning_rate": 3.793626707132019e-05, "loss": 1.6966, "step": 2000 }, { "epoch": 1.03, "learning_rate": 3.8125948406676786e-05, "loss": 1.4465, "step": 2010 }, { "epoch": 1.03, "learning_rate": 3.831562974203339e-05, "loss": 1.6943, "step": 2020 }, { "epoch": 1.03, "learning_rate": 3.850531107738999e-05, "loss": 1.6156, "step": 2030 }, { "epoch": 1.03, "learning_rate": 3.869499241274659e-05, "loss": 1.4584, "step": 2040 }, { "epoch": 1.03, "learning_rate": 3.888467374810319e-05, "loss": 1.1909, "step": 2050 }, { "epoch": 1.03, "learning_rate": 3.907435508345979e-05, "loss": 1.668, "step": 2060 }, { "epoch": 1.03, "learning_rate": 3.926403641881639e-05, "loss": 1.6842, "step": 2070 }, { "epoch": 1.03, "learning_rate": 3.9453717754172994e-05, "loss": 1.7381, "step": 2080 }, { "epoch": 1.03, "learning_rate": 3.964339908952959e-05, "loss": 1.3157, "step": 2090 }, { "epoch": 1.03, "learning_rate": 3.9833080424886195e-05, "loss": 1.5531, "step": 2100 }, { "epoch": 1.03, "learning_rate": 4.002276176024279e-05, "loss": 1.4094, "step": 2110 }, { "epoch": 1.03, "learning_rate": 4.02124430955994e-05, "loss": 1.2909, "step": 2120 }, { "epoch": 1.03, "learning_rate": 4.0402124430955994e-05, "loss": 1.4208, "step": 2130 }, { "epoch": 1.03, "learning_rate": 4.05918057663126e-05, "loss": 1.3868, "step": 2140 }, { "epoch": 1.03, "learning_rate": 4.0781487101669195e-05, "loss": 1.1255, "step": 2150 }, { "epoch": 1.03, "learning_rate": 4.09711684370258e-05, "loss": 1.3676, "step": 2160 }, { "epoch": 1.03, "learning_rate": 4.11608497723824e-05, "loss": 1.1807, "step": 2170 }, { "epoch": 1.03, "learning_rate": 4.1350531107739e-05, "loss": 1.3585, "step": 2180 }, { "epoch": 1.03, "learning_rate": 4.15402124430956e-05, "loss": 1.4394, "step": 2190 }, { "epoch": 1.03, "learning_rate": 4.17298937784522e-05, "loss": 1.2976, "step": 2200 }, { "epoch": 1.03, "learning_rate": 4.19195751138088e-05, "loss": 1.5248, "step": 2210 }, { "epoch": 1.03, "learning_rate": 4.2109256449165404e-05, "loss": 1.1953, "step": 2220 }, { "epoch": 1.03, "learning_rate": 4.2298937784522e-05, "loss": 1.4484, "step": 2230 }, { "epoch": 1.03, "learning_rate": 4.2488619119878605e-05, "loss": 1.3868, "step": 2240 }, { "epoch": 1.04, "learning_rate": 4.267830045523521e-05, "loss": 1.5419, "step": 2250 }, { "epoch": 1.04, "learning_rate": 4.286798179059181e-05, "loss": 1.3191, "step": 2260 }, { "epoch": 1.04, "learning_rate": 4.305766312594841e-05, "loss": 1.1909, "step": 2270 }, { "epoch": 1.04, "learning_rate": 4.3247344461305014e-05, "loss": 1.0572, "step": 2280 }, { "epoch": 1.04, "learning_rate": 4.343702579666161e-05, "loss": 1.3524, "step": 2290 }, { "epoch": 1.04, "learning_rate": 4.3626707132018216e-05, "loss": 1.259, "step": 2300 }, { "epoch": 1.04, "learning_rate": 4.381638846737481e-05, "loss": 1.0507, "step": 2310 }, { "epoch": 1.04, "learning_rate": 4.400606980273142e-05, "loss": 1.0568, "step": 2320 }, { "epoch": 1.04, "learning_rate": 4.4195751138088014e-05, "loss": 1.1594, "step": 2330 }, { "epoch": 1.04, "learning_rate": 4.438543247344462e-05, "loss": 1.0243, "step": 2340 }, { "epoch": 1.04, "learning_rate": 4.4575113808801216e-05, "loss": 1.3847, "step": 2350 }, { "epoch": 1.04, "learning_rate": 4.476479514415782e-05, "loss": 1.1462, "step": 2360 }, { "epoch": 1.04, "learning_rate": 4.495447647951442e-05, "loss": 1.2425, "step": 2370 }, { "epoch": 1.04, "learning_rate": 4.514415781487102e-05, "loss": 0.9946, "step": 2380 }, { "epoch": 1.04, "learning_rate": 4.533383915022762e-05, "loss": 1.2297, "step": 2390 }, { "epoch": 1.04, "learning_rate": 4.552352048558422e-05, "loss": 1.4148, "step": 2400 }, { "epoch": 1.04, "learning_rate": 4.571320182094082e-05, "loss": 1.2376, "step": 2410 }, { "epoch": 1.04, "learning_rate": 4.5902883156297424e-05, "loss": 0.9526, "step": 2420 }, { "epoch": 1.04, "learning_rate": 4.609256449165402e-05, "loss": 1.0764, "step": 2430 }, { "epoch": 1.04, "learning_rate": 4.6282245827010625e-05, "loss": 0.7718, "step": 2440 }, { "epoch": 1.04, "learning_rate": 4.647192716236722e-05, "loss": 1.3313, "step": 2450 }, { "epoch": 1.04, "learning_rate": 4.6661608497723826e-05, "loss": 1.018, "step": 2460 }, { "epoch": 1.04, "learning_rate": 4.6851289833080424e-05, "loss": 1.0567, "step": 2470 }, { "epoch": 1.04, "learning_rate": 4.704097116843703e-05, "loss": 1.2562, "step": 2480 }, { "epoch": 1.04, "learning_rate": 4.7230652503793625e-05, "loss": 1.333, "step": 2490 }, { "epoch": 1.04, "learning_rate": 4.742033383915023e-05, "loss": 0.9299, "step": 2500 }, { "epoch": 1.05, "learning_rate": 4.761001517450683e-05, "loss": 1.0742, "step": 2510 }, { "epoch": 1.05, "learning_rate": 4.779969650986344e-05, "loss": 0.8981, "step": 2520 }, { "epoch": 1.05, "learning_rate": 4.7989377845220035e-05, "loss": 1.3381, "step": 2530 }, { "epoch": 1.05, "learning_rate": 4.817905918057664e-05, "loss": 1.3767, "step": 2540 }, { "epoch": 1.05, "learning_rate": 4.8368740515933236e-05, "loss": 1.211, "step": 2550 }, { "epoch": 1.05, "learning_rate": 4.855842185128984e-05, "loss": 1.2311, "step": 2560 }, { "epoch": 1.05, "learning_rate": 4.874810318664644e-05, "loss": 1.1037, "step": 2570 }, { "epoch": 1.05, "learning_rate": 4.893778452200304e-05, "loss": 1.2958, "step": 2580 }, { "epoch": 1.05, "learning_rate": 4.912746585735964e-05, "loss": 0.9791, "step": 2590 }, { "epoch": 1.05, "learning_rate": 4.931714719271624e-05, "loss": 0.9631, "step": 2600 }, { "epoch": 1.05, "learning_rate": 4.950682852807284e-05, "loss": 1.157, "step": 2610 }, { "epoch": 1.05, "learning_rate": 4.9696509863429444e-05, "loss": 0.9209, "step": 2620 }, { "epoch": 1.05, "learning_rate": 4.988619119878604e-05, "loss": 1.2029, "step": 2630 }, { "epoch": 1.05, "eval_accuracy": 0.6155334795510257, "eval_loss": 1.529559850692749, "eval_runtime": 600.025, "eval_samples_per_second": 12.918, "eval_steps_per_second": 2.153, "step": 2638 }, { "epoch": 2.0, "learning_rate": 4.99915697184286e-05, "loss": 0.8945, "step": 2640 }, { "epoch": 2.0, "learning_rate": 4.997049401450009e-05, "loss": 0.8144, "step": 2650 }, { "epoch": 2.0, "learning_rate": 4.994941831057158e-05, "loss": 0.9437, "step": 2660 }, { "epoch": 2.0, "learning_rate": 4.992834260664306e-05, "loss": 0.7294, "step": 2670 }, { "epoch": 2.0, "learning_rate": 4.990726690271456e-05, "loss": 1.2208, "step": 2680 }, { "epoch": 2.0, "learning_rate": 4.988619119878604e-05, "loss": 0.8924, "step": 2690 }, { "epoch": 2.0, "learning_rate": 4.986511549485753e-05, "loss": 0.8446, "step": 2700 }, { "epoch": 2.0, "learning_rate": 4.984403979092902e-05, "loss": 0.8439, "step": 2710 }, { "epoch": 2.0, "learning_rate": 4.9822964087000504e-05, "loss": 0.7769, "step": 2720 }, { "epoch": 2.0, "learning_rate": 4.9801888383072e-05, "loss": 1.0994, "step": 2730 }, { "epoch": 2.0, "learning_rate": 4.9780812679143484e-05, "loss": 1.1889, "step": 2740 }, { "epoch": 2.0, "learning_rate": 4.9759736975214974e-05, "loss": 0.833, "step": 2750 }, { "epoch": 2.0, "learning_rate": 4.9738661271286464e-05, "loss": 1.0709, "step": 2760 }, { "epoch": 2.01, "learning_rate": 4.971758556735795e-05, "loss": 0.7635, "step": 2770 }, { "epoch": 2.01, "learning_rate": 4.9696509863429444e-05, "loss": 0.7532, "step": 2780 }, { "epoch": 2.01, "learning_rate": 4.967543415950093e-05, "loss": 0.9951, "step": 2790 }, { "epoch": 2.01, "learning_rate": 4.965435845557242e-05, "loss": 0.8811, "step": 2800 }, { "epoch": 2.01, "learning_rate": 4.963328275164391e-05, "loss": 0.8412, "step": 2810 }, { "epoch": 2.01, "learning_rate": 4.96122070477154e-05, "loss": 1.122, "step": 2820 }, { "epoch": 2.01, "learning_rate": 4.959113134378689e-05, "loss": 0.9793, "step": 2830 }, { "epoch": 2.01, "learning_rate": 4.957005563985838e-05, "loss": 0.8735, "step": 2840 }, { "epoch": 2.01, "learning_rate": 4.954897993592986e-05, "loss": 0.9934, "step": 2850 }, { "epoch": 2.01, "learning_rate": 4.952790423200135e-05, "loss": 0.9887, "step": 2860 }, { "epoch": 2.01, "learning_rate": 4.950682852807284e-05, "loss": 0.7727, "step": 2870 }, { "epoch": 2.01, "learning_rate": 4.948575282414433e-05, "loss": 0.8353, "step": 2880 }, { "epoch": 2.01, "learning_rate": 4.946467712021582e-05, "loss": 0.8789, "step": 2890 }, { "epoch": 2.01, "learning_rate": 4.94436014162873e-05, "loss": 0.9352, "step": 2900 }, { "epoch": 2.01, "learning_rate": 4.94225257123588e-05, "loss": 0.9092, "step": 2910 }, { "epoch": 2.01, "learning_rate": 4.940145000843028e-05, "loss": 0.9885, "step": 2920 }, { "epoch": 2.01, "learning_rate": 4.938037430450177e-05, "loss": 1.0428, "step": 2930 }, { "epoch": 2.01, "learning_rate": 4.935929860057326e-05, "loss": 0.7997, "step": 2940 }, { "epoch": 2.01, "learning_rate": 4.9338222896644746e-05, "loss": 0.7975, "step": 2950 }, { "epoch": 2.01, "learning_rate": 4.931714719271624e-05, "loss": 1.2249, "step": 2960 }, { "epoch": 2.01, "learning_rate": 4.9296071488787726e-05, "loss": 0.8115, "step": 2970 }, { "epoch": 2.01, "learning_rate": 4.9274995784859216e-05, "loss": 0.8086, "step": 2980 }, { "epoch": 2.01, "learning_rate": 4.9253920080930706e-05, "loss": 0.8496, "step": 2990 }, { "epoch": 2.01, "learning_rate": 4.9232844377002196e-05, "loss": 0.8936, "step": 3000 }, { "epoch": 2.01, "learning_rate": 4.9211768673073686e-05, "loss": 0.6652, "step": 3010 }, { "epoch": 2.01, "learning_rate": 4.9190692969145176e-05, "loss": 0.7735, "step": 3020 }, { "epoch": 2.01, "learning_rate": 4.916961726521666e-05, "loss": 0.6605, "step": 3030 }, { "epoch": 2.02, "learning_rate": 4.914854156128815e-05, "loss": 0.5288, "step": 3040 }, { "epoch": 2.02, "learning_rate": 4.912746585735964e-05, "loss": 0.7118, "step": 3050 }, { "epoch": 2.02, "learning_rate": 4.910639015343113e-05, "loss": 0.6925, "step": 3060 }, { "epoch": 2.02, "learning_rate": 4.908531444950262e-05, "loss": 0.8388, "step": 3070 }, { "epoch": 2.02, "learning_rate": 4.90642387455741e-05, "loss": 0.8014, "step": 3080 }, { "epoch": 2.02, "learning_rate": 4.90431630416456e-05, "loss": 0.675, "step": 3090 }, { "epoch": 2.02, "learning_rate": 4.902208733771708e-05, "loss": 0.7437, "step": 3100 }, { "epoch": 2.02, "learning_rate": 4.900101163378857e-05, "loss": 0.6269, "step": 3110 }, { "epoch": 2.02, "learning_rate": 4.897993592986006e-05, "loss": 0.7547, "step": 3120 }, { "epoch": 2.02, "learning_rate": 4.8958860225931545e-05, "loss": 0.769, "step": 3130 }, { "epoch": 2.02, "learning_rate": 4.893778452200304e-05, "loss": 0.6497, "step": 3140 }, { "epoch": 2.02, "learning_rate": 4.8916708818074525e-05, "loss": 0.6917, "step": 3150 }, { "epoch": 2.02, "learning_rate": 4.8895633114146014e-05, "loss": 0.7603, "step": 3160 }, { "epoch": 2.02, "learning_rate": 4.8874557410217504e-05, "loss": 0.5138, "step": 3170 }, { "epoch": 2.02, "learning_rate": 4.8853481706288994e-05, "loss": 0.8062, "step": 3180 }, { "epoch": 2.02, "learning_rate": 4.8832406002360484e-05, "loss": 1.0148, "step": 3190 }, { "epoch": 2.02, "learning_rate": 4.881133029843197e-05, "loss": 0.77, "step": 3200 }, { "epoch": 2.02, "learning_rate": 4.879025459450346e-05, "loss": 0.9218, "step": 3210 }, { "epoch": 2.02, "learning_rate": 4.876917889057495e-05, "loss": 0.5389, "step": 3220 }, { "epoch": 2.02, "learning_rate": 4.874810318664644e-05, "loss": 0.6977, "step": 3230 }, { "epoch": 2.02, "learning_rate": 4.872702748271793e-05, "loss": 0.5218, "step": 3240 }, { "epoch": 2.02, "learning_rate": 4.870595177878942e-05, "loss": 0.6837, "step": 3250 }, { "epoch": 2.02, "learning_rate": 4.86848760748609e-05, "loss": 0.676, "step": 3260 }, { "epoch": 2.02, "learning_rate": 4.86638003709324e-05, "loss": 0.4456, "step": 3270 }, { "epoch": 2.02, "learning_rate": 4.864272466700388e-05, "loss": 0.861, "step": 3280 }, { "epoch": 2.02, "learning_rate": 4.862164896307537e-05, "loss": 0.6688, "step": 3290 }, { "epoch": 2.03, "learning_rate": 4.860057325914686e-05, "loss": 0.6082, "step": 3300 }, { "epoch": 2.03, "learning_rate": 4.857949755521834e-05, "loss": 0.5962, "step": 3310 }, { "epoch": 2.03, "learning_rate": 4.855842185128984e-05, "loss": 0.4579, "step": 3320 }, { "epoch": 2.03, "learning_rate": 4.853734614736132e-05, "loss": 0.6682, "step": 3330 }, { "epoch": 2.03, "learning_rate": 4.851627044343281e-05, "loss": 0.6074, "step": 3340 }, { "epoch": 2.03, "learning_rate": 4.84951947395043e-05, "loss": 0.7534, "step": 3350 }, { "epoch": 2.03, "learning_rate": 4.8474119035575786e-05, "loss": 0.6703, "step": 3360 }, { "epoch": 2.03, "learning_rate": 4.845304333164728e-05, "loss": 0.7521, "step": 3370 }, { "epoch": 2.03, "learning_rate": 4.8431967627718766e-05, "loss": 0.5594, "step": 3380 }, { "epoch": 2.03, "learning_rate": 4.8410891923790256e-05, "loss": 0.6991, "step": 3390 }, { "epoch": 2.03, "learning_rate": 4.8389816219861746e-05, "loss": 0.7109, "step": 3400 }, { "epoch": 2.03, "learning_rate": 4.8368740515933236e-05, "loss": 0.357, "step": 3410 }, { "epoch": 2.03, "learning_rate": 4.8347664812004726e-05, "loss": 0.6967, "step": 3420 }, { "epoch": 2.03, "learning_rate": 4.8326589108076216e-05, "loss": 0.67, "step": 3430 }, { "epoch": 2.03, "learning_rate": 4.83055134041477e-05, "loss": 0.4951, "step": 3440 }, { "epoch": 2.03, "learning_rate": 4.828443770021919e-05, "loss": 0.6282, "step": 3450 }, { "epoch": 2.03, "learning_rate": 4.826336199629068e-05, "loss": 0.7869, "step": 3460 }, { "epoch": 2.03, "learning_rate": 4.824228629236217e-05, "loss": 0.4811, "step": 3470 }, { "epoch": 2.03, "learning_rate": 4.822121058843366e-05, "loss": 0.7678, "step": 3480 }, { "epoch": 2.03, "learning_rate": 4.820013488450514e-05, "loss": 0.7246, "step": 3490 }, { "epoch": 2.03, "learning_rate": 4.817905918057664e-05, "loss": 0.4494, "step": 3500 }, { "epoch": 2.03, "learning_rate": 4.815798347664812e-05, "loss": 0.4555, "step": 3510 }, { "epoch": 2.03, "learning_rate": 4.813690777271961e-05, "loss": 0.7484, "step": 3520 }, { "epoch": 2.03, "learning_rate": 4.81158320687911e-05, "loss": 0.72, "step": 3530 }, { "epoch": 2.03, "learning_rate": 4.8094756364862585e-05, "loss": 0.6443, "step": 3540 }, { "epoch": 2.03, "learning_rate": 4.807368066093408e-05, "loss": 0.8899, "step": 3550 }, { "epoch": 2.03, "learning_rate": 4.8052604957005565e-05, "loss": 0.5806, "step": 3560 }, { "epoch": 2.04, "learning_rate": 4.8031529253077055e-05, "loss": 0.4642, "step": 3570 }, { "epoch": 2.04, "learning_rate": 4.8010453549148545e-05, "loss": 0.467, "step": 3580 }, { "epoch": 2.04, "learning_rate": 4.7989377845220035e-05, "loss": 0.6369, "step": 3590 }, { "epoch": 2.04, "learning_rate": 4.7968302141291525e-05, "loss": 0.5246, "step": 3600 }, { "epoch": 2.04, "learning_rate": 4.794722643736301e-05, "loss": 0.6002, "step": 3610 }, { "epoch": 2.04, "learning_rate": 4.79261507334345e-05, "loss": 0.5689, "step": 3620 }, { "epoch": 2.04, "learning_rate": 4.790507502950599e-05, "loss": 0.6291, "step": 3630 }, { "epoch": 2.04, "learning_rate": 4.788399932557748e-05, "loss": 0.572, "step": 3640 }, { "epoch": 2.04, "learning_rate": 4.786292362164896e-05, "loss": 0.4498, "step": 3650 }, { "epoch": 2.04, "learning_rate": 4.784184791772046e-05, "loss": 0.3739, "step": 3660 }, { "epoch": 2.04, "learning_rate": 4.782077221379194e-05, "loss": 0.793, "step": 3670 }, { "epoch": 2.04, "learning_rate": 4.779969650986344e-05, "loss": 0.5815, "step": 3680 }, { "epoch": 2.04, "learning_rate": 4.777862080593492e-05, "loss": 0.4536, "step": 3690 }, { "epoch": 2.04, "learning_rate": 4.7757545102006404e-05, "loss": 0.8622, "step": 3700 }, { "epoch": 2.04, "learning_rate": 4.77364693980779e-05, "loss": 0.5959, "step": 3710 }, { "epoch": 2.04, "learning_rate": 4.7715393694149384e-05, "loss": 0.7036, "step": 3720 }, { "epoch": 2.04, "learning_rate": 4.769431799022088e-05, "loss": 0.404, "step": 3730 }, { "epoch": 2.04, "learning_rate": 4.7673242286292363e-05, "loss": 0.3844, "step": 3740 }, { "epoch": 2.04, "learning_rate": 4.765216658236385e-05, "loss": 0.6977, "step": 3750 }, { "epoch": 2.04, "learning_rate": 4.763109087843534e-05, "loss": 0.666, "step": 3760 }, { "epoch": 2.04, "learning_rate": 4.761001517450683e-05, "loss": 0.3494, "step": 3770 }, { "epoch": 2.04, "learning_rate": 4.758893947057832e-05, "loss": 0.5597, "step": 3780 }, { "epoch": 2.04, "learning_rate": 4.7567863766649806e-05, "loss": 0.6307, "step": 3790 }, { "epoch": 2.04, "learning_rate": 4.7546788062721296e-05, "loss": 0.5367, "step": 3800 }, { "epoch": 2.04, "learning_rate": 4.7525712358792786e-05, "loss": 0.5488, "step": 3810 }, { "epoch": 2.04, "learning_rate": 4.7504636654864276e-05, "loss": 0.5136, "step": 3820 }, { "epoch": 2.05, "learning_rate": 4.748356095093576e-05, "loss": 0.524, "step": 3830 }, { "epoch": 2.05, "learning_rate": 4.7462485247007256e-05, "loss": 0.5213, "step": 3840 }, { "epoch": 2.05, "learning_rate": 4.744140954307874e-05, "loss": 0.6154, "step": 3850 }, { "epoch": 2.05, "learning_rate": 4.742033383915023e-05, "loss": 0.6145, "step": 3860 }, { "epoch": 2.05, "learning_rate": 4.739925813522172e-05, "loss": 0.5454, "step": 3870 }, { "epoch": 2.05, "learning_rate": 4.73781824312932e-05, "loss": 0.6215, "step": 3880 }, { "epoch": 2.05, "learning_rate": 4.73571067273647e-05, "loss": 0.4752, "step": 3890 }, { "epoch": 2.05, "learning_rate": 4.733603102343618e-05, "loss": 0.5089, "step": 3900 }, { "epoch": 2.05, "learning_rate": 4.731495531950768e-05, "loss": 0.3631, "step": 3910 }, { "epoch": 2.05, "learning_rate": 4.729387961557916e-05, "loss": 0.4482, "step": 3920 }, { "epoch": 2.05, "learning_rate": 4.727280391165065e-05, "loss": 0.4062, "step": 3930 }, { "epoch": 2.05, "learning_rate": 4.725172820772214e-05, "loss": 0.581, "step": 3940 }, { "epoch": 2.05, "learning_rate": 4.7230652503793625e-05, "loss": 0.676, "step": 3950 }, { "epoch": 2.05, "eval_accuracy": 0.5866339827119081, "eval_loss": 1.6156681776046753, "eval_runtime": 646.5336, "eval_samples_per_second": 11.989, "eval_steps_per_second": 1.998, "step": 3957 }, { "epoch": 3.0, "learning_rate": 4.7209576799865115e-05, "loss": 0.6418, "step": 3960 }, { "epoch": 3.0, "learning_rate": 4.7188501095936605e-05, "loss": 0.3614, "step": 3970 }, { "epoch": 3.0, "learning_rate": 4.7167425392008095e-05, "loss": 0.2603, "step": 3980 }, { "epoch": 3.0, "learning_rate": 4.7146349688079585e-05, "loss": 0.2727, "step": 3990 }, { "epoch": 3.0, "learning_rate": 4.7125273984151075e-05, "loss": 0.5662, "step": 4000 }, { "epoch": 3.0, "learning_rate": 4.710419828022256e-05, "loss": 0.4175, "step": 4010 }, { "epoch": 3.0, "learning_rate": 4.7083122576294055e-05, "loss": 0.3437, "step": 4020 }, { "epoch": 3.0, "learning_rate": 4.706204687236554e-05, "loss": 0.4068, "step": 4030 }, { "epoch": 3.0, "learning_rate": 4.704097116843703e-05, "loss": 0.3509, "step": 4040 }, { "epoch": 3.0, "learning_rate": 4.701989546450852e-05, "loss": 0.4293, "step": 4050 }, { "epoch": 3.0, "learning_rate": 4.699881976058e-05, "loss": 0.5772, "step": 4060 }, { "epoch": 3.0, "learning_rate": 4.69777440566515e-05, "loss": 0.5707, "step": 4070 }, { "epoch": 3.0, "learning_rate": 4.695666835272298e-05, "loss": 0.4496, "step": 4080 }, { "epoch": 3.01, "learning_rate": 4.693559264879447e-05, "loss": 0.4237, "step": 4090 }, { "epoch": 3.01, "learning_rate": 4.691451694486596e-05, "loss": 0.3144, "step": 4100 }, { "epoch": 3.01, "learning_rate": 4.6893441240937444e-05, "loss": 0.3843, "step": 4110 }, { "epoch": 3.01, "learning_rate": 4.687236553700894e-05, "loss": 0.2888, "step": 4120 }, { "epoch": 3.01, "learning_rate": 4.6851289833080424e-05, "loss": 0.297, "step": 4130 }, { "epoch": 3.01, "learning_rate": 4.6830214129151914e-05, "loss": 0.5346, "step": 4140 }, { "epoch": 3.01, "learning_rate": 4.6809138425223404e-05, "loss": 0.5057, "step": 4150 }, { "epoch": 3.01, "learning_rate": 4.6788062721294894e-05, "loss": 0.4377, "step": 4160 }, { "epoch": 3.01, "learning_rate": 4.6766987017366384e-05, "loss": 0.816, "step": 4170 }, { "epoch": 3.01, "learning_rate": 4.6745911313437873e-05, "loss": 0.4945, "step": 4180 }, { "epoch": 3.01, "learning_rate": 4.672483560950936e-05, "loss": 0.3932, "step": 4190 }, { "epoch": 3.01, "learning_rate": 4.6703759905580847e-05, "loss": 0.2313, "step": 4200 }, { "epoch": 3.01, "learning_rate": 4.6682684201652337e-05, "loss": 0.2922, "step": 4210 }, { "epoch": 3.01, "learning_rate": 4.6661608497723826e-05, "loss": 0.2544, "step": 4220 }, { "epoch": 3.01, "learning_rate": 4.6640532793795316e-05, "loss": 0.4625, "step": 4230 }, { "epoch": 3.01, "learning_rate": 4.66194570898668e-05, "loss": 0.1986, "step": 4240 }, { "epoch": 3.01, "learning_rate": 4.6598381385938296e-05, "loss": 0.7338, "step": 4250 }, { "epoch": 3.01, "learning_rate": 4.657730568200978e-05, "loss": 0.377, "step": 4260 }, { "epoch": 3.01, "learning_rate": 4.655622997808127e-05, "loss": 0.1785, "step": 4270 }, { "epoch": 3.01, "learning_rate": 4.653515427415276e-05, "loss": 0.2459, "step": 4280 }, { "epoch": 3.01, "learning_rate": 4.651407857022424e-05, "loss": 0.4283, "step": 4290 }, { "epoch": 3.01, "learning_rate": 4.649300286629574e-05, "loss": 0.4453, "step": 4300 }, { "epoch": 3.01, "learning_rate": 4.647192716236722e-05, "loss": 0.292, "step": 4310 }, { "epoch": 3.01, "learning_rate": 4.645085145843871e-05, "loss": 0.581, "step": 4320 }, { "epoch": 3.01, "learning_rate": 4.64297757545102e-05, "loss": 0.5727, "step": 4330 }, { "epoch": 3.01, "learning_rate": 4.640870005058169e-05, "loss": 0.2216, "step": 4340 }, { "epoch": 3.01, "learning_rate": 4.638762434665318e-05, "loss": 0.1869, "step": 4350 }, { "epoch": 3.02, "learning_rate": 4.6366548642724665e-05, "loss": 0.5511, "step": 4360 }, { "epoch": 3.02, "learning_rate": 4.6345472938796155e-05, "loss": 0.5957, "step": 4370 }, { "epoch": 3.02, "learning_rate": 4.6324397234867645e-05, "loss": 0.3203, "step": 4380 }, { "epoch": 3.02, "learning_rate": 4.6303321530939135e-05, "loss": 0.361, "step": 4390 }, { "epoch": 3.02, "learning_rate": 4.6282245827010625e-05, "loss": 0.4562, "step": 4400 }, { "epoch": 3.02, "learning_rate": 4.6261170123082115e-05, "loss": 0.277, "step": 4410 }, { "epoch": 3.02, "learning_rate": 4.62400944191536e-05, "loss": 0.3882, "step": 4420 }, { "epoch": 3.02, "learning_rate": 4.6219018715225095e-05, "loss": 0.483, "step": 4430 }, { "epoch": 3.02, "learning_rate": 4.619794301129658e-05, "loss": 0.4542, "step": 4440 }, { "epoch": 3.02, "learning_rate": 4.617686730736807e-05, "loss": 0.3737, "step": 4450 }, { "epoch": 3.02, "learning_rate": 4.615579160343956e-05, "loss": 0.1152, "step": 4460 }, { "epoch": 3.02, "learning_rate": 4.613471589951104e-05, "loss": 0.207, "step": 4470 }, { "epoch": 3.02, "learning_rate": 4.611364019558254e-05, "loss": 0.5553, "step": 4480 }, { "epoch": 3.02, "learning_rate": 4.609256449165402e-05, "loss": 0.2193, "step": 4490 }, { "epoch": 3.02, "learning_rate": 4.607148878772551e-05, "loss": 0.518, "step": 4500 }, { "epoch": 3.02, "learning_rate": 4.6050413083797e-05, "loss": 0.4581, "step": 4510 }, { "epoch": 3.02, "learning_rate": 4.602933737986849e-05, "loss": 0.2633, "step": 4520 }, { "epoch": 3.02, "learning_rate": 4.600826167593998e-05, "loss": 0.2761, "step": 4530 }, { "epoch": 3.02, "learning_rate": 4.5987185972011464e-05, "loss": 0.2893, "step": 4540 }, { "epoch": 3.02, "learning_rate": 4.5966110268082954e-05, "loss": 0.3202, "step": 4550 }, { "epoch": 3.02, "learning_rate": 4.5945034564154444e-05, "loss": 0.4685, "step": 4560 }, { "epoch": 3.02, "learning_rate": 4.5923958860225934e-05, "loss": 0.4898, "step": 4570 }, { "epoch": 3.02, "learning_rate": 4.5902883156297424e-05, "loss": 0.589, "step": 4580 }, { "epoch": 3.02, "learning_rate": 4.5881807452368914e-05, "loss": 0.2862, "step": 4590 }, { "epoch": 3.02, "learning_rate": 4.58607317484404e-05, "loss": 0.2961, "step": 4600 }, { "epoch": 3.02, "learning_rate": 4.5839656044511894e-05, "loss": 0.5167, "step": 4610 }, { "epoch": 3.03, "learning_rate": 4.581858034058338e-05, "loss": 0.2775, "step": 4620 }, { "epoch": 3.03, "learning_rate": 4.579750463665487e-05, "loss": 0.5435, "step": 4630 }, { "epoch": 3.03, "learning_rate": 4.577642893272636e-05, "loss": 0.3508, "step": 4640 }, { "epoch": 3.03, "learning_rate": 4.575535322879784e-05, "loss": 0.4437, "step": 4650 }, { "epoch": 3.03, "learning_rate": 4.5734277524869337e-05, "loss": 0.5257, "step": 4660 }, { "epoch": 3.03, "learning_rate": 4.571320182094082e-05, "loss": 0.3163, "step": 4670 }, { "epoch": 3.03, "learning_rate": 4.569212611701231e-05, "loss": 0.3354, "step": 4680 }, { "epoch": 3.03, "learning_rate": 4.56710504130838e-05, "loss": 0.2716, "step": 4690 }, { "epoch": 3.03, "learning_rate": 4.564997470915528e-05, "loss": 0.3567, "step": 4700 }, { "epoch": 3.03, "learning_rate": 4.562889900522678e-05, "loss": 0.3222, "step": 4710 }, { "epoch": 3.03, "learning_rate": 4.560782330129826e-05, "loss": 0.4045, "step": 4720 }, { "epoch": 3.03, "learning_rate": 4.558674759736975e-05, "loss": 0.4866, "step": 4730 }, { "epoch": 3.03, "learning_rate": 4.556567189344124e-05, "loss": 0.317, "step": 4740 }, { "epoch": 3.03, "learning_rate": 4.554459618951273e-05, "loss": 0.1727, "step": 4750 }, { "epoch": 3.03, "learning_rate": 4.552352048558422e-05, "loss": 0.3413, "step": 4760 }, { "epoch": 3.03, "learning_rate": 4.550244478165571e-05, "loss": 0.2314, "step": 4770 }, { "epoch": 3.03, "learning_rate": 4.5481369077727196e-05, "loss": 0.2794, "step": 4780 }, { "epoch": 3.03, "learning_rate": 4.5460293373798686e-05, "loss": 0.5064, "step": 4790 }, { "epoch": 3.03, "learning_rate": 4.5439217669870175e-05, "loss": 0.2633, "step": 4800 }, { "epoch": 3.03, "learning_rate": 4.5418141965941665e-05, "loss": 0.2901, "step": 4810 }, { "epoch": 3.03, "learning_rate": 4.5397066262013155e-05, "loss": 0.5034, "step": 4820 }, { "epoch": 3.03, "learning_rate": 4.537599055808464e-05, "loss": 0.209, "step": 4830 }, { "epoch": 3.03, "learning_rate": 4.5354914854156135e-05, "loss": 0.2404, "step": 4840 }, { "epoch": 3.03, "learning_rate": 4.533383915022762e-05, "loss": 0.5545, "step": 4850 }, { "epoch": 3.03, "learning_rate": 4.531276344629911e-05, "loss": 0.3652, "step": 4860 }, { "epoch": 3.03, "learning_rate": 4.52916877423706e-05, "loss": 0.3644, "step": 4870 }, { "epoch": 3.04, "learning_rate": 4.527061203844208e-05, "loss": 0.3144, "step": 4880 }, { "epoch": 3.04, "learning_rate": 4.524953633451358e-05, "loss": 0.6066, "step": 4890 }, { "epoch": 3.04, "learning_rate": 4.522846063058506e-05, "loss": 0.3251, "step": 4900 }, { "epoch": 3.04, "learning_rate": 4.520738492665655e-05, "loss": 0.1698, "step": 4910 }, { "epoch": 3.04, "learning_rate": 4.518630922272804e-05, "loss": 0.2872, "step": 4920 }, { "epoch": 3.04, "learning_rate": 4.516523351879953e-05, "loss": 0.3595, "step": 4930 }, { "epoch": 3.04, "learning_rate": 4.514415781487102e-05, "loss": 0.2819, "step": 4940 }, { "epoch": 3.04, "learning_rate": 4.5123082110942504e-05, "loss": 0.4009, "step": 4950 }, { "epoch": 3.04, "learning_rate": 4.5102006407013994e-05, "loss": 0.427, "step": 4960 }, { "epoch": 3.04, "learning_rate": 4.5080930703085484e-05, "loss": 0.3406, "step": 4970 }, { "epoch": 3.04, "learning_rate": 4.5059854999156974e-05, "loss": 0.2869, "step": 4980 }, { "epoch": 3.04, "learning_rate": 4.5038779295228464e-05, "loss": 0.1353, "step": 4990 }, { "epoch": 3.04, "learning_rate": 4.5017703591299954e-05, "loss": 0.3642, "step": 5000 }, { "epoch": 3.04, "learning_rate": 4.499662788737144e-05, "loss": 0.1667, "step": 5010 }, { "epoch": 3.04, "learning_rate": 4.4975552183442934e-05, "loss": 0.3534, "step": 5020 }, { "epoch": 3.04, "learning_rate": 4.495447647951442e-05, "loss": 0.4473, "step": 5030 }, { "epoch": 3.04, "learning_rate": 4.493340077558591e-05, "loss": 0.2571, "step": 5040 }, { "epoch": 3.04, "learning_rate": 4.49123250716574e-05, "loss": 0.5701, "step": 5050 }, { "epoch": 3.04, "learning_rate": 4.489124936772888e-05, "loss": 0.209, "step": 5060 }, { "epoch": 3.04, "learning_rate": 4.487017366380038e-05, "loss": 0.4786, "step": 5070 }, { "epoch": 3.04, "learning_rate": 4.484909795987186e-05, "loss": 0.1807, "step": 5080 }, { "epoch": 3.04, "learning_rate": 4.482802225594335e-05, "loss": 0.2774, "step": 5090 }, { "epoch": 3.04, "learning_rate": 4.480694655201484e-05, "loss": 0.3292, "step": 5100 }, { "epoch": 3.04, "learning_rate": 4.478587084808633e-05, "loss": 0.2858, "step": 5110 }, { "epoch": 3.04, "learning_rate": 4.476479514415782e-05, "loss": 0.4138, "step": 5120 }, { "epoch": 3.04, "learning_rate": 4.47437194402293e-05, "loss": 0.1634, "step": 5130 }, { "epoch": 3.04, "learning_rate": 4.472264373630079e-05, "loss": 0.303, "step": 5140 }, { "epoch": 3.05, "learning_rate": 4.470156803237228e-05, "loss": 0.2129, "step": 5150 }, { "epoch": 3.05, "learning_rate": 4.468049232844377e-05, "loss": 0.3426, "step": 5160 }, { "epoch": 3.05, "learning_rate": 4.465941662451526e-05, "loss": 0.4543, "step": 5170 }, { "epoch": 3.05, "learning_rate": 4.463834092058675e-05, "loss": 0.3419, "step": 5180 }, { "epoch": 3.05, "learning_rate": 4.4617265216658236e-05, "loss": 0.4096, "step": 5190 }, { "epoch": 3.05, "learning_rate": 4.4596189512729726e-05, "loss": 0.2696, "step": 5200 }, { "epoch": 3.05, "learning_rate": 4.4575113808801216e-05, "loss": 0.1778, "step": 5210 }, { "epoch": 3.05, "learning_rate": 4.4554038104872706e-05, "loss": 0.4102, "step": 5220 }, { "epoch": 3.05, "learning_rate": 4.4532962400944196e-05, "loss": 0.5422, "step": 5230 }, { "epoch": 3.05, "learning_rate": 4.451188669701568e-05, "loss": 0.3684, "step": 5240 }, { "epoch": 3.05, "learning_rate": 4.4490810993087175e-05, "loss": 0.6357, "step": 5250 }, { "epoch": 3.05, "learning_rate": 4.446973528915866e-05, "loss": 0.3092, "step": 5260 }, { "epoch": 3.05, "learning_rate": 4.444865958523015e-05, "loss": 0.4869, "step": 5270 }, { "epoch": 3.05, "eval_accuracy": 0.7428718874983873, "eval_loss": 1.0127977132797241, "eval_runtime": 647.4659, "eval_samples_per_second": 11.971, "eval_steps_per_second": 1.995, "step": 5276 }, { "epoch": 4.0, "learning_rate": 4.442758388130164e-05, "loss": 0.177, "step": 5280 }, { "epoch": 4.0, "learning_rate": 4.440650817737312e-05, "loss": 0.2913, "step": 5290 }, { "epoch": 4.0, "learning_rate": 4.438543247344462e-05, "loss": 0.1199, "step": 5300 }, { "epoch": 4.0, "learning_rate": 4.43643567695161e-05, "loss": 0.3458, "step": 5310 }, { "epoch": 4.0, "learning_rate": 4.434328106558759e-05, "loss": 0.3838, "step": 5320 }, { "epoch": 4.0, "learning_rate": 4.432220536165908e-05, "loss": 0.3661, "step": 5330 }, { "epoch": 4.0, "learning_rate": 4.430112965773057e-05, "loss": 0.202, "step": 5340 }, { "epoch": 4.0, "learning_rate": 4.428005395380206e-05, "loss": 0.2447, "step": 5350 }, { "epoch": 4.0, "learning_rate": 4.425897824987355e-05, "loss": 0.2621, "step": 5360 }, { "epoch": 4.0, "learning_rate": 4.4237902545945034e-05, "loss": 0.616, "step": 5370 }, { "epoch": 4.0, "learning_rate": 4.4216826842016524e-05, "loss": 0.2259, "step": 5380 }, { "epoch": 4.0, "learning_rate": 4.4195751138088014e-05, "loss": 0.3565, "step": 5390 }, { "epoch": 4.0, "learning_rate": 4.4174675434159504e-05, "loss": 0.1403, "step": 5400 }, { "epoch": 4.01, "learning_rate": 4.4153599730230994e-05, "loss": 0.1834, "step": 5410 }, { "epoch": 4.01, "learning_rate": 4.413252402630248e-05, "loss": 0.2413, "step": 5420 }, { "epoch": 4.01, "learning_rate": 4.4111448322373974e-05, "loss": 0.2226, "step": 5430 }, { "epoch": 4.01, "learning_rate": 4.409037261844546e-05, "loss": 0.2338, "step": 5440 }, { "epoch": 4.01, "learning_rate": 4.406929691451695e-05, "loss": 0.1076, "step": 5450 }, { "epoch": 4.01, "learning_rate": 4.404822121058844e-05, "loss": 0.1769, "step": 5460 }, { "epoch": 4.01, "learning_rate": 4.402714550665992e-05, "loss": 0.3295, "step": 5470 }, { "epoch": 4.01, "learning_rate": 4.400606980273142e-05, "loss": 0.2033, "step": 5480 }, { "epoch": 4.01, "learning_rate": 4.39849940988029e-05, "loss": 0.1455, "step": 5490 }, { "epoch": 4.01, "learning_rate": 4.396391839487439e-05, "loss": 0.1663, "step": 5500 }, { "epoch": 4.01, "learning_rate": 4.394284269094588e-05, "loss": 0.3529, "step": 5510 }, { "epoch": 4.01, "learning_rate": 4.392176698701737e-05, "loss": 0.2741, "step": 5520 }, { "epoch": 4.01, "learning_rate": 4.390069128308886e-05, "loss": 0.4579, "step": 5530 }, { "epoch": 4.01, "learning_rate": 4.387961557916034e-05, "loss": 0.2324, "step": 5540 }, { "epoch": 4.01, "learning_rate": 4.385853987523183e-05, "loss": 0.1154, "step": 5550 }, { "epoch": 4.01, "learning_rate": 4.383746417130332e-05, "loss": 0.2296, "step": 5560 }, { "epoch": 4.01, "learning_rate": 4.381638846737481e-05, "loss": 0.0611, "step": 5570 }, { "epoch": 4.01, "learning_rate": 4.37953127634463e-05, "loss": 0.1586, "step": 5580 }, { "epoch": 4.01, "learning_rate": 4.377423705951779e-05, "loss": 0.3691, "step": 5590 }, { "epoch": 4.01, "learning_rate": 4.3753161355589276e-05, "loss": 0.1593, "step": 5600 }, { "epoch": 4.01, "learning_rate": 4.373208565166077e-05, "loss": 0.2794, "step": 5610 }, { "epoch": 4.01, "learning_rate": 4.3711009947732256e-05, "loss": 0.1267, "step": 5620 }, { "epoch": 4.01, "learning_rate": 4.3689934243803746e-05, "loss": 0.2784, "step": 5630 }, { "epoch": 4.01, "learning_rate": 4.3668858539875236e-05, "loss": 0.1026, "step": 5640 }, { "epoch": 4.01, "learning_rate": 4.364778283594672e-05, "loss": 0.2721, "step": 5650 }, { "epoch": 4.01, "learning_rate": 4.3626707132018216e-05, "loss": 0.2624, "step": 5660 }, { "epoch": 4.01, "learning_rate": 4.36056314280897e-05, "loss": 0.3984, "step": 5670 }, { "epoch": 4.02, "learning_rate": 4.358455572416119e-05, "loss": 0.1997, "step": 5680 }, { "epoch": 4.02, "learning_rate": 4.356348002023268e-05, "loss": 0.2375, "step": 5690 }, { "epoch": 4.02, "learning_rate": 4.354240431630416e-05, "loss": 0.2193, "step": 5700 }, { "epoch": 4.02, "learning_rate": 4.352132861237566e-05, "loss": 0.23, "step": 5710 }, { "epoch": 4.02, "learning_rate": 4.350025290844714e-05, "loss": 0.1779, "step": 5720 }, { "epoch": 4.02, "learning_rate": 4.347917720451863e-05, "loss": 0.2449, "step": 5730 }, { "epoch": 4.02, "learning_rate": 4.345810150059012e-05, "loss": 0.2579, "step": 5740 }, { "epoch": 4.02, "learning_rate": 4.343702579666161e-05, "loss": 0.0516, "step": 5750 }, { "epoch": 4.02, "learning_rate": 4.34159500927331e-05, "loss": 0.2237, "step": 5760 }, { "epoch": 4.02, "learning_rate": 4.339487438880459e-05, "loss": 0.159, "step": 5770 }, { "epoch": 4.02, "learning_rate": 4.3373798684876075e-05, "loss": 0.1894, "step": 5780 }, { "epoch": 4.02, "learning_rate": 4.3352722980947565e-05, "loss": 0.381, "step": 5790 }, { "epoch": 4.02, "learning_rate": 4.3331647277019055e-05, "loss": 0.2324, "step": 5800 }, { "epoch": 4.02, "learning_rate": 4.3310571573090545e-05, "loss": 0.2134, "step": 5810 }, { "epoch": 4.02, "learning_rate": 4.3289495869162034e-05, "loss": 0.0918, "step": 5820 }, { "epoch": 4.02, "learning_rate": 4.326842016523352e-05, "loss": 0.0286, "step": 5830 }, { "epoch": 4.02, "learning_rate": 4.3247344461305014e-05, "loss": 0.1793, "step": 5840 }, { "epoch": 4.02, "learning_rate": 4.32262687573765e-05, "loss": 0.4101, "step": 5850 }, { "epoch": 4.02, "learning_rate": 4.320519305344799e-05, "loss": 0.2538, "step": 5860 }, { "epoch": 4.02, "learning_rate": 4.318411734951948e-05, "loss": 0.0729, "step": 5870 }, { "epoch": 4.02, "learning_rate": 4.316304164559096e-05, "loss": 0.2183, "step": 5880 }, { "epoch": 4.02, "learning_rate": 4.314196594166246e-05, "loss": 0.164, "step": 5890 }, { "epoch": 4.02, "learning_rate": 4.312089023773394e-05, "loss": 0.1658, "step": 5900 }, { "epoch": 4.02, "learning_rate": 4.309981453380543e-05, "loss": 0.1667, "step": 5910 }, { "epoch": 4.02, "learning_rate": 4.307873882987692e-05, "loss": 0.1992, "step": 5920 }, { "epoch": 4.02, "learning_rate": 4.305766312594841e-05, "loss": 0.1865, "step": 5930 }, { "epoch": 4.03, "learning_rate": 4.30365874220199e-05, "loss": 0.1686, "step": 5940 }, { "epoch": 4.03, "learning_rate": 4.3015511718091383e-05, "loss": 0.1537, "step": 5950 }, { "epoch": 4.03, "learning_rate": 4.299443601416287e-05, "loss": 0.3576, "step": 5960 }, { "epoch": 4.03, "learning_rate": 4.297336031023436e-05, "loss": 0.2725, "step": 5970 }, { "epoch": 4.03, "learning_rate": 4.295228460630585e-05, "loss": 0.0928, "step": 5980 }, { "epoch": 4.03, "learning_rate": 4.293120890237734e-05, "loss": 0.3768, "step": 5990 }, { "epoch": 4.03, "learning_rate": 4.291013319844883e-05, "loss": 0.1115, "step": 6000 }, { "epoch": 4.03, "learning_rate": 4.2889057494520316e-05, "loss": 0.1907, "step": 6010 }, { "epoch": 4.03, "learning_rate": 4.286798179059181e-05, "loss": 0.2348, "step": 6020 }, { "epoch": 4.03, "learning_rate": 4.2846906086663296e-05, "loss": 0.0956, "step": 6030 }, { "epoch": 4.03, "learning_rate": 4.2825830382734786e-05, "loss": 0.2364, "step": 6040 }, { "epoch": 4.03, "learning_rate": 4.2804754678806276e-05, "loss": 0.1108, "step": 6050 }, { "epoch": 4.03, "learning_rate": 4.278367897487776e-05, "loss": 0.1966, "step": 6060 }, { "epoch": 4.03, "learning_rate": 4.2762603270949256e-05, "loss": 0.0861, "step": 6070 }, { "epoch": 4.03, "learning_rate": 4.274152756702074e-05, "loss": 0.2979, "step": 6080 }, { "epoch": 4.03, "learning_rate": 4.272045186309223e-05, "loss": 0.3533, "step": 6090 }, { "epoch": 4.03, "learning_rate": 4.269937615916372e-05, "loss": 0.1652, "step": 6100 }, { "epoch": 4.03, "learning_rate": 4.267830045523521e-05, "loss": 0.4561, "step": 6110 }, { "epoch": 4.03, "learning_rate": 4.26572247513067e-05, "loss": 0.5252, "step": 6120 }, { "epoch": 4.03, "learning_rate": 4.263614904737818e-05, "loss": 0.2804, "step": 6130 }, { "epoch": 4.03, "learning_rate": 4.261507334344967e-05, "loss": 0.3027, "step": 6140 }, { "epoch": 4.03, "learning_rate": 4.259399763952116e-05, "loss": 0.136, "step": 6150 }, { "epoch": 4.03, "learning_rate": 4.257292193559265e-05, "loss": 0.1249, "step": 6160 }, { "epoch": 4.03, "learning_rate": 4.255184623166414e-05, "loss": 0.1661, "step": 6170 }, { "epoch": 4.03, "learning_rate": 4.253077052773563e-05, "loss": 0.1447, "step": 6180 }, { "epoch": 4.03, "learning_rate": 4.2509694823807115e-05, "loss": 0.1439, "step": 6190 }, { "epoch": 4.04, "learning_rate": 4.2488619119878605e-05, "loss": 0.4538, "step": 6200 }, { "epoch": 4.04, "learning_rate": 4.2467543415950095e-05, "loss": 0.3134, "step": 6210 }, { "epoch": 4.04, "learning_rate": 4.2446467712021585e-05, "loss": 0.1245, "step": 6220 }, { "epoch": 4.04, "learning_rate": 4.2425392008093075e-05, "loss": 0.3171, "step": 6230 }, { "epoch": 4.04, "learning_rate": 4.240431630416456e-05, "loss": 0.1668, "step": 6240 }, { "epoch": 4.04, "learning_rate": 4.2383240600236055e-05, "loss": 0.1103, "step": 6250 }, { "epoch": 4.04, "learning_rate": 4.236216489630754e-05, "loss": 0.2651, "step": 6260 }, { "epoch": 4.04, "learning_rate": 4.234108919237903e-05, "loss": 0.422, "step": 6270 }, { "epoch": 4.04, "learning_rate": 4.232001348845052e-05, "loss": 0.1069, "step": 6280 }, { "epoch": 4.04, "learning_rate": 4.2298937784522e-05, "loss": 0.027, "step": 6290 }, { "epoch": 4.04, "learning_rate": 4.22778620805935e-05, "loss": 0.036, "step": 6300 }, { "epoch": 4.04, "learning_rate": 4.225678637666498e-05, "loss": 0.4745, "step": 6310 }, { "epoch": 4.04, "learning_rate": 4.223571067273647e-05, "loss": 0.2455, "step": 6320 }, { "epoch": 4.04, "learning_rate": 4.221463496880796e-05, "loss": 0.2221, "step": 6330 }, { "epoch": 4.04, "learning_rate": 4.219355926487945e-05, "loss": 0.1865, "step": 6340 }, { "epoch": 4.04, "learning_rate": 4.217248356095094e-05, "loss": 0.4888, "step": 6350 }, { "epoch": 4.04, "learning_rate": 4.215140785702243e-05, "loss": 0.0571, "step": 6360 }, { "epoch": 4.04, "learning_rate": 4.2130332153093914e-05, "loss": 0.0955, "step": 6370 }, { "epoch": 4.04, "learning_rate": 4.2109256449165404e-05, "loss": 0.0715, "step": 6380 }, { "epoch": 4.04, "learning_rate": 4.2088180745236894e-05, "loss": 0.2241, "step": 6390 }, { "epoch": 4.04, "learning_rate": 4.206710504130838e-05, "loss": 0.3646, "step": 6400 }, { "epoch": 4.04, "learning_rate": 4.2046029337379873e-05, "loss": 0.3002, "step": 6410 }, { "epoch": 4.04, "learning_rate": 4.2024953633451357e-05, "loss": 0.2378, "step": 6420 }, { "epoch": 4.04, "learning_rate": 4.200387792952285e-05, "loss": 0.3448, "step": 6430 }, { "epoch": 4.04, "learning_rate": 4.1982802225594336e-05, "loss": 0.4826, "step": 6440 }, { "epoch": 4.04, "learning_rate": 4.1961726521665826e-05, "loss": 0.0956, "step": 6450 }, { "epoch": 4.04, "learning_rate": 4.1940650817737316e-05, "loss": 0.5153, "step": 6460 }, { "epoch": 4.05, "learning_rate": 4.19195751138088e-05, "loss": 0.2696, "step": 6470 }, { "epoch": 4.05, "learning_rate": 4.1898499409880296e-05, "loss": 0.4102, "step": 6480 }, { "epoch": 4.05, "learning_rate": 4.187742370595178e-05, "loss": 0.2704, "step": 6490 }, { "epoch": 4.05, "learning_rate": 4.185634800202327e-05, "loss": 0.3626, "step": 6500 }, { "epoch": 4.05, "learning_rate": 4.183527229809476e-05, "loss": 0.289, "step": 6510 }, { "epoch": 4.05, "learning_rate": 4.181419659416625e-05, "loss": 0.0829, "step": 6520 }, { "epoch": 4.05, "learning_rate": 4.179312089023774e-05, "loss": 0.0207, "step": 6530 }, { "epoch": 4.05, "learning_rate": 4.177204518630922e-05, "loss": 0.1628, "step": 6540 }, { "epoch": 4.05, "learning_rate": 4.175096948238071e-05, "loss": 0.3298, "step": 6550 }, { "epoch": 4.05, "learning_rate": 4.17298937784522e-05, "loss": 0.2431, "step": 6560 }, { "epoch": 4.05, "learning_rate": 4.170881807452369e-05, "loss": 0.3157, "step": 6570 }, { "epoch": 4.05, "learning_rate": 4.1687742370595175e-05, "loss": 0.1704, "step": 6580 }, { "epoch": 4.05, "learning_rate": 4.166666666666667e-05, "loss": 0.1384, "step": 6590 }, { "epoch": 4.05, "eval_accuracy": 0.7600309637466134, "eval_loss": 1.0486570596694946, "eval_runtime": 648.1678, "eval_samples_per_second": 11.958, "eval_steps_per_second": 1.993, "step": 6595 }, { "epoch": 5.0, "learning_rate": 4.1645590962738155e-05, "loss": 0.1206, "step": 6600 }, { "epoch": 5.0, "learning_rate": 4.162451525880965e-05, "loss": 0.1343, "step": 6610 }, { "epoch": 5.0, "learning_rate": 4.1603439554881135e-05, "loss": 0.1016, "step": 6620 }, { "epoch": 5.0, "learning_rate": 4.158236385095262e-05, "loss": 0.1174, "step": 6630 }, { "epoch": 5.0, "learning_rate": 4.1561288147024115e-05, "loss": 0.1494, "step": 6640 }, { "epoch": 5.0, "learning_rate": 4.15402124430956e-05, "loss": 0.2598, "step": 6650 }, { "epoch": 5.0, "learning_rate": 4.1519136739167095e-05, "loss": 0.1995, "step": 6660 }, { "epoch": 5.0, "learning_rate": 4.149806103523858e-05, "loss": 0.2618, "step": 6670 }, { "epoch": 5.0, "learning_rate": 4.147698533131007e-05, "loss": 0.0376, "step": 6680 }, { "epoch": 5.0, "learning_rate": 4.145590962738156e-05, "loss": 0.0857, "step": 6690 }, { "epoch": 5.0, "learning_rate": 4.143483392345305e-05, "loss": 0.1378, "step": 6700 }, { "epoch": 5.0, "learning_rate": 4.141375821952453e-05, "loss": 0.1517, "step": 6710 }, { "epoch": 5.0, "learning_rate": 4.139268251559602e-05, "loss": 0.0785, "step": 6720 }, { "epoch": 5.01, "learning_rate": 4.137160681166751e-05, "loss": 0.0116, "step": 6730 }, { "epoch": 5.01, "learning_rate": 4.1350531107739e-05, "loss": 0.1043, "step": 6740 }, { "epoch": 5.01, "learning_rate": 4.132945540381049e-05, "loss": 0.1452, "step": 6750 }, { "epoch": 5.01, "learning_rate": 4.1308379699881974e-05, "loss": 0.405, "step": 6760 }, { "epoch": 5.01, "learning_rate": 4.128730399595347e-05, "loss": 0.1676, "step": 6770 }, { "epoch": 5.01, "learning_rate": 4.1266228292024954e-05, "loss": 0.0867, "step": 6780 }, { "epoch": 5.01, "learning_rate": 4.1245152588096444e-05, "loss": 0.0821, "step": 6790 }, { "epoch": 5.01, "learning_rate": 4.1224076884167934e-05, "loss": 0.1357, "step": 6800 }, { "epoch": 5.01, "learning_rate": 4.120300118023942e-05, "loss": 0.1671, "step": 6810 }, { "epoch": 5.01, "learning_rate": 4.1181925476310914e-05, "loss": 0.124, "step": 6820 }, { "epoch": 5.01, "learning_rate": 4.11608497723824e-05, "loss": 0.3891, "step": 6830 }, { "epoch": 5.01, "learning_rate": 4.1139774068453894e-05, "loss": 0.2542, "step": 6840 }, { "epoch": 5.01, "learning_rate": 4.111869836452538e-05, "loss": 0.0824, "step": 6850 }, { "epoch": 5.01, "learning_rate": 4.109762266059687e-05, "loss": 0.2453, "step": 6860 }, { "epoch": 5.01, "learning_rate": 4.1076546956668357e-05, "loss": 0.1293, "step": 6870 }, { "epoch": 5.01, "learning_rate": 4.105547125273984e-05, "loss": 0.0177, "step": 6880 }, { "epoch": 5.01, "learning_rate": 4.103439554881133e-05, "loss": 0.2207, "step": 6890 }, { "epoch": 5.01, "learning_rate": 4.101331984488282e-05, "loss": 0.0735, "step": 6900 }, { "epoch": 5.01, "learning_rate": 4.099224414095431e-05, "loss": 0.1172, "step": 6910 }, { "epoch": 5.01, "learning_rate": 4.09711684370258e-05, "loss": 0.0927, "step": 6920 }, { "epoch": 5.01, "learning_rate": 4.095009273309729e-05, "loss": 0.102, "step": 6930 }, { "epoch": 5.01, "learning_rate": 4.092901702916877e-05, "loss": 0.0243, "step": 6940 }, { "epoch": 5.01, "learning_rate": 4.090794132524027e-05, "loss": 0.1573, "step": 6950 }, { "epoch": 5.01, "learning_rate": 4.088686562131175e-05, "loss": 0.1497, "step": 6960 }, { "epoch": 5.01, "learning_rate": 4.086578991738324e-05, "loss": 0.0873, "step": 6970 }, { "epoch": 5.01, "learning_rate": 4.084471421345473e-05, "loss": 0.2285, "step": 6980 }, { "epoch": 5.01, "learning_rate": 4.0823638509526216e-05, "loss": 0.1726, "step": 6990 }, { "epoch": 5.02, "learning_rate": 4.080256280559771e-05, "loss": 0.3354, "step": 7000 }, { "epoch": 5.02, "learning_rate": 4.0781487101669195e-05, "loss": 0.1363, "step": 7010 }, { "epoch": 5.02, "learning_rate": 4.0760411397740685e-05, "loss": 0.0677, "step": 7020 }, { "epoch": 5.02, "learning_rate": 4.0739335693812175e-05, "loss": 0.2911, "step": 7030 }, { "epoch": 5.02, "learning_rate": 4.071825998988366e-05, "loss": 0.2698, "step": 7040 }, { "epoch": 5.02, "learning_rate": 4.0697184285955155e-05, "loss": 0.4374, "step": 7050 }, { "epoch": 5.02, "learning_rate": 4.067610858202664e-05, "loss": 0.1656, "step": 7060 }, { "epoch": 5.02, "learning_rate": 4.065503287809813e-05, "loss": 0.023, "step": 7070 }, { "epoch": 5.02, "learning_rate": 4.063395717416962e-05, "loss": 0.1468, "step": 7080 }, { "epoch": 5.02, "learning_rate": 4.061288147024111e-05, "loss": 0.1328, "step": 7090 }, { "epoch": 5.02, "learning_rate": 4.05918057663126e-05, "loss": 0.1943, "step": 7100 }, { "epoch": 5.02, "learning_rate": 4.057073006238409e-05, "loss": 0.2757, "step": 7110 }, { "epoch": 5.02, "learning_rate": 4.054965435845557e-05, "loss": 0.1093, "step": 7120 }, { "epoch": 5.02, "learning_rate": 4.052857865452706e-05, "loss": 0.0385, "step": 7130 }, { "epoch": 5.02, "learning_rate": 4.050750295059855e-05, "loss": 0.1704, "step": 7140 }, { "epoch": 5.02, "learning_rate": 4.048642724667004e-05, "loss": 0.0183, "step": 7150 }, { "epoch": 5.02, "learning_rate": 4.046535154274153e-05, "loss": 0.0468, "step": 7160 }, { "epoch": 5.02, "learning_rate": 4.0444275838813014e-05, "loss": 0.0449, "step": 7170 }, { "epoch": 5.02, "learning_rate": 4.042320013488451e-05, "loss": 0.0331, "step": 7180 }, { "epoch": 5.02, "learning_rate": 4.0402124430955994e-05, "loss": 0.1036, "step": 7190 }, { "epoch": 5.02, "learning_rate": 4.0381048727027484e-05, "loss": 0.0465, "step": 7200 }, { "epoch": 5.02, "learning_rate": 4.0359973023098974e-05, "loss": 0.0518, "step": 7210 }, { "epoch": 5.02, "learning_rate": 4.033889731917046e-05, "loss": 0.1551, "step": 7220 }, { "epoch": 5.02, "learning_rate": 4.0317821615241954e-05, "loss": 0.0987, "step": 7230 }, { "epoch": 5.02, "learning_rate": 4.029674591131344e-05, "loss": 0.13, "step": 7240 }, { "epoch": 5.02, "learning_rate": 4.027567020738493e-05, "loss": 0.0196, "step": 7250 }, { "epoch": 5.03, "learning_rate": 4.025459450345642e-05, "loss": 0.2157, "step": 7260 }, { "epoch": 5.03, "learning_rate": 4.023351879952791e-05, "loss": 0.1829, "step": 7270 }, { "epoch": 5.03, "learning_rate": 4.02124430955994e-05, "loss": 0.1047, "step": 7280 }, { "epoch": 5.03, "learning_rate": 4.019136739167088e-05, "loss": 0.4507, "step": 7290 }, { "epoch": 5.03, "learning_rate": 4.017029168774237e-05, "loss": 0.1305, "step": 7300 }, { "epoch": 5.03, "learning_rate": 4.014921598381386e-05, "loss": 0.3593, "step": 7310 }, { "epoch": 5.03, "learning_rate": 4.012814027988535e-05, "loss": 0.1084, "step": 7320 }, { "epoch": 5.03, "learning_rate": 4.010706457595684e-05, "loss": 0.2447, "step": 7330 }, { "epoch": 5.03, "learning_rate": 4.008598887202833e-05, "loss": 0.4076, "step": 7340 }, { "epoch": 5.03, "learning_rate": 4.006491316809981e-05, "loss": 0.2695, "step": 7350 }, { "epoch": 5.03, "learning_rate": 4.004383746417131e-05, "loss": 0.3687, "step": 7360 }, { "epoch": 5.03, "learning_rate": 4.002276176024279e-05, "loss": 0.2649, "step": 7370 }, { "epoch": 5.03, "learning_rate": 4.000168605631428e-05, "loss": 0.0549, "step": 7380 }, { "epoch": 5.03, "learning_rate": 3.998061035238577e-05, "loss": 0.05, "step": 7390 }, { "epoch": 5.03, "learning_rate": 3.9959534648457256e-05, "loss": 0.1206, "step": 7400 }, { "epoch": 5.03, "learning_rate": 3.993845894452875e-05, "loss": 0.0802, "step": 7410 }, { "epoch": 5.03, "learning_rate": 3.9917383240600236e-05, "loss": 0.1467, "step": 7420 }, { "epoch": 5.03, "learning_rate": 3.9896307536671726e-05, "loss": 0.0298, "step": 7430 }, { "epoch": 5.03, "learning_rate": 3.9875231832743216e-05, "loss": 0.1525, "step": 7440 }, { "epoch": 5.03, "learning_rate": 3.9854156128814706e-05, "loss": 0.0703, "step": 7450 }, { "epoch": 5.03, "learning_rate": 3.9833080424886195e-05, "loss": 0.2298, "step": 7460 }, { "epoch": 5.03, "learning_rate": 3.981200472095768e-05, "loss": 0.1714, "step": 7470 }, { "epoch": 5.03, "learning_rate": 3.979092901702917e-05, "loss": 0.0944, "step": 7480 }, { "epoch": 5.03, "learning_rate": 3.976985331310066e-05, "loss": 0.4073, "step": 7490 }, { "epoch": 5.03, "learning_rate": 3.974877760917215e-05, "loss": 0.0544, "step": 7500 }, { "epoch": 5.03, "learning_rate": 3.972770190524364e-05, "loss": 0.0471, "step": 7510 }, { "epoch": 5.04, "learning_rate": 3.970662620131513e-05, "loss": 0.4026, "step": 7520 }, { "epoch": 5.04, "learning_rate": 3.968555049738661e-05, "loss": 0.1518, "step": 7530 }, { "epoch": 5.04, "learning_rate": 3.96644747934581e-05, "loss": 0.1155, "step": 7540 }, { "epoch": 5.04, "learning_rate": 3.964339908952959e-05, "loss": 0.1529, "step": 7550 }, { "epoch": 5.04, "learning_rate": 3.962232338560108e-05, "loss": 0.226, "step": 7560 }, { "epoch": 5.04, "learning_rate": 3.960124768167257e-05, "loss": 0.0134, "step": 7570 }, { "epoch": 5.04, "learning_rate": 3.9580171977744054e-05, "loss": 0.1451, "step": 7580 }, { "epoch": 5.04, "learning_rate": 3.955909627381555e-05, "loss": 0.2237, "step": 7590 }, { "epoch": 5.04, "learning_rate": 3.9538020569887034e-05, "loss": 0.107, "step": 7600 }, { "epoch": 5.04, "learning_rate": 3.9516944865958524e-05, "loss": 0.229, "step": 7610 }, { "epoch": 5.04, "learning_rate": 3.9495869162030014e-05, "loss": 0.1259, "step": 7620 }, { "epoch": 5.04, "learning_rate": 3.94747934581015e-05, "loss": 0.2581, "step": 7630 }, { "epoch": 5.04, "learning_rate": 3.9453717754172994e-05, "loss": 0.1509, "step": 7640 }, { "epoch": 5.04, "learning_rate": 3.943264205024448e-05, "loss": 0.1457, "step": 7650 }, { "epoch": 5.04, "learning_rate": 3.941156634631597e-05, "loss": 0.3344, "step": 7660 }, { "epoch": 5.04, "learning_rate": 3.939049064238746e-05, "loss": 0.2321, "step": 7670 }, { "epoch": 5.04, "learning_rate": 3.936941493845895e-05, "loss": 0.2558, "step": 7680 }, { "epoch": 5.04, "learning_rate": 3.934833923453044e-05, "loss": 0.0993, "step": 7690 }, { "epoch": 5.04, "learning_rate": 3.932726353060193e-05, "loss": 0.0569, "step": 7700 }, { "epoch": 5.04, "learning_rate": 3.930618782667341e-05, "loss": 0.26, "step": 7710 }, { "epoch": 5.04, "learning_rate": 3.92851121227449e-05, "loss": 0.0707, "step": 7720 }, { "epoch": 5.04, "learning_rate": 3.926403641881639e-05, "loss": 0.2199, "step": 7730 }, { "epoch": 5.04, "learning_rate": 3.924296071488788e-05, "loss": 0.0262, "step": 7740 }, { "epoch": 5.04, "learning_rate": 3.922188501095937e-05, "loss": 0.2839, "step": 7750 }, { "epoch": 5.04, "learning_rate": 3.920080930703085e-05, "loss": 0.04, "step": 7760 }, { "epoch": 5.04, "learning_rate": 3.917973360310235e-05, "loss": 0.072, "step": 7770 }, { "epoch": 5.04, "learning_rate": 3.915865789917383e-05, "loss": 0.0576, "step": 7780 }, { "epoch": 5.05, "learning_rate": 3.913758219524532e-05, "loss": 0.0751, "step": 7790 }, { "epoch": 5.05, "learning_rate": 3.911650649131681e-05, "loss": 0.0498, "step": 7800 }, { "epoch": 5.05, "learning_rate": 3.9095430787388296e-05, "loss": 0.3567, "step": 7810 }, { "epoch": 5.05, "learning_rate": 3.907435508345979e-05, "loss": 0.2262, "step": 7820 }, { "epoch": 5.05, "learning_rate": 3.9053279379531276e-05, "loss": 0.0855, "step": 7830 }, { "epoch": 5.05, "learning_rate": 3.9032203675602766e-05, "loss": 0.058, "step": 7840 }, { "epoch": 5.05, "learning_rate": 3.9011127971674256e-05, "loss": 0.1563, "step": 7850 }, { "epoch": 5.05, "learning_rate": 3.8990052267745746e-05, "loss": 0.0208, "step": 7860 }, { "epoch": 5.05, "learning_rate": 3.8968976563817236e-05, "loss": 0.3057, "step": 7870 }, { "epoch": 5.05, "learning_rate": 3.894790085988872e-05, "loss": 0.0103, "step": 7880 }, { "epoch": 5.05, "learning_rate": 3.892682515596021e-05, "loss": 0.214, "step": 7890 }, { "epoch": 5.05, "learning_rate": 3.89057494520317e-05, "loss": 0.1357, "step": 7900 }, { "epoch": 5.05, "learning_rate": 3.888467374810319e-05, "loss": 0.0755, "step": 7910 }, { "epoch": 5.05, "eval_accuracy": 0.7406786221132757, "eval_loss": 1.2294286489486694, "eval_runtime": 605.1821, "eval_samples_per_second": 12.808, "eval_steps_per_second": 2.135, "step": 7914 }, { "epoch": 6.0, "learning_rate": 3.886359804417468e-05, "loss": 0.0391, "step": 7920 }, { "epoch": 6.0, "learning_rate": 3.884252234024617e-05, "loss": 0.3838, "step": 7930 }, { "epoch": 6.0, "learning_rate": 3.882144663631765e-05, "loss": 0.0614, "step": 7940 }, { "epoch": 6.0, "learning_rate": 3.880037093238915e-05, "loss": 0.2049, "step": 7950 }, { "epoch": 6.0, "learning_rate": 3.877929522846063e-05, "loss": 0.1118, "step": 7960 }, { "epoch": 6.0, "learning_rate": 3.875821952453212e-05, "loss": 0.1334, "step": 7970 }, { "epoch": 6.0, "learning_rate": 3.873714382060361e-05, "loss": 0.0738, "step": 7980 }, { "epoch": 6.0, "learning_rate": 3.8716068116675095e-05, "loss": 0.2063, "step": 7990 }, { "epoch": 6.0, "learning_rate": 3.869499241274659e-05, "loss": 0.2541, "step": 8000 }, { "epoch": 6.0, "learning_rate": 3.8673916708818075e-05, "loss": 0.0132, "step": 8010 }, { "epoch": 6.0, "learning_rate": 3.8652841004889565e-05, "loss": 0.0873, "step": 8020 }, { "epoch": 6.0, "learning_rate": 3.8631765300961055e-05, "loss": 0.0316, "step": 8030 }, { "epoch": 6.0, "learning_rate": 3.861068959703254e-05, "loss": 0.0478, "step": 8040 }, { "epoch": 6.01, "learning_rate": 3.8589613893104034e-05, "loss": 0.0247, "step": 8050 }, { "epoch": 6.01, "learning_rate": 3.856853818917552e-05, "loss": 0.0568, "step": 8060 }, { "epoch": 6.01, "learning_rate": 3.854746248524701e-05, "loss": 0.1418, "step": 8070 }, { "epoch": 6.01, "learning_rate": 3.85263867813185e-05, "loss": 0.192, "step": 8080 }, { "epoch": 6.01, "learning_rate": 3.850531107738999e-05, "loss": 0.0429, "step": 8090 }, { "epoch": 6.01, "learning_rate": 3.848423537346148e-05, "loss": 0.0325, "step": 8100 }, { "epoch": 6.01, "learning_rate": 3.846315966953297e-05, "loss": 0.1144, "step": 8110 }, { "epoch": 6.01, "learning_rate": 3.844208396560445e-05, "loss": 0.2556, "step": 8120 }, { "epoch": 6.01, "learning_rate": 3.842100826167594e-05, "loss": 0.0197, "step": 8130 }, { "epoch": 6.01, "learning_rate": 3.839993255774743e-05, "loss": 0.0796, "step": 8140 }, { "epoch": 6.01, "learning_rate": 3.837885685381892e-05, "loss": 0.1686, "step": 8150 }, { "epoch": 6.01, "learning_rate": 3.835778114989041e-05, "loss": 0.1527, "step": 8160 }, { "epoch": 6.01, "learning_rate": 3.8336705445961893e-05, "loss": 0.0912, "step": 8170 }, { "epoch": 6.01, "learning_rate": 3.831562974203339e-05, "loss": 0.633, "step": 8180 }, { "epoch": 6.01, "learning_rate": 3.829455403810487e-05, "loss": 0.2356, "step": 8190 }, { "epoch": 6.01, "learning_rate": 3.827347833417636e-05, "loss": 0.1507, "step": 8200 }, { "epoch": 6.01, "learning_rate": 3.825240263024785e-05, "loss": 0.0837, "step": 8210 }, { "epoch": 6.01, "learning_rate": 3.8231326926319336e-05, "loss": 0.0667, "step": 8220 }, { "epoch": 6.01, "learning_rate": 3.821025122239083e-05, "loss": 0.1389, "step": 8230 }, { "epoch": 6.01, "learning_rate": 3.8189175518462316e-05, "loss": 0.0843, "step": 8240 }, { "epoch": 6.01, "learning_rate": 3.8168099814533806e-05, "loss": 0.2491, "step": 8250 }, { "epoch": 6.01, "learning_rate": 3.8147024110605296e-05, "loss": 0.096, "step": 8260 }, { "epoch": 6.01, "learning_rate": 3.8125948406676786e-05, "loss": 0.0402, "step": 8270 }, { "epoch": 6.01, "learning_rate": 3.8104872702748276e-05, "loss": 0.0765, "step": 8280 }, { "epoch": 6.01, "learning_rate": 3.8083796998819766e-05, "loss": 0.0348, "step": 8290 }, { "epoch": 6.01, "learning_rate": 3.806272129489125e-05, "loss": 0.1161, "step": 8300 }, { "epoch": 6.02, "learning_rate": 3.804164559096274e-05, "loss": 0.0531, "step": 8310 }, { "epoch": 6.02, "learning_rate": 3.802056988703423e-05, "loss": 0.2312, "step": 8320 }, { "epoch": 6.02, "learning_rate": 3.799949418310572e-05, "loss": 0.0091, "step": 8330 }, { "epoch": 6.02, "learning_rate": 3.797841847917721e-05, "loss": 0.0599, "step": 8340 }, { "epoch": 6.02, "learning_rate": 3.795734277524869e-05, "loss": 0.0274, "step": 8350 }, { "epoch": 6.02, "learning_rate": 3.793626707132019e-05, "loss": 0.104, "step": 8360 }, { "epoch": 6.02, "learning_rate": 3.791519136739167e-05, "loss": 0.0296, "step": 8370 }, { "epoch": 6.02, "learning_rate": 3.789411566346316e-05, "loss": 0.0604, "step": 8380 }, { "epoch": 6.02, "learning_rate": 3.787303995953465e-05, "loss": 0.056, "step": 8390 }, { "epoch": 6.02, "learning_rate": 3.7851964255606135e-05, "loss": 0.0834, "step": 8400 }, { "epoch": 6.02, "learning_rate": 3.783088855167763e-05, "loss": 0.0626, "step": 8410 }, { "epoch": 6.02, "learning_rate": 3.7809812847749115e-05, "loss": 0.0773, "step": 8420 }, { "epoch": 6.02, "learning_rate": 3.7788737143820605e-05, "loss": 0.2198, "step": 8430 }, { "epoch": 6.02, "learning_rate": 3.7767661439892095e-05, "loss": 0.1182, "step": 8440 }, { "epoch": 6.02, "learning_rate": 3.7746585735963585e-05, "loss": 0.0838, "step": 8450 }, { "epoch": 6.02, "learning_rate": 3.7725510032035075e-05, "loss": 0.1011, "step": 8460 }, { "epoch": 6.02, "learning_rate": 3.770443432810656e-05, "loss": 0.1759, "step": 8470 }, { "epoch": 6.02, "learning_rate": 3.768335862417805e-05, "loss": 0.045, "step": 8480 }, { "epoch": 6.02, "learning_rate": 3.766228292024954e-05, "loss": 0.1133, "step": 8490 }, { "epoch": 6.02, "learning_rate": 3.764120721632103e-05, "loss": 0.2381, "step": 8500 }, { "epoch": 6.02, "learning_rate": 3.762013151239252e-05, "loss": 0.0422, "step": 8510 }, { "epoch": 6.02, "learning_rate": 3.759905580846401e-05, "loss": 0.0238, "step": 8520 }, { "epoch": 6.02, "learning_rate": 3.757798010453549e-05, "loss": 0.0263, "step": 8530 }, { "epoch": 6.02, "learning_rate": 3.755690440060699e-05, "loss": 0.0517, "step": 8540 }, { "epoch": 6.02, "learning_rate": 3.753582869667847e-05, "loss": 0.0456, "step": 8550 }, { "epoch": 6.02, "learning_rate": 3.751475299274996e-05, "loss": 0.0399, "step": 8560 }, { "epoch": 6.02, "learning_rate": 3.749367728882145e-05, "loss": 0.0243, "step": 8570 }, { "epoch": 6.03, "learning_rate": 3.7472601584892934e-05, "loss": 0.5305, "step": 8580 }, { "epoch": 6.03, "learning_rate": 3.745152588096443e-05, "loss": 0.1215, "step": 8590 }, { "epoch": 6.03, "learning_rate": 3.7430450177035914e-05, "loss": 0.234, "step": 8600 }, { "epoch": 6.03, "learning_rate": 3.7409374473107403e-05, "loss": 0.0324, "step": 8610 }, { "epoch": 6.03, "learning_rate": 3.7388298769178893e-05, "loss": 0.3401, "step": 8620 }, { "epoch": 6.03, "learning_rate": 3.7367223065250377e-05, "loss": 0.2055, "step": 8630 }, { "epoch": 6.03, "learning_rate": 3.734614736132187e-05, "loss": 0.1096, "step": 8640 }, { "epoch": 6.03, "learning_rate": 3.7325071657393356e-05, "loss": 0.0706, "step": 8650 }, { "epoch": 6.03, "learning_rate": 3.7303995953464846e-05, "loss": 0.0821, "step": 8660 }, { "epoch": 6.03, "learning_rate": 3.7282920249536336e-05, "loss": 0.0995, "step": 8670 }, { "epoch": 6.03, "learning_rate": 3.7261844545607826e-05, "loss": 0.2141, "step": 8680 }, { "epoch": 6.03, "learning_rate": 3.7240768841679316e-05, "loss": 0.0101, "step": 8690 }, { "epoch": 6.03, "learning_rate": 3.7219693137750806e-05, "loss": 0.1691, "step": 8700 }, { "epoch": 6.03, "learning_rate": 3.719861743382229e-05, "loss": 0.0615, "step": 8710 }, { "epoch": 6.03, "learning_rate": 3.717754172989378e-05, "loss": 0.0998, "step": 8720 }, { "epoch": 6.03, "learning_rate": 3.715646602596527e-05, "loss": 0.031, "step": 8730 }, { "epoch": 6.03, "learning_rate": 3.713539032203676e-05, "loss": 0.0524, "step": 8740 }, { "epoch": 6.03, "learning_rate": 3.711431461810825e-05, "loss": 0.1181, "step": 8750 }, { "epoch": 6.03, "learning_rate": 3.709323891417973e-05, "loss": 0.0511, "step": 8760 }, { "epoch": 6.03, "learning_rate": 3.707216321025123e-05, "loss": 0.0511, "step": 8770 }, { "epoch": 6.03, "learning_rate": 3.705108750632271e-05, "loss": 0.2252, "step": 8780 }, { "epoch": 6.03, "learning_rate": 3.70300118023942e-05, "loss": 0.0039, "step": 8790 }, { "epoch": 6.03, "learning_rate": 3.700893609846569e-05, "loss": 0.0809, "step": 8800 }, { "epoch": 6.03, "learning_rate": 3.6987860394537175e-05, "loss": 0.1406, "step": 8810 }, { "epoch": 6.03, "learning_rate": 3.696678469060867e-05, "loss": 0.0729, "step": 8820 }, { "epoch": 6.03, "learning_rate": 3.6945708986680155e-05, "loss": 0.3257, "step": 8830 }, { "epoch": 6.04, "learning_rate": 3.6924633282751645e-05, "loss": 0.0427, "step": 8840 }, { "epoch": 6.04, "learning_rate": 3.6903557578823135e-05, "loss": 0.1501, "step": 8850 }, { "epoch": 6.04, "learning_rate": 3.6882481874894625e-05, "loss": 0.0567, "step": 8860 }, { "epoch": 6.04, "learning_rate": 3.6861406170966115e-05, "loss": 0.3691, "step": 8870 }, { "epoch": 6.04, "learning_rate": 3.68403304670376e-05, "loss": 0.0151, "step": 8880 }, { "epoch": 6.04, "learning_rate": 3.681925476310909e-05, "loss": 0.2122, "step": 8890 }, { "epoch": 6.04, "learning_rate": 3.679817905918058e-05, "loss": 0.0374, "step": 8900 }, { "epoch": 6.04, "learning_rate": 3.677710335525207e-05, "loss": 0.0757, "step": 8910 }, { "epoch": 6.04, "learning_rate": 3.675602765132356e-05, "loss": 0.1226, "step": 8920 }, { "epoch": 6.04, "learning_rate": 3.673495194739505e-05, "loss": 0.0696, "step": 8930 }, { "epoch": 6.04, "learning_rate": 3.671387624346653e-05, "loss": 0.2266, "step": 8940 }, { "epoch": 6.04, "learning_rate": 3.669280053953803e-05, "loss": 0.1409, "step": 8950 }, { "epoch": 6.04, "learning_rate": 3.667172483560951e-05, "loss": 0.4303, "step": 8960 }, { "epoch": 6.04, "learning_rate": 3.6650649131681e-05, "loss": 0.2547, "step": 8970 }, { "epoch": 6.04, "learning_rate": 3.662957342775249e-05, "loss": 0.0188, "step": 8980 }, { "epoch": 6.04, "learning_rate": 3.6608497723823974e-05, "loss": 0.0699, "step": 8990 }, { "epoch": 6.04, "learning_rate": 3.658742201989547e-05, "loss": 0.095, "step": 9000 }, { "epoch": 6.04, "learning_rate": 3.6566346315966954e-05, "loss": 0.2059, "step": 9010 }, { "epoch": 6.04, "learning_rate": 3.6545270612038444e-05, "loss": 0.1879, "step": 9020 }, { "epoch": 6.04, "learning_rate": 3.6524194908109934e-05, "loss": 0.1064, "step": 9030 }, { "epoch": 6.04, "learning_rate": 3.6503119204181424e-05, "loss": 0.2032, "step": 9040 }, { "epoch": 6.04, "learning_rate": 3.6482043500252914e-05, "loss": 0.1994, "step": 9050 }, { "epoch": 6.04, "learning_rate": 3.64609677963244e-05, "loss": 0.2089, "step": 9060 }, { "epoch": 6.04, "learning_rate": 3.643989209239589e-05, "loss": 0.1689, "step": 9070 }, { "epoch": 6.04, "learning_rate": 3.6418816388467377e-05, "loss": 0.1505, "step": 9080 }, { "epoch": 6.04, "learning_rate": 3.6397740684538867e-05, "loss": 0.1723, "step": 9090 }, { "epoch": 6.04, "learning_rate": 3.6376664980610356e-05, "loss": 0.0914, "step": 9100 }, { "epoch": 6.05, "learning_rate": 3.6355589276681846e-05, "loss": 0.3168, "step": 9110 }, { "epoch": 6.05, "learning_rate": 3.633451357275333e-05, "loss": 0.0566, "step": 9120 }, { "epoch": 6.05, "learning_rate": 3.631343786882482e-05, "loss": 0.2216, "step": 9130 }, { "epoch": 6.05, "learning_rate": 3.629236216489631e-05, "loss": 0.3308, "step": 9140 }, { "epoch": 6.05, "learning_rate": 3.627128646096779e-05, "loss": 0.2227, "step": 9150 }, { "epoch": 6.05, "learning_rate": 3.625021075703929e-05, "loss": 0.2014, "step": 9160 }, { "epoch": 6.05, "learning_rate": 3.622913505311077e-05, "loss": 0.5471, "step": 9170 }, { "epoch": 6.05, "learning_rate": 3.620805934918227e-05, "loss": 0.0944, "step": 9180 }, { "epoch": 6.05, "learning_rate": 3.618698364525375e-05, "loss": 0.3864, "step": 9190 }, { "epoch": 6.05, "learning_rate": 3.616590794132524e-05, "loss": 0.1918, "step": 9200 }, { "epoch": 6.05, "learning_rate": 3.614483223739673e-05, "loss": 0.0428, "step": 9210 }, { "epoch": 6.05, "learning_rate": 3.6123756533468215e-05, "loss": 0.1874, "step": 9220 }, { "epoch": 6.05, "learning_rate": 3.610268082953971e-05, "loss": 0.1487, "step": 9230 }, { "epoch": 6.05, "eval_accuracy": 0.7637724164623919, "eval_loss": 1.1746597290039062, "eval_runtime": 610.8052, "eval_samples_per_second": 12.69, "eval_steps_per_second": 2.115, "step": 9233 }, { "epoch": 7.0, "learning_rate": 3.6081605125611195e-05, "loss": 0.1492, "step": 9240 }, { "epoch": 7.0, "learning_rate": 3.6060529421682685e-05, "loss": 0.2345, "step": 9250 }, { "epoch": 7.0, "learning_rate": 3.6039453717754175e-05, "loss": 0.07, "step": 9260 }, { "epoch": 7.0, "learning_rate": 3.6018378013825665e-05, "loss": 0.4247, "step": 9270 }, { "epoch": 7.0, "learning_rate": 3.5997302309897155e-05, "loss": 0.0095, "step": 9280 }, { "epoch": 7.0, "learning_rate": 3.5976226605968645e-05, "loss": 0.0365, "step": 9290 }, { "epoch": 7.0, "learning_rate": 3.595515090204013e-05, "loss": 0.1083, "step": 9300 }, { "epoch": 7.0, "learning_rate": 3.593407519811162e-05, "loss": 0.0088, "step": 9310 }, { "epoch": 7.0, "learning_rate": 3.591299949418311e-05, "loss": 0.1463, "step": 9320 }, { "epoch": 7.0, "learning_rate": 3.589192379025459e-05, "loss": 0.0167, "step": 9330 }, { "epoch": 7.0, "learning_rate": 3.587084808632609e-05, "loss": 0.3574, "step": 9340 }, { "epoch": 7.0, "learning_rate": 3.584977238239757e-05, "loss": 0.0143, "step": 9350 }, { "epoch": 7.0, "learning_rate": 3.582869667846907e-05, "loss": 0.0429, "step": 9360 }, { "epoch": 7.01, "learning_rate": 3.580762097454055e-05, "loss": 0.1318, "step": 9370 }, { "epoch": 7.01, "learning_rate": 3.5786545270612034e-05, "loss": 0.0883, "step": 9380 }, { "epoch": 7.01, "learning_rate": 3.576546956668353e-05, "loss": 0.0721, "step": 9390 }, { "epoch": 7.01, "learning_rate": 3.5744393862755014e-05, "loss": 0.0052, "step": 9400 }, { "epoch": 7.01, "learning_rate": 3.572331815882651e-05, "loss": 0.0861, "step": 9410 }, { "epoch": 7.01, "learning_rate": 3.5702242454897994e-05, "loss": 0.1609, "step": 9420 }, { "epoch": 7.01, "learning_rate": 3.5681166750969484e-05, "loss": 0.1039, "step": 9430 }, { "epoch": 7.01, "learning_rate": 3.5660091047040974e-05, "loss": 0.0848, "step": 9440 }, { "epoch": 7.01, "learning_rate": 3.5639015343112464e-05, "loss": 0.0201, "step": 9450 }, { "epoch": 7.01, "learning_rate": 3.561793963918395e-05, "loss": 0.0989, "step": 9460 }, { "epoch": 7.01, "learning_rate": 3.559686393525544e-05, "loss": 0.1838, "step": 9470 }, { "epoch": 7.01, "learning_rate": 3.557578823132693e-05, "loss": 0.1351, "step": 9480 }, { "epoch": 7.01, "learning_rate": 3.555471252739842e-05, "loss": 0.0719, "step": 9490 }, { "epoch": 7.01, "learning_rate": 3.553363682346991e-05, "loss": 0.0897, "step": 9500 }, { "epoch": 7.01, "learning_rate": 3.551256111954139e-05, "loss": 0.028, "step": 9510 }, { "epoch": 7.01, "learning_rate": 3.549148541561289e-05, "loss": 0.1243, "step": 9520 }, { "epoch": 7.01, "learning_rate": 3.547040971168437e-05, "loss": 0.0094, "step": 9530 }, { "epoch": 7.01, "learning_rate": 3.5449334007755867e-05, "loss": 0.0991, "step": 9540 }, { "epoch": 7.01, "learning_rate": 3.542825830382735e-05, "loss": 0.1256, "step": 9550 }, { "epoch": 7.01, "learning_rate": 3.540718259989883e-05, "loss": 0.0453, "step": 9560 }, { "epoch": 7.01, "learning_rate": 3.538610689597033e-05, "loss": 0.1416, "step": 9570 }, { "epoch": 7.01, "learning_rate": 3.536503119204181e-05, "loss": 0.104, "step": 9580 }, { "epoch": 7.01, "learning_rate": 3.534395548811331e-05, "loss": 0.0387, "step": 9590 }, { "epoch": 7.01, "learning_rate": 3.532287978418479e-05, "loss": 0.0654, "step": 9600 }, { "epoch": 7.01, "learning_rate": 3.530180408025628e-05, "loss": 0.0042, "step": 9610 }, { "epoch": 7.01, "learning_rate": 3.528072837632777e-05, "loss": 0.0146, "step": 9620 }, { "epoch": 7.02, "learning_rate": 3.5259652672399256e-05, "loss": 0.0683, "step": 9630 }, { "epoch": 7.02, "learning_rate": 3.5238576968470746e-05, "loss": 0.1373, "step": 9640 }, { "epoch": 7.02, "learning_rate": 3.5217501264542236e-05, "loss": 0.2132, "step": 9650 }, { "epoch": 7.02, "learning_rate": 3.5196425560613726e-05, "loss": 0.0645, "step": 9660 }, { "epoch": 7.02, "learning_rate": 3.5175349856685216e-05, "loss": 0.1801, "step": 9670 }, { "epoch": 7.02, "learning_rate": 3.5154274152756705e-05, "loss": 0.337, "step": 9680 }, { "epoch": 7.02, "learning_rate": 3.513319844882819e-05, "loss": 0.1692, "step": 9690 }, { "epoch": 7.02, "learning_rate": 3.5112122744899685e-05, "loss": 0.0021, "step": 9700 }, { "epoch": 7.02, "learning_rate": 3.509104704097117e-05, "loss": 0.0099, "step": 9710 }, { "epoch": 7.02, "learning_rate": 3.506997133704266e-05, "loss": 0.0014, "step": 9720 }, { "epoch": 7.02, "learning_rate": 3.504889563311415e-05, "loss": 0.1343, "step": 9730 }, { "epoch": 7.02, "learning_rate": 3.502781992918563e-05, "loss": 0.0116, "step": 9740 }, { "epoch": 7.02, "learning_rate": 3.500674422525713e-05, "loss": 0.2607, "step": 9750 }, { "epoch": 7.02, "learning_rate": 3.498566852132861e-05, "loss": 0.0413, "step": 9760 }, { "epoch": 7.02, "learning_rate": 3.49645928174001e-05, "loss": 0.0224, "step": 9770 }, { "epoch": 7.02, "learning_rate": 3.494351711347159e-05, "loss": 0.0228, "step": 9780 }, { "epoch": 7.02, "learning_rate": 3.492244140954308e-05, "loss": 0.2005, "step": 9790 }, { "epoch": 7.02, "learning_rate": 3.490136570561457e-05, "loss": 0.099, "step": 9800 }, { "epoch": 7.02, "learning_rate": 3.4880290001686054e-05, "loss": 0.1473, "step": 9810 }, { "epoch": 7.02, "learning_rate": 3.4859214297757544e-05, "loss": 0.1825, "step": 9820 }, { "epoch": 7.02, "learning_rate": 3.4838138593829034e-05, "loss": 0.1088, "step": 9830 }, { "epoch": 7.02, "learning_rate": 3.4817062889900524e-05, "loss": 0.1066, "step": 9840 }, { "epoch": 7.02, "learning_rate": 3.4795987185972014e-05, "loss": 0.2643, "step": 9850 }, { "epoch": 7.02, "learning_rate": 3.4774911482043504e-05, "loss": 0.3801, "step": 9860 }, { "epoch": 7.02, "learning_rate": 3.475383577811499e-05, "loss": 0.1097, "step": 9870 }, { "epoch": 7.02, "learning_rate": 3.4732760074186484e-05, "loss": 0.1347, "step": 9880 }, { "epoch": 7.02, "learning_rate": 3.471168437025797e-05, "loss": 0.2211, "step": 9890 }, { "epoch": 7.03, "learning_rate": 3.469060866632946e-05, "loss": 0.1741, "step": 9900 }, { "epoch": 7.03, "learning_rate": 3.466953296240095e-05, "loss": 0.0918, "step": 9910 }, { "epoch": 7.03, "learning_rate": 3.464845725847243e-05, "loss": 0.0079, "step": 9920 }, { "epoch": 7.03, "learning_rate": 3.462738155454393e-05, "loss": 0.0345, "step": 9930 }, { "epoch": 7.03, "learning_rate": 3.460630585061541e-05, "loss": 0.1629, "step": 9940 }, { "epoch": 7.03, "learning_rate": 3.45852301466869e-05, "loss": 0.0475, "step": 9950 }, { "epoch": 7.03, "learning_rate": 3.456415444275839e-05, "loss": 0.0035, "step": 9960 }, { "epoch": 7.03, "learning_rate": 3.454307873882987e-05, "loss": 0.0492, "step": 9970 }, { "epoch": 7.03, "learning_rate": 3.452200303490137e-05, "loss": 0.1363, "step": 9980 }, { "epoch": 7.03, "learning_rate": 3.450092733097285e-05, "loss": 0.0089, "step": 9990 }, { "epoch": 7.03, "learning_rate": 3.447985162704434e-05, "loss": 0.0713, "step": 10000 }, { "epoch": 7.03, "learning_rate": 3.445877592311583e-05, "loss": 0.1701, "step": 10010 }, { "epoch": 7.03, "learning_rate": 3.443770021918732e-05, "loss": 0.086, "step": 10020 }, { "epoch": 7.03, "learning_rate": 3.441662451525881e-05, "loss": 0.0412, "step": 10030 }, { "epoch": 7.03, "learning_rate": 3.43955488113303e-05, "loss": 0.002, "step": 10040 }, { "epoch": 7.03, "learning_rate": 3.4374473107401786e-05, "loss": 0.035, "step": 10050 }, { "epoch": 7.03, "learning_rate": 3.4353397403473276e-05, "loss": 0.0843, "step": 10060 }, { "epoch": 7.03, "learning_rate": 3.4332321699544766e-05, "loss": 0.1066, "step": 10070 }, { "epoch": 7.03, "learning_rate": 3.4311245995616256e-05, "loss": 0.0707, "step": 10080 }, { "epoch": 7.03, "learning_rate": 3.4290170291687746e-05, "loss": 0.1245, "step": 10090 }, { "epoch": 7.03, "learning_rate": 3.426909458775923e-05, "loss": 0.099, "step": 10100 }, { "epoch": 7.03, "learning_rate": 3.4248018883830726e-05, "loss": 0.1556, "step": 10110 }, { "epoch": 7.03, "learning_rate": 3.422694317990221e-05, "loss": 0.0945, "step": 10120 }, { "epoch": 7.03, "learning_rate": 3.42058674759737e-05, "loss": 0.126, "step": 10130 }, { "epoch": 7.03, "learning_rate": 3.418479177204519e-05, "loss": 0.1244, "step": 10140 }, { "epoch": 7.03, "learning_rate": 3.416371606811667e-05, "loss": 0.1639, "step": 10150 }, { "epoch": 7.04, "learning_rate": 3.414264036418817e-05, "loss": 0.0802, "step": 10160 }, { "epoch": 7.04, "learning_rate": 3.412156466025965e-05, "loss": 0.0318, "step": 10170 }, { "epoch": 7.04, "learning_rate": 3.410048895633114e-05, "loss": 0.172, "step": 10180 }, { "epoch": 7.04, "learning_rate": 3.407941325240263e-05, "loss": 0.0431, "step": 10190 }, { "epoch": 7.04, "learning_rate": 3.405833754847412e-05, "loss": 0.0674, "step": 10200 }, { "epoch": 7.04, "learning_rate": 3.403726184454561e-05, "loss": 0.1608, "step": 10210 }, { "epoch": 7.04, "learning_rate": 3.4016186140617095e-05, "loss": 0.1575, "step": 10220 }, { "epoch": 7.04, "learning_rate": 3.3995110436688585e-05, "loss": 0.0202, "step": 10230 }, { "epoch": 7.04, "learning_rate": 3.3974034732760075e-05, "loss": 0.1132, "step": 10240 }, { "epoch": 7.04, "learning_rate": 3.3952959028831564e-05, "loss": 0.076, "step": 10250 }, { "epoch": 7.04, "learning_rate": 3.3931883324903054e-05, "loss": 0.0637, "step": 10260 }, { "epoch": 7.04, "learning_rate": 3.3910807620974544e-05, "loss": 0.057, "step": 10270 }, { "epoch": 7.04, "learning_rate": 3.388973191704603e-05, "loss": 0.075, "step": 10280 }, { "epoch": 7.04, "learning_rate": 3.3868656213117524e-05, "loss": 0.1595, "step": 10290 }, { "epoch": 7.04, "learning_rate": 3.384758050918901e-05, "loss": 0.0128, "step": 10300 }, { "epoch": 7.04, "learning_rate": 3.38265048052605e-05, "loss": 0.089, "step": 10310 }, { "epoch": 7.04, "learning_rate": 3.380542910133199e-05, "loss": 0.0041, "step": 10320 }, { "epoch": 7.04, "learning_rate": 3.378435339740347e-05, "loss": 0.0869, "step": 10330 }, { "epoch": 7.04, "learning_rate": 3.376327769347497e-05, "loss": 0.1031, "step": 10340 }, { "epoch": 7.04, "learning_rate": 3.374220198954645e-05, "loss": 0.1398, "step": 10350 }, { "epoch": 7.04, "learning_rate": 3.372112628561794e-05, "loss": 0.096, "step": 10360 }, { "epoch": 7.04, "learning_rate": 3.370005058168943e-05, "loss": 0.0096, "step": 10370 }, { "epoch": 7.04, "learning_rate": 3.367897487776092e-05, "loss": 0.1873, "step": 10380 }, { "epoch": 7.04, "learning_rate": 3.365789917383241e-05, "loss": 0.0166, "step": 10390 }, { "epoch": 7.04, "learning_rate": 3.363682346990389e-05, "loss": 0.0544, "step": 10400 }, { "epoch": 7.04, "learning_rate": 3.361574776597538e-05, "loss": 0.566, "step": 10410 }, { "epoch": 7.05, "learning_rate": 3.359467206204687e-05, "loss": 0.1079, "step": 10420 }, { "epoch": 7.05, "learning_rate": 3.357359635811836e-05, "loss": 0.032, "step": 10430 }, { "epoch": 7.05, "learning_rate": 3.355252065418985e-05, "loss": 0.0632, "step": 10440 }, { "epoch": 7.05, "learning_rate": 3.353144495026134e-05, "loss": 0.187, "step": 10450 }, { "epoch": 7.05, "learning_rate": 3.3510369246332826e-05, "loss": 0.3464, "step": 10460 }, { "epoch": 7.05, "learning_rate": 3.3489293542404316e-05, "loss": 0.1961, "step": 10470 }, { "epoch": 7.05, "learning_rate": 3.3468217838475806e-05, "loss": 0.139, "step": 10480 }, { "epoch": 7.05, "learning_rate": 3.3447142134547296e-05, "loss": 0.1891, "step": 10490 }, { "epoch": 7.05, "learning_rate": 3.3426066430618786e-05, "loss": 0.1325, "step": 10500 }, { "epoch": 7.05, "learning_rate": 3.340499072669027e-05, "loss": 0.0538, "step": 10510 }, { "epoch": 7.05, "learning_rate": 3.3383915022761766e-05, "loss": 0.0026, "step": 10520 }, { "epoch": 7.05, "learning_rate": 3.336283931883325e-05, "loss": 0.0139, "step": 10530 }, { "epoch": 7.05, "learning_rate": 3.334176361490474e-05, "loss": 0.1247, "step": 10540 }, { "epoch": 7.05, "learning_rate": 3.332068791097623e-05, "loss": 0.0828, "step": 10550 }, { "epoch": 7.05, "eval_accuracy": 0.7054573603406012, "eval_loss": 1.539963960647583, "eval_runtime": 644.2128, "eval_samples_per_second": 12.032, "eval_steps_per_second": 2.006, "step": 10552 }, { "epoch": 8.0, "learning_rate": 3.329961220704771e-05, "loss": 0.0031, "step": 10560 }, { "epoch": 8.0, "learning_rate": 3.327853650311921e-05, "loss": 0.1607, "step": 10570 }, { "epoch": 8.0, "learning_rate": 3.325746079919069e-05, "loss": 0.0568, "step": 10580 }, { "epoch": 8.0, "learning_rate": 3.323638509526218e-05, "loss": 0.0015, "step": 10590 }, { "epoch": 8.0, "learning_rate": 3.321530939133367e-05, "loss": 0.1214, "step": 10600 }, { "epoch": 8.0, "learning_rate": 3.319423368740516e-05, "loss": 0.0934, "step": 10610 }, { "epoch": 8.0, "learning_rate": 3.317315798347665e-05, "loss": 0.0977, "step": 10620 }, { "epoch": 8.0, "learning_rate": 3.315208227954814e-05, "loss": 0.2453, "step": 10630 }, { "epoch": 8.0, "learning_rate": 3.3131006575619625e-05, "loss": 0.0242, "step": 10640 }, { "epoch": 8.0, "learning_rate": 3.3109930871691115e-05, "loss": 0.0069, "step": 10650 }, { "epoch": 8.0, "learning_rate": 3.3088855167762605e-05, "loss": 0.1581, "step": 10660 }, { "epoch": 8.0, "learning_rate": 3.3067779463834095e-05, "loss": 0.0018, "step": 10670 }, { "epoch": 8.0, "learning_rate": 3.3046703759905585e-05, "loss": 0.1494, "step": 10680 }, { "epoch": 8.01, "learning_rate": 3.302562805597707e-05, "loss": 0.1717, "step": 10690 }, { "epoch": 8.01, "learning_rate": 3.3004552352048564e-05, "loss": 0.0037, "step": 10700 }, { "epoch": 8.01, "learning_rate": 3.298347664812005e-05, "loss": 0.0367, "step": 10710 }, { "epoch": 8.01, "learning_rate": 3.296240094419154e-05, "loss": 0.1346, "step": 10720 }, { "epoch": 8.01, "learning_rate": 3.294132524026303e-05, "loss": 0.1699, "step": 10730 }, { "epoch": 8.01, "learning_rate": 3.292024953633451e-05, "loss": 0.0976, "step": 10740 }, { "epoch": 8.01, "learning_rate": 3.289917383240601e-05, "loss": 0.0029, "step": 10750 }, { "epoch": 8.01, "learning_rate": 3.287809812847749e-05, "loss": 0.0037, "step": 10760 }, { "epoch": 8.01, "learning_rate": 3.285702242454898e-05, "loss": 0.0717, "step": 10770 }, { "epoch": 8.01, "learning_rate": 3.283594672062047e-05, "loss": 0.0052, "step": 10780 }, { "epoch": 8.01, "learning_rate": 3.281487101669196e-05, "loss": 0.1157, "step": 10790 }, { "epoch": 8.01, "learning_rate": 3.279379531276345e-05, "loss": 0.1072, "step": 10800 }, { "epoch": 8.01, "learning_rate": 3.2772719608834934e-05, "loss": 0.0497, "step": 10810 }, { "epoch": 8.01, "learning_rate": 3.2751643904906423e-05, "loss": 0.0187, "step": 10820 }, { "epoch": 8.01, "learning_rate": 3.2730568200977913e-05, "loss": 0.1354, "step": 10830 }, { "epoch": 8.01, "learning_rate": 3.27094924970494e-05, "loss": 0.0055, "step": 10840 }, { "epoch": 8.01, "learning_rate": 3.268841679312089e-05, "loss": 0.0044, "step": 10850 }, { "epoch": 8.01, "learning_rate": 3.266734108919238e-05, "loss": 0.0083, "step": 10860 }, { "epoch": 8.01, "learning_rate": 3.2646265385263866e-05, "loss": 0.0459, "step": 10870 }, { "epoch": 8.01, "learning_rate": 3.262518968133536e-05, "loss": 0.0022, "step": 10880 }, { "epoch": 8.01, "learning_rate": 3.2604113977406846e-05, "loss": 0.0456, "step": 10890 }, { "epoch": 8.01, "learning_rate": 3.2583038273478336e-05, "loss": 0.0187, "step": 10900 }, { "epoch": 8.01, "learning_rate": 3.2561962569549826e-05, "loss": 0.0066, "step": 10910 }, { "epoch": 8.01, "learning_rate": 3.254088686562131e-05, "loss": 0.1252, "step": 10920 }, { "epoch": 8.01, "learning_rate": 3.2519811161692806e-05, "loss": 0.0097, "step": 10930 }, { "epoch": 8.01, "learning_rate": 3.249873545776429e-05, "loss": 0.0507, "step": 10940 }, { "epoch": 8.02, "learning_rate": 3.247765975383578e-05, "loss": 0.1821, "step": 10950 }, { "epoch": 8.02, "learning_rate": 3.245658404990727e-05, "loss": 0.0459, "step": 10960 }, { "epoch": 8.02, "learning_rate": 3.243550834597875e-05, "loss": 0.121, "step": 10970 }, { "epoch": 8.02, "learning_rate": 3.241443264205025e-05, "loss": 0.1497, "step": 10980 }, { "epoch": 8.02, "learning_rate": 3.239335693812173e-05, "loss": 0.0187, "step": 10990 }, { "epoch": 8.02, "learning_rate": 3.237228123419322e-05, "loss": 0.1788, "step": 11000 }, { "epoch": 8.02, "learning_rate": 3.235120553026471e-05, "loss": 0.0486, "step": 11010 }, { "epoch": 8.02, "learning_rate": 3.23301298263362e-05, "loss": 0.1032, "step": 11020 }, { "epoch": 8.02, "learning_rate": 3.230905412240769e-05, "loss": 0.0032, "step": 11030 }, { "epoch": 8.02, "learning_rate": 3.228797841847918e-05, "loss": 0.0689, "step": 11040 }, { "epoch": 8.02, "learning_rate": 3.2266902714550665e-05, "loss": 0.1623, "step": 11050 }, { "epoch": 8.02, "learning_rate": 3.2245827010622155e-05, "loss": 0.0113, "step": 11060 }, { "epoch": 8.02, "learning_rate": 3.2224751306693645e-05, "loss": 0.0887, "step": 11070 }, { "epoch": 8.02, "learning_rate": 3.2203675602765135e-05, "loss": 0.1309, "step": 11080 }, { "epoch": 8.02, "learning_rate": 3.2182599898836625e-05, "loss": 0.0249, "step": 11090 }, { "epoch": 8.02, "learning_rate": 3.216152419490811e-05, "loss": 0.0776, "step": 11100 }, { "epoch": 8.02, "learning_rate": 3.2140448490979605e-05, "loss": 0.0621, "step": 11110 }, { "epoch": 8.02, "learning_rate": 3.211937278705109e-05, "loss": 0.0803, "step": 11120 }, { "epoch": 8.02, "learning_rate": 3.209829708312258e-05, "loss": 0.0686, "step": 11130 }, { "epoch": 8.02, "learning_rate": 3.207722137919407e-05, "loss": 0.0119, "step": 11140 }, { "epoch": 8.02, "learning_rate": 3.205614567526555e-05, "loss": 0.1511, "step": 11150 }, { "epoch": 8.02, "learning_rate": 3.203506997133705e-05, "loss": 0.1082, "step": 11160 }, { "epoch": 8.02, "learning_rate": 3.201399426740853e-05, "loss": 0.0069, "step": 11170 }, { "epoch": 8.02, "learning_rate": 3.199291856348002e-05, "loss": 0.143, "step": 11180 }, { "epoch": 8.02, "learning_rate": 3.197184285955151e-05, "loss": 0.1394, "step": 11190 }, { "epoch": 8.02, "learning_rate": 3.1950767155623e-05, "loss": 0.0052, "step": 11200 }, { "epoch": 8.02, "learning_rate": 3.192969145169449e-05, "loss": 0.2117, "step": 11210 }, { "epoch": 8.03, "learning_rate": 3.1908615747765974e-05, "loss": 0.1365, "step": 11220 }, { "epoch": 8.03, "learning_rate": 3.1887540043837464e-05, "loss": 0.0158, "step": 11230 }, { "epoch": 8.03, "learning_rate": 3.1866464339908954e-05, "loss": 0.063, "step": 11240 }, { "epoch": 8.03, "learning_rate": 3.1845388635980444e-05, "loss": 0.0274, "step": 11250 }, { "epoch": 8.03, "learning_rate": 3.1824312932051934e-05, "loss": 0.1097, "step": 11260 }, { "epoch": 8.03, "learning_rate": 3.1803237228123424e-05, "loss": 0.149, "step": 11270 }, { "epoch": 8.03, "learning_rate": 3.178216152419491e-05, "loss": 0.0702, "step": 11280 }, { "epoch": 8.03, "learning_rate": 3.1761085820266403e-05, "loss": 0.0446, "step": 11290 }, { "epoch": 8.03, "learning_rate": 3.1740010116337887e-05, "loss": 0.0241, "step": 11300 }, { "epoch": 8.03, "learning_rate": 3.1718934412409377e-05, "loss": 0.0117, "step": 11310 }, { "epoch": 8.03, "learning_rate": 3.1697858708480866e-05, "loss": 0.0094, "step": 11320 }, { "epoch": 8.03, "learning_rate": 3.167678300455235e-05, "loss": 0.042, "step": 11330 }, { "epoch": 8.03, "learning_rate": 3.1655707300623846e-05, "loss": 0.2712, "step": 11340 }, { "epoch": 8.03, "learning_rate": 3.163463159669533e-05, "loss": 0.1303, "step": 11350 }, { "epoch": 8.03, "learning_rate": 3.161355589276682e-05, "loss": 0.1221, "step": 11360 }, { "epoch": 8.03, "learning_rate": 3.159248018883831e-05, "loss": 0.0967, "step": 11370 }, { "epoch": 8.03, "learning_rate": 3.15714044849098e-05, "loss": 0.122, "step": 11380 }, { "epoch": 8.03, "learning_rate": 3.155032878098129e-05, "loss": 0.0475, "step": 11390 }, { "epoch": 8.03, "learning_rate": 3.152925307705277e-05, "loss": 0.09, "step": 11400 }, { "epoch": 8.03, "learning_rate": 3.150817737312426e-05, "loss": 0.2039, "step": 11410 }, { "epoch": 8.03, "learning_rate": 3.148710166919575e-05, "loss": 0.0298, "step": 11420 }, { "epoch": 8.03, "learning_rate": 3.146602596526724e-05, "loss": 0.2593, "step": 11430 }, { "epoch": 8.03, "learning_rate": 3.144495026133873e-05, "loss": 0.0364, "step": 11440 }, { "epoch": 8.03, "learning_rate": 3.142387455741022e-05, "loss": 0.0293, "step": 11450 }, { "epoch": 8.03, "learning_rate": 3.1402798853481705e-05, "loss": 0.0503, "step": 11460 }, { "epoch": 8.03, "learning_rate": 3.1381723149553195e-05, "loss": 0.0023, "step": 11470 }, { "epoch": 8.04, "learning_rate": 3.1360647445624685e-05, "loss": 0.118, "step": 11480 }, { "epoch": 8.04, "learning_rate": 3.1339571741696175e-05, "loss": 0.0188, "step": 11490 }, { "epoch": 8.04, "learning_rate": 3.1318496037767665e-05, "loss": 0.175, "step": 11500 }, { "epoch": 8.04, "learning_rate": 3.129742033383915e-05, "loss": 0.0687, "step": 11510 }, { "epoch": 8.04, "learning_rate": 3.1276344629910645e-05, "loss": 0.0073, "step": 11520 }, { "epoch": 8.04, "learning_rate": 3.125526892598213e-05, "loss": 0.2899, "step": 11530 }, { "epoch": 8.04, "learning_rate": 3.123419322205362e-05, "loss": 0.0022, "step": 11540 }, { "epoch": 8.04, "learning_rate": 3.121311751812511e-05, "loss": 0.0506, "step": 11550 }, { "epoch": 8.04, "learning_rate": 3.119204181419659e-05, "loss": 0.1832, "step": 11560 }, { "epoch": 8.04, "learning_rate": 3.117096611026809e-05, "loss": 0.0967, "step": 11570 }, { "epoch": 8.04, "learning_rate": 3.114989040633957e-05, "loss": 0.0717, "step": 11580 }, { "epoch": 8.04, "learning_rate": 3.112881470241106e-05, "loss": 0.1246, "step": 11590 }, { "epoch": 8.04, "learning_rate": 3.110773899848255e-05, "loss": 0.0069, "step": 11600 }, { "epoch": 8.04, "learning_rate": 3.108666329455404e-05, "loss": 0.1383, "step": 11610 }, { "epoch": 8.04, "learning_rate": 3.106558759062553e-05, "loss": 0.0956, "step": 11620 }, { "epoch": 8.04, "learning_rate": 3.104451188669702e-05, "loss": 0.0309, "step": 11630 }, { "epoch": 8.04, "learning_rate": 3.1023436182768504e-05, "loss": 0.2256, "step": 11640 }, { "epoch": 8.04, "learning_rate": 3.1002360478839994e-05, "loss": 0.1198, "step": 11650 }, { "epoch": 8.04, "learning_rate": 3.0981284774911484e-05, "loss": 0.106, "step": 11660 }, { "epoch": 8.04, "learning_rate": 3.0960209070982974e-05, "loss": 0.0658, "step": 11670 }, { "epoch": 8.04, "learning_rate": 3.0939133367054464e-05, "loss": 0.1478, "step": 11680 }, { "epoch": 8.04, "learning_rate": 3.091805766312595e-05, "loss": 0.1542, "step": 11690 }, { "epoch": 8.04, "learning_rate": 3.0896981959197444e-05, "loss": 0.0076, "step": 11700 }, { "epoch": 8.04, "learning_rate": 3.087590625526893e-05, "loss": 0.076, "step": 11710 }, { "epoch": 8.04, "learning_rate": 3.085483055134042e-05, "loss": 0.1264, "step": 11720 }, { "epoch": 8.04, "learning_rate": 3.083375484741191e-05, "loss": 0.0054, "step": 11730 }, { "epoch": 8.05, "learning_rate": 3.081267914348339e-05, "loss": 0.0839, "step": 11740 }, { "epoch": 8.05, "learning_rate": 3.0791603439554887e-05, "loss": 0.0185, "step": 11750 }, { "epoch": 8.05, "learning_rate": 3.077052773562637e-05, "loss": 0.2128, "step": 11760 }, { "epoch": 8.05, "learning_rate": 3.074945203169786e-05, "loss": 0.1483, "step": 11770 }, { "epoch": 8.05, "learning_rate": 3.072837632776935e-05, "loss": 0.1028, "step": 11780 }, { "epoch": 8.05, "learning_rate": 3.070730062384084e-05, "loss": 0.0431, "step": 11790 }, { "epoch": 8.05, "learning_rate": 3.068622491991233e-05, "loss": 0.26, "step": 11800 }, { "epoch": 8.05, "learning_rate": 3.066514921598381e-05, "loss": 0.0283, "step": 11810 }, { "epoch": 8.05, "learning_rate": 3.06440735120553e-05, "loss": 0.194, "step": 11820 }, { "epoch": 8.05, "learning_rate": 3.062299780812679e-05, "loss": 0.0243, "step": 11830 }, { "epoch": 8.05, "learning_rate": 3.060192210419828e-05, "loss": 0.0707, "step": 11840 }, { "epoch": 8.05, "learning_rate": 3.058084640026977e-05, "loss": 0.025, "step": 11850 }, { "epoch": 8.05, "learning_rate": 3.055977069634126e-05, "loss": 0.0284, "step": 11860 }, { "epoch": 8.05, "learning_rate": 3.0538694992412746e-05, "loss": 0.03, "step": 11870 }, { "epoch": 8.05, "eval_accuracy": 0.743258934331054, "eval_loss": 1.3480188846588135, "eval_runtime": 609.5156, "eval_samples_per_second": 12.717, "eval_steps_per_second": 2.12, "step": 11871 }, { "epoch": 9.0, "learning_rate": 3.051761928848424e-05, "loss": 0.0331, "step": 11880 }, { "epoch": 9.0, "learning_rate": 3.0496543584555725e-05, "loss": 0.1413, "step": 11890 }, { "epoch": 9.0, "learning_rate": 3.0475467880627212e-05, "loss": 0.1085, "step": 11900 }, { "epoch": 9.0, "learning_rate": 3.0454392176698705e-05, "loss": 0.0653, "step": 11910 }, { "epoch": 9.0, "learning_rate": 3.0433316472770192e-05, "loss": 0.0061, "step": 11920 }, { "epoch": 9.0, "learning_rate": 3.0412240768841682e-05, "loss": 0.0019, "step": 11930 }, { "epoch": 9.0, "learning_rate": 3.039116506491317e-05, "loss": 0.0481, "step": 11940 }, { "epoch": 9.0, "learning_rate": 3.0370089360984662e-05, "loss": 0.0704, "step": 11950 }, { "epoch": 9.0, "learning_rate": 3.0349013657056148e-05, "loss": 0.0011, "step": 11960 }, { "epoch": 9.0, "learning_rate": 3.0327937953127638e-05, "loss": 0.0069, "step": 11970 }, { "epoch": 9.0, "learning_rate": 3.0306862249199125e-05, "loss": 0.0772, "step": 11980 }, { "epoch": 9.0, "learning_rate": 3.028578654527061e-05, "loss": 0.0017, "step": 11990 }, { "epoch": 9.0, "learning_rate": 3.0264710841342105e-05, "loss": 0.2802, "step": 12000 }, { "epoch": 9.01, "learning_rate": 3.024363513741359e-05, "loss": 0.0633, "step": 12010 }, { "epoch": 9.01, "learning_rate": 3.022255943348508e-05, "loss": 0.0199, "step": 12020 }, { "epoch": 9.01, "learning_rate": 3.0201483729556568e-05, "loss": 0.0394, "step": 12030 }, { "epoch": 9.01, "learning_rate": 3.018040802562806e-05, "loss": 0.0423, "step": 12040 }, { "epoch": 9.01, "learning_rate": 3.0159332321699548e-05, "loss": 0.0721, "step": 12050 }, { "epoch": 9.01, "learning_rate": 3.013825661777103e-05, "loss": 0.0605, "step": 12060 }, { "epoch": 9.01, "learning_rate": 3.0117180913842524e-05, "loss": 0.0059, "step": 12070 }, { "epoch": 9.01, "learning_rate": 3.009610520991401e-05, "loss": 0.0752, "step": 12080 }, { "epoch": 9.01, "learning_rate": 3.0075029505985504e-05, "loss": 0.0015, "step": 12090 }, { "epoch": 9.01, "learning_rate": 3.0053953802056987e-05, "loss": 0.0923, "step": 12100 }, { "epoch": 9.01, "learning_rate": 3.003287809812848e-05, "loss": 0.0286, "step": 12110 }, { "epoch": 9.01, "learning_rate": 3.0011802394199967e-05, "loss": 0.1685, "step": 12120 }, { "epoch": 9.01, "learning_rate": 2.999072669027146e-05, "loss": 0.0992, "step": 12130 }, { "epoch": 9.01, "learning_rate": 2.9969650986342947e-05, "loss": 0.0051, "step": 12140 }, { "epoch": 9.01, "learning_rate": 2.994857528241443e-05, "loss": 0.104, "step": 12150 }, { "epoch": 9.01, "learning_rate": 2.9927499578485923e-05, "loss": 0.0012, "step": 12160 }, { "epoch": 9.01, "learning_rate": 2.990642387455741e-05, "loss": 0.0032, "step": 12170 }, { "epoch": 9.01, "learning_rate": 2.9885348170628903e-05, "loss": 0.0198, "step": 12180 }, { "epoch": 9.01, "learning_rate": 2.9864272466700387e-05, "loss": 0.086, "step": 12190 }, { "epoch": 9.01, "learning_rate": 2.984319676277188e-05, "loss": 0.0418, "step": 12200 }, { "epoch": 9.01, "learning_rate": 2.9822121058843366e-05, "loss": 0.0023, "step": 12210 }, { "epoch": 9.01, "learning_rate": 2.980104535491486e-05, "loss": 0.1315, "step": 12220 }, { "epoch": 9.01, "learning_rate": 2.9779969650986346e-05, "loss": 0.026, "step": 12230 }, { "epoch": 9.01, "learning_rate": 2.975889394705783e-05, "loss": 0.0044, "step": 12240 }, { "epoch": 9.01, "learning_rate": 2.9737818243129323e-05, "loss": 0.0038, "step": 12250 }, { "epoch": 9.01, "learning_rate": 2.971674253920081e-05, "loss": 0.2077, "step": 12260 }, { "epoch": 9.02, "learning_rate": 2.9695666835272303e-05, "loss": 0.0023, "step": 12270 }, { "epoch": 9.02, "learning_rate": 2.9674591131343786e-05, "loss": 0.3224, "step": 12280 }, { "epoch": 9.02, "learning_rate": 2.965351542741528e-05, "loss": 0.0481, "step": 12290 }, { "epoch": 9.02, "learning_rate": 2.9632439723486766e-05, "loss": 0.0038, "step": 12300 }, { "epoch": 9.02, "learning_rate": 2.9611364019558252e-05, "loss": 0.0233, "step": 12310 }, { "epoch": 9.02, "learning_rate": 2.9590288315629742e-05, "loss": 0.1463, "step": 12320 }, { "epoch": 9.02, "learning_rate": 2.956921261170123e-05, "loss": 0.163, "step": 12330 }, { "epoch": 9.02, "learning_rate": 2.9548136907772722e-05, "loss": 0.0169, "step": 12340 }, { "epoch": 9.02, "learning_rate": 2.952706120384421e-05, "loss": 0.0185, "step": 12350 }, { "epoch": 9.02, "learning_rate": 2.9505985499915702e-05, "loss": 0.0031, "step": 12360 }, { "epoch": 9.02, "learning_rate": 2.9484909795987185e-05, "loss": 0.0256, "step": 12370 }, { "epoch": 9.02, "learning_rate": 2.946383409205868e-05, "loss": 0.0895, "step": 12380 }, { "epoch": 9.02, "learning_rate": 2.9442758388130165e-05, "loss": 0.0082, "step": 12390 }, { "epoch": 9.02, "learning_rate": 2.942168268420165e-05, "loss": 0.0008, "step": 12400 }, { "epoch": 9.02, "learning_rate": 2.940060698027314e-05, "loss": 0.0751, "step": 12410 }, { "epoch": 9.02, "learning_rate": 2.9379531276344628e-05, "loss": 0.1252, "step": 12420 }, { "epoch": 9.02, "learning_rate": 2.935845557241612e-05, "loss": 0.1227, "step": 12430 }, { "epoch": 9.02, "learning_rate": 2.9337379868487608e-05, "loss": 0.0582, "step": 12440 }, { "epoch": 9.02, "learning_rate": 2.93163041645591e-05, "loss": 0.1869, "step": 12450 }, { "epoch": 9.02, "learning_rate": 2.9295228460630584e-05, "loss": 0.0281, "step": 12460 }, { "epoch": 9.02, "learning_rate": 2.9274152756702078e-05, "loss": 0.0013, "step": 12470 }, { "epoch": 9.02, "learning_rate": 2.9253077052773564e-05, "loss": 0.0016, "step": 12480 }, { "epoch": 9.02, "learning_rate": 2.923200134884505e-05, "loss": 0.1065, "step": 12490 }, { "epoch": 9.02, "learning_rate": 2.921092564491654e-05, "loss": 0.0393, "step": 12500 }, { "epoch": 9.02, "learning_rate": 2.9189849940988027e-05, "loss": 0.0024, "step": 12510 }, { "epoch": 9.02, "learning_rate": 2.916877423705952e-05, "loss": 0.0012, "step": 12520 }, { "epoch": 9.03, "learning_rate": 2.9147698533131007e-05, "loss": 0.2056, "step": 12530 }, { "epoch": 9.03, "learning_rate": 2.91266228292025e-05, "loss": 0.1816, "step": 12540 }, { "epoch": 9.03, "learning_rate": 2.9105547125273984e-05, "loss": 0.0022, "step": 12550 }, { "epoch": 9.03, "learning_rate": 2.908447142134547e-05, "loss": 0.0087, "step": 12560 }, { "epoch": 9.03, "learning_rate": 2.9063395717416964e-05, "loss": 0.0082, "step": 12570 }, { "epoch": 9.03, "learning_rate": 2.904232001348845e-05, "loss": 0.107, "step": 12580 }, { "epoch": 9.03, "learning_rate": 2.902124430955994e-05, "loss": 0.057, "step": 12590 }, { "epoch": 9.03, "learning_rate": 2.9000168605631427e-05, "loss": 0.0009, "step": 12600 }, { "epoch": 9.03, "learning_rate": 2.897909290170292e-05, "loss": 0.0404, "step": 12610 }, { "epoch": 9.03, "learning_rate": 2.8958017197774407e-05, "loss": 0.0704, "step": 12620 }, { "epoch": 9.03, "learning_rate": 2.8936941493845897e-05, "loss": 0.1422, "step": 12630 }, { "epoch": 9.03, "learning_rate": 2.8915865789917383e-05, "loss": 0.0166, "step": 12640 }, { "epoch": 9.03, "learning_rate": 2.889479008598887e-05, "loss": 0.0216, "step": 12650 }, { "epoch": 9.03, "learning_rate": 2.8873714382060363e-05, "loss": 0.3181, "step": 12660 }, { "epoch": 9.03, "learning_rate": 2.885263867813185e-05, "loss": 0.0271, "step": 12670 }, { "epoch": 9.03, "learning_rate": 2.883156297420334e-05, "loss": 0.1131, "step": 12680 }, { "epoch": 9.03, "learning_rate": 2.8810487270274826e-05, "loss": 0.0089, "step": 12690 }, { "epoch": 9.03, "learning_rate": 2.878941156634632e-05, "loss": 0.0006, "step": 12700 }, { "epoch": 9.03, "learning_rate": 2.8768335862417806e-05, "loss": 0.0176, "step": 12710 }, { "epoch": 9.03, "learning_rate": 2.8747260158489296e-05, "loss": 0.3499, "step": 12720 }, { "epoch": 9.03, "learning_rate": 2.8726184454560782e-05, "loss": 0.0159, "step": 12730 }, { "epoch": 9.03, "learning_rate": 2.870510875063227e-05, "loss": 0.0439, "step": 12740 }, { "epoch": 9.03, "learning_rate": 2.8684033046703762e-05, "loss": 0.1318, "step": 12750 }, { "epoch": 9.03, "learning_rate": 2.866295734277525e-05, "loss": 0.0338, "step": 12760 }, { "epoch": 9.03, "learning_rate": 2.864188163884674e-05, "loss": 0.011, "step": 12770 }, { "epoch": 9.03, "learning_rate": 2.8620805934918225e-05, "loss": 0.0874, "step": 12780 }, { "epoch": 9.03, "learning_rate": 2.859973023098972e-05, "loss": 0.0176, "step": 12790 }, { "epoch": 9.04, "learning_rate": 2.8578654527061205e-05, "loss": 0.002, "step": 12800 }, { "epoch": 9.04, "learning_rate": 2.8557578823132692e-05, "loss": 0.1884, "step": 12810 }, { "epoch": 9.04, "learning_rate": 2.8536503119204182e-05, "loss": 0.3473, "step": 12820 }, { "epoch": 9.04, "learning_rate": 2.851542741527567e-05, "loss": 0.0855, "step": 12830 }, { "epoch": 9.04, "learning_rate": 2.849435171134716e-05, "loss": 0.0077, "step": 12840 }, { "epoch": 9.04, "learning_rate": 2.8473276007418648e-05, "loss": 0.1512, "step": 12850 }, { "epoch": 9.04, "learning_rate": 2.8452200303490138e-05, "loss": 0.0308, "step": 12860 }, { "epoch": 9.04, "learning_rate": 2.8431124599561625e-05, "loss": 0.0032, "step": 12870 }, { "epoch": 9.04, "learning_rate": 2.8410048895633118e-05, "loss": 0.0084, "step": 12880 }, { "epoch": 9.04, "learning_rate": 2.8388973191704605e-05, "loss": 0.2689, "step": 12890 }, { "epoch": 9.04, "learning_rate": 2.836789748777609e-05, "loss": 0.1456, "step": 12900 }, { "epoch": 9.04, "learning_rate": 2.834682178384758e-05, "loss": 0.0393, "step": 12910 }, { "epoch": 9.04, "learning_rate": 2.8325746079919068e-05, "loss": 0.1033, "step": 12920 }, { "epoch": 9.04, "learning_rate": 2.830467037599056e-05, "loss": 0.1193, "step": 12930 }, { "epoch": 9.04, "learning_rate": 2.8283594672062048e-05, "loss": 0.0041, "step": 12940 }, { "epoch": 9.04, "learning_rate": 2.8262518968133538e-05, "loss": 0.0041, "step": 12950 }, { "epoch": 9.04, "learning_rate": 2.8241443264205024e-05, "loss": 0.0829, "step": 12960 }, { "epoch": 9.04, "learning_rate": 2.8220367560276517e-05, "loss": 0.035, "step": 12970 }, { "epoch": 9.04, "learning_rate": 2.8199291856348004e-05, "loss": 0.2022, "step": 12980 }, { "epoch": 9.04, "learning_rate": 2.817821615241949e-05, "loss": 0.0066, "step": 12990 }, { "epoch": 9.04, "learning_rate": 2.815714044849098e-05, "loss": 0.1534, "step": 13000 }, { "epoch": 9.04, "learning_rate": 2.8136064744562467e-05, "loss": 0.0507, "step": 13010 }, { "epoch": 9.04, "learning_rate": 2.811498904063396e-05, "loss": 0.1778, "step": 13020 }, { "epoch": 9.04, "learning_rate": 2.8093913336705447e-05, "loss": 0.3274, "step": 13030 }, { "epoch": 9.04, "learning_rate": 2.8072837632776937e-05, "loss": 0.0287, "step": 13040 }, { "epoch": 9.04, "learning_rate": 2.8051761928848423e-05, "loss": 0.1442, "step": 13050 }, { "epoch": 9.05, "learning_rate": 2.803068622491991e-05, "loss": 0.003, "step": 13060 }, { "epoch": 9.05, "learning_rate": 2.8009610520991403e-05, "loss": 0.1799, "step": 13070 }, { "epoch": 9.05, "learning_rate": 2.798853481706289e-05, "loss": 0.081, "step": 13080 }, { "epoch": 9.05, "learning_rate": 2.796745911313438e-05, "loss": 0.006, "step": 13090 }, { "epoch": 9.05, "learning_rate": 2.7946383409205866e-05, "loss": 0.0595, "step": 13100 }, { "epoch": 9.05, "learning_rate": 2.792530770527736e-05, "loss": 0.2145, "step": 13110 }, { "epoch": 9.05, "learning_rate": 2.7904232001348846e-05, "loss": 0.0131, "step": 13120 }, { "epoch": 9.05, "learning_rate": 2.7883156297420336e-05, "loss": 0.0014, "step": 13130 }, { "epoch": 9.05, "learning_rate": 2.7862080593491823e-05, "loss": 0.2057, "step": 13140 }, { "epoch": 9.05, "learning_rate": 2.784100488956331e-05, "loss": 0.1805, "step": 13150 }, { "epoch": 9.05, "learning_rate": 2.7819929185634803e-05, "loss": 0.067, "step": 13160 }, { "epoch": 9.05, "learning_rate": 2.779885348170629e-05, "loss": 0.1443, "step": 13170 }, { "epoch": 9.05, "learning_rate": 2.777777777777778e-05, "loss": 0.0066, "step": 13180 }, { "epoch": 9.05, "learning_rate": 2.7756702073849266e-05, "loss": 0.0261, "step": 13190 }, { "epoch": 9.05, "eval_accuracy": 0.7694491033415043, "eval_loss": 1.2244846820831299, "eval_runtime": 594.4086, "eval_samples_per_second": 13.04, "eval_steps_per_second": 2.174, "step": 13190 }, { "epoch": 10.0, "learning_rate": 2.773562636992076e-05, "loss": 0.0351, "step": 13200 }, { "epoch": 10.0, "learning_rate": 2.7714550665992246e-05, "loss": 0.0724, "step": 13210 }, { "epoch": 10.0, "learning_rate": 2.7693474962063735e-05, "loss": 0.0487, "step": 13220 }, { "epoch": 10.0, "learning_rate": 2.7672399258135222e-05, "loss": 0.0143, "step": 13230 }, { "epoch": 10.0, "learning_rate": 2.765132355420671e-05, "loss": 0.2685, "step": 13240 }, { "epoch": 10.0, "learning_rate": 2.7630247850278202e-05, "loss": 0.0339, "step": 13250 }, { "epoch": 10.0, "learning_rate": 2.760917214634969e-05, "loss": 0.0673, "step": 13260 }, { "epoch": 10.0, "learning_rate": 2.758809644242118e-05, "loss": 0.1107, "step": 13270 }, { "epoch": 10.0, "learning_rate": 2.7567020738492665e-05, "loss": 0.1871, "step": 13280 }, { "epoch": 10.0, "learning_rate": 2.754594503456416e-05, "loss": 0.0396, "step": 13290 }, { "epoch": 10.0, "learning_rate": 2.7524869330635645e-05, "loss": 0.0008, "step": 13300 }, { "epoch": 10.0, "learning_rate": 2.7503793626707135e-05, "loss": 0.0105, "step": 13310 }, { "epoch": 10.0, "learning_rate": 2.748271792277862e-05, "loss": 0.2069, "step": 13320 }, { "epoch": 10.01, "learning_rate": 2.7461642218850108e-05, "loss": 0.0732, "step": 13330 }, { "epoch": 10.01, "learning_rate": 2.74405665149216e-05, "loss": 0.0125, "step": 13340 }, { "epoch": 10.01, "learning_rate": 2.7419490810993088e-05, "loss": 0.0006, "step": 13350 }, { "epoch": 10.01, "learning_rate": 2.7398415107064578e-05, "loss": 0.0013, "step": 13360 }, { "epoch": 10.01, "learning_rate": 2.7377339403136064e-05, "loss": 0.013, "step": 13370 }, { "epoch": 10.01, "learning_rate": 2.7356263699207558e-05, "loss": 0.0149, "step": 13380 }, { "epoch": 10.01, "learning_rate": 2.7335187995279044e-05, "loss": 0.024, "step": 13390 }, { "epoch": 10.01, "learning_rate": 2.731411229135053e-05, "loss": 0.0029, "step": 13400 }, { "epoch": 10.01, "learning_rate": 2.729303658742202e-05, "loss": 0.0012, "step": 13410 }, { "epoch": 10.01, "learning_rate": 2.7271960883493507e-05, "loss": 0.0514, "step": 13420 }, { "epoch": 10.01, "learning_rate": 2.7250885179565e-05, "loss": 0.045, "step": 13430 }, { "epoch": 10.01, "learning_rate": 2.7229809475636487e-05, "loss": 0.1356, "step": 13440 }, { "epoch": 10.01, "learning_rate": 2.7208733771707977e-05, "loss": 0.0934, "step": 13450 }, { "epoch": 10.01, "learning_rate": 2.7187658067779464e-05, "loss": 0.0083, "step": 13460 }, { "epoch": 10.01, "learning_rate": 2.7166582363850957e-05, "loss": 0.0376, "step": 13470 }, { "epoch": 10.01, "learning_rate": 2.7145506659922444e-05, "loss": 0.1596, "step": 13480 }, { "epoch": 10.01, "learning_rate": 2.712443095599393e-05, "loss": 0.0026, "step": 13490 }, { "epoch": 10.01, "learning_rate": 2.710335525206542e-05, "loss": 0.0111, "step": 13500 }, { "epoch": 10.01, "learning_rate": 2.7082279548136907e-05, "loss": 0.045, "step": 13510 }, { "epoch": 10.01, "learning_rate": 2.70612038442084e-05, "loss": 0.0655, "step": 13520 }, { "epoch": 10.01, "learning_rate": 2.7040128140279886e-05, "loss": 0.0023, "step": 13530 }, { "epoch": 10.01, "learning_rate": 2.7019052436351376e-05, "loss": 0.0083, "step": 13540 }, { "epoch": 10.01, "learning_rate": 2.6997976732422863e-05, "loss": 0.0057, "step": 13550 }, { "epoch": 10.01, "learning_rate": 2.6976901028494356e-05, "loss": 0.016, "step": 13560 }, { "epoch": 10.01, "learning_rate": 2.6955825324565843e-05, "loss": 0.0676, "step": 13570 }, { "epoch": 10.01, "learning_rate": 2.693474962063733e-05, "loss": 0.0362, "step": 13580 }, { "epoch": 10.02, "learning_rate": 2.691367391670882e-05, "loss": 0.0003, "step": 13590 }, { "epoch": 10.02, "learning_rate": 2.6892598212780306e-05, "loss": 0.0041, "step": 13600 }, { "epoch": 10.02, "learning_rate": 2.68715225088518e-05, "loss": 0.076, "step": 13610 }, { "epoch": 10.02, "learning_rate": 2.6850446804923286e-05, "loss": 0.0088, "step": 13620 }, { "epoch": 10.02, "learning_rate": 2.6829371100994776e-05, "loss": 0.1108, "step": 13630 }, { "epoch": 10.02, "learning_rate": 2.6808295397066262e-05, "loss": 0.0239, "step": 13640 }, { "epoch": 10.02, "learning_rate": 2.678721969313775e-05, "loss": 0.005, "step": 13650 }, { "epoch": 10.02, "learning_rate": 2.6766143989209242e-05, "loss": 0.0073, "step": 13660 }, { "epoch": 10.02, "learning_rate": 2.674506828528073e-05, "loss": 0.1577, "step": 13670 }, { "epoch": 10.02, "learning_rate": 2.672399258135222e-05, "loss": 0.0017, "step": 13680 }, { "epoch": 10.02, "learning_rate": 2.6702916877423705e-05, "loss": 0.0081, "step": 13690 }, { "epoch": 10.02, "learning_rate": 2.66818411734952e-05, "loss": 0.0005, "step": 13700 }, { "epoch": 10.02, "learning_rate": 2.6660765469566685e-05, "loss": 0.0057, "step": 13710 }, { "epoch": 10.02, "learning_rate": 2.6639689765638175e-05, "loss": 0.074, "step": 13720 }, { "epoch": 10.02, "learning_rate": 2.661861406170966e-05, "loss": 0.0195, "step": 13730 }, { "epoch": 10.02, "learning_rate": 2.6597538357781148e-05, "loss": 0.0383, "step": 13740 }, { "epoch": 10.02, "learning_rate": 2.657646265385264e-05, "loss": 0.1855, "step": 13750 }, { "epoch": 10.02, "learning_rate": 2.6555386949924128e-05, "loss": 0.0089, "step": 13760 }, { "epoch": 10.02, "learning_rate": 2.6534311245995618e-05, "loss": 0.1718, "step": 13770 }, { "epoch": 10.02, "learning_rate": 2.6513235542067105e-05, "loss": 0.2302, "step": 13780 }, { "epoch": 10.02, "learning_rate": 2.6492159838138598e-05, "loss": 0.0712, "step": 13790 }, { "epoch": 10.02, "learning_rate": 2.6471084134210084e-05, "loss": 0.0303, "step": 13800 }, { "epoch": 10.02, "learning_rate": 2.6450008430281574e-05, "loss": 0.0055, "step": 13810 }, { "epoch": 10.02, "learning_rate": 2.642893272635306e-05, "loss": 0.0013, "step": 13820 }, { "epoch": 10.02, "learning_rate": 2.6407857022424548e-05, "loss": 0.0695, "step": 13830 }, { "epoch": 10.02, "learning_rate": 2.638678131849604e-05, "loss": 0.1529, "step": 13840 }, { "epoch": 10.03, "learning_rate": 2.6365705614567527e-05, "loss": 0.2092, "step": 13850 }, { "epoch": 10.03, "learning_rate": 2.6344629910639017e-05, "loss": 0.0786, "step": 13860 }, { "epoch": 10.03, "learning_rate": 2.6323554206710504e-05, "loss": 0.0136, "step": 13870 }, { "epoch": 10.03, "learning_rate": 2.6302478502781997e-05, "loss": 0.0073, "step": 13880 }, { "epoch": 10.03, "learning_rate": 2.6281402798853484e-05, "loss": 0.0004, "step": 13890 }, { "epoch": 10.03, "learning_rate": 2.626032709492497e-05, "loss": 0.0004, "step": 13900 }, { "epoch": 10.03, "learning_rate": 2.623925139099646e-05, "loss": 0.0256, "step": 13910 }, { "epoch": 10.03, "learning_rate": 2.6218175687067947e-05, "loss": 0.0893, "step": 13920 }, { "epoch": 10.03, "learning_rate": 2.619709998313944e-05, "loss": 0.0008, "step": 13930 }, { "epoch": 10.03, "learning_rate": 2.6176024279210927e-05, "loss": 0.0727, "step": 13940 }, { "epoch": 10.03, "learning_rate": 2.6154948575282417e-05, "loss": 0.0777, "step": 13950 }, { "epoch": 10.03, "learning_rate": 2.6133872871353903e-05, "loss": 0.0016, "step": 13960 }, { "epoch": 10.03, "learning_rate": 2.6112797167425397e-05, "loss": 0.2353, "step": 13970 }, { "epoch": 10.03, "learning_rate": 2.6091721463496883e-05, "loss": 0.0045, "step": 13980 }, { "epoch": 10.03, "learning_rate": 2.607064575956837e-05, "loss": 0.0122, "step": 13990 }, { "epoch": 10.03, "learning_rate": 2.604957005563986e-05, "loss": 0.0028, "step": 14000 }, { "epoch": 10.03, "learning_rate": 2.6028494351711346e-05, "loss": 0.0005, "step": 14010 }, { "epoch": 10.03, "learning_rate": 2.600741864778284e-05, "loss": 0.1262, "step": 14020 }, { "epoch": 10.03, "learning_rate": 2.5986342943854326e-05, "loss": 0.0159, "step": 14030 }, { "epoch": 10.03, "learning_rate": 2.5965267239925816e-05, "loss": 0.0003, "step": 14040 }, { "epoch": 10.03, "learning_rate": 2.5944191535997303e-05, "loss": 0.0173, "step": 14050 }, { "epoch": 10.03, "learning_rate": 2.5923115832068796e-05, "loss": 0.0032, "step": 14060 }, { "epoch": 10.03, "learning_rate": 2.5902040128140282e-05, "loss": 0.1639, "step": 14070 }, { "epoch": 10.03, "learning_rate": 2.588096442421177e-05, "loss": 0.0044, "step": 14080 }, { "epoch": 10.03, "learning_rate": 2.585988872028326e-05, "loss": 0.0525, "step": 14090 }, { "epoch": 10.03, "learning_rate": 2.5838813016354745e-05, "loss": 0.0012, "step": 14100 }, { "epoch": 10.03, "learning_rate": 2.581773731242624e-05, "loss": 0.0122, "step": 14110 }, { "epoch": 10.04, "learning_rate": 2.5796661608497725e-05, "loss": 0.0017, "step": 14120 }, { "epoch": 10.04, "learning_rate": 2.5775585904569215e-05, "loss": 0.1154, "step": 14130 }, { "epoch": 10.04, "learning_rate": 2.5754510200640702e-05, "loss": 0.0122, "step": 14140 }, { "epoch": 10.04, "learning_rate": 2.573343449671219e-05, "loss": 0.0006, "step": 14150 }, { "epoch": 10.04, "learning_rate": 2.5712358792783682e-05, "loss": 0.0055, "step": 14160 }, { "epoch": 10.04, "learning_rate": 2.569128308885517e-05, "loss": 0.0946, "step": 14170 }, { "epoch": 10.04, "learning_rate": 2.5670207384926658e-05, "loss": 0.0422, "step": 14180 }, { "epoch": 10.04, "learning_rate": 2.5649131680998145e-05, "loss": 0.0279, "step": 14190 }, { "epoch": 10.04, "learning_rate": 2.5628055977069638e-05, "loss": 0.0324, "step": 14200 }, { "epoch": 10.04, "learning_rate": 2.5606980273141125e-05, "loss": 0.0019, "step": 14210 }, { "epoch": 10.04, "learning_rate": 2.5585904569212615e-05, "loss": 0.0257, "step": 14220 }, { "epoch": 10.04, "learning_rate": 2.55648288652841e-05, "loss": 0.1136, "step": 14230 }, { "epoch": 10.04, "learning_rate": 2.5543753161355588e-05, "loss": 0.0005, "step": 14240 }, { "epoch": 10.04, "learning_rate": 2.552267745742708e-05, "loss": 0.004, "step": 14250 }, { "epoch": 10.04, "learning_rate": 2.5501601753498568e-05, "loss": 0.3242, "step": 14260 }, { "epoch": 10.04, "learning_rate": 2.5480526049570058e-05, "loss": 0.0581, "step": 14270 }, { "epoch": 10.04, "learning_rate": 2.5459450345641544e-05, "loss": 0.0515, "step": 14280 }, { "epoch": 10.04, "learning_rate": 2.5438374641713037e-05, "loss": 0.2941, "step": 14290 }, { "epoch": 10.04, "learning_rate": 2.5417298937784524e-05, "loss": 0.0836, "step": 14300 }, { "epoch": 10.04, "learning_rate": 2.5396223233856014e-05, "loss": 0.2571, "step": 14310 }, { "epoch": 10.04, "learning_rate": 2.53751475299275e-05, "loss": 0.1004, "step": 14320 }, { "epoch": 10.04, "learning_rate": 2.5354071825998987e-05, "loss": 0.0589, "step": 14330 }, { "epoch": 10.04, "learning_rate": 2.533299612207048e-05, "loss": 0.0075, "step": 14340 }, { "epoch": 10.04, "learning_rate": 2.5311920418141967e-05, "loss": 0.1661, "step": 14350 }, { "epoch": 10.04, "learning_rate": 2.5290844714213457e-05, "loss": 0.047, "step": 14360 }, { "epoch": 10.04, "learning_rate": 2.5269769010284943e-05, "loss": 0.0115, "step": 14370 }, { "epoch": 10.05, "learning_rate": 2.5248693306356437e-05, "loss": 0.0364, "step": 14380 }, { "epoch": 10.05, "learning_rate": 2.5227617602427923e-05, "loss": 0.0557, "step": 14390 }, { "epoch": 10.05, "learning_rate": 2.520654189849941e-05, "loss": 0.1003, "step": 14400 }, { "epoch": 10.05, "learning_rate": 2.51854661945709e-05, "loss": 0.0173, "step": 14410 }, { "epoch": 10.05, "learning_rate": 2.5164390490642386e-05, "loss": 0.011, "step": 14420 }, { "epoch": 10.05, "learning_rate": 2.514331478671388e-05, "loss": 0.1699, "step": 14430 }, { "epoch": 10.05, "learning_rate": 2.5122239082785366e-05, "loss": 0.0015, "step": 14440 }, { "epoch": 10.05, "learning_rate": 2.5101163378856856e-05, "loss": 0.0428, "step": 14450 }, { "epoch": 10.05, "learning_rate": 2.5080087674928343e-05, "loss": 0.0087, "step": 14460 }, { "epoch": 10.05, "learning_rate": 2.5059011970999836e-05, "loss": 0.14, "step": 14470 }, { "epoch": 10.05, "learning_rate": 2.5037936267071323e-05, "loss": 0.1463, "step": 14480 }, { "epoch": 10.05, "learning_rate": 2.501686056314281e-05, "loss": 0.0033, "step": 14490 }, { "epoch": 10.05, "learning_rate": 2.49957848592143e-05, "loss": 0.0028, "step": 14500 }, { "epoch": 10.05, "eval_accuracy": 0.7822216488195072, "eval_loss": 1.2192758321762085, "eval_runtime": 570.2791, "eval_samples_per_second": 13.592, "eval_steps_per_second": 2.266, "step": 14509 }, { "epoch": 11.0, "learning_rate": 2.497470915528579e-05, "loss": 0.1325, "step": 14510 }, { "epoch": 11.0, "learning_rate": 2.495363345135728e-05, "loss": 0.0014, "step": 14520 }, { "epoch": 11.0, "learning_rate": 2.4932557747428766e-05, "loss": 0.0507, "step": 14530 }, { "epoch": 11.0, "learning_rate": 2.4911482043500252e-05, "loss": 0.0046, "step": 14540 }, { "epoch": 11.0, "learning_rate": 2.4890406339571742e-05, "loss": 0.0008, "step": 14550 }, { "epoch": 11.0, "learning_rate": 2.4869330635643232e-05, "loss": 0.0002, "step": 14560 }, { "epoch": 11.0, "learning_rate": 2.4848254931714722e-05, "loss": 0.0101, "step": 14570 }, { "epoch": 11.0, "learning_rate": 2.482717922778621e-05, "loss": 0.0065, "step": 14580 }, { "epoch": 11.0, "learning_rate": 2.48061035238577e-05, "loss": 0.004, "step": 14590 }, { "epoch": 11.0, "learning_rate": 2.478502781992919e-05, "loss": 0.0005, "step": 14600 }, { "epoch": 11.0, "learning_rate": 2.4763952116000675e-05, "loss": 0.0025, "step": 14610 }, { "epoch": 11.0, "learning_rate": 2.4742876412072165e-05, "loss": 0.0147, "step": 14620 }, { "epoch": 11.0, "learning_rate": 2.472180070814365e-05, "loss": 0.0002, "step": 14630 }, { "epoch": 11.0, "learning_rate": 2.470072500421514e-05, "loss": 0.0142, "step": 14640 }, { "epoch": 11.01, "learning_rate": 2.467964930028663e-05, "loss": 0.0196, "step": 14650 }, { "epoch": 11.01, "learning_rate": 2.465857359635812e-05, "loss": 0.0141, "step": 14660 }, { "epoch": 11.01, "learning_rate": 2.4637497892429608e-05, "loss": 0.0313, "step": 14670 }, { "epoch": 11.01, "learning_rate": 2.4616422188501098e-05, "loss": 0.0176, "step": 14680 }, { "epoch": 11.01, "learning_rate": 2.4595346484572588e-05, "loss": 0.0711, "step": 14690 }, { "epoch": 11.01, "learning_rate": 2.4574270780644074e-05, "loss": 0.2081, "step": 14700 }, { "epoch": 11.01, "learning_rate": 2.4553195076715564e-05, "loss": 0.073, "step": 14710 }, { "epoch": 11.01, "learning_rate": 2.453211937278705e-05, "loss": 0.0003, "step": 14720 }, { "epoch": 11.01, "learning_rate": 2.451104366885854e-05, "loss": 0.0074, "step": 14730 }, { "epoch": 11.01, "learning_rate": 2.448996796493003e-05, "loss": 0.1092, "step": 14740 }, { "epoch": 11.01, "learning_rate": 2.446889226100152e-05, "loss": 0.0011, "step": 14750 }, { "epoch": 11.01, "learning_rate": 2.4447816557073007e-05, "loss": 0.0447, "step": 14760 }, { "epoch": 11.01, "learning_rate": 2.4426740853144497e-05, "loss": 0.053, "step": 14770 }, { "epoch": 11.01, "learning_rate": 2.4405665149215984e-05, "loss": 0.0015, "step": 14780 }, { "epoch": 11.01, "learning_rate": 2.4384589445287474e-05, "loss": 0.0005, "step": 14790 }, { "epoch": 11.01, "learning_rate": 2.4363513741358964e-05, "loss": 0.0065, "step": 14800 }, { "epoch": 11.01, "learning_rate": 2.434243803743045e-05, "loss": 0.0029, "step": 14810 }, { "epoch": 11.01, "learning_rate": 2.432136233350194e-05, "loss": 0.002, "step": 14820 }, { "epoch": 11.01, "learning_rate": 2.430028662957343e-05, "loss": 0.0764, "step": 14830 }, { "epoch": 11.01, "learning_rate": 2.427921092564492e-05, "loss": 0.0048, "step": 14840 }, { "epoch": 11.01, "learning_rate": 2.4258135221716407e-05, "loss": 0.1215, "step": 14850 }, { "epoch": 11.01, "learning_rate": 2.4237059517787893e-05, "loss": 0.0036, "step": 14860 }, { "epoch": 11.01, "learning_rate": 2.4215983813859383e-05, "loss": 0.0058, "step": 14870 }, { "epoch": 11.01, "learning_rate": 2.4194908109930873e-05, "loss": 0.2247, "step": 14880 }, { "epoch": 11.01, "learning_rate": 2.4173832406002363e-05, "loss": 0.134, "step": 14890 }, { "epoch": 11.01, "learning_rate": 2.415275670207385e-05, "loss": 0.1359, "step": 14900 }, { "epoch": 11.02, "learning_rate": 2.413168099814534e-05, "loss": 0.0026, "step": 14910 }, { "epoch": 11.02, "learning_rate": 2.411060529421683e-05, "loss": 0.1529, "step": 14920 }, { "epoch": 11.02, "learning_rate": 2.408952959028832e-05, "loss": 0.0665, "step": 14930 }, { "epoch": 11.02, "learning_rate": 2.4068453886359806e-05, "loss": 0.1477, "step": 14940 }, { "epoch": 11.02, "learning_rate": 2.4047378182431292e-05, "loss": 0.0005, "step": 14950 }, { "epoch": 11.02, "learning_rate": 2.4026302478502782e-05, "loss": 0.0777, "step": 14960 }, { "epoch": 11.02, "learning_rate": 2.4005226774574272e-05, "loss": 0.0615, "step": 14970 }, { "epoch": 11.02, "learning_rate": 2.3984151070645762e-05, "loss": 0.1264, "step": 14980 }, { "epoch": 11.02, "learning_rate": 2.396307536671725e-05, "loss": 0.0543, "step": 14990 }, { "epoch": 11.02, "learning_rate": 2.394199966278874e-05, "loss": 0.004, "step": 15000 }, { "epoch": 11.02, "learning_rate": 2.392092395886023e-05, "loss": 0.1298, "step": 15010 }, { "epoch": 11.02, "learning_rate": 2.389984825493172e-05, "loss": 0.1468, "step": 15020 }, { "epoch": 11.02, "learning_rate": 2.3878772551003202e-05, "loss": 0.0083, "step": 15030 }, { "epoch": 11.02, "learning_rate": 2.3857696847074692e-05, "loss": 0.0014, "step": 15040 }, { "epoch": 11.02, "learning_rate": 2.3836621143146182e-05, "loss": 0.013, "step": 15050 }, { "epoch": 11.02, "learning_rate": 2.381554543921767e-05, "loss": 0.0044, "step": 15060 }, { "epoch": 11.02, "learning_rate": 2.379446973528916e-05, "loss": 0.0193, "step": 15070 }, { "epoch": 11.02, "learning_rate": 2.3773394031360648e-05, "loss": 0.0903, "step": 15080 }, { "epoch": 11.02, "learning_rate": 2.3752318327432138e-05, "loss": 0.1295, "step": 15090 }, { "epoch": 11.02, "learning_rate": 2.3731242623503628e-05, "loss": 0.0012, "step": 15100 }, { "epoch": 11.02, "learning_rate": 2.3710166919575115e-05, "loss": 0.024, "step": 15110 }, { "epoch": 11.02, "learning_rate": 2.36890912156466e-05, "loss": 0.0034, "step": 15120 }, { "epoch": 11.02, "learning_rate": 2.366801551171809e-05, "loss": 0.0366, "step": 15130 }, { "epoch": 11.02, "learning_rate": 2.364693980778958e-05, "loss": 0.0025, "step": 15140 }, { "epoch": 11.02, "learning_rate": 2.362586410386107e-05, "loss": 0.0312, "step": 15150 }, { "epoch": 11.02, "learning_rate": 2.3604788399932558e-05, "loss": 0.0064, "step": 15160 }, { "epoch": 11.03, "learning_rate": 2.3583712696004047e-05, "loss": 0.0005, "step": 15170 }, { "epoch": 11.03, "learning_rate": 2.3562636992075537e-05, "loss": 0.0133, "step": 15180 }, { "epoch": 11.03, "learning_rate": 2.3541561288147027e-05, "loss": 0.0003, "step": 15190 }, { "epoch": 11.03, "learning_rate": 2.3520485584218514e-05, "loss": 0.1375, "step": 15200 }, { "epoch": 11.03, "learning_rate": 2.349940988029e-05, "loss": 0.1521, "step": 15210 }, { "epoch": 11.03, "learning_rate": 2.347833417636149e-05, "loss": 0.0538, "step": 15220 }, { "epoch": 11.03, "learning_rate": 2.345725847243298e-05, "loss": 0.0768, "step": 15230 }, { "epoch": 11.03, "learning_rate": 2.343618276850447e-05, "loss": 0.0026, "step": 15240 }, { "epoch": 11.03, "learning_rate": 2.3415107064575957e-05, "loss": 0.0009, "step": 15250 }, { "epoch": 11.03, "learning_rate": 2.3394031360647447e-05, "loss": 0.0017, "step": 15260 }, { "epoch": 11.03, "learning_rate": 2.3372955656718937e-05, "loss": 0.056, "step": 15270 }, { "epoch": 11.03, "learning_rate": 2.3351879952790423e-05, "loss": 0.1631, "step": 15280 }, { "epoch": 11.03, "learning_rate": 2.3330804248861913e-05, "loss": 0.1186, "step": 15290 }, { "epoch": 11.03, "learning_rate": 2.33097285449334e-05, "loss": 0.0377, "step": 15300 }, { "epoch": 11.03, "learning_rate": 2.328865284100489e-05, "loss": 0.0759, "step": 15310 }, { "epoch": 11.03, "learning_rate": 2.326757713707638e-05, "loss": 0.0111, "step": 15320 }, { "epoch": 11.03, "learning_rate": 2.324650143314787e-05, "loss": 0.0102, "step": 15330 }, { "epoch": 11.03, "learning_rate": 2.3225425729219356e-05, "loss": 0.1385, "step": 15340 }, { "epoch": 11.03, "learning_rate": 2.3204350025290846e-05, "loss": 0.0004, "step": 15350 }, { "epoch": 11.03, "learning_rate": 2.3183274321362333e-05, "loss": 0.0194, "step": 15360 }, { "epoch": 11.03, "learning_rate": 2.3162198617433823e-05, "loss": 0.0006, "step": 15370 }, { "epoch": 11.03, "learning_rate": 2.3141122913505313e-05, "loss": 0.0715, "step": 15380 }, { "epoch": 11.03, "learning_rate": 2.31200472095768e-05, "loss": 0.1088, "step": 15390 }, { "epoch": 11.03, "learning_rate": 2.309897150564829e-05, "loss": 0.212, "step": 15400 }, { "epoch": 11.03, "learning_rate": 2.307789580171978e-05, "loss": 0.0442, "step": 15410 }, { "epoch": 11.03, "learning_rate": 2.305682009779127e-05, "loss": 0.0187, "step": 15420 }, { "epoch": 11.03, "learning_rate": 2.3035744393862756e-05, "loss": 0.1131, "step": 15430 }, { "epoch": 11.04, "learning_rate": 2.3014668689934245e-05, "loss": 0.2526, "step": 15440 }, { "epoch": 11.04, "learning_rate": 2.2993592986005732e-05, "loss": 0.0034, "step": 15450 }, { "epoch": 11.04, "learning_rate": 2.2972517282077222e-05, "loss": 0.0737, "step": 15460 }, { "epoch": 11.04, "learning_rate": 2.2951441578148712e-05, "loss": 0.0161, "step": 15470 }, { "epoch": 11.04, "learning_rate": 2.29303658742202e-05, "loss": 0.0016, "step": 15480 }, { "epoch": 11.04, "learning_rate": 2.290929017029169e-05, "loss": 0.0014, "step": 15490 }, { "epoch": 11.04, "learning_rate": 2.288821446636318e-05, "loss": 0.0133, "step": 15500 }, { "epoch": 11.04, "learning_rate": 2.2867138762434668e-05, "loss": 0.014, "step": 15510 }, { "epoch": 11.04, "learning_rate": 2.2846063058506155e-05, "loss": 0.019, "step": 15520 }, { "epoch": 11.04, "learning_rate": 2.282498735457764e-05, "loss": 0.0045, "step": 15530 }, { "epoch": 11.04, "learning_rate": 2.280391165064913e-05, "loss": 0.1628, "step": 15540 }, { "epoch": 11.04, "learning_rate": 2.278283594672062e-05, "loss": 0.0012, "step": 15550 }, { "epoch": 11.04, "learning_rate": 2.276176024279211e-05, "loss": 0.0068, "step": 15560 }, { "epoch": 11.04, "learning_rate": 2.2740684538863598e-05, "loss": 0.0348, "step": 15570 }, { "epoch": 11.04, "learning_rate": 2.2719608834935088e-05, "loss": 0.0965, "step": 15580 }, { "epoch": 11.04, "learning_rate": 2.2698533131006578e-05, "loss": 0.0654, "step": 15590 }, { "epoch": 11.04, "learning_rate": 2.2677457427078068e-05, "loss": 0.0037, "step": 15600 }, { "epoch": 11.04, "learning_rate": 2.2656381723149554e-05, "loss": 0.0004, "step": 15610 }, { "epoch": 11.04, "learning_rate": 2.263530601922104e-05, "loss": 0.1374, "step": 15620 }, { "epoch": 11.04, "learning_rate": 2.261423031529253e-05, "loss": 0.0035, "step": 15630 }, { "epoch": 11.04, "learning_rate": 2.259315461136402e-05, "loss": 0.3192, "step": 15640 }, { "epoch": 11.04, "learning_rate": 2.257207890743551e-05, "loss": 0.0385, "step": 15650 }, { "epoch": 11.04, "learning_rate": 2.2551003203506997e-05, "loss": 0.0263, "step": 15660 }, { "epoch": 11.04, "learning_rate": 2.2529927499578487e-05, "loss": 0.001, "step": 15670 }, { "epoch": 11.04, "learning_rate": 2.2508851795649977e-05, "loss": 0.0005, "step": 15680 }, { "epoch": 11.04, "learning_rate": 2.2487776091721467e-05, "loss": 0.007, "step": 15690 }, { "epoch": 11.05, "learning_rate": 2.2466700387792953e-05, "loss": 0.0857, "step": 15700 }, { "epoch": 11.05, "learning_rate": 2.244562468386444e-05, "loss": 0.0004, "step": 15710 }, { "epoch": 11.05, "learning_rate": 2.242454897993593e-05, "loss": 0.001, "step": 15720 }, { "epoch": 11.05, "learning_rate": 2.240347327600742e-05, "loss": 0.0046, "step": 15730 }, { "epoch": 11.05, "learning_rate": 2.238239757207891e-05, "loss": 0.0008, "step": 15740 }, { "epoch": 11.05, "learning_rate": 2.2361321868150396e-05, "loss": 0.0614, "step": 15750 }, { "epoch": 11.05, "learning_rate": 2.2340246164221886e-05, "loss": 0.0005, "step": 15760 }, { "epoch": 11.05, "learning_rate": 2.2319170460293376e-05, "loss": 0.0058, "step": 15770 }, { "epoch": 11.05, "learning_rate": 2.2298094756364863e-05, "loss": 0.0029, "step": 15780 }, { "epoch": 11.05, "learning_rate": 2.2277019052436353e-05, "loss": 0.0322, "step": 15790 }, { "epoch": 11.05, "learning_rate": 2.225594334850784e-05, "loss": 0.0173, "step": 15800 }, { "epoch": 11.05, "learning_rate": 2.223486764457933e-05, "loss": 0.0114, "step": 15810 }, { "epoch": 11.05, "learning_rate": 2.221379194065082e-05, "loss": 0.0039, "step": 15820 }, { "epoch": 11.05, "eval_accuracy": 0.7648045413495033, "eval_loss": 1.4548989534378052, "eval_runtime": 642.7958, "eval_samples_per_second": 12.058, "eval_steps_per_second": 2.01, "step": 15828 }, { "epoch": 12.0, "learning_rate": 2.219271623672231e-05, "loss": 0.0014, "step": 15830 }, { "epoch": 12.0, "learning_rate": 2.2171640532793796e-05, "loss": 0.002, "step": 15840 }, { "epoch": 12.0, "learning_rate": 2.2150564828865286e-05, "loss": 0.0027, "step": 15850 }, { "epoch": 12.0, "learning_rate": 2.2129489124936776e-05, "loss": 0.0146, "step": 15860 }, { "epoch": 12.0, "learning_rate": 2.2108413421008262e-05, "loss": 0.0005, "step": 15870 }, { "epoch": 12.0, "learning_rate": 2.2087337717079752e-05, "loss": 0.0002, "step": 15880 }, { "epoch": 12.0, "learning_rate": 2.206626201315124e-05, "loss": 0.0004, "step": 15890 }, { "epoch": 12.0, "learning_rate": 2.204518630922273e-05, "loss": 0.0075, "step": 15900 }, { "epoch": 12.0, "learning_rate": 2.202411060529422e-05, "loss": 0.0345, "step": 15910 }, { "epoch": 12.0, "learning_rate": 2.200303490136571e-05, "loss": 0.0382, "step": 15920 }, { "epoch": 12.0, "learning_rate": 2.1981959197437195e-05, "loss": 0.035, "step": 15930 }, { "epoch": 12.0, "learning_rate": 2.1960883493508685e-05, "loss": 0.0002, "step": 15940 }, { "epoch": 12.0, "learning_rate": 2.193980778958017e-05, "loss": 0.0002, "step": 15950 }, { "epoch": 12.01, "learning_rate": 2.191873208565166e-05, "loss": 0.046, "step": 15960 }, { "epoch": 12.01, "learning_rate": 2.189765638172315e-05, "loss": 0.0006, "step": 15970 }, { "epoch": 12.01, "learning_rate": 2.1876580677794638e-05, "loss": 0.0032, "step": 15980 }, { "epoch": 12.01, "learning_rate": 2.1855504973866128e-05, "loss": 0.0087, "step": 15990 }, { "epoch": 12.01, "learning_rate": 2.1834429269937618e-05, "loss": 0.0861, "step": 16000 }, { "epoch": 12.01, "learning_rate": 2.1813353566009108e-05, "loss": 0.0386, "step": 16010 }, { "epoch": 12.01, "learning_rate": 2.1792277862080594e-05, "loss": 0.0002, "step": 16020 }, { "epoch": 12.01, "learning_rate": 2.177120215815208e-05, "loss": 0.047, "step": 16030 }, { "epoch": 12.01, "learning_rate": 2.175012645422357e-05, "loss": 0.0223, "step": 16040 }, { "epoch": 12.01, "learning_rate": 2.172905075029506e-05, "loss": 0.0011, "step": 16050 }, { "epoch": 12.01, "learning_rate": 2.170797504636655e-05, "loss": 0.0012, "step": 16060 }, { "epoch": 12.01, "learning_rate": 2.1686899342438037e-05, "loss": 0.0004, "step": 16070 }, { "epoch": 12.01, "learning_rate": 2.1665823638509527e-05, "loss": 0.0042, "step": 16080 }, { "epoch": 12.01, "learning_rate": 2.1644747934581017e-05, "loss": 0.0015, "step": 16090 }, { "epoch": 12.01, "learning_rate": 2.1623672230652507e-05, "loss": 0.1429, "step": 16100 }, { "epoch": 12.01, "learning_rate": 2.1602596526723994e-05, "loss": 0.1381, "step": 16110 }, { "epoch": 12.01, "learning_rate": 2.158152082279548e-05, "loss": 0.0601, "step": 16120 }, { "epoch": 12.01, "learning_rate": 2.156044511886697e-05, "loss": 0.0151, "step": 16130 }, { "epoch": 12.01, "learning_rate": 2.153936941493846e-05, "loss": 0.0165, "step": 16140 }, { "epoch": 12.01, "learning_rate": 2.151829371100995e-05, "loss": 0.0007, "step": 16150 }, { "epoch": 12.01, "learning_rate": 2.1497218007081437e-05, "loss": 0.1182, "step": 16160 }, { "epoch": 12.01, "learning_rate": 2.1476142303152927e-05, "loss": 0.0007, "step": 16170 }, { "epoch": 12.01, "learning_rate": 2.1455066599224417e-05, "loss": 0.023, "step": 16180 }, { "epoch": 12.01, "learning_rate": 2.1433990895295907e-05, "loss": 0.0592, "step": 16190 }, { "epoch": 12.01, "learning_rate": 2.1412915191367393e-05, "loss": 0.0024, "step": 16200 }, { "epoch": 12.01, "learning_rate": 2.139183948743888e-05, "loss": 0.0802, "step": 16210 }, { "epoch": 12.01, "learning_rate": 2.137076378351037e-05, "loss": 0.0901, "step": 16220 }, { "epoch": 12.02, "learning_rate": 2.134968807958186e-05, "loss": 0.0006, "step": 16230 }, { "epoch": 12.02, "learning_rate": 2.132861237565335e-05, "loss": 0.0025, "step": 16240 }, { "epoch": 12.02, "learning_rate": 2.1307536671724836e-05, "loss": 0.0006, "step": 16250 }, { "epoch": 12.02, "learning_rate": 2.1286460967796326e-05, "loss": 0.0019, "step": 16260 }, { "epoch": 12.02, "learning_rate": 2.1265385263867816e-05, "loss": 0.0004, "step": 16270 }, { "epoch": 12.02, "learning_rate": 2.1244309559939302e-05, "loss": 0.004, "step": 16280 }, { "epoch": 12.02, "learning_rate": 2.1223233856010792e-05, "loss": 0.0002, "step": 16290 }, { "epoch": 12.02, "learning_rate": 2.120215815208228e-05, "loss": 0.0026, "step": 16300 }, { "epoch": 12.02, "learning_rate": 2.118108244815377e-05, "loss": 0.0117, "step": 16310 }, { "epoch": 12.02, "learning_rate": 2.116000674422526e-05, "loss": 0.0016, "step": 16320 }, { "epoch": 12.02, "learning_rate": 2.113893104029675e-05, "loss": 0.0044, "step": 16330 }, { "epoch": 12.02, "learning_rate": 2.1117855336368235e-05, "loss": 0.0916, "step": 16340 }, { "epoch": 12.02, "learning_rate": 2.1096779632439725e-05, "loss": 0.0028, "step": 16350 }, { "epoch": 12.02, "learning_rate": 2.1075703928511215e-05, "loss": 0.0295, "step": 16360 }, { "epoch": 12.02, "learning_rate": 2.1054628224582702e-05, "loss": 0.0007, "step": 16370 }, { "epoch": 12.02, "learning_rate": 2.103355252065419e-05, "loss": 0.0254, "step": 16380 }, { "epoch": 12.02, "learning_rate": 2.1012476816725678e-05, "loss": 0.0172, "step": 16390 }, { "epoch": 12.02, "learning_rate": 2.0991401112797168e-05, "loss": 0.0485, "step": 16400 }, { "epoch": 12.02, "learning_rate": 2.0970325408868658e-05, "loss": 0.0035, "step": 16410 }, { "epoch": 12.02, "learning_rate": 2.0949249704940148e-05, "loss": 0.2051, "step": 16420 }, { "epoch": 12.02, "learning_rate": 2.0928174001011635e-05, "loss": 0.0186, "step": 16430 }, { "epoch": 12.02, "learning_rate": 2.0907098297083125e-05, "loss": 0.0004, "step": 16440 }, { "epoch": 12.02, "learning_rate": 2.088602259315461e-05, "loss": 0.0031, "step": 16450 }, { "epoch": 12.02, "learning_rate": 2.08649468892261e-05, "loss": 0.0002, "step": 16460 }, { "epoch": 12.02, "learning_rate": 2.0843871185297588e-05, "loss": 0.0004, "step": 16470 }, { "epoch": 12.02, "learning_rate": 2.0822795481369078e-05, "loss": 0.0517, "step": 16480 }, { "epoch": 12.03, "learning_rate": 2.0801719777440568e-05, "loss": 0.0004, "step": 16490 }, { "epoch": 12.03, "learning_rate": 2.0780644073512057e-05, "loss": 0.0021, "step": 16500 }, { "epoch": 12.03, "learning_rate": 2.0759568369583547e-05, "loss": 0.0044, "step": 16510 }, { "epoch": 12.03, "learning_rate": 2.0738492665655034e-05, "loss": 0.0015, "step": 16520 }, { "epoch": 12.03, "learning_rate": 2.0717416961726524e-05, "loss": 0.1021, "step": 16530 }, { "epoch": 12.03, "learning_rate": 2.069634125779801e-05, "loss": 0.0136, "step": 16540 }, { "epoch": 12.03, "learning_rate": 2.06752655538695e-05, "loss": 0.0945, "step": 16550 }, { "epoch": 12.03, "learning_rate": 2.0654189849940987e-05, "loss": 0.0491, "step": 16560 }, { "epoch": 12.03, "learning_rate": 2.0633114146012477e-05, "loss": 0.1206, "step": 16570 }, { "epoch": 12.03, "learning_rate": 2.0612038442083967e-05, "loss": 0.004, "step": 16580 }, { "epoch": 12.03, "learning_rate": 2.0590962738155457e-05, "loss": 0.008, "step": 16590 }, { "epoch": 12.03, "learning_rate": 2.0569887034226947e-05, "loss": 0.0012, "step": 16600 }, { "epoch": 12.03, "learning_rate": 2.0548811330298433e-05, "loss": 0.0031, "step": 16610 }, { "epoch": 12.03, "learning_rate": 2.052773562636992e-05, "loss": 0.0291, "step": 16620 }, { "epoch": 12.03, "learning_rate": 2.050665992244141e-05, "loss": 0.0052, "step": 16630 }, { "epoch": 12.03, "learning_rate": 2.04855842185129e-05, "loss": 0.0022, "step": 16640 }, { "epoch": 12.03, "learning_rate": 2.0464508514584386e-05, "loss": 0.0451, "step": 16650 }, { "epoch": 12.03, "learning_rate": 2.0443432810655876e-05, "loss": 0.0258, "step": 16660 }, { "epoch": 12.03, "learning_rate": 2.0422357106727366e-05, "loss": 0.0388, "step": 16670 }, { "epoch": 12.03, "learning_rate": 2.0401281402798856e-05, "loss": 0.0009, "step": 16680 }, { "epoch": 12.03, "learning_rate": 2.0380205698870343e-05, "loss": 0.0287, "step": 16690 }, { "epoch": 12.03, "learning_rate": 2.035912999494183e-05, "loss": 0.0005, "step": 16700 }, { "epoch": 12.03, "learning_rate": 2.033805429101332e-05, "loss": 0.0016, "step": 16710 }, { "epoch": 12.03, "learning_rate": 2.031697858708481e-05, "loss": 0.018, "step": 16720 }, { "epoch": 12.03, "learning_rate": 2.02959028831563e-05, "loss": 0.0013, "step": 16730 }, { "epoch": 12.03, "learning_rate": 2.0274827179227786e-05, "loss": 0.1702, "step": 16740 }, { "epoch": 12.03, "learning_rate": 2.0253751475299276e-05, "loss": 0.0014, "step": 16750 }, { "epoch": 12.04, "learning_rate": 2.0232675771370766e-05, "loss": 0.1064, "step": 16760 }, { "epoch": 12.04, "learning_rate": 2.0211600067442255e-05, "loss": 0.0116, "step": 16770 }, { "epoch": 12.04, "learning_rate": 2.0190524363513742e-05, "loss": 0.0002, "step": 16780 }, { "epoch": 12.04, "learning_rate": 2.016944865958523e-05, "loss": 0.0387, "step": 16790 }, { "epoch": 12.04, "learning_rate": 2.014837295565672e-05, "loss": 0.0015, "step": 16800 }, { "epoch": 12.04, "learning_rate": 2.012729725172821e-05, "loss": 0.0003, "step": 16810 }, { "epoch": 12.04, "learning_rate": 2.01062215477997e-05, "loss": 0.0167, "step": 16820 }, { "epoch": 12.04, "learning_rate": 2.0085145843871185e-05, "loss": 0.0002, "step": 16830 }, { "epoch": 12.04, "learning_rate": 2.0064070139942675e-05, "loss": 0.0371, "step": 16840 }, { "epoch": 12.04, "learning_rate": 2.0042994436014165e-05, "loss": 0.001, "step": 16850 }, { "epoch": 12.04, "learning_rate": 2.0021918732085655e-05, "loss": 0.0422, "step": 16860 }, { "epoch": 12.04, "learning_rate": 2.000084302815714e-05, "loss": 0.0101, "step": 16870 }, { "epoch": 12.04, "learning_rate": 1.9979767324228628e-05, "loss": 0.0003, "step": 16880 }, { "epoch": 12.04, "learning_rate": 1.9958691620300118e-05, "loss": 0.088, "step": 16890 }, { "epoch": 12.04, "learning_rate": 1.9937615916371608e-05, "loss": 0.0005, "step": 16900 }, { "epoch": 12.04, "learning_rate": 1.9916540212443098e-05, "loss": 0.0101, "step": 16910 }, { "epoch": 12.04, "learning_rate": 1.9895464508514584e-05, "loss": 0.0008, "step": 16920 }, { "epoch": 12.04, "learning_rate": 1.9874388804586074e-05, "loss": 0.0004, "step": 16930 }, { "epoch": 12.04, "learning_rate": 1.9853313100657564e-05, "loss": 0.0003, "step": 16940 }, { "epoch": 12.04, "learning_rate": 1.983223739672905e-05, "loss": 0.003, "step": 16950 }, { "epoch": 12.04, "learning_rate": 1.981116169280054e-05, "loss": 0.0111, "step": 16960 }, { "epoch": 12.04, "learning_rate": 1.9790085988872027e-05, "loss": 0.0027, "step": 16970 }, { "epoch": 12.04, "learning_rate": 1.9769010284943517e-05, "loss": 0.0009, "step": 16980 }, { "epoch": 12.04, "learning_rate": 1.9747934581015007e-05, "loss": 0.001, "step": 16990 }, { "epoch": 12.04, "learning_rate": 1.9726858877086497e-05, "loss": 0.0024, "step": 17000 }, { "epoch": 12.04, "learning_rate": 1.9705783173157984e-05, "loss": 0.0006, "step": 17010 }, { "epoch": 12.05, "learning_rate": 1.9684707469229474e-05, "loss": 0.0013, "step": 17020 }, { "epoch": 12.05, "learning_rate": 1.9663631765300964e-05, "loss": 0.0101, "step": 17030 }, { "epoch": 12.05, "learning_rate": 1.964255606137245e-05, "loss": 0.0804, "step": 17040 }, { "epoch": 12.05, "learning_rate": 1.962148035744394e-05, "loss": 0.0085, "step": 17050 }, { "epoch": 12.05, "learning_rate": 1.9600404653515427e-05, "loss": 0.0055, "step": 17060 }, { "epoch": 12.05, "learning_rate": 1.9579328949586917e-05, "loss": 0.0006, "step": 17070 }, { "epoch": 12.05, "learning_rate": 1.9558253245658406e-05, "loss": 0.0039, "step": 17080 }, { "epoch": 12.05, "learning_rate": 1.9537177541729896e-05, "loss": 0.2048, "step": 17090 }, { "epoch": 12.05, "learning_rate": 1.9516101837801383e-05, "loss": 0.0017, "step": 17100 }, { "epoch": 12.05, "learning_rate": 1.9495026133872873e-05, "loss": 0.0749, "step": 17110 }, { "epoch": 12.05, "learning_rate": 1.947395042994436e-05, "loss": 0.0007, "step": 17120 }, { "epoch": 12.05, "learning_rate": 1.945287472601585e-05, "loss": 0.1778, "step": 17130 }, { "epoch": 12.05, "learning_rate": 1.943179902208734e-05, "loss": 0.1153, "step": 17140 }, { "epoch": 12.05, "eval_accuracy": 0.7835118049283963, "eval_loss": 1.2979658842086792, "eval_runtime": 609.3856, "eval_samples_per_second": 12.719, "eval_steps_per_second": 2.12, "step": 17147 }, { "epoch": 13.0, "learning_rate": 1.9410723318158826e-05, "loss": 0.0366, "step": 17150 }, { "epoch": 13.0, "learning_rate": 1.9389647614230316e-05, "loss": 0.0023, "step": 17160 }, { "epoch": 13.0, "learning_rate": 1.9368571910301806e-05, "loss": 0.0116, "step": 17170 }, { "epoch": 13.0, "learning_rate": 1.9347496206373296e-05, "loss": 0.0003, "step": 17180 }, { "epoch": 13.0, "learning_rate": 1.9326420502444782e-05, "loss": 0.0005, "step": 17190 }, { "epoch": 13.0, "learning_rate": 1.930534479851627e-05, "loss": 0.0091, "step": 17200 }, { "epoch": 13.0, "learning_rate": 1.928426909458776e-05, "loss": 0.1227, "step": 17210 }, { "epoch": 13.0, "learning_rate": 1.926319339065925e-05, "loss": 0.0006, "step": 17220 }, { "epoch": 13.0, "learning_rate": 1.924211768673074e-05, "loss": 0.0003, "step": 17230 }, { "epoch": 13.0, "learning_rate": 1.9221041982802225e-05, "loss": 0.0166, "step": 17240 }, { "epoch": 13.0, "learning_rate": 1.9199966278873715e-05, "loss": 0.0009, "step": 17250 }, { "epoch": 13.0, "learning_rate": 1.9178890574945205e-05, "loss": 0.0002, "step": 17260 }, { "epoch": 13.0, "learning_rate": 1.9157814871016695e-05, "loss": 0.0002, "step": 17270 }, { "epoch": 13.01, "learning_rate": 1.913673916708818e-05, "loss": 0.0009, "step": 17280 }, { "epoch": 13.01, "learning_rate": 1.9115663463159668e-05, "loss": 0.0001, "step": 17290 }, { "epoch": 13.01, "learning_rate": 1.9094587759231158e-05, "loss": 0.0003, "step": 17300 }, { "epoch": 13.01, "learning_rate": 1.9073512055302648e-05, "loss": 0.0002, "step": 17310 }, { "epoch": 13.01, "learning_rate": 1.9052436351374138e-05, "loss": 0.0152, "step": 17320 }, { "epoch": 13.01, "learning_rate": 1.9031360647445625e-05, "loss": 0.0002, "step": 17330 }, { "epoch": 13.01, "learning_rate": 1.9010284943517114e-05, "loss": 0.1763, "step": 17340 }, { "epoch": 13.01, "learning_rate": 1.8989209239588604e-05, "loss": 0.0002, "step": 17350 }, { "epoch": 13.01, "learning_rate": 1.8968133535660094e-05, "loss": 0.0009, "step": 17360 }, { "epoch": 13.01, "learning_rate": 1.894705783173158e-05, "loss": 0.0015, "step": 17370 }, { "epoch": 13.01, "learning_rate": 1.8925982127803067e-05, "loss": 0.0001, "step": 17380 }, { "epoch": 13.01, "learning_rate": 1.8904906423874557e-05, "loss": 0.009, "step": 17390 }, { "epoch": 13.01, "learning_rate": 1.8883830719946047e-05, "loss": 0.0004, "step": 17400 }, { "epoch": 13.01, "learning_rate": 1.8862755016017537e-05, "loss": 0.0851, "step": 17410 }, { "epoch": 13.01, "learning_rate": 1.8841679312089024e-05, "loss": 0.0002, "step": 17420 }, { "epoch": 13.01, "learning_rate": 1.8820603608160514e-05, "loss": 0.1626, "step": 17430 }, { "epoch": 13.01, "learning_rate": 1.8799527904232004e-05, "loss": 0.0081, "step": 17440 }, { "epoch": 13.01, "learning_rate": 1.8778452200303494e-05, "loss": 0.0272, "step": 17450 }, { "epoch": 13.01, "learning_rate": 1.875737649637498e-05, "loss": 0.0005, "step": 17460 }, { "epoch": 13.01, "learning_rate": 1.8736300792446467e-05, "loss": 0.0002, "step": 17470 }, { "epoch": 13.01, "learning_rate": 1.8715225088517957e-05, "loss": 0.0109, "step": 17480 }, { "epoch": 13.01, "learning_rate": 1.8694149384589447e-05, "loss": 0.0001, "step": 17490 }, { "epoch": 13.01, "learning_rate": 1.8673073680660937e-05, "loss": 0.0005, "step": 17500 }, { "epoch": 13.01, "learning_rate": 1.8651997976732423e-05, "loss": 0.006, "step": 17510 }, { "epoch": 13.01, "learning_rate": 1.8630922272803913e-05, "loss": 0.0075, "step": 17520 }, { "epoch": 13.01, "learning_rate": 1.8609846568875403e-05, "loss": 0.0009, "step": 17530 }, { "epoch": 13.01, "learning_rate": 1.858877086494689e-05, "loss": 0.1346, "step": 17540 }, { "epoch": 13.02, "learning_rate": 1.856769516101838e-05, "loss": 0.0889, "step": 17550 }, { "epoch": 13.02, "learning_rate": 1.8546619457089866e-05, "loss": 0.0007, "step": 17560 }, { "epoch": 13.02, "learning_rate": 1.8525543753161356e-05, "loss": 0.0013, "step": 17570 }, { "epoch": 13.02, "learning_rate": 1.8504468049232846e-05, "loss": 0.0001, "step": 17580 }, { "epoch": 13.02, "learning_rate": 1.8483392345304336e-05, "loss": 0.1176, "step": 17590 }, { "epoch": 13.02, "learning_rate": 1.8462316641375823e-05, "loss": 0.0463, "step": 17600 }, { "epoch": 13.02, "learning_rate": 1.8441240937447312e-05, "loss": 0.0005, "step": 17610 }, { "epoch": 13.02, "learning_rate": 1.84201652335188e-05, "loss": 0.0001, "step": 17620 }, { "epoch": 13.02, "learning_rate": 1.839908952959029e-05, "loss": 0.1531, "step": 17630 }, { "epoch": 13.02, "learning_rate": 1.837801382566178e-05, "loss": 0.0007, "step": 17640 }, { "epoch": 13.02, "learning_rate": 1.8356938121733265e-05, "loss": 0.0172, "step": 17650 }, { "epoch": 13.02, "learning_rate": 1.8335862417804755e-05, "loss": 0.0003, "step": 17660 }, { "epoch": 13.02, "learning_rate": 1.8314786713876245e-05, "loss": 0.012, "step": 17670 }, { "epoch": 13.02, "learning_rate": 1.8293711009947735e-05, "loss": 0.0003, "step": 17680 }, { "epoch": 13.02, "learning_rate": 1.8272635306019222e-05, "loss": 0.003, "step": 17690 }, { "epoch": 13.02, "learning_rate": 1.8251559602090712e-05, "loss": 0.0014, "step": 17700 }, { "epoch": 13.02, "learning_rate": 1.82304838981622e-05, "loss": 0.007, "step": 17710 }, { "epoch": 13.02, "learning_rate": 1.8209408194233688e-05, "loss": 0.0001, "step": 17720 }, { "epoch": 13.02, "learning_rate": 1.8188332490305178e-05, "loss": 0.0024, "step": 17730 }, { "epoch": 13.02, "learning_rate": 1.8167256786376665e-05, "loss": 0.0049, "step": 17740 }, { "epoch": 13.02, "learning_rate": 1.8146181082448155e-05, "loss": 0.0244, "step": 17750 }, { "epoch": 13.02, "learning_rate": 1.8125105378519645e-05, "loss": 0.0089, "step": 17760 }, { "epoch": 13.02, "learning_rate": 1.8104029674591135e-05, "loss": 0.0011, "step": 17770 }, { "epoch": 13.02, "learning_rate": 1.808295397066262e-05, "loss": 0.0006, "step": 17780 }, { "epoch": 13.02, "learning_rate": 1.8061878266734108e-05, "loss": 0.0001, "step": 17790 }, { "epoch": 13.02, "learning_rate": 1.8040802562805598e-05, "loss": 0.0287, "step": 17800 }, { "epoch": 13.03, "learning_rate": 1.8019726858877088e-05, "loss": 0.0005, "step": 17810 }, { "epoch": 13.03, "learning_rate": 1.7998651154948578e-05, "loss": 0.0002, "step": 17820 }, { "epoch": 13.03, "learning_rate": 1.7977575451020064e-05, "loss": 0.0002, "step": 17830 }, { "epoch": 13.03, "learning_rate": 1.7956499747091554e-05, "loss": 0.0001, "step": 17840 }, { "epoch": 13.03, "learning_rate": 1.7935424043163044e-05, "loss": 0.0004, "step": 17850 }, { "epoch": 13.03, "learning_rate": 1.7914348339234534e-05, "loss": 0.1421, "step": 17860 }, { "epoch": 13.03, "learning_rate": 1.7893272635306017e-05, "loss": 0.0579, "step": 17870 }, { "epoch": 13.03, "learning_rate": 1.7872196931377507e-05, "loss": 0.0002, "step": 17880 }, { "epoch": 13.03, "learning_rate": 1.7851121227448997e-05, "loss": 0.0392, "step": 17890 }, { "epoch": 13.03, "learning_rate": 1.7830045523520487e-05, "loss": 0.0227, "step": 17900 }, { "epoch": 13.03, "learning_rate": 1.7808969819591974e-05, "loss": 0.0312, "step": 17910 }, { "epoch": 13.03, "learning_rate": 1.7787894115663463e-05, "loss": 0.0072, "step": 17920 }, { "epoch": 13.03, "learning_rate": 1.7766818411734953e-05, "loss": 0.0306, "step": 17930 }, { "epoch": 13.03, "learning_rate": 1.7745742707806443e-05, "loss": 0.3134, "step": 17940 }, { "epoch": 13.03, "learning_rate": 1.7724667003877933e-05, "loss": 0.0164, "step": 17950 }, { "epoch": 13.03, "learning_rate": 1.7703591299949416e-05, "loss": 0.0003, "step": 17960 }, { "epoch": 13.03, "learning_rate": 1.7682515596020906e-05, "loss": 0.013, "step": 17970 }, { "epoch": 13.03, "learning_rate": 1.7661439892092396e-05, "loss": 0.0091, "step": 17980 }, { "epoch": 13.03, "learning_rate": 1.7640364188163886e-05, "loss": 0.0016, "step": 17990 }, { "epoch": 13.03, "learning_rate": 1.7619288484235373e-05, "loss": 0.0703, "step": 18000 }, { "epoch": 13.03, "learning_rate": 1.7598212780306863e-05, "loss": 0.0138, "step": 18010 }, { "epoch": 13.03, "learning_rate": 1.7577137076378353e-05, "loss": 0.065, "step": 18020 }, { "epoch": 13.03, "learning_rate": 1.7556061372449843e-05, "loss": 0.009, "step": 18030 }, { "epoch": 13.03, "learning_rate": 1.753498566852133e-05, "loss": 0.1055, "step": 18040 }, { "epoch": 13.03, "learning_rate": 1.7513909964592816e-05, "loss": 0.0373, "step": 18050 }, { "epoch": 13.03, "learning_rate": 1.7492834260664306e-05, "loss": 0.0206, "step": 18060 }, { "epoch": 13.04, "learning_rate": 1.7471758556735796e-05, "loss": 0.0083, "step": 18070 }, { "epoch": 13.04, "learning_rate": 1.7450682852807286e-05, "loss": 0.0702, "step": 18080 }, { "epoch": 13.04, "learning_rate": 1.7429607148878772e-05, "loss": 0.0011, "step": 18090 }, { "epoch": 13.04, "learning_rate": 1.7408531444950262e-05, "loss": 0.0004, "step": 18100 }, { "epoch": 13.04, "learning_rate": 1.7387455741021752e-05, "loss": 0.0129, "step": 18110 }, { "epoch": 13.04, "learning_rate": 1.7366380037093242e-05, "loss": 0.0002, "step": 18120 }, { "epoch": 13.04, "learning_rate": 1.734530433316473e-05, "loss": 0.0711, "step": 18130 }, { "epoch": 13.04, "learning_rate": 1.7324228629236215e-05, "loss": 0.0034, "step": 18140 }, { "epoch": 13.04, "learning_rate": 1.7303152925307705e-05, "loss": 0.0005, "step": 18150 }, { "epoch": 13.04, "learning_rate": 1.7282077221379195e-05, "loss": 0.019, "step": 18160 }, { "epoch": 13.04, "learning_rate": 1.7261001517450685e-05, "loss": 0.0007, "step": 18170 }, { "epoch": 13.04, "learning_rate": 1.723992581352217e-05, "loss": 0.0034, "step": 18180 }, { "epoch": 13.04, "learning_rate": 1.721885010959366e-05, "loss": 0.1639, "step": 18190 }, { "epoch": 13.04, "learning_rate": 1.719777440566515e-05, "loss": 0.0005, "step": 18200 }, { "epoch": 13.04, "learning_rate": 1.7176698701736638e-05, "loss": 0.0005, "step": 18210 }, { "epoch": 13.04, "learning_rate": 1.7155622997808128e-05, "loss": 0.0019, "step": 18220 }, { "epoch": 13.04, "learning_rate": 1.7134547293879614e-05, "loss": 0.0739, "step": 18230 }, { "epoch": 13.04, "learning_rate": 1.7113471589951104e-05, "loss": 0.0113, "step": 18240 }, { "epoch": 13.04, "learning_rate": 1.7092395886022594e-05, "loss": 0.0023, "step": 18250 }, { "epoch": 13.04, "learning_rate": 1.7071320182094084e-05, "loss": 0.0044, "step": 18260 }, { "epoch": 13.04, "learning_rate": 1.705024447816557e-05, "loss": 0.0002, "step": 18270 }, { "epoch": 13.04, "learning_rate": 1.702916877423706e-05, "loss": 0.0052, "step": 18280 }, { "epoch": 13.04, "learning_rate": 1.7008093070308547e-05, "loss": 0.0002, "step": 18290 }, { "epoch": 13.04, "learning_rate": 1.6987017366380037e-05, "loss": 0.0005, "step": 18300 }, { "epoch": 13.04, "learning_rate": 1.6965941662451527e-05, "loss": 0.0002, "step": 18310 }, { "epoch": 13.04, "learning_rate": 1.6944865958523014e-05, "loss": 0.0011, "step": 18320 }, { "epoch": 13.04, "learning_rate": 1.6923790254594504e-05, "loss": 0.2794, "step": 18330 }, { "epoch": 13.05, "learning_rate": 1.6902714550665994e-05, "loss": 0.0052, "step": 18340 }, { "epoch": 13.05, "learning_rate": 1.6881638846737484e-05, "loss": 0.0001, "step": 18350 }, { "epoch": 13.05, "learning_rate": 1.686056314280897e-05, "loss": 0.0002, "step": 18360 }, { "epoch": 13.05, "learning_rate": 1.683948743888046e-05, "loss": 0.0004, "step": 18370 }, { "epoch": 13.05, "learning_rate": 1.6818411734951947e-05, "loss": 0.0166, "step": 18380 }, { "epoch": 13.05, "learning_rate": 1.6797336031023437e-05, "loss": 0.0665, "step": 18390 }, { "epoch": 13.05, "learning_rate": 1.6776260327094927e-05, "loss": 0.0029, "step": 18400 }, { "epoch": 13.05, "learning_rate": 1.6755184623166413e-05, "loss": 0.0959, "step": 18410 }, { "epoch": 13.05, "learning_rate": 1.6734108919237903e-05, "loss": 0.0775, "step": 18420 }, { "epoch": 13.05, "learning_rate": 1.6713033215309393e-05, "loss": 0.0006, "step": 18430 }, { "epoch": 13.05, "learning_rate": 1.6691957511380883e-05, "loss": 0.1032, "step": 18440 }, { "epoch": 13.05, "learning_rate": 1.667088180745237e-05, "loss": 0.0241, "step": 18450 }, { "epoch": 13.05, "learning_rate": 1.6649806103523856e-05, "loss": 0.0004, "step": 18460 }, { "epoch": 13.05, "eval_accuracy": 0.7838988517610631, "eval_loss": 1.3540375232696533, "eval_runtime": 570.1136, "eval_samples_per_second": 13.596, "eval_steps_per_second": 2.266, "step": 18466 }, { "epoch": 14.0, "learning_rate": 1.6628730399595346e-05, "loss": 0.0006, "step": 18470 }, { "epoch": 14.0, "learning_rate": 1.6607654695666836e-05, "loss": 0.0002, "step": 18480 }, { "epoch": 14.0, "learning_rate": 1.6586578991738326e-05, "loss": 0.1762, "step": 18490 }, { "epoch": 14.0, "learning_rate": 1.6565503287809812e-05, "loss": 0.0002, "step": 18500 }, { "epoch": 14.0, "learning_rate": 1.6544427583881302e-05, "loss": 0.1359, "step": 18510 }, { "epoch": 14.0, "learning_rate": 1.6523351879952792e-05, "loss": 0.0002, "step": 18520 }, { "epoch": 14.0, "learning_rate": 1.6502276176024282e-05, "loss": 0.0001, "step": 18530 }, { "epoch": 14.0, "learning_rate": 1.648120047209577e-05, "loss": 0.0077, "step": 18540 }, { "epoch": 14.0, "learning_rate": 1.6460124768167255e-05, "loss": 0.0458, "step": 18550 }, { "epoch": 14.0, "learning_rate": 1.6439049064238745e-05, "loss": 0.0041, "step": 18560 }, { "epoch": 14.0, "learning_rate": 1.6417973360310235e-05, "loss": 0.0043, "step": 18570 }, { "epoch": 14.0, "learning_rate": 1.6396897656381725e-05, "loss": 0.0146, "step": 18580 }, { "epoch": 14.0, "learning_rate": 1.6375821952453212e-05, "loss": 0.0244, "step": 18590 }, { "epoch": 14.01, "learning_rate": 1.63547462485247e-05, "loss": 0.0005, "step": 18600 }, { "epoch": 14.01, "learning_rate": 1.633367054459619e-05, "loss": 0.0001, "step": 18610 }, { "epoch": 14.01, "learning_rate": 1.631259484066768e-05, "loss": 0.0344, "step": 18620 }, { "epoch": 14.01, "learning_rate": 1.6291519136739168e-05, "loss": 0.0244, "step": 18630 }, { "epoch": 14.01, "learning_rate": 1.6270443432810655e-05, "loss": 0.0001, "step": 18640 }, { "epoch": 14.01, "learning_rate": 1.6249367728882145e-05, "loss": 0.0001, "step": 18650 }, { "epoch": 14.01, "learning_rate": 1.6228292024953635e-05, "loss": 0.0323, "step": 18660 }, { "epoch": 14.01, "learning_rate": 1.6207216321025125e-05, "loss": 0.0601, "step": 18670 }, { "epoch": 14.01, "learning_rate": 1.618614061709661e-05, "loss": 0.0246, "step": 18680 }, { "epoch": 14.01, "learning_rate": 1.61650649131681e-05, "loss": 0.0003, "step": 18690 }, { "epoch": 14.01, "learning_rate": 1.614398920923959e-05, "loss": 0.0001, "step": 18700 }, { "epoch": 14.01, "learning_rate": 1.6122913505311078e-05, "loss": 0.0002, "step": 18710 }, { "epoch": 14.01, "learning_rate": 1.6101837801382567e-05, "loss": 0.0001, "step": 18720 }, { "epoch": 14.01, "learning_rate": 1.6080762097454054e-05, "loss": 0.0414, "step": 18730 }, { "epoch": 14.01, "learning_rate": 1.6059686393525544e-05, "loss": 0.0148, "step": 18740 }, { "epoch": 14.01, "learning_rate": 1.6038610689597034e-05, "loss": 0.0003, "step": 18750 }, { "epoch": 14.01, "learning_rate": 1.6017534985668524e-05, "loss": 0.0003, "step": 18760 }, { "epoch": 14.01, "learning_rate": 1.599645928174001e-05, "loss": 0.0003, "step": 18770 }, { "epoch": 14.01, "learning_rate": 1.59753835778115e-05, "loss": 0.0033, "step": 18780 }, { "epoch": 14.01, "learning_rate": 1.5954307873882987e-05, "loss": 0.0031, "step": 18790 }, { "epoch": 14.01, "learning_rate": 1.5933232169954477e-05, "loss": 0.0004, "step": 18800 }, { "epoch": 14.01, "learning_rate": 1.5912156466025967e-05, "loss": 0.0016, "step": 18810 }, { "epoch": 14.01, "learning_rate": 1.5891080762097453e-05, "loss": 0.016, "step": 18820 }, { "epoch": 14.01, "learning_rate": 1.5870005058168943e-05, "loss": 0.0008, "step": 18830 }, { "epoch": 14.01, "learning_rate": 1.5848929354240433e-05, "loss": 0.0297, "step": 18840 }, { "epoch": 14.01, "learning_rate": 1.5827853650311923e-05, "loss": 0.0005, "step": 18850 }, { "epoch": 14.01, "learning_rate": 1.580677794638341e-05, "loss": 0.034, "step": 18860 }, { "epoch": 14.02, "learning_rate": 1.57857022424549e-05, "loss": 0.0002, "step": 18870 }, { "epoch": 14.02, "learning_rate": 1.5764626538526386e-05, "loss": 0.0334, "step": 18880 }, { "epoch": 14.02, "learning_rate": 1.5743550834597876e-05, "loss": 0.0022, "step": 18890 }, { "epoch": 14.02, "learning_rate": 1.5722475130669366e-05, "loss": 0.0006, "step": 18900 }, { "epoch": 14.02, "learning_rate": 1.5701399426740853e-05, "loss": 0.2324, "step": 18910 }, { "epoch": 14.02, "learning_rate": 1.5680323722812343e-05, "loss": 0.0987, "step": 18920 }, { "epoch": 14.02, "learning_rate": 1.5659248018883833e-05, "loss": 0.0002, "step": 18930 }, { "epoch": 14.02, "learning_rate": 1.5638172314955322e-05, "loss": 0.0053, "step": 18940 }, { "epoch": 14.02, "learning_rate": 1.561709661102681e-05, "loss": 0.0005, "step": 18950 }, { "epoch": 14.02, "learning_rate": 1.5596020907098296e-05, "loss": 0.0004, "step": 18960 }, { "epoch": 14.02, "learning_rate": 1.5574945203169786e-05, "loss": 0.0016, "step": 18970 }, { "epoch": 14.02, "learning_rate": 1.5553869499241275e-05, "loss": 0.0012, "step": 18980 }, { "epoch": 14.02, "learning_rate": 1.5532793795312765e-05, "loss": 0.0028, "step": 18990 }, { "epoch": 14.02, "learning_rate": 1.5511718091384252e-05, "loss": 0.0004, "step": 19000 }, { "epoch": 14.02, "learning_rate": 1.5490642387455742e-05, "loss": 0.0001, "step": 19010 }, { "epoch": 14.02, "learning_rate": 1.5469566683527232e-05, "loss": 0.1418, "step": 19020 }, { "epoch": 14.02, "learning_rate": 1.5448490979598722e-05, "loss": 0.0229, "step": 19030 }, { "epoch": 14.02, "learning_rate": 1.542741527567021e-05, "loss": 0.0035, "step": 19040 }, { "epoch": 14.02, "learning_rate": 1.5406339571741695e-05, "loss": 0.0006, "step": 19050 }, { "epoch": 14.02, "learning_rate": 1.5385263867813185e-05, "loss": 0.0001, "step": 19060 }, { "epoch": 14.02, "learning_rate": 1.5364188163884675e-05, "loss": 0.0005, "step": 19070 }, { "epoch": 14.02, "learning_rate": 1.5343112459956165e-05, "loss": 0.0032, "step": 19080 }, { "epoch": 14.02, "learning_rate": 1.532203675602765e-05, "loss": 0.0002, "step": 19090 }, { "epoch": 14.02, "learning_rate": 1.530096105209914e-05, "loss": 0.0168, "step": 19100 }, { "epoch": 14.02, "learning_rate": 1.527988534817063e-05, "loss": 0.0055, "step": 19110 }, { "epoch": 14.02, "learning_rate": 1.525880964424212e-05, "loss": 0.0002, "step": 19120 }, { "epoch": 14.03, "learning_rate": 1.5237733940313606e-05, "loss": 0.0447, "step": 19130 }, { "epoch": 14.03, "learning_rate": 1.5216658236385096e-05, "loss": 0.1105, "step": 19140 }, { "epoch": 14.03, "learning_rate": 1.5195582532456584e-05, "loss": 0.0765, "step": 19150 }, { "epoch": 14.03, "learning_rate": 1.5174506828528074e-05, "loss": 0.0186, "step": 19160 }, { "epoch": 14.03, "learning_rate": 1.5153431124599562e-05, "loss": 0.0008, "step": 19170 }, { "epoch": 14.03, "learning_rate": 1.5132355420671052e-05, "loss": 0.0443, "step": 19180 }, { "epoch": 14.03, "learning_rate": 1.511127971674254e-05, "loss": 0.0057, "step": 19190 }, { "epoch": 14.03, "learning_rate": 1.509020401281403e-05, "loss": 0.0003, "step": 19200 }, { "epoch": 14.03, "learning_rate": 1.5069128308885515e-05, "loss": 0.0001, "step": 19210 }, { "epoch": 14.03, "learning_rate": 1.5048052604957005e-05, "loss": 0.0003, "step": 19220 }, { "epoch": 14.03, "learning_rate": 1.5026976901028494e-05, "loss": 0.0012, "step": 19230 }, { "epoch": 14.03, "learning_rate": 1.5005901197099984e-05, "loss": 0.0002, "step": 19240 }, { "epoch": 14.03, "learning_rate": 1.4984825493171473e-05, "loss": 0.0197, "step": 19250 }, { "epoch": 14.03, "learning_rate": 1.4963749789242962e-05, "loss": 0.0001, "step": 19260 }, { "epoch": 14.03, "learning_rate": 1.4942674085314452e-05, "loss": 0.0001, "step": 19270 }, { "epoch": 14.03, "learning_rate": 1.492159838138594e-05, "loss": 0.0031, "step": 19280 }, { "epoch": 14.03, "learning_rate": 1.490052267745743e-05, "loss": 0.0004, "step": 19290 }, { "epoch": 14.03, "learning_rate": 1.4879446973528915e-05, "loss": 0.0034, "step": 19300 }, { "epoch": 14.03, "learning_rate": 1.4858371269600405e-05, "loss": 0.0001, "step": 19310 }, { "epoch": 14.03, "learning_rate": 1.4837295565671893e-05, "loss": 0.0001, "step": 19320 }, { "epoch": 14.03, "learning_rate": 1.4816219861743383e-05, "loss": 0.0364, "step": 19330 }, { "epoch": 14.03, "learning_rate": 1.4795144157814871e-05, "loss": 0.0032, "step": 19340 }, { "epoch": 14.03, "learning_rate": 1.4774068453886361e-05, "loss": 0.1346, "step": 19350 }, { "epoch": 14.03, "learning_rate": 1.4752992749957851e-05, "loss": 0.0002, "step": 19360 }, { "epoch": 14.03, "learning_rate": 1.473191704602934e-05, "loss": 0.0048, "step": 19370 }, { "epoch": 14.03, "learning_rate": 1.4710841342100826e-05, "loss": 0.0032, "step": 19380 }, { "epoch": 14.04, "learning_rate": 1.4689765638172314e-05, "loss": 0.0009, "step": 19390 }, { "epoch": 14.04, "learning_rate": 1.4668689934243804e-05, "loss": 0.1642, "step": 19400 }, { "epoch": 14.04, "learning_rate": 1.4647614230315292e-05, "loss": 0.0009, "step": 19410 }, { "epoch": 14.04, "learning_rate": 1.4626538526386782e-05, "loss": 0.0084, "step": 19420 }, { "epoch": 14.04, "learning_rate": 1.460546282245827e-05, "loss": 0.0004, "step": 19430 }, { "epoch": 14.04, "learning_rate": 1.458438711852976e-05, "loss": 0.0002, "step": 19440 }, { "epoch": 14.04, "learning_rate": 1.456331141460125e-05, "loss": 0.0018, "step": 19450 }, { "epoch": 14.04, "learning_rate": 1.4542235710672735e-05, "loss": 0.0001, "step": 19460 }, { "epoch": 14.04, "learning_rate": 1.4521160006744225e-05, "loss": 0.0002, "step": 19470 }, { "epoch": 14.04, "learning_rate": 1.4500084302815713e-05, "loss": 0.0035, "step": 19480 }, { "epoch": 14.04, "learning_rate": 1.4479008598887203e-05, "loss": 0.0002, "step": 19490 }, { "epoch": 14.04, "learning_rate": 1.4457932894958692e-05, "loss": 0.0243, "step": 19500 }, { "epoch": 14.04, "learning_rate": 1.4436857191030182e-05, "loss": 0.0005, "step": 19510 }, { "epoch": 14.04, "learning_rate": 1.441578148710167e-05, "loss": 0.0024, "step": 19520 }, { "epoch": 14.04, "learning_rate": 1.439470578317316e-05, "loss": 0.0018, "step": 19530 }, { "epoch": 14.04, "learning_rate": 1.4373630079244648e-05, "loss": 0.0018, "step": 19540 }, { "epoch": 14.04, "learning_rate": 1.4352554375316135e-05, "loss": 0.0001, "step": 19550 }, { "epoch": 14.04, "learning_rate": 1.4331478671387624e-05, "loss": 0.168, "step": 19560 }, { "epoch": 14.04, "learning_rate": 1.4310402967459113e-05, "loss": 0.0008, "step": 19570 }, { "epoch": 14.04, "learning_rate": 1.4289327263530603e-05, "loss": 0.0245, "step": 19580 }, { "epoch": 14.04, "learning_rate": 1.4268251559602091e-05, "loss": 0.0019, "step": 19590 }, { "epoch": 14.04, "learning_rate": 1.424717585567358e-05, "loss": 0.0002, "step": 19600 }, { "epoch": 14.04, "learning_rate": 1.4226100151745069e-05, "loss": 0.0001, "step": 19610 }, { "epoch": 14.04, "learning_rate": 1.4205024447816559e-05, "loss": 0.0003, "step": 19620 }, { "epoch": 14.04, "learning_rate": 1.4183948743888046e-05, "loss": 0.0002, "step": 19630 }, { "epoch": 14.04, "learning_rate": 1.4162873039959534e-05, "loss": 0.0049, "step": 19640 }, { "epoch": 14.04, "learning_rate": 1.4141797336031024e-05, "loss": 0.0008, "step": 19650 }, { "epoch": 14.05, "learning_rate": 1.4120721632102512e-05, "loss": 0.0256, "step": 19660 }, { "epoch": 14.05, "learning_rate": 1.4099645928174002e-05, "loss": 0.0001, "step": 19670 }, { "epoch": 14.05, "learning_rate": 1.407857022424549e-05, "loss": 0.0026, "step": 19680 }, { "epoch": 14.05, "learning_rate": 1.405749452031698e-05, "loss": 0.0001, "step": 19690 }, { "epoch": 14.05, "learning_rate": 1.4036418816388468e-05, "loss": 0.0236, "step": 19700 }, { "epoch": 14.05, "learning_rate": 1.4015343112459955e-05, "loss": 0.0003, "step": 19710 }, { "epoch": 14.05, "learning_rate": 1.3994267408531445e-05, "loss": 0.0004, "step": 19720 }, { "epoch": 14.05, "learning_rate": 1.3973191704602933e-05, "loss": 0.0002, "step": 19730 }, { "epoch": 14.05, "learning_rate": 1.3952116000674423e-05, "loss": 0.0026, "step": 19740 }, { "epoch": 14.05, "learning_rate": 1.3931040296745911e-05, "loss": 0.0043, "step": 19750 }, { "epoch": 14.05, "learning_rate": 1.3909964592817401e-05, "loss": 0.0007, "step": 19760 }, { "epoch": 14.05, "learning_rate": 1.388888888888889e-05, "loss": 0.0001, "step": 19770 }, { "epoch": 14.05, "learning_rate": 1.386781318496038e-05, "loss": 0.0456, "step": 19780 }, { "epoch": 14.05, "eval_accuracy": 0.7908656947490647, "eval_loss": 1.3907076120376587, "eval_runtime": 652.1139, "eval_samples_per_second": 11.886, "eval_steps_per_second": 1.981, "step": 19785 }, { "epoch": 15.0, "learning_rate": 1.3846737481031868e-05, "loss": 0.0656, "step": 19790 }, { "epoch": 15.0, "learning_rate": 1.3825661777103354e-05, "loss": 0.0015, "step": 19800 }, { "epoch": 15.0, "learning_rate": 1.3804586073174844e-05, "loss": 0.0004, "step": 19810 }, { "epoch": 15.0, "learning_rate": 1.3783510369246332e-05, "loss": 0.0004, "step": 19820 }, { "epoch": 15.0, "learning_rate": 1.3762434665317822e-05, "loss": 0.0001, "step": 19830 }, { "epoch": 15.0, "learning_rate": 1.374135896138931e-05, "loss": 0.0003, "step": 19840 }, { "epoch": 15.0, "learning_rate": 1.37202832574608e-05, "loss": 0.0004, "step": 19850 }, { "epoch": 15.0, "learning_rate": 1.3699207553532289e-05, "loss": 0.0499, "step": 19860 }, { "epoch": 15.0, "learning_rate": 1.3678131849603779e-05, "loss": 0.0076, "step": 19870 }, { "epoch": 15.0, "learning_rate": 1.3657056145675265e-05, "loss": 0.0002, "step": 19880 }, { "epoch": 15.0, "learning_rate": 1.3635980441746754e-05, "loss": 0.0012, "step": 19890 }, { "epoch": 15.0, "learning_rate": 1.3614904737818244e-05, "loss": 0.0002, "step": 19900 }, { "epoch": 15.0, "learning_rate": 1.3593829033889732e-05, "loss": 0.0381, "step": 19910 }, { "epoch": 15.01, "learning_rate": 1.3572753329961222e-05, "loss": 0.0007, "step": 19920 }, { "epoch": 15.01, "learning_rate": 1.355167762603271e-05, "loss": 0.0003, "step": 19930 }, { "epoch": 15.01, "learning_rate": 1.35306019221042e-05, "loss": 0.0091, "step": 19940 }, { "epoch": 15.01, "learning_rate": 1.3509526218175688e-05, "loss": 0.0317, "step": 19950 }, { "epoch": 15.01, "learning_rate": 1.3488450514247178e-05, "loss": 0.0001, "step": 19960 }, { "epoch": 15.01, "learning_rate": 1.3467374810318665e-05, "loss": 0.1293, "step": 19970 }, { "epoch": 15.01, "learning_rate": 1.3446299106390153e-05, "loss": 0.0118, "step": 19980 }, { "epoch": 15.01, "learning_rate": 1.3425223402461643e-05, "loss": 0.0846, "step": 19990 }, { "epoch": 15.01, "learning_rate": 1.3404147698533131e-05, "loss": 0.0559, "step": 20000 }, { "epoch": 15.01, "learning_rate": 1.3383071994604621e-05, "loss": 0.0002, "step": 20010 }, { "epoch": 15.01, "learning_rate": 1.336199629067611e-05, "loss": 0.0001, "step": 20020 }, { "epoch": 15.01, "learning_rate": 1.33409205867476e-05, "loss": 0.0969, "step": 20030 }, { "epoch": 15.01, "learning_rate": 1.3319844882819088e-05, "loss": 0.065, "step": 20040 }, { "epoch": 15.01, "learning_rate": 1.3298769178890574e-05, "loss": 0.1131, "step": 20050 }, { "epoch": 15.01, "learning_rate": 1.3277693474962064e-05, "loss": 0.0002, "step": 20060 }, { "epoch": 15.01, "learning_rate": 1.3256617771033552e-05, "loss": 0.0002, "step": 20070 }, { "epoch": 15.01, "learning_rate": 1.3235542067105042e-05, "loss": 0.0009, "step": 20080 }, { "epoch": 15.01, "learning_rate": 1.321446636317653e-05, "loss": 0.0001, "step": 20090 }, { "epoch": 15.01, "learning_rate": 1.319339065924802e-05, "loss": 0.0979, "step": 20100 }, { "epoch": 15.01, "learning_rate": 1.3172314955319509e-05, "loss": 0.0002, "step": 20110 }, { "epoch": 15.01, "learning_rate": 1.3151239251390999e-05, "loss": 0.0008, "step": 20120 }, { "epoch": 15.01, "learning_rate": 1.3130163547462485e-05, "loss": 0.0003, "step": 20130 }, { "epoch": 15.01, "learning_rate": 1.3109087843533973e-05, "loss": 0.001, "step": 20140 }, { "epoch": 15.01, "learning_rate": 1.3088012139605463e-05, "loss": 0.0001, "step": 20150 }, { "epoch": 15.01, "learning_rate": 1.3066936435676952e-05, "loss": 0.0001, "step": 20160 }, { "epoch": 15.01, "learning_rate": 1.3045860731748442e-05, "loss": 0.0381, "step": 20170 }, { "epoch": 15.01, "learning_rate": 1.302478502781993e-05, "loss": 0.1874, "step": 20180 }, { "epoch": 15.02, "learning_rate": 1.300370932389142e-05, "loss": 0.0003, "step": 20190 }, { "epoch": 15.02, "learning_rate": 1.2982633619962908e-05, "loss": 0.0001, "step": 20200 }, { "epoch": 15.02, "learning_rate": 1.2961557916034398e-05, "loss": 0.0002, "step": 20210 }, { "epoch": 15.02, "learning_rate": 1.2940482212105884e-05, "loss": 0.0086, "step": 20220 }, { "epoch": 15.02, "learning_rate": 1.2919406508177373e-05, "loss": 0.0038, "step": 20230 }, { "epoch": 15.02, "learning_rate": 1.2898330804248863e-05, "loss": 0.1713, "step": 20240 }, { "epoch": 15.02, "learning_rate": 1.2877255100320351e-05, "loss": 0.0054, "step": 20250 }, { "epoch": 15.02, "learning_rate": 1.2856179396391841e-05, "loss": 0.0004, "step": 20260 }, { "epoch": 15.02, "learning_rate": 1.2835103692463329e-05, "loss": 0.153, "step": 20270 }, { "epoch": 15.02, "learning_rate": 1.2814027988534819e-05, "loss": 0.0004, "step": 20280 }, { "epoch": 15.02, "learning_rate": 1.2792952284606307e-05, "loss": 0.0973, "step": 20290 }, { "epoch": 15.02, "learning_rate": 1.2771876580677794e-05, "loss": 0.0001, "step": 20300 }, { "epoch": 15.02, "learning_rate": 1.2750800876749284e-05, "loss": 0.0067, "step": 20310 }, { "epoch": 15.02, "learning_rate": 1.2729725172820772e-05, "loss": 0.0016, "step": 20320 }, { "epoch": 15.02, "learning_rate": 1.2708649468892262e-05, "loss": 0.0049, "step": 20330 }, { "epoch": 15.02, "learning_rate": 1.268757376496375e-05, "loss": 0.1249, "step": 20340 }, { "epoch": 15.02, "learning_rate": 1.266649806103524e-05, "loss": 0.0001, "step": 20350 }, { "epoch": 15.02, "learning_rate": 1.2645422357106728e-05, "loss": 0.0001, "step": 20360 }, { "epoch": 15.02, "learning_rate": 1.2624346653178218e-05, "loss": 0.2086, "step": 20370 }, { "epoch": 15.02, "learning_rate": 1.2603270949249705e-05, "loss": 0.0012, "step": 20380 }, { "epoch": 15.02, "learning_rate": 1.2582195245321193e-05, "loss": 0.0138, "step": 20390 }, { "epoch": 15.02, "learning_rate": 1.2561119541392683e-05, "loss": 0.0001, "step": 20400 }, { "epoch": 15.02, "learning_rate": 1.2540043837464171e-05, "loss": 0.0001, "step": 20410 }, { "epoch": 15.02, "learning_rate": 1.2518968133535661e-05, "loss": 0.0002, "step": 20420 }, { "epoch": 15.02, "learning_rate": 1.249789242960715e-05, "loss": 0.0001, "step": 20430 }, { "epoch": 15.02, "learning_rate": 1.247681672567864e-05, "loss": 0.074, "step": 20440 }, { "epoch": 15.03, "learning_rate": 1.2455741021750126e-05, "loss": 0.0001, "step": 20450 }, { "epoch": 15.03, "learning_rate": 1.2434665317821616e-05, "loss": 0.0013, "step": 20460 }, { "epoch": 15.03, "learning_rate": 1.2413589613893104e-05, "loss": 0.0375, "step": 20470 }, { "epoch": 15.03, "learning_rate": 1.2392513909964594e-05, "loss": 0.0001, "step": 20480 }, { "epoch": 15.03, "learning_rate": 1.2371438206036082e-05, "loss": 0.0003, "step": 20490 }, { "epoch": 15.03, "learning_rate": 1.235036250210757e-05, "loss": 0.1122, "step": 20500 }, { "epoch": 15.03, "learning_rate": 1.232928679817906e-05, "loss": 0.0087, "step": 20510 }, { "epoch": 15.03, "learning_rate": 1.2308211094250549e-05, "loss": 0.0001, "step": 20520 }, { "epoch": 15.03, "learning_rate": 1.2287135390322037e-05, "loss": 0.0739, "step": 20530 }, { "epoch": 15.03, "learning_rate": 1.2266059686393525e-05, "loss": 0.001, "step": 20540 }, { "epoch": 15.03, "learning_rate": 1.2244983982465015e-05, "loss": 0.0001, "step": 20550 }, { "epoch": 15.03, "learning_rate": 1.2223908278536504e-05, "loss": 0.0002, "step": 20560 }, { "epoch": 15.03, "learning_rate": 1.2202832574607992e-05, "loss": 0.0002, "step": 20570 }, { "epoch": 15.03, "learning_rate": 1.2181756870679482e-05, "loss": 0.0002, "step": 20580 }, { "epoch": 15.03, "learning_rate": 1.216068116675097e-05, "loss": 0.0001, "step": 20590 }, { "epoch": 15.03, "learning_rate": 1.213960546282246e-05, "loss": 0.0089, "step": 20600 }, { "epoch": 15.03, "learning_rate": 1.2118529758893947e-05, "loss": 0.0001, "step": 20610 }, { "epoch": 15.03, "learning_rate": 1.2097454054965436e-05, "loss": 0.0011, "step": 20620 }, { "epoch": 15.03, "learning_rate": 1.2076378351036925e-05, "loss": 0.0005, "step": 20630 }, { "epoch": 15.03, "learning_rate": 1.2055302647108415e-05, "loss": 0.0001, "step": 20640 }, { "epoch": 15.03, "learning_rate": 1.2034226943179903e-05, "loss": 0.002, "step": 20650 }, { "epoch": 15.03, "learning_rate": 1.2013151239251391e-05, "loss": 0.0202, "step": 20660 }, { "epoch": 15.03, "learning_rate": 1.1992075535322881e-05, "loss": 0.0115, "step": 20670 }, { "epoch": 15.03, "learning_rate": 1.197099983139437e-05, "loss": 0.0909, "step": 20680 }, { "epoch": 15.03, "learning_rate": 1.194992412746586e-05, "loss": 0.0002, "step": 20690 }, { "epoch": 15.03, "learning_rate": 1.1928848423537346e-05, "loss": 0.0004, "step": 20700 }, { "epoch": 15.04, "learning_rate": 1.1907772719608836e-05, "loss": 0.0002, "step": 20710 }, { "epoch": 15.04, "learning_rate": 1.1886697015680324e-05, "loss": 0.0908, "step": 20720 }, { "epoch": 15.04, "learning_rate": 1.1865621311751814e-05, "loss": 0.0001, "step": 20730 }, { "epoch": 15.04, "learning_rate": 1.18445456078233e-05, "loss": 0.0048, "step": 20740 }, { "epoch": 15.04, "learning_rate": 1.182346990389479e-05, "loss": 0.0021, "step": 20750 }, { "epoch": 15.04, "learning_rate": 1.1802394199966279e-05, "loss": 0.037, "step": 20760 }, { "epoch": 15.04, "learning_rate": 1.1781318496037769e-05, "loss": 0.0001, "step": 20770 }, { "epoch": 15.04, "learning_rate": 1.1760242792109257e-05, "loss": 0.0141, "step": 20780 }, { "epoch": 15.04, "learning_rate": 1.1739167088180745e-05, "loss": 0.0275, "step": 20790 }, { "epoch": 15.04, "learning_rate": 1.1718091384252235e-05, "loss": 0.0001, "step": 20800 }, { "epoch": 15.04, "learning_rate": 1.1697015680323723e-05, "loss": 0.0066, "step": 20810 }, { "epoch": 15.04, "learning_rate": 1.1675939976395212e-05, "loss": 0.0002, "step": 20820 }, { "epoch": 15.04, "learning_rate": 1.16548642724667e-05, "loss": 0.0002, "step": 20830 }, { "epoch": 15.04, "learning_rate": 1.163378856853819e-05, "loss": 0.0037, "step": 20840 }, { "epoch": 15.04, "learning_rate": 1.1612712864609678e-05, "loss": 0.0004, "step": 20850 }, { "epoch": 15.04, "learning_rate": 1.1591637160681166e-05, "loss": 0.0001, "step": 20860 }, { "epoch": 15.04, "learning_rate": 1.1570561456752656e-05, "loss": 0.0001, "step": 20870 }, { "epoch": 15.04, "learning_rate": 1.1549485752824145e-05, "loss": 0.0001, "step": 20880 }, { "epoch": 15.04, "learning_rate": 1.1528410048895634e-05, "loss": 0.0003, "step": 20890 }, { "epoch": 15.04, "learning_rate": 1.1507334344967123e-05, "loss": 0.0002, "step": 20900 }, { "epoch": 15.04, "learning_rate": 1.1486258641038611e-05, "loss": 0.011, "step": 20910 }, { "epoch": 15.04, "learning_rate": 1.14651829371101e-05, "loss": 0.0029, "step": 20920 }, { "epoch": 15.04, "learning_rate": 1.144410723318159e-05, "loss": 0.0004, "step": 20930 }, { "epoch": 15.04, "learning_rate": 1.1423031529253077e-05, "loss": 0.0186, "step": 20940 }, { "epoch": 15.04, "learning_rate": 1.1401955825324566e-05, "loss": 0.0004, "step": 20950 }, { "epoch": 15.04, "learning_rate": 1.1380880121396056e-05, "loss": 0.0002, "step": 20960 }, { "epoch": 15.04, "learning_rate": 1.1359804417467544e-05, "loss": 0.0006, "step": 20970 }, { "epoch": 15.05, "learning_rate": 1.1338728713539034e-05, "loss": 0.0004, "step": 20980 }, { "epoch": 15.05, "learning_rate": 1.131765300961052e-05, "loss": 0.0001, "step": 20990 }, { "epoch": 15.05, "learning_rate": 1.129657730568201e-05, "loss": 0.0001, "step": 21000 }, { "epoch": 15.05, "learning_rate": 1.1275501601753499e-05, "loss": 0.0001, "step": 21010 }, { "epoch": 15.05, "learning_rate": 1.1254425897824988e-05, "loss": 0.0001, "step": 21020 }, { "epoch": 15.05, "learning_rate": 1.1233350193896477e-05, "loss": 0.0002, "step": 21030 }, { "epoch": 15.05, "learning_rate": 1.1212274489967965e-05, "loss": 0.0002, "step": 21040 }, { "epoch": 15.05, "learning_rate": 1.1191198786039455e-05, "loss": 0.0001, "step": 21050 }, { "epoch": 15.05, "learning_rate": 1.1170123082110943e-05, "loss": 0.0007, "step": 21060 }, { "epoch": 15.05, "learning_rate": 1.1149047378182431e-05, "loss": 0.0002, "step": 21070 }, { "epoch": 15.05, "learning_rate": 1.112797167425392e-05, "loss": 0.0011, "step": 21080 }, { "epoch": 15.05, "learning_rate": 1.110689597032541e-05, "loss": 0.0001, "step": 21090 }, { "epoch": 15.05, "learning_rate": 1.1085820266396898e-05, "loss": 0.0017, "step": 21100 }, { "epoch": 15.05, "eval_accuracy": 0.7969294284608438, "eval_loss": 1.3211185932159424, "eval_runtime": 610.8985, "eval_samples_per_second": 12.688, "eval_steps_per_second": 2.115, "step": 21104 }, { "epoch": 16.0, "learning_rate": 1.1064744562468388e-05, "loss": 0.0001, "step": 21110 }, { "epoch": 16.0, "learning_rate": 1.1043668858539876e-05, "loss": 0.0003, "step": 21120 }, { "epoch": 16.0, "learning_rate": 1.1022593154611364e-05, "loss": 0.0323, "step": 21130 }, { "epoch": 16.0, "learning_rate": 1.1001517450682854e-05, "loss": 0.0002, "step": 21140 }, { "epoch": 16.0, "learning_rate": 1.0980441746754343e-05, "loss": 0.0006, "step": 21150 }, { "epoch": 16.0, "learning_rate": 1.095936604282583e-05, "loss": 0.0001, "step": 21160 }, { "epoch": 16.0, "learning_rate": 1.0938290338897319e-05, "loss": 0.0005, "step": 21170 }, { "epoch": 16.0, "learning_rate": 1.0917214634968809e-05, "loss": 0.0695, "step": 21180 }, { "epoch": 16.0, "learning_rate": 1.0896138931040297e-05, "loss": 0.099, "step": 21190 }, { "epoch": 16.0, "learning_rate": 1.0875063227111785e-05, "loss": 0.0255, "step": 21200 }, { "epoch": 16.0, "learning_rate": 1.0853987523183275e-05, "loss": 0.0001, "step": 21210 }, { "epoch": 16.0, "learning_rate": 1.0832911819254764e-05, "loss": 0.0003, "step": 21220 }, { "epoch": 16.0, "learning_rate": 1.0811836115326254e-05, "loss": 0.0002, "step": 21230 }, { "epoch": 16.01, "learning_rate": 1.079076041139774e-05, "loss": 0.0001, "step": 21240 }, { "epoch": 16.01, "learning_rate": 1.076968470746923e-05, "loss": 0.0001, "step": 21250 }, { "epoch": 16.01, "learning_rate": 1.0748609003540718e-05, "loss": 0.005, "step": 21260 }, { "epoch": 16.01, "learning_rate": 1.0727533299612208e-05, "loss": 0.0004, "step": 21270 }, { "epoch": 16.01, "learning_rate": 1.0706457595683697e-05, "loss": 0.0021, "step": 21280 }, { "epoch": 16.01, "learning_rate": 1.0685381891755185e-05, "loss": 0.0002, "step": 21290 }, { "epoch": 16.01, "learning_rate": 1.0664306187826675e-05, "loss": 0.1126, "step": 21300 }, { "epoch": 16.01, "learning_rate": 1.0643230483898163e-05, "loss": 0.0001, "step": 21310 }, { "epoch": 16.01, "learning_rate": 1.0622154779969651e-05, "loss": 0.0024, "step": 21320 }, { "epoch": 16.01, "learning_rate": 1.060107907604114e-05, "loss": 0.0701, "step": 21330 }, { "epoch": 16.01, "learning_rate": 1.058000337211263e-05, "loss": 0.0438, "step": 21340 }, { "epoch": 16.01, "learning_rate": 1.0558927668184118e-05, "loss": 0.0001, "step": 21350 }, { "epoch": 16.01, "learning_rate": 1.0537851964255608e-05, "loss": 0.0002, "step": 21360 }, { "epoch": 16.01, "learning_rate": 1.0516776260327094e-05, "loss": 0.0001, "step": 21370 }, { "epoch": 16.01, "learning_rate": 1.0495700556398584e-05, "loss": 0.0001, "step": 21380 }, { "epoch": 16.01, "learning_rate": 1.0474624852470074e-05, "loss": 0.0001, "step": 21390 }, { "epoch": 16.01, "learning_rate": 1.0453549148541562e-05, "loss": 0.0001, "step": 21400 }, { "epoch": 16.01, "learning_rate": 1.043247344461305e-05, "loss": 0.0002, "step": 21410 }, { "epoch": 16.01, "learning_rate": 1.0411397740684539e-05, "loss": 0.0002, "step": 21420 }, { "epoch": 16.01, "learning_rate": 1.0390322036756029e-05, "loss": 0.0509, "step": 21430 }, { "epoch": 16.01, "learning_rate": 1.0369246332827517e-05, "loss": 0.0001, "step": 21440 }, { "epoch": 16.01, "learning_rate": 1.0348170628899005e-05, "loss": 0.0036, "step": 21450 }, { "epoch": 16.01, "learning_rate": 1.0327094924970493e-05, "loss": 0.0001, "step": 21460 }, { "epoch": 16.01, "learning_rate": 1.0306019221041983e-05, "loss": 0.0005, "step": 21470 }, { "epoch": 16.01, "learning_rate": 1.0284943517113473e-05, "loss": 0.0002, "step": 21480 }, { "epoch": 16.01, "learning_rate": 1.026386781318496e-05, "loss": 0.0005, "step": 21490 }, { "epoch": 16.02, "learning_rate": 1.024279210925645e-05, "loss": 0.0001, "step": 21500 }, { "epoch": 16.02, "learning_rate": 1.0221716405327938e-05, "loss": 0.0607, "step": 21510 }, { "epoch": 16.02, "learning_rate": 1.0200640701399428e-05, "loss": 0.0985, "step": 21520 }, { "epoch": 16.02, "learning_rate": 1.0179564997470915e-05, "loss": 0.0002, "step": 21530 }, { "epoch": 16.02, "learning_rate": 1.0158489293542405e-05, "loss": 0.0003, "step": 21540 }, { "epoch": 16.02, "learning_rate": 1.0137413589613893e-05, "loss": 0.0006, "step": 21550 }, { "epoch": 16.02, "learning_rate": 1.0116337885685383e-05, "loss": 0.0679, "step": 21560 }, { "epoch": 16.02, "learning_rate": 1.0095262181756871e-05, "loss": 0.0043, "step": 21570 }, { "epoch": 16.02, "learning_rate": 1.007418647782836e-05, "loss": 0.0001, "step": 21580 }, { "epoch": 16.02, "learning_rate": 1.005311077389985e-05, "loss": 0.0001, "step": 21590 }, { "epoch": 16.02, "learning_rate": 1.0032035069971337e-05, "loss": 0.0001, "step": 21600 }, { "epoch": 16.02, "learning_rate": 1.0010959366042827e-05, "loss": 0.1701, "step": 21610 }, { "epoch": 16.02, "learning_rate": 9.989883662114314e-06, "loss": 0.0005, "step": 21620 }, { "epoch": 16.02, "learning_rate": 9.968807958185804e-06, "loss": 0.0399, "step": 21630 }, { "epoch": 16.02, "learning_rate": 9.947732254257292e-06, "loss": 0.0004, "step": 21640 }, { "epoch": 16.02, "learning_rate": 9.926656550328782e-06, "loss": 0.0001, "step": 21650 }, { "epoch": 16.02, "learning_rate": 9.90558084640027e-06, "loss": 0.0012, "step": 21660 }, { "epoch": 16.02, "learning_rate": 9.884505142471759e-06, "loss": 0.0005, "step": 21670 }, { "epoch": 16.02, "learning_rate": 9.863429438543249e-06, "loss": 0.0001, "step": 21680 }, { "epoch": 16.02, "learning_rate": 9.842353734614737e-06, "loss": 0.0019, "step": 21690 }, { "epoch": 16.02, "learning_rate": 9.821278030686225e-06, "loss": 0.0001, "step": 21700 }, { "epoch": 16.02, "learning_rate": 9.800202326757713e-06, "loss": 0.0036, "step": 21710 }, { "epoch": 16.02, "learning_rate": 9.779126622829203e-06, "loss": 0.0002, "step": 21720 }, { "epoch": 16.02, "learning_rate": 9.758050918900691e-06, "loss": 0.0057, "step": 21730 }, { "epoch": 16.02, "learning_rate": 9.73697521497218e-06, "loss": 0.0007, "step": 21740 }, { "epoch": 16.02, "learning_rate": 9.71589951104367e-06, "loss": 0.0079, "step": 21750 }, { "epoch": 16.02, "learning_rate": 9.694823807115158e-06, "loss": 0.0001, "step": 21760 }, { "epoch": 16.03, "learning_rate": 9.673748103186648e-06, "loss": 0.0001, "step": 21770 }, { "epoch": 16.03, "learning_rate": 9.652672399258134e-06, "loss": 0.0001, "step": 21780 }, { "epoch": 16.03, "learning_rate": 9.631596695329624e-06, "loss": 0.0001, "step": 21790 }, { "epoch": 16.03, "learning_rate": 9.610520991401113e-06, "loss": 0.0204, "step": 21800 }, { "epoch": 16.03, "learning_rate": 9.589445287472603e-06, "loss": 0.0001, "step": 21810 }, { "epoch": 16.03, "learning_rate": 9.56836958354409e-06, "loss": 0.0068, "step": 21820 }, { "epoch": 16.03, "learning_rate": 9.547293879615579e-06, "loss": 0.0001, "step": 21830 }, { "epoch": 16.03, "learning_rate": 9.526218175687069e-06, "loss": 0.0001, "step": 21840 }, { "epoch": 16.03, "learning_rate": 9.505142471758557e-06, "loss": 0.0001, "step": 21850 }, { "epoch": 16.03, "learning_rate": 9.484066767830047e-06, "loss": 0.0001, "step": 21860 }, { "epoch": 16.03, "learning_rate": 9.462991063901534e-06, "loss": 0.0001, "step": 21870 }, { "epoch": 16.03, "learning_rate": 9.441915359973024e-06, "loss": 0.0056, "step": 21880 }, { "epoch": 16.03, "learning_rate": 9.420839656044512e-06, "loss": 0.0005, "step": 21890 }, { "epoch": 16.03, "learning_rate": 9.399763952116002e-06, "loss": 0.0001, "step": 21900 }, { "epoch": 16.03, "learning_rate": 9.37868824818749e-06, "loss": 0.0387, "step": 21910 }, { "epoch": 16.03, "learning_rate": 9.357612544258978e-06, "loss": 0.0001, "step": 21920 }, { "epoch": 16.03, "learning_rate": 9.336536840330468e-06, "loss": 0.043, "step": 21930 }, { "epoch": 16.03, "learning_rate": 9.315461136401957e-06, "loss": 0.0004, "step": 21940 }, { "epoch": 16.03, "learning_rate": 9.294385432473445e-06, "loss": 0.0001, "step": 21950 }, { "epoch": 16.03, "learning_rate": 9.273309728544933e-06, "loss": 0.161, "step": 21960 }, { "epoch": 16.03, "learning_rate": 9.252234024616423e-06, "loss": 0.001, "step": 21970 }, { "epoch": 16.03, "learning_rate": 9.231158320687911e-06, "loss": 0.0019, "step": 21980 }, { "epoch": 16.03, "learning_rate": 9.2100826167594e-06, "loss": 0.0002, "step": 21990 }, { "epoch": 16.03, "learning_rate": 9.18900691283089e-06, "loss": 0.0043, "step": 22000 }, { "epoch": 16.03, "learning_rate": 9.167931208902378e-06, "loss": 0.0002, "step": 22010 }, { "epoch": 16.03, "learning_rate": 9.146855504973868e-06, "loss": 0.1765, "step": 22020 }, { "epoch": 16.04, "learning_rate": 9.125779801045356e-06, "loss": 0.0001, "step": 22030 }, { "epoch": 16.04, "learning_rate": 9.104704097116844e-06, "loss": 0.0001, "step": 22040 }, { "epoch": 16.04, "learning_rate": 9.083628393188332e-06, "loss": 0.0005, "step": 22050 }, { "epoch": 16.04, "learning_rate": 9.062552689259822e-06, "loss": 0.0001, "step": 22060 }, { "epoch": 16.04, "learning_rate": 9.04147698533131e-06, "loss": 0.2607, "step": 22070 }, { "epoch": 16.04, "learning_rate": 9.020401281402799e-06, "loss": 0.0001, "step": 22080 }, { "epoch": 16.04, "learning_rate": 8.999325577474289e-06, "loss": 0.0396, "step": 22090 }, { "epoch": 16.04, "learning_rate": 8.978249873545777e-06, "loss": 0.0004, "step": 22100 }, { "epoch": 16.04, "learning_rate": 8.957174169617267e-06, "loss": 0.0269, "step": 22110 }, { "epoch": 16.04, "learning_rate": 8.936098465688754e-06, "loss": 0.0343, "step": 22120 }, { "epoch": 16.04, "learning_rate": 8.915022761760243e-06, "loss": 0.0063, "step": 22130 }, { "epoch": 16.04, "learning_rate": 8.893947057831732e-06, "loss": 0.0002, "step": 22140 }, { "epoch": 16.04, "learning_rate": 8.872871353903222e-06, "loss": 0.0001, "step": 22150 }, { "epoch": 16.04, "learning_rate": 8.851795649974708e-06, "loss": 0.0739, "step": 22160 }, { "epoch": 16.04, "learning_rate": 8.830719946046198e-06, "loss": 0.0001, "step": 22170 }, { "epoch": 16.04, "learning_rate": 8.809644242117686e-06, "loss": 0.0001, "step": 22180 }, { "epoch": 16.04, "learning_rate": 8.788568538189176e-06, "loss": 0.0003, "step": 22190 }, { "epoch": 16.04, "learning_rate": 8.767492834260665e-06, "loss": 0.0003, "step": 22200 }, { "epoch": 16.04, "learning_rate": 8.746417130332153e-06, "loss": 0.0188, "step": 22210 }, { "epoch": 16.04, "learning_rate": 8.725341426403643e-06, "loss": 0.0001, "step": 22220 }, { "epoch": 16.04, "learning_rate": 8.704265722475131e-06, "loss": 0.0002, "step": 22230 }, { "epoch": 16.04, "learning_rate": 8.683190018546621e-06, "loss": 0.0008, "step": 22240 }, { "epoch": 16.04, "learning_rate": 8.662114314618108e-06, "loss": 0.0001, "step": 22250 }, { "epoch": 16.04, "learning_rate": 8.641038610689597e-06, "loss": 0.0001, "step": 22260 }, { "epoch": 16.04, "learning_rate": 8.619962906761086e-06, "loss": 0.0043, "step": 22270 }, { "epoch": 16.04, "learning_rate": 8.598887202832576e-06, "loss": 0.0001, "step": 22280 }, { "epoch": 16.04, "learning_rate": 8.577811498904064e-06, "loss": 0.0001, "step": 22290 }, { "epoch": 16.05, "learning_rate": 8.556735794975552e-06, "loss": 0.0001, "step": 22300 }, { "epoch": 16.05, "learning_rate": 8.535660091047042e-06, "loss": 0.0001, "step": 22310 }, { "epoch": 16.05, "learning_rate": 8.51458438711853e-06, "loss": 0.0068, "step": 22320 }, { "epoch": 16.05, "learning_rate": 8.493508683190019e-06, "loss": 0.0001, "step": 22330 }, { "epoch": 16.05, "learning_rate": 8.472432979261507e-06, "loss": 0.0002, "step": 22340 }, { "epoch": 16.05, "learning_rate": 8.451357275332997e-06, "loss": 0.0001, "step": 22350 }, { "epoch": 16.05, "learning_rate": 8.430281571404485e-06, "loss": 0.0001, "step": 22360 }, { "epoch": 16.05, "learning_rate": 8.409205867475973e-06, "loss": 0.0002, "step": 22370 }, { "epoch": 16.05, "learning_rate": 8.388130163547463e-06, "loss": 0.0001, "step": 22380 }, { "epoch": 16.05, "learning_rate": 8.367054459618952e-06, "loss": 0.0001, "step": 22390 }, { "epoch": 16.05, "learning_rate": 8.345978755690441e-06, "loss": 0.0005, "step": 22400 }, { "epoch": 16.05, "learning_rate": 8.324903051761928e-06, "loss": 0.0065, "step": 22410 }, { "epoch": 16.05, "learning_rate": 8.303827347833418e-06, "loss": 0.0417, "step": 22420 }, { "epoch": 16.05, "eval_accuracy": 0.7948651786866211, "eval_loss": 1.3249075412750244, "eval_runtime": 643.094, "eval_samples_per_second": 12.053, "eval_steps_per_second": 2.009, "step": 22423 }, { "epoch": 17.0, "learning_rate": 8.282751643904906e-06, "loss": 0.0001, "step": 22430 }, { "epoch": 17.0, "learning_rate": 8.261675939976396e-06, "loss": 0.0355, "step": 22440 }, { "epoch": 17.0, "learning_rate": 8.240600236047884e-06, "loss": 0.0002, "step": 22450 }, { "epoch": 17.0, "learning_rate": 8.219524532119373e-06, "loss": 0.0076, "step": 22460 }, { "epoch": 17.0, "learning_rate": 8.198448828190863e-06, "loss": 0.0248, "step": 22470 }, { "epoch": 17.0, "learning_rate": 8.17737312426235e-06, "loss": 0.0001, "step": 22480 }, { "epoch": 17.0, "learning_rate": 8.15629742033384e-06, "loss": 0.0002, "step": 22490 }, { "epoch": 17.0, "learning_rate": 8.135221716405327e-06, "loss": 0.0001, "step": 22500 }, { "epoch": 17.0, "learning_rate": 8.114146012476817e-06, "loss": 0.0004, "step": 22510 }, { "epoch": 17.0, "learning_rate": 8.093070308548306e-06, "loss": 0.0119, "step": 22520 }, { "epoch": 17.0, "learning_rate": 8.071994604619795e-06, "loss": 0.0012, "step": 22530 }, { "epoch": 17.0, "learning_rate": 8.050918900691284e-06, "loss": 0.0091, "step": 22540 }, { "epoch": 17.0, "learning_rate": 8.029843196762772e-06, "loss": 0.001, "step": 22550 }, { "epoch": 17.01, "learning_rate": 8.008767492834262e-06, "loss": 0.0, "step": 22560 }, { "epoch": 17.01, "learning_rate": 7.98769178890575e-06, "loss": 0.0036, "step": 22570 }, { "epoch": 17.01, "learning_rate": 7.966616084977238e-06, "loss": 0.0001, "step": 22580 }, { "epoch": 17.01, "learning_rate": 7.945540381048727e-06, "loss": 0.0001, "step": 22590 }, { "epoch": 17.01, "learning_rate": 7.924464677120217e-06, "loss": 0.0001, "step": 22600 }, { "epoch": 17.01, "learning_rate": 7.903388973191705e-06, "loss": 0.0001, "step": 22610 }, { "epoch": 17.01, "learning_rate": 7.882313269263193e-06, "loss": 0.0001, "step": 22620 }, { "epoch": 17.01, "learning_rate": 7.861237565334683e-06, "loss": 0.0, "step": 22630 }, { "epoch": 17.01, "learning_rate": 7.840161861406171e-06, "loss": 0.0003, "step": 22640 }, { "epoch": 17.01, "learning_rate": 7.819086157477661e-06, "loss": 0.0002, "step": 22650 }, { "epoch": 17.01, "learning_rate": 7.798010453549148e-06, "loss": 0.0029, "step": 22660 }, { "epoch": 17.01, "learning_rate": 7.776934749620638e-06, "loss": 0.0002, "step": 22670 }, { "epoch": 17.01, "learning_rate": 7.755859045692126e-06, "loss": 0.0001, "step": 22680 }, { "epoch": 17.01, "learning_rate": 7.734783341763616e-06, "loss": 0.0001, "step": 22690 }, { "epoch": 17.01, "learning_rate": 7.713707637835104e-06, "loss": 0.0008, "step": 22700 }, { "epoch": 17.01, "learning_rate": 7.692631933906592e-06, "loss": 0.0001, "step": 22710 }, { "epoch": 17.01, "learning_rate": 7.671556229978082e-06, "loss": 0.0001, "step": 22720 }, { "epoch": 17.01, "learning_rate": 7.65048052604957e-06, "loss": 0.0001, "step": 22730 }, { "epoch": 17.01, "learning_rate": 7.62940482212106e-06, "loss": 0.0501, "step": 22740 }, { "epoch": 17.01, "learning_rate": 7.608329118192548e-06, "loss": 0.0001, "step": 22750 }, { "epoch": 17.01, "learning_rate": 7.587253414264037e-06, "loss": 0.0001, "step": 22760 }, { "epoch": 17.01, "learning_rate": 7.566177710335526e-06, "loss": 0.091, "step": 22770 }, { "epoch": 17.01, "learning_rate": 7.545102006407015e-06, "loss": 0.0001, "step": 22780 }, { "epoch": 17.01, "learning_rate": 7.524026302478503e-06, "loss": 0.0001, "step": 22790 }, { "epoch": 17.01, "learning_rate": 7.502950598549992e-06, "loss": 0.0001, "step": 22800 }, { "epoch": 17.01, "learning_rate": 7.481874894621481e-06, "loss": 0.1124, "step": 22810 }, { "epoch": 17.02, "learning_rate": 7.46079919069297e-06, "loss": 0.0001, "step": 22820 }, { "epoch": 17.02, "learning_rate": 7.439723486764457e-06, "loss": 0.0392, "step": 22830 }, { "epoch": 17.02, "learning_rate": 7.4186477828359465e-06, "loss": 0.0001, "step": 22840 }, { "epoch": 17.02, "learning_rate": 7.3975720789074356e-06, "loss": 0.002, "step": 22850 }, { "epoch": 17.02, "learning_rate": 7.3764963749789255e-06, "loss": 0.0001, "step": 22860 }, { "epoch": 17.02, "learning_rate": 7.355420671050413e-06, "loss": 0.0111, "step": 22870 }, { "epoch": 17.02, "learning_rate": 7.334344967121902e-06, "loss": 0.0001, "step": 22880 }, { "epoch": 17.02, "learning_rate": 7.313269263193391e-06, "loss": 0.0003, "step": 22890 }, { "epoch": 17.02, "learning_rate": 7.29219355926488e-06, "loss": 0.0008, "step": 22900 }, { "epoch": 17.02, "learning_rate": 7.271117855336368e-06, "loss": 0.0059, "step": 22910 }, { "epoch": 17.02, "learning_rate": 7.250042151407857e-06, "loss": 0.0047, "step": 22920 }, { "epoch": 17.02, "learning_rate": 7.228966447479346e-06, "loss": 0.0001, "step": 22930 }, { "epoch": 17.02, "learning_rate": 7.207890743550835e-06, "loss": 0.0001, "step": 22940 }, { "epoch": 17.02, "learning_rate": 7.186815039622324e-06, "loss": 0.0505, "step": 22950 }, { "epoch": 17.02, "learning_rate": 7.165739335693812e-06, "loss": 0.0004, "step": 22960 }, { "epoch": 17.02, "learning_rate": 7.144663631765301e-06, "loss": 0.0001, "step": 22970 }, { "epoch": 17.02, "learning_rate": 7.12358792783679e-06, "loss": 0.0002, "step": 22980 }, { "epoch": 17.02, "learning_rate": 7.1025122239082795e-06, "loss": 0.0001, "step": 22990 }, { "epoch": 17.02, "learning_rate": 7.081436519979767e-06, "loss": 0.0001, "step": 23000 }, { "epoch": 17.02, "learning_rate": 7.060360816051256e-06, "loss": 0.0001, "step": 23010 }, { "epoch": 17.02, "learning_rate": 7.039285112122745e-06, "loss": 0.0001, "step": 23020 }, { "epoch": 17.02, "learning_rate": 7.018209408194234e-06, "loss": 0.0001, "step": 23030 }, { "epoch": 17.02, "learning_rate": 6.9971337042657225e-06, "loss": 0.0001, "step": 23040 }, { "epoch": 17.02, "learning_rate": 6.9760580003372116e-06, "loss": 0.0001, "step": 23050 }, { "epoch": 17.02, "learning_rate": 6.954982296408701e-06, "loss": 0.0001, "step": 23060 }, { "epoch": 17.02, "learning_rate": 6.93390659248019e-06, "loss": 0.0001, "step": 23070 }, { "epoch": 17.02, "learning_rate": 6.912830888551677e-06, "loss": 0.0001, "step": 23080 }, { "epoch": 17.03, "learning_rate": 6.891755184623166e-06, "loss": 0.0001, "step": 23090 }, { "epoch": 17.03, "learning_rate": 6.870679480694655e-06, "loss": 0.0001, "step": 23100 }, { "epoch": 17.03, "learning_rate": 6.8496037767661444e-06, "loss": 0.0018, "step": 23110 }, { "epoch": 17.03, "learning_rate": 6.828528072837633e-06, "loss": 0.0001, "step": 23120 }, { "epoch": 17.03, "learning_rate": 6.807452368909122e-06, "loss": 0.0001, "step": 23130 }, { "epoch": 17.03, "learning_rate": 6.786376664980611e-06, "loss": 0.0646, "step": 23140 }, { "epoch": 17.03, "learning_rate": 6.7653009610521e-06, "loss": 0.0001, "step": 23150 }, { "epoch": 17.03, "learning_rate": 6.744225257123589e-06, "loss": 0.0002, "step": 23160 }, { "epoch": 17.03, "learning_rate": 6.7231495531950765e-06, "loss": 0.0014, "step": 23170 }, { "epoch": 17.03, "learning_rate": 6.7020738492665656e-06, "loss": 0.1259, "step": 23180 }, { "epoch": 17.03, "learning_rate": 6.680998145338055e-06, "loss": 0.0001, "step": 23190 }, { "epoch": 17.03, "learning_rate": 6.659922441409544e-06, "loss": 0.0001, "step": 23200 }, { "epoch": 17.03, "learning_rate": 6.638846737481032e-06, "loss": 0.0001, "step": 23210 }, { "epoch": 17.03, "learning_rate": 6.617771033552521e-06, "loss": 0.0001, "step": 23220 }, { "epoch": 17.03, "learning_rate": 6.59669532962401e-06, "loss": 0.0001, "step": 23230 }, { "epoch": 17.03, "learning_rate": 6.575619625695499e-06, "loss": 0.0001, "step": 23240 }, { "epoch": 17.03, "learning_rate": 6.554543921766987e-06, "loss": 0.0001, "step": 23250 }, { "epoch": 17.03, "learning_rate": 6.533468217838476e-06, "loss": 0.0004, "step": 23260 }, { "epoch": 17.03, "learning_rate": 6.512392513909965e-06, "loss": 0.0001, "step": 23270 }, { "epoch": 17.03, "learning_rate": 6.491316809981454e-06, "loss": 0.0001, "step": 23280 }, { "epoch": 17.03, "learning_rate": 6.470241106052942e-06, "loss": 0.0001, "step": 23290 }, { "epoch": 17.03, "learning_rate": 6.449165402124431e-06, "loss": 0.0001, "step": 23300 }, { "epoch": 17.03, "learning_rate": 6.4280896981959204e-06, "loss": 0.1657, "step": 23310 }, { "epoch": 17.03, "learning_rate": 6.4070139942674095e-06, "loss": 0.0008, "step": 23320 }, { "epoch": 17.03, "learning_rate": 6.385938290338897e-06, "loss": 0.0001, "step": 23330 }, { "epoch": 17.03, "learning_rate": 6.364862586410386e-06, "loss": 0.1936, "step": 23340 }, { "epoch": 17.04, "learning_rate": 6.343786882481875e-06, "loss": 0.0001, "step": 23350 }, { "epoch": 17.04, "learning_rate": 6.322711178553364e-06, "loss": 0.0001, "step": 23360 }, { "epoch": 17.04, "learning_rate": 6.3016354746248525e-06, "loss": 0.0007, "step": 23370 }, { "epoch": 17.04, "learning_rate": 6.2805597706963416e-06, "loss": 0.0002, "step": 23380 }, { "epoch": 17.04, "learning_rate": 6.259484066767831e-06, "loss": 0.0015, "step": 23390 }, { "epoch": 17.04, "learning_rate": 6.23840836283932e-06, "loss": 0.0001, "step": 23400 }, { "epoch": 17.04, "learning_rate": 6.217332658910808e-06, "loss": 0.0001, "step": 23410 }, { "epoch": 17.04, "learning_rate": 6.196256954982297e-06, "loss": 0.1618, "step": 23420 }, { "epoch": 17.04, "learning_rate": 6.175181251053785e-06, "loss": 0.0001, "step": 23430 }, { "epoch": 17.04, "learning_rate": 6.1541055471252745e-06, "loss": 0.0, "step": 23440 }, { "epoch": 17.04, "learning_rate": 6.133029843196763e-06, "loss": 0.0001, "step": 23450 }, { "epoch": 17.04, "learning_rate": 6.111954139268252e-06, "loss": 0.02, "step": 23460 }, { "epoch": 17.04, "learning_rate": 6.090878435339741e-06, "loss": 0.0001, "step": 23470 }, { "epoch": 17.04, "learning_rate": 6.06980273141123e-06, "loss": 0.0027, "step": 23480 }, { "epoch": 17.04, "learning_rate": 6.048727027482718e-06, "loss": 0.0017, "step": 23490 }, { "epoch": 17.04, "learning_rate": 6.027651323554207e-06, "loss": 0.0001, "step": 23500 }, { "epoch": 17.04, "learning_rate": 6.006575619625696e-06, "loss": 0.0002, "step": 23510 }, { "epoch": 17.04, "learning_rate": 5.985499915697185e-06, "loss": 0.0024, "step": 23520 }, { "epoch": 17.04, "learning_rate": 5.964424211768673e-06, "loss": 0.0001, "step": 23530 }, { "epoch": 17.04, "learning_rate": 5.943348507840162e-06, "loss": 0.0015, "step": 23540 }, { "epoch": 17.04, "learning_rate": 5.92227280391165e-06, "loss": 0.0109, "step": 23550 }, { "epoch": 17.04, "learning_rate": 5.901197099983139e-06, "loss": 0.0014, "step": 23560 }, { "epoch": 17.04, "learning_rate": 5.8801213960546285e-06, "loss": 0.0001, "step": 23570 }, { "epoch": 17.04, "learning_rate": 5.8590456921261176e-06, "loss": 0.0001, "step": 23580 }, { "epoch": 17.04, "learning_rate": 5.837969988197606e-06, "loss": 0.1583, "step": 23590 }, { "epoch": 17.04, "learning_rate": 5.816894284269095e-06, "loss": 0.0014, "step": 23600 }, { "epoch": 17.05, "learning_rate": 5.795818580340583e-06, "loss": 0.0806, "step": 23610 }, { "epoch": 17.05, "learning_rate": 5.774742876412072e-06, "loss": 0.0004, "step": 23620 }, { "epoch": 17.05, "learning_rate": 5.753667172483561e-06, "loss": 0.0001, "step": 23630 }, { "epoch": 17.05, "learning_rate": 5.73259146855505e-06, "loss": 0.0001, "step": 23640 }, { "epoch": 17.05, "learning_rate": 5.711515764626539e-06, "loss": 0.0008, "step": 23650 }, { "epoch": 17.05, "learning_rate": 5.690440060698028e-06, "loss": 0.0004, "step": 23660 }, { "epoch": 17.05, "learning_rate": 5.669364356769517e-06, "loss": 0.002, "step": 23670 }, { "epoch": 17.05, "learning_rate": 5.648288652841005e-06, "loss": 0.0027, "step": 23680 }, { "epoch": 17.05, "learning_rate": 5.627212948912494e-06, "loss": 0.0001, "step": 23690 }, { "epoch": 17.05, "learning_rate": 5.6061372449839825e-06, "loss": 0.1715, "step": 23700 }, { "epoch": 17.05, "learning_rate": 5.585061541055472e-06, "loss": 0.0001, "step": 23710 }, { "epoch": 17.05, "learning_rate": 5.56398583712696e-06, "loss": 0.0001, "step": 23720 }, { "epoch": 17.05, "learning_rate": 5.542910133198449e-06, "loss": 0.0001, "step": 23730 }, { "epoch": 17.05, "learning_rate": 5.521834429269938e-06, "loss": 0.0001, "step": 23740 }, { "epoch": 17.05, "eval_accuracy": 0.8035092246161786, "eval_loss": 1.2308986186981201, "eval_runtime": 607.0052, "eval_samples_per_second": 12.769, "eval_steps_per_second": 2.128, "step": 23742 }, { "epoch": 18.0, "learning_rate": 5.500758725341427e-06, "loss": 0.0001, "step": 23750 }, { "epoch": 18.0, "learning_rate": 5.479683021412915e-06, "loss": 0.0002, "step": 23760 }, { "epoch": 18.0, "learning_rate": 5.4586073174844045e-06, "loss": 0.0005, "step": 23770 }, { "epoch": 18.0, "learning_rate": 5.437531613555893e-06, "loss": 0.0002, "step": 23780 }, { "epoch": 18.0, "learning_rate": 5.416455909627382e-06, "loss": 0.0002, "step": 23790 }, { "epoch": 18.0, "learning_rate": 5.39538020569887e-06, "loss": 0.0001, "step": 23800 }, { "epoch": 18.0, "learning_rate": 5.374304501770359e-06, "loss": 0.0001, "step": 23810 }, { "epoch": 18.0, "learning_rate": 5.353228797841848e-06, "loss": 0.0073, "step": 23820 }, { "epoch": 18.0, "learning_rate": 5.332153093913337e-06, "loss": 0.0001, "step": 23830 }, { "epoch": 18.0, "learning_rate": 5.311077389984826e-06, "loss": 0.0001, "step": 23840 }, { "epoch": 18.0, "learning_rate": 5.290001686056315e-06, "loss": 0.0001, "step": 23850 }, { "epoch": 18.0, "learning_rate": 5.268925982127804e-06, "loss": 0.0017, "step": 23860 }, { "epoch": 18.0, "learning_rate": 5.247850278199292e-06, "loss": 0.0001, "step": 23870 }, { "epoch": 18.01, "learning_rate": 5.226774574270781e-06, "loss": 0.0001, "step": 23880 }, { "epoch": 18.01, "learning_rate": 5.205698870342269e-06, "loss": 0.0002, "step": 23890 }, { "epoch": 18.01, "learning_rate": 5.1846231664137585e-06, "loss": 0.0001, "step": 23900 }, { "epoch": 18.01, "learning_rate": 5.163547462485247e-06, "loss": 0.0001, "step": 23910 }, { "epoch": 18.01, "learning_rate": 5.142471758556737e-06, "loss": 0.0006, "step": 23920 }, { "epoch": 18.01, "learning_rate": 5.121396054628225e-06, "loss": 0.0001, "step": 23930 }, { "epoch": 18.01, "learning_rate": 5.100320350699714e-06, "loss": 0.0001, "step": 23940 }, { "epoch": 18.01, "learning_rate": 5.079244646771202e-06, "loss": 0.1058, "step": 23950 }, { "epoch": 18.01, "learning_rate": 5.058168942842691e-06, "loss": 0.0001, "step": 23960 }, { "epoch": 18.01, "learning_rate": 5.03709323891418e-06, "loss": 0.0001, "step": 23970 }, { "epoch": 18.01, "learning_rate": 5.016017534985669e-06, "loss": 0.0001, "step": 23980 }, { "epoch": 18.01, "learning_rate": 4.994941831057157e-06, "loss": 0.0002, "step": 23990 }, { "epoch": 18.01, "learning_rate": 4.973866127128646e-06, "loss": 0.0001, "step": 24000 }, { "epoch": 18.01, "learning_rate": 4.952790423200135e-06, "loss": 0.0001, "step": 24010 }, { "epoch": 18.01, "learning_rate": 4.931714719271624e-06, "loss": 0.0, "step": 24020 }, { "epoch": 18.01, "learning_rate": 4.9106390153431125e-06, "loss": 0.0001, "step": 24030 }, { "epoch": 18.01, "learning_rate": 4.889563311414602e-06, "loss": 0.0001, "step": 24040 }, { "epoch": 18.01, "learning_rate": 4.86848760748609e-06, "loss": 0.0001, "step": 24050 }, { "epoch": 18.01, "learning_rate": 4.847411903557579e-06, "loss": 0.0021, "step": 24060 }, { "epoch": 18.01, "learning_rate": 4.826336199629067e-06, "loss": 0.0001, "step": 24070 }, { "epoch": 18.01, "learning_rate": 4.805260495700556e-06, "loss": 0.0001, "step": 24080 }, { "epoch": 18.01, "learning_rate": 4.784184791772045e-06, "loss": 0.0002, "step": 24090 }, { "epoch": 18.01, "learning_rate": 4.7631090878435345e-06, "loss": 0.1492, "step": 24100 }, { "epoch": 18.01, "learning_rate": 4.742033383915024e-06, "loss": 0.0001, "step": 24110 }, { "epoch": 18.01, "learning_rate": 4.720957679986512e-06, "loss": 0.0001, "step": 24120 }, { "epoch": 18.01, "learning_rate": 4.699881976058001e-06, "loss": 0.0001, "step": 24130 }, { "epoch": 18.02, "learning_rate": 4.678806272129489e-06, "loss": 0.1316, "step": 24140 }, { "epoch": 18.02, "learning_rate": 4.657730568200978e-06, "loss": 0.0, "step": 24150 }, { "epoch": 18.02, "learning_rate": 4.6366548642724665e-06, "loss": 0.0001, "step": 24160 }, { "epoch": 18.02, "learning_rate": 4.615579160343956e-06, "loss": 0.0012, "step": 24170 }, { "epoch": 18.02, "learning_rate": 4.594503456415445e-06, "loss": 0.0001, "step": 24180 }, { "epoch": 18.02, "learning_rate": 4.573427752486934e-06, "loss": 0.0001, "step": 24190 }, { "epoch": 18.02, "learning_rate": 4.552352048558422e-06, "loss": 0.0002, "step": 24200 }, { "epoch": 18.02, "learning_rate": 4.531276344629911e-06, "loss": 0.0001, "step": 24210 }, { "epoch": 18.02, "learning_rate": 4.510200640701399e-06, "loss": 0.0004, "step": 24220 }, { "epoch": 18.02, "learning_rate": 4.4891249367728885e-06, "loss": 0.0001, "step": 24230 }, { "epoch": 18.02, "learning_rate": 4.468049232844377e-06, "loss": 0.0001, "step": 24240 }, { "epoch": 18.02, "learning_rate": 4.446973528915866e-06, "loss": 0.0001, "step": 24250 }, { "epoch": 18.02, "learning_rate": 4.425897824987354e-06, "loss": 0.0001, "step": 24260 }, { "epoch": 18.02, "learning_rate": 4.404822121058843e-06, "loss": 0.0002, "step": 24270 }, { "epoch": 18.02, "learning_rate": 4.383746417130332e-06, "loss": 0.0001, "step": 24280 }, { "epoch": 18.02, "learning_rate": 4.362670713201821e-06, "loss": 0.0131, "step": 24290 }, { "epoch": 18.02, "learning_rate": 4.3415950092733105e-06, "loss": 0.0118, "step": 24300 }, { "epoch": 18.02, "learning_rate": 4.320519305344799e-06, "loss": 0.0002, "step": 24310 }, { "epoch": 18.02, "learning_rate": 4.299443601416288e-06, "loss": 0.0187, "step": 24320 }, { "epoch": 18.02, "learning_rate": 4.278367897487776e-06, "loss": 0.0001, "step": 24330 }, { "epoch": 18.02, "learning_rate": 4.257292193559265e-06, "loss": 0.0002, "step": 24340 }, { "epoch": 18.02, "learning_rate": 4.2362164896307534e-06, "loss": 0.0001, "step": 24350 }, { "epoch": 18.02, "learning_rate": 4.2151407857022425e-06, "loss": 0.0002, "step": 24360 }, { "epoch": 18.02, "learning_rate": 4.194065081773732e-06, "loss": 0.0, "step": 24370 }, { "epoch": 18.02, "learning_rate": 4.172989377845221e-06, "loss": 0.0, "step": 24380 }, { "epoch": 18.02, "learning_rate": 4.151913673916709e-06, "loss": 0.0001, "step": 24390 }, { "epoch": 18.02, "learning_rate": 4.130837969988198e-06, "loss": 0.1495, "step": 24400 }, { "epoch": 18.03, "learning_rate": 4.109762266059686e-06, "loss": 0.0001, "step": 24410 }, { "epoch": 18.03, "learning_rate": 4.088686562131175e-06, "loss": 0.0, "step": 24420 }, { "epoch": 18.03, "learning_rate": 4.067610858202664e-06, "loss": 0.0001, "step": 24430 }, { "epoch": 18.03, "learning_rate": 4.046535154274153e-06, "loss": 0.0, "step": 24440 }, { "epoch": 18.03, "learning_rate": 4.025459450345642e-06, "loss": 0.0001, "step": 24450 }, { "epoch": 18.03, "learning_rate": 4.004383746417131e-06, "loss": 0.0, "step": 24460 }, { "epoch": 18.03, "learning_rate": 3.983308042488619e-06, "loss": 0.0, "step": 24470 }, { "epoch": 18.03, "learning_rate": 3.962232338560108e-06, "loss": 0.0001, "step": 24480 }, { "epoch": 18.03, "learning_rate": 3.9411566346315966e-06, "loss": 0.0001, "step": 24490 }, { "epoch": 18.03, "learning_rate": 3.920080930703086e-06, "loss": 0.0, "step": 24500 }, { "epoch": 18.03, "learning_rate": 3.899005226774574e-06, "loss": 0.0001, "step": 24510 }, { "epoch": 18.03, "learning_rate": 3.877929522846063e-06, "loss": 0.0, "step": 24520 }, { "epoch": 18.03, "learning_rate": 3.856853818917552e-06, "loss": 0.0, "step": 24530 }, { "epoch": 18.03, "learning_rate": 3.835778114989041e-06, "loss": 0.0259, "step": 24540 }, { "epoch": 18.03, "learning_rate": 3.81470241106053e-06, "loss": 0.0, "step": 24550 }, { "epoch": 18.03, "learning_rate": 3.7936267071320185e-06, "loss": 0.0001, "step": 24560 }, { "epoch": 18.03, "learning_rate": 3.7725510032035076e-06, "loss": 0.0, "step": 24570 }, { "epoch": 18.03, "learning_rate": 3.751475299274996e-06, "loss": 0.0001, "step": 24580 }, { "epoch": 18.03, "learning_rate": 3.730399595346485e-06, "loss": 0.0633, "step": 24590 }, { "epoch": 18.03, "learning_rate": 3.7093238914179732e-06, "loss": 0.0161, "step": 24600 }, { "epoch": 18.03, "learning_rate": 3.6882481874894627e-06, "loss": 0.0, "step": 24610 }, { "epoch": 18.03, "learning_rate": 3.667172483560951e-06, "loss": 0.0, "step": 24620 }, { "epoch": 18.03, "learning_rate": 3.64609677963244e-06, "loss": 0.0004, "step": 24630 }, { "epoch": 18.03, "learning_rate": 3.6250210757039283e-06, "loss": 0.0001, "step": 24640 }, { "epoch": 18.03, "learning_rate": 3.6039453717754174e-06, "loss": 0.0001, "step": 24650 }, { "epoch": 18.03, "learning_rate": 3.582869667846906e-06, "loss": 0.0, "step": 24660 }, { "epoch": 18.04, "learning_rate": 3.561793963918395e-06, "loss": 0.0001, "step": 24670 }, { "epoch": 18.04, "learning_rate": 3.5407182599898835e-06, "loss": 0.0004, "step": 24680 }, { "epoch": 18.04, "learning_rate": 3.5196425560613726e-06, "loss": 0.0001, "step": 24690 }, { "epoch": 18.04, "learning_rate": 3.4985668521328612e-06, "loss": 0.0, "step": 24700 }, { "epoch": 18.04, "learning_rate": 3.4774911482043503e-06, "loss": 0.0, "step": 24710 }, { "epoch": 18.04, "learning_rate": 3.4564154442758386e-06, "loss": 0.0001, "step": 24720 }, { "epoch": 18.04, "learning_rate": 3.4353397403473277e-06, "loss": 0.0, "step": 24730 }, { "epoch": 18.04, "learning_rate": 3.4142640364188163e-06, "loss": 0.0001, "step": 24740 }, { "epoch": 18.04, "learning_rate": 3.3931883324903054e-06, "loss": 0.0004, "step": 24750 }, { "epoch": 18.04, "learning_rate": 3.3721126285617945e-06, "loss": 0.0001, "step": 24760 }, { "epoch": 18.04, "learning_rate": 3.3510369246332828e-06, "loss": 0.0008, "step": 24770 }, { "epoch": 18.04, "learning_rate": 3.329961220704772e-06, "loss": 0.0001, "step": 24780 }, { "epoch": 18.04, "learning_rate": 3.3088855167762606e-06, "loss": 0.0001, "step": 24790 }, { "epoch": 18.04, "learning_rate": 3.2878098128477497e-06, "loss": 0.0002, "step": 24800 }, { "epoch": 18.04, "learning_rate": 3.266734108919238e-06, "loss": 0.0024, "step": 24810 }, { "epoch": 18.04, "learning_rate": 3.245658404990727e-06, "loss": 0.0, "step": 24820 }, { "epoch": 18.04, "learning_rate": 3.2245827010622157e-06, "loss": 0.0001, "step": 24830 }, { "epoch": 18.04, "learning_rate": 3.2035069971337048e-06, "loss": 0.0001, "step": 24840 }, { "epoch": 18.04, "learning_rate": 3.182431293205193e-06, "loss": 0.0001, "step": 24850 }, { "epoch": 18.04, "learning_rate": 3.161355589276682e-06, "loss": 0.0001, "step": 24860 }, { "epoch": 18.04, "learning_rate": 3.1402798853481708e-06, "loss": 0.041, "step": 24870 }, { "epoch": 18.04, "learning_rate": 3.11920418141966e-06, "loss": 0.0432, "step": 24880 }, { "epoch": 18.04, "learning_rate": 3.0981284774911486e-06, "loss": 0.0, "step": 24890 }, { "epoch": 18.04, "learning_rate": 3.0770527735626372e-06, "loss": 0.0933, "step": 24900 }, { "epoch": 18.04, "learning_rate": 3.055977069634126e-06, "loss": 0.0003, "step": 24910 }, { "epoch": 18.04, "learning_rate": 3.034901365705615e-06, "loss": 0.0, "step": 24920 }, { "epoch": 18.05, "learning_rate": 3.0138256617771037e-06, "loss": 0.0001, "step": 24930 }, { "epoch": 18.05, "learning_rate": 2.9927499578485923e-06, "loss": 0.0001, "step": 24940 }, { "epoch": 18.05, "learning_rate": 2.971674253920081e-06, "loss": 0.0001, "step": 24950 }, { "epoch": 18.05, "learning_rate": 2.9505985499915697e-06, "loss": 0.0005, "step": 24960 }, { "epoch": 18.05, "learning_rate": 2.9295228460630588e-06, "loss": 0.0527, "step": 24970 }, { "epoch": 18.05, "learning_rate": 2.9084471421345475e-06, "loss": 0.0003, "step": 24980 }, { "epoch": 18.05, "learning_rate": 2.887371438206036e-06, "loss": 0.0001, "step": 24990 }, { "epoch": 18.05, "learning_rate": 2.866295734277525e-06, "loss": 0.0, "step": 25000 }, { "epoch": 18.05, "learning_rate": 2.845220030349014e-06, "loss": 0.0001, "step": 25010 }, { "epoch": 18.05, "learning_rate": 2.8241443264205026e-06, "loss": 0.0001, "step": 25020 }, { "epoch": 18.05, "learning_rate": 2.8030686224919912e-06, "loss": 0.0001, "step": 25030 }, { "epoch": 18.05, "learning_rate": 2.78199291856348e-06, "loss": 0.0077, "step": 25040 }, { "epoch": 18.05, "learning_rate": 2.760917214634969e-06, "loss": 0.0071, "step": 25050 }, { "epoch": 18.05, "learning_rate": 2.7398415107064577e-06, "loss": 0.0001, "step": 25060 }, { "epoch": 18.05, "eval_accuracy": 0.7904786479163979, "eval_loss": 1.3197455406188965, "eval_runtime": 600.3976, "eval_samples_per_second": 12.91, "eval_steps_per_second": 2.152, "step": 25061 }, { "epoch": 19.0, "learning_rate": 2.7187658067779464e-06, "loss": 0.0001, "step": 25070 }, { "epoch": 19.0, "learning_rate": 2.697690102849435e-06, "loss": 0.0002, "step": 25080 }, { "epoch": 19.0, "learning_rate": 2.676614398920924e-06, "loss": 0.0001, "step": 25090 }, { "epoch": 19.0, "learning_rate": 2.655538694992413e-06, "loss": 0.0001, "step": 25100 }, { "epoch": 19.0, "learning_rate": 2.634462991063902e-06, "loss": 0.0001, "step": 25110 }, { "epoch": 19.0, "learning_rate": 2.6133872871353906e-06, "loss": 0.1125, "step": 25120 }, { "epoch": 19.0, "learning_rate": 2.5923115832068792e-06, "loss": 0.0001, "step": 25130 }, { "epoch": 19.0, "learning_rate": 2.5712358792783683e-06, "loss": 0.0001, "step": 25140 }, { "epoch": 19.0, "learning_rate": 2.550160175349857e-06, "loss": 0.0, "step": 25150 }, { "epoch": 19.0, "learning_rate": 2.5290844714213457e-06, "loss": 0.0001, "step": 25160 }, { "epoch": 19.0, "learning_rate": 2.5080087674928344e-06, "loss": 0.0001, "step": 25170 }, { "epoch": 19.0, "learning_rate": 2.486933063564323e-06, "loss": 0.0001, "step": 25180 }, { "epoch": 19.0, "learning_rate": 2.465857359635812e-06, "loss": 0.0, "step": 25190 }, { "epoch": 19.01, "learning_rate": 2.444781655707301e-06, "loss": 0.0, "step": 25200 }, { "epoch": 19.01, "learning_rate": 2.4237059517787895e-06, "loss": 0.1093, "step": 25210 }, { "epoch": 19.01, "learning_rate": 2.402630247850278e-06, "loss": 0.0002, "step": 25220 }, { "epoch": 19.01, "learning_rate": 2.3815545439217672e-06, "loss": 0.0, "step": 25230 }, { "epoch": 19.01, "learning_rate": 2.360478839993256e-06, "loss": 0.0001, "step": 25240 }, { "epoch": 19.01, "learning_rate": 2.3394031360647446e-06, "loss": 0.0001, "step": 25250 }, { "epoch": 19.01, "learning_rate": 2.3183274321362333e-06, "loss": 0.0, "step": 25260 }, { "epoch": 19.01, "learning_rate": 2.2972517282077224e-06, "loss": 0.0, "step": 25270 }, { "epoch": 19.01, "learning_rate": 2.276176024279211e-06, "loss": 0.0, "step": 25280 }, { "epoch": 19.01, "learning_rate": 2.2551003203506997e-06, "loss": 0.0, "step": 25290 }, { "epoch": 19.01, "learning_rate": 2.2340246164221884e-06, "loss": 0.0, "step": 25300 }, { "epoch": 19.01, "learning_rate": 2.212948912493677e-06, "loss": 0.0001, "step": 25310 }, { "epoch": 19.01, "learning_rate": 2.191873208565166e-06, "loss": 0.0, "step": 25320 }, { "epoch": 19.01, "learning_rate": 2.1707975046366552e-06, "loss": 0.0001, "step": 25330 }, { "epoch": 19.01, "learning_rate": 2.149721800708144e-06, "loss": 0.0, "step": 25340 }, { "epoch": 19.01, "learning_rate": 2.1286460967796326e-06, "loss": 0.0, "step": 25350 }, { "epoch": 19.01, "learning_rate": 2.1075703928511213e-06, "loss": 0.0001, "step": 25360 }, { "epoch": 19.01, "learning_rate": 2.0864946889226104e-06, "loss": 0.0, "step": 25370 }, { "epoch": 19.01, "learning_rate": 2.065418984994099e-06, "loss": 0.0001, "step": 25380 }, { "epoch": 19.01, "learning_rate": 2.0443432810655877e-06, "loss": 0.0001, "step": 25390 }, { "epoch": 19.01, "learning_rate": 2.0232675771370764e-06, "loss": 0.0075, "step": 25400 }, { "epoch": 19.01, "learning_rate": 2.0021918732085655e-06, "loss": 0.0, "step": 25410 }, { "epoch": 19.01, "learning_rate": 1.981116169280054e-06, "loss": 0.0001, "step": 25420 }, { "epoch": 19.01, "learning_rate": 1.960040465351543e-06, "loss": 0.0001, "step": 25430 }, { "epoch": 19.01, "learning_rate": 1.9389647614230315e-06, "loss": 0.0001, "step": 25440 }, { "epoch": 19.01, "learning_rate": 1.9178890574945206e-06, "loss": 0.0365, "step": 25450 }, { "epoch": 19.02, "learning_rate": 1.8968133535660093e-06, "loss": 0.0001, "step": 25460 }, { "epoch": 19.02, "learning_rate": 1.875737649637498e-06, "loss": 0.0003, "step": 25470 }, { "epoch": 19.02, "learning_rate": 1.8546619457089866e-06, "loss": 0.0001, "step": 25480 }, { "epoch": 19.02, "learning_rate": 1.8335862417804755e-06, "loss": 0.0001, "step": 25490 }, { "epoch": 19.02, "learning_rate": 1.8125105378519642e-06, "loss": 0.0001, "step": 25500 }, { "epoch": 19.02, "learning_rate": 1.791434833923453e-06, "loss": 0.0, "step": 25510 }, { "epoch": 19.02, "learning_rate": 1.7703591299949417e-06, "loss": 0.0, "step": 25520 }, { "epoch": 19.02, "learning_rate": 1.7492834260664306e-06, "loss": 0.0, "step": 25530 }, { "epoch": 19.02, "learning_rate": 1.7282077221379193e-06, "loss": 0.0, "step": 25540 }, { "epoch": 19.02, "learning_rate": 1.7071320182094082e-06, "loss": 0.0001, "step": 25550 }, { "epoch": 19.02, "learning_rate": 1.6860563142808973e-06, "loss": 0.0001, "step": 25560 }, { "epoch": 19.02, "learning_rate": 1.664980610352386e-06, "loss": 0.0001, "step": 25570 }, { "epoch": 19.02, "learning_rate": 1.6439049064238748e-06, "loss": 0.0, "step": 25580 }, { "epoch": 19.02, "learning_rate": 1.6228292024953635e-06, "loss": 0.0001, "step": 25590 }, { "epoch": 19.02, "learning_rate": 1.6017534985668524e-06, "loss": 0.0021, "step": 25600 }, { "epoch": 19.02, "learning_rate": 1.580677794638341e-06, "loss": 0.0, "step": 25610 }, { "epoch": 19.02, "learning_rate": 1.55960209070983e-06, "loss": 0.0001, "step": 25620 }, { "epoch": 19.02, "learning_rate": 1.5385263867813186e-06, "loss": 0.0001, "step": 25630 }, { "epoch": 19.02, "learning_rate": 1.5174506828528075e-06, "loss": 0.0, "step": 25640 }, { "epoch": 19.02, "learning_rate": 1.4963749789242962e-06, "loss": 0.0, "step": 25650 }, { "epoch": 19.02, "learning_rate": 1.4752992749957848e-06, "loss": 0.0019, "step": 25660 }, { "epoch": 19.02, "learning_rate": 1.4542235710672737e-06, "loss": 0.0, "step": 25670 }, { "epoch": 19.02, "learning_rate": 1.4331478671387624e-06, "loss": 0.0001, "step": 25680 }, { "epoch": 19.02, "learning_rate": 1.4120721632102513e-06, "loss": 0.0, "step": 25690 }, { "epoch": 19.02, "learning_rate": 1.39099645928174e-06, "loss": 0.0, "step": 25700 }, { "epoch": 19.02, "learning_rate": 1.3699207553532288e-06, "loss": 0.0, "step": 25710 }, { "epoch": 19.02, "learning_rate": 1.3488450514247175e-06, "loss": 0.0001, "step": 25720 }, { "epoch": 19.03, "learning_rate": 1.3277693474962064e-06, "loss": 0.0, "step": 25730 }, { "epoch": 19.03, "learning_rate": 1.3066936435676953e-06, "loss": 0.0, "step": 25740 }, { "epoch": 19.03, "learning_rate": 1.2856179396391842e-06, "loss": 0.0, "step": 25750 }, { "epoch": 19.03, "learning_rate": 1.2645422357106728e-06, "loss": 0.0, "step": 25760 }, { "epoch": 19.03, "learning_rate": 1.2434665317821615e-06, "loss": 0.0034, "step": 25770 }, { "epoch": 19.03, "learning_rate": 1.2223908278536504e-06, "loss": 0.0002, "step": 25780 }, { "epoch": 19.03, "learning_rate": 1.201315123925139e-06, "loss": 0.0, "step": 25790 }, { "epoch": 19.03, "learning_rate": 1.180239419996628e-06, "loss": 0.0, "step": 25800 }, { "epoch": 19.03, "learning_rate": 1.1591637160681166e-06, "loss": 0.0013, "step": 25810 }, { "epoch": 19.03, "learning_rate": 1.1380880121396055e-06, "loss": 0.0003, "step": 25820 }, { "epoch": 19.03, "learning_rate": 1.1170123082110942e-06, "loss": 0.0, "step": 25830 }, { "epoch": 19.03, "learning_rate": 1.095936604282583e-06, "loss": 0.0002, "step": 25840 }, { "epoch": 19.03, "learning_rate": 1.074860900354072e-06, "loss": 0.0, "step": 25850 }, { "epoch": 19.03, "learning_rate": 1.0537851964255606e-06, "loss": 0.0, "step": 25860 }, { "epoch": 19.03, "learning_rate": 1.0327094924970495e-06, "loss": 0.0001, "step": 25870 }, { "epoch": 19.03, "learning_rate": 1.0116337885685382e-06, "loss": 0.0, "step": 25880 }, { "epoch": 19.03, "learning_rate": 9.90558084640027e-07, "loss": 0.0, "step": 25890 }, { "epoch": 19.03, "learning_rate": 9.694823807115157e-07, "loss": 0.0001, "step": 25900 }, { "epoch": 19.03, "learning_rate": 9.484066767830046e-07, "loss": 0.0058, "step": 25910 }, { "epoch": 19.03, "learning_rate": 9.273309728544933e-07, "loss": 0.0002, "step": 25920 }, { "epoch": 19.03, "learning_rate": 9.062552689259821e-07, "loss": 0.0001, "step": 25930 }, { "epoch": 19.03, "learning_rate": 8.851795649974709e-07, "loss": 0.0, "step": 25940 }, { "epoch": 19.03, "learning_rate": 8.641038610689596e-07, "loss": 0.0012, "step": 25950 }, { "epoch": 19.03, "learning_rate": 8.430281571404486e-07, "loss": 0.0, "step": 25960 }, { "epoch": 19.03, "learning_rate": 8.219524532119374e-07, "loss": 0.0001, "step": 25970 }, { "epoch": 19.03, "learning_rate": 8.008767492834262e-07, "loss": 0.0016, "step": 25980 }, { "epoch": 19.04, "learning_rate": 7.79801045354915e-07, "loss": 0.0001, "step": 25990 }, { "epoch": 19.04, "learning_rate": 7.587253414264037e-07, "loss": 0.0001, "step": 26000 }, { "epoch": 19.04, "learning_rate": 7.376496374978924e-07, "loss": 0.0001, "step": 26010 }, { "epoch": 19.04, "learning_rate": 7.165739335693812e-07, "loss": 0.0, "step": 26020 }, { "epoch": 19.04, "learning_rate": 6.9549822964087e-07, "loss": 0.0, "step": 26030 }, { "epoch": 19.04, "learning_rate": 6.744225257123588e-07, "loss": 0.0001, "step": 26040 }, { "epoch": 19.04, "learning_rate": 6.533468217838476e-07, "loss": 0.0001, "step": 26050 }, { "epoch": 19.04, "learning_rate": 6.322711178553364e-07, "loss": 0.0001, "step": 26060 }, { "epoch": 19.04, "learning_rate": 6.111954139268252e-07, "loss": 0.0007, "step": 26070 }, { "epoch": 19.04, "learning_rate": 5.90119709998314e-07, "loss": 0.0001, "step": 26080 }, { "epoch": 19.04, "learning_rate": 5.690440060698028e-07, "loss": 0.0001, "step": 26090 }, { "epoch": 19.04, "learning_rate": 5.479683021412915e-07, "loss": 0.0001, "step": 26100 }, { "epoch": 19.04, "learning_rate": 5.268925982127803e-07, "loss": 0.0, "step": 26110 }, { "epoch": 19.04, "learning_rate": 5.058168942842691e-07, "loss": 0.0, "step": 26120 }, { "epoch": 19.04, "learning_rate": 4.847411903557579e-07, "loss": 0.0787, "step": 26130 }, { "epoch": 19.04, "learning_rate": 4.6366548642724665e-07, "loss": 0.0, "step": 26140 }, { "epoch": 19.04, "learning_rate": 4.4258978249873543e-07, "loss": 0.0002, "step": 26150 }, { "epoch": 19.04, "learning_rate": 4.215140785702243e-07, "loss": 0.0, "step": 26160 }, { "epoch": 19.04, "learning_rate": 4.004383746417131e-07, "loss": 0.0, "step": 26170 }, { "epoch": 19.04, "learning_rate": 3.793626707132019e-07, "loss": 0.0, "step": 26180 }, { "epoch": 19.04, "learning_rate": 3.582869667846906e-07, "loss": 0.0001, "step": 26190 }, { "epoch": 19.04, "learning_rate": 3.372112628561794e-07, "loss": 0.0001, "step": 26200 }, { "epoch": 19.04, "learning_rate": 3.161355589276682e-07, "loss": 0.0001, "step": 26210 }, { "epoch": 19.04, "learning_rate": 2.95059854999157e-07, "loss": 0.0001, "step": 26220 }, { "epoch": 19.04, "learning_rate": 2.7398415107064577e-07, "loss": 0.0001, "step": 26230 }, { "epoch": 19.04, "learning_rate": 2.5290844714213455e-07, "loss": 0.0001, "step": 26240 }, { "epoch": 19.05, "learning_rate": 2.3183274321362333e-07, "loss": 0.0, "step": 26250 }, { "epoch": 19.05, "learning_rate": 2.1075703928511216e-07, "loss": 0.0001, "step": 26260 }, { "epoch": 19.05, "learning_rate": 1.8968133535660094e-07, "loss": 0.0009, "step": 26270 }, { "epoch": 19.05, "learning_rate": 1.686056314280897e-07, "loss": 0.0001, "step": 26280 }, { "epoch": 19.05, "learning_rate": 1.475299274995785e-07, "loss": 0.0002, "step": 26290 }, { "epoch": 19.05, "learning_rate": 1.2645422357106727e-07, "loss": 0.0, "step": 26300 }, { "epoch": 19.05, "learning_rate": 1.0537851964255608e-07, "loss": 0.0001, "step": 26310 }, { "epoch": 19.05, "learning_rate": 8.430281571404484e-08, "loss": 0.0001, "step": 26320 }, { "epoch": 19.05, "learning_rate": 6.322711178553364e-08, "loss": 0.0001, "step": 26330 }, { "epoch": 19.05, "learning_rate": 4.215140785702242e-08, "loss": 0.0001, "step": 26340 }, { "epoch": 19.05, "learning_rate": 2.107570392851121e-08, "loss": 0.0002, "step": 26350 }, { "epoch": 19.05, "learning_rate": 0.0, "loss": 0.0001, "step": 26360 }, { "epoch": 19.05, "eval_accuracy": 0.7997677719003999, "eval_loss": 1.2805378437042236, "eval_runtime": 639.1646, "eval_samples_per_second": 12.127, "eval_steps_per_second": 2.021, "step": 26360 }, { "epoch": 19.05, "step": 26360, "total_flos": 1.9720418219602536e+20, "train_loss": 0.38878340243031945, "train_runtime": 33047.467, "train_samples_per_second": 4.786, "train_steps_per_second": 0.798 }, { "epoch": 19.05, "eval_accuracy": 0.7732671974937998, "eval_loss": 1.432600498199463, "eval_runtime": 635.0272, "eval_samples_per_second": 12.064, "eval_steps_per_second": 2.011, "step": 26360 } ], "max_steps": 26360, "num_train_epochs": 9223372036854775807, "total_flos": 1.9720418219602536e+20, "trial_name": null, "trial_params": null }