diff --git "a/trainer_state.json" "b/trainer_state.json" --- "a/trainer_state.json" +++ "b/trainer_state.json" @@ -1,11375 +1,9353 @@ { - "best_metric": 0.9701774254435636, - "best_model_checkpoint": "wav2vec2-present/checkpoint-18760", - "epoch": 9.997335464961365, + "best_metric": 0.985280588776449, + "best_model_checkpoint": "wav2vec2-present/checkpoint-15390", + "epoch": 9.996752192270218, "eval_steps": 500, - "global_step": 18760, + "global_step": 15390, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, - "learning_rate": 1.5991471215351813e-07, - "loss": 2.7058, + "learning_rate": 1.9493177387914228e-07, + "loss": 2.564, "step": 10 }, { "epoch": 0.01, - "learning_rate": 3.1982942430703626e-07, - "loss": 2.7051, + "learning_rate": 3.8986354775828457e-07, + "loss": 2.558, "step": 20 }, { "epoch": 0.02, - "learning_rate": 4.797441364605544e-07, - "loss": 2.7029, + "learning_rate": 5.847953216374269e-07, + "loss": 2.5645, "step": 30 }, { - "epoch": 0.02, - "learning_rate": 6.396588486140725e-07, - "loss": 2.7122, + "epoch": 0.03, + "learning_rate": 7.797270955165691e-07, + "loss": 2.568, "step": 40 }, { "epoch": 0.03, - "learning_rate": 7.995735607675906e-07, - "loss": 2.7069, + "learning_rate": 9.746588693957115e-07, + "loss": 2.5642, "step": 50 }, { - "epoch": 0.03, - "learning_rate": 9.594882729211088e-07, - "loss": 2.6964, + "epoch": 0.04, + "learning_rate": 1.1695906432748538e-06, + "loss": 2.5622, "step": 60 }, { - "epoch": 0.04, - "learning_rate": 1.1194029850746267e-06, - "loss": 2.7084, + "epoch": 0.05, + "learning_rate": 1.364522417153996e-06, + "loss": 2.5609, "step": 70 }, { - "epoch": 0.04, - "learning_rate": 1.279317697228145e-06, - "loss": 2.699, + "epoch": 0.05, + "learning_rate": 1.5594541910331383e-06, + "loss": 2.5598, "step": 80 }, { - "epoch": 0.05, - "learning_rate": 1.4392324093816632e-06, - "loss": 2.7013, + "epoch": 0.06, + "learning_rate": 1.7543859649122807e-06, + "loss": 2.552, "step": 90 }, { - "epoch": 0.05, - "learning_rate": 1.5991471215351813e-06, - "loss": 2.7003, + "epoch": 0.06, + "learning_rate": 1.949317738791423e-06, + "loss": 2.5565, "step": 100 }, { - "epoch": 0.06, - "learning_rate": 1.7590618336886994e-06, - "loss": 2.6968, + "epoch": 0.07, + "learning_rate": 2.1442495126705653e-06, + "loss": 2.5584, "step": 110 }, { - "epoch": 0.06, - "learning_rate": 1.9189765458422177e-06, - "loss": 2.7127, + "epoch": 0.08, + "learning_rate": 2.3391812865497075e-06, + "loss": 2.5492, "step": 120 }, { - "epoch": 0.07, - "learning_rate": 2.0788912579957356e-06, - "loss": 2.6958, + "epoch": 0.08, + "learning_rate": 2.5341130604288498e-06, + "loss": 2.5532, "step": 130 }, { - "epoch": 0.07, - "learning_rate": 2.2388059701492535e-06, - "loss": 2.6958, + "epoch": 0.09, + "learning_rate": 2.729044834307992e-06, + "loss": 2.5497, "step": 140 }, { - "epoch": 0.08, - "learning_rate": 2.398720682302772e-06, - "loss": 2.6915, + "epoch": 0.1, + "learning_rate": 2.9239766081871343e-06, + "loss": 2.549, "step": 150 }, { - "epoch": 0.09, - "learning_rate": 2.55863539445629e-06, - "loss": 2.6861, + "epoch": 0.1, + "learning_rate": 3.1189083820662765e-06, + "loss": 2.546, "step": 160 }, { - "epoch": 0.09, - "learning_rate": 2.718550106609808e-06, - "loss": 2.6866, + "epoch": 0.11, + "learning_rate": 3.313840155945419e-06, + "loss": 2.5487, "step": 170 }, { - "epoch": 0.1, - "learning_rate": 2.8784648187633263e-06, - "loss": 2.6888, + "epoch": 0.12, + "learning_rate": 3.5087719298245615e-06, + "loss": 2.5346, "step": 180 }, { - "epoch": 0.1, - "learning_rate": 3.038379530916844e-06, - "loss": 2.6799, + "epoch": 0.12, + "learning_rate": 3.7037037037037037e-06, + "loss": 2.5267, "step": 190 }, { - "epoch": 0.11, - "learning_rate": 3.1982942430703625e-06, - "loss": 2.6873, + "epoch": 0.13, + "learning_rate": 3.898635477582846e-06, + "loss": 2.529, "step": 200 }, { - "epoch": 0.11, - "learning_rate": 3.358208955223881e-06, - "loss": 2.6741, + "epoch": 0.14, + "learning_rate": 4.093567251461988e-06, + "loss": 2.5306, "step": 210 }, { - "epoch": 0.12, - "learning_rate": 3.5181236673773987e-06, - "loss": 2.6815, + "epoch": 0.14, + "learning_rate": 4.2884990253411305e-06, + "loss": 2.5213, "step": 220 }, { - "epoch": 0.12, - "learning_rate": 3.6780383795309166e-06, - "loss": 2.678, + "epoch": 0.15, + "learning_rate": 4.483430799220272e-06, + "loss": 2.512, "step": 230 }, { - "epoch": 0.13, - "learning_rate": 3.837953091684435e-06, - "loss": 2.6623, + "epoch": 0.16, + "learning_rate": 4.678362573099415e-06, + "loss": 2.5016, "step": 240 }, { - "epoch": 0.13, - "learning_rate": 3.997867803837953e-06, - "loss": 2.6546, + "epoch": 0.16, + "learning_rate": 4.873294346978558e-06, + "loss": 2.5006, "step": 250 }, { - "epoch": 0.14, - "learning_rate": 4.157782515991471e-06, - "loss": 2.6595, + "epoch": 0.17, + "learning_rate": 5.0682261208576995e-06, + "loss": 2.5025, "step": 260 }, { - "epoch": 0.14, - "learning_rate": 4.317697228144989e-06, - "loss": 2.6585, + "epoch": 0.18, + "learning_rate": 5.263157894736842e-06, + "loss": 2.498, "step": 270 }, { - "epoch": 0.15, - "learning_rate": 4.477611940298507e-06, - "loss": 2.6639, + "epoch": 0.18, + "learning_rate": 5.458089668615984e-06, + "loss": 2.4611, "step": 280 }, { - "epoch": 0.15, - "learning_rate": 4.637526652452026e-06, - "loss": 2.6492, + "epoch": 0.19, + "learning_rate": 5.653021442495127e-06, + "loss": 2.4517, "step": 290 }, { - "epoch": 0.16, - "learning_rate": 4.797441364605544e-06, - "loss": 2.6367, + "epoch": 0.19, + "learning_rate": 5.8479532163742686e-06, + "loss": 2.4287, "step": 300 }, { - "epoch": 0.17, - "learning_rate": 4.957356076759062e-06, - "loss": 2.6198, + "epoch": 0.2, + "learning_rate": 6.042884990253411e-06, + "loss": 2.4189, "step": 310 }, { - "epoch": 0.17, - "learning_rate": 5.11727078891258e-06, - "loss": 2.6209, + "epoch": 0.21, + "learning_rate": 6.237816764132553e-06, + "loss": 2.3796, "step": 320 }, { - "epoch": 0.18, - "learning_rate": 5.277185501066098e-06, - "loss": 2.5951, + "epoch": 0.21, + "learning_rate": 6.432748538011696e-06, + "loss": 2.3646, "step": 330 }, { - "epoch": 0.18, - "learning_rate": 5.437100213219616e-06, - "loss": 2.5717, + "epoch": 0.22, + "learning_rate": 6.627680311890838e-06, + "loss": 2.3719, "step": 340 }, { - "epoch": 0.19, - "learning_rate": 5.597014925373135e-06, - "loss": 2.5759, + "epoch": 0.23, + "learning_rate": 6.82261208576998e-06, + "loss": 2.3398, "step": 350 }, { - "epoch": 0.19, - "learning_rate": 5.756929637526653e-06, - "loss": 2.584, + "epoch": 0.23, + "learning_rate": 7.017543859649123e-06, + "loss": 2.2933, "step": 360 }, { - "epoch": 0.2, - "learning_rate": 5.9168443496801705e-06, - "loss": 2.561, + "epoch": 0.24, + "learning_rate": 7.212475633528265e-06, + "loss": 2.3268, "step": 370 }, { - "epoch": 0.2, - "learning_rate": 6.076759061833688e-06, - "loss": 2.5333, + "epoch": 0.25, + "learning_rate": 7.4074074074074075e-06, + "loss": 2.2196, "step": 380 }, { - "epoch": 0.21, - "learning_rate": 6.236673773987207e-06, - "loss": 2.4944, + "epoch": 0.25, + "learning_rate": 7.602339181286549e-06, + "loss": 2.1905, "step": 390 }, { - "epoch": 0.21, - "learning_rate": 6.396588486140725e-06, - "loss": 2.5025, + "epoch": 0.26, + "learning_rate": 7.797270955165692e-06, + "loss": 2.2123, "step": 400 }, { - "epoch": 0.22, - "learning_rate": 6.556503198294244e-06, - "loss": 2.4517, + "epoch": 0.27, + "learning_rate": 7.992202729044834e-06, + "loss": 2.1655, "step": 410 }, { - "epoch": 0.22, - "learning_rate": 6.716417910447762e-06, - "loss": 2.4479, + "epoch": 0.27, + "learning_rate": 8.187134502923976e-06, + "loss": 2.1171, "step": 420 }, { - "epoch": 0.23, - "learning_rate": 6.8763326226012796e-06, - "loss": 2.4053, + "epoch": 0.28, + "learning_rate": 8.38206627680312e-06, + "loss": 2.056, "step": 430 }, { - "epoch": 0.23, - "learning_rate": 7.0362473347547975e-06, - "loss": 2.3395, + "epoch": 0.29, + "learning_rate": 8.576998050682261e-06, + "loss": 2.0953, "step": 440 }, { - "epoch": 0.24, - "learning_rate": 7.196162046908315e-06, - "loss": 2.3648, + "epoch": 0.29, + "learning_rate": 8.771929824561403e-06, + "loss": 2.0215, "step": 450 }, { - "epoch": 0.25, - "learning_rate": 7.356076759061833e-06, - "loss": 2.3112, + "epoch": 0.3, + "learning_rate": 8.966861598440545e-06, + "loss": 1.9845, "step": 460 }, { - "epoch": 0.25, - "learning_rate": 7.515991471215352e-06, - "loss": 2.3062, + "epoch": 0.31, + "learning_rate": 9.161793372319688e-06, + "loss": 1.9909, "step": 470 }, { - "epoch": 0.26, - "learning_rate": 7.67590618336887e-06, - "loss": 2.3172, + "epoch": 0.31, + "learning_rate": 9.35672514619883e-06, + "loss": 1.9478, "step": 480 }, { - "epoch": 0.26, - "learning_rate": 7.835820895522387e-06, - "loss": 2.2853, + "epoch": 0.32, + "learning_rate": 9.551656920077972e-06, + "loss": 1.9098, "step": 490 }, { - "epoch": 0.27, - "learning_rate": 7.995735607675907e-06, - "loss": 2.2212, + "epoch": 0.32, + "learning_rate": 9.746588693957115e-06, + "loss": 1.8296, "step": 500 }, { - "epoch": 0.27, - "learning_rate": 8.155650319829424e-06, - "loss": 2.1785, + "epoch": 0.33, + "learning_rate": 9.941520467836257e-06, + "loss": 1.7486, "step": 510 }, { - "epoch": 0.28, - "learning_rate": 8.315565031982942e-06, - "loss": 2.1647, + "epoch": 0.34, + "learning_rate": 1.0136452241715399e-05, + "loss": 1.7578, "step": 520 }, { - "epoch": 0.28, - "learning_rate": 8.475479744136462e-06, - "loss": 2.1815, + "epoch": 0.34, + "learning_rate": 1.0331384015594541e-05, + "loss": 1.708, "step": 530 }, { - "epoch": 0.29, - "learning_rate": 8.635394456289978e-06, - "loss": 2.1073, + "epoch": 0.35, + "learning_rate": 1.0526315789473684e-05, + "loss": 1.5767, "step": 540 }, { - "epoch": 0.29, - "learning_rate": 8.795309168443498e-06, - "loss": 2.078, + "epoch": 0.36, + "learning_rate": 1.0721247563352826e-05, + "loss": 1.7068, "step": 550 }, { - "epoch": 0.3, - "learning_rate": 8.955223880597014e-06, - "loss": 2.0629, + "epoch": 0.36, + "learning_rate": 1.0916179337231968e-05, + "loss": 1.6142, "step": 560 }, { - "epoch": 0.3, - "learning_rate": 9.115138592750533e-06, - "loss": 2.0484, + "epoch": 0.37, + "learning_rate": 1.111111111111111e-05, + "loss": 1.584, "step": 570 }, { - "epoch": 0.31, - "learning_rate": 9.275053304904051e-06, - "loss": 1.9608, + "epoch": 0.38, + "learning_rate": 1.1306042884990253e-05, + "loss": 1.523, "step": 580 }, { - "epoch": 0.31, - "learning_rate": 9.43496801705757e-06, - "loss": 1.9014, + "epoch": 0.38, + "learning_rate": 1.1500974658869395e-05, + "loss": 1.4793, "step": 590 }, { - "epoch": 0.32, - "learning_rate": 9.594882729211089e-06, - "loss": 1.8718, + "epoch": 0.39, + "learning_rate": 1.1695906432748537e-05, + "loss": 1.4863, "step": 600 }, { - "epoch": 0.33, - "learning_rate": 9.754797441364605e-06, - "loss": 1.8846, + "epoch": 0.4, + "learning_rate": 1.1871345029239766e-05, + "loss": 1.4778, "step": 610 }, { - "epoch": 0.33, - "learning_rate": 9.914712153518125e-06, - "loss": 1.9044, + "epoch": 0.4, + "learning_rate": 1.2066276803118908e-05, + "loss": 1.3872, "step": 620 }, { - "epoch": 0.34, - "learning_rate": 1.0074626865671643e-05, - "loss": 1.8436, + "epoch": 0.41, + "learning_rate": 1.226120857699805e-05, + "loss": 1.412, "step": 630 }, { - "epoch": 0.34, - "learning_rate": 1.023454157782516e-05, - "loss": 1.8495, + "epoch": 0.42, + "learning_rate": 1.2456140350877193e-05, + "loss": 1.4054, "step": 640 }, { - "epoch": 0.35, - "learning_rate": 1.0394456289978678e-05, - "loss": 1.7935, + "epoch": 0.42, + "learning_rate": 1.2651072124756335e-05, + "loss": 1.4, "step": 650 }, { - "epoch": 0.35, - "learning_rate": 1.0554371002132196e-05, - "loss": 1.7222, + "epoch": 0.43, + "learning_rate": 1.2846003898635477e-05, + "loss": 1.2976, "step": 660 }, { - "epoch": 0.36, - "learning_rate": 1.0714285714285714e-05, - "loss": 1.7742, + "epoch": 0.44, + "learning_rate": 1.3040935672514619e-05, + "loss": 1.3261, "step": 670 }, { - "epoch": 0.36, - "learning_rate": 1.0874200426439232e-05, - "loss": 1.6794, + "epoch": 0.44, + "learning_rate": 1.3235867446393762e-05, + "loss": 1.2583, "step": 680 }, { - "epoch": 0.37, - "learning_rate": 1.10181236673774e-05, - "loss": 1.6701, + "epoch": 0.45, + "learning_rate": 1.3430799220272904e-05, + "loss": 1.3031, "step": 690 }, { - "epoch": 0.37, - "learning_rate": 1.1178038379530916e-05, - "loss": 1.6795, + "epoch": 0.45, + "learning_rate": 1.3625730994152046e-05, + "loss": 1.1888, "step": 700 }, { - "epoch": 0.38, - "learning_rate": 1.1337953091684436e-05, - "loss": 1.574, + "epoch": 0.46, + "learning_rate": 1.3820662768031188e-05, + "loss": 1.2747, "step": 710 }, { - "epoch": 0.38, - "learning_rate": 1.1497867803837952e-05, - "loss": 1.6778, + "epoch": 0.47, + "learning_rate": 1.4015594541910331e-05, + "loss": 1.1909, "step": 720 }, { - "epoch": 0.39, - "learning_rate": 1.1657782515991471e-05, - "loss": 1.6113, + "epoch": 0.47, + "learning_rate": 1.4210526315789473e-05, + "loss": 1.1954, "step": 730 }, { - "epoch": 0.39, - "learning_rate": 1.1817697228144991e-05, - "loss": 1.5246, + "epoch": 0.48, + "learning_rate": 1.4405458089668615e-05, + "loss": 1.1938, "step": 740 }, { - "epoch": 0.4, - "learning_rate": 1.1977611940298507e-05, - "loss": 1.5274, + "epoch": 0.49, + "learning_rate": 1.4600389863547759e-05, + "loss": 1.1446, "step": 750 }, { - "epoch": 0.41, - "learning_rate": 1.2137526652452027e-05, - "loss": 1.5599, + "epoch": 0.49, + "learning_rate": 1.47953216374269e-05, + "loss": 1.0875, "step": 760 }, { - "epoch": 0.41, - "learning_rate": 1.2297441364605543e-05, - "loss": 1.551, + "epoch": 0.5, + "learning_rate": 1.4990253411306042e-05, + "loss": 1.1029, "step": 770 }, { - "epoch": 0.42, - "learning_rate": 1.2457356076759062e-05, - "loss": 1.5579, + "epoch": 0.51, + "learning_rate": 1.5185185185185186e-05, + "loss": 0.9905, "step": 780 }, { - "epoch": 0.42, - "learning_rate": 1.261727078891258e-05, - "loss": 1.4199, + "epoch": 0.51, + "learning_rate": 1.538011695906433e-05, + "loss": 1.175, "step": 790 }, { - "epoch": 0.43, - "learning_rate": 1.2777185501066098e-05, - "loss": 1.4589, + "epoch": 0.52, + "learning_rate": 1.5555555555555555e-05, + "loss": 1.0142, "step": 800 }, { - "epoch": 0.43, - "learning_rate": 1.2937100213219616e-05, - "loss": 1.4302, + "epoch": 0.53, + "learning_rate": 1.5750487329434697e-05, + "loss": 1.054, "step": 810 }, { - "epoch": 0.44, - "learning_rate": 1.3097014925373134e-05, - "loss": 1.4312, + "epoch": 0.53, + "learning_rate": 1.594541910331384e-05, + "loss": 1.019, "step": 820 }, { - "epoch": 0.44, - "learning_rate": 1.3256929637526654e-05, - "loss": 1.3975, + "epoch": 0.54, + "learning_rate": 1.614035087719298e-05, + "loss": 0.98, "step": 830 }, { - "epoch": 0.45, - "learning_rate": 1.341684434968017e-05, - "loss": 1.3462, + "epoch": 0.55, + "learning_rate": 1.6335282651072126e-05, + "loss": 0.8901, "step": 840 }, { - "epoch": 0.45, - "learning_rate": 1.357675906183369e-05, - "loss": 1.3677, + "epoch": 0.55, + "learning_rate": 1.6530214424951268e-05, + "loss": 0.9091, "step": 850 }, { - "epoch": 0.46, - "learning_rate": 1.3736673773987207e-05, - "loss": 1.3216, + "epoch": 0.56, + "learning_rate": 1.672514619883041e-05, + "loss": 0.8969, "step": 860 }, { - "epoch": 0.46, - "learning_rate": 1.3896588486140725e-05, - "loss": 1.2835, + "epoch": 0.57, + "learning_rate": 1.692007797270955e-05, + "loss": 0.8246, "step": 870 }, { - "epoch": 0.47, - "learning_rate": 1.4056503198294243e-05, - "loss": 1.256, + "epoch": 0.57, + "learning_rate": 1.7115009746588693e-05, + "loss": 1.0441, "step": 880 }, { - "epoch": 0.47, - "learning_rate": 1.4216417910447761e-05, - "loss": 1.2431, + "epoch": 0.58, + "learning_rate": 1.7309941520467835e-05, + "loss": 0.8832, "step": 890 }, { - "epoch": 0.48, - "learning_rate": 1.437633262260128e-05, - "loss": 1.1992, + "epoch": 0.58, + "learning_rate": 1.7504873294346977e-05, + "loss": 0.8898, "step": 900 }, { - "epoch": 0.48, - "learning_rate": 1.4536247334754798e-05, - "loss": 1.1945, + "epoch": 0.59, + "learning_rate": 1.7699805068226122e-05, + "loss": 0.8001, "step": 910 }, { - "epoch": 0.49, - "learning_rate": 1.4696162046908316e-05, - "loss": 1.1973, + "epoch": 0.6, + "learning_rate": 1.7894736842105264e-05, + "loss": 0.7232, "step": 920 }, { - "epoch": 0.5, - "learning_rate": 1.4856076759061834e-05, - "loss": 1.1784, + "epoch": 0.6, + "learning_rate": 1.8089668615984406e-05, + "loss": 0.8311, "step": 930 }, { - "epoch": 0.5, - "learning_rate": 1.5015991471215354e-05, - "loss": 1.189, + "epoch": 0.61, + "learning_rate": 1.8284600389863547e-05, + "loss": 0.7449, "step": 940 }, { - "epoch": 0.51, - "learning_rate": 1.517590618336887e-05, - "loss": 1.0646, + "epoch": 0.62, + "learning_rate": 1.847953216374269e-05, + "loss": 0.8162, "step": 950 }, { - "epoch": 0.51, - "learning_rate": 1.5335820895522386e-05, - "loss": 1.131, + "epoch": 0.62, + "learning_rate": 1.867446393762183e-05, + "loss": 0.7072, "step": 960 }, { - "epoch": 0.52, - "learning_rate": 1.5479744136460556e-05, - "loss": 1.0456, + "epoch": 0.63, + "learning_rate": 1.8869395711500973e-05, + "loss": 0.7233, "step": 970 }, { - "epoch": 0.52, - "learning_rate": 1.5639658848614074e-05, - "loss": 1.0541, + "epoch": 0.64, + "learning_rate": 1.9064327485380115e-05, + "loss": 0.8823, "step": 980 }, { - "epoch": 0.53, - "learning_rate": 1.5799573560767588e-05, - "loss": 1.0176, + "epoch": 0.64, + "learning_rate": 1.925925925925926e-05, + "loss": 0.71, "step": 990 }, { - "epoch": 0.53, - "learning_rate": 1.595948827292111e-05, - "loss": 0.9596, + "epoch": 0.65, + "learning_rate": 1.9454191033138402e-05, + "loss": 0.6826, "step": 1000 }, { - "epoch": 0.54, - "learning_rate": 1.6119402985074627e-05, - "loss": 0.9928, + "epoch": 0.66, + "learning_rate": 1.9649122807017544e-05, + "loss": 0.7723, "step": 1010 }, { - "epoch": 0.54, - "learning_rate": 1.6279317697228145e-05, - "loss": 1.116, + "epoch": 0.66, + "learning_rate": 1.9844054580896685e-05, + "loss": 0.7333, "step": 1020 }, { - "epoch": 0.55, - "learning_rate": 1.6439232409381666e-05, - "loss": 0.8834, + "epoch": 0.67, + "learning_rate": 2.0038986354775827e-05, + "loss": 0.6399, "step": 1030 }, { - "epoch": 0.55, - "learning_rate": 1.659914712153518e-05, - "loss": 0.8796, + "epoch": 0.68, + "learning_rate": 2.023391812865497e-05, + "loss": 0.5773, "step": 1040 }, { - "epoch": 0.56, - "learning_rate": 1.67590618336887e-05, - "loss": 1.1724, + "epoch": 0.68, + "learning_rate": 2.042884990253411e-05, + "loss": 0.5524, "step": 1050 }, { - "epoch": 0.56, - "learning_rate": 1.6918976545842217e-05, - "loss": 1.03, + "epoch": 0.69, + "learning_rate": 2.0623781676413256e-05, + "loss": 0.6107, "step": 1060 }, { - "epoch": 0.57, - "learning_rate": 1.7078891257995738e-05, - "loss": 0.8693, + "epoch": 0.7, + "learning_rate": 2.0818713450292398e-05, + "loss": 0.515, "step": 1070 }, { - "epoch": 0.58, - "learning_rate": 1.7238805970149253e-05, - "loss": 0.8915, + "epoch": 0.7, + "learning_rate": 2.101364522417154e-05, + "loss": 0.5981, "step": 1080 }, { - "epoch": 0.58, - "learning_rate": 1.739872068230277e-05, - "loss": 0.9146, + "epoch": 0.71, + "learning_rate": 2.120857699805068e-05, + "loss": 0.6844, "step": 1090 }, { - "epoch": 0.59, - "learning_rate": 1.7558635394456292e-05, - "loss": 0.8656, + "epoch": 0.71, + "learning_rate": 2.1403508771929824e-05, + "loss": 0.4908, "step": 1100 }, { - "epoch": 0.59, - "learning_rate": 1.771855010660981e-05, - "loss": 0.8612, + "epoch": 0.72, + "learning_rate": 2.1598440545808965e-05, + "loss": 0.5733, "step": 1110 }, { - "epoch": 0.6, - "learning_rate": 1.7878464818763328e-05, - "loss": 0.9181, + "epoch": 0.73, + "learning_rate": 2.1793372319688107e-05, + "loss": 0.4578, "step": 1120 }, { - "epoch": 0.6, - "learning_rate": 1.8038379530916845e-05, - "loss": 0.748, + "epoch": 0.73, + "learning_rate": 2.1988304093567252e-05, + "loss": 0.4443, "step": 1130 }, { - "epoch": 0.61, - "learning_rate": 1.8198294243070363e-05, - "loss": 0.7977, + "epoch": 0.74, + "learning_rate": 2.2183235867446394e-05, + "loss": 0.4854, "step": 1140 }, { - "epoch": 0.61, - "learning_rate": 1.835820895522388e-05, - "loss": 0.8158, + "epoch": 0.75, + "learning_rate": 2.2378167641325536e-05, + "loss": 0.4891, "step": 1150 }, { - "epoch": 0.62, - "learning_rate": 1.85181236673774e-05, - "loss": 0.7881, + "epoch": 0.75, + "learning_rate": 2.2573099415204678e-05, + "loss": 0.4287, "step": 1160 }, { - "epoch": 0.62, - "learning_rate": 1.8678038379530917e-05, - "loss": 0.7023, + "epoch": 0.76, + "learning_rate": 2.2748538011695907e-05, + "loss": 0.7449, "step": 1170 }, { - "epoch": 0.63, - "learning_rate": 1.8837953091684435e-05, - "loss": 0.6825, + "epoch": 0.77, + "learning_rate": 2.294346978557505e-05, + "loss": 0.4233, "step": 1180 }, { - "epoch": 0.63, - "learning_rate": 1.8997867803837953e-05, - "loss": 0.6484, + "epoch": 0.77, + "learning_rate": 2.313840155945419e-05, + "loss": 0.749, "step": 1190 }, { - "epoch": 0.64, - "learning_rate": 1.9157782515991474e-05, - "loss": 0.788, + "epoch": 0.78, + "learning_rate": 2.3333333333333336e-05, + "loss": 0.4584, "step": 1200 }, { - "epoch": 0.64, - "learning_rate": 1.9317697228144992e-05, - "loss": 0.7102, + "epoch": 0.79, + "learning_rate": 2.3528265107212478e-05, + "loss": 0.379, "step": 1210 }, { - "epoch": 0.65, - "learning_rate": 1.9477611940298506e-05, - "loss": 0.719, + "epoch": 0.79, + "learning_rate": 2.372319688109162e-05, + "loss": 0.5038, "step": 1220 }, { - "epoch": 0.66, - "learning_rate": 1.9637526652452024e-05, - "loss": 0.7508, + "epoch": 0.8, + "learning_rate": 2.391812865497076e-05, + "loss": 0.4659, "step": 1230 }, { - "epoch": 0.66, - "learning_rate": 1.9797441364605546e-05, - "loss": 0.6358, + "epoch": 0.81, + "learning_rate": 2.4113060428849903e-05, + "loss": 0.5737, "step": 1240 }, { - "epoch": 0.67, - "learning_rate": 1.9957356076759064e-05, - "loss": 0.6987, + "epoch": 0.81, + "learning_rate": 2.4307992202729045e-05, + "loss": 0.4579, "step": 1250 }, { - "epoch": 0.67, - "learning_rate": 2.0117270788912578e-05, - "loss": 0.7215, + "epoch": 0.82, + "learning_rate": 2.4502923976608187e-05, + "loss": 0.4404, "step": 1260 }, { - "epoch": 0.68, - "learning_rate": 2.02771855010661e-05, - "loss": 0.6801, + "epoch": 0.82, + "learning_rate": 2.4697855750487332e-05, + "loss": 0.3332, "step": 1270 }, { - "epoch": 0.68, - "learning_rate": 2.0437100213219617e-05, - "loss": 0.6987, + "epoch": 0.83, + "learning_rate": 2.4892787524366474e-05, + "loss": 0.4733, "step": 1280 }, { - "epoch": 0.69, - "learning_rate": 2.0581023454157783e-05, - "loss": 0.7564, + "epoch": 0.84, + "learning_rate": 2.5087719298245616e-05, + "loss": 0.4872, "step": 1290 }, { - "epoch": 0.69, - "learning_rate": 2.07409381663113e-05, - "loss": 0.8201, + "epoch": 0.84, + "learning_rate": 2.5282651072124758e-05, + "loss": 0.473, "step": 1300 }, { - "epoch": 0.7, - "learning_rate": 2.090085287846482e-05, - "loss": 0.7547, + "epoch": 0.85, + "learning_rate": 2.54775828460039e-05, + "loss": 0.4366, "step": 1310 }, { - "epoch": 0.7, - "learning_rate": 2.1060767590618337e-05, - "loss": 0.5557, + "epoch": 0.86, + "learning_rate": 2.567251461988304e-05, + "loss": 0.3755, "step": 1320 }, { - "epoch": 0.71, - "learning_rate": 2.1220682302771858e-05, - "loss": 0.6161, + "epoch": 0.86, + "learning_rate": 2.5867446393762183e-05, + "loss": 0.6943, "step": 1330 }, { - "epoch": 0.71, - "learning_rate": 2.1380597014925373e-05, - "loss": 0.6363, + "epoch": 0.87, + "learning_rate": 2.6062378167641325e-05, + "loss": 0.3036, "step": 1340 }, { - "epoch": 0.72, - "learning_rate": 2.154051172707889e-05, - "loss": 0.8074, + "epoch": 0.88, + "learning_rate": 2.625730994152047e-05, + "loss": 0.4545, "step": 1350 }, { - "epoch": 0.72, - "learning_rate": 2.1700426439232412e-05, - "loss": 0.5874, + "epoch": 0.88, + "learning_rate": 2.6452241715399612e-05, + "loss": 0.3032, "step": 1360 }, { - "epoch": 0.73, - "learning_rate": 2.186034115138593e-05, - "loss": 0.6196, + "epoch": 0.89, + "learning_rate": 2.6647173489278754e-05, + "loss": 0.3492, "step": 1370 }, { - "epoch": 0.74, - "learning_rate": 2.2020255863539444e-05, - "loss": 0.7165, + "epoch": 0.9, + "learning_rate": 2.6842105263157896e-05, + "loss": 0.2846, "step": 1380 }, { - "epoch": 0.74, - "learning_rate": 2.2180170575692962e-05, - "loss": 0.6079, + "epoch": 0.9, + "learning_rate": 2.7037037037037037e-05, + "loss": 0.5078, "step": 1390 }, { - "epoch": 0.75, - "learning_rate": 2.2340085287846484e-05, - "loss": 0.5327, + "epoch": 0.91, + "learning_rate": 2.7212475633528263e-05, + "loss": 0.3074, "step": 1400 }, { - "epoch": 0.75, - "learning_rate": 2.25e-05, - "loss": 0.5281, + "epoch": 0.92, + "learning_rate": 2.7407407407407408e-05, + "loss": 0.2837, "step": 1410 }, { - "epoch": 0.76, - "learning_rate": 2.265991471215352e-05, - "loss": 0.6743, + "epoch": 0.92, + "learning_rate": 2.760233918128655e-05, + "loss": 0.4813, "step": 1420 }, { - "epoch": 0.76, - "learning_rate": 2.2819829424307037e-05, - "loss": 0.6146, + "epoch": 0.93, + "learning_rate": 2.7797270955165692e-05, + "loss": 0.3597, "step": 1430 }, { - "epoch": 0.77, - "learning_rate": 2.2963752665245203e-05, - "loss": 0.617, + "epoch": 0.94, + "learning_rate": 2.7992202729044834e-05, + "loss": 0.1955, "step": 1440 }, { - "epoch": 0.77, - "learning_rate": 2.312366737739872e-05, - "loss": 0.6567, + "epoch": 0.94, + "learning_rate": 2.8187134502923976e-05, + "loss": 0.5268, "step": 1450 }, { - "epoch": 0.78, - "learning_rate": 2.328358208955224e-05, - "loss": 0.7102, + "epoch": 0.95, + "learning_rate": 2.8382066276803117e-05, + "loss": 0.5699, "step": 1460 }, { - "epoch": 0.78, - "learning_rate": 2.3443496801705757e-05, - "loss": 0.5687, + "epoch": 0.95, + "learning_rate": 2.857699805068226e-05, + "loss": 0.3092, "step": 1470 }, { - "epoch": 0.79, - "learning_rate": 2.3603411513859275e-05, - "loss": 0.725, + "epoch": 0.96, + "learning_rate": 2.87719298245614e-05, + "loss": 0.3738, "step": 1480 }, { - "epoch": 0.79, - "learning_rate": 2.3763326226012796e-05, - "loss": 0.6255, + "epoch": 0.97, + "learning_rate": 2.8966861598440546e-05, + "loss": 0.5783, "step": 1490 }, { - "epoch": 0.8, - "learning_rate": 2.392324093816631e-05, - "loss": 0.5655, + "epoch": 0.97, + "learning_rate": 2.9161793372319688e-05, + "loss": 0.3053, "step": 1500 }, { - "epoch": 0.8, - "learning_rate": 2.408315565031983e-05, - "loss": 0.6185, + "epoch": 0.98, + "learning_rate": 2.935672514619883e-05, + "loss": 0.3565, "step": 1510 }, { - "epoch": 0.81, - "learning_rate": 2.424307036247335e-05, - "loss": 0.5105, + "epoch": 0.99, + "learning_rate": 2.9551656920077972e-05, + "loss": 0.3092, "step": 1520 }, { - "epoch": 0.82, - "learning_rate": 2.4402985074626868e-05, - "loss": 0.4525, + "epoch": 0.99, + "learning_rate": 2.9746588693957114e-05, + "loss": 0.5208, "step": 1530 }, { - "epoch": 0.82, - "learning_rate": 2.4562899786780386e-05, - "loss": 0.5419, + "epoch": 1.0, + "eval_accuracy": 0.9425022999080037, + "eval_loss": 0.22455397248268127, + "eval_runtime": 13.2379, + "eval_samples_per_second": 164.226, + "eval_steps_per_second": 41.094, + "step": 1539 + }, + { + "epoch": 1.0, + "learning_rate": 2.9941520467836255e-05, + "loss": 0.4893, "step": 1540 }, { - "epoch": 0.83, - "learning_rate": 2.47228144989339e-05, - "loss": 0.5127, + "epoch": 1.01, + "learning_rate": 2.99848386398094e-05, + "loss": 0.2747, "step": 1550 }, { - "epoch": 0.83, - "learning_rate": 2.488272921108742e-05, - "loss": 0.5781, + "epoch": 1.01, + "learning_rate": 2.9963179553822827e-05, + "loss": 0.6032, "step": 1560 }, { - "epoch": 0.84, - "learning_rate": 2.504264392324094e-05, - "loss": 0.7169, + "epoch": 1.02, + "learning_rate": 2.9941520467836255e-05, + "loss": 0.265, "step": 1570 }, { - "epoch": 0.84, - "learning_rate": 2.5202558635394457e-05, - "loss": 0.5577, + "epoch": 1.03, + "learning_rate": 2.9919861381849688e-05, + "loss": 0.4532, "step": 1580 }, { - "epoch": 0.85, - "learning_rate": 2.5362473347547975e-05, - "loss": 0.5131, + "epoch": 1.03, + "learning_rate": 2.9898202295863116e-05, + "loss": 0.3197, "step": 1590 }, { - "epoch": 0.85, - "learning_rate": 2.5522388059701493e-05, - "loss": 0.3743, + "epoch": 1.04, + "learning_rate": 2.9876543209876545e-05, + "loss": 0.3362, "step": 1600 }, { - "epoch": 0.86, - "learning_rate": 2.568230277185501e-05, - "loss": 0.5552, + "epoch": 1.05, + "learning_rate": 2.9854884123889974e-05, + "loss": 0.3188, "step": 1610 }, { - "epoch": 0.86, - "learning_rate": 2.584221748400853e-05, - "loss": 0.5599, + "epoch": 1.05, + "learning_rate": 2.9833225037903402e-05, + "loss": 0.3177, "step": 1620 }, { - "epoch": 0.87, - "learning_rate": 2.600213219616205e-05, - "loss": 0.4605, + "epoch": 1.06, + "learning_rate": 2.981156595191683e-05, + "loss": 0.4515, "step": 1630 }, { - "epoch": 0.87, - "learning_rate": 2.6162046908315565e-05, - "loss": 0.5457, + "epoch": 1.07, + "learning_rate": 2.9789906865930256e-05, + "loss": 0.2545, "step": 1640 }, { - "epoch": 0.88, - "learning_rate": 2.6321961620469082e-05, - "loss": 0.449, + "epoch": 1.07, + "learning_rate": 2.9768247779943685e-05, + "loss": 0.2263, "step": 1650 }, { - "epoch": 0.88, - "learning_rate": 2.6481876332622604e-05, - "loss": 0.3577, + "epoch": 1.08, + "learning_rate": 2.9746588693957114e-05, + "loss": 0.4115, "step": 1660 }, { - "epoch": 0.89, - "learning_rate": 2.664179104477612e-05, - "loss": 0.5797, + "epoch": 1.08, + "learning_rate": 2.9724929607970546e-05, + "loss": 0.2845, "step": 1670 }, { - "epoch": 0.9, - "learning_rate": 2.6801705756929636e-05, - "loss": 0.3892, + "epoch": 1.09, + "learning_rate": 2.9703270521983974e-05, + "loss": 0.3104, "step": 1680 }, { - "epoch": 0.9, - "learning_rate": 2.6961620469083154e-05, - "loss": 0.6802, + "epoch": 1.1, + "learning_rate": 2.9681611435997403e-05, + "loss": 0.3711, "step": 1690 }, { - "epoch": 0.91, - "learning_rate": 2.7121535181236675e-05, - "loss": 0.4291, + "epoch": 1.1, + "learning_rate": 2.9659952350010832e-05, + "loss": 0.3236, "step": 1700 }, { - "epoch": 0.91, - "learning_rate": 2.7281449893390193e-05, - "loss": 0.2939, + "epoch": 1.11, + "learning_rate": 2.9638293264024257e-05, + "loss": 0.216, "step": 1710 }, { - "epoch": 0.92, - "learning_rate": 2.744136460554371e-05, - "loss": 0.4799, + "epoch": 1.12, + "learning_rate": 2.9616634178037686e-05, + "loss": 0.3934, "step": 1720 }, { - "epoch": 0.92, - "learning_rate": 2.760127931769723e-05, - "loss": 0.4763, + "epoch": 1.12, + "learning_rate": 2.9594975092051114e-05, + "loss": 0.6872, "step": 1730 }, { - "epoch": 0.93, - "learning_rate": 2.7761194029850747e-05, - "loss": 0.5389, + "epoch": 1.13, + "learning_rate": 2.9573316006064543e-05, + "loss": 0.5262, "step": 1740 }, { - "epoch": 0.93, - "learning_rate": 2.7921108742004265e-05, - "loss": 0.7226, + "epoch": 1.14, + "learning_rate": 2.9551656920077972e-05, + "loss": 0.3703, "step": 1750 }, { - "epoch": 0.94, - "learning_rate": 2.8081023454157786e-05, - "loss": 0.4911, + "epoch": 1.14, + "learning_rate": 2.9529997834091404e-05, + "loss": 0.3206, "step": 1760 }, { - "epoch": 0.94, - "learning_rate": 2.82409381663113e-05, - "loss": 0.5087, + "epoch": 1.15, + "learning_rate": 2.9508338748104833e-05, + "loss": 0.3157, "step": 1770 }, { - "epoch": 0.95, - "learning_rate": 2.840085287846482e-05, - "loss": 0.5801, + "epoch": 1.16, + "learning_rate": 2.948667966211826e-05, + "loss": 0.3127, "step": 1780 }, { - "epoch": 0.95, - "learning_rate": 2.8560767590618336e-05, - "loss": 0.5971, + "epoch": 1.16, + "learning_rate": 2.9465020576131687e-05, + "loss": 0.2422, "step": 1790 }, { - "epoch": 0.96, - "learning_rate": 2.8720682302771858e-05, - "loss": 0.4516, + "epoch": 1.17, + "learning_rate": 2.9443361490145115e-05, + "loss": 0.6096, "step": 1800 }, { - "epoch": 0.96, - "learning_rate": 2.8880597014925376e-05, - "loss": 0.3991, + "epoch": 1.18, + "learning_rate": 2.9421702404158544e-05, + "loss": 0.4274, "step": 1810 }, { - "epoch": 0.97, - "learning_rate": 2.904051172707889e-05, - "loss": 0.2097, + "epoch": 1.18, + "learning_rate": 2.9400043318171973e-05, + "loss": 0.4009, "step": 1820 }, { - "epoch": 0.98, - "learning_rate": 2.920042643923241e-05, - "loss": 0.5246, + "epoch": 1.19, + "learning_rate": 2.93783842321854e-05, + "loss": 0.4787, "step": 1830 }, { - "epoch": 0.98, - "learning_rate": 2.936034115138593e-05, - "loss": 0.4524, + "epoch": 1.2, + "learning_rate": 2.935672514619883e-05, + "loss": 0.4098, "step": 1840 }, { - "epoch": 0.99, - "learning_rate": 2.9520255863539447e-05, - "loss": 0.4452, + "epoch": 1.2, + "learning_rate": 2.9335066060212262e-05, + "loss": 0.4029, "step": 1850 }, { - "epoch": 0.99, - "learning_rate": 2.968017057569296e-05, - "loss": 0.5266, + "epoch": 1.21, + "learning_rate": 2.931340697422569e-05, + "loss": 0.2639, "step": 1860 }, { - "epoch": 1.0, - "learning_rate": 2.9840085287846483e-05, - "loss": 0.5059, + "epoch": 1.21, + "learning_rate": 2.9291747888239116e-05, + "loss": 0.4326, "step": 1870 }, { - "epoch": 1.0, - "eval_accuracy": 0.93280483201208, - "eval_loss": 0.2955198884010315, - "eval_runtime": 53.1722, - "eval_samples_per_second": 49.819, - "eval_steps_per_second": 12.469, - "step": 1876 - }, - { - "epoch": 1.0, - "learning_rate": 3e-05, - "loss": 0.4238, + "epoch": 1.22, + "learning_rate": 2.9270088802252545e-05, + "loss": 0.6265, "step": 1880 }, { - "epoch": 1.01, - "learning_rate": 2.9982231698649608e-05, - "loss": 0.2719, + "epoch": 1.23, + "learning_rate": 2.9248429716265973e-05, + "loss": 0.453, "step": 1890 }, { - "epoch": 1.01, - "learning_rate": 2.9964463397299218e-05, - "loss": 0.4421, + "epoch": 1.23, + "learning_rate": 2.9226770630279402e-05, + "loss": 0.3825, "step": 1900 }, { - "epoch": 1.02, - "learning_rate": 2.9946695095948828e-05, - "loss": 0.4737, + "epoch": 1.24, + "learning_rate": 2.920511154429283e-05, + "loss": 0.567, "step": 1910 }, { - "epoch": 1.02, - "learning_rate": 2.992892679459844e-05, - "loss": 0.4137, + "epoch": 1.25, + "learning_rate": 2.918345245830626e-05, + "loss": 0.3227, "step": 1920 }, { - "epoch": 1.03, - "learning_rate": 2.9911158493248045e-05, - "loss": 0.3068, + "epoch": 1.25, + "learning_rate": 2.9161793372319688e-05, + "loss": 0.4686, "step": 1930 }, { - "epoch": 1.03, - "learning_rate": 2.9893390191897655e-05, - "loss": 0.4424, + "epoch": 1.26, + "learning_rate": 2.914013428633312e-05, + "loss": 0.4481, "step": 1940 }, { - "epoch": 1.04, - "learning_rate": 2.9875621890547262e-05, - "loss": 0.5185, + "epoch": 1.27, + "learning_rate": 2.9118475200346546e-05, + "loss": 0.3457, "step": 1950 }, { - "epoch": 1.04, - "learning_rate": 2.9857853589196876e-05, - "loss": 0.1856, + "epoch": 1.27, + "learning_rate": 2.9096816114359974e-05, + "loss": 0.3616, "step": 1960 }, { - "epoch": 1.05, - "learning_rate": 2.9840085287846483e-05, - "loss": 0.4217, + "epoch": 1.28, + "learning_rate": 2.9075157028373403e-05, + "loss": 0.3722, "step": 1970 }, { - "epoch": 1.06, - "learning_rate": 2.9822316986496093e-05, - "loss": 0.3361, + "epoch": 1.29, + "learning_rate": 2.905349794238683e-05, + "loss": 0.4628, "step": 1980 }, { - "epoch": 1.06, - "learning_rate": 2.98045486851457e-05, - "loss": 0.3932, + "epoch": 1.29, + "learning_rate": 2.903183885640026e-05, + "loss": 0.1889, "step": 1990 }, { - "epoch": 1.07, - "learning_rate": 2.978678038379531e-05, - "loss": 0.2931, + "epoch": 1.3, + "learning_rate": 2.901017977041369e-05, + "loss": 0.4129, "step": 2000 }, { - "epoch": 1.07, - "learning_rate": 2.9769012082444917e-05, - "loss": 0.4094, + "epoch": 1.31, + "learning_rate": 2.8988520684427118e-05, + "loss": 0.2512, "step": 2010 }, { - "epoch": 1.08, - "learning_rate": 2.975124378109453e-05, - "loss": 0.3642, + "epoch": 1.31, + "learning_rate": 2.8966861598440546e-05, + "loss": 0.3462, "step": 2020 }, { - "epoch": 1.08, - "learning_rate": 2.9733475479744138e-05, - "loss": 0.4747, + "epoch": 1.32, + "learning_rate": 2.8945202512453975e-05, + "loss": 0.2496, "step": 2030 }, { - "epoch": 1.09, - "learning_rate": 2.9715707178393748e-05, - "loss": 0.427, + "epoch": 1.33, + "learning_rate": 2.8923543426467404e-05, + "loss": 0.2584, "step": 2040 }, { - "epoch": 1.09, - "learning_rate": 2.9697938877043355e-05, - "loss": 0.3783, + "epoch": 1.33, + "learning_rate": 2.8901884340480832e-05, + "loss": 0.4408, "step": 2050 }, { - "epoch": 1.1, - "learning_rate": 2.968017057569296e-05, - "loss": 0.4015, + "epoch": 1.34, + "learning_rate": 2.888022525449426e-05, + "loss": 0.1791, "step": 2060 }, { - "epoch": 1.1, - "learning_rate": 2.9662402274342575e-05, - "loss": 0.2633, + "epoch": 1.34, + "learning_rate": 2.885856616850769e-05, + "loss": 0.2065, "step": 2070 }, { - "epoch": 1.11, - "learning_rate": 2.9644633972992182e-05, - "loss": 0.2845, + "epoch": 1.35, + "learning_rate": 2.883690708252112e-05, + "loss": 0.4957, "step": 2080 }, { - "epoch": 1.11, - "learning_rate": 2.9626865671641792e-05, - "loss": 0.5343, + "epoch": 1.36, + "learning_rate": 2.8815247996534547e-05, + "loss": 0.1517, "step": 2090 }, { - "epoch": 1.12, - "learning_rate": 2.96090973702914e-05, - "loss": 0.2071, + "epoch": 1.36, + "learning_rate": 2.8793588910547976e-05, + "loss": 0.2041, "step": 2100 }, { - "epoch": 1.12, - "learning_rate": 2.959132906894101e-05, - "loss": 0.2922, + "epoch": 1.37, + "learning_rate": 2.87719298245614e-05, + "loss": 0.2251, "step": 2110 }, { - "epoch": 1.13, - "learning_rate": 2.957356076759062e-05, - "loss": 0.3438, + "epoch": 1.38, + "learning_rate": 2.8750270738574833e-05, + "loss": 0.1827, "step": 2120 }, { - "epoch": 1.14, - "learning_rate": 2.955579246624023e-05, - "loss": 0.2972, + "epoch": 1.38, + "learning_rate": 2.8730777561186917e-05, + "loss": 0.1692, "step": 2130 }, { - "epoch": 1.14, - "learning_rate": 2.9538024164889837e-05, - "loss": 0.596, + "epoch": 1.39, + "learning_rate": 2.8709118475200346e-05, + "loss": 0.2938, "step": 2140 }, { - "epoch": 1.15, - "learning_rate": 2.9520255863539447e-05, - "loss": 0.1631, + "epoch": 1.4, + "learning_rate": 2.8687459389213774e-05, + "loss": 0.2557, "step": 2150 }, { - "epoch": 1.15, - "learning_rate": 2.9502487562189054e-05, - "loss": 0.2345, + "epoch": 1.4, + "learning_rate": 2.8665800303227203e-05, + "loss": 0.2886, "step": 2160 }, { - "epoch": 1.16, - "learning_rate": 2.9484719260838668e-05, - "loss": 0.3607, + "epoch": 1.41, + "learning_rate": 2.8644141217240635e-05, + "loss": 0.3589, "step": 2170 }, { - "epoch": 1.16, - "learning_rate": 2.9466950959488274e-05, - "loss": 0.4407, + "epoch": 1.42, + "learning_rate": 2.8622482131254064e-05, + "loss": 0.3187, "step": 2180 }, { - "epoch": 1.17, - "learning_rate": 2.9449182658137885e-05, - "loss": 0.2646, + "epoch": 1.42, + "learning_rate": 2.8600823045267492e-05, + "loss": 0.2109, "step": 2190 }, { - "epoch": 1.17, - "learning_rate": 2.943141435678749e-05, - "loss": 0.3628, + "epoch": 1.43, + "learning_rate": 2.857916395928092e-05, + "loss": 0.3777, "step": 2200 }, { - "epoch": 1.18, - "learning_rate": 2.94136460554371e-05, - "loss": 0.3069, + "epoch": 1.44, + "learning_rate": 2.8557504873294346e-05, + "loss": 0.3847, "step": 2210 }, { - "epoch": 1.18, - "learning_rate": 2.939587775408671e-05, - "loss": 0.2738, + "epoch": 1.44, + "learning_rate": 2.8535845787307775e-05, + "loss": 0.5642, "step": 2220 }, { - "epoch": 1.19, - "learning_rate": 2.937810945273632e-05, - "loss": 0.4837, + "epoch": 1.45, + "learning_rate": 2.8514186701321204e-05, + "loss": 0.3966, "step": 2230 }, { - "epoch": 1.19, - "learning_rate": 2.936034115138593e-05, - "loss": 0.3685, + "epoch": 1.46, + "learning_rate": 2.8492527615334633e-05, + "loss": 0.1387, "step": 2240 }, { - "epoch": 1.2, - "learning_rate": 2.9342572850035536e-05, - "loss": 0.4227, + "epoch": 1.46, + "learning_rate": 2.847086852934806e-05, + "loss": 0.3419, "step": 2250 }, { - "epoch": 1.2, - "learning_rate": 2.9324804548685146e-05, - "loss": 0.736, + "epoch": 1.47, + "learning_rate": 2.8449209443361493e-05, + "loss": 0.3061, "step": 2260 }, { - "epoch": 1.21, - "learning_rate": 2.9307036247334753e-05, - "loss": 0.4136, + "epoch": 1.47, + "learning_rate": 2.8427550357374922e-05, + "loss": 0.6589, "step": 2270 }, { - "epoch": 1.22, - "learning_rate": 2.9289267945984367e-05, - "loss": 0.5565, + "epoch": 1.48, + "learning_rate": 2.840589127138835e-05, + "loss": 0.2016, "step": 2280 }, { - "epoch": 1.22, - "learning_rate": 2.9271499644633974e-05, - "loss": 0.4989, + "epoch": 1.49, + "learning_rate": 2.8384232185401776e-05, + "loss": 0.2931, "step": 2290 }, { - "epoch": 1.23, - "learning_rate": 2.9253731343283584e-05, - "loss": 0.2447, + "epoch": 1.49, + "learning_rate": 2.8362573099415205e-05, + "loss": 0.2773, "step": 2300 }, { - "epoch": 1.23, - "learning_rate": 2.923596304193319e-05, - "loss": 0.4846, + "epoch": 1.5, + "learning_rate": 2.8340914013428633e-05, + "loss": 0.2194, "step": 2310 }, { - "epoch": 1.24, - "learning_rate": 2.92181947405828e-05, - "loss": 0.3211, + "epoch": 1.51, + "learning_rate": 2.8319254927442062e-05, + "loss": 0.2638, "step": 2320 }, { - "epoch": 1.24, - "learning_rate": 2.920042643923241e-05, - "loss": 0.6081, + "epoch": 1.51, + "learning_rate": 2.829759584145549e-05, + "loss": 0.3591, "step": 2330 }, { - "epoch": 1.25, - "learning_rate": 2.918265813788202e-05, - "loss": 0.6593, + "epoch": 1.52, + "learning_rate": 2.827593675546892e-05, + "loss": 0.2546, "step": 2340 }, { - "epoch": 1.25, - "learning_rate": 2.916488983653163e-05, - "loss": 0.8716, + "epoch": 1.53, + "learning_rate": 2.825427766948235e-05, + "loss": 0.3646, "step": 2350 }, { - "epoch": 1.26, - "learning_rate": 2.914712153518124e-05, - "loss": 0.6025, + "epoch": 1.53, + "learning_rate": 2.8232618583495777e-05, + "loss": 0.458, "step": 2360 }, { - "epoch": 1.26, - "learning_rate": 2.9129353233830846e-05, - "loss": 0.2675, + "epoch": 1.54, + "learning_rate": 2.8210959497509205e-05, + "loss": 0.313, "step": 2370 }, { - "epoch": 1.27, - "learning_rate": 2.9111584932480456e-05, - "loss": 0.3445, + "epoch": 1.55, + "learning_rate": 2.8189300411522634e-05, + "loss": 0.3892, "step": 2380 }, { - "epoch": 1.27, - "learning_rate": 2.9093816631130066e-05, - "loss": 0.3116, + "epoch": 1.55, + "learning_rate": 2.8167641325536063e-05, + "loss": 0.4741, "step": 2390 }, { - "epoch": 1.28, - "learning_rate": 2.9076048329779673e-05, - "loss": 0.3481, + "epoch": 1.56, + "learning_rate": 2.814598223954949e-05, + "loss": 0.2889, "step": 2400 }, { - "epoch": 1.28, - "learning_rate": 2.9058280028429283e-05, - "loss": 0.3075, + "epoch": 1.57, + "learning_rate": 2.812432315356292e-05, + "loss": 0.5176, "step": 2410 }, { - "epoch": 1.29, - "learning_rate": 2.904051172707889e-05, - "loss": 0.4335, + "epoch": 1.57, + "learning_rate": 2.810266406757635e-05, + "loss": 0.2147, "step": 2420 }, { - "epoch": 1.29, - "learning_rate": 2.90227434257285e-05, - "loss": 0.2051, + "epoch": 1.58, + "learning_rate": 2.8081004981589778e-05, + "loss": 0.1541, "step": 2430 }, { - "epoch": 1.3, - "learning_rate": 2.900497512437811e-05, - "loss": 0.0687, + "epoch": 1.58, + "learning_rate": 2.8059345895603206e-05, + "loss": 0.3722, "step": 2440 }, { - "epoch": 1.31, - "learning_rate": 2.898720682302772e-05, - "loss": 0.2879, + "epoch": 1.59, + "learning_rate": 2.8037686809616635e-05, + "loss": 0.1849, "step": 2450 }, { - "epoch": 1.31, - "learning_rate": 2.8969438521677328e-05, - "loss": 0.2775, + "epoch": 1.6, + "learning_rate": 2.8016027723630064e-05, + "loss": 0.3595, "step": 2460 }, { - "epoch": 1.32, - "learning_rate": 2.8951670220326938e-05, - "loss": 0.2486, + "epoch": 1.6, + "learning_rate": 2.7994368637643492e-05, + "loss": 0.2309, "step": 2470 }, { - "epoch": 1.32, - "learning_rate": 2.8933901918976545e-05, - "loss": 0.2891, + "epoch": 1.61, + "learning_rate": 2.797270955165692e-05, + "loss": 0.2493, "step": 2480 }, { - "epoch": 1.33, - "learning_rate": 2.891613361762616e-05, - "loss": 0.6512, + "epoch": 1.62, + "learning_rate": 2.795105046567035e-05, + "loss": 0.5766, "step": 2490 }, { - "epoch": 1.33, - "learning_rate": 2.8898365316275765e-05, - "loss": 0.3035, + "epoch": 1.62, + "learning_rate": 2.792939137968378e-05, + "loss": 0.4037, "step": 2500 }, { - "epoch": 1.34, - "learning_rate": 2.8880597014925376e-05, - "loss": 0.4896, + "epoch": 1.63, + "learning_rate": 2.7907732293697207e-05, + "loss": 0.4681, "step": 2510 }, { - "epoch": 1.34, - "learning_rate": 2.8862828713574982e-05, - "loss": 0.3122, + "epoch": 1.64, + "learning_rate": 2.7886073207710632e-05, + "loss": 0.1419, "step": 2520 }, { - "epoch": 1.35, - "learning_rate": 2.884506041222459e-05, - "loss": 0.6072, + "epoch": 1.64, + "learning_rate": 2.7864414121724064e-05, + "loss": 0.477, "step": 2530 }, { - "epoch": 1.35, - "learning_rate": 2.8827292110874203e-05, - "loss": 0.3115, + "epoch": 1.65, + "learning_rate": 2.7842755035737493e-05, + "loss": 0.4341, "step": 2540 }, { - "epoch": 1.36, - "learning_rate": 2.880952380952381e-05, - "loss": 0.3176, + "epoch": 1.66, + "learning_rate": 2.7821095949750922e-05, + "loss": 0.2381, "step": 2550 }, { - "epoch": 1.36, - "learning_rate": 2.879175550817342e-05, - "loss": 0.1757, + "epoch": 1.66, + "learning_rate": 2.779943686376435e-05, + "loss": 0.302, "step": 2560 }, { - "epoch": 1.37, - "learning_rate": 2.8773987206823027e-05, - "loss": 0.4121, + "epoch": 1.67, + "learning_rate": 2.777777777777778e-05, + "loss": 0.2982, "step": 2570 }, { - "epoch": 1.37, - "learning_rate": 2.8756218905472637e-05, - "loss": 0.636, + "epoch": 1.68, + "learning_rate": 2.7756118691791208e-05, + "loss": 0.4892, "step": 2580 }, { - "epoch": 1.38, - "learning_rate": 2.8738450604122244e-05, - "loss": 0.6732, + "epoch": 1.68, + "learning_rate": 2.7734459605804636e-05, + "loss": 0.3519, "step": 2590 }, { - "epoch": 1.39, - "learning_rate": 2.8720682302771858e-05, - "loss": 0.3316, + "epoch": 1.69, + "learning_rate": 2.7712800519818062e-05, + "loss": 0.207, "step": 2600 }, { - "epoch": 1.39, - "learning_rate": 2.8702914001421464e-05, - "loss": 0.2115, + "epoch": 1.7, + "learning_rate": 2.769114143383149e-05, + "loss": 0.1381, "step": 2610 }, { - "epoch": 1.4, - "learning_rate": 2.8685145700071075e-05, - "loss": 0.364, + "epoch": 1.7, + "learning_rate": 2.7669482347844923e-05, + "loss": 0.3716, "step": 2620 }, { - "epoch": 1.4, - "learning_rate": 2.866737739872068e-05, - "loss": 0.2027, + "epoch": 1.71, + "learning_rate": 2.764782326185835e-05, + "loss": 0.4123, "step": 2630 }, { - "epoch": 1.41, - "learning_rate": 2.8649609097370292e-05, - "loss": 0.6881, + "epoch": 1.71, + "learning_rate": 2.762616417587178e-05, + "loss": 0.2551, "step": 2640 }, { - "epoch": 1.41, - "learning_rate": 2.8631840796019902e-05, - "loss": 0.4449, + "epoch": 1.72, + "learning_rate": 2.760450508988521e-05, + "loss": 0.2666, "step": 2650 }, { - "epoch": 1.42, - "learning_rate": 2.8614072494669512e-05, - "loss": 0.4018, + "epoch": 1.73, + "learning_rate": 2.7582846003898637e-05, + "loss": 0.1336, "step": 2660 }, { - "epoch": 1.42, - "learning_rate": 2.859630419331912e-05, - "loss": 0.3296, + "epoch": 1.73, + "learning_rate": 2.7561186917912066e-05, + "loss": 0.5134, "step": 2670 }, { - "epoch": 1.43, - "learning_rate": 2.857853589196873e-05, - "loss": 0.4931, + "epoch": 1.74, + "learning_rate": 2.753952783192549e-05, + "loss": 0.2047, "step": 2680 }, { - "epoch": 1.43, - "learning_rate": 2.8560767590618336e-05, - "loss": 0.6511, + "epoch": 1.75, + "learning_rate": 2.751786874593892e-05, + "loss": 0.2533, "step": 2690 }, { - "epoch": 1.44, - "learning_rate": 2.8542999289267947e-05, - "loss": 0.4979, + "epoch": 1.75, + "learning_rate": 2.749620965995235e-05, + "loss": 0.0704, "step": 2700 }, { - "epoch": 1.44, - "learning_rate": 2.8525230987917557e-05, - "loss": 0.5411, + "epoch": 1.76, + "learning_rate": 2.747455057396578e-05, + "loss": 0.269, "step": 2710 }, { - "epoch": 1.45, - "learning_rate": 2.8507462686567164e-05, - "loss": 0.4014, + "epoch": 1.77, + "learning_rate": 2.745289148797921e-05, + "loss": 0.1492, "step": 2720 }, { - "epoch": 1.45, - "learning_rate": 2.8489694385216774e-05, - "loss": 0.5477, + "epoch": 1.77, + "learning_rate": 2.7431232401992638e-05, + "loss": 0.1962, "step": 2730 }, { - "epoch": 1.46, - "learning_rate": 2.847192608386638e-05, - "loss": 0.2564, + "epoch": 1.78, + "learning_rate": 2.7409573316006067e-05, + "loss": 0.251, "step": 2740 }, { - "epoch": 1.47, - "learning_rate": 2.8454157782515994e-05, - "loss": 0.3324, + "epoch": 1.79, + "learning_rate": 2.7387914230019495e-05, + "loss": 0.5038, "step": 2750 }, { - "epoch": 1.47, - "learning_rate": 2.84363894811656e-05, - "loss": 0.7454, + "epoch": 1.79, + "learning_rate": 2.736625514403292e-05, + "loss": 0.0198, "step": 2760 }, { - "epoch": 1.48, - "learning_rate": 2.841862117981521e-05, - "loss": 0.284, + "epoch": 1.8, + "learning_rate": 2.734459605804635e-05, + "loss": 0.3041, "step": 2770 }, { - "epoch": 1.48, - "learning_rate": 2.840085287846482e-05, - "loss": 0.2923, + "epoch": 1.81, + "learning_rate": 2.7322936972059778e-05, + "loss": 0.3146, "step": 2780 }, { - "epoch": 1.49, - "learning_rate": 2.838308457711443e-05, - "loss": 0.3171, + "epoch": 1.81, + "learning_rate": 2.7301277886073207e-05, + "loss": 0.2433, "step": 2790 }, { - "epoch": 1.49, - "learning_rate": 2.8365316275764036e-05, - "loss": 0.3749, + "epoch": 1.82, + "learning_rate": 2.727961880008664e-05, + "loss": 0.5248, "step": 2800 }, { - "epoch": 1.5, - "learning_rate": 2.834754797441365e-05, - "loss": 0.5322, + "epoch": 1.83, + "learning_rate": 2.7257959714100068e-05, + "loss": 0.2415, "step": 2810 }, { - "epoch": 1.5, - "learning_rate": 2.8329779673063256e-05, - "loss": 0.0936, + "epoch": 1.83, + "learning_rate": 2.7236300628113496e-05, + "loss": 0.3897, "step": 2820 }, { - "epoch": 1.51, - "learning_rate": 2.8312011371712866e-05, - "loss": 0.5951, + "epoch": 1.84, + "learning_rate": 2.7214641542126925e-05, + "loss": 0.4774, "step": 2830 }, { - "epoch": 1.51, - "learning_rate": 2.8294243070362473e-05, - "loss": 0.2392, + "epoch": 1.84, + "learning_rate": 2.719298245614035e-05, + "loss": 0.1535, "step": 2840 }, { - "epoch": 1.52, - "learning_rate": 2.827647476901208e-05, - "loss": 0.4549, + "epoch": 1.85, + "learning_rate": 2.717132337015378e-05, + "loss": 0.7375, "step": 2850 }, { - "epoch": 1.52, - "learning_rate": 2.8258706467661694e-05, - "loss": 0.2078, + "epoch": 1.86, + "learning_rate": 2.7149664284167208e-05, + "loss": 0.3043, "step": 2860 }, { - "epoch": 1.53, - "learning_rate": 2.82409381663113e-05, - "loss": 0.4162, + "epoch": 1.86, + "learning_rate": 2.7128005198180636e-05, + "loss": 0.1723, "step": 2870 }, { - "epoch": 1.53, - "learning_rate": 2.822316986496091e-05, - "loss": 0.4833, + "epoch": 1.87, + "learning_rate": 2.7106346112194065e-05, + "loss": 0.2247, "step": 2880 }, { - "epoch": 1.54, - "learning_rate": 2.8205401563610518e-05, - "loss": 0.4599, + "epoch": 1.88, + "learning_rate": 2.7084687026207497e-05, + "loss": 0.4143, "step": 2890 }, { - "epoch": 1.55, - "learning_rate": 2.8187633262260128e-05, - "loss": 0.6298, + "epoch": 1.88, + "learning_rate": 2.7063027940220926e-05, + "loss": 0.3145, "step": 2900 }, { - "epoch": 1.55, - "learning_rate": 2.8169864960909738e-05, - "loss": 0.5949, + "epoch": 1.89, + "learning_rate": 2.7041368854234354e-05, + "loss": 0.2796, "step": 2910 }, { - "epoch": 1.56, - "learning_rate": 2.815209665955935e-05, - "loss": 0.2518, + "epoch": 1.9, + "learning_rate": 2.701970976824778e-05, + "loss": 0.1485, "step": 2920 }, { - "epoch": 1.56, - "learning_rate": 2.8134328358208955e-05, - "loss": 0.3632, + "epoch": 1.9, + "learning_rate": 2.699805068226121e-05, + "loss": 0.3664, "step": 2930 }, { - "epoch": 1.57, - "learning_rate": 2.8116560056858566e-05, - "loss": 0.2924, + "epoch": 1.91, + "learning_rate": 2.6976391596274637e-05, + "loss": 0.298, "step": 2940 }, { - "epoch": 1.57, - "learning_rate": 2.8098791755508172e-05, - "loss": 0.2415, + "epoch": 1.92, + "learning_rate": 2.6954732510288066e-05, + "loss": 0.5404, "step": 2950 }, { - "epoch": 1.58, - "learning_rate": 2.8081023454157786e-05, - "loss": 0.2295, + "epoch": 1.92, + "learning_rate": 2.6933073424301494e-05, + "loss": 0.0554, "step": 2960 }, { - "epoch": 1.58, - "learning_rate": 2.8063255152807393e-05, - "loss": 0.3128, + "epoch": 1.93, + "learning_rate": 2.6911414338314923e-05, + "loss": 0.3279, "step": 2970 }, { - "epoch": 1.59, - "learning_rate": 2.8045486851457003e-05, - "loss": 0.4105, + "epoch": 1.94, + "learning_rate": 2.6889755252328355e-05, + "loss": 0.2289, "step": 2980 }, { - "epoch": 1.59, - "learning_rate": 2.802771855010661e-05, - "loss": 0.4731, + "epoch": 1.94, + "learning_rate": 2.6868096166341784e-05, + "loss": 0.257, "step": 2990 }, { - "epoch": 1.6, - "learning_rate": 2.800995024875622e-05, - "loss": 0.5216, + "epoch": 1.95, + "learning_rate": 2.684643708035521e-05, + "loss": 0.5012, "step": 3000 }, { - "epoch": 1.6, - "learning_rate": 2.7992181947405827e-05, - "loss": 0.4589, + "epoch": 1.96, + "learning_rate": 2.6824777994368638e-05, + "loss": 0.2418, "step": 3010 }, { - "epoch": 1.61, - "learning_rate": 2.7974413646055437e-05, - "loss": 0.3216, + "epoch": 1.96, + "learning_rate": 2.6803118908382067e-05, + "loss": 0.0826, "step": 3020 }, { - "epoch": 1.61, - "learning_rate": 2.7956645344705048e-05, - "loss": 0.3218, + "epoch": 1.97, + "learning_rate": 2.6781459822395495e-05, + "loss": 0.204, "step": 3030 }, { - "epoch": 1.62, - "learning_rate": 2.7938877043354655e-05, - "loss": 0.3906, + "epoch": 1.97, + "learning_rate": 2.6759800736408924e-05, + "loss": 0.2902, "step": 3040 }, { - "epoch": 1.63, - "learning_rate": 2.7921108742004265e-05, - "loss": 0.572, + "epoch": 1.98, + "learning_rate": 2.6738141650422353e-05, + "loss": 0.3245, "step": 3050 }, { - "epoch": 1.63, - "learning_rate": 2.790334044065387e-05, - "loss": 0.33, + "epoch": 1.99, + "learning_rate": 2.671648256443578e-05, + "loss": 0.3886, "step": 3060 }, { - "epoch": 1.64, - "learning_rate": 2.7885572139303485e-05, - "loss": 0.4896, + "epoch": 1.99, + "learning_rate": 2.6694823478449213e-05, + "loss": 0.1232, "step": 3070 }, { - "epoch": 1.64, - "learning_rate": 2.7867803837953092e-05, - "loss": 0.1846, + "epoch": 2.0, + "eval_accuracy": 0.9655013799448022, + "eval_loss": 0.1605590134859085, + "eval_runtime": 12.979, + "eval_samples_per_second": 167.501, + "eval_steps_per_second": 41.914, + "step": 3079 + }, + { + "epoch": 2.0, + "learning_rate": 2.667316439246264e-05, + "loss": 0.1282, "step": 3080 }, { - "epoch": 1.65, - "learning_rate": 2.7850035536602702e-05, - "loss": 0.5928, + "epoch": 2.01, + "learning_rate": 2.6651505306476067e-05, + "loss": 0.4082, "step": 3090 }, { - "epoch": 1.65, - "learning_rate": 2.783226723525231e-05, - "loss": 0.3942, + "epoch": 2.01, + "learning_rate": 2.6629846220489496e-05, + "loss": 0.5166, "step": 3100 }, { - "epoch": 1.66, - "learning_rate": 2.781449893390192e-05, - "loss": 0.2997, + "epoch": 2.02, + "learning_rate": 2.6608187134502925e-05, + "loss": 0.3364, "step": 3110 }, { - "epoch": 1.66, - "learning_rate": 2.779673063255153e-05, - "loss": 0.4637, + "epoch": 2.03, + "learning_rate": 2.6586528048516353e-05, + "loss": 0.2218, "step": 3120 }, { - "epoch": 1.67, - "learning_rate": 2.777896233120114e-05, - "loss": 0.2947, + "epoch": 2.03, + "learning_rate": 2.6564868962529782e-05, + "loss": 0.285, "step": 3130 }, { - "epoch": 1.67, - "learning_rate": 2.7761194029850747e-05, - "loss": 0.3761, + "epoch": 2.04, + "learning_rate": 2.654320987654321e-05, + "loss": 0.214, "step": 3140 }, { - "epoch": 1.68, - "learning_rate": 2.7743425728500357e-05, - "loss": 0.351, + "epoch": 2.05, + "learning_rate": 2.652155079055664e-05, + "loss": 0.547, "step": 3150 }, { - "epoch": 1.68, - "learning_rate": 2.7725657427149964e-05, - "loss": 0.3805, + "epoch": 2.05, + "learning_rate": 2.6499891704570065e-05, + "loss": 0.2743, "step": 3160 }, { - "epoch": 1.69, - "learning_rate": 2.7707889125799574e-05, - "loss": 0.3571, + "epoch": 2.06, + "learning_rate": 2.6478232618583497e-05, + "loss": 0.4205, "step": 3170 }, { - "epoch": 1.69, - "learning_rate": 2.7690120824449184e-05, - "loss": 0.4481, + "epoch": 2.07, + "learning_rate": 2.6456573532596926e-05, + "loss": 0.1901, "step": 3180 }, { - "epoch": 1.7, - "learning_rate": 2.767235252309879e-05, - "loss": 0.226, + "epoch": 2.07, + "learning_rate": 2.6434914446610354e-05, + "loss": 0.1482, "step": 3190 }, { - "epoch": 1.71, - "learning_rate": 2.76545842217484e-05, - "loss": 0.229, + "epoch": 2.08, + "learning_rate": 2.6413255360623783e-05, + "loss": 0.1439, "step": 3200 }, { - "epoch": 1.71, - "learning_rate": 2.763681592039801e-05, - "loss": 0.4969, + "epoch": 2.09, + "learning_rate": 2.639159627463721e-05, + "loss": 0.3271, "step": 3210 }, { - "epoch": 1.72, - "learning_rate": 2.761904761904762e-05, - "loss": 0.5304, + "epoch": 2.09, + "learning_rate": 2.636993718865064e-05, + "loss": 0.237, "step": 3220 }, { - "epoch": 1.72, - "learning_rate": 2.760127931769723e-05, - "loss": 0.4931, + "epoch": 2.1, + "learning_rate": 2.634827810266407e-05, + "loss": 0.3626, "step": 3230 }, { - "epoch": 1.73, - "learning_rate": 2.758351101634684e-05, - "loss": 0.4967, + "epoch": 2.1, + "learning_rate": 2.6326619016677494e-05, + "loss": 0.2673, "step": 3240 }, { - "epoch": 1.73, - "learning_rate": 2.7565742714996446e-05, - "loss": 0.3188, + "epoch": 2.11, + "learning_rate": 2.6304959930690923e-05, + "loss": 0.0236, "step": 3250 }, { - "epoch": 1.74, - "learning_rate": 2.7547974413646056e-05, - "loss": 0.4646, + "epoch": 2.12, + "learning_rate": 2.6283300844704355e-05, + "loss": 0.3381, "step": 3260 }, { - "epoch": 1.74, - "learning_rate": 2.7530206112295663e-05, - "loss": 0.374, + "epoch": 2.12, + "learning_rate": 2.6261641758717784e-05, + "loss": 0.0661, "step": 3270 }, { - "epoch": 1.75, - "learning_rate": 2.7512437810945277e-05, - "loss": 0.2473, + "epoch": 2.13, + "learning_rate": 2.6239982672731212e-05, + "loss": 0.4211, "step": 3280 }, { - "epoch": 1.75, - "learning_rate": 2.7494669509594884e-05, - "loss": 0.2488, + "epoch": 2.14, + "learning_rate": 2.621832358674464e-05, + "loss": 0.3107, "step": 3290 }, { - "epoch": 1.76, - "learning_rate": 2.7476901208244494e-05, - "loss": 0.3767, + "epoch": 2.14, + "learning_rate": 2.619666450075807e-05, + "loss": 0.3576, "step": 3300 }, { - "epoch": 1.76, - "learning_rate": 2.74591329068941e-05, - "loss": 0.6614, + "epoch": 2.15, + "learning_rate": 2.61750054147715e-05, + "loss": 0.4687, "step": 3310 }, { - "epoch": 1.77, - "learning_rate": 2.744136460554371e-05, - "loss": 0.4683, + "epoch": 2.16, + "learning_rate": 2.6153346328784924e-05, + "loss": 0.1991, "step": 3320 }, { - "epoch": 1.77, - "learning_rate": 2.742359630419332e-05, - "loss": 0.3721, + "epoch": 2.16, + "learning_rate": 2.6131687242798352e-05, + "loss": 0.5119, "step": 3330 }, { - "epoch": 1.78, - "learning_rate": 2.7405828002842928e-05, - "loss": 0.3377, + "epoch": 2.17, + "learning_rate": 2.611002815681178e-05, + "loss": 0.1439, "step": 3340 }, { - "epoch": 1.79, - "learning_rate": 2.738805970149254e-05, - "loss": 0.4619, + "epoch": 2.18, + "learning_rate": 2.6088369070825213e-05, + "loss": 0.29, "step": 3350 }, { - "epoch": 1.79, - "learning_rate": 2.7370291400142145e-05, - "loss": 0.5428, + "epoch": 2.18, + "learning_rate": 2.6066709984838642e-05, + "loss": 0.1705, "step": 3360 }, { - "epoch": 1.8, - "learning_rate": 2.7352523098791756e-05, - "loss": 0.4121, + "epoch": 2.19, + "learning_rate": 2.604505089885207e-05, + "loss": 0.1561, "step": 3370 }, { - "epoch": 1.8, - "learning_rate": 2.7334754797441366e-05, - "loss": 0.5911, + "epoch": 2.2, + "learning_rate": 2.60233918128655e-05, + "loss": 0.5298, "step": 3380 }, { - "epoch": 1.81, - "learning_rate": 2.7316986496090976e-05, - "loss": 0.4393, + "epoch": 2.2, + "learning_rate": 2.6001732726878928e-05, + "loss": 0.2279, "step": 3390 }, { - "epoch": 1.81, - "learning_rate": 2.7299218194740583e-05, - "loss": 0.5108, + "epoch": 2.21, + "learning_rate": 2.5980073640892353e-05, + "loss": 0.1045, "step": 3400 }, { - "epoch": 1.82, - "learning_rate": 2.7281449893390193e-05, - "loss": 0.4665, + "epoch": 2.22, + "learning_rate": 2.5958414554905782e-05, + "loss": 0.2926, "step": 3410 }, { - "epoch": 1.82, - "learning_rate": 2.72636815920398e-05, - "loss": 0.496, + "epoch": 2.22, + "learning_rate": 2.593675546891921e-05, + "loss": 0.1234, "step": 3420 }, { - "epoch": 1.83, - "learning_rate": 2.724591329068941e-05, - "loss": 0.419, + "epoch": 2.23, + "learning_rate": 2.591509638293264e-05, + "loss": 0.4732, "step": 3430 }, { - "epoch": 1.83, - "learning_rate": 2.722814498933902e-05, - "loss": 0.4942, + "epoch": 2.23, + "learning_rate": 2.589343729694607e-05, + "loss": 0.2754, "step": 3440 }, { - "epoch": 1.84, - "learning_rate": 2.721037668798863e-05, - "loss": 0.2264, + "epoch": 2.24, + "learning_rate": 2.58717782109595e-05, + "loss": 0.3542, "step": 3450 }, { - "epoch": 1.84, - "learning_rate": 2.7192608386638238e-05, - "loss": 0.5141, + "epoch": 2.25, + "learning_rate": 2.585011912497293e-05, + "loss": 0.5329, "step": 3460 }, { - "epoch": 1.85, - "learning_rate": 2.7174840085287848e-05, - "loss": 0.3937, + "epoch": 2.25, + "learning_rate": 2.5828460038986354e-05, + "loss": 0.2176, "step": 3470 }, { - "epoch": 1.85, - "learning_rate": 2.7157071783937455e-05, - "loss": 0.3538, + "epoch": 2.26, + "learning_rate": 2.5806800952999783e-05, + "loss": 0.1245, "step": 3480 }, { - "epoch": 1.86, - "learning_rate": 2.7139303482587065e-05, - "loss": 0.2969, + "epoch": 2.27, + "learning_rate": 2.578514186701321e-05, + "loss": 0.1505, "step": 3490 }, { - "epoch": 1.87, - "learning_rate": 2.7121535181236675e-05, - "loss": 0.3139, + "epoch": 2.27, + "learning_rate": 2.576348278102664e-05, + "loss": 0.5114, "step": 3500 }, { - "epoch": 1.87, - "learning_rate": 2.7103766879886282e-05, - "loss": 0.5682, + "epoch": 2.28, + "learning_rate": 2.574182369504007e-05, + "loss": 0.2739, "step": 3510 }, { - "epoch": 1.88, - "learning_rate": 2.7085998578535892e-05, - "loss": 0.3292, + "epoch": 2.29, + "learning_rate": 2.5720164609053497e-05, + "loss": 0.4071, "step": 3520 }, { - "epoch": 1.88, - "learning_rate": 2.70682302771855e-05, - "loss": 0.2673, + "epoch": 2.29, + "learning_rate": 2.569850552306693e-05, + "loss": 0.1159, "step": 3530 }, { - "epoch": 1.89, - "learning_rate": 2.7050461975835113e-05, - "loss": 0.3756, + "epoch": 2.3, + "learning_rate": 2.5676846437080358e-05, + "loss": 0.3694, "step": 3540 }, { - "epoch": 1.89, - "learning_rate": 2.703269367448472e-05, - "loss": 0.4084, + "epoch": 2.31, + "learning_rate": 2.5655187351093783e-05, + "loss": 0.4572, "step": 3550 }, { - "epoch": 1.9, - "learning_rate": 2.701492537313433e-05, - "loss": 0.7091, + "epoch": 2.31, + "learning_rate": 2.5633528265107212e-05, + "loss": 0.2517, "step": 3560 }, { - "epoch": 1.9, - "learning_rate": 2.6997157071783937e-05, - "loss": 0.3652, + "epoch": 2.32, + "learning_rate": 2.561186917912064e-05, + "loss": 0.1947, "step": 3570 }, { - "epoch": 1.91, - "learning_rate": 2.6979388770433547e-05, - "loss": 0.2793, + "epoch": 2.33, + "learning_rate": 2.559021009313407e-05, + "loss": 0.2947, "step": 3580 }, { - "epoch": 1.91, - "learning_rate": 2.6961620469083154e-05, - "loss": 0.3673, + "epoch": 2.33, + "learning_rate": 2.5568551007147498e-05, + "loss": 0.1922, "step": 3590 }, { - "epoch": 1.92, - "learning_rate": 2.6943852167732768e-05, - "loss": 0.3701, + "epoch": 2.34, + "learning_rate": 2.5546891921160927e-05, + "loss": 0.3169, "step": 3600 }, { - "epoch": 1.92, - "learning_rate": 2.6926083866382375e-05, - "loss": 0.2466, + "epoch": 2.34, + "learning_rate": 2.5525232835174356e-05, + "loss": 0.065, "step": 3610 }, { - "epoch": 1.93, - "learning_rate": 2.6908315565031985e-05, - "loss": 0.379, + "epoch": 2.35, + "learning_rate": 2.5503573749187788e-05, + "loss": 0.4879, "step": 3620 }, { - "epoch": 1.93, - "learning_rate": 2.689054726368159e-05, - "loss": 0.2436, + "epoch": 2.36, + "learning_rate": 2.5481914663201213e-05, + "loss": 0.1695, "step": 3630 }, { - "epoch": 1.94, - "learning_rate": 2.6872778962331202e-05, - "loss": 0.3154, + "epoch": 2.36, + "learning_rate": 2.546025557721464e-05, + "loss": 0.381, "step": 3640 }, { - "epoch": 1.95, - "learning_rate": 2.6855010660980812e-05, - "loss": 0.4635, + "epoch": 2.37, + "learning_rate": 2.543859649122807e-05, + "loss": 0.2645, "step": 3650 }, { - "epoch": 1.95, - "learning_rate": 2.683724235963042e-05, - "loss": 0.435, + "epoch": 2.38, + "learning_rate": 2.54169374052415e-05, + "loss": 0.2559, "step": 3660 }, { - "epoch": 1.96, - "learning_rate": 2.681947405828003e-05, - "loss": 0.1998, + "epoch": 2.38, + "learning_rate": 2.5395278319254928e-05, + "loss": 0.0956, "step": 3670 }, { - "epoch": 1.96, - "learning_rate": 2.6801705756929636e-05, - "loss": 0.3749, + "epoch": 2.39, + "learning_rate": 2.5373619233268356e-05, + "loss": 0.3473, "step": 3680 }, { - "epoch": 1.97, - "learning_rate": 2.6783937455579246e-05, - "loss": 0.3891, + "epoch": 2.4, + "learning_rate": 2.5351960147281785e-05, + "loss": 0.25, "step": 3690 }, { - "epoch": 1.97, - "learning_rate": 2.6766169154228857e-05, - "loss": 0.3205, + "epoch": 2.4, + "learning_rate": 2.5330301061295214e-05, + "loss": 0.3441, "step": 3700 }, { - "epoch": 1.98, - "learning_rate": 2.6748400852878467e-05, - "loss": 0.3229, + "epoch": 2.41, + "learning_rate": 2.5308641975308642e-05, + "loss": 0.2912, "step": 3710 }, { - "epoch": 1.98, - "learning_rate": 2.6730632551528074e-05, - "loss": 0.2826, + "epoch": 2.42, + "learning_rate": 2.528698288932207e-05, + "loss": 0.2895, "step": 3720 }, { - "epoch": 1.99, - "learning_rate": 2.6714641080312722e-05, - "loss": 0.2948, + "epoch": 2.42, + "learning_rate": 2.52653238033355e-05, + "loss": 0.1336, "step": 3730 }, { - "epoch": 1.99, - "learning_rate": 2.6696872778962332e-05, - "loss": 0.3957, + "epoch": 2.43, + "learning_rate": 2.524366471734893e-05, + "loss": 0.1, "step": 3740 }, { - "epoch": 2.0, - "learning_rate": 2.6679104477611942e-05, - "loss": 0.447, + "epoch": 2.44, + "learning_rate": 2.5222005631362357e-05, + "loss": 0.0469, "step": 3750 }, { - "epoch": 2.0, - "eval_accuracy": 0.9584748961872405, - "eval_loss": 0.1568232774734497, - "eval_runtime": 10.7466, - "eval_samples_per_second": 246.497, - "eval_steps_per_second": 61.694, - "step": 3753 - }, - { - "epoch": 2.0, - "learning_rate": 2.666133617626155e-05, - "loss": 0.2629, + "epoch": 2.44, + "learning_rate": 2.5200346545375786e-05, + "loss": 0.1433, "step": 3760 }, { - "epoch": 2.01, - "learning_rate": 2.664356787491116e-05, - "loss": 0.3573, + "epoch": 2.45, + "learning_rate": 2.5178687459389215e-05, + "loss": 0.1602, "step": 3770 }, { - "epoch": 2.01, - "learning_rate": 2.6625799573560766e-05, - "loss": 0.1743, + "epoch": 2.46, + "learning_rate": 2.5157028373402643e-05, + "loss": 0.3086, "step": 3780 }, { - "epoch": 2.02, - "learning_rate": 2.6608031272210377e-05, - "loss": 0.1252, + "epoch": 2.46, + "learning_rate": 2.513536928741607e-05, + "loss": 0.112, "step": 3790 }, { - "epoch": 2.03, - "learning_rate": 2.6590262970859987e-05, - "loss": 0.3568, + "epoch": 2.47, + "learning_rate": 2.51137102014295e-05, + "loss": 0.3675, "step": 3800 }, { - "epoch": 2.03, - "learning_rate": 2.6572494669509597e-05, - "loss": 0.4184, + "epoch": 2.47, + "learning_rate": 2.509205111544293e-05, + "loss": 0.1579, "step": 3810 }, { - "epoch": 2.04, - "learning_rate": 2.6554726368159204e-05, - "loss": 0.247, + "epoch": 2.48, + "learning_rate": 2.5070392029456358e-05, + "loss": 0.3057, "step": 3820 }, { - "epoch": 2.04, - "learning_rate": 2.6536958066808814e-05, - "loss": 0.1238, + "epoch": 2.49, + "learning_rate": 2.5048732943469787e-05, + "loss": 0.3646, "step": 3830 }, { - "epoch": 2.05, - "learning_rate": 2.651918976545842e-05, - "loss": 0.479, + "epoch": 2.49, + "learning_rate": 2.5027073857483215e-05, + "loss": 0.2384, "step": 3840 }, { - "epoch": 2.05, - "learning_rate": 2.6501421464108035e-05, - "loss": 0.3238, + "epoch": 2.5, + "learning_rate": 2.5005414771496644e-05, + "loss": 0.3239, "step": 3850 }, { - "epoch": 2.06, - "learning_rate": 2.648365316275764e-05, - "loss": 0.4551, + "epoch": 2.51, + "learning_rate": 2.4983755685510073e-05, + "loss": 0.2883, "step": 3860 }, { - "epoch": 2.06, - "learning_rate": 2.646588486140725e-05, - "loss": 0.2478, + "epoch": 2.51, + "learning_rate": 2.4962096599523498e-05, + "loss": 0.2288, "step": 3870 }, { - "epoch": 2.07, - "learning_rate": 2.644811656005686e-05, - "loss": 0.3987, + "epoch": 2.52, + "learning_rate": 2.4940437513536927e-05, + "loss": 0.3717, "step": 3880 }, { - "epoch": 2.07, - "learning_rate": 2.6430348258706466e-05, - "loss": 0.3796, + "epoch": 2.53, + "learning_rate": 2.491877842755036e-05, + "loss": 0.2852, "step": 3890 }, { - "epoch": 2.08, - "learning_rate": 2.641257995735608e-05, - "loss": 0.2588, + "epoch": 2.53, + "learning_rate": 2.4897119341563787e-05, + "loss": 0.6269, "step": 3900 }, { - "epoch": 2.08, - "learning_rate": 2.6394811656005686e-05, - "loss": 0.4075, + "epoch": 2.54, + "learning_rate": 2.4875460255577216e-05, + "loss": 0.2522, "step": 3910 }, { - "epoch": 2.09, - "learning_rate": 2.6377043354655296e-05, - "loss": 0.6444, + "epoch": 2.55, + "learning_rate": 2.4853801169590645e-05, + "loss": 0.3426, "step": 3920 }, { - "epoch": 2.09, - "learning_rate": 2.6359275053304903e-05, - "loss": 0.1015, + "epoch": 2.55, + "learning_rate": 2.4832142083604074e-05, + "loss": 0.2613, "step": 3930 }, { - "epoch": 2.1, - "learning_rate": 2.6341506751954514e-05, - "loss": 0.1624, + "epoch": 2.56, + "learning_rate": 2.4810482997617502e-05, + "loss": 0.3396, "step": 3940 }, { - "epoch": 2.1, - "learning_rate": 2.6323738450604124e-05, - "loss": 0.1836, + "epoch": 2.57, + "learning_rate": 2.4788823911630927e-05, + "loss": 0.225, "step": 3950 }, { - "epoch": 2.11, - "learning_rate": 2.6305970149253734e-05, - "loss": 0.2531, + "epoch": 2.57, + "learning_rate": 2.4767164825644356e-05, + "loss": 0.204, "step": 3960 }, { - "epoch": 2.12, - "learning_rate": 2.628820184790334e-05, - "loss": 0.6271, + "epoch": 2.58, + "learning_rate": 2.4745505739657785e-05, + "loss": 0.6812, "step": 3970 }, { - "epoch": 2.12, - "learning_rate": 2.627043354655295e-05, - "loss": 0.4676, + "epoch": 2.59, + "learning_rate": 2.4723846653671217e-05, + "loss": 0.5684, "step": 3980 }, { - "epoch": 2.13, - "learning_rate": 2.6252665245202558e-05, - "loss": 0.2724, + "epoch": 2.59, + "learning_rate": 2.4702187567684646e-05, + "loss": 0.1882, "step": 3990 }, { - "epoch": 2.13, - "learning_rate": 2.6234896943852168e-05, - "loss": 0.2754, + "epoch": 2.6, + "learning_rate": 2.4680528481698074e-05, + "loss": 0.2217, "step": 4000 }, { - "epoch": 2.14, - "learning_rate": 2.621712864250178e-05, - "loss": 0.3638, + "epoch": 2.6, + "learning_rate": 2.4658869395711503e-05, + "loss": 0.0704, "step": 4010 }, { - "epoch": 2.14, - "learning_rate": 2.619936034115139e-05, - "loss": 0.1941, + "epoch": 2.61, + "learning_rate": 2.463721030972493e-05, + "loss": 0.3599, "step": 4020 }, { - "epoch": 2.15, - "learning_rate": 2.6181592039800996e-05, - "loss": 0.2583, + "epoch": 2.62, + "learning_rate": 2.4615551223738357e-05, + "loss": 0.2779, "step": 4030 }, { - "epoch": 2.15, - "learning_rate": 2.6163823738450603e-05, - "loss": 0.3515, + "epoch": 2.62, + "learning_rate": 2.4593892137751786e-05, + "loss": 0.4508, "step": 4040 }, { - "epoch": 2.16, - "learning_rate": 2.6146055437100213e-05, - "loss": 0.356, + "epoch": 2.63, + "learning_rate": 2.4572233051765214e-05, + "loss": 0.3388, "step": 4050 }, { - "epoch": 2.16, - "learning_rate": 2.6128287135749823e-05, - "loss": 0.3024, + "epoch": 2.64, + "learning_rate": 2.4550573965778643e-05, + "loss": 0.3605, "step": 4060 }, { - "epoch": 2.17, - "learning_rate": 2.6110518834399433e-05, - "loss": 0.1204, + "epoch": 2.64, + "learning_rate": 2.4528914879792075e-05, + "loss": 0.3589, "step": 4070 }, { - "epoch": 2.17, - "learning_rate": 2.609275053304904e-05, - "loss": 0.2978, + "epoch": 2.65, + "learning_rate": 2.4507255793805504e-05, + "loss": 0.2711, "step": 4080 }, { - "epoch": 2.18, - "learning_rate": 2.607498223169865e-05, - "loss": 0.5989, + "epoch": 2.66, + "learning_rate": 2.4485596707818932e-05, + "loss": 0.1015, "step": 4090 }, { - "epoch": 2.18, - "learning_rate": 2.6057213930348257e-05, - "loss": 0.3408, + "epoch": 2.66, + "learning_rate": 2.446393762183236e-05, + "loss": 0.4934, "step": 4100 }, { - "epoch": 2.19, - "learning_rate": 2.603944562899787e-05, - "loss": 0.3551, + "epoch": 2.67, + "learning_rate": 2.4442278535845786e-05, + "loss": 0.5104, "step": 4110 }, { - "epoch": 2.2, - "learning_rate": 2.6021677327647478e-05, - "loss": 0.3388, + "epoch": 2.68, + "learning_rate": 2.4420619449859215e-05, + "loss": 0.2386, "step": 4120 }, { - "epoch": 2.2, - "learning_rate": 2.6003909026297088e-05, - "loss": 0.4641, + "epoch": 2.68, + "learning_rate": 2.4398960363872644e-05, + "loss": 0.3044, "step": 4130 }, { - "epoch": 2.21, - "learning_rate": 2.5986140724946695e-05, - "loss": 0.2188, + "epoch": 2.69, + "learning_rate": 2.4377301277886073e-05, + "loss": 0.4077, "step": 4140 }, { - "epoch": 2.21, - "learning_rate": 2.5968372423596305e-05, - "loss": 0.4134, + "epoch": 2.7, + "learning_rate": 2.43556421918995e-05, + "loss": 0.2545, "step": 4150 }, { - "epoch": 2.22, - "learning_rate": 2.5950604122245915e-05, - "loss": 0.1738, + "epoch": 2.7, + "learning_rate": 2.4333983105912933e-05, + "loss": 0.2894, "step": 4160 }, { - "epoch": 2.22, - "learning_rate": 2.5932835820895526e-05, - "loss": 0.4163, + "epoch": 2.71, + "learning_rate": 2.4312324019926362e-05, + "loss": 0.3408, "step": 4170 }, { - "epoch": 2.23, - "learning_rate": 2.5915067519545132e-05, - "loss": 0.5502, + "epoch": 2.72, + "learning_rate": 2.429066493393979e-05, + "loss": 0.1438, "step": 4180 }, { - "epoch": 2.23, - "learning_rate": 2.589729921819474e-05, - "loss": 0.3584, + "epoch": 2.72, + "learning_rate": 2.4269005847953216e-05, + "loss": 0.2897, "step": 4190 }, { - "epoch": 2.24, - "learning_rate": 2.587953091684435e-05, - "loss": 0.262, + "epoch": 2.73, + "learning_rate": 2.4247346761966645e-05, + "loss": 0.2148, "step": 4200 }, { - "epoch": 2.24, - "learning_rate": 2.5861762615493956e-05, - "loss": 0.1417, + "epoch": 2.73, + "learning_rate": 2.4225687675980073e-05, + "loss": 0.5298, "step": 4210 }, { - "epoch": 2.25, - "learning_rate": 2.584399431414357e-05, - "loss": 0.5752, + "epoch": 2.74, + "learning_rate": 2.4204028589993502e-05, + "loss": 0.1486, "step": 4220 }, { - "epoch": 2.25, - "learning_rate": 2.5826226012793177e-05, - "loss": 0.4802, + "epoch": 2.75, + "learning_rate": 2.418236950400693e-05, + "loss": 0.4059, "step": 4230 }, { - "epoch": 2.26, - "learning_rate": 2.5808457711442787e-05, - "loss": 0.4351, + "epoch": 2.75, + "learning_rate": 2.416071041802036e-05, + "loss": 0.1608, "step": 4240 }, { - "epoch": 2.26, - "learning_rate": 2.5790689410092394e-05, - "loss": 0.4579, + "epoch": 2.76, + "learning_rate": 2.413905133203379e-05, + "loss": 0.2226, "step": 4250 }, { - "epoch": 2.27, - "learning_rate": 2.5772921108742004e-05, - "loss": 0.3316, + "epoch": 2.77, + "learning_rate": 2.411739224604722e-05, + "loss": 0.3627, "step": 4260 }, { - "epoch": 2.28, - "learning_rate": 2.5755152807391615e-05, - "loss": 0.3824, + "epoch": 2.77, + "learning_rate": 2.4095733160060645e-05, + "loss": 0.3048, "step": 4270 }, { - "epoch": 2.28, - "learning_rate": 2.5737384506041225e-05, - "loss": 0.3301, + "epoch": 2.78, + "learning_rate": 2.4074074074074074e-05, + "loss": 0.2084, "step": 4280 }, { - "epoch": 2.29, - "learning_rate": 2.5719616204690832e-05, - "loss": 0.4015, + "epoch": 2.79, + "learning_rate": 2.4052414988087503e-05, + "loss": 0.128, "step": 4290 }, { - "epoch": 2.29, - "learning_rate": 2.5701847903340442e-05, - "loss": 0.2562, + "epoch": 2.79, + "learning_rate": 2.403075590210093e-05, + "loss": 0.4311, "step": 4300 }, { - "epoch": 2.3, - "learning_rate": 2.568407960199005e-05, - "loss": 0.1477, + "epoch": 2.8, + "learning_rate": 2.400909681611436e-05, + "loss": 0.2711, "step": 4310 }, { - "epoch": 2.3, - "learning_rate": 2.5666311300639662e-05, - "loss": 0.3856, + "epoch": 2.81, + "learning_rate": 2.398743773012779e-05, + "loss": 0.2327, "step": 4320 }, { - "epoch": 2.31, - "learning_rate": 2.564854299928927e-05, - "loss": 0.2969, + "epoch": 2.81, + "learning_rate": 2.3965778644141218e-05, + "loss": 0.467, "step": 4330 }, { - "epoch": 2.31, - "learning_rate": 2.563077469793888e-05, - "loss": 0.2749, + "epoch": 2.82, + "learning_rate": 2.394411955815465e-05, + "loss": 0.5556, "step": 4340 }, { - "epoch": 2.32, - "learning_rate": 2.5613006396588486e-05, - "loss": 0.4774, + "epoch": 2.83, + "learning_rate": 2.3922460472168075e-05, + "loss": 0.2591, "step": 4350 }, { - "epoch": 2.32, - "learning_rate": 2.5595238095238093e-05, - "loss": 0.3023, + "epoch": 2.83, + "learning_rate": 2.3900801386181504e-05, + "loss": 0.2438, "step": 4360 }, { - "epoch": 2.33, - "learning_rate": 2.5577469793887704e-05, - "loss": 0.0611, + "epoch": 2.84, + "learning_rate": 2.3879142300194932e-05, + "loss": 0.2504, "step": 4370 }, { - "epoch": 2.33, - "learning_rate": 2.5559701492537314e-05, - "loss": 0.2361, + "epoch": 2.85, + "learning_rate": 2.385748321420836e-05, + "loss": 0.0638, "step": 4380 }, { - "epoch": 2.34, - "learning_rate": 2.5541933191186924e-05, - "loss": 0.0739, + "epoch": 2.85, + "learning_rate": 2.383582412822179e-05, + "loss": 0.2644, "step": 4390 }, { - "epoch": 2.34, - "learning_rate": 2.552416488983653e-05, - "loss": 0.119, + "epoch": 2.86, + "learning_rate": 2.381416504223522e-05, + "loss": 0.1309, "step": 4400 }, { - "epoch": 2.35, - "learning_rate": 2.550639658848614e-05, - "loss": 0.1756, + "epoch": 2.86, + "learning_rate": 2.3792505956248647e-05, + "loss": 0.2903, "step": 4410 }, { - "epoch": 2.36, - "learning_rate": 2.5488628287135748e-05, - "loss": 0.2693, + "epoch": 2.87, + "learning_rate": 2.3770846870262076e-05, + "loss": 0.3967, "step": 4420 }, { - "epoch": 2.36, - "learning_rate": 2.5470859985785362e-05, - "loss": 0.3551, + "epoch": 2.88, + "learning_rate": 2.3749187784275504e-05, + "loss": 0.1492, "step": 4430 }, { - "epoch": 2.37, - "learning_rate": 2.545309168443497e-05, - "loss": 0.4883, + "epoch": 2.88, + "learning_rate": 2.3727528698288933e-05, + "loss": 0.2094, "step": 4440 }, { - "epoch": 2.37, - "learning_rate": 2.543532338308458e-05, - "loss": 0.2657, + "epoch": 2.89, + "learning_rate": 2.3705869612302362e-05, + "loss": 0.1203, "step": 4450 }, { - "epoch": 2.38, - "learning_rate": 2.5417555081734186e-05, - "loss": 0.4308, + "epoch": 2.9, + "learning_rate": 2.368421052631579e-05, + "loss": 0.2751, "step": 4460 }, { - "epoch": 2.38, - "learning_rate": 2.5399786780383796e-05, - "loss": 0.5809, + "epoch": 2.9, + "learning_rate": 2.366255144032922e-05, + "loss": 0.3923, "step": 4470 }, { - "epoch": 2.39, - "learning_rate": 2.5382018479033406e-05, - "loss": 0.2467, + "epoch": 2.91, + "learning_rate": 2.3640892354342648e-05, + "loss": 0.3586, "step": 4480 }, { - "epoch": 2.39, - "learning_rate": 2.5364250177683016e-05, - "loss": 0.0941, + "epoch": 2.92, + "learning_rate": 2.3619233268356076e-05, + "loss": 0.1712, "step": 4490 }, { - "epoch": 2.4, - "learning_rate": 2.5346481876332623e-05, - "loss": 0.4498, + "epoch": 2.92, + "learning_rate": 2.3597574182369505e-05, + "loss": 0.2187, "step": 4500 }, { - "epoch": 2.4, - "learning_rate": 2.532871357498223e-05, - "loss": 0.4368, + "epoch": 2.93, + "learning_rate": 2.357591509638293e-05, + "loss": 0.2134, "step": 4510 }, { - "epoch": 2.41, - "learning_rate": 2.531094527363184e-05, - "loss": 0.561, - "step": 4520 + "epoch": 2.94, + "learning_rate": 2.3554256010396363e-05, + "loss": 0.1906, + "step": 4520 }, { - "epoch": 2.41, - "learning_rate": 2.529317697228145e-05, - "loss": 0.2907, + "epoch": 2.94, + "learning_rate": 2.353259692440979e-05, + "loss": 0.2102, "step": 4530 }, { - "epoch": 2.42, - "learning_rate": 2.527540867093106e-05, - "loss": 0.3229, + "epoch": 2.95, + "learning_rate": 2.351093783842322e-05, + "loss": 0.1499, "step": 4540 }, { - "epoch": 2.42, - "learning_rate": 2.5257640369580668e-05, - "loss": 0.2734, + "epoch": 2.96, + "learning_rate": 2.348927875243665e-05, + "loss": 0.1415, "step": 4550 }, { - "epoch": 2.43, - "learning_rate": 2.5239872068230278e-05, - "loss": 0.3458, + "epoch": 2.96, + "learning_rate": 2.3467619666450077e-05, + "loss": 0.146, "step": 4560 }, { - "epoch": 2.44, - "learning_rate": 2.5222103766879885e-05, - "loss": 0.5105, + "epoch": 2.97, + "learning_rate": 2.3445960580463506e-05, + "loss": 0.4851, "step": 4570 }, { - "epoch": 2.44, - "learning_rate": 2.5204335465529495e-05, - "loss": 0.2893, + "epoch": 2.97, + "learning_rate": 2.342430149447693e-05, + "loss": 0.1137, "step": 4580 }, { - "epoch": 2.45, - "learning_rate": 2.5186567164179105e-05, - "loss": 0.2151, + "epoch": 2.98, + "learning_rate": 2.340264240849036e-05, + "loss": 0.474, "step": 4590 }, { - "epoch": 2.45, - "learning_rate": 2.5168798862828716e-05, - "loss": 0.393, + "epoch": 2.99, + "learning_rate": 2.338098332250379e-05, + "loss": 0.4388, "step": 4600 }, { - "epoch": 2.46, - "learning_rate": 2.5151030561478323e-05, - "loss": 0.3827, + "epoch": 2.99, + "learning_rate": 2.335932423651722e-05, + "loss": 0.2855, "step": 4610 }, { - "epoch": 2.46, - "learning_rate": 2.5133262260127933e-05, - "loss": 0.3617, + "epoch": 3.0, + "eval_accuracy": 0.9696412143514259, + "eval_loss": 0.11773567646741867, + "eval_runtime": 12.9815, + "eval_samples_per_second": 167.469, + "eval_steps_per_second": 41.906, + "step": 4618 + }, + { + "epoch": 3.0, + "learning_rate": 2.333766515053065e-05, + "loss": 0.333, "step": 4620 }, { - "epoch": 2.47, - "learning_rate": 2.511549395877754e-05, - "loss": 0.2941, + "epoch": 3.01, + "learning_rate": 2.3316006064544078e-05, + "loss": 0.1692, "step": 4630 }, { - "epoch": 2.47, - "learning_rate": 2.5097725657427153e-05, - "loss": 0.2795, + "epoch": 3.01, + "learning_rate": 2.3294346978557507e-05, + "loss": 0.1158, "step": 4640 }, { - "epoch": 2.48, - "learning_rate": 2.507995735607676e-05, - "loss": 0.3029, + "epoch": 3.02, + "learning_rate": 2.3272687892570935e-05, + "loss": 0.0129, "step": 4650 }, { - "epoch": 2.48, - "learning_rate": 2.506218905472637e-05, - "loss": 0.3673, + "epoch": 3.03, + "learning_rate": 2.325102880658436e-05, + "loss": 0.2642, "step": 4660 }, { - "epoch": 2.49, - "learning_rate": 2.5044420753375977e-05, - "loss": 0.3834, + "epoch": 3.03, + "learning_rate": 2.322936972059779e-05, + "loss": 0.5089, "step": 4670 }, { - "epoch": 2.49, - "learning_rate": 2.5026652452025584e-05, - "loss": 0.3902, + "epoch": 3.04, + "learning_rate": 2.3207710634611218e-05, + "loss": 0.0762, "step": 4680 }, { - "epoch": 2.5, - "learning_rate": 2.5008884150675198e-05, - "loss": 0.1641, + "epoch": 3.05, + "learning_rate": 2.3186051548624647e-05, + "loss": 0.236, "step": 4690 }, { - "epoch": 2.5, - "learning_rate": 2.4991115849324805e-05, - "loss": 0.3121, + "epoch": 3.05, + "learning_rate": 2.316439246263808e-05, + "loss": 0.263, "step": 4700 }, { - "epoch": 2.51, - "learning_rate": 2.4973347547974415e-05, - "loss": 0.0886, + "epoch": 3.06, + "learning_rate": 2.3142733376651508e-05, + "loss": 0.0997, "step": 4710 }, { - "epoch": 2.52, - "learning_rate": 2.4955579246624022e-05, - "loss": 0.3736, + "epoch": 3.07, + "learning_rate": 2.3121074290664936e-05, + "loss": 0.3237, "step": 4720 }, { - "epoch": 2.52, - "learning_rate": 2.4937810945273632e-05, - "loss": 0.5631, + "epoch": 3.07, + "learning_rate": 2.3099415204678365e-05, + "loss": 0.0913, "step": 4730 }, { - "epoch": 2.53, - "learning_rate": 2.4920042643923242e-05, - "loss": 0.234, + "epoch": 3.08, + "learning_rate": 2.307775611869179e-05, + "loss": 0.154, "step": 4740 }, { - "epoch": 2.53, - "learning_rate": 2.4902274342572853e-05, - "loss": 0.3516, + "epoch": 3.09, + "learning_rate": 2.305609703270522e-05, + "loss": 0.1299, "step": 4750 }, { - "epoch": 2.54, - "learning_rate": 2.488450604122246e-05, - "loss": 0.2165, + "epoch": 3.09, + "learning_rate": 2.3034437946718648e-05, + "loss": 0.2991, "step": 4760 }, { - "epoch": 2.54, - "learning_rate": 2.486673773987207e-05, - "loss": 0.1819, + "epoch": 3.1, + "learning_rate": 2.3012778860732076e-05, + "loss": 0.2063, "step": 4770 }, { - "epoch": 2.55, - "learning_rate": 2.4848969438521676e-05, - "loss": 0.1521, + "epoch": 3.1, + "learning_rate": 2.2991119774745505e-05, + "loss": 0.4323, "step": 4780 }, { - "epoch": 2.55, - "learning_rate": 2.4831201137171287e-05, - "loss": 0.456, + "epoch": 3.11, + "learning_rate": 2.2969460688758937e-05, + "loss": 0.3903, "step": 4790 }, { - "epoch": 2.56, - "learning_rate": 2.4813432835820897e-05, - "loss": 0.2576, + "epoch": 3.12, + "learning_rate": 2.2947801602772366e-05, + "loss": 0.2083, "step": 4800 }, { - "epoch": 2.56, - "learning_rate": 2.4795664534470507e-05, - "loss": 0.4993, + "epoch": 3.12, + "learning_rate": 2.2926142516785794e-05, + "loss": 0.2063, "step": 4810 }, { - "epoch": 2.57, - "learning_rate": 2.4777896233120114e-05, - "loss": 0.2323, + "epoch": 3.13, + "learning_rate": 2.290448343079922e-05, + "loss": 0.4494, "step": 4820 }, { - "epoch": 2.57, - "learning_rate": 2.4761904761904762e-05, - "loss": 0.2738, + "epoch": 3.14, + "learning_rate": 2.288282434481265e-05, + "loss": 0.5917, "step": 4830 }, { - "epoch": 2.58, - "learning_rate": 2.4744136460554373e-05, - "loss": 0.2051, + "epoch": 3.14, + "learning_rate": 2.2861165258826077e-05, + "loss": 0.175, "step": 4840 }, { - "epoch": 2.58, - "learning_rate": 2.4726368159203983e-05, - "loss": 0.2767, + "epoch": 3.15, + "learning_rate": 2.2839506172839506e-05, + "loss": 0.1678, "step": 4850 }, { - "epoch": 2.59, - "learning_rate": 2.470859985785359e-05, - "loss": 0.2283, + "epoch": 3.16, + "learning_rate": 2.2817847086852934e-05, + "loss": 0.397, "step": 4860 }, { - "epoch": 2.6, - "learning_rate": 2.46908315565032e-05, - "loss": 0.303, + "epoch": 3.16, + "learning_rate": 2.2796188000866363e-05, + "loss": 0.3491, "step": 4870 }, { - "epoch": 2.6, - "learning_rate": 2.4673063255152807e-05, - "loss": 0.3372, + "epoch": 3.17, + "learning_rate": 2.2774528914879795e-05, + "loss": 0.1067, "step": 4880 }, { - "epoch": 2.61, - "learning_rate": 2.4655294953802417e-05, - "loss": 0.3467, + "epoch": 3.18, + "learning_rate": 2.2752869828893224e-05, + "loss": 0.2016, "step": 4890 }, { - "epoch": 2.61, - "learning_rate": 2.4637526652452027e-05, - "loss": 0.3654, + "epoch": 3.18, + "learning_rate": 2.273121074290665e-05, + "loss": 0.2037, "step": 4900 }, { - "epoch": 2.62, - "learning_rate": 2.4619758351101634e-05, - "loss": 0.4048, + "epoch": 3.19, + "learning_rate": 2.2709551656920078e-05, + "loss": 0.2404, "step": 4910 }, { - "epoch": 2.62, - "learning_rate": 2.4601990049751244e-05, - "loss": 0.2646, + "epoch": 3.2, + "learning_rate": 2.2687892570933507e-05, + "loss": 0.1275, "step": 4920 }, { - "epoch": 2.63, - "learning_rate": 2.458422174840085e-05, - "loss": 0.2296, + "epoch": 3.2, + "learning_rate": 2.2666233484946935e-05, + "loss": 0.0866, "step": 4930 }, { - "epoch": 2.63, - "learning_rate": 2.4566453447050465e-05, - "loss": 0.5276, + "epoch": 3.21, + "learning_rate": 2.2644574398960364e-05, + "loss": 0.2417, "step": 4940 }, { - "epoch": 2.64, - "learning_rate": 2.4548685145700072e-05, - "loss": 0.3293, + "epoch": 3.22, + "learning_rate": 2.2622915312973793e-05, + "loss": 0.0546, "step": 4950 }, { - "epoch": 2.64, - "learning_rate": 2.4530916844349682e-05, - "loss": 0.1968, + "epoch": 3.22, + "learning_rate": 2.260125622698722e-05, + "loss": 0.2839, "step": 4960 }, { - "epoch": 2.65, - "learning_rate": 2.451314854299929e-05, - "loss": 0.3755, + "epoch": 3.23, + "learning_rate": 2.2579597141000653e-05, + "loss": 0.1398, "step": 4970 }, { - "epoch": 2.65, - "learning_rate": 2.44953802416489e-05, - "loss": 0.3837, + "epoch": 3.23, + "learning_rate": 2.255793805501408e-05, + "loss": 0.3108, "step": 4980 }, { - "epoch": 2.66, - "learning_rate": 2.4477611940298506e-05, - "loss": 0.1855, + "epoch": 3.24, + "learning_rate": 2.2536278969027507e-05, + "loss": 0.4113, "step": 4990 }, { - "epoch": 2.66, - "learning_rate": 2.445984363894812e-05, - "loss": 0.3306, + "epoch": 3.25, + "learning_rate": 2.2514619883040936e-05, + "loss": 0.15, "step": 5000 }, { - "epoch": 2.67, - "learning_rate": 2.4442075337597727e-05, - "loss": 0.2548, + "epoch": 3.25, + "learning_rate": 2.2492960797054365e-05, + "loss": 0.1093, "step": 5010 }, { - "epoch": 2.68, - "learning_rate": 2.4424307036247337e-05, - "loss": 0.2704, + "epoch": 3.26, + "learning_rate": 2.2471301711067793e-05, + "loss": 0.3478, "step": 5020 }, { - "epoch": 2.68, - "learning_rate": 2.4406538734896944e-05, - "loss": 0.3663, + "epoch": 3.27, + "learning_rate": 2.2449642625081222e-05, + "loss": 0.229, "step": 5030 }, { - "epoch": 2.69, - "learning_rate": 2.4388770433546554e-05, - "loss": 0.1645, + "epoch": 3.27, + "learning_rate": 2.242798353909465e-05, + "loss": 0.2711, "step": 5040 }, { - "epoch": 2.69, - "learning_rate": 2.4371002132196164e-05, - "loss": 0.3771, + "epoch": 3.28, + "learning_rate": 2.240632445310808e-05, + "loss": 0.1047, "step": 5050 }, { - "epoch": 2.7, - "learning_rate": 2.435323383084577e-05, - "loss": 0.1138, + "epoch": 3.29, + "learning_rate": 2.2384665367121508e-05, + "loss": 0.1989, "step": 5060 }, { - "epoch": 2.7, - "learning_rate": 2.433546552949538e-05, - "loss": 0.171, + "epoch": 3.29, + "learning_rate": 2.2363006281134937e-05, + "loss": 0.1658, "step": 5070 }, { - "epoch": 2.71, - "learning_rate": 2.4317697228144988e-05, - "loss": 0.2748, + "epoch": 3.3, + "learning_rate": 2.2341347195148366e-05, + "loss": 0.1486, "step": 5080 }, { - "epoch": 2.71, - "learning_rate": 2.42999289267946e-05, - "loss": 0.3241, + "epoch": 3.31, + "learning_rate": 2.2319688109161794e-05, + "loss": 0.1316, "step": 5090 }, { - "epoch": 2.72, - "learning_rate": 2.428216062544421e-05, - "loss": 0.1618, + "epoch": 3.31, + "learning_rate": 2.2298029023175223e-05, + "loss": 0.087, "step": 5100 }, { - "epoch": 2.72, - "learning_rate": 2.426439232409382e-05, - "loss": 0.1906, + "epoch": 3.32, + "learning_rate": 2.227636993718865e-05, + "loss": 0.3231, "step": 5110 }, { - "epoch": 2.73, - "learning_rate": 2.4246624022743426e-05, - "loss": 0.2093, + "epoch": 3.33, + "learning_rate": 2.225471085120208e-05, + "loss": 0.1468, "step": 5120 }, { - "epoch": 2.73, - "learning_rate": 2.4228855721393036e-05, - "loss": 0.3015, + "epoch": 3.33, + "learning_rate": 2.223305176521551e-05, + "loss": 0.1442, "step": 5130 }, { - "epoch": 2.74, - "learning_rate": 2.4211087420042643e-05, - "loss": 0.4417, + "epoch": 3.34, + "learning_rate": 2.2211392679228934e-05, + "loss": 0.3304, "step": 5140 }, { - "epoch": 2.74, - "learning_rate": 2.4193319118692253e-05, - "loss": 0.5219, + "epoch": 3.35, + "learning_rate": 2.2189733593242366e-05, + "loss": 0.2766, "step": 5150 }, { - "epoch": 2.75, - "learning_rate": 2.4175550817341863e-05, - "loss": 0.2737, + "epoch": 3.35, + "learning_rate": 2.2168074507255795e-05, + "loss": 0.1563, "step": 5160 }, { - "epoch": 2.76, - "learning_rate": 2.4157782515991474e-05, - "loss": 0.148, + "epoch": 3.36, + "learning_rate": 2.2146415421269224e-05, + "loss": 0.1921, "step": 5170 }, { - "epoch": 2.76, - "learning_rate": 2.414001421464108e-05, - "loss": 0.495, + "epoch": 3.36, + "learning_rate": 2.2124756335282652e-05, + "loss": 0.1017, "step": 5180 }, { - "epoch": 2.77, - "learning_rate": 2.412224591329069e-05, - "loss": 0.2003, + "epoch": 3.37, + "learning_rate": 2.210309724929608e-05, + "loss": 0.2529, "step": 5190 }, { - "epoch": 2.77, - "learning_rate": 2.4104477611940298e-05, - "loss": 0.3997, + "epoch": 3.38, + "learning_rate": 2.208143816330951e-05, + "loss": 0.0399, "step": 5200 }, { - "epoch": 2.78, - "learning_rate": 2.4086709310589908e-05, - "loss": 0.2408, + "epoch": 3.38, + "learning_rate": 2.205977907732294e-05, + "loss": 0.417, "step": 5210 }, { - "epoch": 2.78, - "learning_rate": 2.4068941009239518e-05, - "loss": 0.4462, + "epoch": 3.39, + "learning_rate": 2.2038119991336364e-05, + "loss": 0.6172, "step": 5220 }, { - "epoch": 2.79, - "learning_rate": 2.4051172707889125e-05, - "loss": 0.3886, + "epoch": 3.4, + "learning_rate": 2.2016460905349792e-05, + "loss": 0.1713, "step": 5230 }, { - "epoch": 2.79, - "learning_rate": 2.4033404406538735e-05, - "loss": 0.4037, + "epoch": 3.4, + "learning_rate": 2.1994801819363224e-05, + "loss": 0.4274, "step": 5240 }, { - "epoch": 2.8, - "learning_rate": 2.4015636105188342e-05, - "loss": 0.1684, + "epoch": 3.41, + "learning_rate": 2.1973142733376653e-05, + "loss": 0.3577, "step": 5250 }, { - "epoch": 2.8, - "learning_rate": 2.3997867803837956e-05, - "loss": 0.2469, + "epoch": 3.42, + "learning_rate": 2.1951483647390082e-05, + "loss": 0.2066, "step": 5260 }, { - "epoch": 2.81, - "learning_rate": 2.3980099502487563e-05, - "loss": 0.4582, + "epoch": 3.42, + "learning_rate": 2.192982456140351e-05, + "loss": 0.3221, "step": 5270 }, { - "epoch": 2.81, - "learning_rate": 2.3962331201137173e-05, - "loss": 0.372, + "epoch": 3.43, + "learning_rate": 2.190816547541694e-05, + "loss": 0.1747, "step": 5280 }, { - "epoch": 2.82, - "learning_rate": 2.394456289978678e-05, - "loss": 0.1701, + "epoch": 3.44, + "learning_rate": 2.1886506389430368e-05, + "loss": 0.1228, "step": 5290 }, { - "epoch": 2.82, - "learning_rate": 2.392679459843639e-05, - "loss": 0.1801, + "epoch": 3.44, + "learning_rate": 2.1864847303443793e-05, + "loss": 0.1929, "step": 5300 }, { - "epoch": 2.83, - "learning_rate": 2.3909026297086e-05, - "loss": 0.629, + "epoch": 3.45, + "learning_rate": 2.1843188217457222e-05, + "loss": 0.2565, "step": 5310 }, { - "epoch": 2.84, - "learning_rate": 2.389125799573561e-05, - "loss": 0.2649, + "epoch": 3.46, + "learning_rate": 2.182152913147065e-05, + "loss": 0.159, "step": 5320 }, { - "epoch": 2.84, - "learning_rate": 2.3873489694385217e-05, - "loss": 0.2126, + "epoch": 3.46, + "learning_rate": 2.1799870045484083e-05, + "loss": 0.1915, "step": 5330 }, { - "epoch": 2.85, - "learning_rate": 2.3855721393034828e-05, - "loss": 0.7138, + "epoch": 3.47, + "learning_rate": 2.177821095949751e-05, + "loss": 0.2584, "step": 5340 }, { - "epoch": 2.85, - "learning_rate": 2.3837953091684434e-05, - "loss": 0.3303, + "epoch": 3.48, + "learning_rate": 2.175655187351094e-05, + "loss": 0.162, "step": 5350 }, { - "epoch": 2.86, - "learning_rate": 2.3820184790334045e-05, - "loss": 0.2639, + "epoch": 3.48, + "learning_rate": 2.173489278752437e-05, + "loss": 0.1473, "step": 5360 }, { - "epoch": 2.86, - "learning_rate": 2.3802416488983655e-05, - "loss": 0.5515, + "epoch": 3.49, + "learning_rate": 2.1713233701537797e-05, + "loss": 0.4753, "step": 5370 }, { - "epoch": 2.87, - "learning_rate": 2.3784648187633262e-05, - "loss": 0.1772, + "epoch": 3.49, + "learning_rate": 2.1691574615551223e-05, + "loss": 0.1635, "step": 5380 }, { - "epoch": 2.87, - "learning_rate": 2.3766879886282872e-05, - "loss": 0.404, + "epoch": 3.5, + "learning_rate": 2.166991552956465e-05, + "loss": 0.2713, "step": 5390 }, { - "epoch": 2.88, - "learning_rate": 2.374911158493248e-05, - "loss": 0.3401, + "epoch": 3.51, + "learning_rate": 2.164825644357808e-05, + "loss": 0.4024, "step": 5400 }, { - "epoch": 2.88, - "learning_rate": 2.373134328358209e-05, - "loss": 0.5859, + "epoch": 3.51, + "learning_rate": 2.162659735759151e-05, + "loss": 0.3595, "step": 5410 }, { - "epoch": 2.89, - "learning_rate": 2.37135749822317e-05, - "loss": 0.3381, + "epoch": 3.52, + "learning_rate": 2.160493827160494e-05, + "loss": 0.2345, "step": 5420 }, { - "epoch": 2.89, - "learning_rate": 2.369580668088131e-05, - "loss": 0.4004, + "epoch": 3.53, + "learning_rate": 2.158327918561837e-05, + "loss": 0.2353, "step": 5430 }, { - "epoch": 2.9, - "learning_rate": 2.3678038379530917e-05, - "loss": 0.2355, + "epoch": 3.53, + "learning_rate": 2.1561620099631798e-05, + "loss": 0.3144, "step": 5440 }, { - "epoch": 2.9, - "learning_rate": 2.3660270078180527e-05, - "loss": 0.3361, + "epoch": 3.54, + "learning_rate": 2.1539961013645227e-05, + "loss": 0.558, "step": 5450 }, { - "epoch": 2.91, - "learning_rate": 2.3642501776830134e-05, - "loss": 0.2862, + "epoch": 3.55, + "learning_rate": 2.1518301927658652e-05, + "loss": 0.1033, "step": 5460 }, { - "epoch": 2.92, - "learning_rate": 2.3624733475479747e-05, - "loss": 0.261, + "epoch": 3.55, + "learning_rate": 2.149664284167208e-05, + "loss": 0.2233, "step": 5470 }, { - "epoch": 2.92, - "learning_rate": 2.3606965174129354e-05, - "loss": 0.3078, + "epoch": 3.56, + "learning_rate": 2.147498375568551e-05, + "loss": 0.2178, "step": 5480 }, { - "epoch": 2.93, - "learning_rate": 2.3589196872778964e-05, - "loss": 0.5584, + "epoch": 3.57, + "learning_rate": 2.1453324669698938e-05, + "loss": 0.0916, "step": 5490 }, { - "epoch": 2.93, - "learning_rate": 2.357142857142857e-05, - "loss": 0.1999, + "epoch": 3.57, + "learning_rate": 2.1431665583712367e-05, + "loss": 0.051, "step": 5500 }, { - "epoch": 2.94, - "learning_rate": 2.355366027007818e-05, - "loss": 0.218, + "epoch": 3.58, + "learning_rate": 2.14100064977258e-05, + "loss": 0.3294, "step": 5510 }, { - "epoch": 2.94, - "learning_rate": 2.3535891968727792e-05, - "loss": 0.2851, + "epoch": 3.59, + "learning_rate": 2.1388347411739228e-05, + "loss": 0.1862, "step": 5520 }, { - "epoch": 2.95, - "learning_rate": 2.35181236673774e-05, - "loss": 0.1605, + "epoch": 3.59, + "learning_rate": 2.1366688325752653e-05, + "loss": 0.2174, "step": 5530 }, { - "epoch": 2.95, - "learning_rate": 2.350035536602701e-05, - "loss": 0.309, + "epoch": 3.6, + "learning_rate": 2.134502923976608e-05, + "loss": 0.2679, "step": 5540 }, { - "epoch": 2.96, - "learning_rate": 2.3482587064676616e-05, - "loss": 0.4761, + "epoch": 3.61, + "learning_rate": 2.132337015377951e-05, + "loss": 0.1024, "step": 5550 }, { - "epoch": 2.96, - "learning_rate": 2.3464818763326226e-05, - "loss": 0.1891, + "epoch": 3.61, + "learning_rate": 2.130171106779294e-05, + "loss": 0.2108, "step": 5560 }, { - "epoch": 2.97, - "learning_rate": 2.3447050461975833e-05, - "loss": 0.3041, + "epoch": 3.62, + "learning_rate": 2.1280051981806368e-05, + "loss": 0.1707, "step": 5570 }, { - "epoch": 2.97, - "learning_rate": 2.3429282160625447e-05, - "loss": 0.1947, + "epoch": 3.62, + "learning_rate": 2.1258392895819796e-05, + "loss": 0.1842, "step": 5580 }, { - "epoch": 2.98, - "learning_rate": 2.3411513859275053e-05, - "loss": 0.5016, + "epoch": 3.63, + "learning_rate": 2.1236733809833225e-05, + "loss": 0.0681, "step": 5590 }, { - "epoch": 2.98, - "learning_rate": 2.3393745557924664e-05, - "loss": 0.1198, + "epoch": 3.64, + "learning_rate": 2.1215074723846657e-05, + "loss": 0.3176, "step": 5600 }, { - "epoch": 2.99, - "learning_rate": 2.337597725657427e-05, - "loss": 0.3073, + "epoch": 3.64, + "learning_rate": 2.1193415637860082e-05, + "loss": 0.3924, "step": 5610 }, { - "epoch": 2.99, - "learning_rate": 2.335820895522388e-05, - "loss": 0.1397, + "epoch": 3.65, + "learning_rate": 2.117175655187351e-05, + "loss": 0.307, "step": 5620 }, { - "epoch": 3.0, - "eval_accuracy": 0.9645149112872782, - "eval_loss": 0.15058819949626923, - "eval_runtime": 11.7917, - "eval_samples_per_second": 224.65, - "eval_steps_per_second": 56.226, - "step": 5629 - }, - { - "epoch": 3.0, - "learning_rate": 2.334044065387349e-05, - "loss": 0.2357, + "epoch": 3.66, + "learning_rate": 2.115009746588694e-05, + "loss": 0.164, "step": 5630 }, { - "epoch": 3.01, - "learning_rate": 2.33226723525231e-05, - "loss": 0.0934, + "epoch": 3.66, + "learning_rate": 2.112843837990037e-05, + "loss": 0.1099, "step": 5640 }, { - "epoch": 3.01, - "learning_rate": 2.3304904051172708e-05, - "loss": 0.1918, + "epoch": 3.67, + "learning_rate": 2.1106779293913797e-05, + "loss": 0.3696, "step": 5650 }, { - "epoch": 3.02, - "learning_rate": 2.328713574982232e-05, - "loss": 0.2025, + "epoch": 3.68, + "learning_rate": 2.1085120207927226e-05, + "loss": 0.2124, "step": 5660 }, { - "epoch": 3.02, - "learning_rate": 2.3269367448471925e-05, - "loss": 0.4236, + "epoch": 3.68, + "learning_rate": 2.1063461121940655e-05, + "loss": 0.212, "step": 5670 }, { - "epoch": 3.03, - "learning_rate": 2.325159914712154e-05, - "loss": 0.36, + "epoch": 3.69, + "learning_rate": 2.1041802035954083e-05, + "loss": 0.2727, "step": 5680 }, { - "epoch": 3.03, - "learning_rate": 2.3233830845771146e-05, - "loss": 0.2928, + "epoch": 3.7, + "learning_rate": 2.1020142949967512e-05, + "loss": 0.2698, "step": 5690 }, { - "epoch": 3.04, - "learning_rate": 2.3216062544420753e-05, - "loss": 0.2982, + "epoch": 3.7, + "learning_rate": 2.099848386398094e-05, + "loss": 0.4189, "step": 5700 }, { - "epoch": 3.04, - "learning_rate": 2.3198294243070363e-05, - "loss": 0.4421, + "epoch": 3.71, + "learning_rate": 2.097682477799437e-05, + "loss": 0.1711, "step": 5710 }, { - "epoch": 3.05, - "learning_rate": 2.318052594171997e-05, - "loss": 0.328, + "epoch": 3.72, + "learning_rate": 2.0955165692007798e-05, + "loss": 0.1526, "step": 5720 }, { - "epoch": 3.05, - "learning_rate": 2.3162757640369583e-05, - "loss": 0.2694, + "epoch": 3.72, + "learning_rate": 2.0933506606021227e-05, + "loss": 0.1894, "step": 5730 }, { - "epoch": 3.06, - "learning_rate": 2.314498933901919e-05, - "loss": 0.2316, + "epoch": 3.73, + "learning_rate": 2.0911847520034655e-05, + "loss": 0.2144, "step": 5740 }, { - "epoch": 3.06, - "learning_rate": 2.31272210376688e-05, - "loss": 0.2651, + "epoch": 3.73, + "learning_rate": 2.0890188434048084e-05, + "loss": 0.1443, "step": 5750 }, { - "epoch": 3.07, - "learning_rate": 2.3109452736318407e-05, - "loss": 0.1724, + "epoch": 3.74, + "learning_rate": 2.0868529348061513e-05, + "loss": 0.0814, "step": 5760 }, { - "epoch": 3.07, - "learning_rate": 2.3091684434968018e-05, - "loss": 0.4642, + "epoch": 3.75, + "learning_rate": 2.0846870262074938e-05, + "loss": 0.2765, "step": 5770 }, { - "epoch": 3.08, - "learning_rate": 2.3073916133617624e-05, - "loss": 0.3785, + "epoch": 3.75, + "learning_rate": 2.082521117608837e-05, + "loss": 0.1244, "step": 5780 }, { - "epoch": 3.09, - "learning_rate": 2.3056147832267238e-05, - "loss": 0.2163, + "epoch": 3.76, + "learning_rate": 2.08035520901018e-05, + "loss": 0.2107, "step": 5790 }, { - "epoch": 3.09, - "learning_rate": 2.3038379530916845e-05, - "loss": 0.3101, + "epoch": 3.77, + "learning_rate": 2.0781893004115227e-05, + "loss": 0.0134, "step": 5800 }, { - "epoch": 3.1, - "learning_rate": 2.3020611229566455e-05, - "loss": 0.2614, + "epoch": 3.77, + "learning_rate": 2.0760233918128656e-05, + "loss": 0.1578, "step": 5810 }, { - "epoch": 3.1, - "learning_rate": 2.3002842928216062e-05, - "loss": 0.3833, + "epoch": 3.78, + "learning_rate": 2.074074074074074e-05, + "loss": 0.1113, "step": 5820 }, { - "epoch": 3.11, - "learning_rate": 2.2985074626865672e-05, - "loss": 0.1791, + "epoch": 3.79, + "learning_rate": 2.071908165475417e-05, + "loss": 0.1734, "step": 5830 }, { - "epoch": 3.11, - "learning_rate": 2.2967306325515283e-05, - "loss": 0.3556, + "epoch": 3.79, + "learning_rate": 2.06974225687676e-05, + "loss": 0.2593, "step": 5840 }, { - "epoch": 3.12, - "learning_rate": 2.294953802416489e-05, - "loss": 0.4476, + "epoch": 3.8, + "learning_rate": 2.067576348278103e-05, + "loss": 0.4005, "step": 5850 }, { - "epoch": 3.12, - "learning_rate": 2.29317697228145e-05, - "loss": 0.0203, + "epoch": 3.81, + "learning_rate": 2.0654104396794458e-05, + "loss": 0.1157, "step": 5860 }, { - "epoch": 3.13, - "learning_rate": 2.2914001421464107e-05, - "loss": 0.1992, + "epoch": 3.81, + "learning_rate": 2.0632445310807883e-05, + "loss": 0.1248, "step": 5870 }, { - "epoch": 3.13, - "learning_rate": 2.2896233120113717e-05, - "loss": 0.1739, + "epoch": 3.82, + "learning_rate": 2.0610786224821312e-05, + "loss": 0.1108, "step": 5880 }, { - "epoch": 3.14, - "learning_rate": 2.2878464818763327e-05, - "loss": 0.2232, + "epoch": 3.83, + "learning_rate": 2.058912713883474e-05, + "loss": 0.1242, "step": 5890 }, { - "epoch": 3.14, - "learning_rate": 2.2860696517412937e-05, - "loss": 0.1936, + "epoch": 3.83, + "learning_rate": 2.056746805284817e-05, + "loss": 0.1443, "step": 5900 }, { - "epoch": 3.15, - "learning_rate": 2.2842928216062544e-05, - "loss": 0.3519, + "epoch": 3.84, + "learning_rate": 2.0545808966861598e-05, + "loss": 0.1957, "step": 5910 }, { - "epoch": 3.15, - "learning_rate": 2.2825159914712154e-05, - "loss": 0.2059, + "epoch": 3.85, + "learning_rate": 2.0524149880875027e-05, + "loss": 0.323, "step": 5920 }, { - "epoch": 3.16, - "learning_rate": 2.280739161336176e-05, - "loss": 0.5305, + "epoch": 3.85, + "learning_rate": 2.050249079488846e-05, + "loss": 0.3315, "step": 5930 }, { - "epoch": 3.17, - "learning_rate": 2.2789623312011375e-05, - "loss": 0.5057, + "epoch": 3.86, + "learning_rate": 2.0480831708901888e-05, + "loss": 0.311, "step": 5940 }, { - "epoch": 3.17, - "learning_rate": 2.2771855010660982e-05, - "loss": 0.3791, + "epoch": 3.86, + "learning_rate": 2.0459172622915313e-05, + "loss": 0.1231, "step": 5950 }, { - "epoch": 3.18, - "learning_rate": 2.2754086709310592e-05, - "loss": 0.1412, + "epoch": 3.87, + "learning_rate": 2.043751353692874e-05, + "loss": 0.1074, "step": 5960 }, { - "epoch": 3.18, - "learning_rate": 2.27363184079602e-05, - "loss": 0.4254, + "epoch": 3.88, + "learning_rate": 2.041585445094217e-05, + "loss": 0.1604, "step": 5970 }, { - "epoch": 3.19, - "learning_rate": 2.271855010660981e-05, - "loss": 0.221, + "epoch": 3.88, + "learning_rate": 2.03941953649556e-05, + "loss": 0.3031, "step": 5980 }, { - "epoch": 3.19, - "learning_rate": 2.2700781805259416e-05, - "loss": 0.2326, + "epoch": 3.89, + "learning_rate": 2.0372536278969028e-05, + "loss": 0.4937, "step": 5990 }, { - "epoch": 3.2, - "learning_rate": 2.268301350390903e-05, - "loss": 0.4275, + "epoch": 3.9, + "learning_rate": 2.0350877192982456e-05, + "loss": 0.1419, "step": 6000 }, { - "epoch": 3.2, - "learning_rate": 2.2665245202558637e-05, - "loss": 0.163, + "epoch": 3.9, + "learning_rate": 2.0329218106995885e-05, + "loss": 0.2078, "step": 6010 }, { - "epoch": 3.21, - "learning_rate": 2.2647476901208243e-05, - "loss": 0.1918, + "epoch": 3.91, + "learning_rate": 2.0307559021009317e-05, + "loss": 0.1859, "step": 6020 }, { - "epoch": 3.21, - "learning_rate": 2.2629708599857854e-05, - "loss": 0.2797, + "epoch": 3.92, + "learning_rate": 2.0285899935022742e-05, + "loss": 0.2744, "step": 6030 }, { - "epoch": 3.22, - "learning_rate": 2.261194029850746e-05, - "loss": 0.2695, + "epoch": 3.92, + "learning_rate": 2.026424084903617e-05, + "loss": 0.039, "step": 6040 }, { - "epoch": 3.22, - "learning_rate": 2.2594171997157074e-05, - "loss": 0.3294, + "epoch": 3.93, + "learning_rate": 2.02425817630496e-05, + "loss": 0.2164, "step": 6050 }, { - "epoch": 3.23, - "learning_rate": 2.257640369580668e-05, - "loss": 0.2364, + "epoch": 3.94, + "learning_rate": 2.022092267706303e-05, + "loss": 0.231, "step": 6060 }, { - "epoch": 3.23, - "learning_rate": 2.255863539445629e-05, - "loss": 0.2612, + "epoch": 3.94, + "learning_rate": 2.0199263591076457e-05, + "loss": 0.182, "step": 6070 }, { - "epoch": 3.24, - "learning_rate": 2.2540867093105898e-05, - "loss": 0.3158, + "epoch": 3.95, + "learning_rate": 2.0177604505089886e-05, + "loss": 0.0891, "step": 6080 }, { - "epoch": 3.25, - "learning_rate": 2.252309879175551e-05, - "loss": 0.2015, + "epoch": 3.96, + "learning_rate": 2.0155945419103314e-05, + "loss": 0.2888, "step": 6090 }, { - "epoch": 3.25, - "learning_rate": 2.250533049040512e-05, - "loss": 0.1495, + "epoch": 3.96, + "learning_rate": 2.0134286333116743e-05, + "loss": 0.2661, "step": 6100 }, { - "epoch": 3.26, - "learning_rate": 2.248756218905473e-05, - "loss": 0.2251, + "epoch": 3.97, + "learning_rate": 2.0112627247130172e-05, + "loss": 0.2692, "step": 6110 }, { - "epoch": 3.26, - "learning_rate": 2.2469793887704336e-05, - "loss": 0.1857, + "epoch": 3.98, + "learning_rate": 2.00909681611436e-05, + "loss": 0.1445, "step": 6120 }, { - "epoch": 3.27, - "learning_rate": 2.2452025586353946e-05, - "loss": 0.1412, + "epoch": 3.98, + "learning_rate": 2.006930907515703e-05, + "loss": 0.2447, "step": 6130 }, { - "epoch": 3.27, - "learning_rate": 2.2434257285003553e-05, - "loss": 0.2889, + "epoch": 3.99, + "learning_rate": 2.0047649989170458e-05, + "loss": 0.1887, "step": 6140 }, { - "epoch": 3.28, - "learning_rate": 2.2416488983653163e-05, - "loss": 0.2145, + "epoch": 3.99, + "learning_rate": 2.0025990903183887e-05, + "loss": 0.2405, "step": 6150 }, { - "epoch": 3.28, - "learning_rate": 2.2398720682302773e-05, - "loss": 0.4985, + "epoch": 4.0, + "eval_accuracy": 0.9793008279668813, + "eval_loss": 0.10150198638439178, + "eval_runtime": 12.9625, + "eval_samples_per_second": 167.715, + "eval_steps_per_second": 41.967, + "step": 6158 + }, + { + "epoch": 4.0, + "learning_rate": 2.0004331817197315e-05, + "loss": 0.172, "step": 6160 }, { - "epoch": 3.29, - "learning_rate": 2.238095238095238e-05, - "loss": 0.1756, + "epoch": 4.01, + "learning_rate": 1.9982672731210744e-05, + "loss": 0.2265, "step": 6170 }, { - "epoch": 3.29, - "learning_rate": 2.236318407960199e-05, - "loss": 0.0672, + "epoch": 4.01, + "learning_rate": 1.9961013645224173e-05, + "loss": 0.1351, "step": 6180 }, { - "epoch": 3.3, - "learning_rate": 2.2345415778251597e-05, - "loss": 0.2029, + "epoch": 4.02, + "learning_rate": 1.9939354559237598e-05, + "loss": 0.2882, "step": 6190 }, { - "epoch": 3.3, - "learning_rate": 2.2327647476901208e-05, - "loss": 0.1887, + "epoch": 4.03, + "learning_rate": 1.991769547325103e-05, + "loss": 0.2578, "step": 6200 }, { - "epoch": 3.31, - "learning_rate": 2.2309879175550818e-05, - "loss": 0.4306, + "epoch": 4.03, + "learning_rate": 1.989603638726446e-05, + "loss": 0.2349, "step": 6210 }, { - "epoch": 3.31, - "learning_rate": 2.2292110874200428e-05, - "loss": 0.0209, + "epoch": 4.04, + "learning_rate": 1.9874377301277887e-05, + "loss": 0.3212, "step": 6220 }, { - "epoch": 3.32, - "learning_rate": 2.2274342572850035e-05, - "loss": 0.1189, + "epoch": 4.05, + "learning_rate": 1.9852718215291316e-05, + "loss": 0.2314, "step": 6230 }, { - "epoch": 3.33, - "learning_rate": 2.2256574271499645e-05, - "loss": 0.3944, + "epoch": 4.05, + "learning_rate": 1.9831059129304745e-05, + "loss": 0.1418, "step": 6240 }, { - "epoch": 3.33, - "learning_rate": 2.2238805970149252e-05, - "loss": 0.449, + "epoch": 4.06, + "learning_rate": 1.9809400043318173e-05, + "loss": 0.1055, "step": 6250 }, { - "epoch": 3.34, - "learning_rate": 2.2221037668798866e-05, - "loss": 0.2608, + "epoch": 4.07, + "learning_rate": 1.9787740957331602e-05, + "loss": 0.1424, "step": 6260 }, { - "epoch": 3.34, - "learning_rate": 2.2203269367448473e-05, - "loss": 0.2762, + "epoch": 4.07, + "learning_rate": 1.9766081871345027e-05, + "loss": 0.1625, "step": 6270 }, { - "epoch": 3.35, - "learning_rate": 2.2185501066098083e-05, - "loss": 0.1201, + "epoch": 4.08, + "learning_rate": 1.9744422785358456e-05, + "loss": 0.2511, "step": 6280 }, { - "epoch": 3.35, - "learning_rate": 2.216773276474769e-05, - "loss": 0.4171, + "epoch": 4.09, + "learning_rate": 1.9722763699371888e-05, + "loss": 0.2538, "step": 6290 }, { - "epoch": 3.36, - "learning_rate": 2.21499644633973e-05, - "loss": 0.1389, + "epoch": 4.09, + "learning_rate": 1.9701104613385317e-05, + "loss": 0.0055, "step": 6300 }, { - "epoch": 3.36, - "learning_rate": 2.213219616204691e-05, - "loss": 0.3493, + "epoch": 4.1, + "learning_rate": 1.9679445527398745e-05, + "loss": 0.2292, "step": 6310 }, { - "epoch": 3.37, - "learning_rate": 2.211442786069652e-05, - "loss": 0.4191, + "epoch": 4.11, + "learning_rate": 1.9657786441412174e-05, + "loss": 0.1772, "step": 6320 }, { - "epoch": 3.37, - "learning_rate": 2.2096659559346127e-05, - "loss": 0.2165, + "epoch": 4.11, + "learning_rate": 1.9636127355425603e-05, + "loss": 0.2582, "step": 6330 }, { - "epoch": 3.38, - "learning_rate": 2.2078891257995734e-05, - "loss": 0.1247, + "epoch": 4.12, + "learning_rate": 1.9614468269439028e-05, + "loss": 0.1229, "step": 6340 }, { - "epoch": 3.38, - "learning_rate": 2.2061122956645344e-05, - "loss": 0.3346, + "epoch": 4.12, + "learning_rate": 1.9592809183452457e-05, + "loss": 0.0285, "step": 6350 }, { - "epoch": 3.39, - "learning_rate": 2.204335465529495e-05, - "loss": 0.4383, + "epoch": 4.13, + "learning_rate": 1.9571150097465886e-05, + "loss": 0.1899, "step": 6360 }, { - "epoch": 3.39, - "learning_rate": 2.2025586353944565e-05, - "loss": 0.3, + "epoch": 4.14, + "learning_rate": 1.9549491011479314e-05, + "loss": 0.4994, "step": 6370 }, { - "epoch": 3.4, - "learning_rate": 2.2007818052594172e-05, - "loss": 0.3107, + "epoch": 4.14, + "learning_rate": 1.9527831925492746e-05, + "loss": 0.2171, "step": 6380 }, { - "epoch": 3.41, - "learning_rate": 2.1990049751243782e-05, - "loss": 0.1952, + "epoch": 4.15, + "learning_rate": 1.9506172839506175e-05, + "loss": 0.2057, "step": 6390 }, { - "epoch": 3.41, - "learning_rate": 2.197228144989339e-05, - "loss": 0.2026, + "epoch": 4.16, + "learning_rate": 1.9484513753519604e-05, + "loss": 0.2704, "step": 6400 }, { - "epoch": 3.42, - "learning_rate": 2.1954513148543e-05, - "loss": 0.0565, + "epoch": 4.16, + "learning_rate": 1.9462854667533032e-05, + "loss": 0.1213, "step": 6410 }, { - "epoch": 3.42, - "learning_rate": 2.193674484719261e-05, - "loss": 0.4237, + "epoch": 4.17, + "learning_rate": 1.9441195581546458e-05, + "loss": 0.2396, "step": 6420 }, { - "epoch": 3.43, - "learning_rate": 2.191897654584222e-05, - "loss": 0.1468, + "epoch": 4.18, + "learning_rate": 1.9419536495559886e-05, + "loss": 0.0396, "step": 6430 }, { - "epoch": 3.43, - "learning_rate": 2.1901208244491827e-05, - "loss": 0.0984, + "epoch": 4.18, + "learning_rate": 1.9397877409573315e-05, + "loss": 0.2299, "step": 6440 }, { - "epoch": 3.44, - "learning_rate": 2.1883439943141437e-05, - "loss": 0.391, + "epoch": 4.19, + "learning_rate": 1.9376218323586744e-05, + "loss": 0.0109, "step": 6450 }, { - "epoch": 3.44, - "learning_rate": 2.1865671641791044e-05, - "loss": 0.4134, + "epoch": 4.2, + "learning_rate": 1.9354559237600172e-05, + "loss": 0.0679, "step": 6460 }, { - "epoch": 3.45, - "learning_rate": 2.1847903340440657e-05, - "loss": 0.2624, + "epoch": 4.2, + "learning_rate": 1.9332900151613604e-05, + "loss": 0.1354, "step": 6470 }, { - "epoch": 3.45, - "learning_rate": 2.1830135039090264e-05, - "loss": 0.2407, + "epoch": 4.21, + "learning_rate": 1.9311241065627033e-05, + "loss": 0.1422, "step": 6480 }, { - "epoch": 3.46, - "learning_rate": 2.181236673773987e-05, - "loss": 0.3131, + "epoch": 4.22, + "learning_rate": 1.9289581979640462e-05, + "loss": 0.3022, "step": 6490 }, { - "epoch": 3.46, - "learning_rate": 2.179459843638948e-05, - "loss": 0.0897, + "epoch": 4.22, + "learning_rate": 1.9267922893653887e-05, + "loss": 0.274, "step": 6500 }, { - "epoch": 3.47, - "learning_rate": 2.1776830135039088e-05, - "loss": 0.2387, + "epoch": 4.23, + "learning_rate": 1.9246263807667316e-05, + "loss": 0.1733, "step": 6510 }, { - "epoch": 3.47, - "learning_rate": 2.1759061833688702e-05, - "loss": 0.3723, + "epoch": 4.24, + "learning_rate": 1.9224604721680744e-05, + "loss": 0.4914, "step": 6520 }, { - "epoch": 3.48, - "learning_rate": 2.174129353233831e-05, - "loss": 0.1334, + "epoch": 4.24, + "learning_rate": 1.9202945635694173e-05, + "loss": 0.1881, "step": 6530 }, { - "epoch": 3.49, - "learning_rate": 2.172352523098792e-05, - "loss": 0.3296, + "epoch": 4.25, + "learning_rate": 1.9181286549707602e-05, + "loss": 0.1131, "step": 6540 }, { - "epoch": 3.49, - "learning_rate": 2.1705756929637526e-05, - "loss": 0.2947, + "epoch": 4.25, + "learning_rate": 1.915962746372103e-05, + "loss": 0.3501, "step": 6550 }, { - "epoch": 3.5, - "learning_rate": 2.1687988628287136e-05, - "loss": 0.3057, + "epoch": 4.26, + "learning_rate": 1.9137968377734463e-05, + "loss": 0.1951, "step": 6560 }, { - "epoch": 3.5, - "learning_rate": 2.1670220326936743e-05, - "loss": 0.2562, + "epoch": 4.27, + "learning_rate": 1.911630929174789e-05, + "loss": 0.1627, "step": 6570 }, { - "epoch": 3.51, - "learning_rate": 2.1652452025586357e-05, - "loss": 0.2795, + "epoch": 4.27, + "learning_rate": 1.9094650205761317e-05, + "loss": 0.0676, "step": 6580 }, { - "epoch": 3.51, - "learning_rate": 2.1634683724235963e-05, - "loss": 0.2412, + "epoch": 4.28, + "learning_rate": 1.9072991119774745e-05, + "loss": 0.2998, "step": 6590 }, { - "epoch": 3.52, - "learning_rate": 2.1616915422885574e-05, - "loss": 0.2474, + "epoch": 4.29, + "learning_rate": 1.9051332033788174e-05, + "loss": 0.1903, "step": 6600 }, { - "epoch": 3.52, - "learning_rate": 2.159914712153518e-05, - "loss": 0.2517, + "epoch": 4.29, + "learning_rate": 1.9029672947801603e-05, + "loss": 0.1043, "step": 6610 }, { - "epoch": 3.53, - "learning_rate": 2.158137882018479e-05, - "loss": 0.3007, + "epoch": 4.3, + "learning_rate": 1.900801386181503e-05, + "loss": 0.2515, "step": 6620 }, { - "epoch": 3.53, - "learning_rate": 2.15636105188344e-05, - "loss": 0.2198, + "epoch": 4.31, + "learning_rate": 1.898635477582846e-05, + "loss": 0.3629, "step": 6630 }, { - "epoch": 3.54, - "learning_rate": 2.154584221748401e-05, - "loss": 0.2663, + "epoch": 4.31, + "learning_rate": 1.896469568984189e-05, + "loss": 0.1478, "step": 6640 }, { - "epoch": 3.54, - "learning_rate": 2.1528073916133618e-05, - "loss": 0.2149, + "epoch": 4.32, + "learning_rate": 1.894303660385532e-05, + "loss": 0.1651, "step": 6650 }, { - "epoch": 3.55, - "learning_rate": 2.1510305614783225e-05, - "loss": 0.1164, + "epoch": 4.33, + "learning_rate": 1.8921377517868746e-05, + "loss": 0.1962, "step": 6660 }, { - "epoch": 3.55, - "learning_rate": 2.1492537313432835e-05, - "loss": 0.353, + "epoch": 4.33, + "learning_rate": 1.8899718431882175e-05, + "loss": 0.0931, "step": 6670 }, { - "epoch": 3.56, - "learning_rate": 2.1474769012082446e-05, - "loss": 0.4201, + "epoch": 4.34, + "learning_rate": 1.8878059345895603e-05, + "loss": 0.1451, "step": 6680 }, { - "epoch": 3.57, - "learning_rate": 2.1457000710732056e-05, - "loss": 0.1847, + "epoch": 4.35, + "learning_rate": 1.8856400259909032e-05, + "loss": 0.2826, "step": 6690 }, { - "epoch": 3.57, - "learning_rate": 2.1439232409381663e-05, - "loss": 0.2781, + "epoch": 4.35, + "learning_rate": 1.883474117392246e-05, + "loss": 0.0117, "step": 6700 }, { - "epoch": 3.58, - "learning_rate": 2.1421464108031273e-05, - "loss": 0.1057, + "epoch": 4.36, + "learning_rate": 1.881308208793589e-05, + "loss": 0.2076, "step": 6710 }, { - "epoch": 3.58, - "learning_rate": 2.140369580668088e-05, - "loss": 0.1671, + "epoch": 4.37, + "learning_rate": 1.8791423001949318e-05, + "loss": 0.2932, "step": 6720 }, { - "epoch": 3.59, - "learning_rate": 2.1385927505330493e-05, - "loss": 0.1736, + "epoch": 4.37, + "learning_rate": 1.8769763915962747e-05, + "loss": 0.0393, "step": 6730 }, { - "epoch": 3.59, - "learning_rate": 2.13681592039801e-05, - "loss": 0.4439, + "epoch": 4.38, + "learning_rate": 1.8748104829976176e-05, + "loss": 0.222, "step": 6740 }, { - "epoch": 3.6, - "learning_rate": 2.135039090262971e-05, - "loss": 0.5057, + "epoch": 4.38, + "learning_rate": 1.8726445743989604e-05, + "loss": 0.2544, "step": 6750 }, { - "epoch": 3.6, - "learning_rate": 2.1332622601279317e-05, - "loss": 0.478, + "epoch": 4.39, + "learning_rate": 1.8704786658003033e-05, + "loss": 0.0992, "step": 6760 }, { - "epoch": 3.61, - "learning_rate": 2.1314854299928928e-05, - "loss": 0.2195, + "epoch": 4.4, + "learning_rate": 1.868312757201646e-05, + "loss": 0.1865, "step": 6770 }, { - "epoch": 3.61, - "learning_rate": 2.1297085998578535e-05, - "loss": 0.3945, + "epoch": 4.4, + "learning_rate": 1.866146848602989e-05, + "loss": 0.0594, "step": 6780 }, { - "epoch": 3.62, - "learning_rate": 2.1279317697228148e-05, - "loss": 0.4781, + "epoch": 4.41, + "learning_rate": 1.863980940004332e-05, + "loss": 0.1626, "step": 6790 }, { - "epoch": 3.62, - "learning_rate": 2.1261549395877755e-05, - "loss": 0.307, + "epoch": 4.42, + "learning_rate": 1.8618150314056748e-05, + "loss": 0.2632, "step": 6800 }, { - "epoch": 3.63, - "learning_rate": 2.1243781094527365e-05, - "loss": 0.2389, + "epoch": 4.42, + "learning_rate": 1.8596491228070176e-05, + "loss": 0.409, "step": 6810 }, { - "epoch": 3.63, - "learning_rate": 2.1226012793176972e-05, - "loss": 0.2373, + "epoch": 4.43, + "learning_rate": 1.85748321420836e-05, + "loss": 0.2442, "step": 6820 }, { - "epoch": 3.64, - "learning_rate": 2.120824449182658e-05, - "loss": 0.2161, + "epoch": 4.44, + "learning_rate": 1.8553173056097034e-05, + "loss": 0.1129, "step": 6830 }, { - "epoch": 3.65, - "learning_rate": 2.1190476190476193e-05, - "loss": 0.199, + "epoch": 4.44, + "learning_rate": 1.8531513970110462e-05, + "loss": 0.2521, "step": 6840 }, { - "epoch": 3.65, - "learning_rate": 2.11727078891258e-05, - "loss": 0.3178, + "epoch": 4.45, + "learning_rate": 1.850985488412389e-05, + "loss": 0.2092, "step": 6850 }, { - "epoch": 3.66, - "learning_rate": 2.115493958777541e-05, - "loss": 0.3191, + "epoch": 4.46, + "learning_rate": 1.848819579813732e-05, + "loss": 0.1882, "step": 6860 }, { - "epoch": 3.66, - "learning_rate": 2.1137171286425017e-05, - "loss": 0.1229, + "epoch": 4.46, + "learning_rate": 1.846653671215075e-05, + "loss": 0.3425, "step": 6870 }, { - "epoch": 3.67, - "learning_rate": 2.1119402985074627e-05, - "loss": 0.2333, + "epoch": 4.47, + "learning_rate": 1.8444877626164177e-05, + "loss": 0.2234, "step": 6880 }, { - "epoch": 3.67, - "learning_rate": 2.1101634683724237e-05, - "loss": 0.234, + "epoch": 4.48, + "learning_rate": 1.8423218540177606e-05, + "loss": 0.0481, "step": 6890 }, { - "epoch": 3.68, - "learning_rate": 2.1083866382373847e-05, - "loss": 0.3015, + "epoch": 4.48, + "learning_rate": 1.840155945419103e-05, + "loss": 0.0574, "step": 6900 }, { - "epoch": 3.68, - "learning_rate": 2.1066098081023454e-05, - "loss": 0.3322, + "epoch": 4.49, + "learning_rate": 1.837990036820446e-05, + "loss": 0.0049, "step": 6910 }, { - "epoch": 3.69, - "learning_rate": 2.1048329779673065e-05, - "loss": 0.0702, + "epoch": 4.49, + "learning_rate": 1.8358241282217892e-05, + "loss": 0.0997, "step": 6920 }, { - "epoch": 3.69, - "learning_rate": 2.103056147832267e-05, - "loss": 0.2745, + "epoch": 4.5, + "learning_rate": 1.833658219623132e-05, + "loss": 0.3253, "step": 6930 }, { - "epoch": 3.7, - "learning_rate": 2.1012793176972285e-05, - "loss": 0.3747, + "epoch": 4.51, + "learning_rate": 1.831492311024475e-05, + "loss": 0.1426, "step": 6940 }, { - "epoch": 3.7, - "learning_rate": 2.0995024875621892e-05, - "loss": 0.1354, + "epoch": 4.51, + "learning_rate": 1.8293264024258178e-05, + "loss": 0.0564, "step": 6950 }, { - "epoch": 3.71, - "learning_rate": 2.0977256574271502e-05, - "loss": 0.3182, + "epoch": 4.52, + "learning_rate": 1.8271604938271607e-05, + "loss": 0.3849, "step": 6960 }, { - "epoch": 3.71, - "learning_rate": 2.095948827292111e-05, - "loss": 0.4134, + "epoch": 4.53, + "learning_rate": 1.8249945852285035e-05, + "loss": 0.0362, "step": 6970 }, { - "epoch": 3.72, - "learning_rate": 2.0941719971570716e-05, - "loss": 0.2383, + "epoch": 4.53, + "learning_rate": 1.822828676629846e-05, + "loss": 0.1942, "step": 6980 }, { - "epoch": 3.73, - "learning_rate": 2.0925728500355367e-05, - "loss": 0.2124, + "epoch": 4.54, + "learning_rate": 1.820662768031189e-05, + "loss": 0.2048, "step": 6990 }, { - "epoch": 3.73, - "learning_rate": 2.0907960199004978e-05, - "loss": 0.1736, + "epoch": 4.55, + "learning_rate": 1.8184968594325318e-05, + "loss": 0.1466, "step": 7000 }, { - "epoch": 3.74, - "learning_rate": 2.0890191897654585e-05, - "loss": 0.4486, + "epoch": 4.55, + "learning_rate": 1.816330950833875e-05, + "loss": 0.2379, "step": 7010 }, { - "epoch": 3.74, - "learning_rate": 2.0872423596304195e-05, - "loss": 0.2231, + "epoch": 4.56, + "learning_rate": 1.814165042235218e-05, + "loss": 0.1948, "step": 7020 }, { - "epoch": 3.75, - "learning_rate": 2.08546552949538e-05, - "loss": 0.3071, + "epoch": 4.57, + "learning_rate": 1.8119991336365607e-05, + "loss": 0.0612, "step": 7030 }, { - "epoch": 3.75, - "learning_rate": 2.0836886993603412e-05, - "loss": 0.2952, + "epoch": 4.57, + "learning_rate": 1.8098332250379036e-05, + "loss": 0.1641, "step": 7040 }, { - "epoch": 3.76, - "learning_rate": 2.0819118692253022e-05, - "loss": 0.1365, + "epoch": 4.58, + "learning_rate": 1.8076673164392465e-05, + "loss": 0.0618, "step": 7050 }, { - "epoch": 3.76, - "learning_rate": 2.080135039090263e-05, - "loss": 0.2228, + "epoch": 4.59, + "learning_rate": 1.805501407840589e-05, + "loss": 0.1693, "step": 7060 }, { - "epoch": 3.77, - "learning_rate": 2.078358208955224e-05, - "loss": 0.3413, + "epoch": 4.59, + "learning_rate": 1.803335499241932e-05, + "loss": 0.134, "step": 7070 }, { - "epoch": 3.77, - "learning_rate": 2.0765813788201846e-05, - "loss": 0.2294, + "epoch": 4.6, + "learning_rate": 1.8011695906432747e-05, + "loss": 0.3439, "step": 7080 }, { - "epoch": 3.78, - "learning_rate": 2.074804548685146e-05, - "loss": 0.1838, + "epoch": 4.61, + "learning_rate": 1.7990036820446176e-05, + "loss": 0.259, "step": 7090 }, { - "epoch": 3.78, - "learning_rate": 2.0730277185501067e-05, - "loss": 0.3928, + "epoch": 4.61, + "learning_rate": 1.7968377734459608e-05, + "loss": 0.114, "step": 7100 }, { - "epoch": 3.79, - "learning_rate": 2.0712508884150677e-05, - "loss": 0.4543, + "epoch": 4.62, + "learning_rate": 1.7946718648473037e-05, + "loss": 0.3295, "step": 7110 }, { - "epoch": 3.79, - "learning_rate": 2.0694740582800284e-05, - "loss": 0.2823, + "epoch": 4.62, + "learning_rate": 1.7925059562486466e-05, + "loss": 0.259, "step": 7120 }, { - "epoch": 3.8, - "learning_rate": 2.0676972281449894e-05, - "loss": 0.1503, + "epoch": 4.63, + "learning_rate": 1.7903400476499894e-05, + "loss": 0.3889, "step": 7130 }, { - "epoch": 3.8, - "learning_rate": 2.06592039800995e-05, - "loss": 0.0793, + "epoch": 4.64, + "learning_rate": 1.788174139051332e-05, + "loss": 0.1208, "step": 7140 }, { - "epoch": 3.81, - "learning_rate": 2.0641435678749115e-05, - "loss": 0.2807, + "epoch": 4.64, + "learning_rate": 1.7860082304526748e-05, + "loss": 0.1495, "step": 7150 }, { - "epoch": 3.82, - "learning_rate": 2.062366737739872e-05, - "loss": 0.1546, + "epoch": 4.65, + "learning_rate": 1.7838423218540177e-05, + "loss": 0.2276, "step": 7160 }, { - "epoch": 3.82, - "learning_rate": 2.060589907604833e-05, - "loss": 0.3252, + "epoch": 4.66, + "learning_rate": 1.7816764132553606e-05, + "loss": 0.4401, "step": 7170 }, { - "epoch": 3.83, - "learning_rate": 2.058813077469794e-05, - "loss": 0.1106, + "epoch": 4.66, + "learning_rate": 1.7795105046567034e-05, + "loss": 0.18, "step": 7180 }, { - "epoch": 3.83, - "learning_rate": 2.0570362473347545e-05, - "loss": 0.293, + "epoch": 4.67, + "learning_rate": 1.7773445960580466e-05, + "loss": 0.1499, "step": 7190 }, { - "epoch": 3.84, - "learning_rate": 2.055259417199716e-05, - "loss": 0.5158, + "epoch": 4.68, + "learning_rate": 1.7751786874593895e-05, + "loss": 0.1996, "step": 7200 }, { - "epoch": 3.84, - "learning_rate": 2.0534825870646766e-05, - "loss": 0.1873, + "epoch": 4.68, + "learning_rate": 1.7730127788607324e-05, + "loss": 0.3012, "step": 7210 }, { - "epoch": 3.85, - "learning_rate": 2.0517057569296376e-05, - "loss": 0.3522, + "epoch": 4.69, + "learning_rate": 1.770846870262075e-05, + "loss": 0.1885, "step": 7220 }, { - "epoch": 3.85, - "learning_rate": 2.0499289267945983e-05, - "loss": 0.1053, + "epoch": 4.7, + "learning_rate": 1.7686809616634178e-05, + "loss": 0.119, "step": 7230 }, { - "epoch": 3.86, - "learning_rate": 2.0481520966595593e-05, - "loss": 0.3428, + "epoch": 4.7, + "learning_rate": 1.7665150530647606e-05, + "loss": 0.2105, "step": 7240 }, { - "epoch": 3.86, - "learning_rate": 2.0463752665245204e-05, - "loss": 0.1377, + "epoch": 4.71, + "learning_rate": 1.7643491444661035e-05, + "loss": 0.1406, "step": 7250 }, { - "epoch": 3.87, - "learning_rate": 2.0445984363894814e-05, - "loss": 0.284, + "epoch": 4.72, + "learning_rate": 1.7621832358674464e-05, + "loss": 0.358, "step": 7260 }, { - "epoch": 3.87, - "learning_rate": 2.042821606254442e-05, - "loss": 0.1183, + "epoch": 4.72, + "learning_rate": 1.7600173272687892e-05, + "loss": 0.1969, "step": 7270 }, { - "epoch": 3.88, - "learning_rate": 2.041044776119403e-05, - "loss": 0.3718, + "epoch": 4.73, + "learning_rate": 1.7578514186701325e-05, + "loss": 0.0513, "step": 7280 }, { - "epoch": 3.88, - "learning_rate": 2.0392679459843638e-05, - "loss": 0.2731, + "epoch": 4.74, + "learning_rate": 1.755685510071475e-05, + "loss": 0.1709, "step": 7290 }, { - "epoch": 3.89, - "learning_rate": 2.037491115849325e-05, - "loss": 0.4646, + "epoch": 4.74, + "learning_rate": 1.753519601472818e-05, + "loss": 0.316, "step": 7300 }, { - "epoch": 3.9, - "learning_rate": 2.0357142857142858e-05, - "loss": 0.4484, + "epoch": 4.75, + "learning_rate": 1.7513536928741607e-05, + "loss": 0.0858, "step": 7310 }, { - "epoch": 3.9, - "learning_rate": 2.033937455579247e-05, - "loss": 0.0881, + "epoch": 4.75, + "learning_rate": 1.7491877842755036e-05, + "loss": 0.1269, "step": 7320 }, { - "epoch": 3.91, - "learning_rate": 2.0321606254442075e-05, - "loss": 0.3786, + "epoch": 4.76, + "learning_rate": 1.7470218756768465e-05, + "loss": 0.1272, "step": 7330 }, { - "epoch": 3.91, - "learning_rate": 2.0303837953091686e-05, - "loss": 0.2494, + "epoch": 4.77, + "learning_rate": 1.7448559670781893e-05, + "loss": 0.2098, "step": 7340 }, { - "epoch": 3.92, - "learning_rate": 2.0286069651741292e-05, - "loss": 0.2121, + "epoch": 4.77, + "learning_rate": 1.7426900584795322e-05, + "loss": 0.1316, "step": 7350 }, { - "epoch": 3.92, - "learning_rate": 2.0268301350390903e-05, - "loss": 0.3804, + "epoch": 4.78, + "learning_rate": 1.740524149880875e-05, + "loss": 0.1895, "step": 7360 }, { - "epoch": 3.93, - "learning_rate": 2.0250533049040513e-05, - "loss": 0.4915, + "epoch": 4.79, + "learning_rate": 1.738358241282218e-05, + "loss": 0.1917, "step": 7370 }, { - "epoch": 3.93, - "learning_rate": 2.023276474769012e-05, - "loss": 0.2501, + "epoch": 4.79, + "learning_rate": 1.7361923326835608e-05, + "loss": 0.2667, "step": 7380 }, { - "epoch": 3.94, - "learning_rate": 2.021499644633973e-05, - "loss": 0.2718, + "epoch": 4.8, + "learning_rate": 1.7340264240849037e-05, + "loss": 0.0624, "step": 7390 }, { - "epoch": 3.94, - "learning_rate": 2.0197228144989337e-05, - "loss": 0.3181, + "epoch": 4.81, + "learning_rate": 1.7318605154862465e-05, + "loss": 0.1343, "step": 7400 }, { - "epoch": 3.95, - "learning_rate": 2.017945984363895e-05, - "loss": 0.1964, + "epoch": 4.81, + "learning_rate": 1.7296946068875894e-05, + "loss": 0.1578, "step": 7410 }, { - "epoch": 3.95, - "learning_rate": 2.0161691542288557e-05, - "loss": 0.1467, + "epoch": 4.82, + "learning_rate": 1.7275286982889323e-05, + "loss": 0.0942, "step": 7420 }, { - "epoch": 3.96, - "learning_rate": 2.0143923240938168e-05, - "loss": 0.1065, + "epoch": 4.83, + "learning_rate": 1.725362789690275e-05, + "loss": 0.1821, "step": 7430 }, { - "epoch": 3.96, - "learning_rate": 2.0126154939587775e-05, - "loss": 0.2254, + "epoch": 4.83, + "learning_rate": 1.723196881091618e-05, + "loss": 0.1143, "step": 7440 }, { - "epoch": 3.97, - "learning_rate": 2.0108386638237385e-05, - "loss": 0.3131, + "epoch": 4.84, + "learning_rate": 1.7210309724929605e-05, + "loss": 0.2072, "step": 7450 }, { - "epoch": 3.98, - "learning_rate": 2.0090618336886995e-05, - "loss": 0.267, + "epoch": 4.85, + "learning_rate": 1.7188650638943038e-05, + "loss": 0.3436, "step": 7460 }, { - "epoch": 3.98, - "learning_rate": 2.0072850035536605e-05, - "loss": 0.0624, + "epoch": 4.85, + "learning_rate": 1.7166991552956466e-05, + "loss": 0.2031, "step": 7470 }, { - "epoch": 3.99, - "learning_rate": 2.0055081734186212e-05, - "loss": 0.1262, + "epoch": 4.86, + "learning_rate": 1.7145332466969895e-05, + "loss": 0.1608, "step": 7480 }, { - "epoch": 3.99, - "learning_rate": 2.0037313432835822e-05, - "loss": 0.2267, + "epoch": 4.87, + "learning_rate": 1.7123673380983324e-05, + "loss": 0.1898, "step": 7490 }, { - "epoch": 4.0, - "learning_rate": 2.001954513148543e-05, - "loss": 0.0953, + "epoch": 4.87, + "learning_rate": 1.7102014294996752e-05, + "loss": 0.2166, "step": 7500 }, { - "epoch": 4.0, - "eval_accuracy": 0.9671574178935447, - "eval_loss": 0.14878489077091217, - "eval_runtime": 9.4741, - "eval_samples_per_second": 279.604, - "eval_steps_per_second": 69.98, - "step": 7506 + "epoch": 4.88, + "learning_rate": 1.708035520901018e-05, + "loss": 0.1145, + "step": 7510 }, { - "epoch": 4.0, - "learning_rate": 2.000177683013504e-05, - "loss": 0.0764, - "step": 7510 + "epoch": 4.88, + "learning_rate": 1.705869612302361e-05, + "loss": 0.3105, + "step": 7520 }, { - "epoch": 4.01, - "learning_rate": 1.998400852878465e-05, - "loss": 0.2969, - "step": 7520 - }, - { - "epoch": 4.01, - "learning_rate": 1.9966240227434257e-05, - "loss": 0.1254, + "epoch": 4.89, + "learning_rate": 1.7037037037037035e-05, + "loss": 0.2545, "step": 7530 }, { - "epoch": 4.02, - "learning_rate": 1.9948471926083867e-05, - "loss": 0.2758, + "epoch": 4.9, + "learning_rate": 1.7015377951050464e-05, + "loss": 0.016, "step": 7540 }, { - "epoch": 4.02, - "learning_rate": 1.9930703624733474e-05, - "loss": 0.1463, + "epoch": 4.9, + "learning_rate": 1.6993718865063896e-05, + "loss": 0.3899, "step": 7550 }, { - "epoch": 4.03, - "learning_rate": 1.9912935323383084e-05, - "loss": 0.0817, + "epoch": 4.91, + "learning_rate": 1.6972059779077324e-05, + "loss": 0.1974, "step": 7560 }, { - "epoch": 4.03, - "learning_rate": 1.9895167022032694e-05, - "loss": 0.2519, + "epoch": 4.92, + "learning_rate": 1.6950400693090753e-05, + "loss": 0.0903, "step": 7570 }, { - "epoch": 4.04, - "learning_rate": 1.9877398720682305e-05, - "loss": 0.0903, + "epoch": 4.92, + "learning_rate": 1.6928741607104182e-05, + "loss": 0.1623, "step": 7580 }, { - "epoch": 4.04, - "learning_rate": 1.985963041933191e-05, - "loss": 0.1582, + "epoch": 4.93, + "learning_rate": 1.690708252111761e-05, + "loss": 0.2203, "step": 7590 }, { - "epoch": 4.05, - "learning_rate": 1.9841862117981522e-05, - "loss": 0.2454, + "epoch": 4.94, + "learning_rate": 1.688542343513104e-05, + "loss": 0.2525, "step": 7600 }, { - "epoch": 4.06, - "learning_rate": 1.982409381663113e-05, - "loss": 0.2263, + "epoch": 4.94, + "learning_rate": 1.6863764349144464e-05, + "loss": 0.3311, "step": 7610 }, { - "epoch": 4.06, - "learning_rate": 1.9806325515280742e-05, - "loss": 0.1168, + "epoch": 4.95, + "learning_rate": 1.6842105263157893e-05, + "loss": 0.0228, "step": 7620 }, { - "epoch": 4.07, - "learning_rate": 1.978855721393035e-05, - "loss": 0.3373, + "epoch": 4.96, + "learning_rate": 1.6820446177171322e-05, + "loss": 0.2533, "step": 7630 }, { - "epoch": 4.07, - "learning_rate": 1.977078891257996e-05, - "loss": 0.127, + "epoch": 4.96, + "learning_rate": 1.6798787091184754e-05, + "loss": 0.1275, "step": 7640 }, { - "epoch": 4.08, - "learning_rate": 1.9753020611229566e-05, - "loss": 0.0557, + "epoch": 4.97, + "learning_rate": 1.6777128005198183e-05, + "loss": 0.0841, "step": 7650 }, { - "epoch": 4.08, - "learning_rate": 1.9735252309879176e-05, - "loss": 0.1603, + "epoch": 4.98, + "learning_rate": 1.675546891921161e-05, + "loss": 0.2046, "step": 7660 }, { - "epoch": 4.09, - "learning_rate": 1.9717484008528787e-05, - "loss": 0.2788, + "epoch": 4.98, + "learning_rate": 1.673380983322504e-05, + "loss": 0.2394, "step": 7670 }, { - "epoch": 4.09, - "learning_rate": 1.9699715707178394e-05, - "loss": 0.1263, + "epoch": 4.99, + "learning_rate": 1.671215074723847e-05, + "loss": 0.1007, "step": 7680 }, { - "epoch": 4.1, - "learning_rate": 1.9681947405828004e-05, - "loss": 0.2358, + "epoch": 5.0, + "learning_rate": 1.6690491661251894e-05, + "loss": 0.0272, "step": 7690 }, { - "epoch": 4.1, - "learning_rate": 1.966417910447761e-05, - "loss": 0.4211, + "epoch": 5.0, + "eval_accuracy": 0.9829806807727691, + "eval_loss": 0.08533850312232971, + "eval_runtime": 12.8473, + "eval_samples_per_second": 169.218, + "eval_steps_per_second": 42.343, + "step": 7697 + }, + { + "epoch": 5.0, + "learning_rate": 1.6668832575265323e-05, + "loss": 0.1804, "step": 7700 }, { - "epoch": 4.11, - "learning_rate": 1.964641080312722e-05, - "loss": 0.3264, + "epoch": 5.01, + "learning_rate": 1.664717348927875e-05, + "loss": 0.0881, "step": 7710 }, { - "epoch": 4.11, - "learning_rate": 1.962864250177683e-05, - "loss": 0.1689, + "epoch": 5.01, + "learning_rate": 1.662551440329218e-05, + "loss": 0.3207, "step": 7720 }, { - "epoch": 4.12, - "learning_rate": 1.961087420042644e-05, - "loss": 0.1767, + "epoch": 5.02, + "learning_rate": 1.660385531730561e-05, + "loss": 0.046, "step": 7730 }, { - "epoch": 4.12, - "learning_rate": 1.9593105899076048e-05, - "loss": 0.2087, + "epoch": 5.03, + "learning_rate": 1.658219623131904e-05, + "loss": 0.0632, "step": 7740 }, { - "epoch": 4.13, - "learning_rate": 1.957533759772566e-05, - "loss": 0.1791, + "epoch": 5.03, + "learning_rate": 1.656053714533247e-05, + "loss": 0.492, "step": 7750 }, { - "epoch": 4.14, - "learning_rate": 1.9557569296375265e-05, - "loss": 0.1712, + "epoch": 5.04, + "learning_rate": 1.6538878059345898e-05, + "loss": 0.1749, "step": 7760 }, { - "epoch": 4.14, - "learning_rate": 1.9539800995024876e-05, - "loss": 0.1747, + "epoch": 5.05, + "learning_rate": 1.6517218973359323e-05, + "loss": 0.0785, "step": 7770 }, { - "epoch": 4.15, - "learning_rate": 1.9522032693674486e-05, - "loss": 0.419, + "epoch": 5.05, + "learning_rate": 1.6495559887372752e-05, + "loss": 0.0355, "step": 7780 }, { - "epoch": 4.15, - "learning_rate": 1.9504264392324096e-05, - "loss": 0.2604, + "epoch": 5.06, + "learning_rate": 1.647390080138618e-05, + "loss": 0.2957, "step": 7790 }, { - "epoch": 4.16, - "learning_rate": 1.9486496090973703e-05, - "loss": 0.2969, + "epoch": 5.07, + "learning_rate": 1.645224171539961e-05, + "loss": 0.3177, "step": 7800 }, { - "epoch": 4.16, - "learning_rate": 1.9468727789623313e-05, - "loss": 0.239, + "epoch": 5.07, + "learning_rate": 1.6430582629413038e-05, + "loss": 0.1878, "step": 7810 }, { - "epoch": 4.17, - "learning_rate": 1.945095948827292e-05, - "loss": 0.4185, + "epoch": 5.08, + "learning_rate": 1.6408923543426467e-05, + "loss": 0.1447, "step": 7820 }, { - "epoch": 4.17, - "learning_rate": 1.943319118692253e-05, - "loss": 0.2845, + "epoch": 5.09, + "learning_rate": 1.63872644574399e-05, + "loss": 0.2844, "step": 7830 }, { - "epoch": 4.18, - "learning_rate": 1.941542288557214e-05, - "loss": 0.2703, + "epoch": 5.09, + "learning_rate": 1.6365605371453328e-05, + "loss": 0.0256, "step": 7840 }, { - "epoch": 4.18, - "learning_rate": 1.9397654584221748e-05, - "loss": 0.1846, + "epoch": 5.1, + "learning_rate": 1.6343946285466753e-05, + "loss": 0.0758, "step": 7850 }, { - "epoch": 4.19, - "learning_rate": 1.9379886282871358e-05, - "loss": 0.214, + "epoch": 5.11, + "learning_rate": 1.632228719948018e-05, + "loss": 0.1041, "step": 7860 }, { - "epoch": 4.19, - "learning_rate": 1.9362117981520965e-05, - "loss": 0.4039, + "epoch": 5.11, + "learning_rate": 1.630062811349361e-05, + "loss": 0.1667, "step": 7870 }, { - "epoch": 4.2, - "learning_rate": 1.9344349680170578e-05, - "loss": 0.2378, + "epoch": 5.12, + "learning_rate": 1.627896902750704e-05, + "loss": 0.2194, "step": 7880 }, { - "epoch": 4.2, - "learning_rate": 1.9326581378820185e-05, - "loss": 0.1834, + "epoch": 5.13, + "learning_rate": 1.6257309941520468e-05, + "loss": 0.2497, "step": 7890 }, { - "epoch": 4.21, - "learning_rate": 1.9308813077469795e-05, - "loss": 0.2221, + "epoch": 5.13, + "learning_rate": 1.6235650855533896e-05, + "loss": 0.2496, "step": 7900 }, { - "epoch": 4.22, - "learning_rate": 1.9291044776119402e-05, - "loss": 0.275, + "epoch": 5.14, + "learning_rate": 1.6213991769547325e-05, + "loss": 0.2154, "step": 7910 }, { - "epoch": 4.22, - "learning_rate": 1.9273276474769013e-05, - "loss": 0.2628, + "epoch": 5.14, + "learning_rate": 1.6192332683560757e-05, + "loss": 0.219, "step": 7920 }, { - "epoch": 4.23, - "learning_rate": 1.925550817341862e-05, - "loss": 0.2543, + "epoch": 5.15, + "learning_rate": 1.6170673597574182e-05, + "loss": 0.0798, "step": 7930 }, { - "epoch": 4.23, - "learning_rate": 1.9237739872068233e-05, - "loss": 0.2252, + "epoch": 5.16, + "learning_rate": 1.614901451158761e-05, + "loss": 0.2998, "step": 7940 }, { - "epoch": 4.24, - "learning_rate": 1.921997157071784e-05, - "loss": 0.1846, + "epoch": 5.16, + "learning_rate": 1.612735542560104e-05, + "loss": 0.0871, "step": 7950 }, { - "epoch": 4.24, - "learning_rate": 1.920220326936745e-05, - "loss": 0.0959, + "epoch": 5.17, + "learning_rate": 1.610569633961447e-05, + "loss": 0.1863, "step": 7960 }, { - "epoch": 4.25, - "learning_rate": 1.9184434968017057e-05, - "loss": 0.2216, + "epoch": 5.18, + "learning_rate": 1.6084037253627897e-05, + "loss": 0.1953, "step": 7970 }, { - "epoch": 4.25, - "learning_rate": 1.9166666666666667e-05, - "loss": 0.1448, + "epoch": 5.18, + "learning_rate": 1.6062378167641326e-05, + "loss": 0.2771, "step": 7980 }, { - "epoch": 4.26, - "learning_rate": 1.9148898365316277e-05, - "loss": 0.2352, + "epoch": 5.19, + "learning_rate": 1.6040719081654754e-05, + "loss": 0.1713, "step": 7990 }, { - "epoch": 4.26, - "learning_rate": 1.9131130063965884e-05, - "loss": 0.2829, + "epoch": 5.2, + "learning_rate": 1.602122590426684e-05, + "loss": 0.4941, "step": 8000 }, { - "epoch": 4.27, - "learning_rate": 1.9113361762615495e-05, - "loss": 0.2239, + "epoch": 5.2, + "learning_rate": 1.599956681828027e-05, + "loss": 0.0853, "step": 8010 }, { - "epoch": 4.27, - "learning_rate": 1.90955934612651e-05, - "loss": 0.1628, + "epoch": 5.21, + "learning_rate": 1.5977907732293696e-05, + "loss": 0.1868, "step": 8020 }, { - "epoch": 4.28, - "learning_rate": 1.9077825159914712e-05, - "loss": 0.2413, + "epoch": 5.22, + "learning_rate": 1.5956248646307124e-05, + "loss": 0.2171, "step": 8030 }, { - "epoch": 4.28, - "learning_rate": 1.9060056858564322e-05, - "loss": 0.2397, + "epoch": 5.22, + "learning_rate": 1.5934589560320553e-05, + "loss": 0.0884, "step": 8040 }, { - "epoch": 4.29, - "learning_rate": 1.9042288557213932e-05, - "loss": 0.3642, + "epoch": 5.23, + "learning_rate": 1.591293047433398e-05, + "loss": 0.2246, "step": 8050 }, { - "epoch": 4.3, - "learning_rate": 1.902452025586354e-05, - "loss": 0.4284, + "epoch": 5.24, + "learning_rate": 1.5891271388347414e-05, + "loss": 0.1167, "step": 8060 }, { - "epoch": 4.3, - "learning_rate": 1.900675195451315e-05, - "loss": 0.2745, + "epoch": 5.24, + "learning_rate": 1.5869612302360842e-05, + "loss": 0.2971, "step": 8070 }, { - "epoch": 4.31, - "learning_rate": 1.8988983653162756e-05, - "loss": 0.3359, + "epoch": 5.25, + "learning_rate": 1.584795321637427e-05, + "loss": 0.1353, "step": 8080 }, { - "epoch": 4.31, - "learning_rate": 1.897121535181237e-05, - "loss": 0.1384, + "epoch": 5.25, + "learning_rate": 1.58262941303877e-05, + "loss": 0.1755, "step": 8090 }, { - "epoch": 4.32, - "learning_rate": 1.8953447050461977e-05, - "loss": 0.0446, + "epoch": 5.26, + "learning_rate": 1.5804635044401125e-05, + "loss": 0.1807, "step": 8100 }, { - "epoch": 4.32, - "learning_rate": 1.8935678749111587e-05, - "loss": 0.0758, + "epoch": 5.27, + "learning_rate": 1.5782975958414554e-05, + "loss": 0.1284, "step": 8110 }, { - "epoch": 4.33, - "learning_rate": 1.8917910447761194e-05, - "loss": 0.23, + "epoch": 5.27, + "learning_rate": 1.5761316872427982e-05, + "loss": 0.113, "step": 8120 }, { - "epoch": 4.33, - "learning_rate": 1.8900142146410804e-05, - "loss": 0.4225, + "epoch": 5.28, + "learning_rate": 1.573965778644141e-05, + "loss": 0.163, "step": 8130 }, { - "epoch": 4.34, - "learning_rate": 1.888237384506041e-05, - "loss": 0.3431, + "epoch": 5.29, + "learning_rate": 1.571799870045484e-05, + "loss": 0.2105, "step": 8140 }, { - "epoch": 4.34, - "learning_rate": 1.886460554371002e-05, - "loss": 0.503, + "epoch": 5.29, + "learning_rate": 1.5696339614468272e-05, + "loss": 0.2947, "step": 8150 }, { - "epoch": 4.35, - "learning_rate": 1.884683724235963e-05, - "loss": 0.2698, + "epoch": 5.3, + "learning_rate": 1.56746805284817e-05, + "loss": 0.0778, "step": 8160 }, { - "epoch": 4.35, - "learning_rate": 1.882906894100924e-05, - "loss": 0.3681, + "epoch": 5.31, + "learning_rate": 1.565302144249513e-05, + "loss": 0.2409, "step": 8170 }, { - "epoch": 4.36, - "learning_rate": 1.881130063965885e-05, - "loss": 0.3156, + "epoch": 5.31, + "learning_rate": 1.5631362356508555e-05, + "loss": 0.2679, "step": 8180 }, { - "epoch": 4.36, - "learning_rate": 1.8793532338308455e-05, - "loss": 0.3023, + "epoch": 5.32, + "learning_rate": 1.5609703270521983e-05, + "loss": 0.1457, "step": 8190 }, { - "epoch": 4.37, - "learning_rate": 1.877576403695807e-05, - "loss": 0.2379, + "epoch": 5.33, + "learning_rate": 1.5588044184535412e-05, + "loss": 0.2009, "step": 8200 }, { - "epoch": 4.38, - "learning_rate": 1.8757995735607676e-05, - "loss": 0.2404, + "epoch": 5.33, + "learning_rate": 1.556638509854884e-05, + "loss": 0.1151, "step": 8210 }, { - "epoch": 4.38, - "learning_rate": 1.8740227434257286e-05, - "loss": 0.5778, + "epoch": 5.34, + "learning_rate": 1.554472601256227e-05, + "loss": 0.1441, "step": 8220 }, { - "epoch": 4.39, - "learning_rate": 1.8722459132906893e-05, - "loss": 0.08, + "epoch": 5.35, + "learning_rate": 1.5523066926575698e-05, + "loss": 0.043, "step": 8230 }, { - "epoch": 4.39, - "learning_rate": 1.8704690831556503e-05, - "loss": 0.1948, + "epoch": 5.35, + "learning_rate": 1.550140784058913e-05, + "loss": 0.344, "step": 8240 }, { - "epoch": 4.4, - "learning_rate": 1.8686922530206114e-05, - "loss": 0.1052, + "epoch": 5.36, + "learning_rate": 1.547974875460256e-05, + "loss": 0.1488, "step": 8250 }, { - "epoch": 4.4, - "learning_rate": 1.8669154228855724e-05, - "loss": 0.1484, + "epoch": 5.37, + "learning_rate": 1.5458089668615984e-05, + "loss": 0.3524, "step": 8260 }, { - "epoch": 4.41, - "learning_rate": 1.865138592750533e-05, - "loss": 0.3001, + "epoch": 5.37, + "learning_rate": 1.5436430582629413e-05, + "loss": 0.1053, "step": 8270 }, { - "epoch": 4.41, - "learning_rate": 1.863361762615494e-05, - "loss": 0.4367, + "epoch": 5.38, + "learning_rate": 1.541477149664284e-05, + "loss": 0.3589, "step": 8280 }, { - "epoch": 4.42, - "learning_rate": 1.8615849324804548e-05, - "loss": 0.0705, + "epoch": 5.38, + "learning_rate": 1.539311241065627e-05, + "loss": 0.1829, "step": 8290 }, { - "epoch": 4.42, - "learning_rate": 1.859808102345416e-05, - "loss": 0.437, + "epoch": 5.39, + "learning_rate": 1.53714533246697e-05, + "loss": 0.2131, "step": 8300 }, { - "epoch": 4.43, - "learning_rate": 1.8580312722103768e-05, - "loss": 0.3417, + "epoch": 5.4, + "learning_rate": 1.5349794238683127e-05, + "loss": 0.0702, "step": 8310 }, { - "epoch": 4.43, - "learning_rate": 1.8562544420753375e-05, - "loss": 0.3891, + "epoch": 5.4, + "learning_rate": 1.5328135152696556e-05, + "loss": 0.0808, "step": 8320 }, { - "epoch": 4.44, - "learning_rate": 1.8544776119402985e-05, - "loss": 0.1453, + "epoch": 5.41, + "learning_rate": 1.5306476066709988e-05, + "loss": 0.184, "step": 8330 }, { - "epoch": 4.44, - "learning_rate": 1.8527007818052592e-05, - "loss": 0.395, + "epoch": 5.42, + "learning_rate": 1.5284816980723414e-05, + "loss": 0.3782, "step": 8340 }, { - "epoch": 4.45, - "learning_rate": 1.8509239516702203e-05, - "loss": 0.0935, + "epoch": 5.42, + "learning_rate": 1.5263157894736842e-05, + "loss": 0.021, "step": 8350 }, { - "epoch": 4.46, - "learning_rate": 1.8491471215351813e-05, - "loss": 0.336, + "epoch": 5.43, + "learning_rate": 1.5241498808750271e-05, + "loss": 0.1233, "step": 8360 }, { - "epoch": 4.46, - "learning_rate": 1.8473702914001423e-05, - "loss": 0.2458, + "epoch": 5.44, + "learning_rate": 1.52198397227637e-05, + "loss": 0.2307, "step": 8370 }, { - "epoch": 4.47, - "learning_rate": 1.845593461265103e-05, - "loss": 0.0496, + "epoch": 5.44, + "learning_rate": 1.5198180636777128e-05, + "loss": 0.3145, "step": 8380 }, { - "epoch": 4.47, - "learning_rate": 1.843816631130064e-05, - "loss": 0.3679, + "epoch": 5.45, + "learning_rate": 1.5176521550790557e-05, + "loss": 0.1034, "step": 8390 }, { - "epoch": 4.48, - "learning_rate": 1.8420398009950247e-05, - "loss": 0.3313, + "epoch": 5.46, + "learning_rate": 1.5154862464803984e-05, + "loss": 0.0123, "step": 8400 }, { - "epoch": 4.48, - "learning_rate": 1.840262970859986e-05, - "loss": 0.2541, + "epoch": 5.46, + "learning_rate": 1.5133203378817413e-05, + "loss": 0.1678, "step": 8410 }, { - "epoch": 4.49, - "learning_rate": 1.8384861407249468e-05, - "loss": 0.1084, + "epoch": 5.47, + "learning_rate": 1.5111544292830845e-05, + "loss": 0.1051, "step": 8420 }, { - "epoch": 4.49, - "learning_rate": 1.8367093105899078e-05, - "loss": 0.3132, + "epoch": 5.48, + "learning_rate": 1.5089885206844273e-05, + "loss": 0.0742, "step": 8430 }, { - "epoch": 4.5, - "learning_rate": 1.8349324804548685e-05, - "loss": 0.1741, + "epoch": 5.48, + "learning_rate": 1.50682261208577e-05, + "loss": 0.2037, "step": 8440 }, { - "epoch": 4.5, - "learning_rate": 1.8331556503198295e-05, - "loss": 0.0488, + "epoch": 5.49, + "learning_rate": 1.5046567034871129e-05, + "loss": 0.3068, "step": 8450 }, { - "epoch": 4.51, - "learning_rate": 1.8313788201847905e-05, - "loss": 0.2318, + "epoch": 5.5, + "learning_rate": 1.5024907948884558e-05, + "loss": 0.2932, "step": 8460 }, { - "epoch": 4.51, - "learning_rate": 1.8296019900497515e-05, - "loss": 0.1861, + "epoch": 5.5, + "learning_rate": 1.5003248862897986e-05, + "loss": 0.0899, "step": 8470 }, { - "epoch": 4.52, - "learning_rate": 1.8278251599147122e-05, - "loss": 0.2651, + "epoch": 5.51, + "learning_rate": 1.4981589776911413e-05, + "loss": 0.1688, "step": 8480 }, { - "epoch": 4.52, - "learning_rate": 1.826048329779673e-05, - "loss": 0.3141, + "epoch": 5.51, + "learning_rate": 1.4959930690924844e-05, + "loss": 0.2213, "step": 8490 }, { - "epoch": 4.53, - "learning_rate": 1.824271499644634e-05, - "loss": 0.1694, + "epoch": 5.52, + "learning_rate": 1.4938271604938272e-05, + "loss": 0.1739, "step": 8500 }, { - "epoch": 4.54, - "learning_rate": 1.822494669509595e-05, - "loss": 0.1018, + "epoch": 5.53, + "learning_rate": 1.4916612518951701e-05, + "loss": 0.1328, "step": 8510 }, { - "epoch": 4.54, - "learning_rate": 1.820717839374556e-05, - "loss": 0.1763, + "epoch": 5.53, + "learning_rate": 1.4894953432965128e-05, + "loss": 0.0799, "step": 8520 }, { - "epoch": 4.55, - "learning_rate": 1.8189410092395167e-05, - "loss": 0.194, + "epoch": 5.54, + "learning_rate": 1.4873294346978557e-05, + "loss": 0.0648, "step": 8530 }, { - "epoch": 4.55, - "learning_rate": 1.8171641791044777e-05, - "loss": 0.1784, + "epoch": 5.55, + "learning_rate": 1.4851635260991987e-05, + "loss": 0.1861, "step": 8540 }, { - "epoch": 4.56, - "learning_rate": 1.8153873489694384e-05, - "loss": 0.1291, + "epoch": 5.55, + "learning_rate": 1.4829976175005416e-05, + "loss": 0.1486, "step": 8550 }, { - "epoch": 4.56, - "learning_rate": 1.8136105188343994e-05, - "loss": 0.3637, + "epoch": 5.56, + "learning_rate": 1.4808317089018843e-05, + "loss": 0.3231, "step": 8560 }, { - "epoch": 4.57, - "learning_rate": 1.8118336886993604e-05, - "loss": 0.3705, + "epoch": 5.57, + "learning_rate": 1.4786658003032272e-05, + "loss": 0.0632, "step": 8570 }, { - "epoch": 4.57, - "learning_rate": 1.8100568585643215e-05, - "loss": 0.321, + "epoch": 5.57, + "learning_rate": 1.4764998917045702e-05, + "loss": 0.0212, "step": 8580 }, { - "epoch": 4.58, - "learning_rate": 1.808280028429282e-05, - "loss": 0.409, + "epoch": 5.58, + "learning_rate": 1.474333983105913e-05, + "loss": 0.0212, "step": 8590 }, { - "epoch": 4.58, - "learning_rate": 1.8065031982942432e-05, - "loss": 0.2915, + "epoch": 5.59, + "learning_rate": 1.4721680745072558e-05, + "loss": 0.0259, "step": 8600 }, { - "epoch": 4.59, - "learning_rate": 1.804726368159204e-05, - "loss": 0.1324, + "epoch": 5.59, + "learning_rate": 1.4700021659085986e-05, + "loss": 0.2181, "step": 8610 }, { - "epoch": 4.59, - "learning_rate": 1.8029495380241652e-05, - "loss": 0.2947, + "epoch": 5.6, + "learning_rate": 1.4678362573099415e-05, + "loss": 0.1272, "step": 8620 }, { - "epoch": 4.6, - "learning_rate": 1.801172707889126e-05, - "loss": 0.3378, + "epoch": 5.61, + "learning_rate": 1.4656703487112845e-05, + "loss": 0.3194, "step": 8630 }, { - "epoch": 4.6, - "learning_rate": 1.7993958777540866e-05, - "loss": 0.2507, + "epoch": 5.61, + "learning_rate": 1.4635044401126272e-05, + "loss": 0.1792, "step": 8640 }, { - "epoch": 4.61, - "learning_rate": 1.7976190476190476e-05, - "loss": 0.1127, + "epoch": 5.62, + "learning_rate": 1.4613385315139701e-05, + "loss": 0.1701, "step": 8650 }, { - "epoch": 4.61, - "learning_rate": 1.7958422174840083e-05, - "loss": 0.0501, + "epoch": 5.63, + "learning_rate": 1.459172622915313e-05, + "loss": 0.2487, "step": 8660 }, { - "epoch": 4.62, - "learning_rate": 1.7940653873489697e-05, - "loss": 0.4004, + "epoch": 5.63, + "learning_rate": 1.457006714316656e-05, + "loss": 0.0454, "step": 8670 }, { - "epoch": 4.63, - "learning_rate": 1.7922885572139304e-05, - "loss": 0.2578, + "epoch": 5.64, + "learning_rate": 1.4548408057179987e-05, + "loss": 0.1839, "step": 8680 }, { - "epoch": 4.63, - "learning_rate": 1.7905117270788914e-05, - "loss": 0.1925, + "epoch": 5.64, + "learning_rate": 1.4526748971193416e-05, + "loss": 0.2466, "step": 8690 }, { - "epoch": 4.64, - "learning_rate": 1.788734896943852e-05, - "loss": 0.233, + "epoch": 5.65, + "learning_rate": 1.4505089885206844e-05, + "loss": 0.2125, "step": 8700 }, { - "epoch": 4.64, - "learning_rate": 1.786958066808813e-05, - "loss": 0.0282, + "epoch": 5.66, + "learning_rate": 1.4483430799220273e-05, + "loss": 0.1713, "step": 8710 }, { - "epoch": 4.65, - "learning_rate": 1.785181236673774e-05, - "loss": 0.0692, + "epoch": 5.66, + "learning_rate": 1.4461771713233702e-05, + "loss": 0.1824, "step": 8720 }, { - "epoch": 4.65, - "learning_rate": 1.783404406538735e-05, - "loss": 0.2596, + "epoch": 5.67, + "learning_rate": 1.444011262724713e-05, + "loss": 0.1248, "step": 8730 }, { - "epoch": 4.66, - "learning_rate": 1.781627576403696e-05, - "loss": 0.2622, + "epoch": 5.68, + "learning_rate": 1.441845354126056e-05, + "loss": 0.0942, "step": 8740 }, { - "epoch": 4.66, - "learning_rate": 1.779850746268657e-05, - "loss": 0.2482, + "epoch": 5.68, + "learning_rate": 1.4396794455273988e-05, + "loss": 0.2349, "step": 8750 }, { - "epoch": 4.67, - "learning_rate": 1.7780739161336175e-05, - "loss": 0.5789, + "epoch": 5.69, + "learning_rate": 1.4375135369287417e-05, + "loss": 0.1787, "step": 8760 }, { - "epoch": 4.67, - "learning_rate": 1.7762970859985786e-05, - "loss": 0.2494, + "epoch": 5.7, + "learning_rate": 1.4353476283300845e-05, + "loss": 0.3789, "step": 8770 }, { - "epoch": 4.68, - "learning_rate": 1.7745202558635396e-05, - "loss": 0.1579, + "epoch": 5.7, + "learning_rate": 1.4331817197314274e-05, + "loss": 0.166, "step": 8780 }, { - "epoch": 4.68, - "learning_rate": 1.7727434257285006e-05, - "loss": 0.1863, + "epoch": 5.71, + "learning_rate": 1.4310158111327703e-05, + "loss": 0.2508, "step": 8790 }, { - "epoch": 4.69, - "learning_rate": 1.7709665955934613e-05, - "loss": 0.1293, + "epoch": 5.72, + "learning_rate": 1.428849902534113e-05, + "loss": 0.3274, "step": 8800 }, { - "epoch": 4.69, - "learning_rate": 1.769189765458422e-05, - "loss": 0.3173, + "epoch": 5.72, + "learning_rate": 1.426683993935456e-05, + "loss": 0.0026, "step": 8810 }, { - "epoch": 4.7, - "learning_rate": 1.767412935323383e-05, - "loss": 0.1341, + "epoch": 5.73, + "learning_rate": 1.4245180853367989e-05, + "loss": 0.3321, "step": 8820 }, { - "epoch": 4.71, - "learning_rate": 1.765636105188344e-05, - "loss": 0.1315, + "epoch": 5.74, + "learning_rate": 1.4223521767381417e-05, + "loss": 0.4053, "step": 8830 }, { - "epoch": 4.71, - "learning_rate": 1.763859275053305e-05, - "loss": 0.3275, + "epoch": 5.74, + "learning_rate": 1.4201862681394844e-05, + "loss": 0.2369, "step": 8840 }, { - "epoch": 4.72, - "learning_rate": 1.7620824449182658e-05, - "loss": 0.1193, + "epoch": 5.75, + "learning_rate": 1.4180203595408275e-05, + "loss": 0.0657, "step": 8850 }, { - "epoch": 4.72, - "learning_rate": 1.7603056147832268e-05, - "loss": 0.1727, + "epoch": 5.76, + "learning_rate": 1.4158544509421703e-05, + "loss": 0.1151, "step": 8860 }, { - "epoch": 4.73, - "learning_rate": 1.7585287846481875e-05, - "loss": 0.0876, + "epoch": 5.76, + "learning_rate": 1.4136885423435132e-05, + "loss": 0.2244, "step": 8870 }, { - "epoch": 4.73, - "learning_rate": 1.756751954513149e-05, - "loss": 0.2599, + "epoch": 5.77, + "learning_rate": 1.4115226337448559e-05, + "loss": 0.0992, "step": 8880 }, { - "epoch": 4.74, - "learning_rate": 1.7549751243781095e-05, - "loss": 0.2715, + "epoch": 5.77, + "learning_rate": 1.4093567251461988e-05, + "loss": 0.0408, "step": 8890 }, { - "epoch": 4.74, - "learning_rate": 1.7531982942430705e-05, - "loss": 0.1787, + "epoch": 5.78, + "learning_rate": 1.4071908165475418e-05, + "loss": 0.1377, "step": 8900 }, { - "epoch": 4.75, - "learning_rate": 1.7514214641080312e-05, - "loss": 0.0881, + "epoch": 5.79, + "learning_rate": 1.4050249079488847e-05, + "loss": 0.2829, "step": 8910 }, { - "epoch": 4.75, - "learning_rate": 1.7496446339729923e-05, - "loss": 0.2697, + "epoch": 5.79, + "learning_rate": 1.4028589993502274e-05, + "loss": 0.2788, "step": 8920 }, { - "epoch": 4.76, - "learning_rate": 1.747867803837953e-05, - "loss": 0.339, + "epoch": 5.8, + "learning_rate": 1.4006930907515703e-05, + "loss": 0.1138, "step": 8930 }, { - "epoch": 4.76, - "learning_rate": 1.7460909737029143e-05, - "loss": 0.2058, + "epoch": 5.81, + "learning_rate": 1.3985271821529133e-05, + "loss": 0.0994, "step": 8940 }, { - "epoch": 4.77, - "learning_rate": 1.744314143567875e-05, - "loss": 0.3014, + "epoch": 5.81, + "learning_rate": 1.3963612735542562e-05, + "loss": 0.1967, "step": 8950 }, { - "epoch": 4.77, - "learning_rate": 1.7425373134328357e-05, - "loss": 0.3826, + "epoch": 5.82, + "learning_rate": 1.3941953649555989e-05, + "loss": 0.0688, "step": 8960 }, { - "epoch": 4.78, - "learning_rate": 1.7407604832977967e-05, - "loss": 0.4267, + "epoch": 5.83, + "learning_rate": 1.3920294563569417e-05, + "loss": 0.1298, "step": 8970 }, { - "epoch": 4.79, - "learning_rate": 1.7389836531627574e-05, - "loss": 0.3408, + "epoch": 5.83, + "learning_rate": 1.3898635477582846e-05, + "loss": 0.1009, "step": 8980 }, { - "epoch": 4.79, - "learning_rate": 1.7372068230277188e-05, - "loss": 0.2966, + "epoch": 5.84, + "learning_rate": 1.3876976391596276e-05, + "loss": 0.2893, "step": 8990 }, { - "epoch": 4.8, - "learning_rate": 1.7354299928926794e-05, - "loss": 0.1679, + "epoch": 5.85, + "learning_rate": 1.3855317305609703e-05, + "loss": 0.2114, "step": 9000 }, { - "epoch": 4.8, - "learning_rate": 1.7336531627576405e-05, - "loss": 0.2911, + "epoch": 5.85, + "learning_rate": 1.3833658219623132e-05, + "loss": 0.306, "step": 9010 }, { - "epoch": 4.81, - "learning_rate": 1.731876332622601e-05, - "loss": 0.3152, + "epoch": 5.86, + "learning_rate": 1.381199913363656e-05, + "loss": 0.0636, "step": 9020 }, { - "epoch": 4.81, - "learning_rate": 1.7300995024875622e-05, - "loss": 0.2926, + "epoch": 5.87, + "learning_rate": 1.379034004764999e-05, + "loss": 0.1042, "step": 9030 }, { - "epoch": 4.82, - "learning_rate": 1.7283226723525232e-05, - "loss": 0.1784, + "epoch": 5.87, + "learning_rate": 1.3768680961663418e-05, + "loss": 0.0434, "step": 9040 }, { - "epoch": 4.82, - "learning_rate": 1.7265458422174842e-05, - "loss": 0.219, + "epoch": 5.88, + "learning_rate": 1.3747021875676847e-05, + "loss": 0.2535, "step": 9050 }, { - "epoch": 4.83, - "learning_rate": 1.724769012082445e-05, - "loss": 0.288, + "epoch": 5.89, + "learning_rate": 1.3725362789690275e-05, + "loss": 0.2026, "step": 9060 }, { - "epoch": 4.83, - "learning_rate": 1.722992181947406e-05, - "loss": 0.2072, + "epoch": 5.89, + "learning_rate": 1.3703703703703704e-05, + "loss": 0.2205, "step": 9070 }, { - "epoch": 4.84, - "learning_rate": 1.7212153518123666e-05, - "loss": 0.1887, + "epoch": 5.9, + "learning_rate": 1.3682044617717133e-05, + "loss": 0.0956, "step": 9080 }, { - "epoch": 4.84, - "learning_rate": 1.719438521677328e-05, - "loss": 0.3482, + "epoch": 5.9, + "learning_rate": 1.3660385531730562e-05, + "loss": 0.2372, "step": 9090 }, { - "epoch": 4.85, - "learning_rate": 1.7176616915422887e-05, - "loss": 0.1357, + "epoch": 5.91, + "learning_rate": 1.363872644574399e-05, + "loss": 0.0798, "step": 9100 }, { - "epoch": 4.85, - "learning_rate": 1.7158848614072497e-05, - "loss": 0.162, + "epoch": 5.92, + "learning_rate": 1.3617067359757417e-05, + "loss": 0.0851, "step": 9110 }, { - "epoch": 4.86, - "learning_rate": 1.7142857142857142e-05, - "loss": 0.4579, + "epoch": 5.92, + "learning_rate": 1.3595408273770848e-05, + "loss": 0.1327, "step": 9120 }, { - "epoch": 4.87, - "learning_rate": 1.7125088841506752e-05, - "loss": 0.3351, + "epoch": 5.93, + "learning_rate": 1.3573749187784276e-05, + "loss": 0.4017, "step": 9130 }, { - "epoch": 4.87, - "learning_rate": 1.7107320540156362e-05, - "loss": 0.2013, + "epoch": 5.94, + "learning_rate": 1.3552090101797705e-05, + "loss": 0.0811, "step": 9140 }, { - "epoch": 4.88, - "learning_rate": 1.7089552238805973e-05, - "loss": 0.1979, + "epoch": 5.94, + "learning_rate": 1.3530431015811132e-05, + "loss": 0.4282, "step": 9150 }, { - "epoch": 4.88, - "learning_rate": 1.707178393745558e-05, - "loss": 0.1711, + "epoch": 5.95, + "learning_rate": 1.350877192982456e-05, + "loss": 0.1739, "step": 9160 }, { - "epoch": 4.89, - "learning_rate": 1.7054015636105186e-05, - "loss": 0.2765, + "epoch": 5.96, + "learning_rate": 1.3487112843837991e-05, + "loss": 0.0615, "step": 9170 }, { - "epoch": 4.89, - "learning_rate": 1.7036247334754797e-05, - "loss": 0.1971, + "epoch": 5.96, + "learning_rate": 1.346545375785142e-05, + "loss": 0.2251, "step": 9180 }, { - "epoch": 4.9, - "learning_rate": 1.7018479033404407e-05, - "loss": 0.171, + "epoch": 5.97, + "learning_rate": 1.3443794671864847e-05, + "loss": 0.0924, "step": 9190 }, { - "epoch": 4.9, - "learning_rate": 1.7000710732054017e-05, - "loss": 0.032, + "epoch": 5.98, + "learning_rate": 1.3422135585878275e-05, + "loss": 0.1031, "step": 9200 }, { - "epoch": 4.91, - "learning_rate": 1.6982942430703624e-05, - "loss": 0.2066, + "epoch": 5.98, + "learning_rate": 1.3400476499891706e-05, + "loss": 0.1001, "step": 9210 }, { - "epoch": 4.91, - "learning_rate": 1.6965174129353234e-05, - "loss": 0.1553, + "epoch": 5.99, + "learning_rate": 1.3378817413905134e-05, + "loss": 0.2866, "step": 9220 }, { - "epoch": 4.92, - "learning_rate": 1.694740582800284e-05, - "loss": 0.2377, + "epoch": 6.0, + "learning_rate": 1.3357158327918561e-05, + "loss": 0.1269, "step": 9230 }, { - "epoch": 4.92, - "learning_rate": 1.6929637526652455e-05, - "loss": 0.2941, + "epoch": 6.0, + "eval_accuracy": 0.9806807727690893, + "eval_loss": 0.10807611048221588, + "eval_runtime": 13.2387, + "eval_samples_per_second": 164.215, + "eval_steps_per_second": 41.092, + "step": 9237 + }, + { + "epoch": 6.0, + "learning_rate": 1.333549924193199e-05, + "loss": 0.1506, "step": 9240 }, { - "epoch": 4.93, - "learning_rate": 1.691186922530206e-05, - "loss": 0.1985, + "epoch": 6.01, + "learning_rate": 1.3313840155945419e-05, + "loss": 0.3085, "step": 9250 }, { - "epoch": 4.93, - "learning_rate": 1.6894100923951672e-05, - "loss": 0.3404, + "epoch": 6.01, + "learning_rate": 1.3292181069958849e-05, + "loss": 0.1471, "step": 9260 }, { - "epoch": 4.94, - "learning_rate": 1.687633262260128e-05, - "loss": 0.2625, + "epoch": 6.02, + "learning_rate": 1.3270521983972276e-05, + "loss": 0.0518, "step": 9270 }, { - "epoch": 4.95, - "learning_rate": 1.685856432125089e-05, - "loss": 0.2072, + "epoch": 6.03, + "learning_rate": 1.3248862897985705e-05, + "loss": 0.1339, "step": 9280 }, { - "epoch": 4.95, - "learning_rate": 1.68407960199005e-05, - "loss": 0.2033, + "epoch": 6.03, + "learning_rate": 1.3227203811999134e-05, + "loss": 0.0966, "step": 9290 }, { - "epoch": 4.96, - "learning_rate": 1.682302771855011e-05, - "loss": 0.3775, + "epoch": 6.04, + "learning_rate": 1.3205544726012564e-05, + "loss": 0.2445, "step": 9300 }, { - "epoch": 4.96, - "learning_rate": 1.6805259417199716e-05, - "loss": 0.1741, + "epoch": 6.05, + "learning_rate": 1.3183885640025991e-05, + "loss": 0.3489, "step": 9310 }, { - "epoch": 4.97, - "learning_rate": 1.6787491115849327e-05, - "loss": 0.0926, + "epoch": 6.05, + "learning_rate": 1.316222655403942e-05, + "loss": 0.127, "step": 9320 }, { - "epoch": 4.97, - "learning_rate": 1.6769722814498933e-05, - "loss": 0.0983, + "epoch": 6.06, + "learning_rate": 1.3140567468052848e-05, + "loss": 0.1226, "step": 9330 }, { - "epoch": 4.98, - "learning_rate": 1.675195451314854e-05, - "loss": 0.4306, + "epoch": 6.07, + "learning_rate": 1.3118908382066277e-05, + "loss": 0.2297, "step": 9340 }, { - "epoch": 4.98, - "learning_rate": 1.6734186211798154e-05, - "loss": 0.3898, + "epoch": 6.07, + "learning_rate": 1.3097249296079706e-05, + "loss": 0.0035, "step": 9350 }, { - "epoch": 4.99, - "learning_rate": 1.671641791044776e-05, - "loss": 0.267, + "epoch": 6.08, + "learning_rate": 1.3075590210093134e-05, + "loss": 0.1268, "step": 9360 }, { - "epoch": 4.99, - "learning_rate": 1.669864960909737e-05, - "loss": 0.4161, + "epoch": 6.09, + "learning_rate": 1.3053931124106563e-05, + "loss": 0.1522, "step": 9370 }, { - "epoch": 5.0, - "learning_rate": 1.6680881307746978e-05, - "loss": 0.2991, + "epoch": 6.09, + "learning_rate": 1.3032272038119992e-05, + "loss": 0.193, "step": 9380 }, { - "epoch": 5.0, - "eval_accuracy": 0.9633824084560212, - "eval_loss": 0.15178656578063965, - "eval_runtime": 9.7238, - "eval_samples_per_second": 272.423, - "eval_steps_per_second": 68.183, - "step": 9382 - }, - { - "epoch": 5.0, - "learning_rate": 1.6663113006396588e-05, - "loss": 0.3262, + "epoch": 6.1, + "learning_rate": 1.301061295213342e-05, + "loss": 0.0452, "step": 9390 }, { - "epoch": 5.01, - "learning_rate": 1.66453447050462e-05, - "loss": 0.2935, + "epoch": 6.11, + "learning_rate": 1.2988953866146849e-05, + "loss": 0.0601, "step": 9400 }, { - "epoch": 5.01, - "learning_rate": 1.662757640369581e-05, - "loss": 0.1617, + "epoch": 6.11, + "learning_rate": 1.2967294780160278e-05, + "loss": 0.1202, "step": 9410 }, { - "epoch": 5.02, - "learning_rate": 1.6609808102345416e-05, - "loss": 0.2312, + "epoch": 6.12, + "learning_rate": 1.2945635694173706e-05, + "loss": 0.0262, "step": 9420 }, { - "epoch": 5.03, - "learning_rate": 1.6592039800995026e-05, - "loss": 0.2038, + "epoch": 6.13, + "learning_rate": 1.2923976608187133e-05, + "loss": 0.1947, "step": 9430 }, { - "epoch": 5.03, - "learning_rate": 1.6574271499644633e-05, - "loss": 0.2859, + "epoch": 6.13, + "learning_rate": 1.2902317522200564e-05, + "loss": 0.0498, "step": 9440 }, { - "epoch": 5.04, - "learning_rate": 1.6556503198294246e-05, - "loss": 0.1854, + "epoch": 6.14, + "learning_rate": 1.2880658436213992e-05, + "loss": 0.1465, "step": 9450 }, { - "epoch": 5.04, - "learning_rate": 1.6538734896943853e-05, - "loss": 0.0593, + "epoch": 6.14, + "learning_rate": 1.2858999350227421e-05, + "loss": 0.148, "step": 9460 }, { - "epoch": 5.05, - "learning_rate": 1.6520966595593463e-05, - "loss": 0.1682, + "epoch": 6.15, + "learning_rate": 1.2837340264240848e-05, + "loss": 0.2404, "step": 9470 }, { - "epoch": 5.05, - "learning_rate": 1.650319829424307e-05, - "loss": 0.1251, + "epoch": 6.16, + "learning_rate": 1.2815681178254279e-05, + "loss": 0.4131, "step": 9480 }, { - "epoch": 5.06, - "learning_rate": 1.6485429992892677e-05, - "loss": 0.1944, + "epoch": 6.16, + "learning_rate": 1.2794022092267707e-05, + "loss": 0.0116, "step": 9490 }, { - "epoch": 5.06, - "learning_rate": 1.646766169154229e-05, - "loss": 0.3266, + "epoch": 6.17, + "learning_rate": 1.2772363006281136e-05, + "loss": 0.2536, "step": 9500 }, { - "epoch": 5.07, - "learning_rate": 1.6449893390191898e-05, - "loss": 0.307, + "epoch": 6.18, + "learning_rate": 1.2750703920294563e-05, + "loss": 0.275, "step": 9510 }, { - "epoch": 5.07, - "learning_rate": 1.6432125088841508e-05, - "loss": 0.1413, + "epoch": 6.18, + "learning_rate": 1.2729044834307992e-05, + "loss": 0.1243, "step": 9520 }, { - "epoch": 5.08, - "learning_rate": 1.6414356787491115e-05, - "loss": 0.2382, + "epoch": 6.19, + "learning_rate": 1.2707385748321422e-05, + "loss": 0.0021, "step": 9530 }, { - "epoch": 5.08, - "learning_rate": 1.6396588486140725e-05, - "loss": 0.1199, + "epoch": 6.2, + "learning_rate": 1.268572666233485e-05, + "loss": 0.3057, "step": 9540 }, { - "epoch": 5.09, - "learning_rate": 1.6378820184790332e-05, - "loss": 0.3172, + "epoch": 6.2, + "learning_rate": 1.2664067576348278e-05, + "loss": 0.163, "step": 9550 }, { - "epoch": 5.09, - "learning_rate": 1.6361051883439946e-05, - "loss": 0.3081, + "epoch": 6.21, + "learning_rate": 1.2642408490361706e-05, + "loss": 0.0507, "step": 9560 }, { - "epoch": 5.1, - "learning_rate": 1.6343283582089552e-05, - "loss": 0.0792, + "epoch": 6.22, + "learning_rate": 1.2620749404375137e-05, + "loss": 0.2131, "step": 9570 }, { - "epoch": 5.11, - "learning_rate": 1.6325515280739163e-05, - "loss": 0.2148, + "epoch": 6.22, + "learning_rate": 1.2599090318388565e-05, + "loss": 0.0124, "step": 9580 }, { - "epoch": 5.11, - "learning_rate": 1.630774697938877e-05, - "loss": 0.1312, + "epoch": 6.23, + "learning_rate": 1.2577431232401992e-05, + "loss": 0.0315, "step": 9590 }, { - "epoch": 5.12, - "learning_rate": 1.628997867803838e-05, - "loss": 0.1554, + "epoch": 6.24, + "learning_rate": 1.2555772146415421e-05, + "loss": 0.3318, "step": 9600 }, { - "epoch": 5.12, - "learning_rate": 1.627221037668799e-05, - "loss": 0.2307, + "epoch": 6.24, + "learning_rate": 1.253411306042885e-05, + "loss": 0.0796, "step": 9610 }, { - "epoch": 5.13, - "learning_rate": 1.62544420753376e-05, - "loss": 0.1898, + "epoch": 6.25, + "learning_rate": 1.251245397444228e-05, + "loss": 0.108, "step": 9620 }, { - "epoch": 5.13, - "learning_rate": 1.6236673773987207e-05, - "loss": 0.1114, + "epoch": 6.26, + "learning_rate": 1.2490794888455707e-05, + "loss": 0.1974, "step": 9630 }, { - "epoch": 5.14, - "learning_rate": 1.6218905472636817e-05, - "loss": 0.087, + "epoch": 6.26, + "learning_rate": 1.2469135802469136e-05, + "loss": 0.2185, "step": 9640 }, { - "epoch": 5.14, - "learning_rate": 1.6201137171286424e-05, - "loss": 0.1768, + "epoch": 6.27, + "learning_rate": 1.2447476716482564e-05, + "loss": 0.1898, "step": 9650 }, { - "epoch": 5.15, - "learning_rate": 1.6183368869936034e-05, - "loss": 0.1524, + "epoch": 6.27, + "learning_rate": 1.2425817630495995e-05, + "loss": 0.0438, "step": 9660 }, { - "epoch": 5.15, - "learning_rate": 1.6165600568585645e-05, - "loss": 0.3336, + "epoch": 6.28, + "learning_rate": 1.2404158544509422e-05, + "loss": 0.0117, "step": 9670 }, { - "epoch": 5.16, - "learning_rate": 1.614783226723525e-05, - "loss": 0.1121, + "epoch": 6.29, + "learning_rate": 1.238249945852285e-05, + "loss": 0.2061, "step": 9680 }, { - "epoch": 5.16, - "learning_rate": 1.6130063965884862e-05, - "loss": 0.4436, + "epoch": 6.29, + "learning_rate": 1.236084037253628e-05, + "loss": 0.0047, "step": 9690 }, { - "epoch": 5.17, - "learning_rate": 1.611229566453447e-05, - "loss": 0.1669, + "epoch": 6.3, + "learning_rate": 1.2339181286549708e-05, + "loss": 0.0662, "step": 9700 }, { - "epoch": 5.17, - "learning_rate": 1.609452736318408e-05, - "loss": 0.0912, + "epoch": 6.31, + "learning_rate": 1.2317522200563137e-05, + "loss": 0.0885, "step": 9710 }, { - "epoch": 5.18, - "learning_rate": 1.607675906183369e-05, - "loss": 0.1686, + "epoch": 6.31, + "learning_rate": 1.2295863114576565e-05, + "loss": 0.0855, "step": 9720 }, { - "epoch": 5.19, - "learning_rate": 1.60589907604833e-05, - "loss": 0.2916, + "epoch": 6.32, + "learning_rate": 1.2274204028589994e-05, + "loss": 0.1832, "step": 9730 }, { - "epoch": 5.19, - "learning_rate": 1.6041222459132906e-05, - "loss": 0.1666, + "epoch": 6.33, + "learning_rate": 1.2252544942603423e-05, + "loss": 0.0117, "step": 9740 }, { - "epoch": 5.2, - "learning_rate": 1.6023454157782517e-05, - "loss": 0.2601, + "epoch": 6.33, + "learning_rate": 1.2230885856616851e-05, + "loss": 0.1825, "step": 9750 }, { - "epoch": 5.2, - "learning_rate": 1.6005685856432123e-05, - "loss": 0.3749, + "epoch": 6.34, + "learning_rate": 1.220922677063028e-05, + "loss": 0.0776, "step": 9760 }, { - "epoch": 5.21, - "learning_rate": 1.5987917555081737e-05, - "loss": 0.1253, + "epoch": 6.35, + "learning_rate": 1.2187567684643709e-05, + "loss": 0.276, "step": 9770 }, { - "epoch": 5.21, - "learning_rate": 1.5970149253731344e-05, - "loss": 0.3499, + "epoch": 6.35, + "learning_rate": 1.2165908598657137e-05, + "loss": 0.0053, "step": 9780 }, { - "epoch": 5.22, - "learning_rate": 1.5952380952380954e-05, - "loss": 0.3119, + "epoch": 6.36, + "learning_rate": 1.2144249512670564e-05, + "loss": 0.2128, "step": 9790 }, { - "epoch": 5.22, - "learning_rate": 1.593461265103056e-05, - "loss": 0.0569, + "epoch": 6.37, + "learning_rate": 1.2122590426683995e-05, + "loss": 0.2099, "step": 9800 }, { - "epoch": 5.23, - "learning_rate": 1.591684434968017e-05, - "loss": 0.2216, + "epoch": 6.37, + "learning_rate": 1.2100931340697423e-05, + "loss": 0.0055, "step": 9810 }, { - "epoch": 5.23, - "learning_rate": 1.589907604832978e-05, - "loss": 0.077, + "epoch": 6.38, + "learning_rate": 1.2079272254710852e-05, + "loss": 0.122, "step": 9820 }, { - "epoch": 5.24, - "learning_rate": 1.588130774697939e-05, - "loss": 0.1609, + "epoch": 6.39, + "learning_rate": 1.2057613168724279e-05, + "loss": 0.0016, "step": 9830 }, { - "epoch": 5.24, - "learning_rate": 1.5863539445629e-05, - "loss": 0.1304, + "epoch": 6.39, + "learning_rate": 1.203595408273771e-05, + "loss": 0.0019, "step": 9840 }, { - "epoch": 5.25, - "learning_rate": 1.5845771144278606e-05, - "loss": 0.1528, + "epoch": 6.4, + "learning_rate": 1.2014294996751138e-05, + "loss": 0.0679, "step": 9850 }, { - "epoch": 5.25, - "learning_rate": 1.5828002842928216e-05, - "loss": 0.1346, + "epoch": 6.4, + "learning_rate": 1.1992635910764567e-05, + "loss": 0.2834, "step": 9860 }, { - "epoch": 5.26, - "learning_rate": 1.5810234541577826e-05, - "loss": 0.2726, + "epoch": 6.41, + "learning_rate": 1.1970976824777994e-05, + "loss": 0.3688, "step": 9870 }, { - "epoch": 5.27, - "learning_rate": 1.5792466240227436e-05, - "loss": 0.1971, + "epoch": 6.42, + "learning_rate": 1.1949317738791423e-05, + "loss": 0.1276, "step": 9880 }, { - "epoch": 5.27, - "learning_rate": 1.5774697938877043e-05, - "loss": 0.4545, + "epoch": 6.42, + "learning_rate": 1.1927658652804853e-05, + "loss": 0.1572, "step": 9890 }, { - "epoch": 5.28, - "learning_rate": 1.5756929637526653e-05, - "loss": 0.221, + "epoch": 6.43, + "learning_rate": 1.1905999566818282e-05, + "loss": 0.2999, "step": 9900 }, { - "epoch": 5.28, - "learning_rate": 1.573916133617626e-05, - "loss": 0.2252, + "epoch": 6.44, + "learning_rate": 1.1884340480831709e-05, + "loss": 0.0549, "step": 9910 }, { - "epoch": 5.29, - "learning_rate": 1.572139303482587e-05, - "loss": 0.3046, + "epoch": 6.44, + "learning_rate": 1.1862681394845137e-05, + "loss": 0.0244, "step": 9920 }, { - "epoch": 5.29, - "learning_rate": 1.570362473347548e-05, - "loss": 0.2913, + "epoch": 6.45, + "learning_rate": 1.1841022308858568e-05, + "loss": 0.0144, "step": 9930 }, { - "epoch": 5.3, - "learning_rate": 1.568585643212509e-05, - "loss": 0.2182, + "epoch": 6.46, + "learning_rate": 1.1819363222871996e-05, + "loss": 0.0892, "step": 9940 }, { - "epoch": 5.3, - "learning_rate": 1.5668088130774698e-05, - "loss": 0.3059, + "epoch": 6.46, + "learning_rate": 1.1797704136885423e-05, + "loss": 0.0441, "step": 9950 }, { - "epoch": 5.31, - "learning_rate": 1.5650319829424308e-05, - "loss": 0.0455, + "epoch": 6.47, + "learning_rate": 1.1776045050898852e-05, + "loss": 0.1115, "step": 9960 }, { - "epoch": 5.31, - "learning_rate": 1.5632551528073915e-05, - "loss": 0.0315, + "epoch": 6.48, + "learning_rate": 1.175438596491228e-05, + "loss": 0.1608, "step": 9970 }, { - "epoch": 5.32, - "learning_rate": 1.5614783226723525e-05, - "loss": 0.4703, + "epoch": 6.48, + "learning_rate": 1.1734892787524366e-05, + "loss": 0.2287, "step": 9980 }, { - "epoch": 5.32, - "learning_rate": 1.5597014925373136e-05, - "loss": 0.4408, + "epoch": 6.49, + "learning_rate": 1.1713233701537797e-05, + "loss": 0.0351, "step": 9990 }, { - "epoch": 5.33, - "learning_rate": 1.5579246624022742e-05, - "loss": 0.0877, + "epoch": 6.5, + "learning_rate": 1.1691574615551224e-05, + "loss": 0.0526, "step": 10000 }, { - "epoch": 5.33, - "learning_rate": 1.5561478322672353e-05, - "loss": 0.0793, + "epoch": 6.5, + "learning_rate": 1.1669915529564652e-05, + "loss": 0.0966, "step": 10010 }, { - "epoch": 5.34, - "learning_rate": 1.554371002132196e-05, - "loss": 0.2256, + "epoch": 6.51, + "learning_rate": 1.1648256443578081e-05, + "loss": 0.2692, "step": 10020 }, { - "epoch": 5.35, - "learning_rate": 1.5525941719971573e-05, - "loss": 0.2232, + "epoch": 6.52, + "learning_rate": 1.162659735759151e-05, + "loss": 0.0803, "step": 10030 }, { - "epoch": 5.35, - "learning_rate": 1.550817341862118e-05, - "loss": 0.2701, + "epoch": 6.52, + "learning_rate": 1.1604938271604938e-05, + "loss": 0.3985, "step": 10040 }, { - "epoch": 5.36, - "learning_rate": 1.549040511727079e-05, - "loss": 0.2856, + "epoch": 6.53, + "learning_rate": 1.1583279185618367e-05, + "loss": 0.1525, "step": 10050 }, { - "epoch": 5.36, - "learning_rate": 1.5472636815920397e-05, - "loss": 0.1921, + "epoch": 6.53, + "learning_rate": 1.1561620099631796e-05, + "loss": 0.1275, "step": 10060 }, { - "epoch": 5.37, - "learning_rate": 1.5454868514570007e-05, - "loss": 0.3531, + "epoch": 6.54, + "learning_rate": 1.1539961013645224e-05, + "loss": 0.0422, "step": 10070 }, { - "epoch": 5.37, - "learning_rate": 1.5437100213219618e-05, - "loss": 0.113, + "epoch": 6.55, + "learning_rate": 1.1518301927658653e-05, + "loss": 0.1179, "step": 10080 }, { - "epoch": 5.38, - "learning_rate": 1.5419331911869228e-05, - "loss": 0.401, + "epoch": 6.55, + "learning_rate": 1.1496642841672082e-05, + "loss": 0.2389, "step": 10090 }, { - "epoch": 5.38, - "learning_rate": 1.5401563610518835e-05, - "loss": 0.3489, + "epoch": 6.56, + "learning_rate": 1.147498375568551e-05, + "loss": 0.0017, "step": 10100 }, { - "epoch": 5.39, - "learning_rate": 1.5383795309168445e-05, - "loss": 0.2369, + "epoch": 6.57, + "learning_rate": 1.1453324669698939e-05, + "loss": 0.5718, "step": 10110 }, { - "epoch": 5.39, - "learning_rate": 1.5366027007818052e-05, - "loss": 0.3311, + "epoch": 6.57, + "learning_rate": 1.1431665583712366e-05, + "loss": 0.1237, "step": 10120 }, { - "epoch": 5.4, - "learning_rate": 1.5348258706467662e-05, - "loss": 0.2526, + "epoch": 6.58, + "learning_rate": 1.1410006497725796e-05, + "loss": 0.1591, "step": 10130 }, { - "epoch": 5.4, - "learning_rate": 1.5330490405117272e-05, - "loss": 0.2244, + "epoch": 6.59, + "learning_rate": 1.1388347411739225e-05, + "loss": 0.0555, "step": 10140 }, { - "epoch": 5.41, - "learning_rate": 1.531272210376688e-05, - "loss": 0.1049, + "epoch": 6.59, + "learning_rate": 1.1366688325752654e-05, + "loss": 0.0478, "step": 10150 }, { - "epoch": 5.41, - "learning_rate": 1.529495380241649e-05, - "loss": 0.3576, + "epoch": 6.6, + "learning_rate": 1.134502923976608e-05, + "loss": 0.1472, "step": 10160 }, { - "epoch": 5.42, - "learning_rate": 1.5277185501066096e-05, - "loss": 0.1735, + "epoch": 6.61, + "learning_rate": 1.1323370153779511e-05, + "loss": 0.1414, "step": 10170 }, { - "epoch": 5.42, - "learning_rate": 1.5259417199715707e-05, - "loss": 0.1664, + "epoch": 6.61, + "learning_rate": 1.130171106779294e-05, + "loss": 0.1624, "step": 10180 }, { - "epoch": 5.43, - "learning_rate": 1.5241648898365319e-05, - "loss": 0.2783, + "epoch": 6.62, + "learning_rate": 1.1280051981806369e-05, + "loss": 0.4795, "step": 10190 }, { - "epoch": 5.44, - "learning_rate": 1.5223880597014927e-05, - "loss": 0.1018, + "epoch": 6.63, + "learning_rate": 1.1258392895819796e-05, + "loss": 0.2595, "step": 10200 }, { - "epoch": 5.44, - "learning_rate": 1.5206112295664536e-05, - "loss": 0.3587, + "epoch": 6.63, + "learning_rate": 1.1236733809833224e-05, + "loss": 0.0409, "step": 10210 }, { - "epoch": 5.45, - "learning_rate": 1.5188343994314143e-05, - "loss": 0.1152, + "epoch": 6.64, + "learning_rate": 1.1215074723846655e-05, + "loss": 0.0421, "step": 10220 }, { - "epoch": 5.45, - "learning_rate": 1.5170575692963751e-05, - "loss": 0.4253, + "epoch": 6.65, + "learning_rate": 1.1193415637860083e-05, + "loss": 0.1452, "step": 10230 }, { - "epoch": 5.46, - "learning_rate": 1.5152807391613363e-05, - "loss": 0.1923, + "epoch": 6.65, + "learning_rate": 1.117175655187351e-05, + "loss": 0.1621, "step": 10240 }, { - "epoch": 5.46, - "learning_rate": 1.5135039090262972e-05, - "loss": 0.2091, + "epoch": 6.66, + "learning_rate": 1.1150097465886939e-05, + "loss": 0.1155, "step": 10250 }, { - "epoch": 5.47, - "learning_rate": 1.511727078891258e-05, - "loss": 0.5119, + "epoch": 6.66, + "learning_rate": 1.112843837990037e-05, + "loss": 0.1035, "step": 10260 }, { - "epoch": 5.47, - "learning_rate": 1.5099502487562189e-05, - "loss": 0.1512, + "epoch": 6.67, + "learning_rate": 1.1106779293913798e-05, + "loss": 0.1507, "step": 10270 }, { - "epoch": 5.48, - "learning_rate": 1.5081734186211797e-05, - "loss": 0.0538, + "epoch": 6.68, + "learning_rate": 1.1085120207927225e-05, + "loss": 0.1554, "step": 10280 }, { - "epoch": 5.48, - "learning_rate": 1.506396588486141e-05, - "loss": 0.238, + "epoch": 6.68, + "learning_rate": 1.1063461121940654e-05, + "loss": 0.0084, "step": 10290 }, { - "epoch": 5.49, - "learning_rate": 1.5046197583511018e-05, - "loss": 0.3083, + "epoch": 6.69, + "learning_rate": 1.1041802035954082e-05, + "loss": 0.2307, "step": 10300 }, { - "epoch": 5.49, - "learning_rate": 1.5028429282160626e-05, - "loss": 0.2114, + "epoch": 6.7, + "learning_rate": 1.1020142949967513e-05, + "loss": 0.197, "step": 10310 }, { - "epoch": 5.5, - "learning_rate": 1.5010660980810235e-05, - "loss": 0.2572, + "epoch": 6.7, + "learning_rate": 1.099848386398094e-05, + "loss": 0.2854, "step": 10320 }, { - "epoch": 5.5, - "learning_rate": 1.4992892679459845e-05, - "loss": 0.3528, + "epoch": 6.71, + "learning_rate": 1.0976824777994368e-05, + "loss": 0.1157, "step": 10330 }, { - "epoch": 5.51, - "learning_rate": 1.4975124378109454e-05, - "loss": 0.3391, + "epoch": 6.72, + "learning_rate": 1.0955165692007797e-05, + "loss": 0.1403, "step": 10340 }, { - "epoch": 5.52, - "learning_rate": 1.4957356076759062e-05, - "loss": 0.1005, + "epoch": 6.72, + "learning_rate": 1.0933506606021228e-05, + "loss": 0.1204, "step": 10350 }, { - "epoch": 5.52, - "learning_rate": 1.4939587775408673e-05, - "loss": 0.1958, + "epoch": 6.73, + "learning_rate": 1.0911847520034655e-05, + "loss": 0.2161, "step": 10360 }, { - "epoch": 5.53, - "learning_rate": 1.4921819474058281e-05, - "loss": 0.3184, + "epoch": 6.74, + "learning_rate": 1.0890188434048083e-05, + "loss": 0.2184, "step": 10370 }, { - "epoch": 5.53, - "learning_rate": 1.4904051172707888e-05, - "loss": 0.3087, - "step": 10380 + "epoch": 6.74, + "learning_rate": 1.0868529348061512e-05, + "loss": 0.2235, + "step": 10380 }, { - "epoch": 5.54, - "learning_rate": 1.4886282871357498e-05, - "loss": 0.0507, + "epoch": 6.75, + "learning_rate": 1.084687026207494e-05, + "loss": 0.0236, "step": 10390 }, { - "epoch": 5.54, - "learning_rate": 1.4868514570007107e-05, - "loss": 0.276, + "epoch": 6.76, + "learning_rate": 1.082521117608837e-05, + "loss": 0.2451, "step": 10400 }, { - "epoch": 5.55, - "learning_rate": 1.4850746268656717e-05, - "loss": 0.1557, + "epoch": 6.76, + "learning_rate": 1.0803552090101798e-05, + "loss": 0.1368, "step": 10410 }, { - "epoch": 5.55, - "learning_rate": 1.4832977967306326e-05, - "loss": 0.2345, + "epoch": 6.77, + "learning_rate": 1.0781893004115227e-05, + "loss": 0.166, "step": 10420 }, { - "epoch": 5.56, - "learning_rate": 1.4815209665955934e-05, - "loss": 0.1626, + "epoch": 6.77, + "learning_rate": 1.0760233918128655e-05, + "loss": 0.0876, "step": 10430 }, { - "epoch": 5.56, - "learning_rate": 1.4797441364605544e-05, - "loss": 0.0546, + "epoch": 6.78, + "learning_rate": 1.0738574832142084e-05, + "loss": 0.1326, "step": 10440 }, { - "epoch": 5.57, - "learning_rate": 1.4779673063255153e-05, - "loss": 0.242, + "epoch": 6.79, + "learning_rate": 1.0716915746155513e-05, + "loss": 0.1558, "step": 10450 }, { - "epoch": 5.57, - "learning_rate": 1.4761904761904761e-05, - "loss": 0.2589, + "epoch": 6.79, + "learning_rate": 1.0695256660168941e-05, + "loss": 0.2767, "step": 10460 }, { - "epoch": 5.58, - "learning_rate": 1.4744136460554372e-05, - "loss": 0.2278, + "epoch": 6.8, + "learning_rate": 1.067359757418237e-05, + "loss": 0.2269, "step": 10470 }, { - "epoch": 5.58, - "learning_rate": 1.472636815920398e-05, - "loss": 0.2676, + "epoch": 6.81, + "learning_rate": 1.0651938488195797e-05, + "loss": 0.2727, "step": 10480 }, { - "epoch": 5.59, - "learning_rate": 1.470859985785359e-05, - "loss": 0.0845, + "epoch": 6.81, + "learning_rate": 1.0630279402209227e-05, + "loss": 0.1883, "step": 10490 }, { - "epoch": 5.6, - "learning_rate": 1.4690831556503199e-05, - "loss": 0.4359, + "epoch": 6.82, + "learning_rate": 1.0608620316222656e-05, + "loss": 0.3771, "step": 10500 }, { - "epoch": 5.6, - "learning_rate": 1.4673063255152808e-05, - "loss": 0.2183, + "epoch": 6.83, + "learning_rate": 1.0586961230236085e-05, + "loss": 0.1681, "step": 10510 }, { - "epoch": 5.61, - "learning_rate": 1.4655294953802418e-05, - "loss": 0.2548, + "epoch": 6.83, + "learning_rate": 1.0565302144249512e-05, + "loss": 0.0599, "step": 10520 }, { - "epoch": 5.61, - "learning_rate": 1.4637526652452026e-05, - "loss": 0.3358, + "epoch": 6.84, + "learning_rate": 1.0543643058262942e-05, + "loss": 0.2127, "step": 10530 }, { - "epoch": 5.62, - "learning_rate": 1.4619758351101635e-05, - "loss": 0.2123, + "epoch": 6.85, + "learning_rate": 1.0521983972276371e-05, + "loss": 0.1691, "step": 10540 }, { - "epoch": 5.62, - "learning_rate": 1.4601990049751244e-05, - "loss": 0.2062, + "epoch": 6.85, + "learning_rate": 1.05003248862898e-05, + "loss": 0.2349, "step": 10550 }, { - "epoch": 5.63, - "learning_rate": 1.4584221748400852e-05, - "loss": 0.2058, + "epoch": 6.86, + "learning_rate": 1.0478665800303227e-05, + "loss": 0.2292, "step": 10560 }, { - "epoch": 5.63, - "learning_rate": 1.4566453447050462e-05, - "loss": 0.284, + "epoch": 6.87, + "learning_rate": 1.0457006714316655e-05, + "loss": 0.3338, "step": 10570 }, { - "epoch": 5.64, - "learning_rate": 1.4548685145700071e-05, - "loss": 0.1807, + "epoch": 6.87, + "learning_rate": 1.0435347628330086e-05, + "loss": 0.1032, "step": 10580 }, { - "epoch": 5.64, - "learning_rate": 1.453091684434968e-05, - "loss": 0.2872, + "epoch": 6.88, + "learning_rate": 1.0413688542343514e-05, + "loss": 0.059, "step": 10590 }, { - "epoch": 5.65, - "learning_rate": 1.451314854299929e-05, - "loss": 0.4493, + "epoch": 6.89, + "learning_rate": 1.0392029456356941e-05, + "loss": 0.272, "step": 10600 }, { - "epoch": 5.65, - "learning_rate": 1.4495380241648898e-05, - "loss": 0.1963, + "epoch": 6.89, + "learning_rate": 1.037037037037037e-05, + "loss": 0.0206, "step": 10610 }, { - "epoch": 5.66, - "learning_rate": 1.4477611940298509e-05, - "loss": 0.1275, + "epoch": 6.9, + "learning_rate": 1.03487112843838e-05, + "loss": 0.2188, "step": 10620 }, { - "epoch": 5.66, - "learning_rate": 1.4459843638948117e-05, - "loss": 0.1878, + "epoch": 6.9, + "learning_rate": 1.0327052198397229e-05, + "loss": 0.1537, "step": 10630 }, { - "epoch": 5.67, - "learning_rate": 1.4442075337597726e-05, - "loss": 0.2029, + "epoch": 6.91, + "learning_rate": 1.0305393112410656e-05, + "loss": 0.2969, "step": 10640 }, { - "epoch": 5.68, - "learning_rate": 1.4424307036247336e-05, - "loss": 0.3139, + "epoch": 6.92, + "learning_rate": 1.0283734026424085e-05, + "loss": 0.1091, "step": 10650 }, { - "epoch": 5.68, - "learning_rate": 1.4406538734896945e-05, - "loss": 0.441, + "epoch": 6.92, + "learning_rate": 1.0262074940437513e-05, + "loss": 0.1372, "step": 10660 }, { - "epoch": 5.69, - "learning_rate": 1.4388770433546553e-05, - "loss": 0.1848, + "epoch": 6.93, + "learning_rate": 1.0240415854450944e-05, + "loss": 0.1222, "step": 10670 }, { - "epoch": 5.69, - "learning_rate": 1.4371002132196163e-05, - "loss": 0.2668, + "epoch": 6.94, + "learning_rate": 1.021875676846437e-05, + "loss": 0.0026, "step": 10680 }, { - "epoch": 5.7, - "learning_rate": 1.4353233830845772e-05, - "loss": 0.3333, + "epoch": 6.94, + "learning_rate": 1.01970976824778e-05, + "loss": 0.0525, "step": 10690 }, { - "epoch": 5.7, - "learning_rate": 1.433546552949538e-05, - "loss": 0.1928, + "epoch": 6.95, + "learning_rate": 1.0175438596491228e-05, + "loss": 0.2373, "step": 10700 }, { - "epoch": 5.71, - "learning_rate": 1.4317697228144989e-05, - "loss": 0.1669, + "epoch": 6.96, + "learning_rate": 1.0153779510504659e-05, + "loss": 0.1444, "step": 10710 }, { - "epoch": 5.71, - "learning_rate": 1.4299928926794598e-05, - "loss": 0.1351, + "epoch": 6.96, + "learning_rate": 1.0132120424518086e-05, + "loss": 0.1887, "step": 10720 }, { - "epoch": 5.72, - "learning_rate": 1.4282160625444208e-05, - "loss": 0.09, + "epoch": 6.97, + "learning_rate": 1.0110461338531514e-05, + "loss": 0.0863, "step": 10730 }, { - "epoch": 5.72, - "learning_rate": 1.4264392324093816e-05, - "loss": 0.1513, + "epoch": 6.98, + "learning_rate": 1.0088802252544943e-05, + "loss": 0.1191, "step": 10740 }, { - "epoch": 5.73, - "learning_rate": 1.4246624022743427e-05, - "loss": 0.3063, + "epoch": 6.98, + "learning_rate": 1.0067143166558372e-05, + "loss": 0.2556, "step": 10750 }, { - "epoch": 5.73, - "learning_rate": 1.4228855721393035e-05, - "loss": 0.1572, + "epoch": 6.99, + "learning_rate": 1.00454840805718e-05, + "loss": 0.2222, "step": 10760 }, { - "epoch": 5.74, - "learning_rate": 1.4211087420042644e-05, - "loss": 0.2248, + "epoch": 7.0, + "learning_rate": 1.0023824994585229e-05, + "loss": 0.031, "step": 10770 }, { - "epoch": 5.74, - "learning_rate": 1.4193319118692254e-05, - "loss": 0.116, + "epoch": 7.0, + "eval_accuracy": 0.984820607175713, + "eval_loss": 0.08112048357725143, + "eval_runtime": 12.6945, + "eval_samples_per_second": 171.255, + "eval_steps_per_second": 42.853, + "step": 10776 + }, + { + "epoch": 7.0, + "learning_rate": 1.0002165908598658e-05, + "loss": 0.0887, "step": 10780 }, { - "epoch": 5.75, - "learning_rate": 1.4175550817341863e-05, - "loss": 0.0609, + "epoch": 7.01, + "learning_rate": 9.980506822612086e-06, + "loss": 0.195, "step": 10790 }, { - "epoch": 5.76, - "learning_rate": 1.4157782515991471e-05, - "loss": 0.1367, + "epoch": 7.02, + "learning_rate": 9.958847736625515e-06, + "loss": 0.176, "step": 10800 }, { - "epoch": 5.76, - "learning_rate": 1.4140014214641081e-05, - "loss": 0.3996, + "epoch": 7.02, + "learning_rate": 9.937188650638944e-06, + "loss": 0.1994, "step": 10810 }, { - "epoch": 5.77, - "learning_rate": 1.412224591329069e-05, - "loss": 0.2125, + "epoch": 7.03, + "learning_rate": 9.915529564652372e-06, + "loss": 0.0794, "step": 10820 }, { - "epoch": 5.77, - "learning_rate": 1.41044776119403e-05, - "loss": 0.1017, + "epoch": 7.03, + "learning_rate": 9.893870478665801e-06, + "loss": 0.0675, "step": 10830 }, { - "epoch": 5.78, - "learning_rate": 1.4086709310589909e-05, - "loss": 0.0487, + "epoch": 7.04, + "learning_rate": 9.872211392679228e-06, + "loss": 0.1071, "step": 10840 }, { - "epoch": 5.78, - "learning_rate": 1.4068941009239517e-05, - "loss": 0.087, + "epoch": 7.05, + "learning_rate": 9.850552306692658e-06, + "loss": 0.033, "step": 10850 }, { - "epoch": 5.79, - "learning_rate": 1.4051172707889126e-05, - "loss": 0.1985, + "epoch": 7.05, + "learning_rate": 9.828893220706087e-06, + "loss": 0.0126, "step": 10860 }, { - "epoch": 5.79, - "learning_rate": 1.4033404406538734e-05, - "loss": 0.1746, + "epoch": 7.06, + "learning_rate": 9.807234134719514e-06, + "loss": 0.2058, "step": 10870 }, { - "epoch": 5.8, - "learning_rate": 1.4015636105188343e-05, - "loss": 0.163, + "epoch": 7.07, + "learning_rate": 9.785575048732943e-06, + "loss": 0.2196, "step": 10880 }, { - "epoch": 5.8, - "learning_rate": 1.3997867803837953e-05, - "loss": 0.0384, + "epoch": 7.07, + "learning_rate": 9.763915962746373e-06, + "loss": 0.0015, "step": 10890 }, { - "epoch": 5.81, - "learning_rate": 1.3980099502487562e-05, - "loss": 0.1654, + "epoch": 7.08, + "learning_rate": 9.742256876759802e-06, + "loss": 0.0216, "step": 10900 }, { - "epoch": 5.81, - "learning_rate": 1.3962331201137172e-05, - "loss": 0.1775, + "epoch": 7.09, + "learning_rate": 9.720597790773229e-06, + "loss": 0.008, "step": 10910 }, { - "epoch": 5.82, - "learning_rate": 1.394456289978678e-05, - "loss": 0.331, + "epoch": 7.09, + "learning_rate": 9.698938704786658e-06, + "loss": 0.3726, "step": 10920 }, { - "epoch": 5.82, - "learning_rate": 1.3926794598436389e-05, - "loss": 0.2888, + "epoch": 7.1, + "learning_rate": 9.677279618800086e-06, + "loss": 0.1296, "step": 10930 }, { - "epoch": 5.83, - "learning_rate": 1.3909026297086e-05, - "loss": 0.2491, + "epoch": 7.11, + "learning_rate": 9.655620532813517e-06, + "loss": 0.034, "step": 10940 }, { - "epoch": 5.84, - "learning_rate": 1.3891257995735608e-05, - "loss": 0.1768, + "epoch": 7.11, + "learning_rate": 9.633961446826944e-06, + "loss": 0.0329, "step": 10950 }, { - "epoch": 5.84, - "learning_rate": 1.3873489694385217e-05, - "loss": 0.0908, + "epoch": 7.12, + "learning_rate": 9.612302360840372e-06, + "loss": 0.1104, "step": 10960 }, { - "epoch": 5.85, - "learning_rate": 1.3855721393034827e-05, - "loss": 0.4437, + "epoch": 7.13, + "learning_rate": 9.590643274853801e-06, + "loss": 0.0433, "step": 10970 }, { - "epoch": 5.85, - "learning_rate": 1.3837953091684435e-05, - "loss": 0.1125, + "epoch": 7.13, + "learning_rate": 9.568984188867231e-06, + "loss": 0.0929, "step": 10980 }, { - "epoch": 5.86, - "learning_rate": 1.3820184790334046e-05, - "loss": 0.1342, + "epoch": 7.14, + "learning_rate": 9.547325102880658e-06, + "loss": 0.0112, "step": 10990 }, { - "epoch": 5.86, - "learning_rate": 1.3802416488983654e-05, - "loss": 0.283, + "epoch": 7.15, + "learning_rate": 9.525666016894087e-06, + "loss": 0.076, "step": 11000 }, { - "epoch": 5.87, - "learning_rate": 1.3784648187633263e-05, - "loss": 0.3936, + "epoch": 7.15, + "learning_rate": 9.504006930907516e-06, + "loss": 0.0653, "step": 11010 }, { - "epoch": 5.87, - "learning_rate": 1.3766879886282871e-05, - "loss": 0.231, + "epoch": 7.16, + "learning_rate": 9.482347844920944e-06, + "loss": 0.3116, "step": 11020 }, { - "epoch": 5.88, - "learning_rate": 1.374911158493248e-05, - "loss": 0.2549, + "epoch": 7.16, + "learning_rate": 9.460688758934373e-06, + "loss": 0.0533, "step": 11030 }, { - "epoch": 5.88, - "learning_rate": 1.373134328358209e-05, - "loss": 0.2584, + "epoch": 7.17, + "learning_rate": 9.439029672947802e-06, + "loss": 0.0627, "step": 11040 }, { - "epoch": 5.89, - "learning_rate": 1.3713574982231699e-05, - "loss": 0.1942, + "epoch": 7.18, + "learning_rate": 9.41737058696123e-06, + "loss": 0.0206, "step": 11050 }, { - "epoch": 5.89, - "learning_rate": 1.3695806680881307e-05, - "loss": 0.2046, + "epoch": 7.18, + "learning_rate": 9.395711500974659e-06, + "loss": 0.1429, "step": 11060 }, { - "epoch": 5.9, - "learning_rate": 1.3678038379530917e-05, - "loss": 0.2606, + "epoch": 7.19, + "learning_rate": 9.374052414988088e-06, + "loss": 0.1702, "step": 11070 }, { - "epoch": 5.9, - "learning_rate": 1.3660270078180526e-05, - "loss": 0.2802, + "epoch": 7.2, + "learning_rate": 9.352393329001516e-06, + "loss": 0.0337, "step": 11080 }, { - "epoch": 5.91, - "learning_rate": 1.3642501776830135e-05, - "loss": 0.1611, + "epoch": 7.2, + "learning_rate": 9.330734243014945e-06, + "loss": 0.1393, "step": 11090 }, { - "epoch": 5.92, - "learning_rate": 1.3624733475479745e-05, - "loss": 0.1257, + "epoch": 7.21, + "learning_rate": 9.309075157028374e-06, + "loss": 0.1942, "step": 11100 }, { - "epoch": 5.92, - "learning_rate": 1.3606965174129353e-05, - "loss": 0.1896, + "epoch": 7.22, + "learning_rate": 9.2874160710418e-06, + "loss": 0.2188, "step": 11110 }, { - "epoch": 5.93, - "learning_rate": 1.3589196872778964e-05, - "loss": 0.3346, + "epoch": 7.22, + "learning_rate": 9.265756985055231e-06, + "loss": 0.0614, "step": 11120 }, { - "epoch": 5.93, - "learning_rate": 1.3571428571428572e-05, - "loss": 0.1341, + "epoch": 7.23, + "learning_rate": 9.24409789906866e-06, + "loss": 0.2601, "step": 11130 }, { - "epoch": 5.94, - "learning_rate": 1.355366027007818e-05, - "loss": 0.0948, + "epoch": 7.24, + "learning_rate": 9.222438813082089e-06, + "loss": 0.2971, "step": 11140 }, { - "epoch": 5.94, - "learning_rate": 1.3535891968727791e-05, - "loss": 0.1281, + "epoch": 7.24, + "learning_rate": 9.200779727095516e-06, + "loss": 0.1568, "step": 11150 }, { - "epoch": 5.95, - "learning_rate": 1.35181236673774e-05, - "loss": 0.2893, + "epoch": 7.25, + "learning_rate": 9.179120641108946e-06, + "loss": 0.2477, "step": 11160 }, { - "epoch": 5.95, - "learning_rate": 1.3500355366027008e-05, - "loss": 0.1948, + "epoch": 7.26, + "learning_rate": 9.157461555122375e-06, + "loss": 0.3047, "step": 11170 }, { - "epoch": 5.96, - "learning_rate": 1.3482587064676617e-05, - "loss": 0.4575, + "epoch": 7.26, + "learning_rate": 9.135802469135803e-06, + "loss": 0.1162, "step": 11180 }, { - "epoch": 5.96, - "learning_rate": 1.3464818763326225e-05, - "loss": 0.1302, + "epoch": 7.27, + "learning_rate": 9.11414338314923e-06, + "loss": 0.112, "step": 11190 }, { - "epoch": 5.97, - "learning_rate": 1.3447050461975835e-05, - "loss": 0.265, + "epoch": 7.28, + "learning_rate": 9.092484297162659e-06, + "loss": 0.1143, "step": 11200 }, { - "epoch": 5.97, - "learning_rate": 1.3429282160625444e-05, - "loss": 0.0898, + "epoch": 7.28, + "learning_rate": 9.07082521117609e-06, + "loss": 0.0668, "step": 11210 }, { - "epoch": 5.98, - "learning_rate": 1.3411513859275053e-05, - "loss": 0.3762, + "epoch": 7.29, + "learning_rate": 9.049166125189518e-06, + "loss": 0.2082, "step": 11220 }, { - "epoch": 5.98, - "learning_rate": 1.3393745557924663e-05, - "loss": 0.123, + "epoch": 7.29, + "learning_rate": 9.027507039202945e-06, + "loss": 0.1127, "step": 11230 }, { - "epoch": 5.99, - "learning_rate": 1.3375977256574271e-05, - "loss": 0.2335, + "epoch": 7.3, + "learning_rate": 9.005847953216374e-06, + "loss": 0.0592, "step": 11240 }, { - "epoch": 6.0, - "learning_rate": 1.3358208955223882e-05, - "loss": 0.2592, + "epoch": 7.31, + "learning_rate": 8.984188867229804e-06, + "loss": 0.1539, "step": 11250 }, { - "epoch": 6.0, - "eval_accuracy": 0.9686674216685541, - "eval_loss": 0.13587088882923126, - "eval_runtime": 9.6926, - "eval_samples_per_second": 273.3, - "eval_steps_per_second": 68.402, - "step": 11259 - }, - { - "epoch": 6.0, - "learning_rate": 1.334044065387349e-05, - "loss": 0.2518, + "epoch": 7.31, + "learning_rate": 8.962529781243233e-06, + "loss": 0.1297, "step": 11260 }, { - "epoch": 6.01, - "learning_rate": 1.3322672352523099e-05, - "loss": 0.1014, + "epoch": 7.32, + "learning_rate": 8.94087069525666e-06, + "loss": 0.1659, "step": 11270 }, { - "epoch": 6.01, - "learning_rate": 1.3304904051172709e-05, - "loss": 0.1545, + "epoch": 7.33, + "learning_rate": 8.919211609270088e-06, + "loss": 0.1437, "step": 11280 }, { - "epoch": 6.02, - "learning_rate": 1.3287135749822318e-05, - "loss": 0.0938, + "epoch": 7.33, + "learning_rate": 8.897552523283517e-06, + "loss": 0.0978, "step": 11290 }, { - "epoch": 6.02, - "learning_rate": 1.3269367448471926e-05, - "loss": 0.116, + "epoch": 7.34, + "learning_rate": 8.875893437296948e-06, + "loss": 0.228, "step": 11300 }, { - "epoch": 6.03, - "learning_rate": 1.3251599147121536e-05, - "loss": 0.0958, + "epoch": 7.35, + "learning_rate": 8.854234351310375e-06, + "loss": 0.0906, "step": 11310 }, { - "epoch": 6.03, - "learning_rate": 1.3233830845771145e-05, - "loss": 0.2064, + "epoch": 7.35, + "learning_rate": 8.832575265323803e-06, + "loss": 0.173, "step": 11320 }, { - "epoch": 6.04, - "learning_rate": 1.3216062544420755e-05, - "loss": 0.0999, + "epoch": 7.36, + "learning_rate": 8.810916179337232e-06, + "loss": 0.0306, "step": 11330 }, { - "epoch": 6.04, - "learning_rate": 1.3198294243070364e-05, - "loss": 0.2526, + "epoch": 7.37, + "learning_rate": 8.789257093350662e-06, + "loss": 0.1072, "step": 11340 }, { - "epoch": 6.05, - "learning_rate": 1.318052594171997e-05, - "loss": 0.1518, + "epoch": 7.37, + "learning_rate": 8.76759800736409e-06, + "loss": 0.0704, "step": 11350 }, { - "epoch": 6.05, - "learning_rate": 1.3162757640369581e-05, - "loss": 0.3599, + "epoch": 7.38, + "learning_rate": 8.745938921377518e-06, + "loss": 0.0096, "step": 11360 }, { - "epoch": 6.06, - "learning_rate": 1.314498933901919e-05, - "loss": 0.1802, + "epoch": 7.39, + "learning_rate": 8.724279835390947e-06, + "loss": 0.4016, "step": 11370 }, { - "epoch": 6.06, - "learning_rate": 1.3127221037668798e-05, - "loss": 0.1063, + "epoch": 7.39, + "learning_rate": 8.702620749404375e-06, + "loss": 0.2172, "step": 11380 }, { - "epoch": 6.07, - "learning_rate": 1.3109452736318408e-05, - "loss": 0.1375, + "epoch": 7.4, + "learning_rate": 8.680961663417804e-06, + "loss": 0.2804, "step": 11390 }, { - "epoch": 6.08, - "learning_rate": 1.3091684434968017e-05, - "loss": 0.1065, + "epoch": 7.41, + "learning_rate": 8.659302577431233e-06, + "loss": 0.1273, "step": 11400 }, { - "epoch": 6.08, - "learning_rate": 1.3073916133617627e-05, - "loss": 0.0906, + "epoch": 7.41, + "learning_rate": 8.637643491444661e-06, + "loss": 0.0394, "step": 11410 }, { - "epoch": 6.09, - "learning_rate": 1.3056147832267236e-05, - "loss": 0.2471, + "epoch": 7.42, + "learning_rate": 8.61598440545809e-06, + "loss": 0.0711, "step": 11420 }, { - "epoch": 6.09, - "learning_rate": 1.3038379530916844e-05, - "loss": 0.1249, + "epoch": 7.42, + "learning_rate": 8.594325319471519e-06, + "loss": 0.188, "step": 11430 }, { - "epoch": 6.1, - "learning_rate": 1.3020611229566454e-05, - "loss": 0.149, + "epoch": 7.43, + "learning_rate": 8.572666233484947e-06, + "loss": 0.046, "step": 11440 }, { - "epoch": 6.1, - "learning_rate": 1.3002842928216063e-05, - "loss": 0.0561, + "epoch": 7.44, + "learning_rate": 8.551007147498376e-06, + "loss": 0.1146, "step": 11450 }, { - "epoch": 6.11, - "learning_rate": 1.2985074626865672e-05, - "loss": 0.0598, + "epoch": 7.44, + "learning_rate": 8.529348061511805e-06, + "loss": 0.039, "step": 11460 }, { - "epoch": 6.11, - "learning_rate": 1.2967306325515282e-05, - "loss": 0.1505, + "epoch": 7.45, + "learning_rate": 8.507688975525232e-06, + "loss": 0.1031, "step": 11470 }, { - "epoch": 6.12, - "learning_rate": 1.294953802416489e-05, - "loss": 0.3823, + "epoch": 7.46, + "learning_rate": 8.486029889538662e-06, + "loss": 0.003, "step": 11480 }, { - "epoch": 6.12, - "learning_rate": 1.29317697228145e-05, - "loss": 0.4194, + "epoch": 7.46, + "learning_rate": 8.464370803552091e-06, + "loss": 0.018, "step": 11490 }, { - "epoch": 6.13, - "learning_rate": 1.291400142146411e-05, - "loss": 0.0924, + "epoch": 7.47, + "learning_rate": 8.44271171756552e-06, + "loss": 0.2962, "step": 11500 }, { - "epoch": 6.13, - "learning_rate": 1.2896233120113716e-05, - "loss": 0.1411, + "epoch": 7.48, + "learning_rate": 8.421052631578947e-06, + "loss": 0.053, "step": 11510 }, { - "epoch": 6.14, - "learning_rate": 1.2878464818763326e-05, - "loss": 0.0874, + "epoch": 7.48, + "learning_rate": 8.399393545592377e-06, + "loss": 0.0209, "step": 11520 }, { - "epoch": 6.14, - "learning_rate": 1.2860696517412935e-05, - "loss": 0.1241, + "epoch": 7.49, + "learning_rate": 8.377734459605806e-06, + "loss": 0.0926, "step": 11530 }, { - "epoch": 6.15, - "learning_rate": 1.2842928216062545e-05, - "loss": 0.1341, + "epoch": 7.5, + "learning_rate": 8.356075373619234e-06, + "loss": 0.1764, "step": 11540 }, { - "epoch": 6.16, - "learning_rate": 1.2825159914712154e-05, - "loss": 0.2681, + "epoch": 7.5, + "learning_rate": 8.334416287632661e-06, + "loss": 0.0722, "step": 11550 }, { - "epoch": 6.16, - "learning_rate": 1.2807391613361762e-05, - "loss": 0.006, + "epoch": 7.51, + "learning_rate": 8.31275720164609e-06, + "loss": 0.1181, "step": 11560 }, { - "epoch": 6.17, - "learning_rate": 1.2789623312011372e-05, - "loss": 0.2687, + "epoch": 7.52, + "learning_rate": 8.29109811565952e-06, + "loss": 0.1074, "step": 11570 }, { - "epoch": 6.17, - "learning_rate": 1.2771855010660981e-05, - "loss": 0.1849, + "epoch": 7.52, + "learning_rate": 8.269439029672949e-06, + "loss": 0.1395, "step": 11580 }, { - "epoch": 6.18, - "learning_rate": 1.275408670931059e-05, - "loss": 0.0629, + "epoch": 7.53, + "learning_rate": 8.247779943686376e-06, + "loss": 0.095, "step": 11590 }, { - "epoch": 6.18, - "learning_rate": 1.27363184079602e-05, - "loss": 0.2106, + "epoch": 7.53, + "learning_rate": 8.226120857699805e-06, + "loss": 0.0765, "step": 11600 }, { - "epoch": 6.19, - "learning_rate": 1.2718550106609808e-05, - "loss": 0.2367, + "epoch": 7.54, + "learning_rate": 8.204461771713233e-06, + "loss": 0.4006, "step": 11610 }, { - "epoch": 6.19, - "learning_rate": 1.2700781805259419e-05, - "loss": 0.3112, + "epoch": 7.55, + "learning_rate": 8.182802685726664e-06, + "loss": 0.0065, "step": 11620 }, { - "epoch": 6.2, - "learning_rate": 1.2683013503909027e-05, - "loss": 0.0986, + "epoch": 7.55, + "learning_rate": 8.16114359974009e-06, + "loss": 0.1837, "step": 11630 }, { - "epoch": 6.2, - "learning_rate": 1.2665245202558636e-05, - "loss": 0.0877, + "epoch": 7.56, + "learning_rate": 8.13948451375352e-06, + "loss": 0.1463, "step": 11640 }, { - "epoch": 6.21, - "learning_rate": 1.2647476901208246e-05, - "loss": 0.0574, + "epoch": 7.57, + "learning_rate": 8.117825427766948e-06, + "loss": 0.2499, "step": 11650 }, { - "epoch": 6.21, - "learning_rate": 1.2629708599857855e-05, - "loss": 0.2242, + "epoch": 7.57, + "learning_rate": 8.096166341780379e-06, + "loss": 0.1759, "step": 11660 }, { - "epoch": 6.22, - "learning_rate": 1.2611940298507461e-05, - "loss": 0.0647, + "epoch": 7.58, + "learning_rate": 8.074507255793806e-06, + "loss": 0.0632, "step": 11670 }, { - "epoch": 6.22, - "learning_rate": 1.2594171997157072e-05, - "loss": 0.0195, + "epoch": 7.59, + "learning_rate": 8.052848169807234e-06, + "loss": 0.046, "step": 11680 }, { - "epoch": 6.23, - "learning_rate": 1.257640369580668e-05, - "loss": 0.3221, + "epoch": 7.59, + "learning_rate": 8.031189083820663e-06, + "loss": 0.1882, "step": 11690 }, { - "epoch": 6.24, - "learning_rate": 1.255863539445629e-05, - "loss": 0.1392, + "epoch": 7.6, + "learning_rate": 8.009529997834092e-06, + "loss": 0.2443, "step": 11700 }, { - "epoch": 6.24, - "learning_rate": 1.2540867093105899e-05, - "loss": 0.1037, + "epoch": 7.61, + "learning_rate": 7.98787091184752e-06, + "loss": 0.0786, "step": 11710 }, { - "epoch": 6.25, - "learning_rate": 1.2523098791755508e-05, - "loss": 0.2926, + "epoch": 7.61, + "learning_rate": 7.966211825860949e-06, + "loss": 0.0354, "step": 11720 }, { - "epoch": 6.25, - "learning_rate": 1.2505330490405118e-05, - "loss": 0.1247, + "epoch": 7.62, + "learning_rate": 7.944552739874378e-06, + "loss": 0.1392, "step": 11730 }, { - "epoch": 6.26, - "learning_rate": 1.2487562189054726e-05, - "loss": 0.0819, + "epoch": 7.63, + "learning_rate": 7.922893653887806e-06, + "loss": 0.1614, "step": 11740 }, { - "epoch": 6.26, - "learning_rate": 1.2469793887704337e-05, - "loss": 0.0125, + "epoch": 7.63, + "learning_rate": 7.901234567901235e-06, + "loss": 0.0229, "step": 11750 }, { - "epoch": 6.27, - "learning_rate": 1.2452025586353945e-05, - "loss": 0.2458, + "epoch": 7.64, + "learning_rate": 7.879575481914664e-06, + "loss": 0.0742, "step": 11760 }, { - "epoch": 6.27, - "learning_rate": 1.2434257285003554e-05, - "loss": 0.4814, + "epoch": 7.65, + "learning_rate": 7.857916395928092e-06, + "loss": 0.0247, "step": 11770 }, { - "epoch": 6.28, - "learning_rate": 1.2416488983653164e-05, - "loss": 0.3716, + "epoch": 7.65, + "learning_rate": 7.836257309941521e-06, + "loss": 0.0734, "step": 11780 }, { - "epoch": 6.28, - "learning_rate": 1.2398720682302773e-05, - "loss": 0.1653, + "epoch": 7.66, + "learning_rate": 7.814598223954948e-06, + "loss": 0.161, "step": 11790 }, { - "epoch": 6.29, - "learning_rate": 1.2380952380952381e-05, - "loss": 0.2104, + "epoch": 7.66, + "learning_rate": 7.792939137968378e-06, + "loss": 0.1736, "step": 11800 }, { - "epoch": 6.29, - "learning_rate": 1.2363184079601991e-05, - "loss": 0.3455, + "epoch": 7.67, + "learning_rate": 7.771280051981807e-06, + "loss": 0.1407, "step": 11810 }, { - "epoch": 6.3, - "learning_rate": 1.23454157782516e-05, - "loss": 0.0626, + "epoch": 7.68, + "learning_rate": 7.749620965995236e-06, + "loss": 0.104, "step": 11820 }, { - "epoch": 6.3, - "learning_rate": 1.2327647476901209e-05, - "loss": 0.2378, + "epoch": 7.68, + "learning_rate": 7.727961880008663e-06, + "loss": 0.1501, "step": 11830 }, { - "epoch": 6.31, - "learning_rate": 1.2309879175550817e-05, - "loss": 0.1161, + "epoch": 7.69, + "learning_rate": 7.706302794022093e-06, + "loss": 0.1137, "step": 11840 }, { - "epoch": 6.31, - "learning_rate": 1.2292110874200426e-05, - "loss": 0.2092, + "epoch": 7.7, + "learning_rate": 7.684643708035522e-06, + "loss": 0.1669, "step": 11850 }, { - "epoch": 6.32, - "learning_rate": 1.2274342572850036e-05, - "loss": 0.0054, + "epoch": 7.7, + "learning_rate": 7.662984622048949e-06, + "loss": 0.0013, "step": 11860 }, { - "epoch": 6.33, - "learning_rate": 1.2256574271499644e-05, - "loss": 0.1932, + "epoch": 7.71, + "learning_rate": 7.641325536062378e-06, + "loss": 0.1373, "step": 11870 }, { - "epoch": 6.33, - "learning_rate": 1.2238805970149253e-05, - "loss": 0.2156, + "epoch": 7.72, + "learning_rate": 7.619666450075806e-06, + "loss": 0.1723, "step": 11880 }, { - "epoch": 6.34, - "learning_rate": 1.2221037668798863e-05, - "loss": 0.0997, + "epoch": 7.72, + "learning_rate": 7.598007364089236e-06, + "loss": 0.0015, "step": 11890 }, { - "epoch": 6.34, - "learning_rate": 1.2203269367448472e-05, - "loss": 0.286, + "epoch": 7.73, + "learning_rate": 7.576348278102664e-06, + "loss": 0.0992, "step": 11900 }, { - "epoch": 6.35, - "learning_rate": 1.2185501066098082e-05, - "loss": 0.2055, + "epoch": 7.74, + "learning_rate": 7.554689192116092e-06, + "loss": 0.0976, "step": 11910 }, { - "epoch": 6.35, - "learning_rate": 1.216773276474769e-05, - "loss": 0.284, + "epoch": 7.74, + "learning_rate": 7.533030106129521e-06, + "loss": 0.0918, "step": 11920 }, { - "epoch": 6.36, - "learning_rate": 1.21499644633973e-05, - "loss": 0.1864, + "epoch": 7.75, + "learning_rate": 7.5113710201429505e-06, + "loss": 0.0709, "step": 11930 }, { - "epoch": 6.36, - "learning_rate": 1.213219616204691e-05, - "loss": 0.3769, + "epoch": 7.76, + "learning_rate": 7.489711934156379e-06, + "loss": 0.2004, "step": 11940 }, { - "epoch": 6.37, - "learning_rate": 1.2114427860696518e-05, - "loss": 0.1859, + "epoch": 7.76, + "learning_rate": 7.468052848169807e-06, + "loss": 0.0302, "step": 11950 }, { - "epoch": 6.37, - "learning_rate": 1.2096659559346127e-05, - "loss": 0.0632, + "epoch": 7.77, + "learning_rate": 7.446393762183236e-06, + "loss": 0.3603, "step": 11960 }, { - "epoch": 6.38, - "learning_rate": 1.2078891257995737e-05, - "loss": 0.2929, + "epoch": 7.78, + "learning_rate": 7.424734676196664e-06, + "loss": 0.0168, "step": 11970 }, { - "epoch": 6.38, - "learning_rate": 1.2061122956645345e-05, - "loss": 0.1536, + "epoch": 7.78, + "learning_rate": 7.403075590210093e-06, + "loss": 0.0821, "step": 11980 }, { - "epoch": 6.39, - "learning_rate": 1.2043354655294954e-05, - "loss": 0.1672, + "epoch": 7.79, + "learning_rate": 7.381416504223522e-06, + "loss": 0.1954, "step": 11990 }, { - "epoch": 6.39, - "learning_rate": 1.2025586353944562e-05, - "loss": 0.2071, + "epoch": 7.79, + "learning_rate": 7.35975741823695e-06, + "loss": 0.1345, "step": 12000 }, { - "epoch": 6.4, - "learning_rate": 1.2007818052594171e-05, - "loss": 0.1402, + "epoch": 7.8, + "learning_rate": 7.338098332250379e-06, + "loss": 0.0208, "step": 12010 }, { - "epoch": 6.41, - "learning_rate": 1.1990049751243781e-05, - "loss": 0.2472, + "epoch": 7.81, + "learning_rate": 7.316439246263808e-06, + "loss": 0.1959, "step": 12020 }, { - "epoch": 6.41, - "learning_rate": 1.197228144989339e-05, - "loss": 0.2139, + "epoch": 7.81, + "learning_rate": 7.2947801602772365e-06, + "loss": 0.0016, "step": 12030 }, { - "epoch": 6.42, - "learning_rate": 1.1954513148543e-05, - "loss": 0.2791, + "epoch": 7.82, + "learning_rate": 7.273121074290665e-06, + "loss": 0.2701, "step": 12040 }, { - "epoch": 6.42, - "learning_rate": 1.1936744847192609e-05, - "loss": 0.2195, + "epoch": 7.83, + "learning_rate": 7.251461988304093e-06, + "loss": 0.0076, "step": 12050 }, { - "epoch": 6.43, - "learning_rate": 1.1918976545842217e-05, - "loss": 0.4341, + "epoch": 7.83, + "learning_rate": 7.2298029023175225e-06, + "loss": 0.0192, "step": 12060 }, { - "epoch": 6.43, - "learning_rate": 1.1901208244491827e-05, - "loss": 0.0895, + "epoch": 7.84, + "learning_rate": 7.20814381633095e-06, + "loss": 0.0733, "step": 12070 }, { - "epoch": 6.44, - "learning_rate": 1.1883439943141436e-05, - "loss": 0.2614, + "epoch": 7.85, + "learning_rate": 7.18648473034438e-06, + "loss": 0.0395, "step": 12080 }, { - "epoch": 6.44, - "learning_rate": 1.1865671641791045e-05, - "loss": 0.0714, + "epoch": 7.85, + "learning_rate": 7.164825644357808e-06, + "loss": 0.044, "step": 12090 }, { - "epoch": 6.45, - "learning_rate": 1.1847903340440655e-05, - "loss": 0.1561, + "epoch": 7.86, + "learning_rate": 7.143166558371237e-06, + "loss": 0.1878, "step": 12100 }, { - "epoch": 6.45, - "learning_rate": 1.1830135039090263e-05, - "loss": 0.1977, + "epoch": 7.87, + "learning_rate": 7.121507472384665e-06, + "loss": 0.233, "step": 12110 }, { - "epoch": 6.46, - "learning_rate": 1.1812366737739874e-05, - "loss": 0.4495, + "epoch": 7.87, + "learning_rate": 7.099848386398095e-06, + "loss": 0.1157, "step": 12120 }, { - "epoch": 6.46, - "learning_rate": 1.1794598436389482e-05, - "loss": 0.3395, + "epoch": 7.88, + "learning_rate": 7.0781893004115225e-06, + "loss": 0.098, "step": 12130 }, { - "epoch": 6.47, - "learning_rate": 1.177683013503909e-05, - "loss": 0.1232, + "epoch": 7.89, + "learning_rate": 7.056530214424951e-06, + "loss": 0.1827, "step": 12140 }, { - "epoch": 6.47, - "learning_rate": 1.17590618336887e-05, - "loss": 0.3605, + "epoch": 7.89, + "learning_rate": 7.03487112843838e-06, + "loss": 0.2982, "step": 12150 }, { - "epoch": 6.48, - "learning_rate": 1.1741293532338308e-05, - "loss": 0.2117, + "epoch": 7.9, + "learning_rate": 7.0132120424518085e-06, + "loss": 0.1493, "step": 12160 }, { - "epoch": 6.49, - "learning_rate": 1.1723525230987916e-05, - "loss": 0.1932, + "epoch": 7.91, + "learning_rate": 6.991552956465237e-06, + "loss": 0.1547, "step": 12170 }, { - "epoch": 6.49, - "learning_rate": 1.1705756929637527e-05, - "loss": 0.1382, + "epoch": 7.91, + "learning_rate": 6.969893870478666e-06, + "loss": 0.0282, "step": 12180 }, { - "epoch": 6.5, - "learning_rate": 1.1687988628287135e-05, - "loss": 0.2565, + "epoch": 7.92, + "learning_rate": 6.948234784492095e-06, + "loss": 0.2962, "step": 12190 }, { - "epoch": 6.5, - "learning_rate": 1.1670220326936746e-05, - "loss": 0.2059, + "epoch": 7.92, + "learning_rate": 6.926575698505523e-06, + "loss": 0.0203, "step": 12200 }, { - "epoch": 6.51, - "learning_rate": 1.1652452025586354e-05, - "loss": 0.009, + "epoch": 7.93, + "learning_rate": 6.904916612518952e-06, + "loss": 0.3606, "step": 12210 }, { - "epoch": 6.51, - "learning_rate": 1.1634683724235963e-05, - "loss": 0.141, + "epoch": 7.94, + "learning_rate": 6.883257526532381e-06, + "loss": 0.2018, "step": 12220 }, { - "epoch": 6.52, - "learning_rate": 1.1616915422885573e-05, - "loss": 0.1422, + "epoch": 7.94, + "learning_rate": 6.8615984405458085e-06, + "loss": 0.1647, "step": 12230 }, { - "epoch": 6.52, - "learning_rate": 1.1599147121535181e-05, - "loss": 0.1808, + "epoch": 7.95, + "learning_rate": 6.839939354559238e-06, + "loss": 0.0782, "step": 12240 }, { - "epoch": 6.53, - "learning_rate": 1.1581378820184792e-05, - "loss": 0.1519, + "epoch": 7.96, + "learning_rate": 6.818280268572666e-06, + "loss": 0.0471, "step": 12250 }, { - "epoch": 6.53, - "learning_rate": 1.15636105188344e-05, - "loss": 0.0677, + "epoch": 7.96, + "learning_rate": 6.796621182586095e-06, + "loss": 0.0793, "step": 12260 }, { - "epoch": 6.54, - "learning_rate": 1.1545842217484009e-05, - "loss": 0.161, + "epoch": 7.97, + "learning_rate": 6.774962096599523e-06, + "loss": 0.1777, "step": 12270 }, { - "epoch": 6.54, - "learning_rate": 1.1528073916133619e-05, - "loss": 0.3092, + "epoch": 7.98, + "learning_rate": 6.753303010612953e-06, + "loss": 0.1029, "step": 12280 }, { - "epoch": 6.55, - "learning_rate": 1.1510305614783228e-05, - "loss": 0.2395, + "epoch": 7.98, + "learning_rate": 6.731643924626381e-06, + "loss": 0.0013, "step": 12290 }, { - "epoch": 6.55, - "learning_rate": 1.1492537313432836e-05, - "loss": 0.0447, + "epoch": 7.99, + "learning_rate": 6.70998483863981e-06, + "loss": 0.1963, "step": 12300 }, { - "epoch": 6.56, - "learning_rate": 1.1474769012082445e-05, - "loss": 0.1726, + "epoch": 8.0, + "learning_rate": 6.688325752653238e-06, + "loss": 0.0781, "step": 12310 }, { - "epoch": 6.57, - "learning_rate": 1.1457000710732053e-05, - "loss": 0.1768, + "epoch": 8.0, + "eval_accuracy": 0.984820607175713, + "eval_loss": 0.07072959840297699, + "eval_runtime": 13.0034, + "eval_samples_per_second": 167.187, + "eval_steps_per_second": 41.835, + "step": 12316 + }, + { + "epoch": 8.0, + "learning_rate": 6.666666666666667e-06, + "loss": 0.1161, "step": 12320 }, { - "epoch": 6.57, - "learning_rate": 1.1439232409381664e-05, - "loss": 0.039, + "epoch": 8.01, + "learning_rate": 6.645007580680095e-06, + "loss": 0.2413, "step": 12330 }, { - "epoch": 6.58, - "learning_rate": 1.1421464108031272e-05, - "loss": 0.094, + "epoch": 8.02, + "learning_rate": 6.623348494693524e-06, + "loss": 0.1146, "step": 12340 }, { - "epoch": 6.58, - "learning_rate": 1.140369580668088e-05, - "loss": 0.1721, + "epoch": 8.02, + "learning_rate": 6.601689408706953e-06, + "loss": 0.0088, "step": 12350 }, { - "epoch": 6.59, - "learning_rate": 1.1385927505330491e-05, - "loss": 0.0734, + "epoch": 8.03, + "learning_rate": 6.580030322720381e-06, + "loss": 0.116, "step": 12360 }, { - "epoch": 6.59, - "learning_rate": 1.13681592039801e-05, - "loss": 0.3424, + "epoch": 8.04, + "learning_rate": 6.55837123673381e-06, + "loss": 0.0927, "step": 12370 }, { - "epoch": 6.6, - "learning_rate": 1.1350390902629708e-05, - "loss": 0.0621, + "epoch": 8.04, + "learning_rate": 6.536712150747239e-06, + "loss": 0.3197, "step": 12380 }, { - "epoch": 6.6, - "learning_rate": 1.1332622601279318e-05, - "loss": 0.257, + "epoch": 8.05, + "learning_rate": 6.5150530647606674e-06, + "loss": 0.1136, "step": 12390 }, { - "epoch": 6.61, - "learning_rate": 1.1314854299928927e-05, - "loss": 0.1345, + "epoch": 8.05, + "learning_rate": 6.493393978774096e-06, + "loss": 0.2585, "step": 12400 }, { - "epoch": 6.61, - "learning_rate": 1.1297085998578537e-05, - "loss": 0.1998, + "epoch": 8.06, + "learning_rate": 6.471734892787524e-06, + "loss": 0.127, "step": 12410 }, { - "epoch": 6.62, - "learning_rate": 1.1279317697228146e-05, - "loss": 0.2423, + "epoch": 8.07, + "learning_rate": 6.4500758068009535e-06, + "loss": 0.0578, "step": 12420 }, { - "epoch": 6.62, - "learning_rate": 1.1261549395877754e-05, - "loss": 0.2326, + "epoch": 8.07, + "learning_rate": 6.428416720814381e-06, + "loss": 0.0706, "step": 12430 }, { - "epoch": 6.63, - "learning_rate": 1.1243781094527364e-05, - "loss": 0.169, + "epoch": 8.08, + "learning_rate": 6.406757634827811e-06, + "loss": 0.1134, "step": 12440 }, { - "epoch": 6.63, - "learning_rate": 1.1226012793176973e-05, - "loss": 0.2371, + "epoch": 8.09, + "learning_rate": 6.385098548841239e-06, + "loss": 0.0335, "step": 12450 }, { - "epoch": 6.64, - "learning_rate": 1.1208244491826582e-05, - "loss": 0.2786, + "epoch": 8.09, + "learning_rate": 6.363439462854668e-06, + "loss": 0.0277, "step": 12460 }, { - "epoch": 6.65, - "learning_rate": 1.119047619047619e-05, - "loss": 0.0565, + "epoch": 8.1, + "learning_rate": 6.341780376868096e-06, + "loss": 0.1412, "step": 12470 }, { - "epoch": 6.65, - "learning_rate": 1.1172707889125799e-05, - "loss": 0.2564, + "epoch": 8.11, + "learning_rate": 6.320121290881526e-06, + "loss": 0.07, "step": 12480 }, { - "epoch": 6.66, - "learning_rate": 1.1154939587775409e-05, - "loss": 0.07, + "epoch": 8.11, + "learning_rate": 6.2984622048949534e-06, + "loss": 0.1496, "step": 12490 }, { - "epoch": 6.66, - "learning_rate": 1.1137171286425018e-05, - "loss": 0.2997, + "epoch": 8.12, + "learning_rate": 6.276803118908382e-06, + "loss": 0.0603, "step": 12500 }, { - "epoch": 6.67, - "learning_rate": 1.1119402985074626e-05, - "loss": 0.2112, + "epoch": 8.13, + "learning_rate": 6.255144032921811e-06, + "loss": 0.2813, "step": 12510 }, { - "epoch": 6.67, - "learning_rate": 1.1101634683724236e-05, - "loss": 0.1539, + "epoch": 8.13, + "learning_rate": 6.2334849469352395e-06, + "loss": 0.1433, "step": 12520 }, { - "epoch": 6.68, - "learning_rate": 1.1083866382373845e-05, - "loss": 0.3336, + "epoch": 8.14, + "learning_rate": 6.211825860948668e-06, + "loss": 0.3679, "step": 12530 }, { - "epoch": 6.68, - "learning_rate": 1.1066098081023455e-05, - "loss": 0.3091, + "epoch": 8.15, + "learning_rate": 6.190166774962097e-06, + "loss": 0.0328, "step": 12540 }, { - "epoch": 6.69, - "learning_rate": 1.1048329779673064e-05, - "loss": 0.2059, + "epoch": 8.15, + "learning_rate": 6.1685076889755256e-06, + "loss": 0.1398, "step": 12550 }, { - "epoch": 6.69, - "learning_rate": 1.1030561478322672e-05, - "loss": 0.1086, + "epoch": 8.16, + "learning_rate": 6.146848602988954e-06, + "loss": 0.1047, "step": 12560 }, { - "epoch": 6.7, - "learning_rate": 1.1012793176972283e-05, - "loss": 0.0637, + "epoch": 8.16, + "learning_rate": 6.125189517002383e-06, + "loss": 0.1391, "step": 12570 }, { - "epoch": 6.7, - "learning_rate": 1.0995024875621891e-05, - "loss": 0.1249, + "epoch": 8.17, + "learning_rate": 6.103530431015812e-06, + "loss": 0.0941, "step": 12580 }, { - "epoch": 6.71, - "learning_rate": 1.09772565742715e-05, - "loss": 0.2296, + "epoch": 8.18, + "learning_rate": 6.0818713450292395e-06, + "loss": 0.0813, "step": 12590 }, { - "epoch": 6.71, - "learning_rate": 1.095948827292111e-05, - "loss": 0.2637, + "epoch": 8.18, + "learning_rate": 6.060212259042669e-06, + "loss": 0.0015, "step": 12600 }, { - "epoch": 6.72, - "learning_rate": 1.0941719971570718e-05, - "loss": 0.2132, + "epoch": 8.19, + "learning_rate": 6.038553173056097e-06, + "loss": 0.1206, "step": 12610 }, { - "epoch": 6.73, - "learning_rate": 1.0923951670220329e-05, - "loss": 0.276, + "epoch": 8.2, + "learning_rate": 6.016894087069526e-06, + "loss": 0.158, "step": 12620 }, { - "epoch": 6.73, - "learning_rate": 1.0906183368869936e-05, - "loss": 0.1516, + "epoch": 8.2, + "learning_rate": 5.995235001082954e-06, + "loss": 0.0406, "step": 12630 }, { - "epoch": 6.74, - "learning_rate": 1.0888415067519544e-05, - "loss": 0.1306, + "epoch": 8.21, + "learning_rate": 5.973575915096384e-06, + "loss": 0.1629, "step": 12640 }, { - "epoch": 6.74, - "learning_rate": 1.0870646766169154e-05, - "loss": 0.2397, + "epoch": 8.22, + "learning_rate": 5.9519168291098116e-06, + "loss": 0.0426, "step": 12650 }, { - "epoch": 6.75, - "learning_rate": 1.0852878464818763e-05, - "loss": 0.188, + "epoch": 8.22, + "learning_rate": 5.930257743123241e-06, + "loss": 0.0673, "step": 12660 }, { - "epoch": 6.75, - "learning_rate": 1.0835110163468371e-05, - "loss": 0.3399, + "epoch": 8.23, + "learning_rate": 5.908598657136669e-06, + "loss": 0.037, "step": 12670 }, { - "epoch": 6.76, - "learning_rate": 1.0817341862117982e-05, - "loss": 0.1839, + "epoch": 8.24, + "learning_rate": 5.886939571150098e-06, + "loss": 0.0649, "step": 12680 }, { - "epoch": 6.76, - "learning_rate": 1.079957356076759e-05, - "loss": 0.1661, + "epoch": 8.24, + "learning_rate": 5.865280485163526e-06, + "loss": 0.2742, "step": 12690 }, { - "epoch": 6.77, - "learning_rate": 1.07818052594172e-05, - "loss": 0.222, + "epoch": 8.25, + "learning_rate": 5.843621399176955e-06, + "loss": 0.2166, "step": 12700 }, { - "epoch": 6.77, - "learning_rate": 1.0764036958066809e-05, - "loss": 0.1946, + "epoch": 8.26, + "learning_rate": 5.821962313190384e-06, + "loss": 0.0853, "step": 12710 }, { - "epoch": 6.78, - "learning_rate": 1.0746268656716418e-05, - "loss": 0.3648, + "epoch": 8.26, + "learning_rate": 5.800303227203812e-06, + "loss": 0.0083, "step": 12720 }, { - "epoch": 6.78, - "learning_rate": 1.0728500355366028e-05, - "loss": 0.5209, + "epoch": 8.27, + "learning_rate": 5.778644141217241e-06, + "loss": 0.1324, "step": 12730 }, { - "epoch": 6.79, - "learning_rate": 1.0710732054015636e-05, - "loss": 0.1622, + "epoch": 8.28, + "learning_rate": 5.75698505523067e-06, + "loss": 0.0543, "step": 12740 }, { - "epoch": 6.79, - "learning_rate": 1.0692963752665247e-05, - "loss": 0.1962, + "epoch": 8.28, + "learning_rate": 5.7353259692440976e-06, + "loss": 0.1978, "step": 12750 }, { - "epoch": 6.8, - "learning_rate": 1.0675195451314855e-05, - "loss": 0.1245, + "epoch": 8.29, + "learning_rate": 5.713666883257527e-06, + "loss": 0.112, "step": 12760 }, { - "epoch": 6.81, - "learning_rate": 1.0657427149964464e-05, - "loss": 0.3121, + "epoch": 8.29, + "learning_rate": 5.692007797270955e-06, + "loss": 0.1806, "step": 12770 }, { - "epoch": 6.81, - "learning_rate": 1.0639658848614074e-05, - "loss": 0.1224, + "epoch": 8.3, + "learning_rate": 5.6703487112843845e-06, + "loss": 0.0336, "step": 12780 }, { - "epoch": 6.82, - "learning_rate": 1.0621890547263683e-05, - "loss": 0.2589, + "epoch": 8.31, + "learning_rate": 5.648689625297812e-06, + "loss": 0.2045, "step": 12790 }, { - "epoch": 6.82, - "learning_rate": 1.060412224591329e-05, - "loss": 0.1718, + "epoch": 8.31, + "learning_rate": 5.627030539311242e-06, + "loss": 0.0968, "step": 12800 }, { - "epoch": 6.83, - "learning_rate": 1.05863539445629e-05, - "loss": 0.1486, + "epoch": 8.32, + "learning_rate": 5.60537145332467e-06, + "loss": 0.2564, "step": 12810 }, { - "epoch": 6.83, - "learning_rate": 1.0568585643212508e-05, - "loss": 0.1162, + "epoch": 8.33, + "learning_rate": 5.583712367338099e-06, + "loss": 0.078, "step": 12820 }, { - "epoch": 6.84, - "learning_rate": 1.0550817341862119e-05, - "loss": 0.1952, + "epoch": 8.33, + "learning_rate": 5.562053281351527e-06, + "loss": 0.2211, "step": 12830 }, { - "epoch": 6.84, - "learning_rate": 1.0533049040511727e-05, - "loss": 0.0806, + "epoch": 8.34, + "learning_rate": 5.540394195364956e-06, + "loss": 0.0235, "step": 12840 }, { - "epoch": 6.85, - "learning_rate": 1.0515280739161336e-05, - "loss": 0.1248, + "epoch": 8.35, + "learning_rate": 5.518735109378384e-06, + "loss": 0.0086, "step": 12850 }, { - "epoch": 6.85, - "learning_rate": 1.0497512437810946e-05, - "loss": 0.0879, + "epoch": 8.35, + "learning_rate": 5.497076023391813e-06, + "loss": 0.0448, "step": 12860 }, { - "epoch": 6.86, - "learning_rate": 1.0479744136460554e-05, - "loss": 0.1795, + "epoch": 8.36, + "learning_rate": 5.475416937405242e-06, + "loss": 0.0874, "step": 12870 }, { - "epoch": 6.86, - "learning_rate": 1.0461975835110163e-05, - "loss": 0.0726, + "epoch": 8.37, + "learning_rate": 5.4537578514186705e-06, + "loss": 0.1144, "step": 12880 }, { - "epoch": 6.87, - "learning_rate": 1.0444207533759773e-05, - "loss": 0.0962, + "epoch": 8.37, + "learning_rate": 5.432098765432099e-06, + "loss": 0.0012, "step": 12890 }, { - "epoch": 6.87, - "learning_rate": 1.0426439232409382e-05, - "loss": 0.2761, + "epoch": 8.38, + "learning_rate": 5.410439679445528e-06, + "loss": 0.1392, "step": 12900 }, { - "epoch": 6.88, - "learning_rate": 1.0408670931058992e-05, - "loss": 0.0489, + "epoch": 8.39, + "learning_rate": 5.3887805934589565e-06, + "loss": 0.0546, "step": 12910 }, { - "epoch": 6.89, - "learning_rate": 1.03909026297086e-05, - "loss": 0.1278, + "epoch": 8.39, + "learning_rate": 5.367121507472384e-06, + "loss": 0.0058, "step": 12920 }, { - "epoch": 6.89, - "learning_rate": 1.037313432835821e-05, - "loss": 0.2155, + "epoch": 8.4, + "learning_rate": 5.345462421485813e-06, + "loss": 0.1225, "step": 12930 }, { - "epoch": 6.9, - "learning_rate": 1.035536602700782e-05, - "loss": 0.2606, + "epoch": 8.41, + "learning_rate": 5.323803335499242e-06, + "loss": 0.0963, "step": 12940 }, { - "epoch": 6.9, - "learning_rate": 1.0337597725657428e-05, - "loss": 0.2111, + "epoch": 8.41, + "learning_rate": 5.30214424951267e-06, + "loss": 0.1001, "step": 12950 }, { - "epoch": 6.91, - "learning_rate": 1.0319829424307035e-05, - "loss": 0.0421, + "epoch": 8.42, + "learning_rate": 5.280485163526099e-06, + "loss": 0.1365, "step": 12960 }, { - "epoch": 6.91, - "learning_rate": 1.0302061122956645e-05, - "loss": 0.2872, + "epoch": 8.42, + "learning_rate": 5.258826077539528e-06, + "loss": 0.1296, "step": 12970 }, { - "epoch": 6.92, - "learning_rate": 1.0284292821606254e-05, - "loss": 0.2347, + "epoch": 8.43, + "learning_rate": 5.2371669915529565e-06, + "loss": 0.0279, "step": 12980 }, { - "epoch": 6.92, - "learning_rate": 1.0266524520255864e-05, - "loss": 0.1892, + "epoch": 8.44, + "learning_rate": 5.215507905566385e-06, + "loss": 0.0445, "step": 12990 }, { - "epoch": 6.93, - "learning_rate": 1.0248756218905473e-05, - "loss": 0.0934, + "epoch": 8.44, + "learning_rate": 5.193848819579814e-06, + "loss": 0.064, "step": 13000 }, { - "epoch": 6.93, - "learning_rate": 1.0230987917555081e-05, - "loss": 0.043, + "epoch": 8.45, + "learning_rate": 5.1721897335932425e-06, + "loss": 0.0262, "step": 13010 }, { - "epoch": 6.94, - "learning_rate": 1.0213219616204691e-05, - "loss": 0.2445, + "epoch": 8.46, + "learning_rate": 5.15053064760667e-06, + "loss": 0.2856, "step": 13020 }, { - "epoch": 6.94, - "learning_rate": 1.01954513148543e-05, - "loss": 0.1192, + "epoch": 8.46, + "learning_rate": 5.1288715616201e-06, + "loss": 0.1308, "step": 13030 }, { - "epoch": 6.95, - "learning_rate": 1.017768301350391e-05, - "loss": 0.2186, + "epoch": 8.47, + "learning_rate": 5.107212475633528e-06, + "loss": 0.1229, "step": 13040 }, { - "epoch": 6.95, - "learning_rate": 1.0159914712153519e-05, - "loss": 0.2833, + "epoch": 8.48, + "learning_rate": 5.085553389646957e-06, + "loss": 0.1929, "step": 13050 }, { - "epoch": 6.96, - "learning_rate": 1.0142146410803127e-05, - "loss": 0.1496, + "epoch": 8.48, + "learning_rate": 5.063894303660385e-06, + "loss": 0.1193, "step": 13060 }, { - "epoch": 6.97, - "learning_rate": 1.0124378109452738e-05, - "loss": 0.1557, + "epoch": 8.49, + "learning_rate": 5.042235217673815e-06, + "loss": 0.059, "step": 13070 }, { - "epoch": 6.97, - "learning_rate": 1.0106609808102346e-05, - "loss": 0.2021, + "epoch": 8.5, + "learning_rate": 5.0205761316872425e-06, + "loss": 0.1365, "step": 13080 }, { - "epoch": 6.98, - "learning_rate": 1.0088841506751955e-05, - "loss": 0.1757, + "epoch": 8.5, + "learning_rate": 4.998917045700672e-06, + "loss": 0.052, "step": 13090 }, { - "epoch": 6.98, - "learning_rate": 1.0071073205401565e-05, - "loss": 0.1087, + "epoch": 8.51, + "learning_rate": 4.9772579597141e-06, + "loss": 0.0587, "step": 13100 }, { - "epoch": 6.99, - "learning_rate": 1.0053304904051173e-05, - "loss": 0.0732, + "epoch": 8.52, + "learning_rate": 4.9555988737275285e-06, + "loss": 0.1808, "step": 13110 }, { - "epoch": 6.99, - "learning_rate": 1.0035536602700782e-05, - "loss": 0.1039, + "epoch": 8.52, + "learning_rate": 4.933939787740957e-06, + "loss": 0.071, "step": 13120 }, { - "epoch": 7.0, - "learning_rate": 1.001776830135039e-05, - "loss": 0.3824, + "epoch": 8.53, + "learning_rate": 4.912280701754386e-06, + "loss": 0.0762, "step": 13130 }, { - "epoch": 7.0, - "eval_accuracy": 0.9645149112872782, - "eval_loss": 0.15657095611095428, - "eval_runtime": 9.7151, - "eval_samples_per_second": 272.667, - "eval_steps_per_second": 68.244, - "step": 13135 - }, - { - "epoch": 7.0, - "learning_rate": 9.999999999999999e-06, - "loss": 0.2278, + "epoch": 8.54, + "learning_rate": 4.890621615767815e-06, + "loss": 0.0501, "step": 13140 }, { - "epoch": 7.01, - "learning_rate": 9.98223169864961e-06, - "loss": 0.252, + "epoch": 8.54, + "learning_rate": 4.868962529781243e-06, + "loss": 0.1167, "step": 13150 }, { - "epoch": 7.01, - "learning_rate": 9.964463397299218e-06, - "loss": 0.112, + "epoch": 8.55, + "learning_rate": 4.847303443794672e-06, + "loss": 0.2363, "step": 13160 }, { - "epoch": 7.02, - "learning_rate": 9.946695095948826e-06, - "loss": 0.091, + "epoch": 8.55, + "learning_rate": 4.825644357808101e-06, + "loss": 0.1063, "step": 13170 }, { - "epoch": 7.02, - "learning_rate": 9.928926794598437e-06, - "loss": 0.3112, + "epoch": 8.56, + "learning_rate": 4.803985271821529e-06, + "loss": 0.0592, "step": 13180 }, { - "epoch": 7.03, - "learning_rate": 9.911158493248045e-06, - "loss": 0.1523, + "epoch": 8.57, + "learning_rate": 4.782326185834958e-06, + "loss": 0.1423, "step": 13190 }, { - "epoch": 7.03, - "learning_rate": 9.893390191897656e-06, - "loss": 0.1401, + "epoch": 8.57, + "learning_rate": 4.760667099848386e-06, + "loss": 0.1531, "step": 13200 }, { - "epoch": 7.04, - "learning_rate": 9.875621890547264e-06, - "loss": 0.1272, + "epoch": 8.58, + "learning_rate": 4.739008013861815e-06, + "loss": 0.0018, "step": 13210 }, { - "epoch": 7.05, - "learning_rate": 9.857853589196873e-06, - "loss": 0.1499, + "epoch": 8.59, + "learning_rate": 4.717348927875243e-06, + "loss": 0.1259, "step": 13220 }, { - "epoch": 7.05, - "learning_rate": 9.840085287846483e-06, - "loss": 0.1578, + "epoch": 8.59, + "learning_rate": 4.695689841888673e-06, + "loss": 0.0096, "step": 13230 }, { - "epoch": 7.06, - "learning_rate": 9.82409381663113e-06, - "loss": 0.181, + "epoch": 8.6, + "learning_rate": 4.674030755902101e-06, + "loss": 0.1893, "step": 13240 }, - { - "epoch": 7.06, - "learning_rate": 9.80632551528074e-06, - "loss": 0.2483, - "step": 13250 - }, - { - "epoch": 7.07, - "learning_rate": 9.788557213930348e-06, - "loss": 0.256, - "step": 13260 - }, - { - "epoch": 7.07, - "learning_rate": 9.770788912579959e-06, - "loss": 0.0513, - "step": 13270 - }, - { - "epoch": 7.08, - "learning_rate": 9.753020611229567e-06, - "loss": 0.2169, - "step": 13280 - }, - { - "epoch": 7.08, - "learning_rate": 9.735252309879176e-06, - "loss": 0.0061, - "step": 13290 - }, - { - "epoch": 7.09, - "learning_rate": 9.717484008528786e-06, - "loss": 0.263, - "step": 13300 - }, - { - "epoch": 7.09, - "learning_rate": 9.699715707178394e-06, - "loss": 0.1737, - "step": 13310 - }, - { - "epoch": 7.1, - "learning_rate": 9.681947405828005e-06, - "loss": 0.2179, - "step": 13320 - }, - { - "epoch": 7.1, - "learning_rate": 9.664179104477612e-06, - "loss": 0.1276, - "step": 13330 - }, - { - "epoch": 7.11, - "learning_rate": 9.64641080312722e-06, - "loss": 0.1599, - "step": 13340 - }, - { - "epoch": 7.11, - "learning_rate": 9.62864250177683e-06, - "loss": 0.2461, - "step": 13350 - }, - { - "epoch": 7.12, - "learning_rate": 9.610874200426439e-06, - "loss": 0.2522, - "step": 13360 - }, - { - "epoch": 7.12, - "learning_rate": 9.593105899076047e-06, - "loss": 0.0608, - "step": 13370 - }, - { - "epoch": 7.13, - "learning_rate": 9.575337597725658e-06, - "loss": 0.0916, - "step": 13380 - }, - { - "epoch": 7.14, - "learning_rate": 9.557569296375266e-06, - "loss": 0.1997, - "step": 13390 - }, - { - "epoch": 7.14, - "learning_rate": 9.539800995024877e-06, - "loss": 0.1801, - "step": 13400 - }, - { - "epoch": 7.15, - "learning_rate": 9.522032693674485e-06, - "loss": 0.4076, - "step": 13410 - }, - { - "epoch": 7.15, - "learning_rate": 9.504264392324094e-06, - "loss": 0.1435, - "step": 13420 - }, - { - "epoch": 7.16, - "learning_rate": 9.486496090973704e-06, - "loss": 0.0819, - "step": 13430 - }, - { - "epoch": 7.16, - "learning_rate": 9.468727789623312e-06, - "loss": 0.0664, - "step": 13440 - }, - { - "epoch": 7.17, - "learning_rate": 9.450959488272921e-06, - "loss": 0.1741, - "step": 13450 - }, - { - "epoch": 7.17, - "learning_rate": 9.433191186922531e-06, - "loss": 0.271, - "step": 13460 - }, - { - "epoch": 7.18, - "learning_rate": 9.41542288557214e-06, - "loss": 0.2559, - "step": 13470 - }, - { - "epoch": 7.18, - "learning_rate": 9.39765458422175e-06, - "loss": 0.2646, - "step": 13480 - }, - { - "epoch": 7.19, - "learning_rate": 9.379886282871357e-06, - "loss": 0.0711, - "step": 13490 - }, - { - "epoch": 7.19, - "learning_rate": 9.362117981520966e-06, - "loss": 0.0912, - "step": 13500 - }, - { - "epoch": 7.2, - "learning_rate": 9.344349680170576e-06, - "loss": 0.1587, - "step": 13510 - }, - { - "epoch": 7.2, - "learning_rate": 9.326581378820184e-06, - "loss": 0.2628, - "step": 13520 - }, - { - "epoch": 7.21, - "learning_rate": 9.308813077469795e-06, - "loss": 0.1617, - "step": 13530 - }, - { - "epoch": 7.22, - "learning_rate": 9.291044776119403e-06, - "loss": 0.0432, - "step": 13540 - }, - { - "epoch": 7.22, - "learning_rate": 9.273276474769012e-06, - "loss": 0.0536, - "step": 13550 - }, - { - "epoch": 7.23, - "learning_rate": 9.255508173418622e-06, - "loss": 0.0355, - "step": 13560 - }, - { - "epoch": 7.23, - "learning_rate": 9.23773987206823e-06, - "loss": 0.0086, - "step": 13570 - }, - { - "epoch": 7.24, - "learning_rate": 9.219971570717839e-06, - "loss": 0.108, - "step": 13580 - }, - { - "epoch": 7.24, - "learning_rate": 9.20220326936745e-06, - "loss": 0.0701, - "step": 13590 - }, - { - "epoch": 7.25, - "learning_rate": 9.184434968017058e-06, - "loss": 0.2314, - "step": 13600 - }, - { - "epoch": 7.25, - "learning_rate": 9.166666666666668e-06, - "loss": 0.328, - "step": 13610 - }, - { - "epoch": 7.26, - "learning_rate": 9.148898365316277e-06, - "loss": 0.3021, - "step": 13620 - }, - { - "epoch": 7.26, - "learning_rate": 9.131130063965885e-06, - "loss": 0.1, - "step": 13630 - }, - { - "epoch": 7.27, - "learning_rate": 9.113361762615495e-06, - "loss": 0.0979, - "step": 13640 - }, - { - "epoch": 7.27, - "learning_rate": 9.095593461265102e-06, - "loss": 0.1966, - "step": 13650 - }, - { - "epoch": 7.28, - "learning_rate": 9.077825159914711e-06, - "loss": 0.2364, - "step": 13660 - }, - { - "epoch": 7.28, - "learning_rate": 9.060056858564321e-06, - "loss": 0.0919, - "step": 13670 - }, - { - "epoch": 7.29, - "learning_rate": 9.04228855721393e-06, - "loss": 0.0814, - "step": 13680 - }, - { - "epoch": 7.3, - "learning_rate": 9.02452025586354e-06, - "loss": 0.164, - "step": 13690 - }, - { - "epoch": 7.3, - "learning_rate": 9.006751954513149e-06, - "loss": 0.0821, - "step": 13700 - }, - { - "epoch": 7.31, - "learning_rate": 8.988983653162757e-06, - "loss": 0.049, - "step": 13710 - }, - { - "epoch": 7.31, - "learning_rate": 8.971215351812367e-06, - "loss": 0.1201, - "step": 13720 - }, - { - "epoch": 7.32, - "learning_rate": 8.953447050461976e-06, - "loss": 0.0126, - "step": 13730 - }, - { - "epoch": 7.32, - "learning_rate": 8.935678749111584e-06, - "loss": 0.0324, - "step": 13740 - }, - { - "epoch": 7.33, - "learning_rate": 8.917910447761195e-06, - "loss": 0.2061, - "step": 13750 - }, - { - "epoch": 7.33, - "learning_rate": 8.900142146410803e-06, - "loss": 0.2395, - "step": 13760 - }, - { - "epoch": 7.34, - "learning_rate": 8.882373845060414e-06, - "loss": 0.218, - "step": 13770 - }, - { - "epoch": 7.34, - "learning_rate": 8.864605543710022e-06, - "loss": 0.1643, - "step": 13780 - }, - { - "epoch": 7.35, - "learning_rate": 8.84683724235963e-06, - "loss": 0.2081, - "step": 13790 - }, - { - "epoch": 7.35, - "learning_rate": 8.829068941009241e-06, - "loss": 0.1802, - "step": 13800 - }, - { - "epoch": 7.36, - "learning_rate": 8.811300639658848e-06, - "loss": 0.1062, - "step": 13810 - }, - { - "epoch": 7.36, - "learning_rate": 8.793532338308458e-06, - "loss": 0.2457, - "step": 13820 - }, - { - "epoch": 7.37, - "learning_rate": 8.775764036958067e-06, - "loss": 0.1597, - "step": 13830 - }, - { - "epoch": 7.38, - "learning_rate": 8.757995735607675e-06, - "loss": 0.1603, - "step": 13840 - }, - { - "epoch": 7.38, - "learning_rate": 8.740227434257285e-06, - "loss": 0.2638, - "step": 13850 - }, - { - "epoch": 7.39, - "learning_rate": 8.722459132906894e-06, - "loss": 0.075, - "step": 13860 - }, - { - "epoch": 7.39, - "learning_rate": 8.704690831556502e-06, - "loss": 0.1756, - "step": 13870 - }, - { - "epoch": 7.4, - "learning_rate": 8.686922530206113e-06, - "loss": 0.1719, - "step": 13880 - }, - { - "epoch": 7.4, - "learning_rate": 8.669154228855721e-06, - "loss": 0.113, - "step": 13890 - }, - { - "epoch": 7.41, - "learning_rate": 8.651385927505332e-06, - "loss": 0.0867, - "step": 13900 - }, - { - "epoch": 7.41, - "learning_rate": 8.63361762615494e-06, - "loss": 0.2506, - "step": 13910 - }, - { - "epoch": 7.42, - "learning_rate": 8.615849324804549e-06, - "loss": 0.3665, - "step": 13920 - }, - { - "epoch": 7.42, - "learning_rate": 8.598081023454159e-06, - "loss": 0.2422, - "step": 13930 - }, - { - "epoch": 7.43, - "learning_rate": 8.580312722103767e-06, - "loss": 0.0068, - "step": 13940 - }, - { - "epoch": 7.43, - "learning_rate": 8.562544420753376e-06, - "loss": 0.1116, - "step": 13950 - }, - { - "epoch": 7.44, - "learning_rate": 8.544776119402986e-06, - "loss": 0.2004, - "step": 13960 - }, - { - "epoch": 7.44, - "learning_rate": 8.527007818052593e-06, - "loss": 0.1025, - "step": 13970 - }, - { - "epoch": 7.45, - "learning_rate": 8.509239516702203e-06, - "loss": 0.0584, - "step": 13980 - }, - { - "epoch": 7.46, - "learning_rate": 8.491471215351812e-06, - "loss": 0.11, - "step": 13990 - }, - { - "epoch": 7.46, - "learning_rate": 8.47370291400142e-06, - "loss": 0.066, - "step": 14000 - }, - { - "epoch": 7.47, - "learning_rate": 8.45593461265103e-06, - "loss": 0.3003, - "step": 14010 - }, - { - "epoch": 7.47, - "learning_rate": 8.43816631130064e-06, - "loss": 0.0167, - "step": 14020 - }, - { - "epoch": 7.48, - "learning_rate": 8.42039800995025e-06, - "loss": 0.3342, - "step": 14030 - }, - { - "epoch": 7.48, - "learning_rate": 8.402629708599858e-06, - "loss": 0.1746, - "step": 14040 - }, - { - "epoch": 7.49, - "learning_rate": 8.384861407249467e-06, - "loss": 0.427, - "step": 14050 - }, - { - "epoch": 7.49, - "learning_rate": 8.367093105899077e-06, - "loss": 0.0993, - "step": 14060 - }, - { - "epoch": 7.5, - "learning_rate": 8.349324804548686e-06, - "loss": 0.223, - "step": 14070 - }, - { - "epoch": 7.5, - "learning_rate": 8.331556503198294e-06, - "loss": 0.223, - "step": 14080 - }, - { - "epoch": 7.51, - "learning_rate": 8.313788201847904e-06, - "loss": 0.1527, - "step": 14090 - }, - { - "epoch": 7.51, - "learning_rate": 8.296019900497513e-06, - "loss": 0.2897, - "step": 14100 - }, - { - "epoch": 7.52, - "learning_rate": 8.278251599147123e-06, - "loss": 0.0562, - "step": 14110 - }, - { - "epoch": 7.52, - "learning_rate": 8.260483297796732e-06, - "loss": 0.1313, - "step": 14120 - }, - { - "epoch": 7.53, - "learning_rate": 8.242714996446339e-06, - "loss": 0.1154, - "step": 14130 - }, - { - "epoch": 7.54, - "learning_rate": 8.224946695095949e-06, - "loss": 0.0253, - "step": 14140 - }, - { - "epoch": 7.54, - "learning_rate": 8.207178393745557e-06, - "loss": 0.2315, - "step": 14150 - }, - { - "epoch": 7.55, - "learning_rate": 8.189410092395166e-06, - "loss": 0.3137, - "step": 14160 - }, - { - "epoch": 7.55, - "learning_rate": 8.171641791044776e-06, - "loss": 0.1433, - "step": 14170 - }, - { - "epoch": 7.56, - "learning_rate": 8.153873489694385e-06, - "loss": 0.0603, - "step": 14180 - }, - { - "epoch": 7.56, - "learning_rate": 8.136105188343995e-06, - "loss": 0.1622, - "step": 14190 - }, - { - "epoch": 7.57, - "learning_rate": 8.118336886993604e-06, - "loss": 0.3569, - "step": 14200 - }, - { - "epoch": 7.57, - "learning_rate": 8.100568585643212e-06, - "loss": 0.2478, - "step": 14210 - }, - { - "epoch": 7.58, - "learning_rate": 8.082800284292822e-06, - "loss": 0.1235, - "step": 14220 - }, - { - "epoch": 7.58, - "learning_rate": 8.065031982942431e-06, - "loss": 0.1639, - "step": 14230 - }, - { - "epoch": 7.59, - "learning_rate": 8.04726368159204e-06, - "loss": 0.2239, - "step": 14240 - }, - { - "epoch": 7.59, - "learning_rate": 8.02949538024165e-06, - "loss": 0.1809, - "step": 14250 - }, - { - "epoch": 7.6, - "learning_rate": 8.011727078891258e-06, - "loss": 0.1679, - "step": 14260 - }, - { - "epoch": 7.6, - "learning_rate": 7.993958777540869e-06, - "loss": 0.2095, - "step": 14270 - }, - { - "epoch": 7.61, - "learning_rate": 7.976190476190477e-06, - "loss": 0.2992, - "step": 14280 - }, - { - "epoch": 7.62, - "learning_rate": 7.958422174840086e-06, - "loss": 0.0062, - "step": 14290 - }, - { - "epoch": 7.62, - "learning_rate": 7.940653873489694e-06, - "loss": 0.13, - "step": 14300 - }, - { - "epoch": 7.63, - "learning_rate": 7.922885572139303e-06, - "loss": 0.0993, - "step": 14310 - }, - { - "epoch": 7.63, - "learning_rate": 7.905117270788913e-06, - "loss": 0.0585, - "step": 14320 - }, - { - "epoch": 7.64, - "learning_rate": 7.887348969438522e-06, - "loss": 0.0551, - "step": 14330 - }, - { - "epoch": 7.64, - "learning_rate": 7.86958066808813e-06, - "loss": 0.0084, - "step": 14340 - }, - { - "epoch": 7.65, - "learning_rate": 7.85181236673774e-06, - "loss": 0.1411, - "step": 14350 - }, - { - "epoch": 7.65, - "learning_rate": 7.834044065387349e-06, - "loss": 0.1393, - "step": 14360 - }, - { - "epoch": 7.66, - "learning_rate": 7.816275764036958e-06, - "loss": 0.2242, - "step": 14370 - }, - { - "epoch": 7.66, - "learning_rate": 7.798507462686568e-06, - "loss": 0.0333, - "step": 14380 - }, - { - "epoch": 7.67, - "learning_rate": 7.780739161336176e-06, - "loss": 0.1796, - "step": 14390 - }, - { - "epoch": 7.67, - "learning_rate": 7.762970859985787e-06, - "loss": 0.1072, - "step": 14400 - }, - { - "epoch": 7.68, - "learning_rate": 7.745202558635395e-06, - "loss": 0.1781, - "step": 14410 - }, - { - "epoch": 7.68, - "learning_rate": 7.727434257285004e-06, - "loss": 0.1305, - "step": 14420 - }, - { - "epoch": 7.69, - "learning_rate": 7.709665955934614e-06, - "loss": 0.1958, - "step": 14430 - }, - { - "epoch": 7.7, - "learning_rate": 7.691897654584223e-06, - "loss": 0.1939, - "step": 14440 - }, - { - "epoch": 7.7, - "learning_rate": 7.674129353233831e-06, - "loss": 0.3947, - "step": 14450 - }, - { - "epoch": 7.71, - "learning_rate": 7.65636105188344e-06, - "loss": 0.0551, - "step": 14460 - }, - { - "epoch": 7.71, - "learning_rate": 7.638592750533048e-06, - "loss": 0.4153, - "step": 14470 - }, - { - "epoch": 7.72, - "learning_rate": 7.620824449182659e-06, - "loss": 0.1806, - "step": 14480 - }, - { - "epoch": 7.72, - "learning_rate": 7.603056147832268e-06, - "loss": 0.0898, - "step": 14490 - }, - { - "epoch": 7.73, - "learning_rate": 7.5852878464818756e-06, - "loss": 0.1065, - "step": 14500 - }, - { - "epoch": 7.73, - "learning_rate": 7.567519545131486e-06, - "loss": 0.2878, - "step": 14510 - }, - { - "epoch": 7.74, - "learning_rate": 7.549751243781094e-06, - "loss": 0.0324, - "step": 14520 - }, - { - "epoch": 7.74, - "learning_rate": 7.531982942430705e-06, - "loss": 0.0308, - "step": 14530 - }, - { - "epoch": 7.75, - "learning_rate": 7.514214641080313e-06, - "loss": 0.1345, - "step": 14540 - }, - { - "epoch": 7.75, - "learning_rate": 7.496446339729923e-06, - "loss": 0.3351, - "step": 14550 - }, - { - "epoch": 7.76, - "learning_rate": 7.478678038379531e-06, - "loss": 0.1744, - "step": 14560 - }, - { - "epoch": 7.76, - "learning_rate": 7.4609097370291405e-06, - "loss": 0.2229, - "step": 14570 - }, - { - "epoch": 7.77, - "learning_rate": 7.443141435678749e-06, - "loss": 0.0062, - "step": 14580 - }, - { - "epoch": 7.78, - "learning_rate": 7.4253731343283585e-06, - "loss": 0.2174, - "step": 14590 - }, - { - "epoch": 7.78, - "learning_rate": 7.407604832977967e-06, - "loss": 0.1333, - "step": 14600 - }, - { - "epoch": 7.79, - "learning_rate": 7.3898365316275765e-06, - "loss": 0.4807, - "step": 14610 - }, - { - "epoch": 7.79, - "learning_rate": 7.372068230277186e-06, - "loss": 0.0466, - "step": 14620 - }, - { - "epoch": 7.8, - "learning_rate": 7.354299928926795e-06, - "loss": 0.0735, - "step": 14630 - }, - { - "epoch": 7.8, - "learning_rate": 7.336531627576404e-06, - "loss": 0.0888, - "step": 14640 - }, - { - "epoch": 7.81, - "learning_rate": 7.318763326226013e-06, - "loss": 0.2913, - "step": 14650 - }, - { - "epoch": 7.81, - "learning_rate": 7.300995024875622e-06, - "loss": 0.3388, - "step": 14660 - }, - { - "epoch": 7.82, - "learning_rate": 7.283226723525231e-06, - "loss": 0.1307, - "step": 14670 - }, - { - "epoch": 7.82, - "learning_rate": 7.26545842217484e-06, - "loss": 0.1983, - "step": 14680 - }, - { - "epoch": 7.83, - "learning_rate": 7.247690120824449e-06, - "loss": 0.2245, - "step": 14690 - }, - { - "epoch": 7.83, - "learning_rate": 7.229921819474059e-06, - "loss": 0.3639, - "step": 14700 - }, - { - "epoch": 7.84, - "learning_rate": 7.212153518123668e-06, - "loss": 0.027, - "step": 14710 - }, - { - "epoch": 7.84, - "learning_rate": 7.1943852167732765e-06, - "loss": 0.1849, - "step": 14720 - }, - { - "epoch": 7.85, - "learning_rate": 7.176616915422886e-06, - "loss": 0.0951, - "step": 14730 - }, - { - "epoch": 7.86, - "learning_rate": 7.1588486140724945e-06, - "loss": 0.1917, - "step": 14740 - }, - { - "epoch": 7.86, - "learning_rate": 7.141080312722104e-06, - "loss": 0.2925, - "step": 14750 - }, - { - "epoch": 7.87, - "learning_rate": 7.123312011371713e-06, - "loss": 0.0974, - "step": 14760 - }, - { - "epoch": 7.87, - "learning_rate": 7.105543710021322e-06, - "loss": 0.2287, - "step": 14770 - }, - { - "epoch": 7.88, - "learning_rate": 7.087775408670931e-06, - "loss": 0.3106, - "step": 14780 - }, - { - "epoch": 7.88, - "learning_rate": 7.070007107320541e-06, - "loss": 0.1268, - "step": 14790 - }, - { - "epoch": 7.89, - "learning_rate": 7.05223880597015e-06, - "loss": 0.2225, - "step": 14800 - }, - { - "epoch": 7.89, - "learning_rate": 7.034470504619759e-06, - "loss": 0.1369, - "step": 14810 - }, - { - "epoch": 7.9, - "learning_rate": 7.016702203269367e-06, - "loss": 0.212, - "step": 14820 - }, - { - "epoch": 7.9, - "learning_rate": 6.998933901918977e-06, - "loss": 0.254, - "step": 14830 - }, - { - "epoch": 7.91, - "learning_rate": 6.981165600568586e-06, - "loss": 0.1284, - "step": 14840 - }, - { - "epoch": 7.91, - "learning_rate": 6.9633972992181946e-06, - "loss": 0.2463, - "step": 14850 - }, - { - "epoch": 7.92, - "learning_rate": 6.945628997867804e-06, - "loss": 0.098, - "step": 14860 - }, - { - "epoch": 7.92, - "learning_rate": 6.927860696517413e-06, - "loss": 0.098, - "step": 14870 - }, - { - "epoch": 7.93, - "learning_rate": 6.910092395167023e-06, - "loss": 0.1395, - "step": 14880 - }, - { - "epoch": 7.93, - "learning_rate": 6.892324093816631e-06, - "loss": 0.148, - "step": 14890 - }, - { - "epoch": 7.94, - "learning_rate": 6.87455579246624e-06, - "loss": 0.0818, - "step": 14900 - }, - { - "epoch": 7.95, - "learning_rate": 6.856787491115849e-06, - "loss": 0.0546, - "step": 14910 - }, - { - "epoch": 7.95, - "learning_rate": 6.839019189765459e-06, - "loss": 0.0495, - "step": 14920 - }, - { - "epoch": 7.96, - "learning_rate": 6.821250888415067e-06, - "loss": 0.133, - "step": 14930 - }, - { - "epoch": 7.96, - "learning_rate": 6.803482587064677e-06, - "loss": 0.1432, - "step": 14940 - }, - { - "epoch": 7.97, - "learning_rate": 6.785714285714286e-06, - "loss": 0.1335, - "step": 14950 - }, - { - "epoch": 7.97, - "learning_rate": 6.7679459843638955e-06, - "loss": 0.1568, - "step": 14960 - }, - { - "epoch": 7.98, - "learning_rate": 6.750177683013504e-06, - "loss": 0.2021, - "step": 14970 - }, - { - "epoch": 7.98, - "learning_rate": 6.732409381663113e-06, - "loss": 0.2746, - "step": 14980 - }, - { - "epoch": 7.99, - "learning_rate": 6.714641080312722e-06, - "loss": 0.0729, - "step": 14990 - }, - { - "epoch": 7.99, - "learning_rate": 6.696872778962331e-06, - "loss": 0.2017, - "step": 15000 - }, - { - "epoch": 8.0, - "learning_rate": 6.679104477611941e-06, - "loss": 0.1782, - "step": 15010 - }, - { - "epoch": 8.0, - "eval_accuracy": 0.9667799169497924, - "eval_loss": 0.16765306890010834, - "eval_runtime": 9.8453, - "eval_samples_per_second": 269.063, - "eval_steps_per_second": 67.342, - "step": 15012 - }, - { - "epoch": 8.0, - "learning_rate": 6.661336176261549e-06, - "loss": 0.0439, - "step": 15020 - }, - { - "epoch": 8.01, - "learning_rate": 6.643567874911159e-06, - "loss": 0.1638, - "step": 15030 - }, - { - "epoch": 8.01, - "learning_rate": 6.625799573560768e-06, - "loss": 0.1502, - "step": 15040 - }, - { - "epoch": 8.02, - "learning_rate": 6.608031272210378e-06, - "loss": 0.0475, - "step": 15050 - }, - { - "epoch": 8.03, - "learning_rate": 6.590262970859985e-06, - "loss": 0.2378, - "step": 15060 - }, - { - "epoch": 8.03, - "learning_rate": 6.572494669509595e-06, - "loss": 0.1054, - "step": 15070 - }, - { - "epoch": 8.04, - "learning_rate": 6.554726368159204e-06, - "loss": 0.1416, - "step": 15080 - }, - { - "epoch": 8.04, - "learning_rate": 6.5369580668088135e-06, - "loss": 0.0498, - "step": 15090 - }, - { - "epoch": 8.05, - "learning_rate": 6.519189765458422e-06, - "loss": 0.1553, - "step": 15100 - }, - { - "epoch": 8.05, - "learning_rate": 6.5014214641080315e-06, - "loss": 0.1345, - "step": 15110 - }, - { - "epoch": 8.06, - "learning_rate": 6.483653162757641e-06, - "loss": 0.1362, - "step": 15120 - }, - { - "epoch": 8.06, - "learning_rate": 6.46588486140725e-06, - "loss": 0.0659, - "step": 15130 - }, - { - "epoch": 8.07, - "learning_rate": 6.448116560056858e-06, - "loss": 0.349, - "step": 15140 - }, - { - "epoch": 8.07, - "learning_rate": 6.430348258706467e-06, - "loss": 0.0375, - "step": 15150 - }, - { - "epoch": 8.08, - "learning_rate": 6.412579957356077e-06, - "loss": 0.3039, - "step": 15160 - }, - { - "epoch": 8.08, - "learning_rate": 6.394811656005686e-06, - "loss": 0.1999, - "step": 15170 - }, - { - "epoch": 8.09, - "learning_rate": 6.377043354655295e-06, - "loss": 0.0703, - "step": 15180 - }, - { - "epoch": 8.09, - "learning_rate": 6.359275053304904e-06, - "loss": 0.4332, - "step": 15190 - }, - { - "epoch": 8.1, - "learning_rate": 6.341506751954514e-06, - "loss": 0.0522, - "step": 15200 - }, - { - "epoch": 8.11, - "learning_rate": 6.323738450604123e-06, - "loss": 0.055, - "step": 15210 - }, - { - "epoch": 8.11, - "learning_rate": 6.305970149253731e-06, - "loss": 0.1256, - "step": 15220 - }, - { - "epoch": 8.12, - "learning_rate": 6.28820184790334e-06, - "loss": 0.2073, - "step": 15230 - }, - { - "epoch": 8.12, - "learning_rate": 6.2704335465529495e-06, - "loss": 0.1362, - "step": 15240 - }, - { - "epoch": 8.13, - "learning_rate": 6.252665245202559e-06, - "loss": 0.2927, - "step": 15250 - }, - { - "epoch": 8.13, - "learning_rate": 6.234896943852168e-06, - "loss": 0.0806, - "step": 15260 - }, - { - "epoch": 8.14, - "learning_rate": 6.217128642501777e-06, - "loss": 0.0703, - "step": 15270 - }, - { - "epoch": 8.14, - "learning_rate": 6.199360341151386e-06, - "loss": 0.0611, - "step": 15280 - }, - { - "epoch": 8.15, - "learning_rate": 6.181592039800996e-06, - "loss": 0.1801, - "step": 15290 - }, - { - "epoch": 8.15, - "learning_rate": 6.163823738450604e-06, - "loss": 0.1462, - "step": 15300 - }, - { - "epoch": 8.16, - "learning_rate": 6.146055437100213e-06, - "loss": 0.0378, - "step": 15310 - }, - { - "epoch": 8.16, - "learning_rate": 6.128287135749822e-06, - "loss": 0.0999, - "step": 15320 - }, - { - "epoch": 8.17, - "learning_rate": 6.110518834399432e-06, - "loss": 0.0059, - "step": 15330 - }, - { - "epoch": 8.17, - "learning_rate": 6.092750533049041e-06, - "loss": 0.1316, - "step": 15340 - }, - { - "epoch": 8.18, - "learning_rate": 6.07498223169865e-06, - "loss": 0.1616, - "step": 15350 - }, - { - "epoch": 8.19, - "learning_rate": 6.057213930348259e-06, - "loss": 0.1688, - "step": 15360 - }, - { - "epoch": 8.19, - "learning_rate": 6.039445628997868e-06, - "loss": 0.1903, - "step": 15370 - }, - { - "epoch": 8.2, - "learning_rate": 6.021677327647477e-06, - "loss": 0.2186, - "step": 15380 - }, - { - "epoch": 8.2, - "learning_rate": 6.0039090262970855e-06, - "loss": 0.2809, - "step": 15390 - }, - { - "epoch": 8.21, - "learning_rate": 5.986140724946695e-06, - "loss": 0.3657, - "step": 15400 - }, - { - "epoch": 8.21, - "learning_rate": 5.968372423596304e-06, - "loss": 0.2632, - "step": 15410 - }, - { - "epoch": 8.22, - "learning_rate": 5.950604122245914e-06, - "loss": 0.1907, - "step": 15420 - }, - { - "epoch": 8.22, - "learning_rate": 5.932835820895522e-06, - "loss": 0.1519, - "step": 15430 - }, - { - "epoch": 8.23, - "learning_rate": 5.915067519545132e-06, - "loss": 0.2733, - "step": 15440 - }, - { - "epoch": 8.23, - "learning_rate": 5.897299218194741e-06, - "loss": 0.222, - "step": 15450 - }, - { - "epoch": 8.24, - "learning_rate": 5.8813077469793885e-06, - "loss": 0.3607, - "step": 15460 - }, - { - "epoch": 8.24, - "learning_rate": 5.863539445628998e-06, - "loss": 0.2804, - "step": 15470 - }, - { - "epoch": 8.25, - "learning_rate": 5.845771144278607e-06, - "loss": 0.0264, - "step": 15480 - }, - { - "epoch": 8.25, - "learning_rate": 5.828002842928217e-06, - "loss": 0.22, - "step": 15490 - }, - { - "epoch": 8.26, - "learning_rate": 5.810234541577825e-06, - "loss": 0.2293, - "step": 15500 - }, - { - "epoch": 8.27, - "learning_rate": 5.792466240227434e-06, - "loss": 0.0466, - "step": 15510 - }, - { - "epoch": 8.27, - "learning_rate": 5.774697938877043e-06, - "loss": 0.2834, - "step": 15520 - }, - { - "epoch": 8.28, - "learning_rate": 5.756929637526653e-06, - "loss": 0.2224, - "step": 15530 - }, - { - "epoch": 8.28, - "learning_rate": 5.739161336176262e-06, - "loss": 0.0211, - "step": 15540 - }, - { - "epoch": 8.29, - "learning_rate": 5.721393034825871e-06, - "loss": 0.0976, - "step": 15550 - }, - { - "epoch": 8.29, - "learning_rate": 5.70362473347548e-06, - "loss": 0.076, - "step": 15560 - }, - { - "epoch": 8.3, - "learning_rate": 5.685856432125089e-06, - "loss": 0.1288, - "step": 15570 - }, - { - "epoch": 8.3, - "learning_rate": 5.668088130774699e-06, - "loss": 0.1142, - "step": 15580 - }, - { - "epoch": 8.31, - "learning_rate": 5.6503198294243065e-06, - "loss": 0.1735, - "step": 15590 - }, - { - "epoch": 8.31, - "learning_rate": 5.632551528073916e-06, - "loss": 0.1031, - "step": 15600 - }, - { - "epoch": 8.32, - "learning_rate": 5.614783226723525e-06, - "loss": 0.1069, - "step": 15610 - }, - { - "epoch": 8.32, - "learning_rate": 5.597014925373135e-06, - "loss": 0.0943, - "step": 15620 - }, - { - "epoch": 8.33, - "learning_rate": 5.579246624022743e-06, - "loss": 0.1284, - "step": 15630 - }, - { - "epoch": 8.33, - "learning_rate": 5.561478322672353e-06, - "loss": 0.1513, - "step": 15640 - }, - { - "epoch": 8.34, - "learning_rate": 5.543710021321962e-06, - "loss": 0.0694, - "step": 15650 - }, - { - "epoch": 8.35, - "learning_rate": 5.5259417199715715e-06, - "loss": 0.2541, - "step": 15660 - }, - { - "epoch": 8.35, - "learning_rate": 5.508173418621179e-06, - "loss": 0.2982, - "step": 15670 - }, - { - "epoch": 8.36, - "learning_rate": 5.490405117270789e-06, - "loss": 0.0732, - "step": 15680 - }, - { - "epoch": 8.36, - "learning_rate": 5.472636815920398e-06, - "loss": 0.2603, - "step": 15690 - }, - { - "epoch": 8.37, - "learning_rate": 5.4548685145700074e-06, - "loss": 0.0966, - "step": 15700 - }, - { - "epoch": 8.37, - "learning_rate": 5.437100213219616e-06, - "loss": 0.1253, - "step": 15710 - }, - { - "epoch": 8.38, - "learning_rate": 5.419331911869225e-06, - "loss": 0.1666, - "step": 15720 - }, - { - "epoch": 8.38, - "learning_rate": 5.401563610518835e-06, - "loss": 0.0112, - "step": 15730 - }, - { - "epoch": 8.39, - "learning_rate": 5.383795309168444e-06, - "loss": 0.0953, - "step": 15740 - }, - { - "epoch": 8.39, - "learning_rate": 5.366027007818052e-06, - "loss": 0.0863, - "step": 15750 - }, - { - "epoch": 8.4, - "learning_rate": 5.348258706467661e-06, - "loss": 0.1284, - "step": 15760 - }, - { - "epoch": 8.4, - "learning_rate": 5.330490405117271e-06, - "loss": 0.2124, - "step": 15770 - }, - { - "epoch": 8.41, - "learning_rate": 5.31272210376688e-06, - "loss": 0.0852, - "step": 15780 - }, - { - "epoch": 8.41, - "learning_rate": 5.2949538024164895e-06, - "loss": 0.2165, - "step": 15790 - }, - { - "epoch": 8.42, - "learning_rate": 5.277185501066098e-06, - "loss": 0.1301, - "step": 15800 - }, - { - "epoch": 8.43, - "learning_rate": 5.2594171997157075e-06, - "loss": 0.1006, - "step": 15810 - }, - { - "epoch": 8.43, - "learning_rate": 5.241648898365317e-06, - "loss": 0.0151, - "step": 15820 - }, - { - "epoch": 8.44, - "learning_rate": 5.2238805970149255e-06, - "loss": 0.0524, - "step": 15830 - }, - { - "epoch": 8.44, - "learning_rate": 5.206112295664534e-06, - "loss": 0.1007, - "step": 15840 - }, - { - "epoch": 8.45, - "learning_rate": 5.188343994314143e-06, - "loss": 0.2105, - "step": 15850 - }, - { - "epoch": 8.45, - "learning_rate": 5.170575692963753e-06, - "loss": 0.0867, - "step": 15860 - }, - { - "epoch": 8.46, - "learning_rate": 5.152807391613362e-06, - "loss": 0.0959, - "step": 15870 - }, - { - "epoch": 8.46, - "learning_rate": 5.135039090262971e-06, - "loss": 0.1961, - "step": 15880 - }, - { - "epoch": 8.47, - "learning_rate": 5.11727078891258e-06, - "loss": 0.1826, - "step": 15890 - }, - { - "epoch": 8.47, - "learning_rate": 5.09950248756219e-06, - "loss": 0.1405, - "step": 15900 - }, - { - "epoch": 8.48, - "learning_rate": 5.081734186211798e-06, - "loss": 0.1544, - "step": 15910 - }, - { - "epoch": 8.48, - "learning_rate": 5.063965884861407e-06, - "loss": 0.287, - "step": 15920 - }, - { - "epoch": 8.49, - "learning_rate": 5.046197583511016e-06, - "loss": 0.0898, - "step": 15930 - }, - { - "epoch": 8.49, - "learning_rate": 5.0284292821606255e-06, - "loss": 0.0566, - "step": 15940 - }, - { - "epoch": 8.5, - "learning_rate": 5.010660980810235e-06, - "loss": 0.1512, - "step": 15950 - }, - { - "epoch": 8.51, - "learning_rate": 4.9928926794598435e-06, - "loss": 0.1629, - "step": 15960 - }, - { - "epoch": 8.51, - "learning_rate": 4.975124378109453e-06, - "loss": 0.1921, - "step": 15970 - }, - { - "epoch": 8.52, - "learning_rate": 4.957356076759062e-06, - "loss": 0.1641, - "step": 15980 - }, - { - "epoch": 8.52, - "learning_rate": 4.939587775408672e-06, - "loss": 0.1718, - "step": 15990 - }, - { - "epoch": 8.53, - "learning_rate": 4.921819474058279e-06, - "loss": 0.1875, - "step": 16000 - }, - { - "epoch": 8.53, - "learning_rate": 4.904051172707889e-06, - "loss": 0.2926, - "step": 16010 - }, - { - "epoch": 8.54, - "learning_rate": 4.886282871357498e-06, - "loss": 0.0978, - "step": 16020 - }, - { - "epoch": 8.54, - "learning_rate": 4.868514570007108e-06, - "loss": 0.2433, - "step": 16030 - }, - { - "epoch": 8.55, - "learning_rate": 4.850746268656717e-06, - "loss": 0.0427, - "step": 16040 - }, - { - "epoch": 8.55, - "learning_rate": 4.832977967306326e-06, - "loss": 0.1835, - "step": 16050 - }, - { - "epoch": 8.56, - "learning_rate": 4.815209665955935e-06, - "loss": 0.0048, - "step": 16060 - }, - { - "epoch": 8.56, - "learning_rate": 4.797441364605544e-06, - "loss": 0.0771, - "step": 16070 - }, - { - "epoch": 8.57, - "learning_rate": 4.779673063255153e-06, - "loss": 0.2721, - "step": 16080 - }, - { - "epoch": 8.57, - "learning_rate": 4.7619047619047615e-06, - "loss": 0.0087, - "step": 16090 - }, - { - "epoch": 8.58, - "learning_rate": 4.744136460554371e-06, - "loss": 0.0533, - "step": 16100 - }, - { - "epoch": 8.59, - "learning_rate": 4.72636815920398e-06, - "loss": 0.1465, - "step": 16110 - }, - { - "epoch": 8.59, - "learning_rate": 4.70859985785359e-06, - "loss": 0.0407, - "step": 16120 - }, - { - "epoch": 8.6, - "learning_rate": 4.690831556503198e-06, - "loss": 0.2535, - "step": 16130 - }, - { - "epoch": 8.6, - "learning_rate": 4.673063255152808e-06, - "loss": 0.1975, - "step": 16140 - }, { "epoch": 8.61, - "learning_rate": 4.655294953802417e-06, - "loss": 0.2429, - "step": 16150 + "learning_rate": 4.65237166991553e-06, + "loss": 0.1007, + "step": 13250 }, { "epoch": 8.61, - "learning_rate": 4.637526652452026e-06, - "loss": 0.1831, - "step": 16160 - }, - { - "epoch": 8.62, - "learning_rate": 4.619758351101634e-06, - "loss": 0.1693, - "step": 16170 + "learning_rate": 4.630712583928958e-06, + "loss": 0.0186, + "step": 13260 }, { "epoch": 8.62, - "learning_rate": 4.601990049751244e-06, - "loss": 0.2018, - "step": 16180 + "learning_rate": 4.6090534979423875e-06, + "loss": 0.1633, + "step": 13270 }, { "epoch": 8.63, - "learning_rate": 4.584221748400853e-06, - "loss": 0.1645, - "step": 16190 + "learning_rate": 4.587394411955815e-06, + "loss": 0.1736, + "step": 13280 }, { "epoch": 8.63, - "learning_rate": 4.5664534470504624e-06, - "loss": 0.1665, - "step": 16200 - }, - { - "epoch": 8.64, - "learning_rate": 4.548685145700071e-06, - "loss": 0.1784, - "step": 16210 + "learning_rate": 4.565735325969244e-06, + "loss": 0.1066, + "step": 13290 }, { "epoch": 8.64, - "learning_rate": 4.53091684434968e-06, - "loss": 0.0408, - "step": 16220 + "learning_rate": 4.544076239982673e-06, + "loss": 0.2152, + "step": 13300 }, { "epoch": 8.65, - "learning_rate": 4.51314854299929e-06, - "loss": 0.2622, - "step": 16230 + "learning_rate": 4.522417153996101e-06, + "loss": 0.1314, + "step": 13310 }, { "epoch": 8.65, - "learning_rate": 4.495380241648898e-06, - "loss": 0.1921, - "step": 16240 + "learning_rate": 4.50075806800953e-06, + "loss": 0.1044, + "step": 13320 }, { "epoch": 8.66, - "learning_rate": 4.477611940298507e-06, - "loss": 0.0048, - "step": 16250 + "learning_rate": 4.479098982022959e-06, + "loss": 0.0462, + "step": 13330 }, { "epoch": 8.67, - "learning_rate": 4.459843638948116e-06, - "loss": 0.027, - "step": 16260 + "learning_rate": 4.4574398960363874e-06, + "loss": 0.1103, + "step": 13340 }, { "epoch": 8.67, - "learning_rate": 4.442075337597726e-06, - "loss": 0.0042, - "step": 16270 + "learning_rate": 4.435780810049816e-06, + "loss": 0.1436, + "step": 13350 }, { "epoch": 8.68, - "learning_rate": 4.424307036247335e-06, - "loss": 0.1927, - "step": 16280 + "learning_rate": 4.414121724063245e-06, + "loss": 0.0242, + "step": 13360 }, { "epoch": 8.68, - "learning_rate": 4.4065387348969446e-06, - "loss": 0.1849, - "step": 16290 - }, - { - "epoch": 8.69, - "learning_rate": 4.388770433546553e-06, - "loss": 0.0609, - "step": 16300 + "learning_rate": 4.3924626380766735e-06, + "loss": 0.1488, + "step": 13370 }, { "epoch": 8.69, - "learning_rate": 4.3710021321961625e-06, - "loss": 0.1703, - "step": 16310 + "learning_rate": 4.370803552090101e-06, + "loss": 0.2303, + "step": 13380 }, { "epoch": 8.7, - "learning_rate": 4.353233830845771e-06, - "loss": 0.0732, - "step": 16320 + "learning_rate": 4.349144466103531e-06, + "loss": 0.1304, + "step": 13390 }, { "epoch": 8.7, - "learning_rate": 4.3354655294953805e-06, - "loss": 0.1348, - "step": 16330 - }, - { - "epoch": 8.71, - "learning_rate": 4.317697228144989e-06, - "loss": 0.242, - "step": 16340 + "learning_rate": 4.327485380116959e-06, + "loss": 0.0573, + "step": 13400 }, { "epoch": 8.71, - "learning_rate": 4.2999289267945984e-06, - "loss": 0.1191, - "step": 16350 + "learning_rate": 4.305826294130388e-06, + "loss": 0.0173, + "step": 13410 }, { "epoch": 8.72, - "learning_rate": 4.282160625444208e-06, - "loss": 0.1095, - "step": 16360 + "learning_rate": 4.284167208143816e-06, + "loss": 0.0028, + "step": 13420 }, { "epoch": 8.72, - "learning_rate": 4.264392324093817e-06, - "loss": 0.2414, - "step": 16370 - }, - { - "epoch": 8.73, - "learning_rate": 4.246624022743426e-06, - "loss": 0.216, - "step": 16380 + "learning_rate": 4.262508122157246e-06, + "loss": 0.0278, + "step": 13430 }, { "epoch": 8.73, - "learning_rate": 4.228855721393035e-06, - "loss": 0.232, - "step": 16390 + "learning_rate": 4.2408490361706735e-06, + "loss": 0.0493, + "step": 13440 }, { "epoch": 8.74, - "learning_rate": 4.211087420042644e-06, - "loss": 0.18, - "step": 16400 + "learning_rate": 4.219189950184103e-06, + "loss": 0.0705, + "step": 13450 }, { - "epoch": 8.75, - "learning_rate": 4.193319118692253e-06, - "loss": 0.1398, - "step": 16410 + "epoch": 8.74, + "learning_rate": 4.197530864197531e-06, + "loss": 0.0259, + "step": 13460 }, { "epoch": 8.75, - "learning_rate": 4.175550817341862e-06, - "loss": 0.1252, - "step": 16420 + "learning_rate": 4.1758717782109595e-06, + "loss": 0.1553, + "step": 13470 }, { "epoch": 8.76, - "learning_rate": 4.157782515991471e-06, - "loss": 0.0874, - "step": 16430 + "learning_rate": 4.154212692224388e-06, + "loss": 0.107, + "step": 13480 }, { "epoch": 8.76, - "learning_rate": 4.1400142146410806e-06, - "loss": 0.1681, - "step": 16440 - }, - { - "epoch": 8.77, - "learning_rate": 4.12224591329069e-06, - "loss": 0.09, - "step": 16450 + "learning_rate": 4.132553606237817e-06, + "loss": 0.0314, + "step": 13490 }, { "epoch": 8.77, - "learning_rate": 4.1044776119402985e-06, - "loss": 0.1471, - "step": 16460 + "learning_rate": 4.1108945202512456e-06, + "loss": 0.1201, + "step": 13500 }, { "epoch": 8.78, - "learning_rate": 4.086709310589908e-06, - "loss": 0.0694, - "step": 16470 + "learning_rate": 4.089235434264674e-06, + "loss": 0.0249, + "step": 13510 }, { "epoch": 8.78, - "learning_rate": 4.0689410092395165e-06, - "loss": 0.0104, - "step": 16480 - }, - { - "epoch": 8.79, - "learning_rate": 4.051172707889126e-06, - "loss": 0.0828, - "step": 16490 + "learning_rate": 4.067576348278103e-06, + "loss": 0.0269, + "step": 13520 }, { "epoch": 8.79, - "learning_rate": 4.0334044065387344e-06, - "loss": 0.1524, - "step": 16500 + "learning_rate": 4.045917262291532e-06, + "loss": 0.1419, + "step": 13530 }, { "epoch": 8.8, - "learning_rate": 4.015636105188344e-06, - "loss": 0.1535, - "step": 16510 + "learning_rate": 4.0242581763049595e-06, + "loss": 0.2158, + "step": 13540 }, { "epoch": 8.8, - "learning_rate": 3.997867803837953e-06, - "loss": 0.1934, - "step": 16520 + "learning_rate": 4.002599090318389e-06, + "loss": 0.1973, + "step": 13550 }, { "epoch": 8.81, - "learning_rate": 3.980099502487563e-06, - "loss": 0.2095, - "step": 16530 + "learning_rate": 3.980940004331817e-06, + "loss": 0.2355, + "step": 13560 }, { "epoch": 8.81, - "learning_rate": 3.962331201137172e-06, - "loss": 0.0038, - "step": 16540 - }, - { - "epoch": 8.82, - "learning_rate": 3.944562899786781e-06, - "loss": 0.184, - "step": 16550 + "learning_rate": 3.959280918345246e-06, + "loss": 0.0418, + "step": 13570 }, { "epoch": 8.82, - "learning_rate": 3.926794598436389e-06, - "loss": 0.1415, - "step": 16560 + "learning_rate": 3.937621832358674e-06, + "loss": 0.1702, + "step": 13580 }, { "epoch": 8.83, - "learning_rate": 3.909026297085999e-06, - "loss": 0.1367, - "step": 16570 + "learning_rate": 3.915962746372104e-06, + "loss": 0.1813, + "step": 13590 }, { - "epoch": 8.84, - "learning_rate": 3.891257995735608e-06, - "loss": 0.1508, - "step": 16580 + "epoch": 8.83, + "learning_rate": 3.8943036603855316e-06, + "loss": 0.089, + "step": 13600 }, { "epoch": 8.84, - "learning_rate": 3.8734896943852165e-06, - "loss": 0.1848, - "step": 16590 + "learning_rate": 3.872644574398961e-06, + "loss": 0.0309, + "step": 13610 }, { "epoch": 8.85, - "learning_rate": 3.855721393034826e-06, - "loss": 0.1393, - "step": 16600 + "learning_rate": 3.850985488412389e-06, + "loss": 0.0278, + "step": 13620 }, { "epoch": 8.85, - "learning_rate": 3.837953091684435e-06, - "loss": 0.2528, - "step": 16610 - }, - { - "epoch": 8.86, - "learning_rate": 3.820184790334045e-06, - "loss": 0.1602, - "step": 16620 + "learning_rate": 3.829326402425818e-06, + "loss": 0.0381, + "step": 13630 }, { "epoch": 8.86, - "learning_rate": 3.802416488983653e-06, - "loss": 0.0056, - "step": 16630 + "learning_rate": 3.8076673164392463e-06, + "loss": 0.014, + "step": 13640 }, { "epoch": 8.87, - "learning_rate": 3.7846481876332623e-06, - "loss": 0.1015, - "step": 16640 + "learning_rate": 3.7860082304526746e-06, + "loss": 0.109, + "step": 13650 }, { "epoch": 8.87, - "learning_rate": 3.7668798862828717e-06, - "loss": 0.0721, - "step": 16650 - }, - { - "epoch": 8.88, - "learning_rate": 3.7491115849324803e-06, - "loss": 0.0128, - "step": 16660 + "learning_rate": 3.7643491444661037e-06, + "loss": 0.3331, + "step": 13660 }, { "epoch": 8.88, - "learning_rate": 3.7313432835820897e-06, - "loss": 0.1249, - "step": 16670 + "learning_rate": 3.742690058479532e-06, + "loss": 0.0013, + "step": 13670 }, { "epoch": 8.89, - "learning_rate": 3.7135749822316987e-06, - "loss": 0.0834, - "step": 16680 + "learning_rate": 3.7210309724929606e-06, + "loss": 0.016, + "step": 13680 }, { "epoch": 8.89, - "learning_rate": 3.695806680881308e-06, - "loss": 0.1556, - "step": 16690 + "learning_rate": 3.6993718865063893e-06, + "loss": 0.1149, + "step": 13690 }, { "epoch": 8.9, - "learning_rate": 3.6780383795309166e-06, - "loss": 0.0972, - "step": 16700 + "learning_rate": 3.677712800519818e-06, + "loss": 0.3126, + "step": 13700 }, { - "epoch": 8.9, - "learning_rate": 3.660270078180526e-06, - "loss": 0.1865, - "step": 16710 + "epoch": 8.91, + "learning_rate": 3.6560537145332467e-06, + "loss": 0.2456, + "step": 13710 }, { "epoch": 8.91, - "learning_rate": 3.642501776830135e-06, - "loss": 0.1862, - "step": 16720 + "learning_rate": 3.6343946285466754e-06, + "loss": 0.0794, + "step": 13720 }, { "epoch": 8.92, - "learning_rate": 3.6247334754797444e-06, - "loss": 0.3996, - "step": 16730 + "learning_rate": 3.612735542560104e-06, + "loss": 0.1407, + "step": 13730 }, { "epoch": 8.92, - "learning_rate": 3.606965174129353e-06, - "loss": 0.1532, - "step": 16740 - }, - { - "epoch": 8.93, - "learning_rate": 3.5891968727789624e-06, - "loss": 0.2456, - "step": 16750 + "learning_rate": 3.5910764565735327e-06, + "loss": 0.1953, + "step": 13740 }, { "epoch": 8.93, - "learning_rate": 3.5714285714285714e-06, - "loss": 0.0266, - "step": 16760 + "learning_rate": 3.5694173705869614e-06, + "loss": 0.2692, + "step": 13750 }, { "epoch": 8.94, - "learning_rate": 3.5536602700781808e-06, - "loss": 0.0648, - "step": 16770 + "learning_rate": 3.5477582846003897e-06, + "loss": 0.235, + "step": 13760 }, { "epoch": 8.94, - "learning_rate": 3.5358919687277897e-06, - "loss": 0.0921, - "step": 16780 - }, - { - "epoch": 8.95, - "learning_rate": 3.5181236673773987e-06, - "loss": 0.0659, - "step": 16790 + "learning_rate": 3.5260991986138184e-06, + "loss": 0.1149, + "step": 13770 }, { "epoch": 8.95, - "learning_rate": 3.500355366027008e-06, - "loss": 0.1455, - "step": 16800 + "learning_rate": 3.504440112627247e-06, + "loss": 0.1316, + "step": 13780 }, { "epoch": 8.96, - "learning_rate": 3.482587064676617e-06, - "loss": 0.0803, - "step": 16810 + "learning_rate": 3.4827810266406757e-06, + "loss": 0.0752, + "step": 13790 }, { "epoch": 8.96, - "learning_rate": 3.464818763326226e-06, - "loss": 0.0835, - "step": 16820 - }, - { - "epoch": 8.97, - "learning_rate": 3.447050461975835e-06, - "loss": 0.1825, - "step": 16830 + "learning_rate": 3.4611219406541044e-06, + "loss": 0.0281, + "step": 13800 }, { "epoch": 8.97, - "learning_rate": 3.4292821606254445e-06, - "loss": 0.0729, - "step": 16840 + "learning_rate": 3.439462854667533e-06, + "loss": 0.161, + "step": 13810 }, { "epoch": 8.98, - "learning_rate": 3.4115138592750535e-06, - "loss": 0.1473, - "step": 16850 + "learning_rate": 3.417803768680962e-06, + "loss": 0.0827, + "step": 13820 }, { "epoch": 8.98, - "learning_rate": 3.3937455579246624e-06, - "loss": 0.1838, - "step": 16860 + "learning_rate": 3.3961446826943905e-06, + "loss": 0.0172, + "step": 13830 }, { "epoch": 8.99, - "learning_rate": 3.3759772565742714e-06, - "loss": 0.1872, - "step": 16870 + "learning_rate": 3.374485596707819e-06, + "loss": 0.1149, + "step": 13840 }, { "epoch": 9.0, - "learning_rate": 3.358208955223881e-06, - "loss": 0.1122, - "step": 16880 + "learning_rate": 3.3528265107212474e-06, + "loss": 0.0317, + "step": 13850 }, { "epoch": 9.0, - "eval_accuracy": 0.9690449226123066, - "eval_loss": 0.16566720604896545, - "eval_runtime": 12.4189, - "eval_samples_per_second": 213.303, - "eval_steps_per_second": 53.386, - "step": 16888 + "eval_accuracy": 0.984820607175713, + "eval_loss": 0.0851309597492218, + "eval_runtime": 12.8784, + "eval_samples_per_second": 168.809, + "eval_steps_per_second": 42.241, + "step": 13855 }, { "epoch": 9.0, - "learning_rate": 3.34044065387349e-06, - "loss": 0.0261, - "step": 16890 - }, - { - "epoch": 9.01, - "learning_rate": 3.322672352523099e-06, - "loss": 0.0868, - "step": 16900 + "learning_rate": 3.331167424734676e-06, + "loss": 0.2191, + "step": 13860 }, { "epoch": 9.01, - "learning_rate": 3.3049040511727078e-06, - "loss": 0.1513, - "step": 16910 + "learning_rate": 3.309508338748105e-06, + "loss": 0.1574, + "step": 13870 }, { "epoch": 9.02, - "learning_rate": 3.287135749822317e-06, - "loss": 0.1557, - "step": 16920 + "learning_rate": 3.2878492527615335e-06, + "loss": 0.0723, + "step": 13880 }, { "epoch": 9.02, - "learning_rate": 3.269367448471926e-06, - "loss": 0.0315, - "step": 16930 - }, - { - "epoch": 9.03, - "learning_rate": 3.251599147121535e-06, - "loss": 0.1541, - "step": 16940 + "learning_rate": 3.266190166774962e-06, + "loss": 0.0881, + "step": 13890 }, { "epoch": 9.03, - "learning_rate": 3.233830845771144e-06, - "loss": 0.1336, - "step": 16950 + "learning_rate": 3.244531080788391e-06, + "loss": 0.1085, + "step": 13900 }, { "epoch": 9.04, - "learning_rate": 3.2160625444207535e-06, - "loss": 0.1488, - "step": 16960 + "learning_rate": 3.2228719948018195e-06, + "loss": 0.097, + "step": 13910 }, { "epoch": 9.04, - "learning_rate": 3.1982942430703625e-06, - "loss": 0.1563, - "step": 16970 + "learning_rate": 3.2012129088152482e-06, + "loss": 0.0165, + "step": 13920 }, { "epoch": 9.05, - "learning_rate": 3.1805259417199715e-06, - "loss": 0.0514, - "step": 16980 + "learning_rate": 3.179553822828677e-06, + "loss": 0.1146, + "step": 13930 }, { "epoch": 9.05, - "learning_rate": 3.1627576403695805e-06, - "loss": 0.1087, - "step": 16990 - }, - { - "epoch": 9.06, - "learning_rate": 3.14498933901919e-06, - "loss": 0.1073, - "step": 17000 + "learning_rate": 3.157894736842105e-06, + "loss": 0.0318, + "step": 13940 }, { "epoch": 9.06, - "learning_rate": 3.127221037668799e-06, - "loss": 0.1164, - "step": 17010 + "learning_rate": 3.136235650855534e-06, + "loss": 0.0328, + "step": 13950 }, { "epoch": 9.07, - "learning_rate": 3.109452736318408e-06, - "loss": 0.2671, - "step": 17020 + "learning_rate": 3.1145765648689625e-06, + "loss": 0.0659, + "step": 13960 }, { - "epoch": 9.08, - "learning_rate": 3.0916844349680173e-06, - "loss": 0.2317, - "step": 17030 + "epoch": 9.07, + "learning_rate": 3.0929174788823912e-06, + "loss": 0.0173, + "step": 13970 }, { "epoch": 9.08, - "learning_rate": 3.0739161336176262e-06, - "loss": 0.0039, - "step": 17040 + "learning_rate": 3.07125839289582e-06, + "loss": 0.0772, + "step": 13980 }, { "epoch": 9.09, - "learning_rate": 3.0561478322672356e-06, - "loss": 0.0917, - "step": 17050 + "learning_rate": 3.0495993069092486e-06, + "loss": 0.002, + "step": 13990 }, { "epoch": 9.09, - "learning_rate": 3.038379530916844e-06, - "loss": 0.0779, - "step": 17060 - }, - { - "epoch": 9.1, - "learning_rate": 3.0206112295664536e-06, - "loss": 0.1645, - "step": 17070 + "learning_rate": 3.0279402209226773e-06, + "loss": 0.326, + "step": 14000 }, { "epoch": 9.1, - "learning_rate": 3.0028429282160626e-06, - "loss": 0.1872, - "step": 17080 + "learning_rate": 3.006281134936106e-06, + "loss": 0.0963, + "step": 14010 }, { "epoch": 9.11, - "learning_rate": 2.985074626865672e-06, - "loss": 0.1813, - "step": 17090 + "learning_rate": 2.9846220489495346e-06, + "loss": 0.0407, + "step": 14020 }, { "epoch": 9.11, - "learning_rate": 2.9673063255152806e-06, - "loss": 0.0797, - "step": 17100 - }, - { - "epoch": 9.12, - "learning_rate": 2.94953802416489e-06, - "loss": 0.0525, - "step": 17110 + "learning_rate": 2.962962962962963e-06, + "loss": 0.0449, + "step": 14030 }, { "epoch": 9.12, - "learning_rate": 2.931769722814499e-06, - "loss": 0.0677, - "step": 17120 + "learning_rate": 2.9413038769763916e-06, + "loss": 0.196, + "step": 14040 }, { "epoch": 9.13, - "learning_rate": 2.9140014214641083e-06, - "loss": 0.1069, - "step": 17130 + "learning_rate": 2.9196447909898203e-06, + "loss": 0.0058, + "step": 14050 }, { "epoch": 9.13, - "learning_rate": 2.896233120113717e-06, - "loss": 0.2235, - "step": 17140 - }, - { - "epoch": 9.14, - "learning_rate": 2.8784648187633263e-06, - "loss": 0.2728, - "step": 17150 + "learning_rate": 2.897985705003249e-06, + "loss": 0.0504, + "step": 14060 }, { "epoch": 9.14, - "learning_rate": 2.8606965174129353e-06, - "loss": 0.1087, - "step": 17160 + "learning_rate": 2.8763266190166776e-06, + "loss": 0.2405, + "step": 14070 }, { "epoch": 9.15, - "learning_rate": 2.8429282160625447e-06, - "loss": 0.1018, - "step": 17170 + "learning_rate": 2.8546675330301063e-06, + "loss": 0.2004, + "step": 14080 }, { - "epoch": 9.16, - "learning_rate": 2.8251599147121533e-06, - "loss": 0.0089, - "step": 17180 + "epoch": 9.15, + "learning_rate": 2.833008447043535e-06, + "loss": 0.1501, + "step": 14090 }, { "epoch": 9.16, - "learning_rate": 2.8073916133617627e-06, - "loss": 0.1461, - "step": 17190 + "learning_rate": 2.8113493610569637e-06, + "loss": 0.0012, + "step": 14100 }, { "epoch": 9.17, - "learning_rate": 2.7896233120113716e-06, - "loss": 0.2538, - "step": 17200 + "learning_rate": 2.789690275070392e-06, + "loss": 0.0938, + "step": 14110 }, { "epoch": 9.17, - "learning_rate": 2.771855010660981e-06, - "loss": 0.0054, - "step": 17210 + "learning_rate": 2.7680311890838206e-06, + "loss": 0.1683, + "step": 14120 }, { "epoch": 9.18, - "learning_rate": 2.7540867093105896e-06, - "loss": 0.1755, - "step": 17220 + "learning_rate": 2.7463721030972493e-06, + "loss": 0.0288, + "step": 14130 }, { "epoch": 9.18, - "learning_rate": 2.736318407960199e-06, - "loss": 0.1104, - "step": 17230 - }, - { - "epoch": 9.19, - "learning_rate": 2.718550106609808e-06, - "loss": 0.3796, - "step": 17240 + "learning_rate": 2.724713017110678e-06, + "loss": 0.0936, + "step": 14140 }, { "epoch": 9.19, - "learning_rate": 2.7007818052594174e-06, - "loss": 0.3211, - "step": 17250 + "learning_rate": 2.7030539311241067e-06, + "loss": 0.0241, + "step": 14150 }, { "epoch": 9.2, - "learning_rate": 2.683013503909026e-06, - "loss": 0.3341, - "step": 17260 + "learning_rate": 2.6813948451375354e-06, + "loss": 0.1308, + "step": 14160 }, { "epoch": 9.2, - "learning_rate": 2.6652452025586354e-06, - "loss": 0.0128, - "step": 17270 - }, - { - "epoch": 9.21, - "learning_rate": 2.6474769012082448e-06, - "loss": 0.2494, - "step": 17280 + "learning_rate": 2.659735759150964e-06, + "loss": 0.0011, + "step": 14170 }, { "epoch": 9.21, - "learning_rate": 2.6297085998578537e-06, - "loss": 0.1577, - "step": 17290 + "learning_rate": 2.6380766731643928e-06, + "loss": 0.0892, + "step": 14180 }, { "epoch": 9.22, - "learning_rate": 2.6119402985074627e-06, - "loss": 0.1099, - "step": 17300 + "learning_rate": 2.6164175871778214e-06, + "loss": 0.0683, + "step": 14190 }, { "epoch": 9.22, - "learning_rate": 2.5941719971570717e-06, - "loss": 0.123, - "step": 17310 + "learning_rate": 2.5947585011912497e-06, + "loss": 0.0821, + "step": 14200 }, { "epoch": 9.23, - "learning_rate": 2.576403695806681e-06, - "loss": 0.1552, - "step": 17320 + "learning_rate": 2.5730994152046784e-06, + "loss": 0.1705, + "step": 14210 }, { "epoch": 9.24, - "learning_rate": 2.55863539445629e-06, - "loss": 0.2153, - "step": 17330 + "learning_rate": 2.551440329218107e-06, + "loss": 0.2017, + "step": 14220 }, { "epoch": 9.24, - "learning_rate": 2.540867093105899e-06, - "loss": 0.1935, - "step": 17340 - }, - { - "epoch": 9.25, - "learning_rate": 2.523098791755508e-06, - "loss": 0.0169, - "step": 17350 + "learning_rate": 2.5297812432315358e-06, + "loss": 0.2258, + "step": 14230 }, { "epoch": 9.25, - "learning_rate": 2.5053304904051175e-06, - "loss": 0.1679, - "step": 17360 + "learning_rate": 2.5081221572449644e-06, + "loss": 0.0655, + "step": 14240 }, { "epoch": 9.26, - "learning_rate": 2.4875621890547264e-06, - "loss": 0.1197, - "step": 17370 + "learning_rate": 2.486463071258393e-06, + "loss": 0.0019, + "step": 14250 }, { "epoch": 9.26, - "learning_rate": 2.469793887704336e-06, - "loss": 0.0579, - "step": 17380 - }, - { - "epoch": 9.27, - "learning_rate": 2.4520255863539444e-06, - "loss": 0.1345, - "step": 17390 + "learning_rate": 2.464803985271822e-06, + "loss": 0.1095, + "step": 14260 }, { "epoch": 9.27, - "learning_rate": 2.434257285003554e-06, - "loss": 0.1089, - "step": 17400 + "learning_rate": 2.4431448992852505e-06, + "loss": 0.0099, + "step": 14270 }, { "epoch": 9.28, - "learning_rate": 2.416488983653163e-06, - "loss": 0.2661, - "step": 17410 + "learning_rate": 2.421485813298679e-06, + "loss": 0.1379, + "step": 14280 }, { "epoch": 9.28, - "learning_rate": 2.398720682302772e-06, - "loss": 0.1682, - "step": 17420 - }, - { - "epoch": 9.29, - "learning_rate": 2.3809523809523808e-06, - "loss": 0.0431, - "step": 17430 + "learning_rate": 2.3998267273121074e-06, + "loss": 0.0783, + "step": 14290 }, { "epoch": 9.29, - "learning_rate": 2.36318407960199e-06, - "loss": 0.0867, - "step": 17440 + "learning_rate": 2.378167641325536e-06, + "loss": 0.0081, + "step": 14300 }, { "epoch": 9.3, - "learning_rate": 2.345415778251599e-06, - "loss": 0.077, - "step": 17450 + "learning_rate": 2.356508555338965e-06, + "loss": 0.0195, + "step": 14310 }, { "epoch": 9.3, - "learning_rate": 2.3276474769012086e-06, - "loss": 0.1747, - "step": 17460 + "learning_rate": 2.3348494693523935e-06, + "loss": 0.0019, + "step": 14320 }, { "epoch": 9.31, - "learning_rate": 2.309879175550817e-06, - "loss": 0.2127, - "step": 17470 + "learning_rate": 2.313190383365822e-06, + "loss": 0.0339, + "step": 14330 }, { - "epoch": 9.32, - "learning_rate": 2.2921108742004265e-06, - "loss": 0.0764, - "step": 17480 + "epoch": 9.31, + "learning_rate": 2.291531297379251e-06, + "loss": 0.0434, + "step": 14340 }, { "epoch": 9.32, - "learning_rate": 2.2743425728500355e-06, - "loss": 0.0987, - "step": 17490 + "learning_rate": 2.2698722113926796e-06, + "loss": 0.1738, + "step": 14350 }, { "epoch": 9.33, - "learning_rate": 2.256574271499645e-06, - "loss": 0.1409, - "step": 17500 + "learning_rate": 2.2482131254061082e-06, + "loss": 0.1285, + "step": 14360 }, { "epoch": 9.33, - "learning_rate": 2.2388059701492535e-06, - "loss": 0.1721, - "step": 17510 - }, - { - "epoch": 9.34, - "learning_rate": 2.221037668798863e-06, - "loss": 0.1667, - "step": 17520 + "learning_rate": 2.226554039419537e-06, + "loss": 0.0907, + "step": 14370 }, { "epoch": 9.34, - "learning_rate": 2.2032693674484723e-06, - "loss": 0.0724, - "step": 17530 + "learning_rate": 2.204894953432965e-06, + "loss": 0.0349, + "step": 14380 }, { "epoch": 9.35, - "learning_rate": 2.1855010660980813e-06, - "loss": 0.1922, - "step": 17540 + "learning_rate": 2.183235867446394e-06, + "loss": 0.0509, + "step": 14390 }, { "epoch": 9.35, - "learning_rate": 2.1677327647476902e-06, - "loss": 0.2376, - "step": 17550 - }, - { - "epoch": 9.36, - "learning_rate": 2.1499644633972992e-06, - "loss": 0.1517, - "step": 17560 + "learning_rate": 2.1615767814598226e-06, + "loss": 0.0015, + "step": 14400 }, { "epoch": 9.36, - "learning_rate": 2.1321961620469086e-06, - "loss": 0.1196, - "step": 17570 + "learning_rate": 2.1399176954732512e-06, + "loss": 0.0035, + "step": 14410 }, { "epoch": 9.37, - "learning_rate": 2.1144278606965176e-06, - "loss": 0.227, - "step": 17580 + "learning_rate": 2.11825860948668e-06, + "loss": 0.1029, + "step": 14420 }, { "epoch": 9.37, - "learning_rate": 2.0966595593461266e-06, - "loss": 0.073, - "step": 17590 - }, - { - "epoch": 9.38, - "learning_rate": 2.0788912579957356e-06, - "loss": 0.3464, - "step": 17600 + "learning_rate": 2.0965995235001086e-06, + "loss": 0.1722, + "step": 14430 }, { "epoch": 9.38, - "learning_rate": 2.061122956645345e-06, - "loss": 0.0305, - "step": 17610 + "learning_rate": 2.0749404375135373e-06, + "loss": 0.1884, + "step": 14440 }, { "epoch": 9.39, - "learning_rate": 2.043354655294954e-06, - "loss": 0.1058, - "step": 17620 + "learning_rate": 2.053281351526966e-06, + "loss": 0.153, + "step": 14450 }, { - "epoch": 9.4, - "learning_rate": 2.025586353944563e-06, - "loss": 0.1741, - "step": 17630 + "epoch": 9.39, + "learning_rate": 2.0316222655403942e-06, + "loss": 0.0016, + "step": 14460 }, { "epoch": 9.4, - "learning_rate": 2.007818052594172e-06, - "loss": 0.0935, - "step": 17640 + "learning_rate": 2.0099631795538225e-06, + "loss": 0.1055, + "step": 14470 }, { "epoch": 9.41, - "learning_rate": 1.9900497512437813e-06, - "loss": 0.2519, - "step": 17650 + "learning_rate": 1.988304093567251e-06, + "loss": 0.0803, + "step": 14480 }, { "epoch": 9.41, - "learning_rate": 1.9722814498933903e-06, - "loss": 0.2169, - "step": 17660 - }, - { - "epoch": 9.42, - "learning_rate": 1.9545131485429993e-06, - "loss": 0.1693, - "step": 17670 + "learning_rate": 1.96664500758068e-06, + "loss": 0.0262, + "step": 14490 }, { "epoch": 9.42, - "learning_rate": 1.9367448471926083e-06, - "loss": 0.0618, - "step": 17680 + "learning_rate": 1.9449859215941086e-06, + "loss": 0.0813, + "step": 14500 }, { "epoch": 9.43, - "learning_rate": 1.9189765458422177e-06, - "loss": 0.2301, - "step": 17690 + "learning_rate": 1.9233268356075373e-06, + "loss": 0.1877, + "step": 14510 }, { "epoch": 9.43, - "learning_rate": 1.9012082444918264e-06, - "loss": 0.2456, - "step": 17700 + "learning_rate": 1.9016677496209661e-06, + "loss": 0.0272, + "step": 14520 }, { "epoch": 9.44, - "learning_rate": 1.8834399431414359e-06, - "loss": 0.0162, - "step": 17710 + "learning_rate": 1.8800086636343948e-06, + "loss": 0.1979, + "step": 14530 }, { "epoch": 9.44, - "learning_rate": 1.8656716417910448e-06, - "loss": 0.1827, - "step": 17720 - }, - { - "epoch": 9.45, - "learning_rate": 1.847903340440654e-06, - "loss": 0.0705, - "step": 17730 + "learning_rate": 1.8583495776478233e-06, + "loss": 0.1209, + "step": 14540 }, { "epoch": 9.45, - "learning_rate": 1.830135039090263e-06, - "loss": 0.1498, - "step": 17740 + "learning_rate": 1.836690491661252e-06, + "loss": 0.0729, + "step": 14550 }, { "epoch": 9.46, - "learning_rate": 1.8123667377398722e-06, - "loss": 0.0657, - "step": 17750 + "learning_rate": 1.8150314056746807e-06, + "loss": 0.1729, + "step": 14560 }, { "epoch": 9.46, - "learning_rate": 1.7945984363894812e-06, - "loss": 0.1942, - "step": 17760 + "learning_rate": 1.7933723196881092e-06, + "loss": 0.1455, + "step": 14570 }, { "epoch": 9.47, - "learning_rate": 1.7768301350390904e-06, - "loss": 0.1175, - "step": 17770 + "learning_rate": 1.7717132337015378e-06, + "loss": 0.0725, + "step": 14580 }, { "epoch": 9.48, - "learning_rate": 1.7590618336886994e-06, - "loss": 0.1058, - "step": 17780 + "learning_rate": 1.7500541477149665e-06, + "loss": 0.0148, + "step": 14590 }, { "epoch": 9.48, - "learning_rate": 1.7412935323383086e-06, - "loss": 0.0422, - "step": 17790 - }, - { - "epoch": 9.49, - "learning_rate": 1.7235252309879175e-06, - "loss": 0.0756, - "step": 17800 + "learning_rate": 1.7283950617283952e-06, + "loss": 0.0011, + "step": 14600 }, { "epoch": 9.49, - "learning_rate": 1.7057569296375267e-06, - "loss": 0.0969, - "step": 17810 + "learning_rate": 1.7067359757418239e-06, + "loss": 0.002, + "step": 14610 }, { "epoch": 9.5, - "learning_rate": 1.6879886282871357e-06, - "loss": 0.1972, - "step": 17820 + "learning_rate": 1.6850768897552524e-06, + "loss": 0.2557, + "step": 14620 }, { "epoch": 9.5, - "learning_rate": 1.670220326936745e-06, - "loss": 0.1797, - "step": 17830 - }, - { - "epoch": 9.51, - "learning_rate": 1.6524520255863539e-06, - "loss": 0.0116, - "step": 17840 + "learning_rate": 1.663417803768681e-06, + "loss": 0.2756, + "step": 14630 }, { "epoch": 9.51, - "learning_rate": 1.634683724235963e-06, - "loss": 0.151, - "step": 17850 + "learning_rate": 1.6417587177821097e-06, + "loss": 0.0519, + "step": 14640 }, { "epoch": 9.52, - "learning_rate": 1.616915422885572e-06, - "loss": 0.1435, - "step": 17860 + "learning_rate": 1.6200996317955384e-06, + "loss": 0.0122, + "step": 14650 }, { "epoch": 9.52, - "learning_rate": 1.5991471215351813e-06, - "loss": 0.0928, - "step": 17870 - }, - { - "epoch": 9.53, - "learning_rate": 1.5813788201847902e-06, - "loss": 0.0176, - "step": 17880 + "learning_rate": 1.5984405458089669e-06, + "loss": 0.0782, + "step": 14660 }, { "epoch": 9.53, - "learning_rate": 1.5636105188343994e-06, - "loss": 0.2134, - "step": 17890 + "learning_rate": 1.5767814598223956e-06, + "loss": 0.181, + "step": 14670 }, { "epoch": 9.54, - "learning_rate": 1.5458422174840086e-06, - "loss": 0.0071, - "step": 17900 + "learning_rate": 1.5551223738358243e-06, + "loss": 0.0997, + "step": 14680 }, { "epoch": 9.54, - "learning_rate": 1.5280739161336178e-06, - "loss": 0.264, - "step": 17910 + "learning_rate": 1.533463287849253e-06, + "loss": 0.1639, + "step": 14690 }, { "epoch": 9.55, - "learning_rate": 1.5103056147832268e-06, - "loss": 0.0787, - "step": 17920 + "learning_rate": 1.5118042018626816e-06, + "loss": 0.0852, + "step": 14700 }, { "epoch": 9.56, - "learning_rate": 1.492537313432836e-06, - "loss": 0.0499, - "step": 17930 + "learning_rate": 1.4901451158761101e-06, + "loss": 0.001, + "step": 14710 }, { "epoch": 9.56, - "learning_rate": 1.474769012082445e-06, - "loss": 0.0121, - "step": 17940 + "learning_rate": 1.4684860298895388e-06, + "loss": 0.2217, + "step": 14720 }, { "epoch": 9.57, - "learning_rate": 1.4570007107320542e-06, - "loss": 0.1383, - "step": 17950 + "learning_rate": 1.4468269439029673e-06, + "loss": 0.1359, + "step": 14730 }, { "epoch": 9.57, - "learning_rate": 1.4392324093816632e-06, - "loss": 0.1471, - "step": 17960 - }, - { - "epoch": 9.58, - "learning_rate": 1.4214641080312723e-06, - "loss": 0.0029, - "step": 17970 + "learning_rate": 1.425167857916396e-06, + "loss": 0.1462, + "step": 14740 }, { "epoch": 9.58, - "learning_rate": 1.4036958066808813e-06, - "loss": 0.1737, - "step": 17980 + "learning_rate": 1.4035087719298244e-06, + "loss": 0.002, + "step": 14750 }, { "epoch": 9.59, - "learning_rate": 1.3859275053304905e-06, - "loss": 0.2449, - "step": 17990 + "learning_rate": 1.3818496859432531e-06, + "loss": 0.0147, + "step": 14760 }, { "epoch": 9.59, - "learning_rate": 1.3681592039800995e-06, - "loss": 0.0151, - "step": 18000 - }, - { - "epoch": 9.6, - "learning_rate": 1.3503909026297087e-06, - "loss": 0.0731, - "step": 18010 + "learning_rate": 1.3601905999566818e-06, + "loss": 0.0607, + "step": 14770 }, { "epoch": 9.6, - "learning_rate": 1.3326226012793177e-06, - "loss": 0.036, - "step": 18020 + "learning_rate": 1.3385315139701105e-06, + "loss": 0.0903, + "step": 14780 }, { "epoch": 9.61, - "learning_rate": 1.3148542999289269e-06, - "loss": 0.083, - "step": 18030 + "learning_rate": 1.316872427983539e-06, + "loss": 0.1384, + "step": 14790 }, { "epoch": 9.61, - "learning_rate": 1.2970859985785359e-06, - "loss": 0.1487, - "step": 18040 - }, - { - "epoch": 9.62, - "learning_rate": 1.279317697228145e-06, - "loss": 0.0465, - "step": 18050 + "learning_rate": 1.2952133419969676e-06, + "loss": 0.1349, + "step": 14800 }, { "epoch": 9.62, - "learning_rate": 1.261549395877754e-06, - "loss": 0.0879, - "step": 18060 + "learning_rate": 1.2735542560103963e-06, + "loss": 0.145, + "step": 14810 }, { "epoch": 9.63, - "learning_rate": 1.2437810945273632e-06, - "loss": 0.0055, - "step": 18070 + "learning_rate": 1.251895170023825e-06, + "loss": 0.0957, + "step": 14820 }, { "epoch": 9.63, - "learning_rate": 1.2260127931769722e-06, - "loss": 0.1127, - "step": 18080 + "learning_rate": 1.2302360840372537e-06, + "loss": 0.0971, + "step": 14830 }, { "epoch": 9.64, - "learning_rate": 1.2082444918265814e-06, - "loss": 0.1623, - "step": 18090 + "learning_rate": 1.2085769980506822e-06, + "loss": 0.0578, + "step": 14840 }, { "epoch": 9.65, - "learning_rate": 1.1904761904761904e-06, - "loss": 0.1791, - "step": 18100 + "learning_rate": 1.1869179120641109e-06, + "loss": 0.0793, + "step": 14850 }, { "epoch": 9.65, - "learning_rate": 1.1727078891257996e-06, - "loss": 0.0452, - "step": 18110 - }, - { - "epoch": 9.66, - "learning_rate": 1.1549395877754086e-06, - "loss": 0.1865, - "step": 18120 + "learning_rate": 1.1652588260775395e-06, + "loss": 0.0914, + "step": 14860 }, { "epoch": 9.66, - "learning_rate": 1.1371712864250178e-06, - "loss": 0.0478, - "step": 18130 + "learning_rate": 1.1435997400909682e-06, + "loss": 0.0207, + "step": 14870 }, { "epoch": 9.67, - "learning_rate": 1.1194029850746267e-06, - "loss": 0.0148, - "step": 18140 + "learning_rate": 1.1219406541043967e-06, + "loss": 0.0121, + "step": 14880 }, { "epoch": 9.67, - "learning_rate": 1.1016346837242361e-06, - "loss": 0.1548, - "step": 18150 + "learning_rate": 1.1002815681178254e-06, + "loss": 0.0013, + "step": 14890 }, { "epoch": 9.68, - "learning_rate": 1.0838663823738451e-06, - "loss": 0.1777, - "step": 18160 + "learning_rate": 1.078622482131254e-06, + "loss": 0.1251, + "step": 14900 }, { "epoch": 9.68, - "learning_rate": 1.0660980810234543e-06, - "loss": 0.004, - "step": 18170 - }, - { - "epoch": 9.69, - "learning_rate": 1.0483297796730633e-06, - "loss": 0.0372, - "step": 18180 + "learning_rate": 1.0569633961446828e-06, + "loss": 0.0711, + "step": 14910 }, { "epoch": 9.69, - "learning_rate": 1.0305614783226725e-06, - "loss": 0.1137, - "step": 18190 + "learning_rate": 1.0353043101581112e-06, + "loss": 0.032, + "step": 14920 }, { "epoch": 9.7, - "learning_rate": 1.0127931769722815e-06, - "loss": 0.0058, - "step": 18200 + "learning_rate": 1.01364522417154e-06, + "loss": 0.1033, + "step": 14930 }, { "epoch": 9.7, - "learning_rate": 9.950248756218907e-07, - "loss": 0.1374, - "step": 18210 - }, - { - "epoch": 9.71, - "learning_rate": 9.772565742714996e-07, - "loss": 0.005, - "step": 18220 + "learning_rate": 9.919861381849686e-07, + "loss": 0.0706, + "step": 14940 }, { "epoch": 9.71, - "learning_rate": 9.594882729211088e-07, - "loss": 0.1157, - "step": 18230 + "learning_rate": 9.703270521983973e-07, + "loss": 0.0011, + "step": 14950 }, { "epoch": 9.72, - "learning_rate": 9.417199715707179e-07, - "loss": 0.1709, - "step": 18240 + "learning_rate": 9.48667966211826e-07, + "loss": 0.1376, + "step": 14960 }, { - "epoch": 9.73, - "learning_rate": 9.23951670220327e-07, - "loss": 0.1785, - "step": 18250 + "epoch": 9.72, + "learning_rate": 9.270088802252545e-07, + "loss": 0.0821, + "step": 14970 }, { "epoch": 9.73, - "learning_rate": 9.061833688699361e-07, - "loss": 0.1329, - "step": 18260 + "learning_rate": 9.053497942386831e-07, + "loss": 0.0325, + "step": 14980 }, { "epoch": 9.74, - "learning_rate": 8.884150675195452e-07, - "loss": 0.3087, - "step": 18270 + "learning_rate": 8.836907082521118e-07, + "loss": 0.1046, + "step": 14990 }, { "epoch": 9.74, - "learning_rate": 8.706467661691543e-07, - "loss": 0.0041, - "step": 18280 - }, - { - "epoch": 9.75, - "learning_rate": 8.528784648187634e-07, - "loss": 0.1333, - "step": 18290 + "learning_rate": 8.620316222655404e-07, + "loss": 0.001, + "step": 15000 }, { "epoch": 9.75, - "learning_rate": 8.351101634683725e-07, - "loss": 0.1337, - "step": 18300 + "learning_rate": 8.403725362789691e-07, + "loss": 0.0316, + "step": 15010 }, { "epoch": 9.76, - "learning_rate": 8.173418621179815e-07, - "loss": 0.4065, - "step": 18310 + "learning_rate": 8.187134502923977e-07, + "loss": 0.0583, + "step": 15020 }, { "epoch": 9.76, - "learning_rate": 7.995735607675906e-07, - "loss": 0.2073, - "step": 18320 - }, - { - "epoch": 9.77, - "learning_rate": 7.818052594171997e-07, - "loss": 0.069, - "step": 18330 + "learning_rate": 7.970543643058263e-07, + "loss": 0.3065, + "step": 15030 }, { "epoch": 9.77, - "learning_rate": 7.640369580668089e-07, - "loss": 0.1076, - "step": 18340 + "learning_rate": 7.75395278319255e-07, + "loss": 0.0385, + "step": 15040 }, { "epoch": 9.78, - "learning_rate": 7.46268656716418e-07, - "loss": 0.1072, - "step": 18350 + "learning_rate": 7.537361923326836e-07, + "loss": 0.0798, + "step": 15050 }, { "epoch": 9.78, - "learning_rate": 7.285003553660271e-07, - "loss": 0.1113, - "step": 18360 + "learning_rate": 7.320771063461123e-07, + "loss": 0.0639, + "step": 15060 }, { "epoch": 9.79, - "learning_rate": 7.107320540156362e-07, - "loss": 0.075, - "step": 18370 + "learning_rate": 7.104180203595409e-07, + "loss": 0.1085, + "step": 15070 }, { - "epoch": 9.79, - "learning_rate": 6.929637526652453e-07, - "loss": 0.1634, - "step": 18380 + "epoch": 9.8, + "learning_rate": 6.887589343729695e-07, + "loss": 0.0518, + "step": 15080 }, { "epoch": 9.8, - "learning_rate": 6.751954513148543e-07, - "loss": 0.0616, - "step": 18390 + "learning_rate": 6.670998483863981e-07, + "loss": 0.16, + "step": 15090 }, { "epoch": 9.81, - "learning_rate": 6.574271499644634e-07, - "loss": 0.0949, - "step": 18400 + "learning_rate": 6.454407623998268e-07, + "loss": 0.0204, + "step": 15100 }, { "epoch": 9.81, - "learning_rate": 6.396588486140725e-07, - "loss": 0.0272, - "step": 18410 - }, - { - "epoch": 9.82, - "learning_rate": 6.218905472636816e-07, - "loss": 0.2118, - "step": 18420 + "learning_rate": 6.237816764132554e-07, + "loss": 0.1528, + "step": 15110 }, { "epoch": 9.82, - "learning_rate": 6.041222459132907e-07, - "loss": 0.1582, - "step": 18430 + "learning_rate": 6.02122590426684e-07, + "loss": 0.1124, + "step": 15120 }, { "epoch": 9.83, - "learning_rate": 5.863539445628998e-07, - "loss": 0.0692, - "step": 18440 + "learning_rate": 5.804635044401126e-07, + "loss": 0.169, + "step": 15130 }, { "epoch": 9.83, - "learning_rate": 5.685856432125089e-07, - "loss": 0.2514, - "step": 18450 - }, - { - "epoch": 9.84, - "learning_rate": 5.508173418621181e-07, - "loss": 0.052, - "step": 18460 + "learning_rate": 5.588044184535412e-07, + "loss": 0.0796, + "step": 15140 }, { "epoch": 9.84, - "learning_rate": 5.330490405117272e-07, - "loss": 0.0122, - "step": 18470 + "learning_rate": 5.371453324669699e-07, + "loss": 0.1531, + "step": 15150 }, { "epoch": 9.85, - "learning_rate": 5.152807391613362e-07, - "loss": 0.0698, - "step": 18480 + "learning_rate": 5.154862464803985e-07, + "loss": 0.1019, + "step": 15160 }, { "epoch": 9.85, - "learning_rate": 4.975124378109453e-07, - "loss": 0.2055, - "step": 18490 - }, - { - "epoch": 9.86, - "learning_rate": 4.797441364605544e-07, - "loss": 0.1785, - "step": 18500 + "learning_rate": 4.938271604938272e-07, + "loss": 0.0018, + "step": 15170 }, { "epoch": 9.86, - "learning_rate": 4.619758351101635e-07, - "loss": 0.2698, - "step": 18510 + "learning_rate": 4.7216807450725577e-07, + "loss": 0.021, + "step": 15180 }, { "epoch": 9.87, - "learning_rate": 4.442075337597726e-07, - "loss": 0.1172, - "step": 18520 + "learning_rate": 4.505089885206844e-07, + "loss": 0.0517, + "step": 15190 }, { "epoch": 9.87, - "learning_rate": 4.264392324093817e-07, - "loss": 0.2256, - "step": 18530 + "learning_rate": 4.2884990253411303e-07, + "loss": 0.0759, + "step": 15200 }, { "epoch": 9.88, - "learning_rate": 4.0867093105899077e-07, - "loss": 0.1225, - "step": 18540 + "learning_rate": 4.071908165475417e-07, + "loss": 0.2548, + "step": 15210 }, { "epoch": 9.89, - "learning_rate": 3.9090262970859986e-07, - "loss": 0.1917, - "step": 18550 + "learning_rate": 3.8553173056097035e-07, + "loss": 0.1891, + "step": 15220 }, { "epoch": 9.89, - "learning_rate": 3.73134328358209e-07, - "loss": 0.2195, - "step": 18560 - }, - { - "epoch": 9.9, - "learning_rate": 3.553660270078181e-07, - "loss": 0.1751, - "step": 18570 + "learning_rate": 3.63872644574399e-07, + "loss": 0.1289, + "step": 15230 }, { "epoch": 9.9, - "learning_rate": 3.375977256574272e-07, - "loss": 0.1095, - "step": 18580 + "learning_rate": 3.422135585878276e-07, + "loss": 0.0315, + "step": 15240 }, { "epoch": 9.91, - "learning_rate": 3.1982942430703626e-07, - "loss": 0.0894, - "step": 18590 + "learning_rate": 3.2055447260125624e-07, + "loss": 0.0379, + "step": 15250 }, { "epoch": 9.91, - "learning_rate": 3.0206112295664535e-07, - "loss": 0.0621, - "step": 18600 - }, - { - "epoch": 9.92, - "learning_rate": 2.8429282160625444e-07, - "loss": 0.1031, - "step": 18610 + "learning_rate": 2.988953866146849e-07, + "loss": 0.1247, + "step": 15260 }, { "epoch": 9.92, - "learning_rate": 2.665245202558636e-07, - "loss": 0.1549, - "step": 18620 + "learning_rate": 2.772363006281135e-07, + "loss": 0.1522, + "step": 15270 }, { "epoch": 9.93, - "learning_rate": 2.4875621890547267e-07, - "loss": 0.0501, - "step": 18630 + "learning_rate": 2.5557721464154214e-07, + "loss": 0.1842, + "step": 15280 }, { "epoch": 9.93, - "learning_rate": 2.3098791755508175e-07, - "loss": 0.3934, - "step": 18640 + "learning_rate": 2.3391812865497075e-07, + "loss": 0.1641, + "step": 15290 }, { "epoch": 9.94, - "learning_rate": 2.1321961620469084e-07, - "loss": 0.0506, - "step": 18650 + "learning_rate": 2.122590426683994e-07, + "loss": 0.0641, + "step": 15300 }, { "epoch": 9.94, - "learning_rate": 1.9545131485429993e-07, - "loss": 0.0022, - "step": 18660 - }, - { - "epoch": 9.95, - "learning_rate": 1.7768301350390904e-07, - "loss": 0.1445, - "step": 18670 + "learning_rate": 1.9059995668182804e-07, + "loss": 0.0768, + "step": 15310 }, { "epoch": 9.95, - "learning_rate": 1.5991471215351813e-07, - "loss": 0.1325, - "step": 18680 + "learning_rate": 1.6894087069525667e-07, + "loss": 0.0525, + "step": 15320 }, { "epoch": 9.96, - "learning_rate": 1.4214641080312722e-07, - "loss": 0.0923, - "step": 18690 + "learning_rate": 1.472817847086853e-07, + "loss": 0.0982, + "step": 15330 }, { - "epoch": 9.97, - "learning_rate": 1.2437810945273633e-07, - "loss": 0.2186, - "step": 18700 + "epoch": 9.96, + "learning_rate": 1.256226987221139e-07, + "loss": 0.197, + "step": 15340 }, { "epoch": 9.97, - "learning_rate": 1.0660980810234542e-07, - "loss": 0.2451, - "step": 18710 + "learning_rate": 1.0396361273554257e-07, + "loss": 0.1669, + "step": 15350 }, { "epoch": 9.98, - "learning_rate": 8.884150675195452e-08, - "loss": 0.1022, - "step": 18720 + "learning_rate": 8.230452674897118e-08, + "loss": 0.0749, + "step": 15360 }, { "epoch": 9.98, - "learning_rate": 7.107320540156361e-08, - "loss": 0.0566, - "step": 18730 - }, - { - "epoch": 9.99, - "learning_rate": 5.330490405117271e-08, - "loss": 0.2908, - "step": 18740 + "learning_rate": 6.064544076239983e-08, + "loss": 0.1194, + "step": 15370 }, { "epoch": 9.99, - "learning_rate": 3.5536602700781805e-08, - "loss": 0.0709, - "step": 18750 + "learning_rate": 3.898635477582846e-08, + "loss": 0.1512, + "step": 15380 }, { "epoch": 10.0, - "learning_rate": 1.7768301350390902e-08, - "loss": 0.1843, - "step": 18760 + "learning_rate": 1.7327268789257094e-08, + "loss": 0.068, + "step": 15390 }, { "epoch": 10.0, - "eval_accuracy": 0.9701774254435636, - "eval_loss": 0.15903720259666443, - "eval_runtime": 12.4575, - "eval_samples_per_second": 212.643, - "eval_steps_per_second": 53.221, - "step": 18760 + "eval_accuracy": 0.985280588776449, + "eval_loss": 0.0865689218044281, + "eval_runtime": 13.3643, + "eval_samples_per_second": 162.673, + "eval_steps_per_second": 40.706, + "step": 15390 }, { "epoch": 10.0, - "step": 18760, - "total_flos": 1.4520994115341998e+18, - "train_loss": 0.3472037715730128, - "train_runtime": 2497.0366, - "train_samples_per_second": 60.111, - "train_steps_per_second": 7.513 + "step": 15390, + "total_flos": 1.1936517061793697e+18, + "train_loss": 0.29998462175571583, + "train_runtime": 2944.6409, + "train_samples_per_second": 41.825, + "train_steps_per_second": 5.226 } ], "logging_steps": 10, - "max_steps": 18760, + "max_steps": 15390, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, - "total_flos": 1.4520994115341998e+18, + "total_flos": 1.1936517061793697e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null