diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,72504 @@ +{ + "best_metric": 1.6387135982513428, + "best_model_checkpoint": "model_output/checkpoint-106600", + "epoch": 3.964741324803809, + "global_step": 106600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 9.999628073046454e-06, + "loss": 71.1823, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 9.999256146092908e-06, + "loss": 22.0626, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 9.998884219139361e-06, + "loss": 5.7338, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 9.998512292185816e-06, + "loss": 4.687, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 9.99814036523227e-06, + "loss": 4.8034, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 9.997768438278723e-06, + "loss": 3.667, + "step": 60 + }, + { + "epoch": 0.0, + "learning_rate": 9.997396511325177e-06, + "loss": 3.2856, + "step": 70 + }, + { + "epoch": 0.0, + "learning_rate": 9.99702458437163e-06, + "loss": 3.231, + "step": 80 + }, + { + "epoch": 0.0, + "learning_rate": 9.996652657418084e-06, + "loss": 2.8601, + "step": 90 + }, + { + "epoch": 0.0, + "learning_rate": 9.996280730464537e-06, + "loss": 3.0438, + "step": 100 + }, + { + "epoch": 0.0, + "eval_loss": 3.962357521057129, + "eval_runtime": 16.8251, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 100 + }, + { + "epoch": 0.0, + "learning_rate": 9.99590880351099e-06, + "loss": 2.8138, + "step": 110 + }, + { + "epoch": 0.0, + "learning_rate": 9.995536876557444e-06, + "loss": 2.6645, + "step": 120 + }, + { + "epoch": 0.0, + "learning_rate": 9.995164949603897e-06, + "loss": 2.9119, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 9.994793022650353e-06, + "loss": 2.6138, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 9.994421095696806e-06, + "loss": 2.8455, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 9.99404916874326e-06, + "loss": 2.6266, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 9.993677241789713e-06, + "loss": 2.5916, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 9.993305314836166e-06, + "loss": 2.5542, + "step": 180 + }, + { + "epoch": 0.01, + "learning_rate": 9.99293338788262e-06, + "loss": 2.4615, + "step": 190 + }, + { + "epoch": 0.01, + "learning_rate": 9.992561460929075e-06, + "loss": 2.5009, + "step": 200 + }, + { + "epoch": 0.01, + "eval_loss": 2.8816134929656982, + "eval_runtime": 16.8301, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 200 + }, + { + "epoch": 0.01, + "learning_rate": 9.992189533975529e-06, + "loss": 2.5594, + "step": 210 + }, + { + "epoch": 0.01, + "learning_rate": 9.991817607021982e-06, + "loss": 2.4448, + "step": 220 + }, + { + "epoch": 0.01, + "learning_rate": 9.991445680068435e-06, + "loss": 2.4259, + "step": 230 + }, + { + "epoch": 0.01, + "learning_rate": 9.991073753114889e-06, + "loss": 2.5527, + "step": 240 + }, + { + "epoch": 0.01, + "learning_rate": 9.990701826161342e-06, + "loss": 2.4081, + "step": 250 + }, + { + "epoch": 0.01, + "learning_rate": 9.990329899207798e-06, + "loss": 2.6282, + "step": 260 + }, + { + "epoch": 0.01, + "learning_rate": 9.989957972254251e-06, + "loss": 2.3536, + "step": 270 + }, + { + "epoch": 0.01, + "learning_rate": 9.989586045300704e-06, + "loss": 2.487, + "step": 280 + }, + { + "epoch": 0.01, + "learning_rate": 9.989214118347156e-06, + "loss": 2.4916, + "step": 290 + }, + { + "epoch": 0.01, + "learning_rate": 9.988842191393611e-06, + "loss": 2.4249, + "step": 300 + }, + { + "epoch": 0.01, + "eval_loss": 2.49206805229187, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 300 + }, + { + "epoch": 0.01, + "learning_rate": 9.988470264440065e-06, + "loss": 2.4538, + "step": 310 + }, + { + "epoch": 0.01, + "learning_rate": 9.988098337486518e-06, + "loss": 2.3917, + "step": 320 + }, + { + "epoch": 0.01, + "learning_rate": 9.987726410532972e-06, + "loss": 2.3133, + "step": 330 + }, + { + "epoch": 0.01, + "learning_rate": 9.987354483579425e-06, + "loss": 2.3267, + "step": 340 + }, + { + "epoch": 0.01, + "learning_rate": 9.986982556625879e-06, + "loss": 2.5134, + "step": 350 + }, + { + "epoch": 0.01, + "learning_rate": 9.986610629672334e-06, + "loss": 2.3831, + "step": 360 + }, + { + "epoch": 0.01, + "learning_rate": 9.986238702718787e-06, + "loss": 2.2785, + "step": 370 + }, + { + "epoch": 0.01, + "learning_rate": 9.98586677576524e-06, + "loss": 2.3534, + "step": 380 + }, + { + "epoch": 0.01, + "learning_rate": 9.985494848811694e-06, + "loss": 2.4644, + "step": 390 + }, + { + "epoch": 0.01, + "learning_rate": 9.985122921858148e-06, + "loss": 2.2904, + "step": 400 + }, + { + "epoch": 0.01, + "eval_loss": 2.252032518386841, + "eval_runtime": 16.8355, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 400 + }, + { + "epoch": 0.02, + "learning_rate": 9.984750994904601e-06, + "loss": 2.3051, + "step": 410 + }, + { + "epoch": 0.02, + "learning_rate": 9.984379067951056e-06, + "loss": 2.3027, + "step": 420 + }, + { + "epoch": 0.02, + "learning_rate": 9.98400714099751e-06, + "loss": 2.26, + "step": 430 + }, + { + "epoch": 0.02, + "learning_rate": 9.983635214043963e-06, + "loss": 2.3387, + "step": 440 + }, + { + "epoch": 0.02, + "learning_rate": 9.983263287090417e-06, + "loss": 2.3419, + "step": 450 + }, + { + "epoch": 0.02, + "learning_rate": 9.98289136013687e-06, + "loss": 2.326, + "step": 460 + }, + { + "epoch": 0.02, + "learning_rate": 9.982519433183324e-06, + "loss": 2.3524, + "step": 470 + }, + { + "epoch": 0.02, + "learning_rate": 9.982147506229777e-06, + "loss": 2.289, + "step": 480 + }, + { + "epoch": 0.02, + "learning_rate": 9.98177557927623e-06, + "loss": 2.4909, + "step": 490 + }, + { + "epoch": 0.02, + "learning_rate": 9.981403652322684e-06, + "loss": 2.3466, + "step": 500 + }, + { + "epoch": 0.02, + "eval_loss": 2.157212495803833, + "eval_runtime": 16.8281, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 500 + }, + { + "epoch": 0.02, + "learning_rate": 9.981031725369137e-06, + "loss": 2.2045, + "step": 510 + }, + { + "epoch": 0.02, + "learning_rate": 9.980659798415593e-06, + "loss": 2.3359, + "step": 520 + }, + { + "epoch": 0.02, + "learning_rate": 9.980287871462046e-06, + "loss": 2.2821, + "step": 530 + }, + { + "epoch": 0.02, + "learning_rate": 9.9799159445085e-06, + "loss": 2.3181, + "step": 540 + }, + { + "epoch": 0.02, + "learning_rate": 9.979544017554953e-06, + "loss": 2.1781, + "step": 550 + }, + { + "epoch": 0.02, + "learning_rate": 9.979172090601406e-06, + "loss": 2.2583, + "step": 560 + }, + { + "epoch": 0.02, + "learning_rate": 9.97880016364786e-06, + "loss": 2.1951, + "step": 570 + }, + { + "epoch": 0.02, + "learning_rate": 9.978428236694313e-06, + "loss": 2.3709, + "step": 580 + }, + { + "epoch": 0.02, + "learning_rate": 9.978056309740768e-06, + "loss": 2.2752, + "step": 590 + }, + { + "epoch": 0.02, + "learning_rate": 9.977684382787222e-06, + "loss": 2.1594, + "step": 600 + }, + { + "epoch": 0.02, + "eval_loss": 2.1550936698913574, + "eval_runtime": 16.8062, + "eval_samples_per_second": 59.502, + "eval_steps_per_second": 3.749, + "step": 600 + }, + { + "epoch": 0.02, + "learning_rate": 9.977312455833675e-06, + "loss": 2.1717, + "step": 610 + }, + { + "epoch": 0.02, + "learning_rate": 9.976940528880129e-06, + "loss": 2.2996, + "step": 620 + }, + { + "epoch": 0.02, + "learning_rate": 9.976568601926582e-06, + "loss": 2.3696, + "step": 630 + }, + { + "epoch": 0.02, + "learning_rate": 9.976196674973036e-06, + "loss": 2.1121, + "step": 640 + }, + { + "epoch": 0.02, + "learning_rate": 9.975824748019491e-06, + "loss": 2.378, + "step": 650 + }, + { + "epoch": 0.02, + "learning_rate": 9.975452821065943e-06, + "loss": 2.1941, + "step": 660 + }, + { + "epoch": 0.02, + "learning_rate": 9.975080894112396e-06, + "loss": 2.2032, + "step": 670 + }, + { + "epoch": 0.03, + "learning_rate": 9.97470896715885e-06, + "loss": 2.1514, + "step": 680 + }, + { + "epoch": 0.03, + "learning_rate": 9.974337040205305e-06, + "loss": 2.1634, + "step": 690 + }, + { + "epoch": 0.03, + "learning_rate": 9.973965113251758e-06, + "loss": 2.2594, + "step": 700 + }, + { + "epoch": 0.03, + "eval_loss": 2.1305952072143555, + "eval_runtime": 16.8148, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 700 + }, + { + "epoch": 0.03, + "learning_rate": 9.973593186298212e-06, + "loss": 2.2202, + "step": 710 + }, + { + "epoch": 0.03, + "learning_rate": 9.973221259344665e-06, + "loss": 2.0464, + "step": 720 + }, + { + "epoch": 0.03, + "learning_rate": 9.972849332391119e-06, + "loss": 2.1932, + "step": 730 + }, + { + "epoch": 0.03, + "learning_rate": 9.972477405437572e-06, + "loss": 2.2536, + "step": 740 + }, + { + "epoch": 0.03, + "learning_rate": 9.972105478484027e-06, + "loss": 2.2631, + "step": 750 + }, + { + "epoch": 0.03, + "learning_rate": 9.97173355153048e-06, + "loss": 2.3873, + "step": 760 + }, + { + "epoch": 0.03, + "learning_rate": 9.971361624576934e-06, + "loss": 2.4013, + "step": 770 + }, + { + "epoch": 0.03, + "learning_rate": 9.970989697623388e-06, + "loss": 2.1388, + "step": 780 + }, + { + "epoch": 0.03, + "learning_rate": 9.970617770669841e-06, + "loss": 2.1701, + "step": 790 + }, + { + "epoch": 0.03, + "learning_rate": 9.970245843716294e-06, + "loss": 2.1495, + "step": 800 + }, + { + "epoch": 0.03, + "eval_loss": 2.11495041847229, + "eval_runtime": 16.8211, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 800 + }, + { + "epoch": 0.03, + "learning_rate": 9.96987391676275e-06, + "loss": 2.1654, + "step": 810 + }, + { + "epoch": 0.03, + "learning_rate": 9.969501989809203e-06, + "loss": 2.2645, + "step": 820 + }, + { + "epoch": 0.03, + "learning_rate": 9.969130062855657e-06, + "loss": 2.145, + "step": 830 + }, + { + "epoch": 0.03, + "learning_rate": 9.96875813590211e-06, + "loss": 2.3723, + "step": 840 + }, + { + "epoch": 0.03, + "learning_rate": 9.968386208948563e-06, + "loss": 2.1619, + "step": 850 + }, + { + "epoch": 0.03, + "learning_rate": 9.968014281995017e-06, + "loss": 2.2993, + "step": 860 + }, + { + "epoch": 0.03, + "learning_rate": 9.96764235504147e-06, + "loss": 2.2055, + "step": 870 + }, + { + "epoch": 0.03, + "learning_rate": 9.967270428087924e-06, + "loss": 2.1748, + "step": 880 + }, + { + "epoch": 0.03, + "learning_rate": 9.966898501134377e-06, + "loss": 2.1042, + "step": 890 + }, + { + "epoch": 0.03, + "learning_rate": 9.96652657418083e-06, + "loss": 2.0062, + "step": 900 + }, + { + "epoch": 0.03, + "eval_loss": 2.095651865005493, + "eval_runtime": 16.8286, + "eval_samples_per_second": 59.423, + "eval_steps_per_second": 3.744, + "step": 900 + }, + { + "epoch": 0.03, + "learning_rate": 9.966154647227286e-06, + "loss": 2.1417, + "step": 910 + }, + { + "epoch": 0.03, + "learning_rate": 9.96578272027374e-06, + "loss": 2.0974, + "step": 920 + }, + { + "epoch": 0.03, + "learning_rate": 9.965410793320193e-06, + "loss": 2.25, + "step": 930 + }, + { + "epoch": 0.03, + "learning_rate": 9.965038866366646e-06, + "loss": 2.1695, + "step": 940 + }, + { + "epoch": 0.04, + "learning_rate": 9.9646669394131e-06, + "loss": 2.1342, + "step": 950 + }, + { + "epoch": 0.04, + "learning_rate": 9.964295012459553e-06, + "loss": 2.1814, + "step": 960 + }, + { + "epoch": 0.04, + "learning_rate": 9.963923085506008e-06, + "loss": 2.2674, + "step": 970 + }, + { + "epoch": 0.04, + "learning_rate": 9.963551158552462e-06, + "loss": 2.2211, + "step": 980 + }, + { + "epoch": 0.04, + "learning_rate": 9.963179231598915e-06, + "loss": 2.2157, + "step": 990 + }, + { + "epoch": 0.04, + "learning_rate": 9.962807304645369e-06, + "loss": 2.197, + "step": 1000 + }, + { + "epoch": 0.04, + "eval_loss": 2.1001698970794678, + "eval_runtime": 16.8363, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 1000 + }, + { + "epoch": 0.04, + "learning_rate": 9.962435377691822e-06, + "loss": 2.1803, + "step": 1010 + }, + { + "epoch": 0.04, + "learning_rate": 9.962063450738276e-06, + "loss": 2.2047, + "step": 1020 + }, + { + "epoch": 0.04, + "learning_rate": 9.96169152378473e-06, + "loss": 2.2239, + "step": 1030 + }, + { + "epoch": 0.04, + "learning_rate": 9.961319596831183e-06, + "loss": 2.1944, + "step": 1040 + }, + { + "epoch": 0.04, + "learning_rate": 9.960947669877636e-06, + "loss": 2.1835, + "step": 1050 + }, + { + "epoch": 0.04, + "learning_rate": 9.96057574292409e-06, + "loss": 2.1642, + "step": 1060 + }, + { + "epoch": 0.04, + "learning_rate": 9.960203815970545e-06, + "loss": 2.0982, + "step": 1070 + }, + { + "epoch": 0.04, + "learning_rate": 9.959831889016998e-06, + "loss": 2.1505, + "step": 1080 + }, + { + "epoch": 0.04, + "learning_rate": 9.959459962063452e-06, + "loss": 2.076, + "step": 1090 + }, + { + "epoch": 0.04, + "learning_rate": 9.959088035109905e-06, + "loss": 2.2292, + "step": 1100 + }, + { + "epoch": 0.04, + "eval_loss": 2.0761303901672363, + "eval_runtime": 16.8122, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 1100 + }, + { + "epoch": 0.04, + "learning_rate": 9.958716108156359e-06, + "loss": 2.2362, + "step": 1110 + }, + { + "epoch": 0.04, + "learning_rate": 9.958344181202812e-06, + "loss": 2.2465, + "step": 1120 + }, + { + "epoch": 0.04, + "learning_rate": 9.957972254249267e-06, + "loss": 2.306, + "step": 1130 + }, + { + "epoch": 0.04, + "learning_rate": 9.95760032729572e-06, + "loss": 2.0976, + "step": 1140 + }, + { + "epoch": 0.04, + "learning_rate": 9.957228400342174e-06, + "loss": 2.2947, + "step": 1150 + }, + { + "epoch": 0.04, + "learning_rate": 9.956856473388627e-06, + "loss": 2.1385, + "step": 1160 + }, + { + "epoch": 0.04, + "learning_rate": 9.956484546435081e-06, + "loss": 2.0761, + "step": 1170 + }, + { + "epoch": 0.04, + "learning_rate": 9.956112619481534e-06, + "loss": 2.0952, + "step": 1180 + }, + { + "epoch": 0.04, + "learning_rate": 9.955740692527988e-06, + "loss": 2.1337, + "step": 1190 + }, + { + "epoch": 0.04, + "learning_rate": 9.955368765574443e-06, + "loss": 2.1494, + "step": 1200 + }, + { + "epoch": 0.04, + "eval_loss": 2.050685167312622, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 1200 + }, + { + "epoch": 0.05, + "learning_rate": 9.954996838620896e-06, + "loss": 2.2067, + "step": 1210 + }, + { + "epoch": 0.05, + "learning_rate": 9.95462491166735e-06, + "loss": 2.2118, + "step": 1220 + }, + { + "epoch": 0.05, + "learning_rate": 9.954252984713802e-06, + "loss": 2.1195, + "step": 1230 + }, + { + "epoch": 0.05, + "learning_rate": 9.953881057760257e-06, + "loss": 2.0755, + "step": 1240 + }, + { + "epoch": 0.05, + "learning_rate": 9.95350913080671e-06, + "loss": 2.1954, + "step": 1250 + }, + { + "epoch": 0.05, + "learning_rate": 9.953137203853164e-06, + "loss": 2.1428, + "step": 1260 + }, + { + "epoch": 0.05, + "learning_rate": 9.952765276899617e-06, + "loss": 2.2481, + "step": 1270 + }, + { + "epoch": 0.05, + "learning_rate": 9.95239334994607e-06, + "loss": 2.3441, + "step": 1280 + }, + { + "epoch": 0.05, + "learning_rate": 9.952021422992524e-06, + "loss": 2.0913, + "step": 1290 + }, + { + "epoch": 0.05, + "learning_rate": 9.95164949603898e-06, + "loss": 2.1925, + "step": 1300 + }, + { + "epoch": 0.05, + "eval_loss": 2.04333233833313, + "eval_runtime": 16.838, + "eval_samples_per_second": 59.39, + "eval_steps_per_second": 3.742, + "step": 1300 + }, + { + "epoch": 0.05, + "learning_rate": 9.951277569085433e-06, + "loss": 2.0924, + "step": 1310 + }, + { + "epoch": 0.05, + "learning_rate": 9.950905642131886e-06, + "loss": 2.2056, + "step": 1320 + }, + { + "epoch": 0.05, + "learning_rate": 9.95053371517834e-06, + "loss": 2.1989, + "step": 1330 + }, + { + "epoch": 0.05, + "learning_rate": 9.950161788224793e-06, + "loss": 2.1813, + "step": 1340 + }, + { + "epoch": 0.05, + "learning_rate": 9.949789861271247e-06, + "loss": 2.1662, + "step": 1350 + }, + { + "epoch": 0.05, + "learning_rate": 9.949417934317702e-06, + "loss": 2.0805, + "step": 1360 + }, + { + "epoch": 0.05, + "learning_rate": 9.949046007364155e-06, + "loss": 2.211, + "step": 1370 + }, + { + "epoch": 0.05, + "learning_rate": 9.948674080410609e-06, + "loss": 2.0674, + "step": 1380 + }, + { + "epoch": 0.05, + "learning_rate": 9.948302153457062e-06, + "loss": 2.16, + "step": 1390 + }, + { + "epoch": 0.05, + "learning_rate": 9.947930226503516e-06, + "loss": 2.2423, + "step": 1400 + }, + { + "epoch": 0.05, + "eval_loss": 2.0331242084503174, + "eval_runtime": 16.8149, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 1400 + }, + { + "epoch": 0.05, + "learning_rate": 9.947558299549969e-06, + "loss": 2.0895, + "step": 1410 + }, + { + "epoch": 0.05, + "learning_rate": 9.947186372596423e-06, + "loss": 2.1887, + "step": 1420 + }, + { + "epoch": 0.05, + "learning_rate": 9.946814445642876e-06, + "loss": 2.0913, + "step": 1430 + }, + { + "epoch": 0.05, + "learning_rate": 9.94644251868933e-06, + "loss": 2.2748, + "step": 1440 + }, + { + "epoch": 0.05, + "learning_rate": 9.946070591735783e-06, + "loss": 2.0926, + "step": 1450 + }, + { + "epoch": 0.05, + "learning_rate": 9.945698664782238e-06, + "loss": 2.1495, + "step": 1460 + }, + { + "epoch": 0.05, + "learning_rate": 9.945326737828692e-06, + "loss": 2.1222, + "step": 1470 + }, + { + "epoch": 0.06, + "learning_rate": 9.944954810875145e-06, + "loss": 2.2022, + "step": 1480 + }, + { + "epoch": 0.06, + "learning_rate": 9.944582883921598e-06, + "loss": 2.1274, + "step": 1490 + }, + { + "epoch": 0.06, + "learning_rate": 9.944210956968052e-06, + "loss": 2.2059, + "step": 1500 + }, + { + "epoch": 0.06, + "eval_loss": 2.060030221939087, + "eval_runtime": 16.8378, + "eval_samples_per_second": 59.39, + "eval_steps_per_second": 3.742, + "step": 1500 + }, + { + "epoch": 0.06, + "learning_rate": 9.943839030014505e-06, + "loss": 2.0747, + "step": 1510 + }, + { + "epoch": 0.06, + "learning_rate": 9.94346710306096e-06, + "loss": 2.2129, + "step": 1520 + }, + { + "epoch": 0.06, + "learning_rate": 9.943095176107414e-06, + "loss": 2.229, + "step": 1530 + }, + { + "epoch": 0.06, + "learning_rate": 9.942723249153867e-06, + "loss": 2.0872, + "step": 1540 + }, + { + "epoch": 0.06, + "learning_rate": 9.942351322200321e-06, + "loss": 2.1704, + "step": 1550 + }, + { + "epoch": 0.06, + "learning_rate": 9.941979395246774e-06, + "loss": 2.0278, + "step": 1560 + }, + { + "epoch": 0.06, + "learning_rate": 9.941607468293228e-06, + "loss": 2.136, + "step": 1570 + }, + { + "epoch": 0.06, + "learning_rate": 9.941235541339683e-06, + "loss": 2.1737, + "step": 1580 + }, + { + "epoch": 0.06, + "learning_rate": 9.940863614386136e-06, + "loss": 2.1343, + "step": 1590 + }, + { + "epoch": 0.06, + "learning_rate": 9.940491687432588e-06, + "loss": 2.1649, + "step": 1600 + }, + { + "epoch": 0.06, + "eval_loss": 2.0412840843200684, + "eval_runtime": 16.8235, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 1600 + }, + { + "epoch": 0.06, + "learning_rate": 9.940119760479042e-06, + "loss": 2.0797, + "step": 1610 + }, + { + "epoch": 0.06, + "learning_rate": 9.939747833525497e-06, + "loss": 2.1072, + "step": 1620 + }, + { + "epoch": 0.06, + "learning_rate": 9.93937590657195e-06, + "loss": 2.1234, + "step": 1630 + }, + { + "epoch": 0.06, + "learning_rate": 9.939003979618404e-06, + "loss": 2.0634, + "step": 1640 + }, + { + "epoch": 0.06, + "learning_rate": 9.938632052664857e-06, + "loss": 2.29, + "step": 1650 + }, + { + "epoch": 0.06, + "learning_rate": 9.93826012571131e-06, + "loss": 2.0382, + "step": 1660 + }, + { + "epoch": 0.06, + "learning_rate": 9.937888198757764e-06, + "loss": 2.1327, + "step": 1670 + }, + { + "epoch": 0.06, + "learning_rate": 9.93751627180422e-06, + "loss": 2.0681, + "step": 1680 + }, + { + "epoch": 0.06, + "learning_rate": 9.937144344850673e-06, + "loss": 2.0619, + "step": 1690 + }, + { + "epoch": 0.06, + "learning_rate": 9.936772417897126e-06, + "loss": 2.0284, + "step": 1700 + }, + { + "epoch": 0.06, + "eval_loss": 2.0280797481536865, + "eval_runtime": 16.8227, + "eval_samples_per_second": 59.444, + "eval_steps_per_second": 3.745, + "step": 1700 + }, + { + "epoch": 0.06, + "learning_rate": 9.93640049094358e-06, + "loss": 2.1322, + "step": 1710 + }, + { + "epoch": 0.06, + "learning_rate": 9.936028563990033e-06, + "loss": 2.0629, + "step": 1720 + }, + { + "epoch": 0.06, + "learning_rate": 9.935656637036487e-06, + "loss": 2.0483, + "step": 1730 + }, + { + "epoch": 0.06, + "learning_rate": 9.93528471008294e-06, + "loss": 2.1661, + "step": 1740 + }, + { + "epoch": 0.07, + "learning_rate": 9.934912783129395e-06, + "loss": 2.1455, + "step": 1750 + }, + { + "epoch": 0.07, + "learning_rate": 9.934540856175849e-06, + "loss": 2.05, + "step": 1760 + }, + { + "epoch": 0.07, + "learning_rate": 9.934168929222302e-06, + "loss": 2.119, + "step": 1770 + }, + { + "epoch": 0.07, + "learning_rate": 9.933797002268756e-06, + "loss": 2.0101, + "step": 1780 + }, + { + "epoch": 0.07, + "learning_rate": 9.933425075315209e-06, + "loss": 2.064, + "step": 1790 + }, + { + "epoch": 0.07, + "learning_rate": 9.933053148361662e-06, + "loss": 1.9721, + "step": 1800 + }, + { + "epoch": 0.07, + "eval_loss": 2.004784345626831, + "eval_runtime": 16.8421, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 1800 + }, + { + "epoch": 0.07, + "learning_rate": 9.932681221408116e-06, + "loss": 2.2195, + "step": 1810 + }, + { + "epoch": 0.07, + "learning_rate": 9.93230929445457e-06, + "loss": 2.077, + "step": 1820 + }, + { + "epoch": 0.07, + "learning_rate": 9.931937367501023e-06, + "loss": 2.0149, + "step": 1830 + }, + { + "epoch": 0.07, + "learning_rate": 9.931565440547476e-06, + "loss": 2.2177, + "step": 1840 + }, + { + "epoch": 0.07, + "learning_rate": 9.931193513593931e-06, + "loss": 2.1127, + "step": 1850 + }, + { + "epoch": 0.07, + "learning_rate": 9.930821586640385e-06, + "loss": 2.0352, + "step": 1860 + }, + { + "epoch": 0.07, + "learning_rate": 9.930449659686838e-06, + "loss": 2.1237, + "step": 1870 + }, + { + "epoch": 0.07, + "learning_rate": 9.930077732733292e-06, + "loss": 2.046, + "step": 1880 + }, + { + "epoch": 0.07, + "learning_rate": 9.929705805779745e-06, + "loss": 2.1227, + "step": 1890 + }, + { + "epoch": 0.07, + "learning_rate": 9.929333878826199e-06, + "loss": 1.9553, + "step": 1900 + }, + { + "epoch": 0.07, + "eval_loss": 2.0045270919799805, + "eval_runtime": 16.8191, + "eval_samples_per_second": 59.456, + "eval_steps_per_second": 3.746, + "step": 1900 + }, + { + "epoch": 0.07, + "learning_rate": 9.928961951872654e-06, + "loss": 2.128, + "step": 1910 + }, + { + "epoch": 0.07, + "learning_rate": 9.928590024919107e-06, + "loss": 2.0731, + "step": 1920 + }, + { + "epoch": 0.07, + "learning_rate": 9.92821809796556e-06, + "loss": 2.1488, + "step": 1930 + }, + { + "epoch": 0.07, + "learning_rate": 9.927846171012014e-06, + "loss": 2.1605, + "step": 1940 + }, + { + "epoch": 0.07, + "learning_rate": 9.927474244058468e-06, + "loss": 2.1304, + "step": 1950 + }, + { + "epoch": 0.07, + "learning_rate": 9.927102317104921e-06, + "loss": 2.0949, + "step": 1960 + }, + { + "epoch": 0.07, + "learning_rate": 9.926730390151376e-06, + "loss": 2.1037, + "step": 1970 + }, + { + "epoch": 0.07, + "learning_rate": 9.926358463197828e-06, + "loss": 2.0626, + "step": 1980 + }, + { + "epoch": 0.07, + "learning_rate": 9.925986536244282e-06, + "loss": 2.1526, + "step": 1990 + }, + { + "epoch": 0.07, + "learning_rate": 9.925614609290735e-06, + "loss": 2.0819, + "step": 2000 + }, + { + "epoch": 0.07, + "eval_loss": 2.0006372928619385, + "eval_runtime": 16.8194, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 2000 + }, + { + "epoch": 0.07, + "learning_rate": 9.92524268233719e-06, + "loss": 2.2745, + "step": 2010 + }, + { + "epoch": 0.08, + "learning_rate": 9.924870755383644e-06, + "loss": 2.0069, + "step": 2020 + }, + { + "epoch": 0.08, + "learning_rate": 9.924498828430097e-06, + "loss": 2.0527, + "step": 2030 + }, + { + "epoch": 0.08, + "learning_rate": 9.92412690147655e-06, + "loss": 2.1802, + "step": 2040 + }, + { + "epoch": 0.08, + "learning_rate": 9.923754974523004e-06, + "loss": 1.9367, + "step": 2050 + }, + { + "epoch": 0.08, + "learning_rate": 9.923383047569457e-06, + "loss": 2.1893, + "step": 2060 + }, + { + "epoch": 0.08, + "learning_rate": 9.923011120615913e-06, + "loss": 2.1842, + "step": 2070 + }, + { + "epoch": 0.08, + "learning_rate": 9.922639193662366e-06, + "loss": 2.1706, + "step": 2080 + }, + { + "epoch": 0.08, + "learning_rate": 9.92226726670882e-06, + "loss": 2.0484, + "step": 2090 + }, + { + "epoch": 0.08, + "learning_rate": 9.921895339755273e-06, + "loss": 1.9896, + "step": 2100 + }, + { + "epoch": 0.08, + "eval_loss": 1.9967702627182007, + "eval_runtime": 16.8373, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 2100 + }, + { + "epoch": 0.08, + "learning_rate": 9.921523412801726e-06, + "loss": 2.0492, + "step": 2110 + }, + { + "epoch": 0.08, + "learning_rate": 9.92115148584818e-06, + "loss": 2.0365, + "step": 2120 + }, + { + "epoch": 0.08, + "learning_rate": 9.920779558894635e-06, + "loss": 2.2038, + "step": 2130 + }, + { + "epoch": 0.08, + "learning_rate": 9.920407631941089e-06, + "loss": 2.2791, + "step": 2140 + }, + { + "epoch": 0.08, + "learning_rate": 9.920035704987542e-06, + "loss": 2.0421, + "step": 2150 + }, + { + "epoch": 0.08, + "learning_rate": 9.919663778033994e-06, + "loss": 2.0615, + "step": 2160 + }, + { + "epoch": 0.08, + "learning_rate": 9.919291851080449e-06, + "loss": 2.2056, + "step": 2170 + }, + { + "epoch": 0.08, + "learning_rate": 9.918919924126902e-06, + "loss": 2.0442, + "step": 2180 + }, + { + "epoch": 0.08, + "learning_rate": 9.918547997173356e-06, + "loss": 2.0525, + "step": 2190 + }, + { + "epoch": 0.08, + "learning_rate": 9.91817607021981e-06, + "loss": 2.2227, + "step": 2200 + }, + { + "epoch": 0.08, + "eval_loss": 1.9981184005737305, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 2200 + }, + { + "epoch": 0.08, + "learning_rate": 9.917804143266263e-06, + "loss": 2.0289, + "step": 2210 + }, + { + "epoch": 0.08, + "learning_rate": 9.917432216312716e-06, + "loss": 2.0327, + "step": 2220 + }, + { + "epoch": 0.08, + "learning_rate": 9.917060289359171e-06, + "loss": 2.0734, + "step": 2230 + }, + { + "epoch": 0.08, + "learning_rate": 9.916688362405625e-06, + "loss": 2.2529, + "step": 2240 + }, + { + "epoch": 0.08, + "learning_rate": 9.916316435452078e-06, + "loss": 2.1185, + "step": 2250 + }, + { + "epoch": 0.08, + "learning_rate": 9.915944508498532e-06, + "loss": 2.0257, + "step": 2260 + }, + { + "epoch": 0.08, + "learning_rate": 9.915572581544985e-06, + "loss": 2.028, + "step": 2270 + }, + { + "epoch": 0.08, + "learning_rate": 9.915200654591439e-06, + "loss": 1.9844, + "step": 2280 + }, + { + "epoch": 0.09, + "learning_rate": 9.914828727637894e-06, + "loss": 2.1085, + "step": 2290 + }, + { + "epoch": 0.09, + "learning_rate": 9.914456800684347e-06, + "loss": 2.0831, + "step": 2300 + }, + { + "epoch": 0.09, + "eval_loss": 2.0069336891174316, + "eval_runtime": 16.8545, + "eval_samples_per_second": 59.331, + "eval_steps_per_second": 3.738, + "step": 2300 + }, + { + "epoch": 0.09, + "learning_rate": 9.9140848737308e-06, + "loss": 2.0853, + "step": 2310 + }, + { + "epoch": 0.09, + "learning_rate": 9.913712946777254e-06, + "loss": 2.0553, + "step": 2320 + }, + { + "epoch": 0.09, + "learning_rate": 9.913341019823708e-06, + "loss": 2.1851, + "step": 2330 + }, + { + "epoch": 0.09, + "learning_rate": 9.912969092870161e-06, + "loss": 2.0729, + "step": 2340 + }, + { + "epoch": 0.09, + "learning_rate": 9.912597165916615e-06, + "loss": 1.9086, + "step": 2350 + }, + { + "epoch": 0.09, + "learning_rate": 9.912225238963068e-06, + "loss": 2.0589, + "step": 2360 + }, + { + "epoch": 0.09, + "learning_rate": 9.911853312009521e-06, + "loss": 2.126, + "step": 2370 + }, + { + "epoch": 0.09, + "learning_rate": 9.911481385055975e-06, + "loss": 2.0638, + "step": 2380 + }, + { + "epoch": 0.09, + "learning_rate": 9.911109458102428e-06, + "loss": 2.0589, + "step": 2390 + }, + { + "epoch": 0.09, + "learning_rate": 9.910737531148884e-06, + "loss": 2.1017, + "step": 2400 + }, + { + "epoch": 0.09, + "eval_loss": 1.9943194389343262, + "eval_runtime": 16.836, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 2400 + }, + { + "epoch": 0.09, + "learning_rate": 9.910365604195337e-06, + "loss": 2.0899, + "step": 2410 + }, + { + "epoch": 0.09, + "learning_rate": 9.90999367724179e-06, + "loss": 2.094, + "step": 2420 + }, + { + "epoch": 0.09, + "learning_rate": 9.909621750288244e-06, + "loss": 2.0716, + "step": 2430 + }, + { + "epoch": 0.09, + "learning_rate": 9.909249823334697e-06, + "loss": 2.0112, + "step": 2440 + }, + { + "epoch": 0.09, + "learning_rate": 9.90887789638115e-06, + "loss": 2.005, + "step": 2450 + }, + { + "epoch": 0.09, + "learning_rate": 9.908505969427606e-06, + "loss": 2.1492, + "step": 2460 + }, + { + "epoch": 0.09, + "learning_rate": 9.90813404247406e-06, + "loss": 1.9881, + "step": 2470 + }, + { + "epoch": 0.09, + "learning_rate": 9.907762115520513e-06, + "loss": 2.0611, + "step": 2480 + }, + { + "epoch": 0.09, + "learning_rate": 9.907390188566966e-06, + "loss": 2.1282, + "step": 2490 + }, + { + "epoch": 0.09, + "learning_rate": 9.90701826161342e-06, + "loss": 1.891, + "step": 2500 + }, + { + "epoch": 0.09, + "eval_loss": 1.9879616498947144, + "eval_runtime": 16.8299, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 2500 + }, + { + "epoch": 0.09, + "learning_rate": 9.906646334659873e-06, + "loss": 2.1076, + "step": 2510 + }, + { + "epoch": 0.09, + "learning_rate": 9.906274407706328e-06, + "loss": 2.1421, + "step": 2520 + }, + { + "epoch": 0.09, + "learning_rate": 9.905902480752782e-06, + "loss": 2.0143, + "step": 2530 + }, + { + "epoch": 0.09, + "learning_rate": 9.905530553799234e-06, + "loss": 1.9922, + "step": 2540 + }, + { + "epoch": 0.09, + "learning_rate": 9.905158626845687e-06, + "loss": 2.1349, + "step": 2550 + }, + { + "epoch": 0.1, + "learning_rate": 9.904786699892142e-06, + "loss": 2.1105, + "step": 2560 + }, + { + "epoch": 0.1, + "learning_rate": 9.904414772938596e-06, + "loss": 2.1753, + "step": 2570 + }, + { + "epoch": 0.1, + "learning_rate": 9.90404284598505e-06, + "loss": 2.106, + "step": 2580 + }, + { + "epoch": 0.1, + "learning_rate": 9.903670919031503e-06, + "loss": 1.9762, + "step": 2590 + }, + { + "epoch": 0.1, + "learning_rate": 9.903298992077956e-06, + "loss": 2.0112, + "step": 2600 + }, + { + "epoch": 0.1, + "eval_loss": 1.9715689420700073, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 2600 + }, + { + "epoch": 0.1, + "learning_rate": 9.90292706512441e-06, + "loss": 2.0119, + "step": 2610 + }, + { + "epoch": 0.1, + "learning_rate": 9.902555138170865e-06, + "loss": 2.0999, + "step": 2620 + }, + { + "epoch": 0.1, + "learning_rate": 9.902183211217318e-06, + "loss": 2.0154, + "step": 2630 + }, + { + "epoch": 0.1, + "learning_rate": 9.901811284263772e-06, + "loss": 2.0698, + "step": 2640 + }, + { + "epoch": 0.1, + "learning_rate": 9.901439357310225e-06, + "loss": 1.9999, + "step": 2650 + }, + { + "epoch": 0.1, + "learning_rate": 9.901067430356679e-06, + "loss": 2.0175, + "step": 2660 + }, + { + "epoch": 0.1, + "learning_rate": 9.900695503403132e-06, + "loss": 2.0891, + "step": 2670 + }, + { + "epoch": 0.1, + "learning_rate": 9.900323576449587e-06, + "loss": 2.0225, + "step": 2680 + }, + { + "epoch": 0.1, + "learning_rate": 9.89995164949604e-06, + "loss": 2.0925, + "step": 2690 + }, + { + "epoch": 0.1, + "learning_rate": 9.899579722542494e-06, + "loss": 2.0952, + "step": 2700 + }, + { + "epoch": 0.1, + "eval_loss": 1.9811919927597046, + "eval_runtime": 16.8303, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 2700 + }, + { + "epoch": 0.1, + "learning_rate": 9.899207795588948e-06, + "loss": 2.1467, + "step": 2710 + }, + { + "epoch": 0.1, + "learning_rate": 9.898835868635401e-06, + "loss": 2.0246, + "step": 2720 + }, + { + "epoch": 0.1, + "learning_rate": 9.898463941681854e-06, + "loss": 2.0171, + "step": 2730 + }, + { + "epoch": 0.1, + "learning_rate": 9.898092014728308e-06, + "loss": 1.9908, + "step": 2740 + }, + { + "epoch": 0.1, + "learning_rate": 9.897720087774761e-06, + "loss": 2.1182, + "step": 2750 + }, + { + "epoch": 0.1, + "learning_rate": 9.897348160821215e-06, + "loss": 2.1706, + "step": 2760 + }, + { + "epoch": 0.1, + "learning_rate": 9.896976233867668e-06, + "loss": 1.9075, + "step": 2770 + }, + { + "epoch": 0.1, + "learning_rate": 9.896604306914123e-06, + "loss": 2.1133, + "step": 2780 + }, + { + "epoch": 0.1, + "learning_rate": 9.896232379960577e-06, + "loss": 2.2064, + "step": 2790 + }, + { + "epoch": 0.1, + "learning_rate": 9.89586045300703e-06, + "loss": 1.9835, + "step": 2800 + }, + { + "epoch": 0.1, + "eval_loss": 1.9721286296844482, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 2800 + }, + { + "epoch": 0.1, + "learning_rate": 9.895488526053484e-06, + "loss": 1.9549, + "step": 2810 + }, + { + "epoch": 0.1, + "learning_rate": 9.895116599099937e-06, + "loss": 2.0606, + "step": 2820 + }, + { + "epoch": 0.11, + "learning_rate": 9.89474467214639e-06, + "loss": 2.0762, + "step": 2830 + }, + { + "epoch": 0.11, + "learning_rate": 9.894372745192846e-06, + "loss": 2.1925, + "step": 2840 + }, + { + "epoch": 0.11, + "learning_rate": 9.8940008182393e-06, + "loss": 2.0178, + "step": 2850 + }, + { + "epoch": 0.11, + "learning_rate": 9.893628891285753e-06, + "loss": 2.1136, + "step": 2860 + }, + { + "epoch": 0.11, + "learning_rate": 9.893256964332206e-06, + "loss": 1.9453, + "step": 2870 + }, + { + "epoch": 0.11, + "learning_rate": 9.89288503737866e-06, + "loss": 2.1051, + "step": 2880 + }, + { + "epoch": 0.11, + "learning_rate": 9.892513110425113e-06, + "loss": 1.9757, + "step": 2890 + }, + { + "epoch": 0.11, + "learning_rate": 9.892141183471567e-06, + "loss": 2.0505, + "step": 2900 + }, + { + "epoch": 0.11, + "eval_loss": 1.9705374240875244, + "eval_runtime": 16.8107, + "eval_samples_per_second": 59.486, + "eval_steps_per_second": 3.748, + "step": 2900 + }, + { + "epoch": 0.11, + "learning_rate": 9.891769256518022e-06, + "loss": 2.0333, + "step": 2910 + }, + { + "epoch": 0.11, + "learning_rate": 9.891397329564474e-06, + "loss": 2.0407, + "step": 2920 + }, + { + "epoch": 0.11, + "learning_rate": 9.891025402610927e-06, + "loss": 2.085, + "step": 2930 + }, + { + "epoch": 0.11, + "learning_rate": 9.89065347565738e-06, + "loss": 1.9987, + "step": 2940 + }, + { + "epoch": 0.11, + "learning_rate": 9.890281548703836e-06, + "loss": 1.9486, + "step": 2950 + }, + { + "epoch": 0.11, + "learning_rate": 9.889909621750289e-06, + "loss": 2.0357, + "step": 2960 + }, + { + "epoch": 0.11, + "learning_rate": 9.889537694796743e-06, + "loss": 1.9693, + "step": 2970 + }, + { + "epoch": 0.11, + "learning_rate": 9.889165767843196e-06, + "loss": 1.9722, + "step": 2980 + }, + { + "epoch": 0.11, + "learning_rate": 9.88879384088965e-06, + "loss": 2.1225, + "step": 2990 + }, + { + "epoch": 0.11, + "learning_rate": 9.888421913936103e-06, + "loss": 2.0883, + "step": 3000 + }, + { + "epoch": 0.11, + "eval_loss": 1.9732450246810913, + "eval_runtime": 16.8357, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 3000 + }, + { + "epoch": 0.11, + "learning_rate": 9.888049986982558e-06, + "loss": 1.9756, + "step": 3010 + }, + { + "epoch": 0.11, + "learning_rate": 9.887678060029012e-06, + "loss": 2.0282, + "step": 3020 + }, + { + "epoch": 0.11, + "learning_rate": 9.887306133075465e-06, + "loss": 2.1421, + "step": 3030 + }, + { + "epoch": 0.11, + "learning_rate": 9.886934206121918e-06, + "loss": 1.9579, + "step": 3040 + }, + { + "epoch": 0.11, + "learning_rate": 9.886562279168372e-06, + "loss": 2.041, + "step": 3050 + }, + { + "epoch": 0.11, + "learning_rate": 9.886190352214825e-06, + "loss": 1.9177, + "step": 3060 + }, + { + "epoch": 0.11, + "learning_rate": 9.88581842526128e-06, + "loss": 2.036, + "step": 3070 + }, + { + "epoch": 0.11, + "learning_rate": 9.885446498307734e-06, + "loss": 1.9655, + "step": 3080 + }, + { + "epoch": 0.11, + "learning_rate": 9.885074571354187e-06, + "loss": 2.0324, + "step": 3090 + }, + { + "epoch": 0.12, + "learning_rate": 9.88470264440064e-06, + "loss": 1.9806, + "step": 3100 + }, + { + "epoch": 0.12, + "eval_loss": 1.9621933698654175, + "eval_runtime": 16.8243, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 3100 + }, + { + "epoch": 0.12, + "learning_rate": 9.884330717447094e-06, + "loss": 2.145, + "step": 3110 + }, + { + "epoch": 0.12, + "learning_rate": 9.883958790493548e-06, + "loss": 2.0649, + "step": 3120 + }, + { + "epoch": 0.12, + "learning_rate": 9.883586863540001e-06, + "loss": 2.0173, + "step": 3130 + }, + { + "epoch": 0.12, + "learning_rate": 9.883214936586455e-06, + "loss": 2.0104, + "step": 3140 + }, + { + "epoch": 0.12, + "learning_rate": 9.882843009632908e-06, + "loss": 1.9858, + "step": 3150 + }, + { + "epoch": 0.12, + "learning_rate": 9.882471082679362e-06, + "loss": 2.1752, + "step": 3160 + }, + { + "epoch": 0.12, + "learning_rate": 9.882099155725817e-06, + "loss": 2.1013, + "step": 3170 + }, + { + "epoch": 0.12, + "learning_rate": 9.88172722877227e-06, + "loss": 2.1175, + "step": 3180 + }, + { + "epoch": 0.12, + "learning_rate": 9.881355301818724e-06, + "loss": 2.0764, + "step": 3190 + }, + { + "epoch": 0.12, + "learning_rate": 9.880983374865177e-06, + "loss": 2.0962, + "step": 3200 + }, + { + "epoch": 0.12, + "eval_loss": 1.959442377090454, + "eval_runtime": 16.8337, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 3200 + }, + { + "epoch": 0.12, + "learning_rate": 9.88061144791163e-06, + "loss": 2.1563, + "step": 3210 + }, + { + "epoch": 0.12, + "learning_rate": 9.880239520958084e-06, + "loss": 1.998, + "step": 3220 + }, + { + "epoch": 0.12, + "learning_rate": 9.87986759400454e-06, + "loss": 2.0864, + "step": 3230 + }, + { + "epoch": 0.12, + "learning_rate": 9.879495667050993e-06, + "loss": 2.1352, + "step": 3240 + }, + { + "epoch": 0.12, + "learning_rate": 9.879123740097446e-06, + "loss": 2.0018, + "step": 3250 + }, + { + "epoch": 0.12, + "learning_rate": 9.8787518131439e-06, + "loss": 1.9288, + "step": 3260 + }, + { + "epoch": 0.12, + "learning_rate": 9.878379886190353e-06, + "loss": 1.9761, + "step": 3270 + }, + { + "epoch": 0.12, + "learning_rate": 9.878007959236807e-06, + "loss": 2.0486, + "step": 3280 + }, + { + "epoch": 0.12, + "learning_rate": 9.87763603228326e-06, + "loss": 1.8714, + "step": 3290 + }, + { + "epoch": 0.12, + "learning_rate": 9.877264105329713e-06, + "loss": 2.1508, + "step": 3300 + }, + { + "epoch": 0.12, + "eval_loss": 1.9481189250946045, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 3300 + }, + { + "epoch": 0.12, + "learning_rate": 9.876892178376167e-06, + "loss": 1.9742, + "step": 3310 + }, + { + "epoch": 0.12, + "learning_rate": 9.87652025142262e-06, + "loss": 1.9033, + "step": 3320 + }, + { + "epoch": 0.12, + "learning_rate": 9.876148324469076e-06, + "loss": 1.9479, + "step": 3330 + }, + { + "epoch": 0.12, + "learning_rate": 9.875776397515529e-06, + "loss": 2.1927, + "step": 3340 + }, + { + "epoch": 0.12, + "learning_rate": 9.875404470561982e-06, + "loss": 2.1926, + "step": 3350 + }, + { + "epoch": 0.12, + "learning_rate": 9.875032543608436e-06, + "loss": 1.9195, + "step": 3360 + }, + { + "epoch": 0.13, + "learning_rate": 9.87466061665489e-06, + "loss": 1.9323, + "step": 3370 + }, + { + "epoch": 0.13, + "learning_rate": 9.874288689701343e-06, + "loss": 1.9957, + "step": 3380 + }, + { + "epoch": 0.13, + "learning_rate": 9.873916762747798e-06, + "loss": 2.1192, + "step": 3390 + }, + { + "epoch": 0.13, + "learning_rate": 9.873544835794251e-06, + "loss": 2.0201, + "step": 3400 + }, + { + "epoch": 0.13, + "eval_loss": 1.9522182941436768, + "eval_runtime": 16.8246, + "eval_samples_per_second": 59.437, + "eval_steps_per_second": 3.745, + "step": 3400 + }, + { + "epoch": 0.13, + "learning_rate": 9.873172908840705e-06, + "loss": 2.2182, + "step": 3410 + }, + { + "epoch": 0.13, + "learning_rate": 9.872800981887158e-06, + "loss": 1.9313, + "step": 3420 + }, + { + "epoch": 0.13, + "learning_rate": 9.872429054933612e-06, + "loss": 2.0371, + "step": 3430 + }, + { + "epoch": 0.13, + "learning_rate": 9.872057127980065e-06, + "loss": 1.9896, + "step": 3440 + }, + { + "epoch": 0.13, + "learning_rate": 9.87168520102652e-06, + "loss": 1.9921, + "step": 3450 + }, + { + "epoch": 0.13, + "learning_rate": 9.871313274072974e-06, + "loss": 2.0575, + "step": 3460 + }, + { + "epoch": 0.13, + "learning_rate": 9.870941347119427e-06, + "loss": 2.0386, + "step": 3470 + }, + { + "epoch": 0.13, + "learning_rate": 9.870569420165879e-06, + "loss": 1.9216, + "step": 3480 + }, + { + "epoch": 0.13, + "learning_rate": 9.870197493212333e-06, + "loss": 2.0783, + "step": 3490 + }, + { + "epoch": 0.13, + "learning_rate": 9.869825566258788e-06, + "loss": 1.9807, + "step": 3500 + }, + { + "epoch": 0.13, + "eval_loss": 1.944342017173767, + "eval_runtime": 16.8402, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 3500 + }, + { + "epoch": 0.13, + "learning_rate": 9.869453639305241e-06, + "loss": 2.0455, + "step": 3510 + }, + { + "epoch": 0.13, + "learning_rate": 9.869081712351695e-06, + "loss": 1.9546, + "step": 3520 + }, + { + "epoch": 0.13, + "learning_rate": 9.868709785398148e-06, + "loss": 2.0597, + "step": 3530 + }, + { + "epoch": 0.13, + "learning_rate": 9.868337858444602e-06, + "loss": 2.0842, + "step": 3540 + }, + { + "epoch": 0.13, + "learning_rate": 9.867965931491055e-06, + "loss": 2.0452, + "step": 3550 + }, + { + "epoch": 0.13, + "learning_rate": 9.86759400453751e-06, + "loss": 2.108, + "step": 3560 + }, + { + "epoch": 0.13, + "learning_rate": 9.867222077583964e-06, + "loss": 2.1205, + "step": 3570 + }, + { + "epoch": 0.13, + "learning_rate": 9.866850150630417e-06, + "loss": 2.0624, + "step": 3580 + }, + { + "epoch": 0.13, + "learning_rate": 9.86647822367687e-06, + "loss": 2.117, + "step": 3590 + }, + { + "epoch": 0.13, + "learning_rate": 9.866106296723324e-06, + "loss": 2.0119, + "step": 3600 + }, + { + "epoch": 0.13, + "eval_loss": 1.94246244430542, + "eval_runtime": 16.8303, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 3600 + }, + { + "epoch": 0.13, + "learning_rate": 9.865734369769778e-06, + "loss": 2.0083, + "step": 3610 + }, + { + "epoch": 0.13, + "learning_rate": 9.865362442816233e-06, + "loss": 2.067, + "step": 3620 + }, + { + "epoch": 0.14, + "learning_rate": 9.864990515862686e-06, + "loss": 1.947, + "step": 3630 + }, + { + "epoch": 0.14, + "learning_rate": 9.86461858890914e-06, + "loss": 2.0286, + "step": 3640 + }, + { + "epoch": 0.14, + "learning_rate": 9.864246661955593e-06, + "loss": 2.2124, + "step": 3650 + }, + { + "epoch": 0.14, + "learning_rate": 9.863874735002046e-06, + "loss": 2.0814, + "step": 3660 + }, + { + "epoch": 0.14, + "learning_rate": 9.8635028080485e-06, + "loss": 2.1467, + "step": 3670 + }, + { + "epoch": 0.14, + "learning_rate": 9.863130881094953e-06, + "loss": 2.043, + "step": 3680 + }, + { + "epoch": 0.14, + "learning_rate": 9.862758954141407e-06, + "loss": 1.9248, + "step": 3690 + }, + { + "epoch": 0.14, + "learning_rate": 9.86238702718786e-06, + "loss": 2.0956, + "step": 3700 + }, + { + "epoch": 0.14, + "eval_loss": 1.9371663331985474, + "eval_runtime": 16.826, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 3700 + }, + { + "epoch": 0.14, + "learning_rate": 9.862015100234314e-06, + "loss": 1.9403, + "step": 3710 + }, + { + "epoch": 0.14, + "learning_rate": 9.861643173280769e-06, + "loss": 2.067, + "step": 3720 + }, + { + "epoch": 0.14, + "learning_rate": 9.861271246327222e-06, + "loss": 1.9781, + "step": 3730 + }, + { + "epoch": 0.14, + "learning_rate": 9.860899319373676e-06, + "loss": 2.0204, + "step": 3740 + }, + { + "epoch": 0.14, + "learning_rate": 9.86052739242013e-06, + "loss": 2.0511, + "step": 3750 + }, + { + "epoch": 0.14, + "learning_rate": 9.860155465466583e-06, + "loss": 2.0486, + "step": 3760 + }, + { + "epoch": 0.14, + "learning_rate": 9.859783538513036e-06, + "loss": 2.0433, + "step": 3770 + }, + { + "epoch": 0.14, + "learning_rate": 9.859411611559491e-06, + "loss": 2.0397, + "step": 3780 + }, + { + "epoch": 0.14, + "learning_rate": 9.859039684605945e-06, + "loss": 2.0406, + "step": 3790 + }, + { + "epoch": 0.14, + "learning_rate": 9.858667757652398e-06, + "loss": 2.0023, + "step": 3800 + }, + { + "epoch": 0.14, + "eval_loss": 1.9379023313522339, + "eval_runtime": 16.8338, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 3800 + }, + { + "epoch": 0.14, + "learning_rate": 9.858295830698852e-06, + "loss": 2.281, + "step": 3810 + }, + { + "epoch": 0.14, + "learning_rate": 9.857923903745305e-06, + "loss": 2.0962, + "step": 3820 + }, + { + "epoch": 0.14, + "learning_rate": 9.857551976791759e-06, + "loss": 2.1421, + "step": 3830 + }, + { + "epoch": 0.14, + "learning_rate": 9.857180049838214e-06, + "loss": 2.0722, + "step": 3840 + }, + { + "epoch": 0.14, + "learning_rate": 9.856808122884666e-06, + "loss": 2.0503, + "step": 3850 + }, + { + "epoch": 0.14, + "learning_rate": 9.856436195931119e-06, + "loss": 2.1348, + "step": 3860 + }, + { + "epoch": 0.14, + "learning_rate": 9.856064268977573e-06, + "loss": 2.0629, + "step": 3870 + }, + { + "epoch": 0.14, + "learning_rate": 9.855692342024028e-06, + "loss": 2.0942, + "step": 3880 + }, + { + "epoch": 0.14, + "learning_rate": 9.855320415070481e-06, + "loss": 1.9819, + "step": 3890 + }, + { + "epoch": 0.15, + "learning_rate": 9.854948488116935e-06, + "loss": 2.0076, + "step": 3900 + }, + { + "epoch": 0.15, + "eval_loss": 1.933185338973999, + "eval_runtime": 16.8303, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 3900 + }, + { + "epoch": 0.15, + "learning_rate": 9.854576561163388e-06, + "loss": 2.0579, + "step": 3910 + }, + { + "epoch": 0.15, + "learning_rate": 9.854204634209842e-06, + "loss": 2.0622, + "step": 3920 + }, + { + "epoch": 0.15, + "learning_rate": 9.853832707256295e-06, + "loss": 2.0098, + "step": 3930 + }, + { + "epoch": 0.15, + "learning_rate": 9.85346078030275e-06, + "loss": 2.0697, + "step": 3940 + }, + { + "epoch": 0.15, + "learning_rate": 9.853088853349204e-06, + "loss": 2.0872, + "step": 3950 + }, + { + "epoch": 0.15, + "learning_rate": 9.852716926395657e-06, + "loss": 1.9855, + "step": 3960 + }, + { + "epoch": 0.15, + "learning_rate": 9.85234499944211e-06, + "loss": 2.102, + "step": 3970 + }, + { + "epoch": 0.15, + "learning_rate": 9.851973072488564e-06, + "loss": 2.128, + "step": 3980 + }, + { + "epoch": 0.15, + "learning_rate": 9.851601145535017e-06, + "loss": 1.993, + "step": 3990 + }, + { + "epoch": 0.15, + "learning_rate": 9.851229218581473e-06, + "loss": 2.0998, + "step": 4000 + }, + { + "epoch": 0.15, + "eval_loss": 1.9302043914794922, + "eval_runtime": 16.8299, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 4000 + }, + { + "epoch": 0.15, + "learning_rate": 9.850857291627926e-06, + "loss": 2.0054, + "step": 4010 + }, + { + "epoch": 0.15, + "learning_rate": 9.85048536467438e-06, + "loss": 1.9661, + "step": 4020 + }, + { + "epoch": 0.15, + "learning_rate": 9.850113437720833e-06, + "loss": 1.9283, + "step": 4030 + }, + { + "epoch": 0.15, + "learning_rate": 9.849741510767286e-06, + "loss": 2.1524, + "step": 4040 + }, + { + "epoch": 0.15, + "learning_rate": 9.84936958381374e-06, + "loss": 2.2004, + "step": 4050 + }, + { + "epoch": 0.15, + "learning_rate": 9.848997656860193e-06, + "loss": 1.9404, + "step": 4060 + }, + { + "epoch": 0.15, + "learning_rate": 9.848625729906647e-06, + "loss": 1.968, + "step": 4070 + }, + { + "epoch": 0.15, + "learning_rate": 9.8482538029531e-06, + "loss": 2.0188, + "step": 4080 + }, + { + "epoch": 0.15, + "learning_rate": 9.847881875999554e-06, + "loss": 1.9749, + "step": 4090 + }, + { + "epoch": 0.15, + "learning_rate": 9.847509949046007e-06, + "loss": 2.0155, + "step": 4100 + }, + { + "epoch": 0.15, + "eval_loss": 1.927007794380188, + "eval_runtime": 16.8376, + "eval_samples_per_second": 59.391, + "eval_steps_per_second": 3.742, + "step": 4100 + }, + { + "epoch": 0.15, + "learning_rate": 9.847138022092462e-06, + "loss": 1.8884, + "step": 4110 + }, + { + "epoch": 0.15, + "learning_rate": 9.846766095138916e-06, + "loss": 2.0067, + "step": 4120 + }, + { + "epoch": 0.15, + "learning_rate": 9.84639416818537e-06, + "loss": 2.1435, + "step": 4130 + }, + { + "epoch": 0.15, + "learning_rate": 9.846022241231823e-06, + "loss": 2.0163, + "step": 4140 + }, + { + "epoch": 0.15, + "learning_rate": 9.845650314278276e-06, + "loss": 2.0201, + "step": 4150 + }, + { + "epoch": 0.15, + "learning_rate": 9.84527838732473e-06, + "loss": 2.0199, + "step": 4160 + }, + { + "epoch": 0.16, + "learning_rate": 9.844906460371185e-06, + "loss": 2.0061, + "step": 4170 + }, + { + "epoch": 0.16, + "learning_rate": 9.844534533417638e-06, + "loss": 2.0336, + "step": 4180 + }, + { + "epoch": 0.16, + "learning_rate": 9.844162606464092e-06, + "loss": 2.058, + "step": 4190 + }, + { + "epoch": 0.16, + "learning_rate": 9.843790679510545e-06, + "loss": 2.2712, + "step": 4200 + }, + { + "epoch": 0.16, + "eval_loss": 1.9237558841705322, + "eval_runtime": 16.847, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 4200 + }, + { + "epoch": 0.16, + "learning_rate": 9.843418752556999e-06, + "loss": 2.1402, + "step": 4210 + }, + { + "epoch": 0.16, + "learning_rate": 9.843046825603452e-06, + "loss": 2.0155, + "step": 4220 + }, + { + "epoch": 0.16, + "learning_rate": 9.842674898649906e-06, + "loss": 1.8526, + "step": 4230 + }, + { + "epoch": 0.16, + "learning_rate": 9.842302971696359e-06, + "loss": 2.0003, + "step": 4240 + }, + { + "epoch": 0.16, + "learning_rate": 9.841931044742812e-06, + "loss": 2.0294, + "step": 4250 + }, + { + "epoch": 0.16, + "learning_rate": 9.841559117789266e-06, + "loss": 2.0249, + "step": 4260 + }, + { + "epoch": 0.16, + "learning_rate": 9.841187190835721e-06, + "loss": 1.9468, + "step": 4270 + }, + { + "epoch": 0.16, + "learning_rate": 9.840815263882175e-06, + "loss": 1.8496, + "step": 4280 + }, + { + "epoch": 0.16, + "learning_rate": 9.840443336928628e-06, + "loss": 1.9572, + "step": 4290 + }, + { + "epoch": 0.16, + "learning_rate": 9.840071409975081e-06, + "loss": 2.0045, + "step": 4300 + }, + { + "epoch": 0.16, + "eval_loss": 1.9251017570495605, + "eval_runtime": 16.832, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 4300 + }, + { + "epoch": 0.16, + "learning_rate": 9.839699483021535e-06, + "loss": 2.0248, + "step": 4310 + }, + { + "epoch": 0.16, + "learning_rate": 9.839327556067988e-06, + "loss": 2.0397, + "step": 4320 + }, + { + "epoch": 0.16, + "learning_rate": 9.838955629114444e-06, + "loss": 2.0032, + "step": 4330 + }, + { + "epoch": 0.16, + "learning_rate": 9.838583702160897e-06, + "loss": 2.0939, + "step": 4340 + }, + { + "epoch": 0.16, + "learning_rate": 9.83821177520735e-06, + "loss": 1.9474, + "step": 4350 + }, + { + "epoch": 0.16, + "learning_rate": 9.837839848253804e-06, + "loss": 2.177, + "step": 4360 + }, + { + "epoch": 0.16, + "learning_rate": 9.837467921300257e-06, + "loss": 2.0608, + "step": 4370 + }, + { + "epoch": 0.16, + "learning_rate": 9.83709599434671e-06, + "loss": 2.0217, + "step": 4380 + }, + { + "epoch": 0.16, + "learning_rate": 9.836724067393166e-06, + "loss": 1.897, + "step": 4390 + }, + { + "epoch": 0.16, + "learning_rate": 9.83635214043962e-06, + "loss": 2.0266, + "step": 4400 + }, + { + "epoch": 0.16, + "eval_loss": 1.921541452407837, + "eval_runtime": 16.8285, + "eval_samples_per_second": 59.423, + "eval_steps_per_second": 3.744, + "step": 4400 + }, + { + "epoch": 0.16, + "learning_rate": 9.835980213486073e-06, + "loss": 1.9881, + "step": 4410 + }, + { + "epoch": 0.16, + "learning_rate": 9.835608286532525e-06, + "loss": 1.9673, + "step": 4420 + }, + { + "epoch": 0.16, + "learning_rate": 9.83523635957898e-06, + "loss": 2.0031, + "step": 4430 + }, + { + "epoch": 0.17, + "learning_rate": 9.834864432625433e-06, + "loss": 1.8846, + "step": 4440 + }, + { + "epoch": 0.17, + "learning_rate": 9.834492505671887e-06, + "loss": 2.0923, + "step": 4450 + }, + { + "epoch": 0.17, + "learning_rate": 9.83412057871834e-06, + "loss": 1.9709, + "step": 4460 + }, + { + "epoch": 0.17, + "learning_rate": 9.833748651764794e-06, + "loss": 2.0195, + "step": 4470 + }, + { + "epoch": 0.17, + "learning_rate": 9.833376724811247e-06, + "loss": 2.0835, + "step": 4480 + }, + { + "epoch": 0.17, + "learning_rate": 9.833004797857702e-06, + "loss": 2.264, + "step": 4490 + }, + { + "epoch": 0.17, + "learning_rate": 9.832632870904156e-06, + "loss": 1.8623, + "step": 4500 + }, + { + "epoch": 0.17, + "eval_loss": 1.9191681146621704, + "eval_runtime": 16.8323, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 4500 + }, + { + "epoch": 0.17, + "learning_rate": 9.83226094395061e-06, + "loss": 2.0829, + "step": 4510 + }, + { + "epoch": 0.17, + "learning_rate": 9.831889016997063e-06, + "loss": 1.9569, + "step": 4520 + }, + { + "epoch": 0.17, + "learning_rate": 9.831517090043516e-06, + "loss": 2.054, + "step": 4530 + }, + { + "epoch": 0.17, + "learning_rate": 9.83114516308997e-06, + "loss": 1.9547, + "step": 4540 + }, + { + "epoch": 0.17, + "learning_rate": 9.830773236136425e-06, + "loss": 1.9291, + "step": 4550 + }, + { + "epoch": 0.17, + "learning_rate": 9.830401309182878e-06, + "loss": 1.9591, + "step": 4560 + }, + { + "epoch": 0.17, + "learning_rate": 9.830029382229332e-06, + "loss": 2.1235, + "step": 4570 + }, + { + "epoch": 0.17, + "learning_rate": 9.829657455275785e-06, + "loss": 1.8917, + "step": 4580 + }, + { + "epoch": 0.17, + "learning_rate": 9.829285528322239e-06, + "loss": 1.9812, + "step": 4590 + }, + { + "epoch": 0.17, + "learning_rate": 9.828913601368692e-06, + "loss": 2.1646, + "step": 4600 + }, + { + "epoch": 0.17, + "eval_loss": 1.9193947315216064, + "eval_runtime": 16.8487, + "eval_samples_per_second": 59.352, + "eval_steps_per_second": 3.739, + "step": 4600 + }, + { + "epoch": 0.17, + "learning_rate": 9.828541674415145e-06, + "loss": 2.0164, + "step": 4610 + }, + { + "epoch": 0.17, + "learning_rate": 9.828169747461599e-06, + "loss": 2.0248, + "step": 4620 + }, + { + "epoch": 0.17, + "learning_rate": 9.827797820508052e-06, + "loss": 1.9374, + "step": 4630 + }, + { + "epoch": 0.17, + "learning_rate": 9.827425893554506e-06, + "loss": 2.0366, + "step": 4640 + }, + { + "epoch": 0.17, + "learning_rate": 9.82705396660096e-06, + "loss": 1.9934, + "step": 4650 + }, + { + "epoch": 0.17, + "learning_rate": 9.826682039647414e-06, + "loss": 1.8741, + "step": 4660 + }, + { + "epoch": 0.17, + "learning_rate": 9.826310112693868e-06, + "loss": 2.0398, + "step": 4670 + }, + { + "epoch": 0.17, + "learning_rate": 9.825938185740321e-06, + "loss": 2.0354, + "step": 4680 + }, + { + "epoch": 0.17, + "learning_rate": 9.825566258786775e-06, + "loss": 2.1191, + "step": 4690 + }, + { + "epoch": 0.17, + "learning_rate": 9.825194331833228e-06, + "loss": 1.9351, + "step": 4700 + }, + { + "epoch": 0.17, + "eval_loss": 1.919795036315918, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 4700 + }, + { + "epoch": 0.18, + "learning_rate": 9.824822404879682e-06, + "loss": 1.9547, + "step": 4710 + }, + { + "epoch": 0.18, + "learning_rate": 9.824450477926137e-06, + "loss": 2.0801, + "step": 4720 + }, + { + "epoch": 0.18, + "learning_rate": 9.82407855097259e-06, + "loss": 2.0242, + "step": 4730 + }, + { + "epoch": 0.18, + "learning_rate": 9.823706624019044e-06, + "loss": 2.0567, + "step": 4740 + }, + { + "epoch": 0.18, + "learning_rate": 9.823334697065497e-06, + "loss": 1.955, + "step": 4750 + }, + { + "epoch": 0.18, + "learning_rate": 9.82296277011195e-06, + "loss": 2.1442, + "step": 4760 + }, + { + "epoch": 0.18, + "learning_rate": 9.822590843158404e-06, + "loss": 1.8734, + "step": 4770 + }, + { + "epoch": 0.18, + "learning_rate": 9.82221891620486e-06, + "loss": 1.9236, + "step": 4780 + }, + { + "epoch": 0.18, + "learning_rate": 9.821846989251311e-06, + "loss": 1.9737, + "step": 4790 + }, + { + "epoch": 0.18, + "learning_rate": 9.821475062297765e-06, + "loss": 1.9223, + "step": 4800 + }, + { + "epoch": 0.18, + "eval_loss": 1.9221227169036865, + "eval_runtime": 16.8337, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.742, + "step": 4800 + }, + { + "epoch": 0.18, + "learning_rate": 9.821103135344218e-06, + "loss": 1.9653, + "step": 4810 + }, + { + "epoch": 0.18, + "learning_rate": 9.820731208390673e-06, + "loss": 2.0168, + "step": 4820 + }, + { + "epoch": 0.18, + "learning_rate": 9.820359281437127e-06, + "loss": 1.9993, + "step": 4830 + }, + { + "epoch": 0.18, + "learning_rate": 9.81998735448358e-06, + "loss": 2.0576, + "step": 4840 + }, + { + "epoch": 0.18, + "learning_rate": 9.819615427530034e-06, + "loss": 1.9841, + "step": 4850 + }, + { + "epoch": 0.18, + "learning_rate": 9.819243500576487e-06, + "loss": 2.0298, + "step": 4860 + }, + { + "epoch": 0.18, + "learning_rate": 9.81887157362294e-06, + "loss": 1.9399, + "step": 4870 + }, + { + "epoch": 0.18, + "learning_rate": 9.818499646669396e-06, + "loss": 2.0899, + "step": 4880 + }, + { + "epoch": 0.18, + "learning_rate": 9.818127719715849e-06, + "loss": 2.0294, + "step": 4890 + }, + { + "epoch": 0.18, + "learning_rate": 9.817755792762303e-06, + "loss": 2.0776, + "step": 4900 + }, + { + "epoch": 0.18, + "eval_loss": 1.9141274690628052, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 4900 + }, + { + "epoch": 0.18, + "learning_rate": 9.817383865808756e-06, + "loss": 1.9424, + "step": 4910 + }, + { + "epoch": 0.18, + "learning_rate": 9.81701193885521e-06, + "loss": 1.9367, + "step": 4920 + }, + { + "epoch": 0.18, + "learning_rate": 9.816640011901663e-06, + "loss": 1.8644, + "step": 4930 + }, + { + "epoch": 0.18, + "learning_rate": 9.816268084948118e-06, + "loss": 2.0231, + "step": 4940 + }, + { + "epoch": 0.18, + "learning_rate": 9.815896157994572e-06, + "loss": 2.144, + "step": 4950 + }, + { + "epoch": 0.18, + "learning_rate": 9.815524231041025e-06, + "loss": 1.9173, + "step": 4960 + }, + { + "epoch": 0.18, + "learning_rate": 9.815152304087478e-06, + "loss": 1.9723, + "step": 4970 + }, + { + "epoch": 0.19, + "learning_rate": 9.814780377133932e-06, + "loss": 1.9573, + "step": 4980 + }, + { + "epoch": 0.19, + "learning_rate": 9.814408450180385e-06, + "loss": 1.9459, + "step": 4990 + }, + { + "epoch": 0.19, + "learning_rate": 9.814036523226839e-06, + "loss": 2.0508, + "step": 5000 + }, + { + "epoch": 0.19, + "eval_loss": 1.9126524925231934, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 5000 + }, + { + "epoch": 0.19, + "learning_rate": 9.813664596273292e-06, + "loss": 1.9793, + "step": 5010 + }, + { + "epoch": 0.19, + "learning_rate": 9.813292669319746e-06, + "loss": 2.1502, + "step": 5020 + }, + { + "epoch": 0.19, + "learning_rate": 9.8129207423662e-06, + "loss": 1.9677, + "step": 5030 + }, + { + "epoch": 0.19, + "learning_rate": 9.812548815412654e-06, + "loss": 1.8442, + "step": 5040 + }, + { + "epoch": 0.19, + "learning_rate": 9.812176888459108e-06, + "loss": 1.8811, + "step": 5050 + }, + { + "epoch": 0.19, + "learning_rate": 9.811804961505561e-06, + "loss": 1.966, + "step": 5060 + }, + { + "epoch": 0.19, + "learning_rate": 9.811433034552015e-06, + "loss": 1.8527, + "step": 5070 + }, + { + "epoch": 0.19, + "learning_rate": 9.811061107598468e-06, + "loss": 1.9843, + "step": 5080 + }, + { + "epoch": 0.19, + "learning_rate": 9.810689180644922e-06, + "loss": 2.1711, + "step": 5090 + }, + { + "epoch": 0.19, + "learning_rate": 9.810317253691377e-06, + "loss": 1.9888, + "step": 5100 + }, + { + "epoch": 0.19, + "eval_loss": 1.9115619659423828, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 5100 + }, + { + "epoch": 0.19, + "learning_rate": 9.80994532673783e-06, + "loss": 1.955, + "step": 5110 + }, + { + "epoch": 0.19, + "learning_rate": 9.809573399784284e-06, + "loss": 1.9913, + "step": 5120 + }, + { + "epoch": 0.19, + "learning_rate": 9.809201472830737e-06, + "loss": 2.0475, + "step": 5130 + }, + { + "epoch": 0.19, + "learning_rate": 9.80882954587719e-06, + "loss": 2.0179, + "step": 5140 + }, + { + "epoch": 0.19, + "learning_rate": 9.808457618923644e-06, + "loss": 2.0869, + "step": 5150 + }, + { + "epoch": 0.19, + "learning_rate": 9.8080856919701e-06, + "loss": 2.0244, + "step": 5160 + }, + { + "epoch": 0.19, + "learning_rate": 9.807713765016551e-06, + "loss": 1.9388, + "step": 5170 + }, + { + "epoch": 0.19, + "learning_rate": 9.807341838063004e-06, + "loss": 2.0594, + "step": 5180 + }, + { + "epoch": 0.19, + "learning_rate": 9.806969911109458e-06, + "loss": 1.9007, + "step": 5190 + }, + { + "epoch": 0.19, + "learning_rate": 9.806597984155913e-06, + "loss": 2.0339, + "step": 5200 + }, + { + "epoch": 0.19, + "eval_loss": 1.912042498588562, + "eval_runtime": 16.8331, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 5200 + }, + { + "epoch": 0.19, + "learning_rate": 9.806226057202367e-06, + "loss": 1.9673, + "step": 5210 + }, + { + "epoch": 0.19, + "learning_rate": 9.80585413024882e-06, + "loss": 1.9397, + "step": 5220 + }, + { + "epoch": 0.19, + "learning_rate": 9.805482203295273e-06, + "loss": 2.0432, + "step": 5230 + }, + { + "epoch": 0.19, + "learning_rate": 9.805110276341727e-06, + "loss": 2.0134, + "step": 5240 + }, + { + "epoch": 0.2, + "learning_rate": 9.80473834938818e-06, + "loss": 1.9951, + "step": 5250 + }, + { + "epoch": 0.2, + "learning_rate": 9.804366422434634e-06, + "loss": 2.0436, + "step": 5260 + }, + { + "epoch": 0.2, + "learning_rate": 9.803994495481089e-06, + "loss": 1.9983, + "step": 5270 + }, + { + "epoch": 0.2, + "learning_rate": 9.803622568527542e-06, + "loss": 1.9577, + "step": 5280 + }, + { + "epoch": 0.2, + "learning_rate": 9.803250641573996e-06, + "loss": 1.9581, + "step": 5290 + }, + { + "epoch": 0.2, + "learning_rate": 9.80287871462045e-06, + "loss": 2.0191, + "step": 5300 + }, + { + "epoch": 0.2, + "eval_loss": 1.9122568368911743, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 5300 + }, + { + "epoch": 0.2, + "learning_rate": 9.802506787666903e-06, + "loss": 1.9798, + "step": 5310 + }, + { + "epoch": 0.2, + "learning_rate": 9.802134860713356e-06, + "loss": 2.0613, + "step": 5320 + }, + { + "epoch": 0.2, + "learning_rate": 9.801762933759811e-06, + "loss": 2.1313, + "step": 5330 + }, + { + "epoch": 0.2, + "learning_rate": 9.801391006806265e-06, + "loss": 2.0523, + "step": 5340 + }, + { + "epoch": 0.2, + "learning_rate": 9.801019079852718e-06, + "loss": 1.8671, + "step": 5350 + }, + { + "epoch": 0.2, + "learning_rate": 9.80064715289917e-06, + "loss": 2.0409, + "step": 5360 + }, + { + "epoch": 0.2, + "learning_rate": 9.800275225945625e-06, + "loss": 1.9568, + "step": 5370 + }, + { + "epoch": 0.2, + "learning_rate": 9.799903298992079e-06, + "loss": 1.9417, + "step": 5380 + }, + { + "epoch": 0.2, + "learning_rate": 9.799531372038532e-06, + "loss": 2.0626, + "step": 5390 + }, + { + "epoch": 0.2, + "learning_rate": 9.799159445084986e-06, + "loss": 2.0104, + "step": 5400 + }, + { + "epoch": 0.2, + "eval_loss": 1.9155107736587524, + "eval_runtime": 16.8346, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 5400 + }, + { + "epoch": 0.2, + "learning_rate": 9.798787518131439e-06, + "loss": 1.9909, + "step": 5410 + }, + { + "epoch": 0.2, + "learning_rate": 9.798415591177893e-06, + "loss": 2.1993, + "step": 5420 + }, + { + "epoch": 0.2, + "learning_rate": 9.798043664224348e-06, + "loss": 2.0269, + "step": 5430 + }, + { + "epoch": 0.2, + "learning_rate": 9.797671737270801e-06, + "loss": 1.9893, + "step": 5440 + }, + { + "epoch": 0.2, + "learning_rate": 9.797299810317255e-06, + "loss": 1.9779, + "step": 5450 + }, + { + "epoch": 0.2, + "learning_rate": 9.796927883363708e-06, + "loss": 1.8788, + "step": 5460 + }, + { + "epoch": 0.2, + "learning_rate": 9.796555956410162e-06, + "loss": 2.0172, + "step": 5470 + }, + { + "epoch": 0.2, + "learning_rate": 9.796184029456615e-06, + "loss": 1.9206, + "step": 5480 + }, + { + "epoch": 0.2, + "learning_rate": 9.79581210250307e-06, + "loss": 2.0694, + "step": 5490 + }, + { + "epoch": 0.2, + "learning_rate": 9.795440175549524e-06, + "loss": 1.9987, + "step": 5500 + }, + { + "epoch": 0.2, + "eval_loss": 1.9101520776748657, + "eval_runtime": 16.8356, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 5500 + }, + { + "epoch": 0.2, + "learning_rate": 9.795068248595977e-06, + "loss": 1.945, + "step": 5510 + }, + { + "epoch": 0.21, + "learning_rate": 9.79469632164243e-06, + "loss": 1.989, + "step": 5520 + }, + { + "epoch": 0.21, + "learning_rate": 9.794324394688884e-06, + "loss": 1.871, + "step": 5530 + }, + { + "epoch": 0.21, + "learning_rate": 9.793952467735337e-06, + "loss": 2.1483, + "step": 5540 + }, + { + "epoch": 0.21, + "learning_rate": 9.793580540781791e-06, + "loss": 1.832, + "step": 5550 + }, + { + "epoch": 0.21, + "learning_rate": 9.793208613828244e-06, + "loss": 1.9617, + "step": 5560 + }, + { + "epoch": 0.21, + "learning_rate": 9.792836686874698e-06, + "loss": 1.9328, + "step": 5570 + }, + { + "epoch": 0.21, + "learning_rate": 9.792464759921151e-06, + "loss": 2.0306, + "step": 5580 + }, + { + "epoch": 0.21, + "learning_rate": 9.792092832967606e-06, + "loss": 2.0602, + "step": 5590 + }, + { + "epoch": 0.21, + "learning_rate": 9.79172090601406e-06, + "loss": 2.0494, + "step": 5600 + }, + { + "epoch": 0.21, + "eval_loss": 1.9096143245697021, + "eval_runtime": 16.8219, + "eval_samples_per_second": 59.446, + "eval_steps_per_second": 3.745, + "step": 5600 + }, + { + "epoch": 0.21, + "learning_rate": 9.791348979060513e-06, + "loss": 1.9896, + "step": 5610 + }, + { + "epoch": 0.21, + "learning_rate": 9.790977052106967e-06, + "loss": 1.8843, + "step": 5620 + }, + { + "epoch": 0.21, + "learning_rate": 9.79060512515342e-06, + "loss": 1.9506, + "step": 5630 + }, + { + "epoch": 0.21, + "learning_rate": 9.790233198199874e-06, + "loss": 1.983, + "step": 5640 + }, + { + "epoch": 0.21, + "learning_rate": 9.789861271246329e-06, + "loss": 2.0443, + "step": 5650 + }, + { + "epoch": 0.21, + "learning_rate": 9.789489344292782e-06, + "loss": 1.9442, + "step": 5660 + }, + { + "epoch": 0.21, + "learning_rate": 9.789117417339236e-06, + "loss": 1.9465, + "step": 5670 + }, + { + "epoch": 0.21, + "learning_rate": 9.78874549038569e-06, + "loss": 1.9612, + "step": 5680 + }, + { + "epoch": 0.21, + "learning_rate": 9.788373563432143e-06, + "loss": 1.8793, + "step": 5690 + }, + { + "epoch": 0.21, + "learning_rate": 9.788001636478596e-06, + "loss": 2.078, + "step": 5700 + }, + { + "epoch": 0.21, + "eval_loss": 1.9048564434051514, + "eval_runtime": 16.8367, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 5700 + }, + { + "epoch": 0.21, + "learning_rate": 9.787629709525051e-06, + "loss": 2.0617, + "step": 5710 + }, + { + "epoch": 0.21, + "learning_rate": 9.787257782571505e-06, + "loss": 1.9407, + "step": 5720 + }, + { + "epoch": 0.21, + "learning_rate": 9.786885855617957e-06, + "loss": 1.8201, + "step": 5730 + }, + { + "epoch": 0.21, + "learning_rate": 9.78651392866441e-06, + "loss": 1.9353, + "step": 5740 + }, + { + "epoch": 0.21, + "learning_rate": 9.786142001710865e-06, + "loss": 1.9478, + "step": 5750 + }, + { + "epoch": 0.21, + "learning_rate": 9.785770074757319e-06, + "loss": 2.0192, + "step": 5760 + }, + { + "epoch": 0.21, + "learning_rate": 9.785398147803772e-06, + "loss": 1.9749, + "step": 5770 + }, + { + "epoch": 0.21, + "learning_rate": 9.785026220850226e-06, + "loss": 2.1136, + "step": 5780 + }, + { + "epoch": 0.22, + "learning_rate": 9.784654293896679e-06, + "loss": 1.959, + "step": 5790 + }, + { + "epoch": 0.22, + "learning_rate": 9.784282366943132e-06, + "loss": 1.8892, + "step": 5800 + }, + { + "epoch": 0.22, + "eval_loss": 1.9054968357086182, + "eval_runtime": 16.8281, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 5800 + }, + { + "epoch": 0.22, + "learning_rate": 9.783910439989586e-06, + "loss": 2.0147, + "step": 5810 + }, + { + "epoch": 0.22, + "learning_rate": 9.783538513036041e-06, + "loss": 2.0906, + "step": 5820 + }, + { + "epoch": 0.22, + "learning_rate": 9.783166586082495e-06, + "loss": 2.1051, + "step": 5830 + }, + { + "epoch": 0.22, + "learning_rate": 9.782794659128948e-06, + "loss": 1.9774, + "step": 5840 + }, + { + "epoch": 0.22, + "learning_rate": 9.782422732175401e-06, + "loss": 2.0288, + "step": 5850 + }, + { + "epoch": 0.22, + "learning_rate": 9.782050805221855e-06, + "loss": 2.1783, + "step": 5860 + }, + { + "epoch": 0.22, + "learning_rate": 9.781678878268308e-06, + "loss": 1.9965, + "step": 5870 + }, + { + "epoch": 0.22, + "learning_rate": 9.781306951314764e-06, + "loss": 2.0568, + "step": 5880 + }, + { + "epoch": 0.22, + "learning_rate": 9.780935024361217e-06, + "loss": 2.0059, + "step": 5890 + }, + { + "epoch": 0.22, + "learning_rate": 9.78056309740767e-06, + "loss": 1.8558, + "step": 5900 + }, + { + "epoch": 0.22, + "eval_loss": 1.9047229290008545, + "eval_runtime": 16.8262, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 5900 + }, + { + "epoch": 0.22, + "learning_rate": 9.780191170454124e-06, + "loss": 1.997, + "step": 5910 + }, + { + "epoch": 0.22, + "learning_rate": 9.779819243500577e-06, + "loss": 1.9937, + "step": 5920 + }, + { + "epoch": 0.22, + "learning_rate": 9.77944731654703e-06, + "loss": 1.9417, + "step": 5930 + }, + { + "epoch": 0.22, + "learning_rate": 9.779075389593484e-06, + "loss": 1.9275, + "step": 5940 + }, + { + "epoch": 0.22, + "learning_rate": 9.778703462639938e-06, + "loss": 1.8407, + "step": 5950 + }, + { + "epoch": 0.22, + "learning_rate": 9.778331535686391e-06, + "loss": 1.973, + "step": 5960 + }, + { + "epoch": 0.22, + "learning_rate": 9.777959608732845e-06, + "loss": 1.9622, + "step": 5970 + }, + { + "epoch": 0.22, + "learning_rate": 9.7775876817793e-06, + "loss": 2.038, + "step": 5980 + }, + { + "epoch": 0.22, + "learning_rate": 9.777215754825753e-06, + "loss": 1.8937, + "step": 5990 + }, + { + "epoch": 0.22, + "learning_rate": 9.776843827872207e-06, + "loss": 1.9597, + "step": 6000 + }, + { + "epoch": 0.22, + "eval_loss": 1.8967465162277222, + "eval_runtime": 16.8209, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 6000 + }, + { + "epoch": 0.22, + "learning_rate": 9.77647190091866e-06, + "loss": 2.119, + "step": 6010 + }, + { + "epoch": 0.22, + "learning_rate": 9.776099973965114e-06, + "loss": 2.1791, + "step": 6020 + }, + { + "epoch": 0.22, + "learning_rate": 9.775728047011567e-06, + "loss": 2.0648, + "step": 6030 + }, + { + "epoch": 0.22, + "learning_rate": 9.775356120058022e-06, + "loss": 1.9939, + "step": 6040 + }, + { + "epoch": 0.23, + "learning_rate": 9.774984193104476e-06, + "loss": 1.8311, + "step": 6050 + }, + { + "epoch": 0.23, + "learning_rate": 9.77461226615093e-06, + "loss": 1.9906, + "step": 6060 + }, + { + "epoch": 0.23, + "learning_rate": 9.774240339197383e-06, + "loss": 1.9755, + "step": 6070 + }, + { + "epoch": 0.23, + "learning_rate": 9.773868412243836e-06, + "loss": 2.0392, + "step": 6080 + }, + { + "epoch": 0.23, + "learning_rate": 9.77349648529029e-06, + "loss": 1.9918, + "step": 6090 + }, + { + "epoch": 0.23, + "learning_rate": 9.773124558336745e-06, + "loss": 1.9902, + "step": 6100 + }, + { + "epoch": 0.23, + "eval_loss": 1.895453929901123, + "eval_runtime": 16.8209, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 6100 + }, + { + "epoch": 0.23, + "learning_rate": 9.772752631383196e-06, + "loss": 1.9977, + "step": 6110 + }, + { + "epoch": 0.23, + "learning_rate": 9.77238070442965e-06, + "loss": 1.9805, + "step": 6120 + }, + { + "epoch": 0.23, + "learning_rate": 9.772008777476103e-06, + "loss": 2.0199, + "step": 6130 + }, + { + "epoch": 0.23, + "learning_rate": 9.771636850522559e-06, + "loss": 1.9392, + "step": 6140 + }, + { + "epoch": 0.23, + "learning_rate": 9.771264923569012e-06, + "loss": 1.9794, + "step": 6150 + }, + { + "epoch": 0.23, + "learning_rate": 9.770892996615465e-06, + "loss": 2.0179, + "step": 6160 + }, + { + "epoch": 0.23, + "learning_rate": 9.770521069661919e-06, + "loss": 2.0611, + "step": 6170 + }, + { + "epoch": 0.23, + "learning_rate": 9.770149142708372e-06, + "loss": 1.9865, + "step": 6180 + }, + { + "epoch": 0.23, + "learning_rate": 9.769777215754826e-06, + "loss": 1.8678, + "step": 6190 + }, + { + "epoch": 0.23, + "learning_rate": 9.769405288801281e-06, + "loss": 1.9531, + "step": 6200 + }, + { + "epoch": 0.23, + "eval_loss": 1.8942316770553589, + "eval_runtime": 16.8235, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 6200 + }, + { + "epoch": 0.23, + "learning_rate": 9.769033361847734e-06, + "loss": 2.1851, + "step": 6210 + }, + { + "epoch": 0.23, + "learning_rate": 9.768661434894188e-06, + "loss": 2.0044, + "step": 6220 + }, + { + "epoch": 0.23, + "learning_rate": 9.768289507940641e-06, + "loss": 1.9072, + "step": 6230 + }, + { + "epoch": 0.23, + "learning_rate": 9.767917580987095e-06, + "loss": 1.9468, + "step": 6240 + }, + { + "epoch": 0.23, + "learning_rate": 9.767545654033548e-06, + "loss": 1.9555, + "step": 6250 + }, + { + "epoch": 0.23, + "learning_rate": 9.767173727080003e-06, + "loss": 1.9278, + "step": 6260 + }, + { + "epoch": 0.23, + "learning_rate": 9.766801800126457e-06, + "loss": 2.0138, + "step": 6270 + }, + { + "epoch": 0.23, + "learning_rate": 9.76642987317291e-06, + "loss": 1.9865, + "step": 6280 + }, + { + "epoch": 0.23, + "learning_rate": 9.766057946219362e-06, + "loss": 2.0242, + "step": 6290 + }, + { + "epoch": 0.23, + "learning_rate": 9.765686019265817e-06, + "loss": 1.9298, + "step": 6300 + }, + { + "epoch": 0.23, + "eval_loss": 1.8902751207351685, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 6300 + }, + { + "epoch": 0.23, + "learning_rate": 9.76531409231227e-06, + "loss": 1.9307, + "step": 6310 + }, + { + "epoch": 0.24, + "learning_rate": 9.764942165358724e-06, + "loss": 2.0182, + "step": 6320 + }, + { + "epoch": 0.24, + "learning_rate": 9.764570238405178e-06, + "loss": 2.0203, + "step": 6330 + }, + { + "epoch": 0.24, + "learning_rate": 9.764198311451631e-06, + "loss": 1.806, + "step": 6340 + }, + { + "epoch": 0.24, + "learning_rate": 9.763826384498085e-06, + "loss": 2.059, + "step": 6350 + }, + { + "epoch": 0.24, + "learning_rate": 9.76345445754454e-06, + "loss": 2.0167, + "step": 6360 + }, + { + "epoch": 0.24, + "learning_rate": 9.763082530590993e-06, + "loss": 2.0017, + "step": 6370 + }, + { + "epoch": 0.24, + "learning_rate": 9.762710603637447e-06, + "loss": 2.0096, + "step": 6380 + }, + { + "epoch": 0.24, + "learning_rate": 9.7623386766839e-06, + "loss": 1.9239, + "step": 6390 + }, + { + "epoch": 0.24, + "learning_rate": 9.761966749730354e-06, + "loss": 1.9084, + "step": 6400 + }, + { + "epoch": 0.24, + "eval_loss": 1.8916540145874023, + "eval_runtime": 16.824, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 6400 + }, + { + "epoch": 0.24, + "learning_rate": 9.761594822776807e-06, + "loss": 2.0255, + "step": 6410 + }, + { + "epoch": 0.24, + "learning_rate": 9.76122289582326e-06, + "loss": 2.0281, + "step": 6420 + }, + { + "epoch": 0.24, + "learning_rate": 9.760850968869716e-06, + "loss": 2.0373, + "step": 6430 + }, + { + "epoch": 0.24, + "learning_rate": 9.760479041916169e-06, + "loss": 1.9281, + "step": 6440 + }, + { + "epoch": 0.24, + "learning_rate": 9.760107114962623e-06, + "loss": 2.0854, + "step": 6450 + }, + { + "epoch": 0.24, + "learning_rate": 9.759735188009076e-06, + "loss": 2.0352, + "step": 6460 + }, + { + "epoch": 0.24, + "learning_rate": 9.75936326105553e-06, + "loss": 1.9261, + "step": 6470 + }, + { + "epoch": 0.24, + "learning_rate": 9.758991334101983e-06, + "loss": 1.8969, + "step": 6480 + }, + { + "epoch": 0.24, + "learning_rate": 9.758619407148436e-06, + "loss": 2.0106, + "step": 6490 + }, + { + "epoch": 0.24, + "learning_rate": 9.75824748019489e-06, + "loss": 2.0465, + "step": 6500 + }, + { + "epoch": 0.24, + "eval_loss": 1.8900212049484253, + "eval_runtime": 16.8116, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 6500 + }, + { + "epoch": 0.24, + "learning_rate": 9.757875553241343e-06, + "loss": 1.9807, + "step": 6510 + }, + { + "epoch": 0.24, + "learning_rate": 9.757503626287797e-06, + "loss": 2.003, + "step": 6520 + }, + { + "epoch": 0.24, + "learning_rate": 9.757131699334252e-06, + "loss": 2.0631, + "step": 6530 + }, + { + "epoch": 0.24, + "learning_rate": 9.756759772380705e-06, + "loss": 2.0839, + "step": 6540 + }, + { + "epoch": 0.24, + "learning_rate": 9.756387845427159e-06, + "loss": 1.9819, + "step": 6550 + }, + { + "epoch": 0.24, + "learning_rate": 9.756015918473612e-06, + "loss": 1.9348, + "step": 6560 + }, + { + "epoch": 0.24, + "learning_rate": 9.755643991520066e-06, + "loss": 2.0094, + "step": 6570 + }, + { + "epoch": 0.24, + "learning_rate": 9.75527206456652e-06, + "loss": 1.877, + "step": 6580 + }, + { + "epoch": 0.25, + "learning_rate": 9.754900137612974e-06, + "loss": 1.9055, + "step": 6590 + }, + { + "epoch": 0.25, + "learning_rate": 9.754528210659428e-06, + "loss": 2.0091, + "step": 6600 + }, + { + "epoch": 0.25, + "eval_loss": 1.8880226612091064, + "eval_runtime": 16.8189, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 6600 + }, + { + "epoch": 0.25, + "learning_rate": 9.754156283705881e-06, + "loss": 1.9949, + "step": 6610 + }, + { + "epoch": 0.25, + "learning_rate": 9.753784356752335e-06, + "loss": 1.8727, + "step": 6620 + }, + { + "epoch": 0.25, + "learning_rate": 9.753412429798788e-06, + "loss": 1.8865, + "step": 6630 + }, + { + "epoch": 0.25, + "learning_rate": 9.753040502845242e-06, + "loss": 1.9949, + "step": 6640 + }, + { + "epoch": 0.25, + "learning_rate": 9.752668575891697e-06, + "loss": 1.9176, + "step": 6650 + }, + { + "epoch": 0.25, + "learning_rate": 9.75229664893815e-06, + "loss": 1.982, + "step": 6660 + }, + { + "epoch": 0.25, + "learning_rate": 9.751924721984602e-06, + "loss": 2.0463, + "step": 6670 + }, + { + "epoch": 0.25, + "learning_rate": 9.751552795031056e-06, + "loss": 1.8276, + "step": 6680 + }, + { + "epoch": 0.25, + "learning_rate": 9.75118086807751e-06, + "loss": 2.0304, + "step": 6690 + }, + { + "epoch": 0.25, + "learning_rate": 9.750808941123964e-06, + "loss": 1.9945, + "step": 6700 + }, + { + "epoch": 0.25, + "eval_loss": 1.8881603479385376, + "eval_runtime": 16.8272, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 6700 + }, + { + "epoch": 0.25, + "learning_rate": 9.750437014170418e-06, + "loss": 1.993, + "step": 6710 + }, + { + "epoch": 0.25, + "learning_rate": 9.750065087216871e-06, + "loss": 1.9917, + "step": 6720 + }, + { + "epoch": 0.25, + "learning_rate": 9.749693160263325e-06, + "loss": 1.8952, + "step": 6730 + }, + { + "epoch": 0.25, + "learning_rate": 9.749321233309778e-06, + "loss": 1.8433, + "step": 6740 + }, + { + "epoch": 0.25, + "learning_rate": 9.748949306356233e-06, + "loss": 1.9371, + "step": 6750 + }, + { + "epoch": 0.25, + "learning_rate": 9.748577379402687e-06, + "loss": 1.985, + "step": 6760 + }, + { + "epoch": 0.25, + "learning_rate": 9.74820545244914e-06, + "loss": 1.8897, + "step": 6770 + }, + { + "epoch": 0.25, + "learning_rate": 9.747833525495594e-06, + "loss": 1.9607, + "step": 6780 + }, + { + "epoch": 0.25, + "learning_rate": 9.747461598542047e-06, + "loss": 1.9725, + "step": 6790 + }, + { + "epoch": 0.25, + "learning_rate": 9.7470896715885e-06, + "loss": 1.9321, + "step": 6800 + }, + { + "epoch": 0.25, + "eval_loss": 1.8857440948486328, + "eval_runtime": 16.8148, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 6800 + }, + { + "epoch": 0.25, + "learning_rate": 9.746717744634956e-06, + "loss": 2.0192, + "step": 6810 + }, + { + "epoch": 0.25, + "learning_rate": 9.746345817681409e-06, + "loss": 1.9211, + "step": 6820 + }, + { + "epoch": 0.25, + "learning_rate": 9.745973890727862e-06, + "loss": 1.9812, + "step": 6830 + }, + { + "epoch": 0.25, + "learning_rate": 9.745601963774316e-06, + "loss": 1.9951, + "step": 6840 + }, + { + "epoch": 0.25, + "learning_rate": 9.74523003682077e-06, + "loss": 1.9981, + "step": 6850 + }, + { + "epoch": 0.26, + "learning_rate": 9.744858109867223e-06, + "loss": 1.9167, + "step": 6860 + }, + { + "epoch": 0.26, + "learning_rate": 9.744486182913676e-06, + "loss": 1.9713, + "step": 6870 + }, + { + "epoch": 0.26, + "learning_rate": 9.74411425596013e-06, + "loss": 2.0237, + "step": 6880 + }, + { + "epoch": 0.26, + "learning_rate": 9.743742329006583e-06, + "loss": 1.8537, + "step": 6890 + }, + { + "epoch": 0.26, + "learning_rate": 9.743370402053037e-06, + "loss": 1.8943, + "step": 6900 + }, + { + "epoch": 0.26, + "eval_loss": 1.8879536390304565, + "eval_runtime": 16.8197, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 6900 + }, + { + "epoch": 0.26, + "learning_rate": 9.742998475099492e-06, + "loss": 1.9362, + "step": 6910 + }, + { + "epoch": 0.26, + "learning_rate": 9.742626548145945e-06, + "loss": 1.9677, + "step": 6920 + }, + { + "epoch": 0.26, + "learning_rate": 9.742254621192399e-06, + "loss": 2.1238, + "step": 6930 + }, + { + "epoch": 0.26, + "learning_rate": 9.741882694238852e-06, + "loss": 1.9277, + "step": 6940 + }, + { + "epoch": 0.26, + "learning_rate": 9.741510767285306e-06, + "loss": 1.8551, + "step": 6950 + }, + { + "epoch": 0.26, + "learning_rate": 9.74113884033176e-06, + "loss": 2.1602, + "step": 6960 + }, + { + "epoch": 0.26, + "learning_rate": 9.740766913378213e-06, + "loss": 1.8708, + "step": 6970 + }, + { + "epoch": 0.26, + "learning_rate": 9.740394986424668e-06, + "loss": 2.0258, + "step": 6980 + }, + { + "epoch": 0.26, + "learning_rate": 9.740023059471121e-06, + "loss": 2.0533, + "step": 6990 + }, + { + "epoch": 0.26, + "learning_rate": 9.739651132517575e-06, + "loss": 1.9737, + "step": 7000 + }, + { + "epoch": 0.26, + "eval_loss": 1.8878487348556519, + "eval_runtime": 16.8363, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 7000 + }, + { + "epoch": 0.26, + "learning_rate": 9.739279205564028e-06, + "loss": 1.9694, + "step": 7010 + }, + { + "epoch": 0.26, + "learning_rate": 9.738907278610482e-06, + "loss": 1.828, + "step": 7020 + }, + { + "epoch": 0.26, + "learning_rate": 9.738535351656935e-06, + "loss": 2.0664, + "step": 7030 + }, + { + "epoch": 0.26, + "learning_rate": 9.73816342470339e-06, + "loss": 2.0769, + "step": 7040 + }, + { + "epoch": 0.26, + "learning_rate": 9.737791497749842e-06, + "loss": 1.9868, + "step": 7050 + }, + { + "epoch": 0.26, + "learning_rate": 9.737419570796295e-06, + "loss": 2.0315, + "step": 7060 + }, + { + "epoch": 0.26, + "learning_rate": 9.737047643842749e-06, + "loss": 1.938, + "step": 7070 + }, + { + "epoch": 0.26, + "learning_rate": 9.736675716889204e-06, + "loss": 1.8413, + "step": 7080 + }, + { + "epoch": 0.26, + "learning_rate": 9.736303789935658e-06, + "loss": 1.9853, + "step": 7090 + }, + { + "epoch": 0.26, + "learning_rate": 9.735931862982111e-06, + "loss": 1.9476, + "step": 7100 + }, + { + "epoch": 0.26, + "eval_loss": 1.8864392042160034, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 7100 + }, + { + "epoch": 0.26, + "learning_rate": 9.735559936028564e-06, + "loss": 1.9498, + "step": 7110 + }, + { + "epoch": 0.26, + "learning_rate": 9.735188009075018e-06, + "loss": 2.0476, + "step": 7120 + }, + { + "epoch": 0.27, + "learning_rate": 9.734816082121471e-06, + "loss": 1.9957, + "step": 7130 + }, + { + "epoch": 0.27, + "learning_rate": 9.734444155167927e-06, + "loss": 1.9642, + "step": 7140 + }, + { + "epoch": 0.27, + "learning_rate": 9.73407222821438e-06, + "loss": 1.9553, + "step": 7150 + }, + { + "epoch": 0.27, + "learning_rate": 9.733700301260833e-06, + "loss": 1.9887, + "step": 7160 + }, + { + "epoch": 0.27, + "learning_rate": 9.733328374307287e-06, + "loss": 1.8338, + "step": 7170 + }, + { + "epoch": 0.27, + "learning_rate": 9.73295644735374e-06, + "loss": 1.9726, + "step": 7180 + }, + { + "epoch": 0.27, + "learning_rate": 9.732584520400194e-06, + "loss": 1.9377, + "step": 7190 + }, + { + "epoch": 0.27, + "learning_rate": 9.732212593446649e-06, + "loss": 1.8352, + "step": 7200 + }, + { + "epoch": 0.27, + "eval_loss": 1.8819342851638794, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 7200 + }, + { + "epoch": 0.27, + "learning_rate": 9.731840666493102e-06, + "loss": 2.0074, + "step": 7210 + }, + { + "epoch": 0.27, + "learning_rate": 9.731468739539556e-06, + "loss": 1.8959, + "step": 7220 + }, + { + "epoch": 0.27, + "learning_rate": 9.731096812586008e-06, + "loss": 1.9623, + "step": 7230 + }, + { + "epoch": 0.27, + "learning_rate": 9.730724885632463e-06, + "loss": 1.9568, + "step": 7240 + }, + { + "epoch": 0.27, + "learning_rate": 9.730352958678916e-06, + "loss": 1.8745, + "step": 7250 + }, + { + "epoch": 0.27, + "learning_rate": 9.72998103172537e-06, + "loss": 2.0406, + "step": 7260 + }, + { + "epoch": 0.27, + "learning_rate": 9.729609104771823e-06, + "loss": 1.8616, + "step": 7270 + }, + { + "epoch": 0.27, + "learning_rate": 9.729237177818277e-06, + "loss": 1.9525, + "step": 7280 + }, + { + "epoch": 0.27, + "learning_rate": 9.72886525086473e-06, + "loss": 2.006, + "step": 7290 + }, + { + "epoch": 0.27, + "learning_rate": 9.728493323911185e-06, + "loss": 2.0574, + "step": 7300 + }, + { + "epoch": 0.27, + "eval_loss": 1.883543610572815, + "eval_runtime": 16.8314, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 7300 + }, + { + "epoch": 0.27, + "learning_rate": 9.728121396957639e-06, + "loss": 1.9153, + "step": 7310 + }, + { + "epoch": 0.27, + "learning_rate": 9.727749470004092e-06, + "loss": 1.9406, + "step": 7320 + }, + { + "epoch": 0.27, + "learning_rate": 9.727377543050546e-06, + "loss": 1.9616, + "step": 7330 + }, + { + "epoch": 0.27, + "learning_rate": 9.727005616096999e-06, + "loss": 1.9082, + "step": 7340 + }, + { + "epoch": 0.27, + "learning_rate": 9.726633689143453e-06, + "loss": 1.9292, + "step": 7350 + }, + { + "epoch": 0.27, + "learning_rate": 9.726261762189908e-06, + "loss": 1.9795, + "step": 7360 + }, + { + "epoch": 0.27, + "learning_rate": 9.725889835236361e-06, + "loss": 2.0354, + "step": 7370 + }, + { + "epoch": 0.27, + "learning_rate": 9.725517908282815e-06, + "loss": 2.0062, + "step": 7380 + }, + { + "epoch": 0.27, + "learning_rate": 9.725145981329268e-06, + "loss": 1.8995, + "step": 7390 + }, + { + "epoch": 0.28, + "learning_rate": 9.724774054375722e-06, + "loss": 1.9776, + "step": 7400 + }, + { + "epoch": 0.28, + "eval_loss": 1.8800158500671387, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 7400 + }, + { + "epoch": 0.28, + "learning_rate": 9.724402127422175e-06, + "loss": 1.9775, + "step": 7410 + }, + { + "epoch": 0.28, + "learning_rate": 9.724030200468628e-06, + "loss": 1.9863, + "step": 7420 + }, + { + "epoch": 0.28, + "learning_rate": 9.723658273515082e-06, + "loss": 1.8726, + "step": 7430 + }, + { + "epoch": 0.28, + "learning_rate": 9.723286346561535e-06, + "loss": 1.9946, + "step": 7440 + }, + { + "epoch": 0.28, + "learning_rate": 9.722914419607989e-06, + "loss": 1.9625, + "step": 7450 + }, + { + "epoch": 0.28, + "learning_rate": 9.722542492654444e-06, + "loss": 1.893, + "step": 7460 + }, + { + "epoch": 0.28, + "learning_rate": 9.722170565700897e-06, + "loss": 2.035, + "step": 7470 + }, + { + "epoch": 0.28, + "learning_rate": 9.721798638747351e-06, + "loss": 1.9216, + "step": 7480 + }, + { + "epoch": 0.28, + "learning_rate": 9.721426711793804e-06, + "loss": 1.9558, + "step": 7490 + }, + { + "epoch": 0.28, + "learning_rate": 9.721054784840258e-06, + "loss": 2.0261, + "step": 7500 + }, + { + "epoch": 0.28, + "eval_loss": 1.8786169290542603, + "eval_runtime": 16.8274, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 7500 + }, + { + "epoch": 0.28, + "learning_rate": 9.720682857886711e-06, + "loss": 1.7762, + "step": 7510 + }, + { + "epoch": 0.28, + "learning_rate": 9.720310930933165e-06, + "loss": 1.8367, + "step": 7520 + }, + { + "epoch": 0.28, + "learning_rate": 9.71993900397962e-06, + "loss": 1.9953, + "step": 7530 + }, + { + "epoch": 0.28, + "learning_rate": 9.719567077026073e-06, + "loss": 1.9119, + "step": 7540 + }, + { + "epoch": 0.28, + "learning_rate": 9.719195150072527e-06, + "loss": 1.922, + "step": 7550 + }, + { + "epoch": 0.28, + "learning_rate": 9.71882322311898e-06, + "loss": 1.9226, + "step": 7560 + }, + { + "epoch": 0.28, + "learning_rate": 9.718451296165434e-06, + "loss": 2.0163, + "step": 7570 + }, + { + "epoch": 0.28, + "learning_rate": 9.718079369211887e-06, + "loss": 1.9424, + "step": 7580 + }, + { + "epoch": 0.28, + "learning_rate": 9.717707442258342e-06, + "loss": 2.0619, + "step": 7590 + }, + { + "epoch": 0.28, + "learning_rate": 9.717335515304796e-06, + "loss": 1.8973, + "step": 7600 + }, + { + "epoch": 0.28, + "eval_loss": 1.8772923946380615, + "eval_runtime": 16.8095, + "eval_samples_per_second": 59.49, + "eval_steps_per_second": 3.748, + "step": 7600 + }, + { + "epoch": 0.28, + "learning_rate": 9.716963588351248e-06, + "loss": 1.9365, + "step": 7610 + }, + { + "epoch": 0.28, + "learning_rate": 9.716591661397701e-06, + "loss": 1.7177, + "step": 7620 + }, + { + "epoch": 0.28, + "learning_rate": 9.716219734444156e-06, + "loss": 1.8984, + "step": 7630 + }, + { + "epoch": 0.28, + "learning_rate": 9.71584780749061e-06, + "loss": 1.8743, + "step": 7640 + }, + { + "epoch": 0.28, + "learning_rate": 9.715475880537063e-06, + "loss": 2.0656, + "step": 7650 + }, + { + "epoch": 0.28, + "learning_rate": 9.715103953583517e-06, + "loss": 1.9945, + "step": 7660 + }, + { + "epoch": 0.29, + "learning_rate": 9.71473202662997e-06, + "loss": 2.0213, + "step": 7670 + }, + { + "epoch": 0.29, + "learning_rate": 9.714360099676423e-06, + "loss": 1.949, + "step": 7680 + }, + { + "epoch": 0.29, + "learning_rate": 9.713988172722879e-06, + "loss": 1.9851, + "step": 7690 + }, + { + "epoch": 0.29, + "learning_rate": 9.713616245769332e-06, + "loss": 1.8438, + "step": 7700 + }, + { + "epoch": 0.29, + "eval_loss": 1.8785651922225952, + "eval_runtime": 16.8276, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 7700 + }, + { + "epoch": 0.29, + "learning_rate": 9.713244318815786e-06, + "loss": 1.9437, + "step": 7710 + }, + { + "epoch": 0.29, + "learning_rate": 9.712872391862239e-06, + "loss": 1.9535, + "step": 7720 + }, + { + "epoch": 0.29, + "learning_rate": 9.712500464908692e-06, + "loss": 1.9458, + "step": 7730 + }, + { + "epoch": 0.29, + "learning_rate": 9.712128537955146e-06, + "loss": 2.0191, + "step": 7740 + }, + { + "epoch": 0.29, + "learning_rate": 9.711756611001601e-06, + "loss": 1.8845, + "step": 7750 + }, + { + "epoch": 0.29, + "learning_rate": 9.711384684048055e-06, + "loss": 1.9411, + "step": 7760 + }, + { + "epoch": 0.29, + "learning_rate": 9.711012757094508e-06, + "loss": 1.8929, + "step": 7770 + }, + { + "epoch": 0.29, + "learning_rate": 9.710640830140961e-06, + "loss": 1.9979, + "step": 7780 + }, + { + "epoch": 0.29, + "learning_rate": 9.710268903187415e-06, + "loss": 1.9636, + "step": 7790 + }, + { + "epoch": 0.29, + "learning_rate": 9.709896976233868e-06, + "loss": 2.0353, + "step": 7800 + }, + { + "epoch": 0.29, + "eval_loss": 1.8773882389068604, + "eval_runtime": 16.8255, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 7800 + }, + { + "epoch": 0.29, + "learning_rate": 9.709525049280322e-06, + "loss": 1.9065, + "step": 7810 + }, + { + "epoch": 0.29, + "learning_rate": 9.709153122326775e-06, + "loss": 1.9353, + "step": 7820 + }, + { + "epoch": 0.29, + "learning_rate": 9.708781195373229e-06, + "loss": 2.0252, + "step": 7830 + }, + { + "epoch": 0.29, + "learning_rate": 9.708409268419682e-06, + "loss": 1.8606, + "step": 7840 + }, + { + "epoch": 0.29, + "learning_rate": 9.708037341466137e-06, + "loss": 1.9133, + "step": 7850 + }, + { + "epoch": 0.29, + "learning_rate": 9.70766541451259e-06, + "loss": 1.9924, + "step": 7860 + }, + { + "epoch": 0.29, + "learning_rate": 9.707293487559044e-06, + "loss": 1.9038, + "step": 7870 + }, + { + "epoch": 0.29, + "learning_rate": 9.706921560605498e-06, + "loss": 1.9059, + "step": 7880 + }, + { + "epoch": 0.29, + "learning_rate": 9.706549633651951e-06, + "loss": 2.0534, + "step": 7890 + }, + { + "epoch": 0.29, + "learning_rate": 9.706177706698405e-06, + "loss": 1.8767, + "step": 7900 + }, + { + "epoch": 0.29, + "eval_loss": 1.8742619752883911, + "eval_runtime": 16.8231, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 7900 + }, + { + "epoch": 0.29, + "learning_rate": 9.70580577974486e-06, + "loss": 2.0407, + "step": 7910 + }, + { + "epoch": 0.29, + "learning_rate": 9.705433852791313e-06, + "loss": 1.928, + "step": 7920 + }, + { + "epoch": 0.29, + "learning_rate": 9.705061925837767e-06, + "loss": 1.9481, + "step": 7930 + }, + { + "epoch": 0.3, + "learning_rate": 9.70468999888422e-06, + "loss": 2.0844, + "step": 7940 + }, + { + "epoch": 0.3, + "learning_rate": 9.704318071930674e-06, + "loss": 2.0224, + "step": 7950 + }, + { + "epoch": 0.3, + "learning_rate": 9.703946144977127e-06, + "loss": 1.992, + "step": 7960 + }, + { + "epoch": 0.3, + "learning_rate": 9.703574218023582e-06, + "loss": 1.7892, + "step": 7970 + }, + { + "epoch": 0.3, + "learning_rate": 9.703202291070034e-06, + "loss": 1.9528, + "step": 7980 + }, + { + "epoch": 0.3, + "learning_rate": 9.702830364116487e-06, + "loss": 2.0032, + "step": 7990 + }, + { + "epoch": 0.3, + "learning_rate": 9.702458437162941e-06, + "loss": 1.9045, + "step": 8000 + }, + { + "epoch": 0.3, + "eval_loss": 1.8734521865844727, + "eval_runtime": 16.8282, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 8000 + }, + { + "epoch": 0.3, + "learning_rate": 9.702086510209396e-06, + "loss": 2.0364, + "step": 8010 + }, + { + "epoch": 0.3, + "learning_rate": 9.70171458325585e-06, + "loss": 1.8269, + "step": 8020 + }, + { + "epoch": 0.3, + "learning_rate": 9.701342656302303e-06, + "loss": 2.011, + "step": 8030 + }, + { + "epoch": 0.3, + "learning_rate": 9.700970729348756e-06, + "loss": 2.0326, + "step": 8040 + }, + { + "epoch": 0.3, + "learning_rate": 9.70059880239521e-06, + "loss": 2.0155, + "step": 8050 + }, + { + "epoch": 0.3, + "learning_rate": 9.700226875441663e-06, + "loss": 1.9218, + "step": 8060 + }, + { + "epoch": 0.3, + "learning_rate": 9.699854948488119e-06, + "loss": 1.9317, + "step": 8070 + }, + { + "epoch": 0.3, + "learning_rate": 9.699483021534572e-06, + "loss": 2.1204, + "step": 8080 + }, + { + "epoch": 0.3, + "learning_rate": 9.699111094581025e-06, + "loss": 1.9385, + "step": 8090 + }, + { + "epoch": 0.3, + "learning_rate": 9.698739167627479e-06, + "loss": 1.8664, + "step": 8100 + }, + { + "epoch": 0.3, + "eval_loss": 1.8717455863952637, + "eval_runtime": 16.8128, + "eval_samples_per_second": 59.478, + "eval_steps_per_second": 3.747, + "step": 8100 + }, + { + "epoch": 0.3, + "learning_rate": 9.698367240673932e-06, + "loss": 1.732, + "step": 8110 + }, + { + "epoch": 0.3, + "learning_rate": 9.697995313720386e-06, + "loss": 2.0378, + "step": 8120 + }, + { + "epoch": 0.3, + "learning_rate": 9.69762338676684e-06, + "loss": 2.0631, + "step": 8130 + }, + { + "epoch": 0.3, + "learning_rate": 9.697251459813294e-06, + "loss": 2.0359, + "step": 8140 + }, + { + "epoch": 0.3, + "learning_rate": 9.696879532859748e-06, + "loss": 1.9218, + "step": 8150 + }, + { + "epoch": 0.3, + "learning_rate": 9.696507605906201e-06, + "loss": 1.9166, + "step": 8160 + }, + { + "epoch": 0.3, + "learning_rate": 9.696135678952653e-06, + "loss": 1.9311, + "step": 8170 + }, + { + "epoch": 0.3, + "learning_rate": 9.695763751999108e-06, + "loss": 1.9484, + "step": 8180 + }, + { + "epoch": 0.3, + "learning_rate": 9.695391825045562e-06, + "loss": 1.7885, + "step": 8190 + }, + { + "epoch": 0.3, + "learning_rate": 9.695019898092015e-06, + "loss": 1.9283, + "step": 8200 + }, + { + "epoch": 0.3, + "eval_loss": 1.8711845874786377, + "eval_runtime": 16.8127, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 8200 + }, + { + "epoch": 0.31, + "learning_rate": 9.694647971138469e-06, + "loss": 1.8568, + "step": 8210 + }, + { + "epoch": 0.31, + "learning_rate": 9.694276044184922e-06, + "loss": 1.9537, + "step": 8220 + }, + { + "epoch": 0.31, + "learning_rate": 9.693904117231376e-06, + "loss": 2.0028, + "step": 8230 + }, + { + "epoch": 0.31, + "learning_rate": 9.69353219027783e-06, + "loss": 1.9092, + "step": 8240 + }, + { + "epoch": 0.31, + "learning_rate": 9.693160263324284e-06, + "loss": 2.0082, + "step": 8250 + }, + { + "epoch": 0.31, + "learning_rate": 9.692788336370738e-06, + "loss": 1.9852, + "step": 8260 + }, + { + "epoch": 0.31, + "learning_rate": 9.692416409417191e-06, + "loss": 1.9856, + "step": 8270 + }, + { + "epoch": 0.31, + "learning_rate": 9.692044482463645e-06, + "loss": 2.0116, + "step": 8280 + }, + { + "epoch": 0.31, + "learning_rate": 9.691672555510098e-06, + "loss": 1.9898, + "step": 8290 + }, + { + "epoch": 0.31, + "learning_rate": 9.691300628556553e-06, + "loss": 2.0428, + "step": 8300 + }, + { + "epoch": 0.31, + "eval_loss": 1.8744663000106812, + "eval_runtime": 16.8162, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 8300 + }, + { + "epoch": 0.31, + "learning_rate": 9.690928701603007e-06, + "loss": 1.9636, + "step": 8310 + }, + { + "epoch": 0.31, + "learning_rate": 9.69055677464946e-06, + "loss": 2.0233, + "step": 8320 + }, + { + "epoch": 0.31, + "learning_rate": 9.690184847695914e-06, + "loss": 1.9857, + "step": 8330 + }, + { + "epoch": 0.31, + "learning_rate": 9.689812920742367e-06, + "loss": 1.9263, + "step": 8340 + }, + { + "epoch": 0.31, + "learning_rate": 9.68944099378882e-06, + "loss": 1.908, + "step": 8350 + }, + { + "epoch": 0.31, + "learning_rate": 9.689069066835274e-06, + "loss": 1.9687, + "step": 8360 + }, + { + "epoch": 0.31, + "learning_rate": 9.688697139881727e-06, + "loss": 1.9584, + "step": 8370 + }, + { + "epoch": 0.31, + "learning_rate": 9.688325212928181e-06, + "loss": 1.9424, + "step": 8380 + }, + { + "epoch": 0.31, + "learning_rate": 9.687953285974634e-06, + "loss": 1.974, + "step": 8390 + }, + { + "epoch": 0.31, + "learning_rate": 9.68758135902109e-06, + "loss": 1.9173, + "step": 8400 + }, + { + "epoch": 0.31, + "eval_loss": 1.8701244592666626, + "eval_runtime": 16.8181, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 8400 + }, + { + "epoch": 0.31, + "learning_rate": 9.687209432067543e-06, + "loss": 1.8277, + "step": 8410 + }, + { + "epoch": 0.31, + "learning_rate": 9.686837505113996e-06, + "loss": 2.105, + "step": 8420 + }, + { + "epoch": 0.31, + "learning_rate": 9.68646557816045e-06, + "loss": 2.0949, + "step": 8430 + }, + { + "epoch": 0.31, + "learning_rate": 9.686093651206903e-06, + "loss": 2.0093, + "step": 8440 + }, + { + "epoch": 0.31, + "learning_rate": 9.685721724253357e-06, + "loss": 2.2189, + "step": 8450 + }, + { + "epoch": 0.31, + "learning_rate": 9.685349797299812e-06, + "loss": 2.0575, + "step": 8460 + }, + { + "epoch": 0.32, + "learning_rate": 9.684977870346265e-06, + "loss": 2.0442, + "step": 8470 + }, + { + "epoch": 0.32, + "learning_rate": 9.684605943392719e-06, + "loss": 1.9435, + "step": 8480 + }, + { + "epoch": 0.32, + "learning_rate": 9.684234016439172e-06, + "loss": 2.0108, + "step": 8490 + }, + { + "epoch": 0.32, + "learning_rate": 9.683862089485626e-06, + "loss": 2.0075, + "step": 8500 + }, + { + "epoch": 0.32, + "eval_loss": 1.8706469535827637, + "eval_runtime": 16.8287, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 8500 + }, + { + "epoch": 0.32, + "learning_rate": 9.68349016253208e-06, + "loss": 2.0971, + "step": 8510 + }, + { + "epoch": 0.32, + "learning_rate": 9.683118235578534e-06, + "loss": 2.0299, + "step": 8520 + }, + { + "epoch": 0.32, + "learning_rate": 9.682746308624988e-06, + "loss": 1.9106, + "step": 8530 + }, + { + "epoch": 0.32, + "learning_rate": 9.682374381671441e-06, + "loss": 1.789, + "step": 8540 + }, + { + "epoch": 0.32, + "learning_rate": 9.682002454717893e-06, + "loss": 1.8727, + "step": 8550 + }, + { + "epoch": 0.32, + "learning_rate": 9.681630527764348e-06, + "loss": 1.9376, + "step": 8560 + }, + { + "epoch": 0.32, + "learning_rate": 9.681258600810802e-06, + "loss": 1.9903, + "step": 8570 + }, + { + "epoch": 0.32, + "learning_rate": 9.680886673857255e-06, + "loss": 1.8791, + "step": 8580 + }, + { + "epoch": 0.32, + "learning_rate": 9.680514746903709e-06, + "loss": 1.9755, + "step": 8590 + }, + { + "epoch": 0.32, + "learning_rate": 9.680142819950162e-06, + "loss": 2.0905, + "step": 8600 + }, + { + "epoch": 0.32, + "eval_loss": 1.8696200847625732, + "eval_runtime": 16.8165, + "eval_samples_per_second": 59.465, + "eval_steps_per_second": 3.746, + "step": 8600 + }, + { + "epoch": 0.32, + "learning_rate": 9.679770892996615e-06, + "loss": 2.0818, + "step": 8610 + }, + { + "epoch": 0.32, + "learning_rate": 9.67939896604307e-06, + "loss": 1.8777, + "step": 8620 + }, + { + "epoch": 0.32, + "learning_rate": 9.679027039089524e-06, + "loss": 2.117, + "step": 8630 + }, + { + "epoch": 0.32, + "learning_rate": 9.678655112135978e-06, + "loss": 2.0485, + "step": 8640 + }, + { + "epoch": 0.32, + "learning_rate": 9.678283185182431e-06, + "loss": 1.904, + "step": 8650 + }, + { + "epoch": 0.32, + "learning_rate": 9.677911258228884e-06, + "loss": 2.0025, + "step": 8660 + }, + { + "epoch": 0.32, + "learning_rate": 9.677539331275338e-06, + "loss": 1.9852, + "step": 8670 + }, + { + "epoch": 0.32, + "learning_rate": 9.677167404321791e-06, + "loss": 1.8404, + "step": 8680 + }, + { + "epoch": 0.32, + "learning_rate": 9.676795477368247e-06, + "loss": 1.9061, + "step": 8690 + }, + { + "epoch": 0.32, + "learning_rate": 9.6764235504147e-06, + "loss": 1.9931, + "step": 8700 + }, + { + "epoch": 0.32, + "eval_loss": 1.8706672191619873, + "eval_runtime": 16.831, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 8700 + }, + { + "epoch": 0.32, + "learning_rate": 9.676051623461153e-06, + "loss": 1.8874, + "step": 8710 + }, + { + "epoch": 0.32, + "learning_rate": 9.675679696507607e-06, + "loss": 1.8478, + "step": 8720 + }, + { + "epoch": 0.32, + "learning_rate": 9.67530776955406e-06, + "loss": 1.9486, + "step": 8730 + }, + { + "epoch": 0.33, + "learning_rate": 9.674935842600514e-06, + "loss": 1.8841, + "step": 8740 + }, + { + "epoch": 0.33, + "learning_rate": 9.674563915646967e-06, + "loss": 1.8593, + "step": 8750 + }, + { + "epoch": 0.33, + "learning_rate": 9.67419198869342e-06, + "loss": 1.8346, + "step": 8760 + }, + { + "epoch": 0.33, + "learning_rate": 9.673820061739874e-06, + "loss": 1.8282, + "step": 8770 + }, + { + "epoch": 0.33, + "learning_rate": 9.673448134786328e-06, + "loss": 2.0108, + "step": 8780 + }, + { + "epoch": 0.33, + "learning_rate": 9.673076207832783e-06, + "loss": 1.9766, + "step": 8790 + }, + { + "epoch": 0.33, + "learning_rate": 9.672704280879236e-06, + "loss": 1.9328, + "step": 8800 + }, + { + "epoch": 0.33, + "eval_loss": 1.8670976161956787, + "eval_runtime": 16.8213, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 8800 + }, + { + "epoch": 0.33, + "learning_rate": 9.67233235392569e-06, + "loss": 1.9187, + "step": 8810 + }, + { + "epoch": 0.33, + "learning_rate": 9.671960426972143e-06, + "loss": 1.8738, + "step": 8820 + }, + { + "epoch": 0.33, + "learning_rate": 9.671588500018597e-06, + "loss": 1.9658, + "step": 8830 + }, + { + "epoch": 0.33, + "learning_rate": 9.67121657306505e-06, + "loss": 2.0027, + "step": 8840 + }, + { + "epoch": 0.33, + "learning_rate": 9.670844646111505e-06, + "loss": 1.8268, + "step": 8850 + }, + { + "epoch": 0.33, + "learning_rate": 9.670472719157959e-06, + "loss": 1.9513, + "step": 8860 + }, + { + "epoch": 0.33, + "learning_rate": 9.670100792204412e-06, + "loss": 1.9652, + "step": 8870 + }, + { + "epoch": 0.33, + "learning_rate": 9.669728865250866e-06, + "loss": 2.0514, + "step": 8880 + }, + { + "epoch": 0.33, + "learning_rate": 9.669356938297319e-06, + "loss": 2.0311, + "step": 8890 + }, + { + "epoch": 0.33, + "learning_rate": 9.668985011343773e-06, + "loss": 1.9449, + "step": 8900 + }, + { + "epoch": 0.33, + "eval_loss": 1.8643999099731445, + "eval_runtime": 16.8197, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 8900 + }, + { + "epoch": 0.33, + "learning_rate": 9.668613084390228e-06, + "loss": 2.069, + "step": 8910 + }, + { + "epoch": 0.33, + "learning_rate": 9.66824115743668e-06, + "loss": 1.9548, + "step": 8920 + }, + { + "epoch": 0.33, + "learning_rate": 9.667869230483133e-06, + "loss": 2.0358, + "step": 8930 + }, + { + "epoch": 0.33, + "learning_rate": 9.667497303529586e-06, + "loss": 1.9443, + "step": 8940 + }, + { + "epoch": 0.33, + "learning_rate": 9.667125376576042e-06, + "loss": 1.8525, + "step": 8950 + }, + { + "epoch": 0.33, + "learning_rate": 9.666753449622495e-06, + "loss": 1.9456, + "step": 8960 + }, + { + "epoch": 0.33, + "learning_rate": 9.666381522668948e-06, + "loss": 1.9908, + "step": 8970 + }, + { + "epoch": 0.33, + "learning_rate": 9.666009595715402e-06, + "loss": 1.8824, + "step": 8980 + }, + { + "epoch": 0.33, + "learning_rate": 9.665637668761855e-06, + "loss": 1.845, + "step": 8990 + }, + { + "epoch": 0.33, + "learning_rate": 9.665265741808309e-06, + "loss": 1.9073, + "step": 9000 + }, + { + "epoch": 0.33, + "eval_loss": 1.8662636280059814, + "eval_runtime": 16.8221, + "eval_samples_per_second": 59.446, + "eval_steps_per_second": 3.745, + "step": 9000 + }, + { + "epoch": 0.34, + "learning_rate": 9.664893814854764e-06, + "loss": 1.9108, + "step": 9010 + }, + { + "epoch": 0.34, + "learning_rate": 9.664521887901217e-06, + "loss": 1.8132, + "step": 9020 + }, + { + "epoch": 0.34, + "learning_rate": 9.664149960947671e-06, + "loss": 1.9811, + "step": 9030 + }, + { + "epoch": 0.34, + "learning_rate": 9.663778033994124e-06, + "loss": 1.9575, + "step": 9040 + }, + { + "epoch": 0.34, + "learning_rate": 9.663406107040578e-06, + "loss": 1.9373, + "step": 9050 + }, + { + "epoch": 0.34, + "learning_rate": 9.663034180087031e-06, + "loss": 2.1178, + "step": 9060 + }, + { + "epoch": 0.34, + "learning_rate": 9.662662253133486e-06, + "loss": 2.1018, + "step": 9070 + }, + { + "epoch": 0.34, + "learning_rate": 9.66229032617994e-06, + "loss": 1.8958, + "step": 9080 + }, + { + "epoch": 0.34, + "learning_rate": 9.661918399226393e-06, + "loss": 1.8905, + "step": 9090 + }, + { + "epoch": 0.34, + "learning_rate": 9.661546472272847e-06, + "loss": 1.9774, + "step": 9100 + }, + { + "epoch": 0.34, + "eval_loss": 1.8647375106811523, + "eval_runtime": 16.8, + "eval_samples_per_second": 59.524, + "eval_steps_per_second": 3.75, + "step": 9100 + }, + { + "epoch": 0.34, + "learning_rate": 9.6611745453193e-06, + "loss": 1.9108, + "step": 9110 + }, + { + "epoch": 0.34, + "learning_rate": 9.660802618365754e-06, + "loss": 1.951, + "step": 9120 + }, + { + "epoch": 0.34, + "learning_rate": 9.660430691412207e-06, + "loss": 1.9389, + "step": 9130 + }, + { + "epoch": 0.34, + "learning_rate": 9.66005876445866e-06, + "loss": 1.9521, + "step": 9140 + }, + { + "epoch": 0.34, + "learning_rate": 9.659686837505114e-06, + "loss": 1.7988, + "step": 9150 + }, + { + "epoch": 0.34, + "learning_rate": 9.659314910551568e-06, + "loss": 1.9867, + "step": 9160 + }, + { + "epoch": 0.34, + "learning_rate": 9.658942983598023e-06, + "loss": 1.8457, + "step": 9170 + }, + { + "epoch": 0.34, + "learning_rate": 9.658571056644476e-06, + "loss": 1.9041, + "step": 9180 + }, + { + "epoch": 0.34, + "learning_rate": 9.65819912969093e-06, + "loss": 1.8572, + "step": 9190 + }, + { + "epoch": 0.34, + "learning_rate": 9.657827202737383e-06, + "loss": 1.8756, + "step": 9200 + }, + { + "epoch": 0.34, + "eval_loss": 1.8641449213027954, + "eval_runtime": 16.8099, + "eval_samples_per_second": 59.489, + "eval_steps_per_second": 3.748, + "step": 9200 + }, + { + "epoch": 0.34, + "learning_rate": 9.657455275783837e-06, + "loss": 1.8275, + "step": 9210 + }, + { + "epoch": 0.34, + "learning_rate": 9.65708334883029e-06, + "loss": 2.0637, + "step": 9220 + }, + { + "epoch": 0.34, + "learning_rate": 9.656711421876745e-06, + "loss": 1.9206, + "step": 9230 + }, + { + "epoch": 0.34, + "learning_rate": 9.656339494923199e-06, + "loss": 2.1286, + "step": 9240 + }, + { + "epoch": 0.34, + "learning_rate": 9.655967567969652e-06, + "loss": 2.0932, + "step": 9250 + }, + { + "epoch": 0.34, + "learning_rate": 9.655595641016106e-06, + "loss": 1.9205, + "step": 9260 + }, + { + "epoch": 0.34, + "learning_rate": 9.655223714062559e-06, + "loss": 1.9019, + "step": 9270 + }, + { + "epoch": 0.35, + "learning_rate": 9.654851787109013e-06, + "loss": 2.0212, + "step": 9280 + }, + { + "epoch": 0.35, + "learning_rate": 9.654479860155466e-06, + "loss": 1.9477, + "step": 9290 + }, + { + "epoch": 0.35, + "learning_rate": 9.65410793320192e-06, + "loss": 1.8955, + "step": 9300 + }, + { + "epoch": 0.35, + "eval_loss": 1.8633332252502441, + "eval_runtime": 16.816, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 9300 + }, + { + "epoch": 0.35, + "learning_rate": 9.653736006248373e-06, + "loss": 2.0075, + "step": 9310 + }, + { + "epoch": 0.35, + "learning_rate": 9.653364079294826e-06, + "loss": 2.0321, + "step": 9320 + }, + { + "epoch": 0.35, + "learning_rate": 9.65299215234128e-06, + "loss": 2.1042, + "step": 9330 + }, + { + "epoch": 0.35, + "learning_rate": 9.652620225387735e-06, + "loss": 1.7861, + "step": 9340 + }, + { + "epoch": 0.35, + "learning_rate": 9.652248298434188e-06, + "loss": 2.0919, + "step": 9350 + }, + { + "epoch": 0.35, + "learning_rate": 9.651876371480642e-06, + "loss": 1.8522, + "step": 9360 + }, + { + "epoch": 0.35, + "learning_rate": 9.651504444527095e-06, + "loss": 2.0533, + "step": 9370 + }, + { + "epoch": 0.35, + "learning_rate": 9.651132517573549e-06, + "loss": 2.0081, + "step": 9380 + }, + { + "epoch": 0.35, + "learning_rate": 9.650760590620002e-06, + "loss": 1.9981, + "step": 9390 + }, + { + "epoch": 0.35, + "learning_rate": 9.650388663666457e-06, + "loss": 1.9746, + "step": 9400 + }, + { + "epoch": 0.35, + "eval_loss": 1.8577659130096436, + "eval_runtime": 16.8067, + "eval_samples_per_second": 59.5, + "eval_steps_per_second": 3.749, + "step": 9400 + }, + { + "epoch": 0.35, + "learning_rate": 9.650016736712911e-06, + "loss": 1.9718, + "step": 9410 + }, + { + "epoch": 0.35, + "learning_rate": 9.649644809759364e-06, + "loss": 1.9442, + "step": 9420 + }, + { + "epoch": 0.35, + "learning_rate": 9.649272882805818e-06, + "loss": 1.8887, + "step": 9430 + }, + { + "epoch": 0.35, + "learning_rate": 9.648900955852271e-06, + "loss": 1.9275, + "step": 9440 + }, + { + "epoch": 0.35, + "learning_rate": 9.648529028898725e-06, + "loss": 1.9196, + "step": 9450 + }, + { + "epoch": 0.35, + "learning_rate": 9.64815710194518e-06, + "loss": 2.0226, + "step": 9460 + }, + { + "epoch": 0.35, + "learning_rate": 9.647785174991633e-06, + "loss": 2.0056, + "step": 9470 + }, + { + "epoch": 0.35, + "learning_rate": 9.647413248038087e-06, + "loss": 1.899, + "step": 9480 + }, + { + "epoch": 0.35, + "learning_rate": 9.647041321084539e-06, + "loss": 1.9778, + "step": 9490 + }, + { + "epoch": 0.35, + "learning_rate": 9.646669394130994e-06, + "loss": 1.9409, + "step": 9500 + }, + { + "epoch": 0.35, + "eval_loss": 1.8597506284713745, + "eval_runtime": 16.8325, + "eval_samples_per_second": 59.409, + "eval_steps_per_second": 3.743, + "step": 9500 + }, + { + "epoch": 0.35, + "learning_rate": 9.646297467177447e-06, + "loss": 2.0183, + "step": 9510 + }, + { + "epoch": 0.35, + "learning_rate": 9.6459255402239e-06, + "loss": 1.9728, + "step": 9520 + }, + { + "epoch": 0.35, + "learning_rate": 9.645553613270354e-06, + "loss": 1.8418, + "step": 9530 + }, + { + "epoch": 0.35, + "learning_rate": 9.645181686316808e-06, + "loss": 1.968, + "step": 9540 + }, + { + "epoch": 0.36, + "learning_rate": 9.644809759363261e-06, + "loss": 1.8436, + "step": 9550 + }, + { + "epoch": 0.36, + "learning_rate": 9.644437832409716e-06, + "loss": 2.0512, + "step": 9560 + }, + { + "epoch": 0.36, + "learning_rate": 9.64406590545617e-06, + "loss": 2.0271, + "step": 9570 + }, + { + "epoch": 0.36, + "learning_rate": 9.643693978502623e-06, + "loss": 1.9475, + "step": 9580 + }, + { + "epoch": 0.36, + "learning_rate": 9.643322051549077e-06, + "loss": 1.8715, + "step": 9590 + }, + { + "epoch": 0.36, + "learning_rate": 9.64295012459553e-06, + "loss": 2.0537, + "step": 9600 + }, + { + "epoch": 0.36, + "eval_loss": 1.8580541610717773, + "eval_runtime": 16.8355, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 9600 + }, + { + "epoch": 0.36, + "learning_rate": 9.642578197641983e-06, + "loss": 2.0827, + "step": 9610 + }, + { + "epoch": 0.36, + "learning_rate": 9.642206270688439e-06, + "loss": 1.8029, + "step": 9620 + }, + { + "epoch": 0.36, + "learning_rate": 9.641834343734892e-06, + "loss": 2.0328, + "step": 9630 + }, + { + "epoch": 0.36, + "learning_rate": 9.641462416781346e-06, + "loss": 1.9055, + "step": 9640 + }, + { + "epoch": 0.36, + "learning_rate": 9.641090489827799e-06, + "loss": 2.1182, + "step": 9650 + }, + { + "epoch": 0.36, + "learning_rate": 9.640718562874252e-06, + "loss": 1.8678, + "step": 9660 + }, + { + "epoch": 0.36, + "learning_rate": 9.640346635920706e-06, + "loss": 2.0485, + "step": 9670 + }, + { + "epoch": 0.36, + "learning_rate": 9.63997470896716e-06, + "loss": 1.994, + "step": 9680 + }, + { + "epoch": 0.36, + "learning_rate": 9.639602782013613e-06, + "loss": 2.0223, + "step": 9690 + }, + { + "epoch": 0.36, + "learning_rate": 9.639230855060066e-06, + "loss": 2.01, + "step": 9700 + }, + { + "epoch": 0.36, + "eval_loss": 1.8563753366470337, + "eval_runtime": 16.8133, + "eval_samples_per_second": 59.477, + "eval_steps_per_second": 3.747, + "step": 9700 + }, + { + "epoch": 0.36, + "learning_rate": 9.63885892810652e-06, + "loss": 1.9113, + "step": 9710 + }, + { + "epoch": 0.36, + "learning_rate": 9.638487001152975e-06, + "loss": 1.8786, + "step": 9720 + }, + { + "epoch": 0.36, + "learning_rate": 9.638115074199428e-06, + "loss": 2.0031, + "step": 9730 + }, + { + "epoch": 0.36, + "learning_rate": 9.637743147245882e-06, + "loss": 2.0529, + "step": 9740 + }, + { + "epoch": 0.36, + "learning_rate": 9.637371220292335e-06, + "loss": 1.9154, + "step": 9750 + }, + { + "epoch": 0.36, + "learning_rate": 9.636999293338789e-06, + "loss": 1.7814, + "step": 9760 + }, + { + "epoch": 0.36, + "learning_rate": 9.636627366385242e-06, + "loss": 2.1063, + "step": 9770 + }, + { + "epoch": 0.36, + "learning_rate": 9.636255439431697e-06, + "loss": 1.9382, + "step": 9780 + }, + { + "epoch": 0.36, + "learning_rate": 9.63588351247815e-06, + "loss": 2.0797, + "step": 9790 + }, + { + "epoch": 0.36, + "learning_rate": 9.635511585524604e-06, + "loss": 1.9055, + "step": 9800 + }, + { + "epoch": 0.36, + "eval_loss": 1.8567332029342651, + "eval_runtime": 16.8204, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.745, + "step": 9800 + }, + { + "epoch": 0.36, + "learning_rate": 9.635139658571058e-06, + "loss": 2.0969, + "step": 9810 + }, + { + "epoch": 0.37, + "learning_rate": 9.634767731617511e-06, + "loss": 1.8479, + "step": 9820 + }, + { + "epoch": 0.37, + "learning_rate": 9.634395804663965e-06, + "loss": 1.997, + "step": 9830 + }, + { + "epoch": 0.37, + "learning_rate": 9.634023877710418e-06, + "loss": 1.8851, + "step": 9840 + }, + { + "epoch": 0.37, + "learning_rate": 9.633651950756873e-06, + "loss": 1.9262, + "step": 9850 + }, + { + "epoch": 0.37, + "learning_rate": 9.633280023803325e-06, + "loss": 1.911, + "step": 9860 + }, + { + "epoch": 0.37, + "learning_rate": 9.632908096849778e-06, + "loss": 1.9572, + "step": 9870 + }, + { + "epoch": 0.37, + "learning_rate": 9.632536169896232e-06, + "loss": 2.0842, + "step": 9880 + }, + { + "epoch": 0.37, + "learning_rate": 9.632164242942687e-06, + "loss": 2.0615, + "step": 9890 + }, + { + "epoch": 0.37, + "learning_rate": 9.63179231598914e-06, + "loss": 1.999, + "step": 9900 + }, + { + "epoch": 0.37, + "eval_loss": 1.8570407629013062, + "eval_runtime": 16.814, + "eval_samples_per_second": 59.474, + "eval_steps_per_second": 3.747, + "step": 9900 + }, + { + "epoch": 0.37, + "learning_rate": 9.631420389035594e-06, + "loss": 1.8704, + "step": 9910 + }, + { + "epoch": 0.37, + "learning_rate": 9.631048462082047e-06, + "loss": 2.0175, + "step": 9920 + }, + { + "epoch": 0.37, + "learning_rate": 9.630676535128501e-06, + "loss": 1.9032, + "step": 9930 + }, + { + "epoch": 0.37, + "learning_rate": 9.630304608174954e-06, + "loss": 1.9634, + "step": 9940 + }, + { + "epoch": 0.37, + "learning_rate": 9.62993268122141e-06, + "loss": 2.0186, + "step": 9950 + }, + { + "epoch": 0.37, + "learning_rate": 9.629560754267863e-06, + "loss": 1.8741, + "step": 9960 + }, + { + "epoch": 0.37, + "learning_rate": 9.629188827314316e-06, + "loss": 1.9107, + "step": 9970 + }, + { + "epoch": 0.37, + "learning_rate": 9.62881690036077e-06, + "loss": 1.8088, + "step": 9980 + }, + { + "epoch": 0.37, + "learning_rate": 9.628444973407223e-06, + "loss": 1.942, + "step": 9990 + }, + { + "epoch": 0.37, + "learning_rate": 9.628073046453677e-06, + "loss": 1.9663, + "step": 10000 + }, + { + "epoch": 0.37, + "eval_loss": 1.8567376136779785, + "eval_runtime": 16.8369, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 10000 + }, + { + "epoch": 0.37, + "learning_rate": 9.627701119500132e-06, + "loss": 1.9407, + "step": 10010 + }, + { + "epoch": 0.37, + "learning_rate": 9.627329192546585e-06, + "loss": 1.8744, + "step": 10020 + }, + { + "epoch": 0.37, + "learning_rate": 9.626957265593039e-06, + "loss": 1.9235, + "step": 10030 + }, + { + "epoch": 0.37, + "learning_rate": 9.626585338639492e-06, + "loss": 1.9835, + "step": 10040 + }, + { + "epoch": 0.37, + "learning_rate": 9.626213411685946e-06, + "loss": 1.9128, + "step": 10050 + }, + { + "epoch": 0.37, + "learning_rate": 9.6258414847324e-06, + "loss": 1.8057, + "step": 10060 + }, + { + "epoch": 0.37, + "learning_rate": 9.625469557778853e-06, + "loss": 2.1001, + "step": 10070 + }, + { + "epoch": 0.37, + "learning_rate": 9.625097630825306e-06, + "loss": 2.1614, + "step": 10080 + }, + { + "epoch": 0.38, + "learning_rate": 9.62472570387176e-06, + "loss": 1.9882, + "step": 10090 + }, + { + "epoch": 0.38, + "learning_rate": 9.624353776918213e-06, + "loss": 1.8385, + "step": 10100 + }, + { + "epoch": 0.38, + "eval_loss": 1.8523606061935425, + "eval_runtime": 16.8283, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 10100 + }, + { + "epoch": 0.38, + "learning_rate": 9.623981849964668e-06, + "loss": 1.9698, + "step": 10110 + }, + { + "epoch": 0.38, + "learning_rate": 9.623609923011122e-06, + "loss": 1.9215, + "step": 10120 + }, + { + "epoch": 0.38, + "learning_rate": 9.623237996057575e-06, + "loss": 1.9724, + "step": 10130 + }, + { + "epoch": 0.38, + "learning_rate": 9.622866069104029e-06, + "loss": 1.9774, + "step": 10140 + }, + { + "epoch": 0.38, + "learning_rate": 9.622494142150482e-06, + "loss": 2.004, + "step": 10150 + }, + { + "epoch": 0.38, + "learning_rate": 9.622122215196936e-06, + "loss": 1.8738, + "step": 10160 + }, + { + "epoch": 0.38, + "learning_rate": 9.62175028824339e-06, + "loss": 1.9645, + "step": 10170 + }, + { + "epoch": 0.38, + "learning_rate": 9.621378361289844e-06, + "loss": 1.9608, + "step": 10180 + }, + { + "epoch": 0.38, + "learning_rate": 9.621006434336298e-06, + "loss": 1.8931, + "step": 10190 + }, + { + "epoch": 0.38, + "learning_rate": 9.620634507382751e-06, + "loss": 1.9356, + "step": 10200 + }, + { + "epoch": 0.38, + "eval_loss": 1.8533039093017578, + "eval_runtime": 16.8188, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 10200 + }, + { + "epoch": 0.38, + "learning_rate": 9.620262580429205e-06, + "loss": 1.8837, + "step": 10210 + }, + { + "epoch": 0.38, + "learning_rate": 9.619890653475658e-06, + "loss": 1.862, + "step": 10220 + }, + { + "epoch": 0.38, + "learning_rate": 9.619518726522113e-06, + "loss": 1.9737, + "step": 10230 + }, + { + "epoch": 0.38, + "learning_rate": 9.619146799568565e-06, + "loss": 1.969, + "step": 10240 + }, + { + "epoch": 0.38, + "learning_rate": 9.618774872615018e-06, + "loss": 1.8778, + "step": 10250 + }, + { + "epoch": 0.38, + "learning_rate": 9.618402945661472e-06, + "loss": 1.9126, + "step": 10260 + }, + { + "epoch": 0.38, + "learning_rate": 9.618031018707927e-06, + "loss": 1.8314, + "step": 10270 + }, + { + "epoch": 0.38, + "learning_rate": 9.61765909175438e-06, + "loss": 1.885, + "step": 10280 + }, + { + "epoch": 0.38, + "learning_rate": 9.617287164800834e-06, + "loss": 2.0045, + "step": 10290 + }, + { + "epoch": 0.38, + "learning_rate": 9.616915237847287e-06, + "loss": 1.9269, + "step": 10300 + }, + { + "epoch": 0.38, + "eval_loss": 1.8533763885498047, + "eval_runtime": 16.8312, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 10300 + }, + { + "epoch": 0.38, + "learning_rate": 9.61654331089374e-06, + "loss": 1.9042, + "step": 10310 + }, + { + "epoch": 0.38, + "learning_rate": 9.616171383940194e-06, + "loss": 1.9717, + "step": 10320 + }, + { + "epoch": 0.38, + "learning_rate": 9.61579945698665e-06, + "loss": 1.886, + "step": 10330 + }, + { + "epoch": 0.38, + "learning_rate": 9.615427530033103e-06, + "loss": 1.8995, + "step": 10340 + }, + { + "epoch": 0.38, + "learning_rate": 9.615055603079556e-06, + "loss": 1.8554, + "step": 10350 + }, + { + "epoch": 0.39, + "learning_rate": 9.61468367612601e-06, + "loss": 1.9901, + "step": 10360 + }, + { + "epoch": 0.39, + "learning_rate": 9.614311749172463e-06, + "loss": 2.0715, + "step": 10370 + }, + { + "epoch": 0.39, + "learning_rate": 9.613939822218917e-06, + "loss": 2.0556, + "step": 10380 + }, + { + "epoch": 0.39, + "learning_rate": 9.613567895265372e-06, + "loss": 1.9045, + "step": 10390 + }, + { + "epoch": 0.39, + "learning_rate": 9.613195968311825e-06, + "loss": 1.9519, + "step": 10400 + }, + { + "epoch": 0.39, + "eval_loss": 1.8529212474822998, + "eval_runtime": 16.8134, + "eval_samples_per_second": 59.476, + "eval_steps_per_second": 3.747, + "step": 10400 + }, + { + "epoch": 0.39, + "learning_rate": 9.612824041358279e-06, + "loss": 2.0166, + "step": 10410 + }, + { + "epoch": 0.39, + "learning_rate": 9.612452114404732e-06, + "loss": 2.0801, + "step": 10420 + }, + { + "epoch": 0.39, + "learning_rate": 9.612080187451184e-06, + "loss": 2.0127, + "step": 10430 + }, + { + "epoch": 0.39, + "learning_rate": 9.61170826049764e-06, + "loss": 2.0158, + "step": 10440 + }, + { + "epoch": 0.39, + "learning_rate": 9.611336333544093e-06, + "loss": 1.8752, + "step": 10450 + }, + { + "epoch": 0.39, + "learning_rate": 9.610964406590546e-06, + "loss": 1.9225, + "step": 10460 + }, + { + "epoch": 0.39, + "learning_rate": 9.610592479637e-06, + "loss": 1.9323, + "step": 10470 + }, + { + "epoch": 0.39, + "learning_rate": 9.610220552683453e-06, + "loss": 1.9977, + "step": 10480 + }, + { + "epoch": 0.39, + "learning_rate": 9.609848625729906e-06, + "loss": 2.0431, + "step": 10490 + }, + { + "epoch": 0.39, + "learning_rate": 9.609476698776362e-06, + "loss": 1.988, + "step": 10500 + }, + { + "epoch": 0.39, + "eval_loss": 1.8510937690734863, + "eval_runtime": 16.8243, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 10500 + }, + { + "epoch": 0.39, + "learning_rate": 9.609104771822815e-06, + "loss": 1.8602, + "step": 10510 + }, + { + "epoch": 0.39, + "learning_rate": 9.608732844869269e-06, + "loss": 1.932, + "step": 10520 + }, + { + "epoch": 0.39, + "learning_rate": 9.608360917915722e-06, + "loss": 1.8225, + "step": 10530 + }, + { + "epoch": 0.39, + "learning_rate": 9.607988990962175e-06, + "loss": 1.9037, + "step": 10540 + }, + { + "epoch": 0.39, + "learning_rate": 9.607617064008629e-06, + "loss": 2.0357, + "step": 10550 + }, + { + "epoch": 0.39, + "learning_rate": 9.607245137055084e-06, + "loss": 1.9619, + "step": 10560 + }, + { + "epoch": 0.39, + "learning_rate": 9.606873210101538e-06, + "loss": 2.0987, + "step": 10570 + }, + { + "epoch": 0.39, + "learning_rate": 9.606501283147991e-06, + "loss": 1.9239, + "step": 10580 + }, + { + "epoch": 0.39, + "learning_rate": 9.606129356194444e-06, + "loss": 1.8333, + "step": 10590 + }, + { + "epoch": 0.39, + "learning_rate": 9.605757429240898e-06, + "loss": 1.9705, + "step": 10600 + }, + { + "epoch": 0.39, + "eval_loss": 1.8516511917114258, + "eval_runtime": 16.8209, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 10600 + }, + { + "epoch": 0.39, + "learning_rate": 9.605385502287351e-06, + "loss": 1.9475, + "step": 10610 + }, + { + "epoch": 0.39, + "learning_rate": 9.605013575333805e-06, + "loss": 1.9137, + "step": 10620 + }, + { + "epoch": 0.4, + "learning_rate": 9.604641648380258e-06, + "loss": 1.9569, + "step": 10630 + }, + { + "epoch": 0.4, + "learning_rate": 9.604269721426712e-06, + "loss": 1.8528, + "step": 10640 + }, + { + "epoch": 0.4, + "learning_rate": 9.603897794473165e-06, + "loss": 1.8664, + "step": 10650 + }, + { + "epoch": 0.4, + "learning_rate": 9.60352586751962e-06, + "loss": 1.9529, + "step": 10660 + }, + { + "epoch": 0.4, + "learning_rate": 9.603153940566074e-06, + "loss": 1.8117, + "step": 10670 + }, + { + "epoch": 0.4, + "learning_rate": 9.602782013612527e-06, + "loss": 1.9474, + "step": 10680 + }, + { + "epoch": 0.4, + "learning_rate": 9.60241008665898e-06, + "loss": 1.8773, + "step": 10690 + }, + { + "epoch": 0.4, + "learning_rate": 9.602038159705434e-06, + "loss": 1.81, + "step": 10700 + }, + { + "epoch": 0.4, + "eval_loss": 1.850650668144226, + "eval_runtime": 16.8291, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.744, + "step": 10700 + }, + { + "epoch": 0.4, + "learning_rate": 9.601666232751888e-06, + "loss": 2.0255, + "step": 10710 + }, + { + "epoch": 0.4, + "learning_rate": 9.601294305798343e-06, + "loss": 2.0621, + "step": 10720 + }, + { + "epoch": 0.4, + "learning_rate": 9.600922378844796e-06, + "loss": 2.1422, + "step": 10730 + }, + { + "epoch": 0.4, + "learning_rate": 9.60055045189125e-06, + "loss": 1.9984, + "step": 10740 + }, + { + "epoch": 0.4, + "learning_rate": 9.600178524937703e-06, + "loss": 2.0822, + "step": 10750 + }, + { + "epoch": 0.4, + "learning_rate": 9.599806597984157e-06, + "loss": 1.8931, + "step": 10760 + }, + { + "epoch": 0.4, + "learning_rate": 9.59943467103061e-06, + "loss": 1.9722, + "step": 10770 + }, + { + "epoch": 0.4, + "learning_rate": 9.599062744077065e-06, + "loss": 1.8645, + "step": 10780 + }, + { + "epoch": 0.4, + "learning_rate": 9.598690817123519e-06, + "loss": 1.8067, + "step": 10790 + }, + { + "epoch": 0.4, + "learning_rate": 9.59831889016997e-06, + "loss": 1.9581, + "step": 10800 + }, + { + "epoch": 0.4, + "eval_loss": 1.8508254289627075, + "eval_runtime": 16.8214, + "eval_samples_per_second": 59.448, + "eval_steps_per_second": 3.745, + "step": 10800 + }, + { + "epoch": 0.4, + "learning_rate": 9.597946963216424e-06, + "loss": 1.9459, + "step": 10810 + }, + { + "epoch": 0.4, + "learning_rate": 9.597575036262879e-06, + "loss": 2.0849, + "step": 10820 + }, + { + "epoch": 0.4, + "learning_rate": 9.597203109309333e-06, + "loss": 1.8947, + "step": 10830 + }, + { + "epoch": 0.4, + "learning_rate": 9.596831182355786e-06, + "loss": 1.946, + "step": 10840 + }, + { + "epoch": 0.4, + "learning_rate": 9.59645925540224e-06, + "loss": 1.9967, + "step": 10850 + }, + { + "epoch": 0.4, + "learning_rate": 9.596087328448693e-06, + "loss": 1.8801, + "step": 10860 + }, + { + "epoch": 0.4, + "learning_rate": 9.595715401495146e-06, + "loss": 1.9641, + "step": 10870 + }, + { + "epoch": 0.4, + "learning_rate": 9.595343474541602e-06, + "loss": 1.9928, + "step": 10880 + }, + { + "epoch": 0.41, + "learning_rate": 9.594971547588055e-06, + "loss": 1.8806, + "step": 10890 + }, + { + "epoch": 0.41, + "learning_rate": 9.594599620634508e-06, + "loss": 2.0344, + "step": 10900 + }, + { + "epoch": 0.41, + "eval_loss": 1.8497482538223267, + "eval_runtime": 16.8297, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 10900 + }, + { + "epoch": 0.41, + "learning_rate": 9.594227693680962e-06, + "loss": 1.8467, + "step": 10910 + }, + { + "epoch": 0.41, + "learning_rate": 9.593855766727415e-06, + "loss": 2.0472, + "step": 10920 + }, + { + "epoch": 0.41, + "learning_rate": 9.593483839773869e-06, + "loss": 1.9924, + "step": 10930 + }, + { + "epoch": 0.41, + "learning_rate": 9.593111912820324e-06, + "loss": 1.6832, + "step": 10940 + }, + { + "epoch": 0.41, + "learning_rate": 9.592739985866777e-06, + "loss": 1.9562, + "step": 10950 + }, + { + "epoch": 0.41, + "learning_rate": 9.592368058913231e-06, + "loss": 1.9305, + "step": 10960 + }, + { + "epoch": 0.41, + "learning_rate": 9.591996131959684e-06, + "loss": 1.8626, + "step": 10970 + }, + { + "epoch": 0.41, + "learning_rate": 9.591624205006138e-06, + "loss": 1.9778, + "step": 10980 + }, + { + "epoch": 0.41, + "learning_rate": 9.591252278052591e-06, + "loss": 2.0609, + "step": 10990 + }, + { + "epoch": 0.41, + "learning_rate": 9.590880351099045e-06, + "loss": 2.0615, + "step": 11000 + }, + { + "epoch": 0.41, + "eval_loss": 1.8485528230667114, + "eval_runtime": 16.8066, + "eval_samples_per_second": 59.5, + "eval_steps_per_second": 3.749, + "step": 11000 + }, + { + "epoch": 0.41, + "learning_rate": 9.590508424145498e-06, + "loss": 1.965, + "step": 11010 + }, + { + "epoch": 0.41, + "learning_rate": 9.590136497191952e-06, + "loss": 1.9183, + "step": 11020 + }, + { + "epoch": 0.41, + "learning_rate": 9.589764570238405e-06, + "loss": 1.9218, + "step": 11030 + }, + { + "epoch": 0.41, + "learning_rate": 9.589392643284859e-06, + "loss": 1.794, + "step": 11040 + }, + { + "epoch": 0.41, + "learning_rate": 9.589020716331314e-06, + "loss": 1.8992, + "step": 11050 + }, + { + "epoch": 0.41, + "learning_rate": 9.588648789377767e-06, + "loss": 1.8487, + "step": 11060 + }, + { + "epoch": 0.41, + "learning_rate": 9.58827686242422e-06, + "loss": 1.8664, + "step": 11070 + }, + { + "epoch": 0.41, + "learning_rate": 9.587904935470674e-06, + "loss": 1.8848, + "step": 11080 + }, + { + "epoch": 0.41, + "learning_rate": 9.587533008517128e-06, + "loss": 1.8933, + "step": 11090 + }, + { + "epoch": 0.41, + "learning_rate": 9.587161081563581e-06, + "loss": 1.8127, + "step": 11100 + }, + { + "epoch": 0.41, + "eval_loss": 1.8472386598587036, + "eval_runtime": 16.8288, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 11100 + }, + { + "epoch": 0.41, + "learning_rate": 9.586789154610036e-06, + "loss": 2.0499, + "step": 11110 + }, + { + "epoch": 0.41, + "learning_rate": 9.58641722765649e-06, + "loss": 1.8562, + "step": 11120 + }, + { + "epoch": 0.41, + "learning_rate": 9.586045300702943e-06, + "loss": 1.9476, + "step": 11130 + }, + { + "epoch": 0.41, + "learning_rate": 9.585673373749397e-06, + "loss": 1.9857, + "step": 11140 + }, + { + "epoch": 0.41, + "learning_rate": 9.58530144679585e-06, + "loss": 2.0244, + "step": 11150 + }, + { + "epoch": 0.42, + "learning_rate": 9.584929519842303e-06, + "loss": 1.9518, + "step": 11160 + }, + { + "epoch": 0.42, + "learning_rate": 9.584557592888759e-06, + "loss": 1.8763, + "step": 11170 + }, + { + "epoch": 0.42, + "learning_rate": 9.58418566593521e-06, + "loss": 2.1081, + "step": 11180 + }, + { + "epoch": 0.42, + "learning_rate": 9.583813738981664e-06, + "loss": 1.9645, + "step": 11190 + }, + { + "epoch": 0.42, + "learning_rate": 9.583441812028117e-06, + "loss": 1.9471, + "step": 11200 + }, + { + "epoch": 0.42, + "eval_loss": 1.847569465637207, + "eval_runtime": 16.8368, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 11200 + }, + { + "epoch": 0.42, + "learning_rate": 9.583069885074572e-06, + "loss": 1.8609, + "step": 11210 + }, + { + "epoch": 0.42, + "learning_rate": 9.582697958121026e-06, + "loss": 1.9413, + "step": 11220 + }, + { + "epoch": 0.42, + "learning_rate": 9.58232603116748e-06, + "loss": 1.8674, + "step": 11230 + }, + { + "epoch": 0.42, + "learning_rate": 9.581954104213933e-06, + "loss": 1.7665, + "step": 11240 + }, + { + "epoch": 0.42, + "learning_rate": 9.581582177260386e-06, + "loss": 2.0251, + "step": 11250 + }, + { + "epoch": 0.42, + "learning_rate": 9.58121025030684e-06, + "loss": 1.9468, + "step": 11260 + }, + { + "epoch": 0.42, + "learning_rate": 9.580838323353295e-06, + "loss": 1.8334, + "step": 11270 + }, + { + "epoch": 0.42, + "learning_rate": 9.580466396399748e-06, + "loss": 2.009, + "step": 11280 + }, + { + "epoch": 0.42, + "learning_rate": 9.580094469446202e-06, + "loss": 1.9281, + "step": 11290 + }, + { + "epoch": 0.42, + "learning_rate": 9.579722542492655e-06, + "loss": 1.8831, + "step": 11300 + }, + { + "epoch": 0.42, + "eval_loss": 1.847017765045166, + "eval_runtime": 16.8299, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 11300 + }, + { + "epoch": 0.42, + "learning_rate": 9.579350615539109e-06, + "loss": 1.9077, + "step": 11310 + }, + { + "epoch": 0.42, + "learning_rate": 9.578978688585562e-06, + "loss": 1.9013, + "step": 11320 + }, + { + "epoch": 0.42, + "learning_rate": 9.578606761632017e-06, + "loss": 1.8924, + "step": 11330 + }, + { + "epoch": 0.42, + "learning_rate": 9.57823483467847e-06, + "loss": 1.9313, + "step": 11340 + }, + { + "epoch": 0.42, + "learning_rate": 9.577862907724924e-06, + "loss": 1.8765, + "step": 11350 + }, + { + "epoch": 0.42, + "learning_rate": 9.577490980771376e-06, + "loss": 2.0377, + "step": 11360 + }, + { + "epoch": 0.42, + "learning_rate": 9.577119053817831e-06, + "loss": 2.0506, + "step": 11370 + }, + { + "epoch": 0.42, + "learning_rate": 9.576747126864285e-06, + "loss": 1.9891, + "step": 11380 + }, + { + "epoch": 0.42, + "learning_rate": 9.576375199910738e-06, + "loss": 1.9072, + "step": 11390 + }, + { + "epoch": 0.42, + "learning_rate": 9.576003272957192e-06, + "loss": 1.8578, + "step": 11400 + }, + { + "epoch": 0.42, + "eval_loss": 1.8445854187011719, + "eval_runtime": 16.8336, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 11400 + }, + { + "epoch": 0.42, + "learning_rate": 9.575631346003645e-06, + "loss": 1.9203, + "step": 11410 + }, + { + "epoch": 0.42, + "learning_rate": 9.575259419050099e-06, + "loss": 2.0603, + "step": 11420 + }, + { + "epoch": 0.43, + "learning_rate": 9.574887492096554e-06, + "loss": 1.8654, + "step": 11430 + }, + { + "epoch": 0.43, + "learning_rate": 9.574515565143007e-06, + "loss": 1.7942, + "step": 11440 + }, + { + "epoch": 0.43, + "learning_rate": 9.57414363818946e-06, + "loss": 1.9473, + "step": 11450 + }, + { + "epoch": 0.43, + "learning_rate": 9.573771711235914e-06, + "loss": 1.9142, + "step": 11460 + }, + { + "epoch": 0.43, + "learning_rate": 9.573399784282367e-06, + "loss": 1.8657, + "step": 11470 + }, + { + "epoch": 0.43, + "learning_rate": 9.573027857328821e-06, + "loss": 1.9683, + "step": 11480 + }, + { + "epoch": 0.43, + "learning_rate": 9.572655930375276e-06, + "loss": 1.9755, + "step": 11490 + }, + { + "epoch": 0.43, + "learning_rate": 9.57228400342173e-06, + "loss": 2.1186, + "step": 11500 + }, + { + "epoch": 0.43, + "eval_loss": 1.844204068183899, + "eval_runtime": 16.8188, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 11500 + }, + { + "epoch": 0.43, + "learning_rate": 9.571912076468183e-06, + "loss": 2.0759, + "step": 11510 + }, + { + "epoch": 0.43, + "learning_rate": 9.571540149514636e-06, + "loss": 1.9129, + "step": 11520 + }, + { + "epoch": 0.43, + "learning_rate": 9.57116822256109e-06, + "loss": 1.9795, + "step": 11530 + }, + { + "epoch": 0.43, + "learning_rate": 9.570796295607543e-06, + "loss": 2.0057, + "step": 11540 + }, + { + "epoch": 0.43, + "learning_rate": 9.570424368653997e-06, + "loss": 1.9447, + "step": 11550 + }, + { + "epoch": 0.43, + "learning_rate": 9.57005244170045e-06, + "loss": 1.9131, + "step": 11560 + }, + { + "epoch": 0.43, + "learning_rate": 9.569680514746904e-06, + "loss": 2.1643, + "step": 11570 + }, + { + "epoch": 0.43, + "learning_rate": 9.569308587793357e-06, + "loss": 1.8338, + "step": 11580 + }, + { + "epoch": 0.43, + "learning_rate": 9.56893666083981e-06, + "loss": 1.8711, + "step": 11590 + }, + { + "epoch": 0.43, + "learning_rate": 9.568564733886266e-06, + "loss": 1.9805, + "step": 11600 + }, + { + "epoch": 0.43, + "eval_loss": 1.8419580459594727, + "eval_runtime": 16.8368, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 11600 + }, + { + "epoch": 0.43, + "learning_rate": 9.56819280693272e-06, + "loss": 1.9051, + "step": 11610 + }, + { + "epoch": 0.43, + "learning_rate": 9.567820879979173e-06, + "loss": 1.8258, + "step": 11620 + }, + { + "epoch": 0.43, + "learning_rate": 9.567448953025626e-06, + "loss": 1.9221, + "step": 11630 + }, + { + "epoch": 0.43, + "learning_rate": 9.56707702607208e-06, + "loss": 2.1013, + "step": 11640 + }, + { + "epoch": 0.43, + "learning_rate": 9.566705099118533e-06, + "loss": 1.8668, + "step": 11650 + }, + { + "epoch": 0.43, + "learning_rate": 9.566333172164988e-06, + "loss": 1.87, + "step": 11660 + }, + { + "epoch": 0.43, + "learning_rate": 9.565961245211442e-06, + "loss": 1.9749, + "step": 11670 + }, + { + "epoch": 0.43, + "learning_rate": 9.565589318257895e-06, + "loss": 1.9681, + "step": 11680 + }, + { + "epoch": 0.43, + "learning_rate": 9.565217391304349e-06, + "loss": 1.8749, + "step": 11690 + }, + { + "epoch": 0.44, + "learning_rate": 9.564845464350802e-06, + "loss": 1.8478, + "step": 11700 + }, + { + "epoch": 0.44, + "eval_loss": 1.842067003250122, + "eval_runtime": 16.8297, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 11700 + }, + { + "epoch": 0.44, + "learning_rate": 9.564473537397256e-06, + "loss": 1.8597, + "step": 11710 + }, + { + "epoch": 0.44, + "learning_rate": 9.56410161044371e-06, + "loss": 2.0192, + "step": 11720 + }, + { + "epoch": 0.44, + "learning_rate": 9.563729683490164e-06, + "loss": 1.9678, + "step": 11730 + }, + { + "epoch": 0.44, + "learning_rate": 9.563357756536616e-06, + "loss": 1.9967, + "step": 11740 + }, + { + "epoch": 0.44, + "learning_rate": 9.56298582958307e-06, + "loss": 2.0199, + "step": 11750 + }, + { + "epoch": 0.44, + "learning_rate": 9.562613902629525e-06, + "loss": 1.8997, + "step": 11760 + }, + { + "epoch": 0.44, + "learning_rate": 9.562241975675978e-06, + "loss": 1.9952, + "step": 11770 + }, + { + "epoch": 0.44, + "learning_rate": 9.561870048722432e-06, + "loss": 1.8487, + "step": 11780 + }, + { + "epoch": 0.44, + "learning_rate": 9.561498121768885e-06, + "loss": 1.8041, + "step": 11790 + }, + { + "epoch": 0.44, + "learning_rate": 9.561126194815338e-06, + "loss": 1.9987, + "step": 11800 + }, + { + "epoch": 0.44, + "eval_loss": 1.8429533243179321, + "eval_runtime": 16.8184, + "eval_samples_per_second": 59.459, + "eval_steps_per_second": 3.746, + "step": 11800 + }, + { + "epoch": 0.44, + "learning_rate": 9.560754267861792e-06, + "loss": 1.8621, + "step": 11810 + }, + { + "epoch": 0.44, + "learning_rate": 9.560382340908247e-06, + "loss": 1.8946, + "step": 11820 + }, + { + "epoch": 0.44, + "learning_rate": 9.5600104139547e-06, + "loss": 1.9071, + "step": 11830 + }, + { + "epoch": 0.44, + "learning_rate": 9.559638487001154e-06, + "loss": 2.0927, + "step": 11840 + }, + { + "epoch": 0.44, + "learning_rate": 9.559266560047607e-06, + "loss": 1.9437, + "step": 11850 + }, + { + "epoch": 0.44, + "learning_rate": 9.558894633094061e-06, + "loss": 1.8801, + "step": 11860 + }, + { + "epoch": 0.44, + "learning_rate": 9.558522706140514e-06, + "loss": 1.9109, + "step": 11870 + }, + { + "epoch": 0.44, + "learning_rate": 9.55815077918697e-06, + "loss": 1.9168, + "step": 11880 + }, + { + "epoch": 0.44, + "learning_rate": 9.557778852233423e-06, + "loss": 1.9262, + "step": 11890 + }, + { + "epoch": 0.44, + "learning_rate": 9.557406925279876e-06, + "loss": 1.7763, + "step": 11900 + }, + { + "epoch": 0.44, + "eval_loss": 1.843021035194397, + "eval_runtime": 16.8299, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 11900 + }, + { + "epoch": 0.44, + "learning_rate": 9.55703499832633e-06, + "loss": 1.9546, + "step": 11910 + }, + { + "epoch": 0.44, + "learning_rate": 9.556663071372783e-06, + "loss": 1.9474, + "step": 11920 + }, + { + "epoch": 0.44, + "learning_rate": 9.556291144419237e-06, + "loss": 1.94, + "step": 11930 + }, + { + "epoch": 0.44, + "learning_rate": 9.55591921746569e-06, + "loss": 1.9035, + "step": 11940 + }, + { + "epoch": 0.44, + "learning_rate": 9.555547290512144e-06, + "loss": 1.8, + "step": 11950 + }, + { + "epoch": 0.44, + "learning_rate": 9.555175363558597e-06, + "loss": 2.0115, + "step": 11960 + }, + { + "epoch": 0.45, + "learning_rate": 9.55480343660505e-06, + "loss": 1.8331, + "step": 11970 + }, + { + "epoch": 0.45, + "learning_rate": 9.554431509651506e-06, + "loss": 2.0048, + "step": 11980 + }, + { + "epoch": 0.45, + "learning_rate": 9.55405958269796e-06, + "loss": 2.0741, + "step": 11990 + }, + { + "epoch": 0.45, + "learning_rate": 9.553687655744413e-06, + "loss": 2.1347, + "step": 12000 + }, + { + "epoch": 0.45, + "eval_loss": 1.841482400894165, + "eval_runtime": 16.8171, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 12000 + }, + { + "epoch": 0.45, + "learning_rate": 9.553315728790866e-06, + "loss": 1.8329, + "step": 12010 + }, + { + "epoch": 0.45, + "learning_rate": 9.55294380183732e-06, + "loss": 1.9471, + "step": 12020 + }, + { + "epoch": 0.45, + "learning_rate": 9.552571874883773e-06, + "loss": 1.8577, + "step": 12030 + }, + { + "epoch": 0.45, + "learning_rate": 9.552199947930228e-06, + "loss": 1.9633, + "step": 12040 + }, + { + "epoch": 0.45, + "learning_rate": 9.551828020976682e-06, + "loss": 1.9126, + "step": 12050 + }, + { + "epoch": 0.45, + "learning_rate": 9.551456094023135e-06, + "loss": 2.0451, + "step": 12060 + }, + { + "epoch": 0.45, + "learning_rate": 9.551084167069589e-06, + "loss": 1.9179, + "step": 12070 + }, + { + "epoch": 0.45, + "learning_rate": 9.550712240116042e-06, + "loss": 2.0231, + "step": 12080 + }, + { + "epoch": 0.45, + "learning_rate": 9.550340313162496e-06, + "loss": 1.8845, + "step": 12090 + }, + { + "epoch": 0.45, + "learning_rate": 9.54996838620895e-06, + "loss": 1.8396, + "step": 12100 + }, + { + "epoch": 0.45, + "eval_loss": 1.8402087688446045, + "eval_runtime": 16.8106, + "eval_samples_per_second": 59.486, + "eval_steps_per_second": 3.748, + "step": 12100 + }, + { + "epoch": 0.45, + "learning_rate": 9.549596459255404e-06, + "loss": 1.8092, + "step": 12110 + }, + { + "epoch": 0.45, + "learning_rate": 9.549224532301856e-06, + "loss": 2.0054, + "step": 12120 + }, + { + "epoch": 0.45, + "learning_rate": 9.54885260534831e-06, + "loss": 1.972, + "step": 12130 + }, + { + "epoch": 0.45, + "learning_rate": 9.548480678394765e-06, + "loss": 1.9161, + "step": 12140 + }, + { + "epoch": 0.45, + "learning_rate": 9.548108751441218e-06, + "loss": 1.7991, + "step": 12150 + }, + { + "epoch": 0.45, + "learning_rate": 9.547736824487671e-06, + "loss": 1.9737, + "step": 12160 + }, + { + "epoch": 0.45, + "learning_rate": 9.547364897534125e-06, + "loss": 1.9063, + "step": 12170 + }, + { + "epoch": 0.45, + "learning_rate": 9.546992970580578e-06, + "loss": 2.0464, + "step": 12180 + }, + { + "epoch": 0.45, + "learning_rate": 9.546621043627032e-06, + "loss": 1.8624, + "step": 12190 + }, + { + "epoch": 0.45, + "learning_rate": 9.546249116673485e-06, + "loss": 1.9432, + "step": 12200 + }, + { + "epoch": 0.45, + "eval_loss": 1.8391833305358887, + "eval_runtime": 16.8099, + "eval_samples_per_second": 59.489, + "eval_steps_per_second": 3.748, + "step": 12200 + }, + { + "epoch": 0.45, + "learning_rate": 9.54587718971994e-06, + "loss": 1.8992, + "step": 12210 + }, + { + "epoch": 0.45, + "learning_rate": 9.545505262766394e-06, + "loss": 1.9265, + "step": 12220 + }, + { + "epoch": 0.45, + "learning_rate": 9.545133335812847e-06, + "loss": 1.9267, + "step": 12230 + }, + { + "epoch": 0.46, + "learning_rate": 9.5447614088593e-06, + "loss": 1.7988, + "step": 12240 + }, + { + "epoch": 0.46, + "learning_rate": 9.544389481905754e-06, + "loss": 1.9202, + "step": 12250 + }, + { + "epoch": 0.46, + "learning_rate": 9.544017554952208e-06, + "loss": 1.8807, + "step": 12260 + }, + { + "epoch": 0.46, + "learning_rate": 9.543645627998663e-06, + "loss": 1.8081, + "step": 12270 + }, + { + "epoch": 0.46, + "learning_rate": 9.543273701045116e-06, + "loss": 1.9412, + "step": 12280 + }, + { + "epoch": 0.46, + "learning_rate": 9.54290177409157e-06, + "loss": 1.8884, + "step": 12290 + }, + { + "epoch": 0.46, + "learning_rate": 9.542529847138022e-06, + "loss": 1.9445, + "step": 12300 + }, + { + "epoch": 0.46, + "eval_loss": 1.8391860723495483, + "eval_runtime": 16.8276, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 12300 + }, + { + "epoch": 0.46, + "learning_rate": 9.542157920184477e-06, + "loss": 2.0575, + "step": 12310 + }, + { + "epoch": 0.46, + "learning_rate": 9.54178599323093e-06, + "loss": 1.8342, + "step": 12320 + }, + { + "epoch": 0.46, + "learning_rate": 9.541414066277384e-06, + "loss": 1.801, + "step": 12330 + }, + { + "epoch": 0.46, + "learning_rate": 9.541042139323837e-06, + "loss": 1.9542, + "step": 12340 + }, + { + "epoch": 0.46, + "learning_rate": 9.54067021237029e-06, + "loss": 1.9183, + "step": 12350 + }, + { + "epoch": 0.46, + "learning_rate": 9.540298285416744e-06, + "loss": 1.9173, + "step": 12360 + }, + { + "epoch": 0.46, + "learning_rate": 9.539926358463199e-06, + "loss": 1.962, + "step": 12370 + }, + { + "epoch": 0.46, + "learning_rate": 9.539554431509653e-06, + "loss": 1.9862, + "step": 12380 + }, + { + "epoch": 0.46, + "learning_rate": 9.539182504556106e-06, + "loss": 1.9318, + "step": 12390 + }, + { + "epoch": 0.46, + "learning_rate": 9.53881057760256e-06, + "loss": 1.9166, + "step": 12400 + }, + { + "epoch": 0.46, + "eval_loss": 1.8377732038497925, + "eval_runtime": 16.8299, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 12400 + }, + { + "epoch": 0.46, + "learning_rate": 9.538438650649013e-06, + "loss": 2.0308, + "step": 12410 + }, + { + "epoch": 0.46, + "learning_rate": 9.538066723695466e-06, + "loss": 1.9418, + "step": 12420 + }, + { + "epoch": 0.46, + "learning_rate": 9.537694796741922e-06, + "loss": 1.9811, + "step": 12430 + }, + { + "epoch": 0.46, + "learning_rate": 9.537322869788375e-06, + "loss": 1.9416, + "step": 12440 + }, + { + "epoch": 0.46, + "learning_rate": 9.536950942834829e-06, + "loss": 1.987, + "step": 12450 + }, + { + "epoch": 0.46, + "learning_rate": 9.536579015881282e-06, + "loss": 1.9649, + "step": 12460 + }, + { + "epoch": 0.46, + "learning_rate": 9.536207088927735e-06, + "loss": 1.949, + "step": 12470 + }, + { + "epoch": 0.46, + "learning_rate": 9.535835161974189e-06, + "loss": 1.8417, + "step": 12480 + }, + { + "epoch": 0.46, + "learning_rate": 9.535463235020642e-06, + "loss": 1.8234, + "step": 12490 + }, + { + "epoch": 0.46, + "learning_rate": 9.535091308067096e-06, + "loss": 1.8046, + "step": 12500 + }, + { + "epoch": 0.46, + "eval_loss": 1.8379321098327637, + "eval_runtime": 16.822, + "eval_samples_per_second": 59.446, + "eval_steps_per_second": 3.745, + "step": 12500 + }, + { + "epoch": 0.47, + "learning_rate": 9.53471938111355e-06, + "loss": 1.9002, + "step": 12510 + }, + { + "epoch": 0.47, + "learning_rate": 9.534347454160003e-06, + "loss": 1.8896, + "step": 12520 + }, + { + "epoch": 0.47, + "learning_rate": 9.533975527206458e-06, + "loss": 1.8854, + "step": 12530 + }, + { + "epoch": 0.47, + "learning_rate": 9.533603600252911e-06, + "loss": 1.928, + "step": 12540 + }, + { + "epoch": 0.47, + "learning_rate": 9.533231673299365e-06, + "loss": 1.8974, + "step": 12550 + }, + { + "epoch": 0.47, + "learning_rate": 9.532859746345818e-06, + "loss": 1.9013, + "step": 12560 + }, + { + "epoch": 0.47, + "learning_rate": 9.532487819392272e-06, + "loss": 1.9722, + "step": 12570 + }, + { + "epoch": 0.47, + "learning_rate": 9.532115892438725e-06, + "loss": 1.8973, + "step": 12580 + }, + { + "epoch": 0.47, + "learning_rate": 9.53174396548518e-06, + "loss": 1.9055, + "step": 12590 + }, + { + "epoch": 0.47, + "learning_rate": 9.531372038531634e-06, + "loss": 1.9517, + "step": 12600 + }, + { + "epoch": 0.47, + "eval_loss": 1.8372893333435059, + "eval_runtime": 16.8314, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 12600 + }, + { + "epoch": 0.47, + "learning_rate": 9.531000111578087e-06, + "loss": 1.829, + "step": 12610 + }, + { + "epoch": 0.47, + "learning_rate": 9.53062818462454e-06, + "loss": 1.9814, + "step": 12620 + }, + { + "epoch": 0.47, + "learning_rate": 9.530256257670994e-06, + "loss": 1.837, + "step": 12630 + }, + { + "epoch": 0.47, + "learning_rate": 9.529884330717448e-06, + "loss": 1.9487, + "step": 12640 + }, + { + "epoch": 0.47, + "learning_rate": 9.529512403763903e-06, + "loss": 1.6875, + "step": 12650 + }, + { + "epoch": 0.47, + "learning_rate": 9.529140476810356e-06, + "loss": 1.8731, + "step": 12660 + }, + { + "epoch": 0.47, + "learning_rate": 9.52876854985681e-06, + "loss": 1.8459, + "step": 12670 + }, + { + "epoch": 0.47, + "learning_rate": 9.528396622903261e-06, + "loss": 2.0183, + "step": 12680 + }, + { + "epoch": 0.47, + "learning_rate": 9.528024695949717e-06, + "loss": 1.8784, + "step": 12690 + }, + { + "epoch": 0.47, + "learning_rate": 9.52765276899617e-06, + "loss": 1.9327, + "step": 12700 + }, + { + "epoch": 0.47, + "eval_loss": 1.8363125324249268, + "eval_runtime": 16.8271, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 12700 + }, + { + "epoch": 0.47, + "learning_rate": 9.527280842042624e-06, + "loss": 1.986, + "step": 12710 + }, + { + "epoch": 0.47, + "learning_rate": 9.526908915089077e-06, + "loss": 1.8515, + "step": 12720 + }, + { + "epoch": 0.47, + "learning_rate": 9.52653698813553e-06, + "loss": 1.8577, + "step": 12730 + }, + { + "epoch": 0.47, + "learning_rate": 9.526165061181984e-06, + "loss": 1.8856, + "step": 12740 + }, + { + "epoch": 0.47, + "learning_rate": 9.525793134228437e-06, + "loss": 1.9459, + "step": 12750 + }, + { + "epoch": 0.47, + "learning_rate": 9.525421207274893e-06, + "loss": 1.9956, + "step": 12760 + }, + { + "epoch": 0.47, + "learning_rate": 9.525049280321346e-06, + "loss": 1.8494, + "step": 12770 + }, + { + "epoch": 0.48, + "learning_rate": 9.5246773533678e-06, + "loss": 2.0059, + "step": 12780 + }, + { + "epoch": 0.48, + "learning_rate": 9.524305426414253e-06, + "loss": 1.9044, + "step": 12790 + }, + { + "epoch": 0.48, + "learning_rate": 9.523933499460706e-06, + "loss": 1.9194, + "step": 12800 + }, + { + "epoch": 0.48, + "eval_loss": 1.8350125551223755, + "eval_runtime": 16.8288, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 12800 + }, + { + "epoch": 0.48, + "learning_rate": 9.52356157250716e-06, + "loss": 1.7897, + "step": 12810 + }, + { + "epoch": 0.48, + "learning_rate": 9.523189645553615e-06, + "loss": 2.0779, + "step": 12820 + }, + { + "epoch": 0.48, + "learning_rate": 9.522817718600068e-06, + "loss": 1.8979, + "step": 12830 + }, + { + "epoch": 0.48, + "learning_rate": 9.522445791646522e-06, + "loss": 1.9109, + "step": 12840 + }, + { + "epoch": 0.48, + "learning_rate": 9.522073864692975e-06, + "loss": 1.9778, + "step": 12850 + }, + { + "epoch": 0.48, + "learning_rate": 9.521701937739429e-06, + "loss": 1.9508, + "step": 12860 + }, + { + "epoch": 0.48, + "learning_rate": 9.521330010785882e-06, + "loss": 1.9517, + "step": 12870 + }, + { + "epoch": 0.48, + "learning_rate": 9.520958083832336e-06, + "loss": 1.8181, + "step": 12880 + }, + { + "epoch": 0.48, + "learning_rate": 9.52058615687879e-06, + "loss": 1.9745, + "step": 12890 + }, + { + "epoch": 0.48, + "learning_rate": 9.520214229925243e-06, + "loss": 1.7343, + "step": 12900 + }, + { + "epoch": 0.48, + "eval_loss": 1.8344188928604126, + "eval_runtime": 16.8309, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 12900 + }, + { + "epoch": 0.48, + "learning_rate": 9.519842302971696e-06, + "loss": 1.9416, + "step": 12910 + }, + { + "epoch": 0.48, + "learning_rate": 9.519470376018151e-06, + "loss": 1.848, + "step": 12920 + }, + { + "epoch": 0.48, + "learning_rate": 9.519098449064605e-06, + "loss": 1.8714, + "step": 12930 + }, + { + "epoch": 0.48, + "learning_rate": 9.518726522111058e-06, + "loss": 1.9935, + "step": 12940 + }, + { + "epoch": 0.48, + "learning_rate": 9.518354595157512e-06, + "loss": 1.9201, + "step": 12950 + }, + { + "epoch": 0.48, + "learning_rate": 9.517982668203965e-06, + "loss": 1.9717, + "step": 12960 + }, + { + "epoch": 0.48, + "learning_rate": 9.517610741250419e-06, + "loss": 1.9419, + "step": 12970 + }, + { + "epoch": 0.48, + "learning_rate": 9.517238814296874e-06, + "loss": 1.9144, + "step": 12980 + }, + { + "epoch": 0.48, + "learning_rate": 9.516866887343327e-06, + "loss": 1.9451, + "step": 12990 + }, + { + "epoch": 0.48, + "learning_rate": 9.51649496038978e-06, + "loss": 1.9164, + "step": 13000 + }, + { + "epoch": 0.48, + "eval_loss": 1.8348335027694702, + "eval_runtime": 16.8201, + "eval_samples_per_second": 59.453, + "eval_steps_per_second": 3.746, + "step": 13000 + }, + { + "epoch": 0.48, + "learning_rate": 9.516123033436234e-06, + "loss": 1.8944, + "step": 13010 + }, + { + "epoch": 0.48, + "learning_rate": 9.515751106482688e-06, + "loss": 1.9754, + "step": 13020 + }, + { + "epoch": 0.48, + "learning_rate": 9.515379179529141e-06, + "loss": 2.0317, + "step": 13030 + }, + { + "epoch": 0.48, + "learning_rate": 9.515007252575596e-06, + "loss": 1.9101, + "step": 13040 + }, + { + "epoch": 0.49, + "learning_rate": 9.514635325622048e-06, + "loss": 1.8403, + "step": 13050 + }, + { + "epoch": 0.49, + "learning_rate": 9.514263398668501e-06, + "loss": 1.9402, + "step": 13060 + }, + { + "epoch": 0.49, + "learning_rate": 9.513891471714955e-06, + "loss": 2.0417, + "step": 13070 + }, + { + "epoch": 0.49, + "learning_rate": 9.51351954476141e-06, + "loss": 1.8261, + "step": 13080 + }, + { + "epoch": 0.49, + "learning_rate": 9.513147617807863e-06, + "loss": 1.9291, + "step": 13090 + }, + { + "epoch": 0.49, + "learning_rate": 9.512775690854317e-06, + "loss": 1.8674, + "step": 13100 + }, + { + "epoch": 0.49, + "eval_loss": 1.8338229656219482, + "eval_runtime": 16.8237, + "eval_samples_per_second": 59.44, + "eval_steps_per_second": 3.745, + "step": 13100 + }, + { + "epoch": 0.49, + "learning_rate": 9.51240376390077e-06, + "loss": 1.9119, + "step": 13110 + }, + { + "epoch": 0.49, + "learning_rate": 9.512031836947224e-06, + "loss": 1.7523, + "step": 13120 + }, + { + "epoch": 0.49, + "learning_rate": 9.511659909993677e-06, + "loss": 1.9581, + "step": 13130 + }, + { + "epoch": 0.49, + "learning_rate": 9.511287983040132e-06, + "loss": 1.905, + "step": 13140 + }, + { + "epoch": 0.49, + "learning_rate": 9.510916056086586e-06, + "loss": 1.8199, + "step": 13150 + }, + { + "epoch": 0.49, + "learning_rate": 9.51054412913304e-06, + "loss": 1.8247, + "step": 13160 + }, + { + "epoch": 0.49, + "learning_rate": 9.510172202179493e-06, + "loss": 1.8786, + "step": 13170 + }, + { + "epoch": 0.49, + "learning_rate": 9.509800275225946e-06, + "loss": 2.0233, + "step": 13180 + }, + { + "epoch": 0.49, + "learning_rate": 9.5094283482724e-06, + "loss": 2.0317, + "step": 13190 + }, + { + "epoch": 0.49, + "learning_rate": 9.509056421318855e-06, + "loss": 1.8224, + "step": 13200 + }, + { + "epoch": 0.49, + "eval_loss": 1.8326748609542847, + "eval_runtime": 16.8329, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 13200 + }, + { + "epoch": 0.49, + "learning_rate": 9.508684494365308e-06, + "loss": 1.9388, + "step": 13210 + }, + { + "epoch": 0.49, + "learning_rate": 9.508312567411762e-06, + "loss": 1.9422, + "step": 13220 + }, + { + "epoch": 0.49, + "learning_rate": 9.507940640458215e-06, + "loss": 1.9097, + "step": 13230 + }, + { + "epoch": 0.49, + "learning_rate": 9.507568713504669e-06, + "loss": 1.7386, + "step": 13240 + }, + { + "epoch": 0.49, + "learning_rate": 9.507196786551122e-06, + "loss": 1.8624, + "step": 13250 + }, + { + "epoch": 0.49, + "learning_rate": 9.506824859597576e-06, + "loss": 2.0384, + "step": 13260 + }, + { + "epoch": 0.49, + "learning_rate": 9.506452932644029e-06, + "loss": 1.9091, + "step": 13270 + }, + { + "epoch": 0.49, + "learning_rate": 9.506081005690483e-06, + "loss": 1.9435, + "step": 13280 + }, + { + "epoch": 0.49, + "learning_rate": 9.505709078736936e-06, + "loss": 1.9646, + "step": 13290 + }, + { + "epoch": 0.49, + "learning_rate": 9.505337151783391e-06, + "loss": 1.9924, + "step": 13300 + }, + { + "epoch": 0.49, + "eval_loss": 1.8338093757629395, + "eval_runtime": 16.8248, + "eval_samples_per_second": 59.436, + "eval_steps_per_second": 3.744, + "step": 13300 + }, + { + "epoch": 0.5, + "learning_rate": 9.504965224829845e-06, + "loss": 1.9697, + "step": 13310 + }, + { + "epoch": 0.5, + "learning_rate": 9.504593297876298e-06, + "loss": 1.9054, + "step": 13320 + }, + { + "epoch": 0.5, + "learning_rate": 9.504221370922752e-06, + "loss": 1.9565, + "step": 13330 + }, + { + "epoch": 0.5, + "learning_rate": 9.503849443969205e-06, + "loss": 1.8742, + "step": 13340 + }, + { + "epoch": 0.5, + "learning_rate": 9.503477517015658e-06, + "loss": 1.8197, + "step": 13350 + }, + { + "epoch": 0.5, + "learning_rate": 9.503105590062112e-06, + "loss": 1.8103, + "step": 13360 + }, + { + "epoch": 0.5, + "learning_rate": 9.502733663108567e-06, + "loss": 1.8261, + "step": 13370 + }, + { + "epoch": 0.5, + "learning_rate": 9.50236173615502e-06, + "loss": 2.0472, + "step": 13380 + }, + { + "epoch": 0.5, + "learning_rate": 9.501989809201474e-06, + "loss": 1.9049, + "step": 13390 + }, + { + "epoch": 0.5, + "learning_rate": 9.501617882247927e-06, + "loss": 1.8961, + "step": 13400 + }, + { + "epoch": 0.5, + "eval_loss": 1.8328715562820435, + "eval_runtime": 16.8254, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 13400 + }, + { + "epoch": 0.5, + "learning_rate": 9.501245955294381e-06, + "loss": 1.8121, + "step": 13410 + }, + { + "epoch": 0.5, + "learning_rate": 9.500874028340834e-06, + "loss": 1.9968, + "step": 13420 + }, + { + "epoch": 0.5, + "learning_rate": 9.500502101387288e-06, + "loss": 1.9694, + "step": 13430 + }, + { + "epoch": 0.5, + "learning_rate": 9.500130174433741e-06, + "loss": 1.9238, + "step": 13440 + }, + { + "epoch": 0.5, + "learning_rate": 9.499758247480195e-06, + "loss": 1.9064, + "step": 13450 + }, + { + "epoch": 0.5, + "learning_rate": 9.499386320526648e-06, + "loss": 2.1233, + "step": 13460 + }, + { + "epoch": 0.5, + "learning_rate": 9.499014393573103e-06, + "loss": 1.8304, + "step": 13470 + }, + { + "epoch": 0.5, + "learning_rate": 9.498642466619557e-06, + "loss": 1.7853, + "step": 13480 + }, + { + "epoch": 0.5, + "learning_rate": 9.49827053966601e-06, + "loss": 1.8133, + "step": 13490 + }, + { + "epoch": 0.5, + "learning_rate": 9.497898612712464e-06, + "loss": 2.0171, + "step": 13500 + }, + { + "epoch": 0.5, + "eval_loss": 1.8327510356903076, + "eval_runtime": 16.8306, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 13500 + }, + { + "epoch": 0.5, + "learning_rate": 9.497526685758917e-06, + "loss": 2.0381, + "step": 13510 + }, + { + "epoch": 0.5, + "learning_rate": 9.49715475880537e-06, + "loss": 1.9076, + "step": 13520 + }, + { + "epoch": 0.5, + "learning_rate": 9.496782831851826e-06, + "loss": 1.8842, + "step": 13530 + }, + { + "epoch": 0.5, + "learning_rate": 9.49641090489828e-06, + "loss": 1.8831, + "step": 13540 + }, + { + "epoch": 0.5, + "learning_rate": 9.496038977944733e-06, + "loss": 1.9028, + "step": 13550 + }, + { + "epoch": 0.5, + "learning_rate": 9.495667050991186e-06, + "loss": 1.8053, + "step": 13560 + }, + { + "epoch": 0.5, + "learning_rate": 9.49529512403764e-06, + "loss": 1.9401, + "step": 13570 + }, + { + "epoch": 0.51, + "learning_rate": 9.494923197084093e-06, + "loss": 1.8608, + "step": 13580 + }, + { + "epoch": 0.51, + "learning_rate": 9.494551270130548e-06, + "loss": 1.7496, + "step": 13590 + }, + { + "epoch": 0.51, + "learning_rate": 9.494179343177002e-06, + "loss": 1.8906, + "step": 13600 + }, + { + "epoch": 0.51, + "eval_loss": 1.832607388496399, + "eval_runtime": 16.817, + "eval_samples_per_second": 59.464, + "eval_steps_per_second": 3.746, + "step": 13600 + }, + { + "epoch": 0.51, + "learning_rate": 9.493807416223455e-06, + "loss": 1.8876, + "step": 13610 + }, + { + "epoch": 0.51, + "learning_rate": 9.493435489269907e-06, + "loss": 1.9164, + "step": 13620 + }, + { + "epoch": 0.51, + "learning_rate": 9.493063562316362e-06, + "loss": 1.9323, + "step": 13630 + }, + { + "epoch": 0.51, + "learning_rate": 9.492691635362816e-06, + "loss": 1.9006, + "step": 13640 + }, + { + "epoch": 0.51, + "learning_rate": 9.492319708409269e-06, + "loss": 1.7719, + "step": 13650 + }, + { + "epoch": 0.51, + "learning_rate": 9.491947781455722e-06, + "loss": 1.8693, + "step": 13660 + }, + { + "epoch": 0.51, + "learning_rate": 9.491575854502176e-06, + "loss": 1.8733, + "step": 13670 + }, + { + "epoch": 0.51, + "learning_rate": 9.49120392754863e-06, + "loss": 1.7712, + "step": 13680 + }, + { + "epoch": 0.51, + "learning_rate": 9.490832000595085e-06, + "loss": 1.9448, + "step": 13690 + }, + { + "epoch": 0.51, + "learning_rate": 9.490460073641538e-06, + "loss": 1.937, + "step": 13700 + }, + { + "epoch": 0.51, + "eval_loss": 1.8322150707244873, + "eval_runtime": 16.8123, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 13700 + }, + { + "epoch": 0.51, + "learning_rate": 9.490088146687991e-06, + "loss": 1.8571, + "step": 13710 + }, + { + "epoch": 0.51, + "learning_rate": 9.489716219734445e-06, + "loss": 1.8938, + "step": 13720 + }, + { + "epoch": 0.51, + "learning_rate": 9.489344292780898e-06, + "loss": 1.8895, + "step": 13730 + }, + { + "epoch": 0.51, + "learning_rate": 9.488972365827352e-06, + "loss": 2.0197, + "step": 13740 + }, + { + "epoch": 0.51, + "learning_rate": 9.488600438873807e-06, + "loss": 1.8698, + "step": 13750 + }, + { + "epoch": 0.51, + "learning_rate": 9.48822851192026e-06, + "loss": 1.9766, + "step": 13760 + }, + { + "epoch": 0.51, + "learning_rate": 9.487856584966714e-06, + "loss": 1.9697, + "step": 13770 + }, + { + "epoch": 0.51, + "learning_rate": 9.487484658013167e-06, + "loss": 2.0144, + "step": 13780 + }, + { + "epoch": 0.51, + "learning_rate": 9.48711273105962e-06, + "loss": 1.9016, + "step": 13790 + }, + { + "epoch": 0.51, + "learning_rate": 9.486740804106074e-06, + "loss": 1.9073, + "step": 13800 + }, + { + "epoch": 0.51, + "eval_loss": 1.8308039903640747, + "eval_runtime": 16.8114, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 13800 + }, + { + "epoch": 0.51, + "learning_rate": 9.486368877152528e-06, + "loss": 1.8869, + "step": 13810 + }, + { + "epoch": 0.51, + "learning_rate": 9.485996950198981e-06, + "loss": 1.9095, + "step": 13820 + }, + { + "epoch": 0.51, + "learning_rate": 9.485625023245435e-06, + "loss": 1.9746, + "step": 13830 + }, + { + "epoch": 0.51, + "learning_rate": 9.485253096291888e-06, + "loss": 2.0194, + "step": 13840 + }, + { + "epoch": 0.52, + "learning_rate": 9.484881169338343e-06, + "loss": 1.9659, + "step": 13850 + }, + { + "epoch": 0.52, + "learning_rate": 9.484509242384797e-06, + "loss": 2.0, + "step": 13860 + }, + { + "epoch": 0.52, + "learning_rate": 9.48413731543125e-06, + "loss": 1.9107, + "step": 13870 + }, + { + "epoch": 0.52, + "learning_rate": 9.483765388477704e-06, + "loss": 1.8335, + "step": 13880 + }, + { + "epoch": 0.52, + "learning_rate": 9.483393461524157e-06, + "loss": 2.0412, + "step": 13890 + }, + { + "epoch": 0.52, + "learning_rate": 9.48302153457061e-06, + "loss": 1.9282, + "step": 13900 + }, + { + "epoch": 0.52, + "eval_loss": 1.8307106494903564, + "eval_runtime": 16.8061, + "eval_samples_per_second": 59.502, + "eval_steps_per_second": 3.749, + "step": 13900 + }, + { + "epoch": 0.52, + "learning_rate": 9.482649607617064e-06, + "loss": 1.9105, + "step": 13910 + }, + { + "epoch": 0.52, + "learning_rate": 9.48227768066352e-06, + "loss": 1.9207, + "step": 13920 + }, + { + "epoch": 0.52, + "learning_rate": 9.481905753709973e-06, + "loss": 1.942, + "step": 13930 + }, + { + "epoch": 0.52, + "learning_rate": 9.481533826756426e-06, + "loss": 1.9359, + "step": 13940 + }, + { + "epoch": 0.52, + "learning_rate": 9.48116189980288e-06, + "loss": 1.9479, + "step": 13950 + }, + { + "epoch": 0.52, + "learning_rate": 9.480789972849333e-06, + "loss": 1.9038, + "step": 13960 + }, + { + "epoch": 0.52, + "learning_rate": 9.480418045895786e-06, + "loss": 1.9093, + "step": 13970 + }, + { + "epoch": 0.52, + "learning_rate": 9.480046118942242e-06, + "loss": 1.9877, + "step": 13980 + }, + { + "epoch": 0.52, + "learning_rate": 9.479674191988693e-06, + "loss": 1.8369, + "step": 13990 + }, + { + "epoch": 0.52, + "learning_rate": 9.479302265035147e-06, + "loss": 1.8197, + "step": 14000 + }, + { + "epoch": 0.52, + "eval_loss": 1.8284493684768677, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 14000 + }, + { + "epoch": 0.52, + "learning_rate": 9.4789303380816e-06, + "loss": 1.9444, + "step": 14010 + }, + { + "epoch": 0.52, + "learning_rate": 9.478558411128055e-06, + "loss": 1.9268, + "step": 14020 + }, + { + "epoch": 0.52, + "learning_rate": 9.478186484174509e-06, + "loss": 1.8795, + "step": 14030 + }, + { + "epoch": 0.52, + "learning_rate": 9.477814557220962e-06, + "loss": 1.8791, + "step": 14040 + }, + { + "epoch": 0.52, + "learning_rate": 9.477442630267416e-06, + "loss": 1.9863, + "step": 14050 + }, + { + "epoch": 0.52, + "learning_rate": 9.47707070331387e-06, + "loss": 2.0319, + "step": 14060 + }, + { + "epoch": 0.52, + "learning_rate": 9.476698776360323e-06, + "loss": 1.9349, + "step": 14070 + }, + { + "epoch": 0.52, + "learning_rate": 9.476326849406778e-06, + "loss": 1.9426, + "step": 14080 + }, + { + "epoch": 0.52, + "learning_rate": 9.475954922453231e-06, + "loss": 1.8943, + "step": 14090 + }, + { + "epoch": 0.52, + "learning_rate": 9.475582995499685e-06, + "loss": 2.0872, + "step": 14100 + }, + { + "epoch": 0.52, + "eval_loss": 1.827129602432251, + "eval_runtime": 16.8251, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 14100 + }, + { + "epoch": 0.52, + "learning_rate": 9.475211068546138e-06, + "loss": 1.8617, + "step": 14110 + }, + { + "epoch": 0.53, + "learning_rate": 9.474839141592592e-06, + "loss": 1.9557, + "step": 14120 + }, + { + "epoch": 0.53, + "learning_rate": 9.474467214639045e-06, + "loss": 1.9375, + "step": 14130 + }, + { + "epoch": 0.53, + "learning_rate": 9.4740952876855e-06, + "loss": 1.8629, + "step": 14140 + }, + { + "epoch": 0.53, + "learning_rate": 9.473723360731954e-06, + "loss": 1.8977, + "step": 14150 + }, + { + "epoch": 0.53, + "learning_rate": 9.473351433778407e-06, + "loss": 1.7463, + "step": 14160 + }, + { + "epoch": 0.53, + "learning_rate": 9.47297950682486e-06, + "loss": 1.8867, + "step": 14170 + }, + { + "epoch": 0.53, + "learning_rate": 9.472607579871314e-06, + "loss": 1.8894, + "step": 14180 + }, + { + "epoch": 0.53, + "learning_rate": 9.472235652917768e-06, + "loss": 1.8975, + "step": 14190 + }, + { + "epoch": 0.53, + "learning_rate": 9.471863725964221e-06, + "loss": 1.8529, + "step": 14200 + }, + { + "epoch": 0.53, + "eval_loss": 1.8273029327392578, + "eval_runtime": 16.8197, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 14200 + }, + { + "epoch": 0.53, + "learning_rate": 9.471491799010675e-06, + "loss": 1.8635, + "step": 14210 + }, + { + "epoch": 0.53, + "learning_rate": 9.471119872057128e-06, + "loss": 1.8043, + "step": 14220 + }, + { + "epoch": 0.53, + "learning_rate": 9.470747945103582e-06, + "loss": 1.8639, + "step": 14230 + }, + { + "epoch": 0.53, + "learning_rate": 9.470376018150037e-06, + "loss": 1.9559, + "step": 14240 + }, + { + "epoch": 0.53, + "learning_rate": 9.47000409119649e-06, + "loss": 1.897, + "step": 14250 + }, + { + "epoch": 0.53, + "learning_rate": 9.469632164242944e-06, + "loss": 1.8898, + "step": 14260 + }, + { + "epoch": 0.53, + "learning_rate": 9.469260237289397e-06, + "loss": 1.9793, + "step": 14270 + }, + { + "epoch": 0.53, + "learning_rate": 9.46888831033585e-06, + "loss": 1.8172, + "step": 14280 + }, + { + "epoch": 0.53, + "learning_rate": 9.468516383382304e-06, + "loss": 2.0301, + "step": 14290 + }, + { + "epoch": 0.53, + "learning_rate": 9.468144456428759e-06, + "loss": 1.9048, + "step": 14300 + }, + { + "epoch": 0.53, + "eval_loss": 1.8272839784622192, + "eval_runtime": 16.808, + "eval_samples_per_second": 59.495, + "eval_steps_per_second": 3.748, + "step": 14300 + }, + { + "epoch": 0.53, + "learning_rate": 9.467772529475213e-06, + "loss": 1.9368, + "step": 14310 + }, + { + "epoch": 0.53, + "learning_rate": 9.467400602521666e-06, + "loss": 1.962, + "step": 14320 + }, + { + "epoch": 0.53, + "learning_rate": 9.46702867556812e-06, + "loss": 1.8836, + "step": 14330 + }, + { + "epoch": 0.53, + "learning_rate": 9.466656748614573e-06, + "loss": 1.9635, + "step": 14340 + }, + { + "epoch": 0.53, + "learning_rate": 9.466284821661026e-06, + "loss": 2.0393, + "step": 14350 + }, + { + "epoch": 0.53, + "learning_rate": 9.465912894707482e-06, + "loss": 1.8551, + "step": 14360 + }, + { + "epoch": 0.53, + "learning_rate": 9.465540967753933e-06, + "loss": 2.1026, + "step": 14370 + }, + { + "epoch": 0.53, + "learning_rate": 9.465169040800387e-06, + "loss": 1.923, + "step": 14380 + }, + { + "epoch": 0.54, + "learning_rate": 9.46479711384684e-06, + "loss": 1.9674, + "step": 14390 + }, + { + "epoch": 0.54, + "learning_rate": 9.464425186893295e-06, + "loss": 1.9634, + "step": 14400 + }, + { + "epoch": 0.54, + "eval_loss": 1.8250888586044312, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.744, + "step": 14400 + }, + { + "epoch": 0.54, + "learning_rate": 9.464053259939749e-06, + "loss": 1.9093, + "step": 14410 + }, + { + "epoch": 0.54, + "learning_rate": 9.463681332986202e-06, + "loss": 1.9618, + "step": 14420 + }, + { + "epoch": 0.54, + "learning_rate": 9.463309406032656e-06, + "loss": 1.886, + "step": 14430 + }, + { + "epoch": 0.54, + "learning_rate": 9.46293747907911e-06, + "loss": 1.855, + "step": 14440 + }, + { + "epoch": 0.54, + "learning_rate": 9.462565552125563e-06, + "loss": 1.8751, + "step": 14450 + }, + { + "epoch": 0.54, + "learning_rate": 9.462193625172016e-06, + "loss": 1.8646, + "step": 14460 + }, + { + "epoch": 0.54, + "learning_rate": 9.461821698218471e-06, + "loss": 1.8274, + "step": 14470 + }, + { + "epoch": 0.54, + "learning_rate": 9.461449771264925e-06, + "loss": 1.8836, + "step": 14480 + }, + { + "epoch": 0.54, + "learning_rate": 9.461077844311378e-06, + "loss": 2.0772, + "step": 14490 + }, + { + "epoch": 0.54, + "learning_rate": 9.460705917357832e-06, + "loss": 1.946, + "step": 14500 + }, + { + "epoch": 0.54, + "eval_loss": 1.8252687454223633, + "eval_runtime": 16.8208, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 14500 + }, + { + "epoch": 0.54, + "learning_rate": 9.460333990404285e-06, + "loss": 1.7211, + "step": 14510 + }, + { + "epoch": 0.54, + "learning_rate": 9.459962063450739e-06, + "loss": 1.8904, + "step": 14520 + }, + { + "epoch": 0.54, + "learning_rate": 9.459590136497194e-06, + "loss": 1.917, + "step": 14530 + }, + { + "epoch": 0.54, + "learning_rate": 9.459218209543647e-06, + "loss": 2.0526, + "step": 14540 + }, + { + "epoch": 0.54, + "learning_rate": 9.4588462825901e-06, + "loss": 1.8675, + "step": 14550 + }, + { + "epoch": 0.54, + "learning_rate": 9.458474355636552e-06, + "loss": 1.9116, + "step": 14560 + }, + { + "epoch": 0.54, + "learning_rate": 9.458102428683008e-06, + "loss": 1.8619, + "step": 14570 + }, + { + "epoch": 0.54, + "learning_rate": 9.457730501729461e-06, + "loss": 1.8825, + "step": 14580 + }, + { + "epoch": 0.54, + "learning_rate": 9.457358574775915e-06, + "loss": 1.8987, + "step": 14590 + }, + { + "epoch": 0.54, + "learning_rate": 9.456986647822368e-06, + "loss": 1.791, + "step": 14600 + }, + { + "epoch": 0.54, + "eval_loss": 1.8247240781784058, + "eval_runtime": 16.8364, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 14600 + }, + { + "epoch": 0.54, + "learning_rate": 9.456614720868821e-06, + "loss": 1.7797, + "step": 14610 + }, + { + "epoch": 0.54, + "learning_rate": 9.456242793915275e-06, + "loss": 1.8585, + "step": 14620 + }, + { + "epoch": 0.54, + "learning_rate": 9.45587086696173e-06, + "loss": 1.8268, + "step": 14630 + }, + { + "epoch": 0.54, + "learning_rate": 9.455498940008184e-06, + "loss": 1.774, + "step": 14640 + }, + { + "epoch": 0.54, + "learning_rate": 9.455127013054637e-06, + "loss": 1.983, + "step": 14650 + }, + { + "epoch": 0.55, + "learning_rate": 9.45475508610109e-06, + "loss": 1.8517, + "step": 14660 + }, + { + "epoch": 0.55, + "learning_rate": 9.454383159147544e-06, + "loss": 1.9738, + "step": 14670 + }, + { + "epoch": 0.55, + "learning_rate": 9.454011232193997e-06, + "loss": 1.937, + "step": 14680 + }, + { + "epoch": 0.55, + "learning_rate": 9.453639305240452e-06, + "loss": 1.8961, + "step": 14690 + }, + { + "epoch": 0.55, + "learning_rate": 9.453267378286906e-06, + "loss": 1.9671, + "step": 14700 + }, + { + "epoch": 0.55, + "eval_loss": 1.823534369468689, + "eval_runtime": 16.8139, + "eval_samples_per_second": 59.475, + "eval_steps_per_second": 3.747, + "step": 14700 + }, + { + "epoch": 0.55, + "learning_rate": 9.45289545133336e-06, + "loss": 1.8555, + "step": 14710 + }, + { + "epoch": 0.55, + "learning_rate": 9.452523524379813e-06, + "loss": 1.8638, + "step": 14720 + }, + { + "epoch": 0.55, + "learning_rate": 9.452151597426266e-06, + "loss": 1.8629, + "step": 14730 + }, + { + "epoch": 0.55, + "learning_rate": 9.45177967047272e-06, + "loss": 2.0029, + "step": 14740 + }, + { + "epoch": 0.55, + "learning_rate": 9.451407743519173e-06, + "loss": 1.7814, + "step": 14750 + }, + { + "epoch": 0.55, + "learning_rate": 9.451035816565627e-06, + "loss": 1.9046, + "step": 14760 + }, + { + "epoch": 0.55, + "learning_rate": 9.45066388961208e-06, + "loss": 1.9609, + "step": 14770 + }, + { + "epoch": 0.55, + "learning_rate": 9.450291962658534e-06, + "loss": 2.2302, + "step": 14780 + }, + { + "epoch": 0.55, + "learning_rate": 9.449920035704989e-06, + "loss": 1.7665, + "step": 14790 + }, + { + "epoch": 0.55, + "learning_rate": 9.449548108751442e-06, + "loss": 1.9723, + "step": 14800 + }, + { + "epoch": 0.55, + "eval_loss": 1.822148084640503, + "eval_runtime": 16.8258, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 14800 + }, + { + "epoch": 0.55, + "learning_rate": 9.449176181797896e-06, + "loss": 1.9597, + "step": 14810 + }, + { + "epoch": 0.55, + "learning_rate": 9.44880425484435e-06, + "loss": 1.8255, + "step": 14820 + }, + { + "epoch": 0.55, + "learning_rate": 9.448432327890803e-06, + "loss": 1.8549, + "step": 14830 + }, + { + "epoch": 0.55, + "learning_rate": 9.448060400937256e-06, + "loss": 1.9549, + "step": 14840 + }, + { + "epoch": 0.55, + "learning_rate": 9.447688473983711e-06, + "loss": 1.7905, + "step": 14850 + }, + { + "epoch": 0.55, + "learning_rate": 9.447316547030165e-06, + "loss": 1.9976, + "step": 14860 + }, + { + "epoch": 0.55, + "learning_rate": 9.446944620076618e-06, + "loss": 1.9226, + "step": 14870 + }, + { + "epoch": 0.55, + "learning_rate": 9.446572693123072e-06, + "loss": 1.7896, + "step": 14880 + }, + { + "epoch": 0.55, + "learning_rate": 9.446200766169525e-06, + "loss": 2.0436, + "step": 14890 + }, + { + "epoch": 0.55, + "learning_rate": 9.445828839215979e-06, + "loss": 1.8626, + "step": 14900 + }, + { + "epoch": 0.55, + "eval_loss": 1.8222570419311523, + "eval_runtime": 16.8256, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 14900 + }, + { + "epoch": 0.55, + "learning_rate": 9.445456912262434e-06, + "loss": 2.1029, + "step": 14910 + }, + { + "epoch": 0.55, + "learning_rate": 9.445084985308887e-06, + "loss": 1.845, + "step": 14920 + }, + { + "epoch": 0.56, + "learning_rate": 9.444713058355339e-06, + "loss": 1.928, + "step": 14930 + }, + { + "epoch": 0.56, + "learning_rate": 9.444341131401792e-06, + "loss": 1.9764, + "step": 14940 + }, + { + "epoch": 0.56, + "learning_rate": 9.443969204448248e-06, + "loss": 1.9468, + "step": 14950 + }, + { + "epoch": 0.56, + "learning_rate": 9.443597277494701e-06, + "loss": 1.7523, + "step": 14960 + }, + { + "epoch": 0.56, + "learning_rate": 9.443225350541154e-06, + "loss": 2.0144, + "step": 14970 + }, + { + "epoch": 0.56, + "learning_rate": 9.442853423587608e-06, + "loss": 1.8715, + "step": 14980 + }, + { + "epoch": 0.56, + "learning_rate": 9.442481496634061e-06, + "loss": 1.86, + "step": 14990 + }, + { + "epoch": 0.56, + "learning_rate": 9.442109569680515e-06, + "loss": 1.8802, + "step": 15000 + }, + { + "epoch": 0.56, + "eval_loss": 1.82314133644104, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 15000 + }, + { + "epoch": 0.56, + "learning_rate": 9.44173764272697e-06, + "loss": 1.9415, + "step": 15010 + }, + { + "epoch": 0.56, + "learning_rate": 9.441365715773423e-06, + "loss": 1.8855, + "step": 15020 + }, + { + "epoch": 0.56, + "learning_rate": 9.440993788819877e-06, + "loss": 1.8373, + "step": 15030 + }, + { + "epoch": 0.56, + "learning_rate": 9.44062186186633e-06, + "loss": 1.8002, + "step": 15040 + }, + { + "epoch": 0.56, + "learning_rate": 9.440249934912784e-06, + "loss": 1.88, + "step": 15050 + }, + { + "epoch": 0.56, + "learning_rate": 9.439878007959237e-06, + "loss": 1.809, + "step": 15060 + }, + { + "epoch": 0.56, + "learning_rate": 9.43950608100569e-06, + "loss": 2.0015, + "step": 15070 + }, + { + "epoch": 0.56, + "learning_rate": 9.439134154052146e-06, + "loss": 1.861, + "step": 15080 + }, + { + "epoch": 0.56, + "learning_rate": 9.4387622270986e-06, + "loss": 2.0243, + "step": 15090 + }, + { + "epoch": 0.56, + "learning_rate": 9.438390300145053e-06, + "loss": 1.9703, + "step": 15100 + }, + { + "epoch": 0.56, + "eval_loss": 1.8210952281951904, + "eval_runtime": 16.8144, + "eval_samples_per_second": 59.473, + "eval_steps_per_second": 3.747, + "step": 15100 + }, + { + "epoch": 0.56, + "learning_rate": 9.438018373191506e-06, + "loss": 1.8183, + "step": 15110 + }, + { + "epoch": 0.56, + "learning_rate": 9.43764644623796e-06, + "loss": 1.8339, + "step": 15120 + }, + { + "epoch": 0.56, + "learning_rate": 9.437274519284413e-06, + "loss": 1.9487, + "step": 15130 + }, + { + "epoch": 0.56, + "learning_rate": 9.436902592330867e-06, + "loss": 1.8316, + "step": 15140 + }, + { + "epoch": 0.56, + "learning_rate": 9.43653066537732e-06, + "loss": 1.9137, + "step": 15150 + }, + { + "epoch": 0.56, + "learning_rate": 9.436158738423774e-06, + "loss": 1.9444, + "step": 15160 + }, + { + "epoch": 0.56, + "learning_rate": 9.435786811470227e-06, + "loss": 1.9062, + "step": 15170 + }, + { + "epoch": 0.56, + "learning_rate": 9.435414884516682e-06, + "loss": 1.9533, + "step": 15180 + }, + { + "epoch": 0.56, + "learning_rate": 9.435042957563136e-06, + "loss": 1.9332, + "step": 15190 + }, + { + "epoch": 0.57, + "learning_rate": 9.434671030609589e-06, + "loss": 1.9421, + "step": 15200 + }, + { + "epoch": 0.57, + "eval_loss": 1.8214372396469116, + "eval_runtime": 16.8023, + "eval_samples_per_second": 59.516, + "eval_steps_per_second": 3.749, + "step": 15200 + }, + { + "epoch": 0.57, + "learning_rate": 9.434299103656043e-06, + "loss": 2.0052, + "step": 15210 + }, + { + "epoch": 0.57, + "learning_rate": 9.433927176702496e-06, + "loss": 1.8295, + "step": 15220 + }, + { + "epoch": 0.57, + "learning_rate": 9.43355524974895e-06, + "loss": 1.9704, + "step": 15230 + }, + { + "epoch": 0.57, + "learning_rate": 9.433183322795405e-06, + "loss": 1.8904, + "step": 15240 + }, + { + "epoch": 0.57, + "learning_rate": 9.432811395841858e-06, + "loss": 1.942, + "step": 15250 + }, + { + "epoch": 0.57, + "learning_rate": 9.432439468888312e-06, + "loss": 1.8677, + "step": 15260 + }, + { + "epoch": 0.57, + "learning_rate": 9.432067541934765e-06, + "loss": 1.978, + "step": 15270 + }, + { + "epoch": 0.57, + "learning_rate": 9.431695614981218e-06, + "loss": 1.8951, + "step": 15280 + }, + { + "epoch": 0.57, + "learning_rate": 9.431323688027672e-06, + "loss": 1.9136, + "step": 15290 + }, + { + "epoch": 0.57, + "learning_rate": 9.430951761074127e-06, + "loss": 1.801, + "step": 15300 + }, + { + "epoch": 0.57, + "eval_loss": 1.8213530778884888, + "eval_runtime": 16.8181, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 15300 + }, + { + "epoch": 0.57, + "learning_rate": 9.430579834120579e-06, + "loss": 1.8251, + "step": 15310 + }, + { + "epoch": 0.57, + "learning_rate": 9.430207907167032e-06, + "loss": 1.9278, + "step": 15320 + }, + { + "epoch": 0.57, + "learning_rate": 9.429835980213486e-06, + "loss": 2.0303, + "step": 15330 + }, + { + "epoch": 0.57, + "learning_rate": 9.429464053259941e-06, + "loss": 1.9687, + "step": 15340 + }, + { + "epoch": 0.57, + "learning_rate": 9.429092126306394e-06, + "loss": 1.9667, + "step": 15350 + }, + { + "epoch": 0.57, + "learning_rate": 9.428720199352848e-06, + "loss": 1.9268, + "step": 15360 + }, + { + "epoch": 0.57, + "learning_rate": 9.428348272399301e-06, + "loss": 1.7736, + "step": 15370 + }, + { + "epoch": 0.57, + "learning_rate": 9.427976345445755e-06, + "loss": 1.8442, + "step": 15380 + }, + { + "epoch": 0.57, + "learning_rate": 9.427604418492208e-06, + "loss": 1.7584, + "step": 15390 + }, + { + "epoch": 0.57, + "learning_rate": 9.427232491538663e-06, + "loss": 1.9991, + "step": 15400 + }, + { + "epoch": 0.57, + "eval_loss": 1.819464087486267, + "eval_runtime": 16.8117, + "eval_samples_per_second": 59.482, + "eval_steps_per_second": 3.747, + "step": 15400 + }, + { + "epoch": 0.57, + "learning_rate": 9.426860564585117e-06, + "loss": 1.8629, + "step": 15410 + }, + { + "epoch": 0.57, + "learning_rate": 9.42648863763157e-06, + "loss": 1.8572, + "step": 15420 + }, + { + "epoch": 0.57, + "learning_rate": 9.426116710678024e-06, + "loss": 1.8255, + "step": 15430 + }, + { + "epoch": 0.57, + "learning_rate": 9.425744783724477e-06, + "loss": 1.9373, + "step": 15440 + }, + { + "epoch": 0.57, + "learning_rate": 9.42537285677093e-06, + "loss": 1.8852, + "step": 15450 + }, + { + "epoch": 0.57, + "learning_rate": 9.425000929817386e-06, + "loss": 1.9114, + "step": 15460 + }, + { + "epoch": 0.58, + "learning_rate": 9.42462900286384e-06, + "loss": 2.051, + "step": 15470 + }, + { + "epoch": 0.58, + "learning_rate": 9.424257075910293e-06, + "loss": 1.7801, + "step": 15480 + }, + { + "epoch": 0.58, + "learning_rate": 9.423885148956746e-06, + "loss": 1.8575, + "step": 15490 + }, + { + "epoch": 0.58, + "learning_rate": 9.4235132220032e-06, + "loss": 1.8867, + "step": 15500 + }, + { + "epoch": 0.58, + "eval_loss": 1.8202195167541504, + "eval_runtime": 16.8338, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 15500 + }, + { + "epoch": 0.58, + "learning_rate": 9.423141295049653e-06, + "loss": 1.8556, + "step": 15510 + }, + { + "epoch": 0.58, + "learning_rate": 9.422769368096107e-06, + "loss": 2.0485, + "step": 15520 + }, + { + "epoch": 0.58, + "learning_rate": 9.42239744114256e-06, + "loss": 1.9337, + "step": 15530 + }, + { + "epoch": 0.58, + "learning_rate": 9.422025514189013e-06, + "loss": 1.9793, + "step": 15540 + }, + { + "epoch": 0.58, + "learning_rate": 9.421653587235467e-06, + "loss": 2.0306, + "step": 15550 + }, + { + "epoch": 0.58, + "learning_rate": 9.421281660281922e-06, + "loss": 1.8969, + "step": 15560 + }, + { + "epoch": 0.58, + "learning_rate": 9.420909733328376e-06, + "loss": 1.875, + "step": 15570 + }, + { + "epoch": 0.58, + "learning_rate": 9.420537806374829e-06, + "loss": 1.8239, + "step": 15580 + }, + { + "epoch": 0.58, + "learning_rate": 9.420165879421282e-06, + "loss": 1.9004, + "step": 15590 + }, + { + "epoch": 0.58, + "learning_rate": 9.419793952467736e-06, + "loss": 1.8969, + "step": 15600 + }, + { + "epoch": 0.58, + "eval_loss": 1.818640112876892, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 15600 + }, + { + "epoch": 0.58, + "learning_rate": 9.41942202551419e-06, + "loss": 1.8663, + "step": 15610 + }, + { + "epoch": 0.58, + "learning_rate": 9.419050098560643e-06, + "loss": 1.9313, + "step": 15620 + }, + { + "epoch": 0.58, + "learning_rate": 9.418678171607098e-06, + "loss": 1.8211, + "step": 15630 + }, + { + "epoch": 0.58, + "learning_rate": 9.418306244653551e-06, + "loss": 1.8117, + "step": 15640 + }, + { + "epoch": 0.58, + "learning_rate": 9.417934317700005e-06, + "loss": 1.7498, + "step": 15650 + }, + { + "epoch": 0.58, + "learning_rate": 9.417562390746458e-06, + "loss": 2.0367, + "step": 15660 + }, + { + "epoch": 0.58, + "learning_rate": 9.417190463792912e-06, + "loss": 1.7851, + "step": 15670 + }, + { + "epoch": 0.58, + "learning_rate": 9.416818536839365e-06, + "loss": 1.969, + "step": 15680 + }, + { + "epoch": 0.58, + "learning_rate": 9.416446609885819e-06, + "loss": 1.8979, + "step": 15690 + }, + { + "epoch": 0.58, + "learning_rate": 9.416074682932272e-06, + "loss": 1.8545, + "step": 15700 + }, + { + "epoch": 0.58, + "eval_loss": 1.8180123567581177, + "eval_runtime": 16.8192, + "eval_samples_per_second": 59.456, + "eval_steps_per_second": 3.746, + "step": 15700 + }, + { + "epoch": 0.58, + "learning_rate": 9.415702755978726e-06, + "loss": 1.8434, + "step": 15710 + }, + { + "epoch": 0.58, + "learning_rate": 9.415330829025179e-06, + "loss": 2.0654, + "step": 15720 + }, + { + "epoch": 0.59, + "learning_rate": 9.414958902071634e-06, + "loss": 1.8461, + "step": 15730 + }, + { + "epoch": 0.59, + "learning_rate": 9.414586975118088e-06, + "loss": 1.9169, + "step": 15740 + }, + { + "epoch": 0.59, + "learning_rate": 9.414215048164541e-06, + "loss": 1.9364, + "step": 15750 + }, + { + "epoch": 0.59, + "learning_rate": 9.413843121210995e-06, + "loss": 2.0344, + "step": 15760 + }, + { + "epoch": 0.59, + "learning_rate": 9.413471194257448e-06, + "loss": 1.7018, + "step": 15770 + }, + { + "epoch": 0.59, + "learning_rate": 9.413099267303902e-06, + "loss": 1.8541, + "step": 15780 + }, + { + "epoch": 0.59, + "learning_rate": 9.412727340350357e-06, + "loss": 1.8523, + "step": 15790 + }, + { + "epoch": 0.59, + "learning_rate": 9.41235541339681e-06, + "loss": 1.8378, + "step": 15800 + }, + { + "epoch": 0.59, + "eval_loss": 1.8169505596160889, + "eval_runtime": 16.8186, + "eval_samples_per_second": 59.458, + "eval_steps_per_second": 3.746, + "step": 15800 + }, + { + "epoch": 0.59, + "learning_rate": 9.411983486443264e-06, + "loss": 1.8805, + "step": 15810 + }, + { + "epoch": 0.59, + "learning_rate": 9.411611559489717e-06, + "loss": 2.0251, + "step": 15820 + }, + { + "epoch": 0.59, + "learning_rate": 9.41123963253617e-06, + "loss": 1.8559, + "step": 15830 + }, + { + "epoch": 0.59, + "learning_rate": 9.410867705582624e-06, + "loss": 1.9167, + "step": 15840 + }, + { + "epoch": 0.59, + "learning_rate": 9.41049577862908e-06, + "loss": 1.9706, + "step": 15850 + }, + { + "epoch": 0.59, + "learning_rate": 9.410123851675533e-06, + "loss": 1.8619, + "step": 15860 + }, + { + "epoch": 0.59, + "learning_rate": 9.409751924721984e-06, + "loss": 1.835, + "step": 15870 + }, + { + "epoch": 0.59, + "learning_rate": 9.409379997768438e-06, + "loss": 1.9062, + "step": 15880 + }, + { + "epoch": 0.59, + "learning_rate": 9.409008070814893e-06, + "loss": 1.9844, + "step": 15890 + }, + { + "epoch": 0.59, + "learning_rate": 9.408636143861346e-06, + "loss": 1.9344, + "step": 15900 + }, + { + "epoch": 0.59, + "eval_loss": 1.8166559934616089, + "eval_runtime": 16.8089, + "eval_samples_per_second": 59.492, + "eval_steps_per_second": 3.748, + "step": 15900 + }, + { + "epoch": 0.59, + "learning_rate": 9.4082642169078e-06, + "loss": 1.8522, + "step": 15910 + }, + { + "epoch": 0.59, + "learning_rate": 9.407892289954253e-06, + "loss": 2.0409, + "step": 15920 + }, + { + "epoch": 0.59, + "learning_rate": 9.407520363000707e-06, + "loss": 1.9049, + "step": 15930 + }, + { + "epoch": 0.59, + "learning_rate": 9.40714843604716e-06, + "loss": 1.7673, + "step": 15940 + }, + { + "epoch": 0.59, + "learning_rate": 9.406776509093615e-06, + "loss": 1.8405, + "step": 15950 + }, + { + "epoch": 0.59, + "learning_rate": 9.406404582140069e-06, + "loss": 1.803, + "step": 15960 + }, + { + "epoch": 0.59, + "learning_rate": 9.406032655186522e-06, + "loss": 1.8901, + "step": 15970 + }, + { + "epoch": 0.59, + "learning_rate": 9.405660728232976e-06, + "loss": 1.9251, + "step": 15980 + }, + { + "epoch": 0.59, + "learning_rate": 9.40528880127943e-06, + "loss": 1.8921, + "step": 15990 + }, + { + "epoch": 0.6, + "learning_rate": 9.404916874325883e-06, + "loss": 1.913, + "step": 16000 + }, + { + "epoch": 0.6, + "eval_loss": 1.8152141571044922, + "eval_runtime": 16.8166, + "eval_samples_per_second": 59.465, + "eval_steps_per_second": 3.746, + "step": 16000 + }, + { + "epoch": 0.6, + "learning_rate": 9.404544947372338e-06, + "loss": 1.9656, + "step": 16010 + }, + { + "epoch": 0.6, + "learning_rate": 9.404173020418791e-06, + "loss": 1.8009, + "step": 16020 + }, + { + "epoch": 0.6, + "learning_rate": 9.403801093465245e-06, + "loss": 1.8948, + "step": 16030 + }, + { + "epoch": 0.6, + "learning_rate": 9.403429166511698e-06, + "loss": 1.911, + "step": 16040 + }, + { + "epoch": 0.6, + "learning_rate": 9.403057239558152e-06, + "loss": 1.9963, + "step": 16050 + }, + { + "epoch": 0.6, + "learning_rate": 9.402685312604605e-06, + "loss": 1.9104, + "step": 16060 + }, + { + "epoch": 0.6, + "learning_rate": 9.402313385651059e-06, + "loss": 1.9582, + "step": 16070 + }, + { + "epoch": 0.6, + "learning_rate": 9.401941458697512e-06, + "loss": 1.9733, + "step": 16080 + }, + { + "epoch": 0.6, + "learning_rate": 9.401569531743966e-06, + "loss": 1.9587, + "step": 16090 + }, + { + "epoch": 0.6, + "learning_rate": 9.401197604790419e-06, + "loss": 1.9178, + "step": 16100 + }, + { + "epoch": 0.6, + "eval_loss": 1.8163400888442993, + "eval_runtime": 16.8213, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 16100 + }, + { + "epoch": 0.6, + "learning_rate": 9.400825677836874e-06, + "loss": 2.0436, + "step": 16110 + }, + { + "epoch": 0.6, + "learning_rate": 9.400453750883328e-06, + "loss": 1.8957, + "step": 16120 + }, + { + "epoch": 0.6, + "learning_rate": 9.400081823929781e-06, + "loss": 1.7258, + "step": 16130 + }, + { + "epoch": 0.6, + "learning_rate": 9.399709896976235e-06, + "loss": 1.901, + "step": 16140 + }, + { + "epoch": 0.6, + "learning_rate": 9.399337970022688e-06, + "loss": 1.7542, + "step": 16150 + }, + { + "epoch": 0.6, + "learning_rate": 9.398966043069141e-06, + "loss": 2.0453, + "step": 16160 + }, + { + "epoch": 0.6, + "learning_rate": 9.398594116115597e-06, + "loss": 1.8116, + "step": 16170 + }, + { + "epoch": 0.6, + "learning_rate": 9.39822218916205e-06, + "loss": 1.9308, + "step": 16180 + }, + { + "epoch": 0.6, + "learning_rate": 9.397850262208504e-06, + "loss": 2.0448, + "step": 16190 + }, + { + "epoch": 0.6, + "learning_rate": 9.397478335254957e-06, + "loss": 1.8693, + "step": 16200 + }, + { + "epoch": 0.6, + "eval_loss": 1.8151843547821045, + "eval_runtime": 16.8152, + "eval_samples_per_second": 59.47, + "eval_steps_per_second": 3.747, + "step": 16200 + }, + { + "epoch": 0.6, + "learning_rate": 9.39710640830141e-06, + "loss": 1.8988, + "step": 16210 + }, + { + "epoch": 0.6, + "learning_rate": 9.396734481347864e-06, + "loss": 1.9627, + "step": 16220 + }, + { + "epoch": 0.6, + "learning_rate": 9.396362554394317e-06, + "loss": 1.8621, + "step": 16230 + }, + { + "epoch": 0.6, + "learning_rate": 9.395990627440773e-06, + "loss": 1.9913, + "step": 16240 + }, + { + "epoch": 0.6, + "learning_rate": 9.395618700487224e-06, + "loss": 1.794, + "step": 16250 + }, + { + "epoch": 0.6, + "learning_rate": 9.395246773533678e-06, + "loss": 1.9232, + "step": 16260 + }, + { + "epoch": 0.61, + "learning_rate": 9.394874846580131e-06, + "loss": 1.9205, + "step": 16270 + }, + { + "epoch": 0.61, + "learning_rate": 9.394502919626586e-06, + "loss": 1.7761, + "step": 16280 + }, + { + "epoch": 0.61, + "learning_rate": 9.39413099267304e-06, + "loss": 1.9081, + "step": 16290 + }, + { + "epoch": 0.61, + "learning_rate": 9.393759065719493e-06, + "loss": 1.9345, + "step": 16300 + }, + { + "epoch": 0.61, + "eval_loss": 1.8143271207809448, + "eval_runtime": 16.8094, + "eval_samples_per_second": 59.491, + "eval_steps_per_second": 3.748, + "step": 16300 + }, + { + "epoch": 0.61, + "learning_rate": 9.393387138765947e-06, + "loss": 1.8522, + "step": 16310 + }, + { + "epoch": 0.61, + "learning_rate": 9.3930152118124e-06, + "loss": 1.8206, + "step": 16320 + }, + { + "epoch": 0.61, + "learning_rate": 9.392643284858854e-06, + "loss": 2.0469, + "step": 16330 + }, + { + "epoch": 0.61, + "learning_rate": 9.392271357905309e-06, + "loss": 1.9423, + "step": 16340 + }, + { + "epoch": 0.61, + "learning_rate": 9.391899430951762e-06, + "loss": 1.9214, + "step": 16350 + }, + { + "epoch": 0.61, + "learning_rate": 9.391527503998216e-06, + "loss": 1.8794, + "step": 16360 + }, + { + "epoch": 0.61, + "learning_rate": 9.39115557704467e-06, + "loss": 1.8315, + "step": 16370 + }, + { + "epoch": 0.61, + "learning_rate": 9.390783650091123e-06, + "loss": 1.8967, + "step": 16380 + }, + { + "epoch": 0.61, + "learning_rate": 9.390411723137576e-06, + "loss": 1.9413, + "step": 16390 + }, + { + "epoch": 0.61, + "learning_rate": 9.390039796184031e-06, + "loss": 1.8007, + "step": 16400 + }, + { + "epoch": 0.61, + "eval_loss": 1.8144868612289429, + "eval_runtime": 16.8281, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 16400 + }, + { + "epoch": 0.61, + "learning_rate": 9.389667869230485e-06, + "loss": 2.0774, + "step": 16410 + }, + { + "epoch": 0.61, + "learning_rate": 9.389295942276938e-06, + "loss": 1.9123, + "step": 16420 + }, + { + "epoch": 0.61, + "learning_rate": 9.38892401532339e-06, + "loss": 1.7971, + "step": 16430 + }, + { + "epoch": 0.61, + "learning_rate": 9.388552088369845e-06, + "loss": 2.0361, + "step": 16440 + }, + { + "epoch": 0.61, + "learning_rate": 9.388180161416299e-06, + "loss": 1.7902, + "step": 16450 + }, + { + "epoch": 0.61, + "learning_rate": 9.387808234462752e-06, + "loss": 1.8996, + "step": 16460 + }, + { + "epoch": 0.61, + "learning_rate": 9.387436307509205e-06, + "loss": 1.9554, + "step": 16470 + }, + { + "epoch": 0.61, + "learning_rate": 9.387064380555659e-06, + "loss": 2.0068, + "step": 16480 + }, + { + "epoch": 0.61, + "learning_rate": 9.386692453602112e-06, + "loss": 1.8041, + "step": 16490 + }, + { + "epoch": 0.61, + "learning_rate": 9.386320526648568e-06, + "loss": 1.954, + "step": 16500 + }, + { + "epoch": 0.61, + "eval_loss": 1.8150795698165894, + "eval_runtime": 16.8229, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 16500 + }, + { + "epoch": 0.61, + "learning_rate": 9.385948599695021e-06, + "loss": 1.798, + "step": 16510 + }, + { + "epoch": 0.61, + "learning_rate": 9.385576672741474e-06, + "loss": 1.8964, + "step": 16520 + }, + { + "epoch": 0.61, + "learning_rate": 9.385204745787928e-06, + "loss": 1.9508, + "step": 16530 + }, + { + "epoch": 0.62, + "learning_rate": 9.384832818834381e-06, + "loss": 1.8681, + "step": 16540 + }, + { + "epoch": 0.62, + "learning_rate": 9.384460891880835e-06, + "loss": 1.8184, + "step": 16550 + }, + { + "epoch": 0.62, + "learning_rate": 9.38408896492729e-06, + "loss": 1.9298, + "step": 16560 + }, + { + "epoch": 0.62, + "learning_rate": 9.383717037973743e-06, + "loss": 1.8189, + "step": 16570 + }, + { + "epoch": 0.62, + "learning_rate": 9.383345111020197e-06, + "loss": 1.8976, + "step": 16580 + }, + { + "epoch": 0.62, + "learning_rate": 9.38297318406665e-06, + "loss": 1.7897, + "step": 16590 + }, + { + "epoch": 0.62, + "learning_rate": 9.382601257113104e-06, + "loss": 1.9457, + "step": 16600 + }, + { + "epoch": 0.62, + "eval_loss": 1.814284324645996, + "eval_runtime": 16.8255, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 16600 + }, + { + "epoch": 0.62, + "learning_rate": 9.382229330159557e-06, + "loss": 1.9308, + "step": 16610 + }, + { + "epoch": 0.62, + "learning_rate": 9.38185740320601e-06, + "loss": 1.9004, + "step": 16620 + }, + { + "epoch": 0.62, + "learning_rate": 9.381485476252464e-06, + "loss": 2.0056, + "step": 16630 + }, + { + "epoch": 0.62, + "learning_rate": 9.381113549298918e-06, + "loss": 1.7858, + "step": 16640 + }, + { + "epoch": 0.62, + "learning_rate": 9.380741622345371e-06, + "loss": 1.8657, + "step": 16650 + }, + { + "epoch": 0.62, + "learning_rate": 9.380369695391826e-06, + "loss": 1.9787, + "step": 16660 + }, + { + "epoch": 0.62, + "learning_rate": 9.37999776843828e-06, + "loss": 1.836, + "step": 16670 + }, + { + "epoch": 0.62, + "learning_rate": 9.379625841484733e-06, + "loss": 1.8622, + "step": 16680 + }, + { + "epoch": 0.62, + "learning_rate": 9.379253914531187e-06, + "loss": 1.7491, + "step": 16690 + }, + { + "epoch": 0.62, + "learning_rate": 9.37888198757764e-06, + "loss": 1.8273, + "step": 16700 + }, + { + "epoch": 0.62, + "eval_loss": 1.813612937927246, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 16700 + }, + { + "epoch": 0.62, + "learning_rate": 9.378510060624094e-06, + "loss": 1.7958, + "step": 16710 + }, + { + "epoch": 0.62, + "learning_rate": 9.378138133670549e-06, + "loss": 1.8571, + "step": 16720 + }, + { + "epoch": 0.62, + "learning_rate": 9.377766206717002e-06, + "loss": 2.1173, + "step": 16730 + }, + { + "epoch": 0.62, + "learning_rate": 9.377394279763456e-06, + "loss": 2.0652, + "step": 16740 + }, + { + "epoch": 0.62, + "learning_rate": 9.377022352809909e-06, + "loss": 1.8725, + "step": 16750 + }, + { + "epoch": 0.62, + "learning_rate": 9.376650425856363e-06, + "loss": 1.915, + "step": 16760 + }, + { + "epoch": 0.62, + "learning_rate": 9.376278498902816e-06, + "loss": 1.9305, + "step": 16770 + }, + { + "epoch": 0.62, + "learning_rate": 9.37590657194927e-06, + "loss": 1.8722, + "step": 16780 + }, + { + "epoch": 0.62, + "learning_rate": 9.375534644995725e-06, + "loss": 2.0319, + "step": 16790 + }, + { + "epoch": 0.62, + "learning_rate": 9.375162718042178e-06, + "loss": 1.9533, + "step": 16800 + }, + { + "epoch": 0.62, + "eval_loss": 1.8114231824874878, + "eval_runtime": 16.8162, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 16800 + }, + { + "epoch": 0.63, + "learning_rate": 9.37479079108863e-06, + "loss": 1.908, + "step": 16810 + }, + { + "epoch": 0.63, + "learning_rate": 9.374418864135083e-06, + "loss": 1.8459, + "step": 16820 + }, + { + "epoch": 0.63, + "learning_rate": 9.374046937181538e-06, + "loss": 2.0201, + "step": 16830 + }, + { + "epoch": 0.63, + "learning_rate": 9.373675010227992e-06, + "loss": 1.8625, + "step": 16840 + }, + { + "epoch": 0.63, + "learning_rate": 9.373303083274445e-06, + "loss": 2.0815, + "step": 16850 + }, + { + "epoch": 0.63, + "learning_rate": 9.372931156320899e-06, + "loss": 1.8748, + "step": 16860 + }, + { + "epoch": 0.63, + "learning_rate": 9.372559229367352e-06, + "loss": 1.8433, + "step": 16870 + }, + { + "epoch": 0.63, + "learning_rate": 9.372187302413806e-06, + "loss": 1.903, + "step": 16880 + }, + { + "epoch": 0.63, + "learning_rate": 9.371815375460261e-06, + "loss": 1.7646, + "step": 16890 + }, + { + "epoch": 0.63, + "learning_rate": 9.371443448506714e-06, + "loss": 1.8763, + "step": 16900 + }, + { + "epoch": 0.63, + "eval_loss": 1.8112995624542236, + "eval_runtime": 16.8345, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 16900 + }, + { + "epoch": 0.63, + "learning_rate": 9.371071521553168e-06, + "loss": 1.7951, + "step": 16910 + }, + { + "epoch": 0.63, + "learning_rate": 9.370699594599621e-06, + "loss": 1.9535, + "step": 16920 + }, + { + "epoch": 0.63, + "learning_rate": 9.370327667646075e-06, + "loss": 1.8792, + "step": 16930 + }, + { + "epoch": 0.63, + "learning_rate": 9.369955740692528e-06, + "loss": 2.0364, + "step": 16940 + }, + { + "epoch": 0.63, + "learning_rate": 9.369583813738983e-06, + "loss": 1.9098, + "step": 16950 + }, + { + "epoch": 0.63, + "learning_rate": 9.369211886785437e-06, + "loss": 1.8188, + "step": 16960 + }, + { + "epoch": 0.63, + "learning_rate": 9.36883995983189e-06, + "loss": 1.9231, + "step": 16970 + }, + { + "epoch": 0.63, + "learning_rate": 9.368468032878344e-06, + "loss": 2.0106, + "step": 16980 + }, + { + "epoch": 0.63, + "learning_rate": 9.368096105924797e-06, + "loss": 2.0036, + "step": 16990 + }, + { + "epoch": 0.63, + "learning_rate": 9.36772417897125e-06, + "loss": 1.8377, + "step": 17000 + }, + { + "epoch": 0.63, + "eval_loss": 1.8109996318817139, + "eval_runtime": 16.8486, + "eval_samples_per_second": 59.352, + "eval_steps_per_second": 3.739, + "step": 17000 + }, + { + "epoch": 0.63, + "learning_rate": 9.367352252017704e-06, + "loss": 1.9069, + "step": 17010 + }, + { + "epoch": 0.63, + "learning_rate": 9.366980325064158e-06, + "loss": 1.9342, + "step": 17020 + }, + { + "epoch": 0.63, + "learning_rate": 9.366608398110611e-06, + "loss": 1.8849, + "step": 17030 + }, + { + "epoch": 0.63, + "learning_rate": 9.366236471157065e-06, + "loss": 1.9406, + "step": 17040 + }, + { + "epoch": 0.63, + "learning_rate": 9.36586454420352e-06, + "loss": 2.11, + "step": 17050 + }, + { + "epoch": 0.63, + "learning_rate": 9.365492617249973e-06, + "loss": 1.9893, + "step": 17060 + }, + { + "epoch": 0.63, + "learning_rate": 9.365120690296427e-06, + "loss": 1.9506, + "step": 17070 + }, + { + "epoch": 0.64, + "learning_rate": 9.36474876334288e-06, + "loss": 1.8172, + "step": 17080 + }, + { + "epoch": 0.64, + "learning_rate": 9.364376836389334e-06, + "loss": 1.9546, + "step": 17090 + }, + { + "epoch": 0.64, + "learning_rate": 9.364004909435787e-06, + "loss": 2.0447, + "step": 17100 + }, + { + "epoch": 0.64, + "eval_loss": 1.8103302717208862, + "eval_runtime": 16.8215, + "eval_samples_per_second": 59.448, + "eval_steps_per_second": 3.745, + "step": 17100 + }, + { + "epoch": 0.64, + "learning_rate": 9.363632982482242e-06, + "loss": 1.7016, + "step": 17110 + }, + { + "epoch": 0.64, + "learning_rate": 9.363261055528696e-06, + "loss": 2.0031, + "step": 17120 + }, + { + "epoch": 0.64, + "learning_rate": 9.362889128575149e-06, + "loss": 1.9219, + "step": 17130 + }, + { + "epoch": 0.64, + "learning_rate": 9.362517201621603e-06, + "loss": 1.962, + "step": 17140 + }, + { + "epoch": 0.64, + "learning_rate": 9.362145274668056e-06, + "loss": 1.9408, + "step": 17150 + }, + { + "epoch": 0.64, + "learning_rate": 9.36177334771451e-06, + "loss": 1.8316, + "step": 17160 + }, + { + "epoch": 0.64, + "learning_rate": 9.361401420760965e-06, + "loss": 1.8171, + "step": 17170 + }, + { + "epoch": 0.64, + "learning_rate": 9.361029493807416e-06, + "loss": 1.9557, + "step": 17180 + }, + { + "epoch": 0.64, + "learning_rate": 9.36065756685387e-06, + "loss": 1.6996, + "step": 17190 + }, + { + "epoch": 0.64, + "learning_rate": 9.360285639900323e-06, + "loss": 1.9615, + "step": 17200 + }, + { + "epoch": 0.64, + "eval_loss": 1.810136079788208, + "eval_runtime": 16.8207, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 17200 + }, + { + "epoch": 0.64, + "learning_rate": 9.359913712946778e-06, + "loss": 1.9471, + "step": 17210 + }, + { + "epoch": 0.64, + "learning_rate": 9.359541785993232e-06, + "loss": 1.9294, + "step": 17220 + }, + { + "epoch": 0.64, + "learning_rate": 9.359169859039685e-06, + "loss": 1.857, + "step": 17230 + }, + { + "epoch": 0.64, + "learning_rate": 9.358797932086139e-06, + "loss": 1.8448, + "step": 17240 + }, + { + "epoch": 0.64, + "learning_rate": 9.358426005132592e-06, + "loss": 1.8196, + "step": 17250 + }, + { + "epoch": 0.64, + "learning_rate": 9.358054078179046e-06, + "loss": 1.858, + "step": 17260 + }, + { + "epoch": 0.64, + "learning_rate": 9.357682151225501e-06, + "loss": 1.8875, + "step": 17270 + }, + { + "epoch": 0.64, + "learning_rate": 9.357310224271954e-06, + "loss": 1.9303, + "step": 17280 + }, + { + "epoch": 0.64, + "learning_rate": 9.356938297318408e-06, + "loss": 1.8777, + "step": 17290 + }, + { + "epoch": 0.64, + "learning_rate": 9.356566370364861e-06, + "loss": 1.8287, + "step": 17300 + }, + { + "epoch": 0.64, + "eval_loss": 1.8100138902664185, + "eval_runtime": 16.8196, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 17300 + }, + { + "epoch": 0.64, + "learning_rate": 9.356194443411315e-06, + "loss": 1.8826, + "step": 17310 + }, + { + "epoch": 0.64, + "learning_rate": 9.355822516457768e-06, + "loss": 1.9315, + "step": 17320 + }, + { + "epoch": 0.64, + "learning_rate": 9.355450589504223e-06, + "loss": 1.8228, + "step": 17330 + }, + { + "epoch": 0.64, + "learning_rate": 9.355078662550677e-06, + "loss": 1.9159, + "step": 17340 + }, + { + "epoch": 0.65, + "learning_rate": 9.35470673559713e-06, + "loss": 1.9759, + "step": 17350 + }, + { + "epoch": 0.65, + "learning_rate": 9.354334808643584e-06, + "loss": 2.0457, + "step": 17360 + }, + { + "epoch": 0.65, + "learning_rate": 9.353962881690035e-06, + "loss": 2.0284, + "step": 17370 + }, + { + "epoch": 0.65, + "learning_rate": 9.35359095473649e-06, + "loss": 1.9044, + "step": 17380 + }, + { + "epoch": 0.65, + "learning_rate": 9.353219027782944e-06, + "loss": 1.8885, + "step": 17390 + }, + { + "epoch": 0.65, + "learning_rate": 9.352847100829398e-06, + "loss": 1.738, + "step": 17400 + }, + { + "epoch": 0.65, + "eval_loss": 1.8087905645370483, + "eval_runtime": 16.8197, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 17400 + }, + { + "epoch": 0.65, + "learning_rate": 9.352475173875851e-06, + "loss": 1.9846, + "step": 17410 + }, + { + "epoch": 0.65, + "learning_rate": 9.352103246922304e-06, + "loss": 1.8451, + "step": 17420 + }, + { + "epoch": 0.65, + "learning_rate": 9.351731319968758e-06, + "loss": 1.887, + "step": 17430 + }, + { + "epoch": 0.65, + "learning_rate": 9.351359393015213e-06, + "loss": 1.8705, + "step": 17440 + }, + { + "epoch": 0.65, + "learning_rate": 9.350987466061667e-06, + "loss": 1.8075, + "step": 17450 + }, + { + "epoch": 0.65, + "learning_rate": 9.35061553910812e-06, + "loss": 1.7812, + "step": 17460 + }, + { + "epoch": 0.65, + "learning_rate": 9.350243612154573e-06, + "loss": 1.8737, + "step": 17470 + }, + { + "epoch": 0.65, + "learning_rate": 9.349871685201027e-06, + "loss": 1.9316, + "step": 17480 + }, + { + "epoch": 0.65, + "learning_rate": 9.34949975824748e-06, + "loss": 1.81, + "step": 17490 + }, + { + "epoch": 0.65, + "learning_rate": 9.349127831293936e-06, + "loss": 1.7928, + "step": 17500 + }, + { + "epoch": 0.65, + "eval_loss": 1.807530403137207, + "eval_runtime": 16.8328, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 17500 + }, + { + "epoch": 0.65, + "learning_rate": 9.348755904340389e-06, + "loss": 1.9521, + "step": 17510 + }, + { + "epoch": 0.65, + "learning_rate": 9.348383977386842e-06, + "loss": 1.8202, + "step": 17520 + }, + { + "epoch": 0.65, + "learning_rate": 9.348012050433296e-06, + "loss": 1.8573, + "step": 17530 + }, + { + "epoch": 0.65, + "learning_rate": 9.34764012347975e-06, + "loss": 1.9481, + "step": 17540 + }, + { + "epoch": 0.65, + "learning_rate": 9.347268196526203e-06, + "loss": 1.8602, + "step": 17550 + }, + { + "epoch": 0.65, + "learning_rate": 9.346896269572656e-06, + "loss": 1.742, + "step": 17560 + }, + { + "epoch": 0.65, + "learning_rate": 9.34652434261911e-06, + "loss": 1.8451, + "step": 17570 + }, + { + "epoch": 0.65, + "learning_rate": 9.346152415665563e-06, + "loss": 1.8301, + "step": 17580 + }, + { + "epoch": 0.65, + "learning_rate": 9.345780488712017e-06, + "loss": 1.9347, + "step": 17590 + }, + { + "epoch": 0.65, + "learning_rate": 9.345408561758472e-06, + "loss": 1.8194, + "step": 17600 + }, + { + "epoch": 0.65, + "eval_loss": 1.8073227405548096, + "eval_runtime": 16.8224, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 17600 + }, + { + "epoch": 0.65, + "learning_rate": 9.345036634804925e-06, + "loss": 1.9515, + "step": 17610 + }, + { + "epoch": 0.66, + "learning_rate": 9.344664707851379e-06, + "loss": 1.9625, + "step": 17620 + }, + { + "epoch": 0.66, + "learning_rate": 9.344292780897832e-06, + "loss": 1.9569, + "step": 17630 + }, + { + "epoch": 0.66, + "learning_rate": 9.343920853944286e-06, + "loss": 1.8445, + "step": 17640 + }, + { + "epoch": 0.66, + "learning_rate": 9.343548926990739e-06, + "loss": 1.8604, + "step": 17650 + }, + { + "epoch": 0.66, + "learning_rate": 9.343177000037194e-06, + "loss": 1.9713, + "step": 17660 + }, + { + "epoch": 0.66, + "learning_rate": 9.342805073083648e-06, + "loss": 2.017, + "step": 17670 + }, + { + "epoch": 0.66, + "learning_rate": 9.342433146130101e-06, + "loss": 1.9644, + "step": 17680 + }, + { + "epoch": 0.66, + "learning_rate": 9.342061219176555e-06, + "loss": 1.8427, + "step": 17690 + }, + { + "epoch": 0.66, + "learning_rate": 9.341689292223008e-06, + "loss": 1.9937, + "step": 17700 + }, + { + "epoch": 0.66, + "eval_loss": 1.8088315725326538, + "eval_runtime": 16.7995, + "eval_samples_per_second": 59.526, + "eval_steps_per_second": 3.75, + "step": 17700 + }, + { + "epoch": 0.66, + "learning_rate": 9.341317365269462e-06, + "loss": 1.9479, + "step": 17710 + }, + { + "epoch": 0.66, + "learning_rate": 9.340945438315917e-06, + "loss": 1.9524, + "step": 17720 + }, + { + "epoch": 0.66, + "learning_rate": 9.34057351136237e-06, + "loss": 1.836, + "step": 17730 + }, + { + "epoch": 0.66, + "learning_rate": 9.340201584408824e-06, + "loss": 1.9877, + "step": 17740 + }, + { + "epoch": 0.66, + "learning_rate": 9.339829657455275e-06, + "loss": 1.8134, + "step": 17750 + }, + { + "epoch": 0.66, + "learning_rate": 9.33945773050173e-06, + "loss": 1.9107, + "step": 17760 + }, + { + "epoch": 0.66, + "learning_rate": 9.339085803548184e-06, + "loss": 1.7801, + "step": 17770 + }, + { + "epoch": 0.66, + "learning_rate": 9.338713876594637e-06, + "loss": 1.9064, + "step": 17780 + }, + { + "epoch": 0.66, + "learning_rate": 9.338341949641091e-06, + "loss": 1.8702, + "step": 17790 + }, + { + "epoch": 0.66, + "learning_rate": 9.337970022687544e-06, + "loss": 2.0698, + "step": 17800 + }, + { + "epoch": 0.66, + "eval_loss": 1.8077470064163208, + "eval_runtime": 16.8333, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 17800 + }, + { + "epoch": 0.66, + "learning_rate": 9.337598095733998e-06, + "loss": 1.9585, + "step": 17810 + }, + { + "epoch": 0.66, + "learning_rate": 9.337226168780453e-06, + "loss": 1.9243, + "step": 17820 + }, + { + "epoch": 0.66, + "learning_rate": 9.336854241826906e-06, + "loss": 1.942, + "step": 17830 + }, + { + "epoch": 0.66, + "learning_rate": 9.33648231487336e-06, + "loss": 1.9735, + "step": 17840 + }, + { + "epoch": 0.66, + "learning_rate": 9.336110387919813e-06, + "loss": 1.8662, + "step": 17850 + }, + { + "epoch": 0.66, + "learning_rate": 9.335738460966267e-06, + "loss": 1.817, + "step": 17860 + }, + { + "epoch": 0.66, + "learning_rate": 9.33536653401272e-06, + "loss": 1.8361, + "step": 17870 + }, + { + "epoch": 0.67, + "learning_rate": 9.334994607059175e-06, + "loss": 1.8647, + "step": 17880 + }, + { + "epoch": 0.67, + "learning_rate": 9.334622680105629e-06, + "loss": 1.8303, + "step": 17890 + }, + { + "epoch": 0.67, + "learning_rate": 9.334250753152082e-06, + "loss": 1.9343, + "step": 17900 + }, + { + "epoch": 0.67, + "eval_loss": 1.807924509048462, + "eval_runtime": 16.8202, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.745, + "step": 17900 + }, + { + "epoch": 0.67, + "learning_rate": 9.333878826198536e-06, + "loss": 1.8484, + "step": 17910 + }, + { + "epoch": 0.67, + "learning_rate": 9.33350689924499e-06, + "loss": 1.7811, + "step": 17920 + }, + { + "epoch": 0.67, + "learning_rate": 9.333134972291443e-06, + "loss": 2.1255, + "step": 17930 + }, + { + "epoch": 0.67, + "learning_rate": 9.332763045337896e-06, + "loss": 1.8251, + "step": 17940 + }, + { + "epoch": 0.67, + "learning_rate": 9.33239111838435e-06, + "loss": 1.7875, + "step": 17950 + }, + { + "epoch": 0.67, + "learning_rate": 9.332019191430803e-06, + "loss": 1.8069, + "step": 17960 + }, + { + "epoch": 0.67, + "learning_rate": 9.331647264477257e-06, + "loss": 1.8394, + "step": 17970 + }, + { + "epoch": 0.67, + "learning_rate": 9.33127533752371e-06, + "loss": 1.8793, + "step": 17980 + }, + { + "epoch": 0.67, + "learning_rate": 9.330903410570165e-06, + "loss": 1.821, + "step": 17990 + }, + { + "epoch": 0.67, + "learning_rate": 9.330531483616619e-06, + "loss": 1.9009, + "step": 18000 + }, + { + "epoch": 0.67, + "eval_loss": 1.8062797784805298, + "eval_runtime": 16.8178, + "eval_samples_per_second": 59.461, + "eval_steps_per_second": 3.746, + "step": 18000 + }, + { + "epoch": 0.67, + "learning_rate": 9.330159556663072e-06, + "loss": 1.7867, + "step": 18010 + }, + { + "epoch": 0.67, + "learning_rate": 9.329787629709526e-06, + "loss": 1.7998, + "step": 18020 + }, + { + "epoch": 0.67, + "learning_rate": 9.329415702755979e-06, + "loss": 1.9882, + "step": 18030 + }, + { + "epoch": 0.67, + "learning_rate": 9.329043775802432e-06, + "loss": 2.1404, + "step": 18040 + }, + { + "epoch": 0.67, + "learning_rate": 9.328671848848888e-06, + "loss": 1.8921, + "step": 18050 + }, + { + "epoch": 0.67, + "learning_rate": 9.328299921895341e-06, + "loss": 1.8267, + "step": 18060 + }, + { + "epoch": 0.67, + "learning_rate": 9.327927994941795e-06, + "loss": 1.9387, + "step": 18070 + }, + { + "epoch": 0.67, + "learning_rate": 9.327556067988248e-06, + "loss": 1.8951, + "step": 18080 + }, + { + "epoch": 0.67, + "learning_rate": 9.327184141034701e-06, + "loss": 1.7624, + "step": 18090 + }, + { + "epoch": 0.67, + "learning_rate": 9.326812214081155e-06, + "loss": 1.843, + "step": 18100 + }, + { + "epoch": 0.67, + "eval_loss": 1.8066542148590088, + "eval_runtime": 16.831, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 18100 + }, + { + "epoch": 0.67, + "learning_rate": 9.32644028712761e-06, + "loss": 1.888, + "step": 18110 + }, + { + "epoch": 0.67, + "learning_rate": 9.326068360174062e-06, + "loss": 2.0219, + "step": 18120 + }, + { + "epoch": 0.67, + "learning_rate": 9.325696433220515e-06, + "loss": 1.808, + "step": 18130 + }, + { + "epoch": 0.67, + "learning_rate": 9.325324506266969e-06, + "loss": 1.881, + "step": 18140 + }, + { + "epoch": 0.68, + "learning_rate": 9.324952579313424e-06, + "loss": 1.9364, + "step": 18150 + }, + { + "epoch": 0.68, + "learning_rate": 9.324580652359877e-06, + "loss": 1.9455, + "step": 18160 + }, + { + "epoch": 0.68, + "learning_rate": 9.32420872540633e-06, + "loss": 1.9077, + "step": 18170 + }, + { + "epoch": 0.68, + "learning_rate": 9.323836798452784e-06, + "loss": 1.9997, + "step": 18180 + }, + { + "epoch": 0.68, + "learning_rate": 9.323464871499238e-06, + "loss": 1.8985, + "step": 18190 + }, + { + "epoch": 0.68, + "learning_rate": 9.323092944545691e-06, + "loss": 1.9004, + "step": 18200 + }, + { + "epoch": 0.68, + "eval_loss": 1.807144284248352, + "eval_runtime": 16.8087, + "eval_samples_per_second": 59.493, + "eval_steps_per_second": 3.748, + "step": 18200 + }, + { + "epoch": 0.68, + "learning_rate": 9.322721017592146e-06, + "loss": 1.835, + "step": 18210 + }, + { + "epoch": 0.68, + "learning_rate": 9.3223490906386e-06, + "loss": 1.9869, + "step": 18220 + }, + { + "epoch": 0.68, + "learning_rate": 9.321977163685053e-06, + "loss": 1.8067, + "step": 18230 + }, + { + "epoch": 0.68, + "learning_rate": 9.321605236731507e-06, + "loss": 1.7987, + "step": 18240 + }, + { + "epoch": 0.68, + "learning_rate": 9.32123330977796e-06, + "loss": 1.8041, + "step": 18250 + }, + { + "epoch": 0.68, + "learning_rate": 9.320861382824414e-06, + "loss": 1.7175, + "step": 18260 + }, + { + "epoch": 0.68, + "learning_rate": 9.320489455870869e-06, + "loss": 1.6998, + "step": 18270 + }, + { + "epoch": 0.68, + "learning_rate": 9.320117528917322e-06, + "loss": 1.8607, + "step": 18280 + }, + { + "epoch": 0.68, + "learning_rate": 9.319745601963776e-06, + "loss": 1.8388, + "step": 18290 + }, + { + "epoch": 0.68, + "learning_rate": 9.31937367501023e-06, + "loss": 1.8411, + "step": 18300 + }, + { + "epoch": 0.68, + "eval_loss": 1.8052631616592407, + "eval_runtime": 16.8345, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 18300 + }, + { + "epoch": 0.68, + "learning_rate": 9.319001748056683e-06, + "loss": 1.9125, + "step": 18310 + }, + { + "epoch": 0.68, + "learning_rate": 9.318629821103136e-06, + "loss": 2.0492, + "step": 18320 + }, + { + "epoch": 0.68, + "learning_rate": 9.31825789414959e-06, + "loss": 1.8205, + "step": 18330 + }, + { + "epoch": 0.68, + "learning_rate": 9.317885967196043e-06, + "loss": 1.9736, + "step": 18340 + }, + { + "epoch": 0.68, + "learning_rate": 9.317514040242496e-06, + "loss": 2.0215, + "step": 18350 + }, + { + "epoch": 0.68, + "learning_rate": 9.31714211328895e-06, + "loss": 1.9327, + "step": 18360 + }, + { + "epoch": 0.68, + "learning_rate": 9.316770186335405e-06, + "loss": 1.7763, + "step": 18370 + }, + { + "epoch": 0.68, + "learning_rate": 9.316398259381859e-06, + "loss": 1.8757, + "step": 18380 + }, + { + "epoch": 0.68, + "learning_rate": 9.316026332428312e-06, + "loss": 1.7547, + "step": 18390 + }, + { + "epoch": 0.68, + "learning_rate": 9.315654405474765e-06, + "loss": 1.764, + "step": 18400 + }, + { + "epoch": 0.68, + "eval_loss": 1.8043029308319092, + "eval_runtime": 16.8283, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 18400 + }, + { + "epoch": 0.68, + "learning_rate": 9.315282478521219e-06, + "loss": 1.9403, + "step": 18410 + }, + { + "epoch": 0.69, + "learning_rate": 9.314910551567672e-06, + "loss": 1.8599, + "step": 18420 + }, + { + "epoch": 0.69, + "learning_rate": 9.314538624614128e-06, + "loss": 1.9101, + "step": 18430 + }, + { + "epoch": 0.69, + "learning_rate": 9.314166697660581e-06, + "loss": 1.8759, + "step": 18440 + }, + { + "epoch": 0.69, + "learning_rate": 9.313794770707034e-06, + "loss": 1.9925, + "step": 18450 + }, + { + "epoch": 0.69, + "learning_rate": 9.313422843753488e-06, + "loss": 1.9331, + "step": 18460 + }, + { + "epoch": 0.69, + "learning_rate": 9.313050916799941e-06, + "loss": 1.8033, + "step": 18470 + }, + { + "epoch": 0.69, + "learning_rate": 9.312678989846395e-06, + "loss": 2.1201, + "step": 18480 + }, + { + "epoch": 0.69, + "learning_rate": 9.312307062892848e-06, + "loss": 1.9369, + "step": 18490 + }, + { + "epoch": 0.69, + "learning_rate": 9.311935135939302e-06, + "loss": 1.9215, + "step": 18500 + }, + { + "epoch": 0.69, + "eval_loss": 1.8048959970474243, + "eval_runtime": 16.8258, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 18500 + }, + { + "epoch": 0.69, + "learning_rate": 9.311563208985755e-06, + "loss": 1.8321, + "step": 18510 + }, + { + "epoch": 0.69, + "learning_rate": 9.311191282032209e-06, + "loss": 1.9488, + "step": 18520 + }, + { + "epoch": 0.69, + "learning_rate": 9.310819355078662e-06, + "loss": 1.7599, + "step": 18530 + }, + { + "epoch": 0.69, + "learning_rate": 9.310447428125117e-06, + "loss": 1.8833, + "step": 18540 + }, + { + "epoch": 0.69, + "learning_rate": 9.31007550117157e-06, + "loss": 1.8752, + "step": 18550 + }, + { + "epoch": 0.69, + "learning_rate": 9.309703574218024e-06, + "loss": 1.7998, + "step": 18560 + }, + { + "epoch": 0.69, + "learning_rate": 9.309331647264478e-06, + "loss": 1.8629, + "step": 18570 + }, + { + "epoch": 0.69, + "learning_rate": 9.308959720310931e-06, + "loss": 1.899, + "step": 18580 + }, + { + "epoch": 0.69, + "learning_rate": 9.308587793357385e-06, + "loss": 1.9192, + "step": 18590 + }, + { + "epoch": 0.69, + "learning_rate": 9.30821586640384e-06, + "loss": 1.862, + "step": 18600 + }, + { + "epoch": 0.69, + "eval_loss": 1.8039705753326416, + "eval_runtime": 16.8213, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 18600 + }, + { + "epoch": 0.69, + "learning_rate": 9.307843939450293e-06, + "loss": 1.8693, + "step": 18610 + }, + { + "epoch": 0.69, + "learning_rate": 9.307472012496747e-06, + "loss": 1.9837, + "step": 18620 + }, + { + "epoch": 0.69, + "learning_rate": 9.3071000855432e-06, + "loss": 1.8557, + "step": 18630 + }, + { + "epoch": 0.69, + "learning_rate": 9.306728158589654e-06, + "loss": 1.9184, + "step": 18640 + }, + { + "epoch": 0.69, + "learning_rate": 9.306356231636107e-06, + "loss": 1.9066, + "step": 18650 + }, + { + "epoch": 0.69, + "learning_rate": 9.305984304682562e-06, + "loss": 1.8554, + "step": 18660 + }, + { + "epoch": 0.69, + "learning_rate": 9.305612377729016e-06, + "loss": 1.8302, + "step": 18670 + }, + { + "epoch": 0.69, + "learning_rate": 9.305240450775469e-06, + "loss": 1.8663, + "step": 18680 + }, + { + "epoch": 0.7, + "learning_rate": 9.304868523821921e-06, + "loss": 1.8874, + "step": 18690 + }, + { + "epoch": 0.7, + "learning_rate": 9.304496596868376e-06, + "loss": 1.9921, + "step": 18700 + }, + { + "epoch": 0.7, + "eval_loss": 1.8026127815246582, + "eval_runtime": 16.8161, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 18700 + }, + { + "epoch": 0.7, + "learning_rate": 9.30412466991483e-06, + "loss": 1.8114, + "step": 18710 + }, + { + "epoch": 0.7, + "learning_rate": 9.303752742961283e-06, + "loss": 2.0103, + "step": 18720 + }, + { + "epoch": 0.7, + "learning_rate": 9.303380816007736e-06, + "loss": 2.0294, + "step": 18730 + }, + { + "epoch": 0.7, + "learning_rate": 9.30300888905419e-06, + "loss": 1.8668, + "step": 18740 + }, + { + "epoch": 0.7, + "learning_rate": 9.302636962100643e-06, + "loss": 1.744, + "step": 18750 + }, + { + "epoch": 0.7, + "learning_rate": 9.302265035147098e-06, + "loss": 1.9285, + "step": 18760 + }, + { + "epoch": 0.7, + "learning_rate": 9.301893108193552e-06, + "loss": 1.8607, + "step": 18770 + }, + { + "epoch": 0.7, + "learning_rate": 9.301521181240005e-06, + "loss": 1.8435, + "step": 18780 + }, + { + "epoch": 0.7, + "learning_rate": 9.301149254286459e-06, + "loss": 1.9196, + "step": 18790 + }, + { + "epoch": 0.7, + "learning_rate": 9.300777327332912e-06, + "loss": 1.8668, + "step": 18800 + }, + { + "epoch": 0.7, + "eval_loss": 1.8023154735565186, + "eval_runtime": 16.821, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 18800 + }, + { + "epoch": 0.7, + "learning_rate": 9.300405400379366e-06, + "loss": 1.8655, + "step": 18810 + }, + { + "epoch": 0.7, + "learning_rate": 9.300033473425821e-06, + "loss": 2.0006, + "step": 18820 + }, + { + "epoch": 0.7, + "learning_rate": 9.299661546472274e-06, + "loss": 1.8217, + "step": 18830 + }, + { + "epoch": 0.7, + "learning_rate": 9.299289619518728e-06, + "loss": 1.9742, + "step": 18840 + }, + { + "epoch": 0.7, + "learning_rate": 9.298917692565181e-06, + "loss": 1.9937, + "step": 18850 + }, + { + "epoch": 0.7, + "learning_rate": 9.298545765611635e-06, + "loss": 1.9222, + "step": 18860 + }, + { + "epoch": 0.7, + "learning_rate": 9.298173838658088e-06, + "loss": 1.8708, + "step": 18870 + }, + { + "epoch": 0.7, + "learning_rate": 9.297801911704542e-06, + "loss": 1.9187, + "step": 18880 + }, + { + "epoch": 0.7, + "learning_rate": 9.297429984750995e-06, + "loss": 1.949, + "step": 18890 + }, + { + "epoch": 0.7, + "learning_rate": 9.297058057797449e-06, + "loss": 1.9963, + "step": 18900 + }, + { + "epoch": 0.7, + "eval_loss": 1.8022814989089966, + "eval_runtime": 16.8258, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 18900 + }, + { + "epoch": 0.7, + "learning_rate": 9.296686130843902e-06, + "loss": 1.859, + "step": 18910 + }, + { + "epoch": 0.7, + "learning_rate": 9.296314203890357e-06, + "loss": 1.8828, + "step": 18920 + }, + { + "epoch": 0.7, + "learning_rate": 9.29594227693681e-06, + "loss": 1.7951, + "step": 18930 + }, + { + "epoch": 0.7, + "learning_rate": 9.295570349983264e-06, + "loss": 1.9205, + "step": 18940 + }, + { + "epoch": 0.7, + "learning_rate": 9.295198423029718e-06, + "loss": 1.7684, + "step": 18950 + }, + { + "epoch": 0.71, + "learning_rate": 9.294826496076171e-06, + "loss": 1.8358, + "step": 18960 + }, + { + "epoch": 0.71, + "learning_rate": 9.294454569122624e-06, + "loss": 1.8163, + "step": 18970 + }, + { + "epoch": 0.71, + "learning_rate": 9.29408264216908e-06, + "loss": 1.9861, + "step": 18980 + }, + { + "epoch": 0.71, + "learning_rate": 9.293710715215533e-06, + "loss": 2.0459, + "step": 18990 + }, + { + "epoch": 0.71, + "learning_rate": 9.293338788261987e-06, + "loss": 1.8599, + "step": 19000 + }, + { + "epoch": 0.71, + "eval_loss": 1.8019967079162598, + "eval_runtime": 16.8064, + "eval_samples_per_second": 59.501, + "eval_steps_per_second": 3.749, + "step": 19000 + }, + { + "epoch": 0.71, + "learning_rate": 9.29296686130844e-06, + "loss": 1.8071, + "step": 19010 + }, + { + "epoch": 0.71, + "learning_rate": 9.292594934354893e-06, + "loss": 1.7762, + "step": 19020 + }, + { + "epoch": 0.71, + "learning_rate": 9.292223007401347e-06, + "loss": 1.9678, + "step": 19030 + }, + { + "epoch": 0.71, + "learning_rate": 9.291851080447802e-06, + "loss": 2.0671, + "step": 19040 + }, + { + "epoch": 0.71, + "learning_rate": 9.291479153494256e-06, + "loss": 1.7892, + "step": 19050 + }, + { + "epoch": 0.71, + "learning_rate": 9.291107226540707e-06, + "loss": 1.6901, + "step": 19060 + }, + { + "epoch": 0.71, + "learning_rate": 9.29073529958716e-06, + "loss": 1.9977, + "step": 19070 + }, + { + "epoch": 0.71, + "learning_rate": 9.290363372633616e-06, + "loss": 1.8662, + "step": 19080 + }, + { + "epoch": 0.71, + "learning_rate": 9.28999144568007e-06, + "loss": 1.9876, + "step": 19090 + }, + { + "epoch": 0.71, + "learning_rate": 9.289619518726523e-06, + "loss": 1.8798, + "step": 19100 + }, + { + "epoch": 0.71, + "eval_loss": 1.8004133701324463, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 19100 + }, + { + "epoch": 0.71, + "learning_rate": 9.289247591772976e-06, + "loss": 1.9503, + "step": 19110 + }, + { + "epoch": 0.71, + "learning_rate": 9.28887566481943e-06, + "loss": 1.9242, + "step": 19120 + }, + { + "epoch": 0.71, + "learning_rate": 9.288503737865883e-06, + "loss": 2.0161, + "step": 19130 + }, + { + "epoch": 0.71, + "learning_rate": 9.288131810912337e-06, + "loss": 1.827, + "step": 19140 + }, + { + "epoch": 0.71, + "learning_rate": 9.287759883958792e-06, + "loss": 1.9231, + "step": 19150 + }, + { + "epoch": 0.71, + "learning_rate": 9.287387957005245e-06, + "loss": 1.8444, + "step": 19160 + }, + { + "epoch": 0.71, + "learning_rate": 9.287016030051699e-06, + "loss": 1.8491, + "step": 19170 + }, + { + "epoch": 0.71, + "learning_rate": 9.286644103098152e-06, + "loss": 1.8706, + "step": 19180 + }, + { + "epoch": 0.71, + "learning_rate": 9.286272176144606e-06, + "loss": 1.8432, + "step": 19190 + }, + { + "epoch": 0.71, + "learning_rate": 9.285900249191059e-06, + "loss": 1.8617, + "step": 19200 + }, + { + "epoch": 0.71, + "eval_loss": 1.8001582622528076, + "eval_runtime": 16.8334, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 19200 + }, + { + "epoch": 0.71, + "learning_rate": 9.285528322237514e-06, + "loss": 1.7654, + "step": 19210 + }, + { + "epoch": 0.71, + "learning_rate": 9.285156395283968e-06, + "loss": 1.992, + "step": 19220 + }, + { + "epoch": 0.72, + "learning_rate": 9.284784468330421e-06, + "loss": 1.9235, + "step": 19230 + }, + { + "epoch": 0.72, + "learning_rate": 9.284412541376875e-06, + "loss": 1.7033, + "step": 19240 + }, + { + "epoch": 0.72, + "learning_rate": 9.284040614423328e-06, + "loss": 1.9088, + "step": 19250 + }, + { + "epoch": 0.72, + "learning_rate": 9.283668687469782e-06, + "loss": 1.9663, + "step": 19260 + }, + { + "epoch": 0.72, + "learning_rate": 9.283296760516235e-06, + "loss": 1.9424, + "step": 19270 + }, + { + "epoch": 0.72, + "learning_rate": 9.282924833562689e-06, + "loss": 2.0033, + "step": 19280 + }, + { + "epoch": 0.72, + "learning_rate": 9.282552906609142e-06, + "loss": 1.7857, + "step": 19290 + }, + { + "epoch": 0.72, + "learning_rate": 9.282180979655595e-06, + "loss": 1.8742, + "step": 19300 + }, + { + "epoch": 0.72, + "eval_loss": 1.799532175064087, + "eval_runtime": 16.8083, + "eval_samples_per_second": 59.494, + "eval_steps_per_second": 3.748, + "step": 19300 + }, + { + "epoch": 0.72, + "learning_rate": 9.28180905270205e-06, + "loss": 1.8948, + "step": 19310 + }, + { + "epoch": 0.72, + "learning_rate": 9.281437125748504e-06, + "loss": 1.8003, + "step": 19320 + }, + { + "epoch": 0.72, + "learning_rate": 9.281065198794957e-06, + "loss": 1.9369, + "step": 19330 + }, + { + "epoch": 0.72, + "learning_rate": 9.280693271841411e-06, + "loss": 1.961, + "step": 19340 + }, + { + "epoch": 0.72, + "learning_rate": 9.280321344887864e-06, + "loss": 1.7905, + "step": 19350 + }, + { + "epoch": 0.72, + "learning_rate": 9.279949417934318e-06, + "loss": 1.8983, + "step": 19360 + }, + { + "epoch": 0.72, + "learning_rate": 9.279577490980773e-06, + "loss": 1.9052, + "step": 19370 + }, + { + "epoch": 0.72, + "learning_rate": 9.279205564027226e-06, + "loss": 2.089, + "step": 19380 + }, + { + "epoch": 0.72, + "learning_rate": 9.27883363707368e-06, + "loss": 1.9043, + "step": 19390 + }, + { + "epoch": 0.72, + "learning_rate": 9.278461710120133e-06, + "loss": 1.9158, + "step": 19400 + }, + { + "epoch": 0.72, + "eval_loss": 1.8010286092758179, + "eval_runtime": 16.8325, + "eval_samples_per_second": 59.409, + "eval_steps_per_second": 3.743, + "step": 19400 + }, + { + "epoch": 0.72, + "learning_rate": 9.278089783166587e-06, + "loss": 1.7842, + "step": 19410 + }, + { + "epoch": 0.72, + "learning_rate": 9.27771785621304e-06, + "loss": 1.9649, + "step": 19420 + }, + { + "epoch": 0.72, + "learning_rate": 9.277345929259495e-06, + "loss": 1.8074, + "step": 19430 + }, + { + "epoch": 0.72, + "learning_rate": 9.276974002305947e-06, + "loss": 1.8083, + "step": 19440 + }, + { + "epoch": 0.72, + "learning_rate": 9.2766020753524e-06, + "loss": 1.9567, + "step": 19450 + }, + { + "epoch": 0.72, + "learning_rate": 9.276230148398854e-06, + "loss": 1.8178, + "step": 19460 + }, + { + "epoch": 0.72, + "learning_rate": 9.27585822144531e-06, + "loss": 1.998, + "step": 19470 + }, + { + "epoch": 0.72, + "learning_rate": 9.275486294491763e-06, + "loss": 1.8393, + "step": 19480 + }, + { + "epoch": 0.72, + "learning_rate": 9.275114367538216e-06, + "loss": 1.8499, + "step": 19490 + }, + { + "epoch": 0.73, + "learning_rate": 9.27474244058467e-06, + "loss": 1.7427, + "step": 19500 + }, + { + "epoch": 0.73, + "eval_loss": 1.7988439798355103, + "eval_runtime": 16.8082, + "eval_samples_per_second": 59.495, + "eval_steps_per_second": 3.748, + "step": 19500 + }, + { + "epoch": 0.73, + "learning_rate": 9.274370513631123e-06, + "loss": 2.0717, + "step": 19510 + }, + { + "epoch": 0.73, + "learning_rate": 9.273998586677577e-06, + "loss": 1.7039, + "step": 19520 + }, + { + "epoch": 0.73, + "learning_rate": 9.273626659724032e-06, + "loss": 1.9877, + "step": 19530 + }, + { + "epoch": 0.73, + "learning_rate": 9.273254732770485e-06, + "loss": 1.8202, + "step": 19540 + }, + { + "epoch": 0.73, + "learning_rate": 9.272882805816939e-06, + "loss": 1.9211, + "step": 19550 + }, + { + "epoch": 0.73, + "learning_rate": 9.272510878863392e-06, + "loss": 1.8783, + "step": 19560 + }, + { + "epoch": 0.73, + "learning_rate": 9.272138951909846e-06, + "loss": 1.8932, + "step": 19570 + }, + { + "epoch": 0.73, + "learning_rate": 9.271767024956299e-06, + "loss": 1.8564, + "step": 19580 + }, + { + "epoch": 0.73, + "learning_rate": 9.271395098002754e-06, + "loss": 1.9493, + "step": 19590 + }, + { + "epoch": 0.73, + "learning_rate": 9.271023171049208e-06, + "loss": 1.8922, + "step": 19600 + }, + { + "epoch": 0.73, + "eval_loss": 1.798166036605835, + "eval_runtime": 16.8131, + "eval_samples_per_second": 59.477, + "eval_steps_per_second": 3.747, + "step": 19600 + }, + { + "epoch": 0.73, + "learning_rate": 9.270651244095661e-06, + "loss": 1.7781, + "step": 19610 + }, + { + "epoch": 0.73, + "learning_rate": 9.270279317142115e-06, + "loss": 1.8803, + "step": 19620 + }, + { + "epoch": 0.73, + "learning_rate": 9.269907390188568e-06, + "loss": 1.9266, + "step": 19630 + }, + { + "epoch": 0.73, + "learning_rate": 9.269535463235022e-06, + "loss": 1.8509, + "step": 19640 + }, + { + "epoch": 0.73, + "learning_rate": 9.269163536281475e-06, + "loss": 1.9881, + "step": 19650 + }, + { + "epoch": 0.73, + "learning_rate": 9.268791609327928e-06, + "loss": 1.9509, + "step": 19660 + }, + { + "epoch": 0.73, + "learning_rate": 9.268419682374382e-06, + "loss": 1.9267, + "step": 19670 + }, + { + "epoch": 0.73, + "learning_rate": 9.268047755420835e-06, + "loss": 1.8849, + "step": 19680 + }, + { + "epoch": 0.73, + "learning_rate": 9.267675828467289e-06, + "loss": 1.8409, + "step": 19690 + }, + { + "epoch": 0.73, + "learning_rate": 9.267303901513744e-06, + "loss": 1.8697, + "step": 19700 + }, + { + "epoch": 0.73, + "eval_loss": 1.7988104820251465, + "eval_runtime": 16.8158, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.746, + "step": 19700 + }, + { + "epoch": 0.73, + "learning_rate": 9.266931974560197e-06, + "loss": 1.9088, + "step": 19710 + }, + { + "epoch": 0.73, + "learning_rate": 9.266560047606651e-06, + "loss": 1.9904, + "step": 19720 + }, + { + "epoch": 0.73, + "learning_rate": 9.266188120653104e-06, + "loss": 1.8991, + "step": 19730 + }, + { + "epoch": 0.73, + "learning_rate": 9.265816193699558e-06, + "loss": 1.9517, + "step": 19740 + }, + { + "epoch": 0.73, + "learning_rate": 9.265444266746011e-06, + "loss": 2.052, + "step": 19750 + }, + { + "epoch": 0.73, + "learning_rate": 9.265072339792466e-06, + "loss": 1.932, + "step": 19760 + }, + { + "epoch": 0.74, + "learning_rate": 9.26470041283892e-06, + "loss": 1.8008, + "step": 19770 + }, + { + "epoch": 0.74, + "learning_rate": 9.264328485885373e-06, + "loss": 1.8813, + "step": 19780 + }, + { + "epoch": 0.74, + "learning_rate": 9.263956558931827e-06, + "loss": 1.8797, + "step": 19790 + }, + { + "epoch": 0.74, + "learning_rate": 9.26358463197828e-06, + "loss": 1.7233, + "step": 19800 + }, + { + "epoch": 0.74, + "eval_loss": 1.7992478609085083, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 19800 + }, + { + "epoch": 0.74, + "learning_rate": 9.263212705024734e-06, + "loss": 2.0666, + "step": 19810 + }, + { + "epoch": 0.74, + "learning_rate": 9.262840778071187e-06, + "loss": 1.8975, + "step": 19820 + }, + { + "epoch": 0.74, + "learning_rate": 9.26246885111764e-06, + "loss": 1.9236, + "step": 19830 + }, + { + "epoch": 0.74, + "learning_rate": 9.262096924164094e-06, + "loss": 1.8508, + "step": 19840 + }, + { + "epoch": 0.74, + "learning_rate": 9.261724997210548e-06, + "loss": 1.8036, + "step": 19850 + }, + { + "epoch": 0.74, + "learning_rate": 9.261353070257003e-06, + "loss": 1.8428, + "step": 19860 + }, + { + "epoch": 0.74, + "learning_rate": 9.260981143303456e-06, + "loss": 1.8958, + "step": 19870 + }, + { + "epoch": 0.74, + "learning_rate": 9.26060921634991e-06, + "loss": 1.8822, + "step": 19880 + }, + { + "epoch": 0.74, + "learning_rate": 9.260237289396363e-06, + "loss": 1.7913, + "step": 19890 + }, + { + "epoch": 0.74, + "learning_rate": 9.259865362442817e-06, + "loss": 1.8741, + "step": 19900 + }, + { + "epoch": 0.74, + "eval_loss": 1.7968498468399048, + "eval_runtime": 16.8125, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 19900 + }, + { + "epoch": 0.74, + "learning_rate": 9.25949343548927e-06, + "loss": 2.0024, + "step": 19910 + }, + { + "epoch": 0.74, + "learning_rate": 9.259121508535725e-06, + "loss": 1.9503, + "step": 19920 + }, + { + "epoch": 0.74, + "learning_rate": 9.258749581582179e-06, + "loss": 1.8621, + "step": 19930 + }, + { + "epoch": 0.74, + "learning_rate": 9.258377654628632e-06, + "loss": 1.8049, + "step": 19940 + }, + { + "epoch": 0.74, + "learning_rate": 9.258005727675086e-06, + "loss": 1.8456, + "step": 19950 + }, + { + "epoch": 0.74, + "learning_rate": 9.257633800721539e-06, + "loss": 1.8999, + "step": 19960 + }, + { + "epoch": 0.74, + "learning_rate": 9.257261873767992e-06, + "loss": 1.886, + "step": 19970 + }, + { + "epoch": 0.74, + "learning_rate": 9.256889946814448e-06, + "loss": 1.8167, + "step": 19980 + }, + { + "epoch": 0.74, + "learning_rate": 9.256518019860901e-06, + "loss": 1.8295, + "step": 19990 + }, + { + "epoch": 0.74, + "learning_rate": 9.256146092907353e-06, + "loss": 1.8359, + "step": 20000 + }, + { + "epoch": 0.74, + "eval_loss": 1.7967942953109741, + "eval_runtime": 16.8277, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 20000 + }, + { + "epoch": 0.74, + "learning_rate": 9.255774165953806e-06, + "loss": 1.8048, + "step": 20010 + }, + { + "epoch": 0.74, + "learning_rate": 9.255402239000261e-06, + "loss": 1.9499, + "step": 20020 + }, + { + "epoch": 0.74, + "learning_rate": 9.255030312046715e-06, + "loss": 1.9165, + "step": 20030 + }, + { + "epoch": 0.75, + "learning_rate": 9.254658385093168e-06, + "loss": 1.8713, + "step": 20040 + }, + { + "epoch": 0.75, + "learning_rate": 9.254286458139622e-06, + "loss": 1.9066, + "step": 20050 + }, + { + "epoch": 0.75, + "learning_rate": 9.253914531186075e-06, + "loss": 1.8378, + "step": 20060 + }, + { + "epoch": 0.75, + "learning_rate": 9.253542604232529e-06, + "loss": 1.9627, + "step": 20070 + }, + { + "epoch": 0.75, + "learning_rate": 9.253170677278984e-06, + "loss": 1.7933, + "step": 20080 + }, + { + "epoch": 0.75, + "learning_rate": 9.252798750325437e-06, + "loss": 1.7546, + "step": 20090 + }, + { + "epoch": 0.75, + "learning_rate": 9.25242682337189e-06, + "loss": 1.8839, + "step": 20100 + }, + { + "epoch": 0.75, + "eval_loss": 1.79719877243042, + "eval_runtime": 16.8337, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.742, + "step": 20100 + }, + { + "epoch": 0.75, + "learning_rate": 9.252054896418344e-06, + "loss": 1.8931, + "step": 20110 + }, + { + "epoch": 0.75, + "learning_rate": 9.251682969464798e-06, + "loss": 1.9311, + "step": 20120 + }, + { + "epoch": 0.75, + "learning_rate": 9.251311042511251e-06, + "loss": 1.9393, + "step": 20130 + }, + { + "epoch": 0.75, + "learning_rate": 9.250939115557706e-06, + "loss": 1.8395, + "step": 20140 + }, + { + "epoch": 0.75, + "learning_rate": 9.25056718860416e-06, + "loss": 1.8863, + "step": 20150 + }, + { + "epoch": 0.75, + "learning_rate": 9.250195261650613e-06, + "loss": 1.8222, + "step": 20160 + }, + { + "epoch": 0.75, + "learning_rate": 9.249823334697067e-06, + "loss": 1.8347, + "step": 20170 + }, + { + "epoch": 0.75, + "learning_rate": 9.24945140774352e-06, + "loss": 1.773, + "step": 20180 + }, + { + "epoch": 0.75, + "learning_rate": 9.249079480789974e-06, + "loss": 1.871, + "step": 20190 + }, + { + "epoch": 0.75, + "learning_rate": 9.248707553836427e-06, + "loss": 1.9126, + "step": 20200 + }, + { + "epoch": 0.75, + "eval_loss": 1.7970482110977173, + "eval_runtime": 16.8254, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 20200 + }, + { + "epoch": 0.75, + "learning_rate": 9.24833562688288e-06, + "loss": 1.8121, + "step": 20210 + }, + { + "epoch": 0.75, + "learning_rate": 9.247963699929334e-06, + "loss": 1.8617, + "step": 20220 + }, + { + "epoch": 0.75, + "learning_rate": 9.247591772975787e-06, + "loss": 1.9284, + "step": 20230 + }, + { + "epoch": 0.75, + "learning_rate": 9.247219846022243e-06, + "loss": 1.8773, + "step": 20240 + }, + { + "epoch": 0.75, + "learning_rate": 9.246847919068696e-06, + "loss": 1.8956, + "step": 20250 + }, + { + "epoch": 0.75, + "learning_rate": 9.24647599211515e-06, + "loss": 2.0032, + "step": 20260 + }, + { + "epoch": 0.75, + "learning_rate": 9.246104065161603e-06, + "loss": 1.7154, + "step": 20270 + }, + { + "epoch": 0.75, + "learning_rate": 9.245732138208056e-06, + "loss": 2.0179, + "step": 20280 + }, + { + "epoch": 0.75, + "learning_rate": 9.24536021125451e-06, + "loss": 1.8235, + "step": 20290 + }, + { + "epoch": 0.76, + "learning_rate": 9.244988284300963e-06, + "loss": 1.8968, + "step": 20300 + }, + { + "epoch": 0.76, + "eval_loss": 1.796415090560913, + "eval_runtime": 16.8172, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 20300 + }, + { + "epoch": 0.76, + "learning_rate": 9.244616357347419e-06, + "loss": 1.8424, + "step": 20310 + }, + { + "epoch": 0.76, + "learning_rate": 9.244244430393872e-06, + "loss": 1.9373, + "step": 20320 + }, + { + "epoch": 0.76, + "learning_rate": 9.243872503440325e-06, + "loss": 1.7785, + "step": 20330 + }, + { + "epoch": 0.76, + "learning_rate": 9.243500576486779e-06, + "loss": 1.9037, + "step": 20340 + }, + { + "epoch": 0.76, + "learning_rate": 9.243128649533232e-06, + "loss": 1.8659, + "step": 20350 + }, + { + "epoch": 0.76, + "learning_rate": 9.242756722579686e-06, + "loss": 1.898, + "step": 20360 + }, + { + "epoch": 0.76, + "learning_rate": 9.242384795626141e-06, + "loss": 1.86, + "step": 20370 + }, + { + "epoch": 0.76, + "learning_rate": 9.242012868672593e-06, + "loss": 1.8578, + "step": 20380 + }, + { + "epoch": 0.76, + "learning_rate": 9.241640941719046e-06, + "loss": 1.8102, + "step": 20390 + }, + { + "epoch": 0.76, + "learning_rate": 9.2412690147655e-06, + "loss": 2.0094, + "step": 20400 + }, + { + "epoch": 0.76, + "eval_loss": 1.7961169481277466, + "eval_runtime": 16.819, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 20400 + }, + { + "epoch": 0.76, + "learning_rate": 9.240897087811955e-06, + "loss": 1.7733, + "step": 20410 + }, + { + "epoch": 0.76, + "learning_rate": 9.240525160858408e-06, + "loss": 1.7666, + "step": 20420 + }, + { + "epoch": 0.76, + "learning_rate": 9.240153233904862e-06, + "loss": 1.9264, + "step": 20430 + }, + { + "epoch": 0.76, + "learning_rate": 9.239781306951315e-06, + "loss": 1.7586, + "step": 20440 + }, + { + "epoch": 0.76, + "learning_rate": 9.239409379997769e-06, + "loss": 1.8495, + "step": 20450 + }, + { + "epoch": 0.76, + "learning_rate": 9.239037453044222e-06, + "loss": 1.9742, + "step": 20460 + }, + { + "epoch": 0.76, + "learning_rate": 9.238665526090677e-06, + "loss": 1.9848, + "step": 20470 + }, + { + "epoch": 0.76, + "learning_rate": 9.23829359913713e-06, + "loss": 2.0454, + "step": 20480 + }, + { + "epoch": 0.76, + "learning_rate": 9.237921672183584e-06, + "loss": 1.8452, + "step": 20490 + }, + { + "epoch": 0.76, + "learning_rate": 9.237549745230038e-06, + "loss": 1.9024, + "step": 20500 + }, + { + "epoch": 0.76, + "eval_loss": 1.7946195602416992, + "eval_runtime": 16.8007, + "eval_samples_per_second": 59.521, + "eval_steps_per_second": 3.75, + "step": 20500 + }, + { + "epoch": 0.76, + "learning_rate": 9.237177818276491e-06, + "loss": 1.8643, + "step": 20510 + }, + { + "epoch": 0.76, + "learning_rate": 9.236805891322945e-06, + "loss": 1.7969, + "step": 20520 + }, + { + "epoch": 0.76, + "learning_rate": 9.2364339643694e-06, + "loss": 1.9102, + "step": 20530 + }, + { + "epoch": 0.76, + "learning_rate": 9.236062037415853e-06, + "loss": 1.7943, + "step": 20540 + }, + { + "epoch": 0.76, + "learning_rate": 9.235690110462307e-06, + "loss": 2.0352, + "step": 20550 + }, + { + "epoch": 0.76, + "learning_rate": 9.235318183508758e-06, + "loss": 1.8466, + "step": 20560 + }, + { + "epoch": 0.77, + "learning_rate": 9.234946256555214e-06, + "loss": 1.9332, + "step": 20570 + }, + { + "epoch": 0.77, + "learning_rate": 9.234574329601667e-06, + "loss": 1.9005, + "step": 20580 + }, + { + "epoch": 0.77, + "learning_rate": 9.23420240264812e-06, + "loss": 1.9256, + "step": 20590 + }, + { + "epoch": 0.77, + "learning_rate": 9.233830475694574e-06, + "loss": 1.8861, + "step": 20600 + }, + { + "epoch": 0.77, + "eval_loss": 1.7940990924835205, + "eval_runtime": 16.8124, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 20600 + }, + { + "epoch": 0.77, + "learning_rate": 9.233458548741027e-06, + "loss": 1.8085, + "step": 20610 + }, + { + "epoch": 0.77, + "learning_rate": 9.23308662178748e-06, + "loss": 1.964, + "step": 20620 + }, + { + "epoch": 0.77, + "learning_rate": 9.232714694833936e-06, + "loss": 1.8388, + "step": 20630 + }, + { + "epoch": 0.77, + "learning_rate": 9.23234276788039e-06, + "loss": 1.8772, + "step": 20640 + }, + { + "epoch": 0.77, + "learning_rate": 9.231970840926843e-06, + "loss": 1.9268, + "step": 20650 + }, + { + "epoch": 0.77, + "learning_rate": 9.231598913973296e-06, + "loss": 1.9625, + "step": 20660 + }, + { + "epoch": 0.77, + "learning_rate": 9.23122698701975e-06, + "loss": 1.8247, + "step": 20670 + }, + { + "epoch": 0.77, + "learning_rate": 9.230855060066203e-06, + "loss": 1.8218, + "step": 20680 + }, + { + "epoch": 0.77, + "learning_rate": 9.230483133112658e-06, + "loss": 1.9494, + "step": 20690 + }, + { + "epoch": 0.77, + "learning_rate": 9.230111206159112e-06, + "loss": 1.9091, + "step": 20700 + }, + { + "epoch": 0.77, + "eval_loss": 1.7952451705932617, + "eval_runtime": 16.8173, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 20700 + }, + { + "epoch": 0.77, + "learning_rate": 9.229739279205565e-06, + "loss": 1.8624, + "step": 20710 + }, + { + "epoch": 0.77, + "learning_rate": 9.229367352252019e-06, + "loss": 1.7471, + "step": 20720 + }, + { + "epoch": 0.77, + "learning_rate": 9.228995425298472e-06, + "loss": 1.9157, + "step": 20730 + }, + { + "epoch": 0.77, + "learning_rate": 9.228623498344926e-06, + "loss": 1.8521, + "step": 20740 + }, + { + "epoch": 0.77, + "learning_rate": 9.22825157139138e-06, + "loss": 1.8361, + "step": 20750 + }, + { + "epoch": 0.77, + "learning_rate": 9.227879644437833e-06, + "loss": 1.8806, + "step": 20760 + }, + { + "epoch": 0.77, + "learning_rate": 9.227507717484286e-06, + "loss": 1.7884, + "step": 20770 + }, + { + "epoch": 0.77, + "learning_rate": 9.22713579053074e-06, + "loss": 1.8055, + "step": 20780 + }, + { + "epoch": 0.77, + "learning_rate": 9.226763863577195e-06, + "loss": 1.8589, + "step": 20790 + }, + { + "epoch": 0.77, + "learning_rate": 9.226391936623648e-06, + "loss": 1.7771, + "step": 20800 + }, + { + "epoch": 0.77, + "eval_loss": 1.7924972772598267, + "eval_runtime": 16.8273, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 20800 + }, + { + "epoch": 0.77, + "learning_rate": 9.226020009670102e-06, + "loss": 1.8576, + "step": 20810 + }, + { + "epoch": 0.77, + "learning_rate": 9.225648082716555e-06, + "loss": 1.8592, + "step": 20820 + }, + { + "epoch": 0.77, + "learning_rate": 9.225276155763009e-06, + "loss": 1.8829, + "step": 20830 + }, + { + "epoch": 0.78, + "learning_rate": 9.224904228809462e-06, + "loss": 2.1066, + "step": 20840 + }, + { + "epoch": 0.78, + "learning_rate": 9.224532301855915e-06, + "loss": 1.8416, + "step": 20850 + }, + { + "epoch": 0.78, + "learning_rate": 9.22416037490237e-06, + "loss": 2.0652, + "step": 20860 + }, + { + "epoch": 0.78, + "learning_rate": 9.223788447948824e-06, + "loss": 1.9064, + "step": 20870 + }, + { + "epoch": 0.78, + "learning_rate": 9.223416520995278e-06, + "loss": 1.8918, + "step": 20880 + }, + { + "epoch": 0.78, + "learning_rate": 9.223044594041731e-06, + "loss": 1.9152, + "step": 20890 + }, + { + "epoch": 0.78, + "learning_rate": 9.222672667088184e-06, + "loss": 1.9249, + "step": 20900 + }, + { + "epoch": 0.78, + "eval_loss": 1.793939471244812, + "eval_runtime": 16.813, + "eval_samples_per_second": 59.478, + "eval_steps_per_second": 3.747, + "step": 20900 + }, + { + "epoch": 0.78, + "learning_rate": 9.222300740134638e-06, + "loss": 1.7517, + "step": 20910 + }, + { + "epoch": 0.78, + "learning_rate": 9.221928813181093e-06, + "loss": 1.7759, + "step": 20920 + }, + { + "epoch": 0.78, + "learning_rate": 9.221556886227547e-06, + "loss": 1.9206, + "step": 20930 + }, + { + "epoch": 0.78, + "learning_rate": 9.221184959273998e-06, + "loss": 1.8998, + "step": 20940 + }, + { + "epoch": 0.78, + "learning_rate": 9.220813032320452e-06, + "loss": 1.7703, + "step": 20950 + }, + { + "epoch": 0.78, + "learning_rate": 9.220441105366907e-06, + "loss": 1.8761, + "step": 20960 + }, + { + "epoch": 0.78, + "learning_rate": 9.22006917841336e-06, + "loss": 1.9025, + "step": 20970 + }, + { + "epoch": 0.78, + "learning_rate": 9.219697251459814e-06, + "loss": 1.9056, + "step": 20980 + }, + { + "epoch": 0.78, + "learning_rate": 9.219325324506267e-06, + "loss": 1.9108, + "step": 20990 + }, + { + "epoch": 0.78, + "learning_rate": 9.21895339755272e-06, + "loss": 2.0666, + "step": 21000 + }, + { + "epoch": 0.78, + "eval_loss": 1.7911180257797241, + "eval_runtime": 16.8372, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 21000 + }, + { + "epoch": 0.78, + "learning_rate": 9.218581470599174e-06, + "loss": 1.8608, + "step": 21010 + }, + { + "epoch": 0.78, + "learning_rate": 9.21820954364563e-06, + "loss": 1.8441, + "step": 21020 + }, + { + "epoch": 0.78, + "learning_rate": 9.217837616692083e-06, + "loss": 1.7956, + "step": 21030 + }, + { + "epoch": 0.78, + "learning_rate": 9.217465689738536e-06, + "loss": 1.9373, + "step": 21040 + }, + { + "epoch": 0.78, + "learning_rate": 9.21709376278499e-06, + "loss": 1.9125, + "step": 21050 + }, + { + "epoch": 0.78, + "learning_rate": 9.216721835831443e-06, + "loss": 1.8243, + "step": 21060 + }, + { + "epoch": 0.78, + "learning_rate": 9.216349908877897e-06, + "loss": 1.9668, + "step": 21070 + }, + { + "epoch": 0.78, + "learning_rate": 9.215977981924352e-06, + "loss": 1.8339, + "step": 21080 + }, + { + "epoch": 0.78, + "learning_rate": 9.215606054970805e-06, + "loss": 1.9283, + "step": 21090 + }, + { + "epoch": 0.78, + "learning_rate": 9.215234128017259e-06, + "loss": 1.8521, + "step": 21100 + }, + { + "epoch": 0.78, + "eval_loss": 1.7927309274673462, + "eval_runtime": 16.8109, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 21100 + }, + { + "epoch": 0.79, + "learning_rate": 9.214862201063712e-06, + "loss": 1.8551, + "step": 21110 + }, + { + "epoch": 0.79, + "learning_rate": 9.214490274110166e-06, + "loss": 1.9421, + "step": 21120 + }, + { + "epoch": 0.79, + "learning_rate": 9.214118347156619e-06, + "loss": 1.8956, + "step": 21130 + }, + { + "epoch": 0.79, + "learning_rate": 9.213746420203073e-06, + "loss": 1.8887, + "step": 21140 + }, + { + "epoch": 0.79, + "learning_rate": 9.213374493249526e-06, + "loss": 1.7971, + "step": 21150 + }, + { + "epoch": 0.79, + "learning_rate": 9.21300256629598e-06, + "loss": 1.8684, + "step": 21160 + }, + { + "epoch": 0.79, + "learning_rate": 9.212630639342433e-06, + "loss": 1.878, + "step": 21170 + }, + { + "epoch": 0.79, + "learning_rate": 9.212258712388888e-06, + "loss": 1.8687, + "step": 21180 + }, + { + "epoch": 0.79, + "learning_rate": 9.211886785435342e-06, + "loss": 1.8511, + "step": 21190 + }, + { + "epoch": 0.79, + "learning_rate": 9.211514858481795e-06, + "loss": 1.8954, + "step": 21200 + }, + { + "epoch": 0.79, + "eval_loss": 1.790475845336914, + "eval_runtime": 16.8156, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.747, + "step": 21200 + }, + { + "epoch": 0.79, + "learning_rate": 9.211142931528248e-06, + "loss": 1.8702, + "step": 21210 + }, + { + "epoch": 0.79, + "learning_rate": 9.210771004574702e-06, + "loss": 1.8705, + "step": 21220 + }, + { + "epoch": 0.79, + "learning_rate": 9.210399077621155e-06, + "loss": 1.7024, + "step": 21230 + }, + { + "epoch": 0.79, + "learning_rate": 9.21002715066761e-06, + "loss": 1.8567, + "step": 21240 + }, + { + "epoch": 0.79, + "learning_rate": 9.209655223714064e-06, + "loss": 1.8826, + "step": 21250 + }, + { + "epoch": 0.79, + "learning_rate": 9.209283296760517e-06, + "loss": 1.9221, + "step": 21260 + }, + { + "epoch": 0.79, + "learning_rate": 9.208911369806971e-06, + "loss": 1.8382, + "step": 21270 + }, + { + "epoch": 0.79, + "learning_rate": 9.208539442853424e-06, + "loss": 1.9545, + "step": 21280 + }, + { + "epoch": 0.79, + "learning_rate": 9.208167515899878e-06, + "loss": 1.8464, + "step": 21290 + }, + { + "epoch": 0.79, + "learning_rate": 9.207795588946333e-06, + "loss": 1.8159, + "step": 21300 + }, + { + "epoch": 0.79, + "eval_loss": 1.790505051612854, + "eval_runtime": 16.8154, + "eval_samples_per_second": 59.469, + "eval_steps_per_second": 3.747, + "step": 21300 + }, + { + "epoch": 0.79, + "learning_rate": 9.207423661992786e-06, + "loss": 1.8778, + "step": 21310 + }, + { + "epoch": 0.79, + "learning_rate": 9.207051735039238e-06, + "loss": 1.9889, + "step": 21320 + }, + { + "epoch": 0.79, + "learning_rate": 9.206679808085692e-06, + "loss": 1.8751, + "step": 21330 + }, + { + "epoch": 0.79, + "learning_rate": 9.206307881132147e-06, + "loss": 2.0509, + "step": 21340 + }, + { + "epoch": 0.79, + "learning_rate": 9.2059359541786e-06, + "loss": 1.7862, + "step": 21350 + }, + { + "epoch": 0.79, + "learning_rate": 9.205564027225054e-06, + "loss": 1.8746, + "step": 21360 + }, + { + "epoch": 0.79, + "learning_rate": 9.205192100271507e-06, + "loss": 1.8216, + "step": 21370 + }, + { + "epoch": 0.8, + "learning_rate": 9.20482017331796e-06, + "loss": 1.8995, + "step": 21380 + }, + { + "epoch": 0.8, + "learning_rate": 9.204448246364414e-06, + "loss": 1.7255, + "step": 21390 + }, + { + "epoch": 0.8, + "learning_rate": 9.204076319410868e-06, + "loss": 1.6939, + "step": 21400 + }, + { + "epoch": 0.8, + "eval_loss": 1.7889704704284668, + "eval_runtime": 16.8323, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 21400 + }, + { + "epoch": 0.8, + "learning_rate": 9.203704392457323e-06, + "loss": 1.7775, + "step": 21410 + }, + { + "epoch": 0.8, + "learning_rate": 9.203332465503776e-06, + "loss": 2.0639, + "step": 21420 + }, + { + "epoch": 0.8, + "learning_rate": 9.20296053855023e-06, + "loss": 1.7462, + "step": 21430 + }, + { + "epoch": 0.8, + "learning_rate": 9.202588611596683e-06, + "loss": 1.7609, + "step": 21440 + }, + { + "epoch": 0.8, + "learning_rate": 9.202216684643137e-06, + "loss": 1.8894, + "step": 21450 + }, + { + "epoch": 0.8, + "learning_rate": 9.20184475768959e-06, + "loss": 2.0115, + "step": 21460 + }, + { + "epoch": 0.8, + "learning_rate": 9.201472830736045e-06, + "loss": 1.9377, + "step": 21470 + }, + { + "epoch": 0.8, + "learning_rate": 9.201100903782499e-06, + "loss": 1.777, + "step": 21480 + }, + { + "epoch": 0.8, + "learning_rate": 9.200728976828952e-06, + "loss": 1.8779, + "step": 21490 + }, + { + "epoch": 0.8, + "learning_rate": 9.200357049875404e-06, + "loss": 1.7788, + "step": 21500 + }, + { + "epoch": 0.8, + "eval_loss": 1.790098786354065, + "eval_runtime": 16.8287, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 21500 + }, + { + "epoch": 0.8, + "learning_rate": 9.199985122921859e-06, + "loss": 1.8615, + "step": 21510 + }, + { + "epoch": 0.8, + "learning_rate": 9.199613195968312e-06, + "loss": 1.7817, + "step": 21520 + }, + { + "epoch": 0.8, + "learning_rate": 9.199241269014766e-06, + "loss": 1.9587, + "step": 21530 + }, + { + "epoch": 0.8, + "learning_rate": 9.19886934206122e-06, + "loss": 1.8323, + "step": 21540 + }, + { + "epoch": 0.8, + "learning_rate": 9.198497415107673e-06, + "loss": 1.7834, + "step": 21550 + }, + { + "epoch": 0.8, + "learning_rate": 9.198125488154126e-06, + "loss": 1.8787, + "step": 21560 + }, + { + "epoch": 0.8, + "learning_rate": 9.197753561200581e-06, + "loss": 1.8568, + "step": 21570 + }, + { + "epoch": 0.8, + "learning_rate": 9.197381634247035e-06, + "loss": 1.8134, + "step": 21580 + }, + { + "epoch": 0.8, + "learning_rate": 9.197009707293488e-06, + "loss": 1.7081, + "step": 21590 + }, + { + "epoch": 0.8, + "learning_rate": 9.196637780339942e-06, + "loss": 1.9533, + "step": 21600 + }, + { + "epoch": 0.8, + "eval_loss": 1.7904787063598633, + "eval_runtime": 16.8231, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 21600 + }, + { + "epoch": 0.8, + "learning_rate": 9.196265853386395e-06, + "loss": 1.7686, + "step": 21610 + }, + { + "epoch": 0.8, + "learning_rate": 9.195893926432849e-06, + "loss": 1.977, + "step": 21620 + }, + { + "epoch": 0.8, + "learning_rate": 9.195521999479304e-06, + "loss": 2.0164, + "step": 21630 + }, + { + "epoch": 0.8, + "learning_rate": 9.195150072525757e-06, + "loss": 1.8751, + "step": 21640 + }, + { + "epoch": 0.81, + "learning_rate": 9.19477814557221e-06, + "loss": 1.7952, + "step": 21650 + }, + { + "epoch": 0.81, + "learning_rate": 9.194406218618664e-06, + "loss": 1.699, + "step": 21660 + }, + { + "epoch": 0.81, + "learning_rate": 9.194034291665118e-06, + "loss": 1.8096, + "step": 21670 + }, + { + "epoch": 0.81, + "learning_rate": 9.193662364711571e-06, + "loss": 1.9427, + "step": 21680 + }, + { + "epoch": 0.81, + "learning_rate": 9.193290437758025e-06, + "loss": 1.968, + "step": 21690 + }, + { + "epoch": 0.81, + "learning_rate": 9.192918510804478e-06, + "loss": 1.9614, + "step": 21700 + }, + { + "epoch": 0.81, + "eval_loss": 1.789485216140747, + "eval_runtime": 16.8239, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 21700 + }, + { + "epoch": 0.81, + "learning_rate": 9.192546583850932e-06, + "loss": 1.8617, + "step": 21710 + }, + { + "epoch": 0.81, + "learning_rate": 9.192174656897385e-06, + "loss": 1.8689, + "step": 21720 + }, + { + "epoch": 0.81, + "learning_rate": 9.19180272994384e-06, + "loss": 1.8474, + "step": 21730 + }, + { + "epoch": 0.81, + "learning_rate": 9.191430802990294e-06, + "loss": 2.0014, + "step": 21740 + }, + { + "epoch": 0.81, + "learning_rate": 9.191058876036747e-06, + "loss": 1.9473, + "step": 21750 + }, + { + "epoch": 0.81, + "learning_rate": 9.1906869490832e-06, + "loss": 1.7724, + "step": 21760 + }, + { + "epoch": 0.81, + "learning_rate": 9.190315022129654e-06, + "loss": 1.9773, + "step": 21770 + }, + { + "epoch": 0.81, + "learning_rate": 9.189943095176108e-06, + "loss": 1.8857, + "step": 21780 + }, + { + "epoch": 0.81, + "learning_rate": 9.189571168222563e-06, + "loss": 1.8998, + "step": 21790 + }, + { + "epoch": 0.81, + "learning_rate": 9.189199241269016e-06, + "loss": 1.8282, + "step": 21800 + }, + { + "epoch": 0.81, + "eval_loss": 1.7884807586669922, + "eval_runtime": 16.8093, + "eval_samples_per_second": 59.491, + "eval_steps_per_second": 3.748, + "step": 21800 + }, + { + "epoch": 0.81, + "learning_rate": 9.18882731431547e-06, + "loss": 1.8586, + "step": 21810 + }, + { + "epoch": 0.81, + "learning_rate": 9.188455387361923e-06, + "loss": 1.9234, + "step": 21820 + }, + { + "epoch": 0.81, + "learning_rate": 9.188083460408376e-06, + "loss": 1.8578, + "step": 21830 + }, + { + "epoch": 0.81, + "learning_rate": 9.18771153345483e-06, + "loss": 2.006, + "step": 21840 + }, + { + "epoch": 0.81, + "learning_rate": 9.187339606501285e-06, + "loss": 1.876, + "step": 21850 + }, + { + "epoch": 0.81, + "learning_rate": 9.186967679547739e-06, + "loss": 1.8387, + "step": 21860 + }, + { + "epoch": 0.81, + "learning_rate": 9.186595752594192e-06, + "loss": 1.9089, + "step": 21870 + }, + { + "epoch": 0.81, + "learning_rate": 9.186223825640644e-06, + "loss": 1.9454, + "step": 21880 + }, + { + "epoch": 0.81, + "learning_rate": 9.185851898687099e-06, + "loss": 1.9192, + "step": 21890 + }, + { + "epoch": 0.81, + "learning_rate": 9.185479971733552e-06, + "loss": 1.9363, + "step": 21900 + }, + { + "epoch": 0.81, + "eval_loss": 1.788086175918579, + "eval_runtime": 16.8209, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 21900 + }, + { + "epoch": 0.81, + "learning_rate": 9.185108044780006e-06, + "loss": 1.9386, + "step": 21910 + }, + { + "epoch": 0.82, + "learning_rate": 9.18473611782646e-06, + "loss": 1.7052, + "step": 21920 + }, + { + "epoch": 0.82, + "learning_rate": 9.184364190872913e-06, + "loss": 1.9321, + "step": 21930 + }, + { + "epoch": 0.82, + "learning_rate": 9.183992263919366e-06, + "loss": 1.846, + "step": 21940 + }, + { + "epoch": 0.82, + "learning_rate": 9.183620336965821e-06, + "loss": 1.9082, + "step": 21950 + }, + { + "epoch": 0.82, + "learning_rate": 9.183248410012275e-06, + "loss": 1.9423, + "step": 21960 + }, + { + "epoch": 0.82, + "learning_rate": 9.182876483058728e-06, + "loss": 1.9373, + "step": 21970 + }, + { + "epoch": 0.82, + "learning_rate": 9.182504556105182e-06, + "loss": 1.7522, + "step": 21980 + }, + { + "epoch": 0.82, + "learning_rate": 9.182132629151635e-06, + "loss": 1.9374, + "step": 21990 + }, + { + "epoch": 0.82, + "learning_rate": 9.181760702198089e-06, + "loss": 1.9042, + "step": 22000 + }, + { + "epoch": 0.82, + "eval_loss": 1.7878955602645874, + "eval_runtime": 16.828, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 22000 + }, + { + "epoch": 0.82, + "learning_rate": 9.181388775244542e-06, + "loss": 1.9077, + "step": 22010 + }, + { + "epoch": 0.82, + "learning_rate": 9.181016848290997e-06, + "loss": 1.8192, + "step": 22020 + }, + { + "epoch": 0.82, + "learning_rate": 9.18064492133745e-06, + "loss": 1.7847, + "step": 22030 + }, + { + "epoch": 0.82, + "learning_rate": 9.180272994383904e-06, + "loss": 1.8656, + "step": 22040 + }, + { + "epoch": 0.82, + "learning_rate": 9.179901067430358e-06, + "loss": 1.869, + "step": 22050 + }, + { + "epoch": 0.82, + "learning_rate": 9.179529140476811e-06, + "loss": 1.9698, + "step": 22060 + }, + { + "epoch": 0.82, + "learning_rate": 9.179157213523265e-06, + "loss": 1.9163, + "step": 22070 + }, + { + "epoch": 0.82, + "learning_rate": 9.178785286569718e-06, + "loss": 1.853, + "step": 22080 + }, + { + "epoch": 0.82, + "learning_rate": 9.178413359616172e-06, + "loss": 1.8052, + "step": 22090 + }, + { + "epoch": 0.82, + "learning_rate": 9.178041432662625e-06, + "loss": 1.8276, + "step": 22100 + }, + { + "epoch": 0.82, + "eval_loss": 1.7876057624816895, + "eval_runtime": 16.8204, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.745, + "step": 22100 + }, + { + "epoch": 0.82, + "learning_rate": 9.177669505709078e-06, + "loss": 1.9291, + "step": 22110 + }, + { + "epoch": 0.82, + "learning_rate": 9.177297578755534e-06, + "loss": 1.8482, + "step": 22120 + }, + { + "epoch": 0.82, + "learning_rate": 9.176925651801987e-06, + "loss": 1.7011, + "step": 22130 + }, + { + "epoch": 0.82, + "learning_rate": 9.17655372484844e-06, + "loss": 1.9254, + "step": 22140 + }, + { + "epoch": 0.82, + "learning_rate": 9.176181797894894e-06, + "loss": 1.6883, + "step": 22150 + }, + { + "epoch": 0.82, + "learning_rate": 9.175809870941347e-06, + "loss": 1.7495, + "step": 22160 + }, + { + "epoch": 0.82, + "learning_rate": 9.175437943987801e-06, + "loss": 1.846, + "step": 22170 + }, + { + "epoch": 0.82, + "learning_rate": 9.175066017034256e-06, + "loss": 1.8424, + "step": 22180 + }, + { + "epoch": 0.83, + "learning_rate": 9.17469409008071e-06, + "loss": 1.8777, + "step": 22190 + }, + { + "epoch": 0.83, + "learning_rate": 9.174322163127163e-06, + "loss": 2.0082, + "step": 22200 + }, + { + "epoch": 0.83, + "eval_loss": 1.7881793975830078, + "eval_runtime": 16.8137, + "eval_samples_per_second": 59.475, + "eval_steps_per_second": 3.747, + "step": 22200 + }, + { + "epoch": 0.83, + "learning_rate": 9.173950236173616e-06, + "loss": 1.9012, + "step": 22210 + }, + { + "epoch": 0.83, + "learning_rate": 9.17357830922007e-06, + "loss": 1.9604, + "step": 22220 + }, + { + "epoch": 0.83, + "learning_rate": 9.173206382266523e-06, + "loss": 1.9586, + "step": 22230 + }, + { + "epoch": 0.83, + "learning_rate": 9.172834455312978e-06, + "loss": 1.8343, + "step": 22240 + }, + { + "epoch": 0.83, + "learning_rate": 9.17246252835943e-06, + "loss": 1.8622, + "step": 22250 + }, + { + "epoch": 0.83, + "learning_rate": 9.172090601405884e-06, + "loss": 1.8519, + "step": 22260 + }, + { + "epoch": 0.83, + "learning_rate": 9.171718674452337e-06, + "loss": 1.9421, + "step": 22270 + }, + { + "epoch": 0.83, + "learning_rate": 9.171346747498792e-06, + "loss": 1.7241, + "step": 22280 + }, + { + "epoch": 0.83, + "learning_rate": 9.170974820545246e-06, + "loss": 1.799, + "step": 22290 + }, + { + "epoch": 0.83, + "learning_rate": 9.1706028935917e-06, + "loss": 1.8619, + "step": 22300 + }, + { + "epoch": 0.83, + "eval_loss": 1.7877296209335327, + "eval_runtime": 16.8132, + "eval_samples_per_second": 59.477, + "eval_steps_per_second": 3.747, + "step": 22300 + }, + { + "epoch": 0.83, + "learning_rate": 9.170230966638153e-06, + "loss": 1.875, + "step": 22310 + }, + { + "epoch": 0.83, + "learning_rate": 9.169859039684606e-06, + "loss": 1.8581, + "step": 22320 + }, + { + "epoch": 0.83, + "learning_rate": 9.16948711273106e-06, + "loss": 1.7001, + "step": 22330 + }, + { + "epoch": 0.83, + "learning_rate": 9.169115185777515e-06, + "loss": 1.8696, + "step": 22340 + }, + { + "epoch": 0.83, + "learning_rate": 9.168743258823968e-06, + "loss": 1.8822, + "step": 22350 + }, + { + "epoch": 0.83, + "learning_rate": 9.168371331870422e-06, + "loss": 2.0228, + "step": 22360 + }, + { + "epoch": 0.83, + "learning_rate": 9.167999404916875e-06, + "loss": 1.9806, + "step": 22370 + }, + { + "epoch": 0.83, + "learning_rate": 9.167627477963329e-06, + "loss": 2.0814, + "step": 22380 + }, + { + "epoch": 0.83, + "learning_rate": 9.167255551009782e-06, + "loss": 1.8921, + "step": 22390 + }, + { + "epoch": 0.83, + "learning_rate": 9.166883624056237e-06, + "loss": 1.9482, + "step": 22400 + }, + { + "epoch": 0.83, + "eval_loss": 1.7875075340270996, + "eval_runtime": 16.8249, + "eval_samples_per_second": 59.436, + "eval_steps_per_second": 3.744, + "step": 22400 + }, + { + "epoch": 0.83, + "learning_rate": 9.16651169710269e-06, + "loss": 1.814, + "step": 22410 + }, + { + "epoch": 0.83, + "learning_rate": 9.166139770149144e-06, + "loss": 1.8692, + "step": 22420 + }, + { + "epoch": 0.83, + "learning_rate": 9.165767843195598e-06, + "loss": 1.8519, + "step": 22430 + }, + { + "epoch": 0.83, + "learning_rate": 9.165395916242051e-06, + "loss": 1.9837, + "step": 22440 + }, + { + "epoch": 0.83, + "learning_rate": 9.165023989288505e-06, + "loss": 1.9651, + "step": 22450 + }, + { + "epoch": 0.84, + "learning_rate": 9.164652062334958e-06, + "loss": 1.9806, + "step": 22460 + }, + { + "epoch": 0.84, + "learning_rate": 9.164280135381411e-06, + "loss": 1.916, + "step": 22470 + }, + { + "epoch": 0.84, + "learning_rate": 9.163908208427865e-06, + "loss": 2.065, + "step": 22480 + }, + { + "epoch": 0.84, + "learning_rate": 9.163536281474318e-06, + "loss": 1.8896, + "step": 22490 + }, + { + "epoch": 0.84, + "learning_rate": 9.163164354520774e-06, + "loss": 1.9319, + "step": 22500 + }, + { + "epoch": 0.84, + "eval_loss": 1.7863953113555908, + "eval_runtime": 16.8269, + "eval_samples_per_second": 59.429, + "eval_steps_per_second": 3.744, + "step": 22500 + }, + { + "epoch": 0.84, + "learning_rate": 9.162792427567227e-06, + "loss": 1.8656, + "step": 22510 + }, + { + "epoch": 0.84, + "learning_rate": 9.16242050061368e-06, + "loss": 1.8457, + "step": 22520 + }, + { + "epoch": 0.84, + "learning_rate": 9.162048573660134e-06, + "loss": 1.8031, + "step": 22530 + }, + { + "epoch": 0.84, + "learning_rate": 9.161676646706587e-06, + "loss": 1.9792, + "step": 22540 + }, + { + "epoch": 0.84, + "learning_rate": 9.16130471975304e-06, + "loss": 1.8829, + "step": 22550 + }, + { + "epoch": 0.84, + "learning_rate": 9.160932792799494e-06, + "loss": 1.7898, + "step": 22560 + }, + { + "epoch": 0.84, + "learning_rate": 9.16056086584595e-06, + "loss": 1.9236, + "step": 22570 + }, + { + "epoch": 0.84, + "learning_rate": 9.160188938892403e-06, + "loss": 1.871, + "step": 22580 + }, + { + "epoch": 0.84, + "learning_rate": 9.159817011938856e-06, + "loss": 1.83, + "step": 22590 + }, + { + "epoch": 0.84, + "learning_rate": 9.15944508498531e-06, + "loss": 1.9633, + "step": 22600 + }, + { + "epoch": 0.84, + "eval_loss": 1.7852234840393066, + "eval_runtime": 16.8189, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 22600 + }, + { + "epoch": 0.84, + "learning_rate": 9.159073158031763e-06, + "loss": 1.9874, + "step": 22610 + }, + { + "epoch": 0.84, + "learning_rate": 9.158701231078217e-06, + "loss": 2.0622, + "step": 22620 + }, + { + "epoch": 0.84, + "learning_rate": 9.15832930412467e-06, + "loss": 1.8915, + "step": 22630 + }, + { + "epoch": 0.84, + "learning_rate": 9.157957377171124e-06, + "loss": 1.8303, + "step": 22640 + }, + { + "epoch": 0.84, + "learning_rate": 9.157585450217577e-06, + "loss": 1.8654, + "step": 22650 + }, + { + "epoch": 0.84, + "learning_rate": 9.15721352326403e-06, + "loss": 1.9066, + "step": 22660 + }, + { + "epoch": 0.84, + "learning_rate": 9.156841596310486e-06, + "loss": 1.8578, + "step": 22670 + }, + { + "epoch": 0.84, + "learning_rate": 9.15646966935694e-06, + "loss": 1.7821, + "step": 22680 + }, + { + "epoch": 0.84, + "learning_rate": 9.156097742403393e-06, + "loss": 1.9068, + "step": 22690 + }, + { + "epoch": 0.84, + "learning_rate": 9.155725815449846e-06, + "loss": 1.9336, + "step": 22700 + }, + { + "epoch": 0.84, + "eval_loss": 1.7857043743133545, + "eval_runtime": 16.8326, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 22700 + }, + { + "epoch": 0.84, + "learning_rate": 9.1553538884963e-06, + "loss": 1.8525, + "step": 22710 + }, + { + "epoch": 0.85, + "learning_rate": 9.154981961542753e-06, + "loss": 1.8797, + "step": 22720 + }, + { + "epoch": 0.85, + "learning_rate": 9.154610034589208e-06, + "loss": 1.955, + "step": 22730 + }, + { + "epoch": 0.85, + "learning_rate": 9.154238107635662e-06, + "loss": 1.8501, + "step": 22740 + }, + { + "epoch": 0.85, + "learning_rate": 9.153866180682115e-06, + "loss": 1.8478, + "step": 22750 + }, + { + "epoch": 0.85, + "learning_rate": 9.153494253728569e-06, + "loss": 2.0115, + "step": 22760 + }, + { + "epoch": 0.85, + "learning_rate": 9.153122326775022e-06, + "loss": 1.8949, + "step": 22770 + }, + { + "epoch": 0.85, + "learning_rate": 9.152750399821475e-06, + "loss": 1.9025, + "step": 22780 + }, + { + "epoch": 0.85, + "learning_rate": 9.15237847286793e-06, + "loss": 1.7681, + "step": 22790 + }, + { + "epoch": 0.85, + "learning_rate": 9.152006545914384e-06, + "loss": 1.784, + "step": 22800 + }, + { + "epoch": 0.85, + "eval_loss": 1.7855826616287231, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 22800 + }, + { + "epoch": 0.85, + "learning_rate": 9.151634618960838e-06, + "loss": 1.7926, + "step": 22810 + }, + { + "epoch": 0.85, + "learning_rate": 9.15126269200729e-06, + "loss": 1.9028, + "step": 22820 + }, + { + "epoch": 0.85, + "learning_rate": 9.150890765053744e-06, + "loss": 1.8042, + "step": 22830 + }, + { + "epoch": 0.85, + "learning_rate": 9.150518838100198e-06, + "loss": 1.9223, + "step": 22840 + }, + { + "epoch": 0.85, + "learning_rate": 9.150146911146651e-06, + "loss": 2.0503, + "step": 22850 + }, + { + "epoch": 0.85, + "learning_rate": 9.149774984193105e-06, + "loss": 1.8302, + "step": 22860 + }, + { + "epoch": 0.85, + "learning_rate": 9.149403057239558e-06, + "loss": 1.826, + "step": 22870 + }, + { + "epoch": 0.85, + "learning_rate": 9.149031130286012e-06, + "loss": 1.966, + "step": 22880 + }, + { + "epoch": 0.85, + "learning_rate": 9.148659203332467e-06, + "loss": 1.9939, + "step": 22890 + }, + { + "epoch": 0.85, + "learning_rate": 9.14828727637892e-06, + "loss": 1.8342, + "step": 22900 + }, + { + "epoch": 0.85, + "eval_loss": 1.783772349357605, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 22900 + }, + { + "epoch": 0.85, + "learning_rate": 9.147915349425374e-06, + "loss": 1.9988, + "step": 22910 + }, + { + "epoch": 0.85, + "learning_rate": 9.147543422471827e-06, + "loss": 1.849, + "step": 22920 + }, + { + "epoch": 0.85, + "learning_rate": 9.14717149551828e-06, + "loss": 1.8212, + "step": 22930 + }, + { + "epoch": 0.85, + "learning_rate": 9.146799568564734e-06, + "loss": 1.9242, + "step": 22940 + }, + { + "epoch": 0.85, + "learning_rate": 9.14642764161119e-06, + "loss": 1.8006, + "step": 22950 + }, + { + "epoch": 0.85, + "learning_rate": 9.146055714657643e-06, + "loss": 1.7922, + "step": 22960 + }, + { + "epoch": 0.85, + "learning_rate": 9.145683787704096e-06, + "loss": 1.8404, + "step": 22970 + }, + { + "epoch": 0.85, + "learning_rate": 9.14531186075055e-06, + "loss": 1.8081, + "step": 22980 + }, + { + "epoch": 0.86, + "learning_rate": 9.144939933797003e-06, + "loss": 1.823, + "step": 22990 + }, + { + "epoch": 0.86, + "learning_rate": 9.144568006843457e-06, + "loss": 1.7423, + "step": 23000 + }, + { + "epoch": 0.86, + "eval_loss": 1.78406822681427, + "eval_runtime": 16.8062, + "eval_samples_per_second": 59.502, + "eval_steps_per_second": 3.749, + "step": 23000 + }, + { + "epoch": 0.86, + "learning_rate": 9.14419607988991e-06, + "loss": 1.6985, + "step": 23010 + }, + { + "epoch": 0.86, + "learning_rate": 9.143824152936364e-06, + "loss": 1.8699, + "step": 23020 + }, + { + "epoch": 0.86, + "learning_rate": 9.143452225982817e-06, + "loss": 1.9513, + "step": 23030 + }, + { + "epoch": 0.86, + "learning_rate": 9.14308029902927e-06, + "loss": 1.7759, + "step": 23040 + }, + { + "epoch": 0.86, + "learning_rate": 9.142708372075726e-06, + "loss": 1.76, + "step": 23050 + }, + { + "epoch": 0.86, + "learning_rate": 9.142336445122179e-06, + "loss": 1.8393, + "step": 23060 + }, + { + "epoch": 0.86, + "learning_rate": 9.141964518168633e-06, + "loss": 1.7866, + "step": 23070 + }, + { + "epoch": 0.86, + "learning_rate": 9.141592591215086e-06, + "loss": 1.903, + "step": 23080 + }, + { + "epoch": 0.86, + "learning_rate": 9.14122066426154e-06, + "loss": 2.044, + "step": 23090 + }, + { + "epoch": 0.86, + "learning_rate": 9.140848737307993e-06, + "loss": 1.8962, + "step": 23100 + }, + { + "epoch": 0.86, + "eval_loss": 1.782977819442749, + "eval_runtime": 16.817, + "eval_samples_per_second": 59.464, + "eval_steps_per_second": 3.746, + "step": 23100 + }, + { + "epoch": 0.86, + "learning_rate": 9.140476810354448e-06, + "loss": 1.9329, + "step": 23110 + }, + { + "epoch": 0.86, + "learning_rate": 9.140104883400902e-06, + "loss": 1.8383, + "step": 23120 + }, + { + "epoch": 0.86, + "learning_rate": 9.139732956447355e-06, + "loss": 1.8463, + "step": 23130 + }, + { + "epoch": 0.86, + "learning_rate": 9.139361029493808e-06, + "loss": 1.795, + "step": 23140 + }, + { + "epoch": 0.86, + "learning_rate": 9.138989102540262e-06, + "loss": 1.9273, + "step": 23150 + }, + { + "epoch": 0.86, + "learning_rate": 9.138617175586715e-06, + "loss": 1.7961, + "step": 23160 + }, + { + "epoch": 0.86, + "learning_rate": 9.138245248633169e-06, + "loss": 2.0443, + "step": 23170 + }, + { + "epoch": 0.86, + "learning_rate": 9.137873321679624e-06, + "loss": 2.01, + "step": 23180 + }, + { + "epoch": 0.86, + "learning_rate": 9.137501394726076e-06, + "loss": 1.8077, + "step": 23190 + }, + { + "epoch": 0.86, + "learning_rate": 9.13712946777253e-06, + "loss": 1.8753, + "step": 23200 + }, + { + "epoch": 0.86, + "eval_loss": 1.7827882766723633, + "eval_runtime": 16.824, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 23200 + }, + { + "epoch": 0.86, + "learning_rate": 9.136757540818983e-06, + "loss": 1.7234, + "step": 23210 + }, + { + "epoch": 0.86, + "learning_rate": 9.136385613865438e-06, + "loss": 1.876, + "step": 23220 + }, + { + "epoch": 0.86, + "learning_rate": 9.136013686911891e-06, + "loss": 1.8888, + "step": 23230 + }, + { + "epoch": 0.86, + "learning_rate": 9.135641759958345e-06, + "loss": 1.9058, + "step": 23240 + }, + { + "epoch": 0.86, + "learning_rate": 9.135269833004798e-06, + "loss": 1.8209, + "step": 23250 + }, + { + "epoch": 0.87, + "learning_rate": 9.134897906051252e-06, + "loss": 1.8233, + "step": 23260 + }, + { + "epoch": 0.87, + "learning_rate": 9.134525979097705e-06, + "loss": 1.9008, + "step": 23270 + }, + { + "epoch": 0.87, + "learning_rate": 9.13415405214416e-06, + "loss": 1.8274, + "step": 23280 + }, + { + "epoch": 0.87, + "learning_rate": 9.133782125190614e-06, + "loss": 1.9483, + "step": 23290 + }, + { + "epoch": 0.87, + "learning_rate": 9.133410198237067e-06, + "loss": 1.8741, + "step": 23300 + }, + { + "epoch": 0.87, + "eval_loss": 1.7832889556884766, + "eval_runtime": 16.8012, + "eval_samples_per_second": 59.52, + "eval_steps_per_second": 3.75, + "step": 23300 + }, + { + "epoch": 0.87, + "learning_rate": 9.13303827128352e-06, + "loss": 1.779, + "step": 23310 + }, + { + "epoch": 0.87, + "learning_rate": 9.132666344329974e-06, + "loss": 1.9686, + "step": 23320 + }, + { + "epoch": 0.87, + "learning_rate": 9.132294417376428e-06, + "loss": 1.9534, + "step": 23330 + }, + { + "epoch": 0.87, + "learning_rate": 9.131922490422883e-06, + "loss": 1.9523, + "step": 23340 + }, + { + "epoch": 0.87, + "learning_rate": 9.131550563469336e-06, + "loss": 1.8339, + "step": 23350 + }, + { + "epoch": 0.87, + "learning_rate": 9.13117863651579e-06, + "loss": 1.8257, + "step": 23360 + }, + { + "epoch": 0.87, + "learning_rate": 9.130806709562243e-06, + "loss": 1.8369, + "step": 23370 + }, + { + "epoch": 0.87, + "learning_rate": 9.130434782608697e-06, + "loss": 1.95, + "step": 23380 + }, + { + "epoch": 0.87, + "learning_rate": 9.13006285565515e-06, + "loss": 1.8949, + "step": 23390 + }, + { + "epoch": 0.87, + "learning_rate": 9.129690928701603e-06, + "loss": 1.8906, + "step": 23400 + }, + { + "epoch": 0.87, + "eval_loss": 1.7827751636505127, + "eval_runtime": 16.8066, + "eval_samples_per_second": 59.5, + "eval_steps_per_second": 3.749, + "step": 23400 + }, + { + "epoch": 0.87, + "learning_rate": 9.129319001748057e-06, + "loss": 1.8599, + "step": 23410 + }, + { + "epoch": 0.87, + "learning_rate": 9.12894707479451e-06, + "loss": 1.9105, + "step": 23420 + }, + { + "epoch": 0.87, + "learning_rate": 9.128575147840964e-06, + "loss": 1.9875, + "step": 23430 + }, + { + "epoch": 0.87, + "learning_rate": 9.128203220887419e-06, + "loss": 1.8016, + "step": 23440 + }, + { + "epoch": 0.87, + "learning_rate": 9.127831293933872e-06, + "loss": 1.8275, + "step": 23450 + }, + { + "epoch": 0.87, + "learning_rate": 9.127459366980326e-06, + "loss": 1.7936, + "step": 23460 + }, + { + "epoch": 0.87, + "learning_rate": 9.12708744002678e-06, + "loss": 1.9569, + "step": 23470 + }, + { + "epoch": 0.87, + "learning_rate": 9.126715513073233e-06, + "loss": 1.7753, + "step": 23480 + }, + { + "epoch": 0.87, + "learning_rate": 9.126343586119686e-06, + "loss": 1.8333, + "step": 23490 + }, + { + "epoch": 0.87, + "learning_rate": 9.125971659166141e-06, + "loss": 1.8954, + "step": 23500 + }, + { + "epoch": 0.87, + "eval_loss": 1.7830890417099, + "eval_runtime": 16.8222, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 23500 + }, + { + "epoch": 0.87, + "learning_rate": 9.125599732212595e-06, + "loss": 1.8635, + "step": 23510 + }, + { + "epoch": 0.87, + "learning_rate": 9.125227805259048e-06, + "loss": 1.8991, + "step": 23520 + }, + { + "epoch": 0.88, + "learning_rate": 9.124855878305502e-06, + "loss": 1.7809, + "step": 23530 + }, + { + "epoch": 0.88, + "learning_rate": 9.124483951351955e-06, + "loss": 1.9556, + "step": 23540 + }, + { + "epoch": 0.88, + "learning_rate": 9.124112024398409e-06, + "loss": 1.8984, + "step": 23550 + }, + { + "epoch": 0.88, + "learning_rate": 9.123740097444864e-06, + "loss": 1.744, + "step": 23560 + }, + { + "epoch": 0.88, + "learning_rate": 9.123368170491316e-06, + "loss": 1.8414, + "step": 23570 + }, + { + "epoch": 0.88, + "learning_rate": 9.122996243537769e-06, + "loss": 1.8431, + "step": 23580 + }, + { + "epoch": 0.88, + "learning_rate": 9.122624316584223e-06, + "loss": 1.9227, + "step": 23590 + }, + { + "epoch": 0.88, + "learning_rate": 9.122252389630678e-06, + "loss": 1.9675, + "step": 23600 + }, + { + "epoch": 0.88, + "eval_loss": 1.7820348739624023, + "eval_runtime": 16.8146, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 23600 + }, + { + "epoch": 0.88, + "learning_rate": 9.121880462677131e-06, + "loss": 1.8875, + "step": 23610 + }, + { + "epoch": 0.88, + "learning_rate": 9.121508535723585e-06, + "loss": 1.8543, + "step": 23620 + }, + { + "epoch": 0.88, + "learning_rate": 9.121136608770038e-06, + "loss": 1.9495, + "step": 23630 + }, + { + "epoch": 0.88, + "learning_rate": 9.120764681816492e-06, + "loss": 1.8256, + "step": 23640 + }, + { + "epoch": 0.88, + "learning_rate": 9.120392754862945e-06, + "loss": 1.7763, + "step": 23650 + }, + { + "epoch": 0.88, + "learning_rate": 9.1200208279094e-06, + "loss": 1.7404, + "step": 23660 + }, + { + "epoch": 0.88, + "learning_rate": 9.119648900955854e-06, + "loss": 1.877, + "step": 23670 + }, + { + "epoch": 0.88, + "learning_rate": 9.119276974002307e-06, + "loss": 1.9735, + "step": 23680 + }, + { + "epoch": 0.88, + "learning_rate": 9.11890504704876e-06, + "loss": 1.9451, + "step": 23690 + }, + { + "epoch": 0.88, + "learning_rate": 9.118533120095214e-06, + "loss": 1.8317, + "step": 23700 + }, + { + "epoch": 0.88, + "eval_loss": 1.7827292680740356, + "eval_runtime": 16.8112, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 23700 + }, + { + "epoch": 0.88, + "learning_rate": 9.118161193141667e-06, + "loss": 1.9792, + "step": 23710 + }, + { + "epoch": 0.88, + "learning_rate": 9.117789266188121e-06, + "loss": 1.814, + "step": 23720 + }, + { + "epoch": 0.88, + "learning_rate": 9.117417339234576e-06, + "loss": 1.8603, + "step": 23730 + }, + { + "epoch": 0.88, + "learning_rate": 9.11704541228103e-06, + "loss": 1.7482, + "step": 23740 + }, + { + "epoch": 0.88, + "learning_rate": 9.116673485327483e-06, + "loss": 2.0409, + "step": 23750 + }, + { + "epoch": 0.88, + "learning_rate": 9.116301558373935e-06, + "loss": 2.0291, + "step": 23760 + }, + { + "epoch": 0.88, + "learning_rate": 9.11592963142039e-06, + "loss": 1.8127, + "step": 23770 + }, + { + "epoch": 0.88, + "learning_rate": 9.115557704466843e-06, + "loss": 1.8941, + "step": 23780 + }, + { + "epoch": 0.88, + "learning_rate": 9.115185777513297e-06, + "loss": 1.817, + "step": 23790 + }, + { + "epoch": 0.89, + "learning_rate": 9.11481385055975e-06, + "loss": 1.8363, + "step": 23800 + }, + { + "epoch": 0.89, + "eval_loss": 1.7809303998947144, + "eval_runtime": 16.8344, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 23800 + }, + { + "epoch": 0.89, + "learning_rate": 9.114441923606204e-06, + "loss": 1.8594, + "step": 23810 + }, + { + "epoch": 0.89, + "learning_rate": 9.114069996652657e-06, + "loss": 1.8896, + "step": 23820 + }, + { + "epoch": 0.89, + "learning_rate": 9.113698069699112e-06, + "loss": 1.8913, + "step": 23830 + }, + { + "epoch": 0.89, + "learning_rate": 9.113326142745566e-06, + "loss": 1.8568, + "step": 23840 + }, + { + "epoch": 0.89, + "learning_rate": 9.11295421579202e-06, + "loss": 1.8531, + "step": 23850 + }, + { + "epoch": 0.89, + "learning_rate": 9.112582288838473e-06, + "loss": 1.8193, + "step": 23860 + }, + { + "epoch": 0.89, + "learning_rate": 9.112210361884926e-06, + "loss": 1.8888, + "step": 23870 + }, + { + "epoch": 0.89, + "learning_rate": 9.11183843493138e-06, + "loss": 2.0432, + "step": 23880 + }, + { + "epoch": 0.89, + "learning_rate": 9.111466507977835e-06, + "loss": 1.7754, + "step": 23890 + }, + { + "epoch": 0.89, + "learning_rate": 9.111094581024288e-06, + "loss": 1.8309, + "step": 23900 + }, + { + "epoch": 0.89, + "eval_loss": 1.780165672302246, + "eval_runtime": 16.8218, + "eval_samples_per_second": 59.447, + "eval_steps_per_second": 3.745, + "step": 23900 + }, + { + "epoch": 0.89, + "learning_rate": 9.110722654070742e-06, + "loss": 1.7455, + "step": 23910 + }, + { + "epoch": 0.89, + "learning_rate": 9.110350727117195e-06, + "loss": 1.7861, + "step": 23920 + }, + { + "epoch": 0.89, + "learning_rate": 9.109978800163649e-06, + "loss": 1.8584, + "step": 23930 + }, + { + "epoch": 0.89, + "learning_rate": 9.109606873210102e-06, + "loss": 1.8603, + "step": 23940 + }, + { + "epoch": 0.89, + "learning_rate": 9.109234946256556e-06, + "loss": 2.0211, + "step": 23950 + }, + { + "epoch": 0.89, + "learning_rate": 9.108863019303009e-06, + "loss": 1.8546, + "step": 23960 + }, + { + "epoch": 0.89, + "learning_rate": 9.108491092349462e-06, + "loss": 1.9064, + "step": 23970 + }, + { + "epoch": 0.89, + "learning_rate": 9.108119165395916e-06, + "loss": 1.8816, + "step": 23980 + }, + { + "epoch": 0.89, + "learning_rate": 9.107747238442371e-06, + "loss": 1.8366, + "step": 23990 + }, + { + "epoch": 0.89, + "learning_rate": 9.107375311488825e-06, + "loss": 1.8589, + "step": 24000 + }, + { + "epoch": 0.89, + "eval_loss": 1.780618667602539, + "eval_runtime": 16.8418, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 24000 + }, + { + "epoch": 0.89, + "learning_rate": 9.107003384535278e-06, + "loss": 1.8575, + "step": 24010 + }, + { + "epoch": 0.89, + "learning_rate": 9.106631457581731e-06, + "loss": 1.7758, + "step": 24020 + }, + { + "epoch": 0.89, + "learning_rate": 9.106259530628185e-06, + "loss": 1.8835, + "step": 24030 + }, + { + "epoch": 0.89, + "learning_rate": 9.105887603674638e-06, + "loss": 1.9042, + "step": 24040 + }, + { + "epoch": 0.89, + "learning_rate": 9.105515676721094e-06, + "loss": 1.8538, + "step": 24050 + }, + { + "epoch": 0.89, + "learning_rate": 9.105143749767547e-06, + "loss": 2.2385, + "step": 24060 + }, + { + "epoch": 0.9, + "learning_rate": 9.104771822814e-06, + "loss": 1.7993, + "step": 24070 + }, + { + "epoch": 0.9, + "learning_rate": 9.104399895860454e-06, + "loss": 1.7948, + "step": 24080 + }, + { + "epoch": 0.9, + "learning_rate": 9.104027968906907e-06, + "loss": 1.8662, + "step": 24090 + }, + { + "epoch": 0.9, + "learning_rate": 9.103656041953361e-06, + "loss": 1.8956, + "step": 24100 + }, + { + "epoch": 0.9, + "eval_loss": 1.780117392539978, + "eval_runtime": 16.8108, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 24100 + }, + { + "epoch": 0.9, + "learning_rate": 9.103284114999816e-06, + "loss": 1.8945, + "step": 24110 + }, + { + "epoch": 0.9, + "learning_rate": 9.10291218804627e-06, + "loss": 1.827, + "step": 24120 + }, + { + "epoch": 0.9, + "learning_rate": 9.102540261092721e-06, + "loss": 1.8936, + "step": 24130 + }, + { + "epoch": 0.9, + "learning_rate": 9.102168334139175e-06, + "loss": 1.8519, + "step": 24140 + }, + { + "epoch": 0.9, + "learning_rate": 9.10179640718563e-06, + "loss": 1.7903, + "step": 24150 + }, + { + "epoch": 0.9, + "learning_rate": 9.101424480232083e-06, + "loss": 1.8473, + "step": 24160 + }, + { + "epoch": 0.9, + "learning_rate": 9.101052553278537e-06, + "loss": 1.7975, + "step": 24170 + }, + { + "epoch": 0.9, + "learning_rate": 9.10068062632499e-06, + "loss": 1.8813, + "step": 24180 + }, + { + "epoch": 0.9, + "learning_rate": 9.100308699371444e-06, + "loss": 1.7891, + "step": 24190 + }, + { + "epoch": 0.9, + "learning_rate": 9.099936772417897e-06, + "loss": 1.8668, + "step": 24200 + }, + { + "epoch": 0.9, + "eval_loss": 1.7802742719650269, + "eval_runtime": 16.8101, + "eval_samples_per_second": 59.488, + "eval_steps_per_second": 3.748, + "step": 24200 + }, + { + "epoch": 0.9, + "learning_rate": 9.099564845464352e-06, + "loss": 1.9716, + "step": 24210 + }, + { + "epoch": 0.9, + "learning_rate": 9.099192918510806e-06, + "loss": 1.8658, + "step": 24220 + }, + { + "epoch": 0.9, + "learning_rate": 9.09882099155726e-06, + "loss": 1.9696, + "step": 24230 + }, + { + "epoch": 0.9, + "learning_rate": 9.098449064603713e-06, + "loss": 1.8437, + "step": 24240 + }, + { + "epoch": 0.9, + "learning_rate": 9.098077137650166e-06, + "loss": 1.8442, + "step": 24250 + }, + { + "epoch": 0.9, + "learning_rate": 9.09770521069662e-06, + "loss": 1.7239, + "step": 24260 + }, + { + "epoch": 0.9, + "learning_rate": 9.097333283743075e-06, + "loss": 1.8586, + "step": 24270 + }, + { + "epoch": 0.9, + "learning_rate": 9.096961356789528e-06, + "loss": 1.8661, + "step": 24280 + }, + { + "epoch": 0.9, + "learning_rate": 9.096589429835982e-06, + "loss": 1.7904, + "step": 24290 + }, + { + "epoch": 0.9, + "learning_rate": 9.096217502882435e-06, + "loss": 2.1079, + "step": 24300 + }, + { + "epoch": 0.9, + "eval_loss": 1.778773307800293, + "eval_runtime": 16.8069, + "eval_samples_per_second": 59.499, + "eval_steps_per_second": 3.748, + "step": 24300 + }, + { + "epoch": 0.9, + "learning_rate": 9.095845575928889e-06, + "loss": 1.8824, + "step": 24310 + }, + { + "epoch": 0.9, + "learning_rate": 9.095473648975342e-06, + "loss": 2.0655, + "step": 24320 + }, + { + "epoch": 0.9, + "learning_rate": 9.095101722021795e-06, + "loss": 1.8592, + "step": 24330 + }, + { + "epoch": 0.91, + "learning_rate": 9.094729795068249e-06, + "loss": 1.8754, + "step": 24340 + }, + { + "epoch": 0.91, + "learning_rate": 9.094357868114702e-06, + "loss": 1.7637, + "step": 24350 + }, + { + "epoch": 0.91, + "learning_rate": 9.093985941161156e-06, + "loss": 1.8006, + "step": 24360 + }, + { + "epoch": 0.91, + "learning_rate": 9.09361401420761e-06, + "loss": 1.935, + "step": 24370 + }, + { + "epoch": 0.91, + "learning_rate": 9.093242087254064e-06, + "loss": 1.8339, + "step": 24380 + }, + { + "epoch": 0.91, + "learning_rate": 9.092870160300518e-06, + "loss": 1.824, + "step": 24390 + }, + { + "epoch": 0.91, + "learning_rate": 9.092498233346971e-06, + "loss": 1.8794, + "step": 24400 + }, + { + "epoch": 0.91, + "eval_loss": 1.7778249979019165, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 24400 + }, + { + "epoch": 0.91, + "learning_rate": 9.092126306393425e-06, + "loss": 1.7296, + "step": 24410 + }, + { + "epoch": 0.91, + "learning_rate": 9.091754379439878e-06, + "loss": 1.7929, + "step": 24420 + }, + { + "epoch": 0.91, + "learning_rate": 9.091382452486332e-06, + "loss": 1.8553, + "step": 24430 + }, + { + "epoch": 0.91, + "learning_rate": 9.091010525532787e-06, + "loss": 1.8748, + "step": 24440 + }, + { + "epoch": 0.91, + "learning_rate": 9.09063859857924e-06, + "loss": 1.8166, + "step": 24450 + }, + { + "epoch": 0.91, + "learning_rate": 9.090266671625694e-06, + "loss": 1.8515, + "step": 24460 + }, + { + "epoch": 0.91, + "learning_rate": 9.089894744672147e-06, + "loss": 1.8453, + "step": 24470 + }, + { + "epoch": 0.91, + "learning_rate": 9.0895228177186e-06, + "loss": 1.8653, + "step": 24480 + }, + { + "epoch": 0.91, + "learning_rate": 9.089150890765054e-06, + "loss": 1.8353, + "step": 24490 + }, + { + "epoch": 0.91, + "learning_rate": 9.08877896381151e-06, + "loss": 1.9756, + "step": 24500 + }, + { + "epoch": 0.91, + "eval_loss": 1.7772235870361328, + "eval_runtime": 16.8112, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 24500 + }, + { + "epoch": 0.91, + "learning_rate": 9.088407036857961e-06, + "loss": 1.8528, + "step": 24510 + }, + { + "epoch": 0.91, + "learning_rate": 9.088035109904415e-06, + "loss": 1.8117, + "step": 24520 + }, + { + "epoch": 0.91, + "learning_rate": 9.087663182950868e-06, + "loss": 1.8685, + "step": 24530 + }, + { + "epoch": 0.91, + "learning_rate": 9.087291255997323e-06, + "loss": 1.7352, + "step": 24540 + }, + { + "epoch": 0.91, + "learning_rate": 9.086919329043777e-06, + "loss": 1.8586, + "step": 24550 + }, + { + "epoch": 0.91, + "learning_rate": 9.08654740209023e-06, + "loss": 1.8399, + "step": 24560 + }, + { + "epoch": 0.91, + "learning_rate": 9.086175475136684e-06, + "loss": 1.8524, + "step": 24570 + }, + { + "epoch": 0.91, + "learning_rate": 9.085803548183137e-06, + "loss": 1.8675, + "step": 24580 + }, + { + "epoch": 0.91, + "learning_rate": 9.08543162122959e-06, + "loss": 1.8745, + "step": 24590 + }, + { + "epoch": 0.91, + "learning_rate": 9.085059694276046e-06, + "loss": 1.7694, + "step": 24600 + }, + { + "epoch": 0.91, + "eval_loss": 1.776825189590454, + "eval_runtime": 16.8181, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 24600 + }, + { + "epoch": 0.92, + "learning_rate": 9.084687767322499e-06, + "loss": 1.8297, + "step": 24610 + }, + { + "epoch": 0.92, + "learning_rate": 9.084315840368953e-06, + "loss": 1.9477, + "step": 24620 + }, + { + "epoch": 0.92, + "learning_rate": 9.083943913415406e-06, + "loss": 1.9275, + "step": 24630 + }, + { + "epoch": 0.92, + "learning_rate": 9.08357198646186e-06, + "loss": 1.8714, + "step": 24640 + }, + { + "epoch": 0.92, + "learning_rate": 9.083200059508313e-06, + "loss": 1.8252, + "step": 24650 + }, + { + "epoch": 0.92, + "learning_rate": 9.082828132554768e-06, + "loss": 1.8654, + "step": 24660 + }, + { + "epoch": 0.92, + "learning_rate": 9.082456205601222e-06, + "loss": 1.8484, + "step": 24670 + }, + { + "epoch": 0.92, + "learning_rate": 9.082084278647675e-06, + "loss": 1.7689, + "step": 24680 + }, + { + "epoch": 0.92, + "learning_rate": 9.081712351694128e-06, + "loss": 1.8547, + "step": 24690 + }, + { + "epoch": 0.92, + "learning_rate": 9.081340424740582e-06, + "loss": 1.7082, + "step": 24700 + }, + { + "epoch": 0.92, + "eval_loss": 1.7778432369232178, + "eval_runtime": 16.8114, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 24700 + }, + { + "epoch": 0.92, + "learning_rate": 9.080968497787035e-06, + "loss": 1.8488, + "step": 24710 + }, + { + "epoch": 0.92, + "learning_rate": 9.080596570833489e-06, + "loss": 1.7839, + "step": 24720 + }, + { + "epoch": 0.92, + "learning_rate": 9.080224643879942e-06, + "loss": 1.738, + "step": 24730 + }, + { + "epoch": 0.92, + "learning_rate": 9.079852716926396e-06, + "loss": 1.8031, + "step": 24740 + }, + { + "epoch": 0.92, + "learning_rate": 9.07948078997285e-06, + "loss": 1.8992, + "step": 24750 + }, + { + "epoch": 0.92, + "learning_rate": 9.079108863019304e-06, + "loss": 1.8739, + "step": 24760 + }, + { + "epoch": 0.92, + "learning_rate": 9.078736936065758e-06, + "loss": 1.907, + "step": 24770 + }, + { + "epoch": 0.92, + "learning_rate": 9.078365009112211e-06, + "loss": 1.9273, + "step": 24780 + }, + { + "epoch": 0.92, + "learning_rate": 9.077993082158665e-06, + "loss": 1.7827, + "step": 24790 + }, + { + "epoch": 0.92, + "learning_rate": 9.077621155205118e-06, + "loss": 1.9094, + "step": 24800 + }, + { + "epoch": 0.92, + "eval_loss": 1.778052568435669, + "eval_runtime": 16.815, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 24800 + }, + { + "epoch": 0.92, + "learning_rate": 9.077249228251572e-06, + "loss": 1.848, + "step": 24810 + }, + { + "epoch": 0.92, + "learning_rate": 9.076877301298027e-06, + "loss": 2.0053, + "step": 24820 + }, + { + "epoch": 0.92, + "learning_rate": 9.07650537434448e-06, + "loss": 1.8765, + "step": 24830 + }, + { + "epoch": 0.92, + "learning_rate": 9.076133447390934e-06, + "loss": 1.9675, + "step": 24840 + }, + { + "epoch": 0.92, + "learning_rate": 9.075761520437387e-06, + "loss": 1.8255, + "step": 24850 + }, + { + "epoch": 0.92, + "learning_rate": 9.07538959348384e-06, + "loss": 1.8278, + "step": 24860 + }, + { + "epoch": 0.92, + "learning_rate": 9.075017666530294e-06, + "loss": 1.9158, + "step": 24870 + }, + { + "epoch": 0.93, + "learning_rate": 9.074645739576748e-06, + "loss": 1.7952, + "step": 24880 + }, + { + "epoch": 0.93, + "learning_rate": 9.074273812623201e-06, + "loss": 1.8447, + "step": 24890 + }, + { + "epoch": 0.93, + "learning_rate": 9.073901885669655e-06, + "loss": 1.8471, + "step": 24900 + }, + { + "epoch": 0.93, + "eval_loss": 1.7771838903427124, + "eval_runtime": 16.7993, + "eval_samples_per_second": 59.526, + "eval_steps_per_second": 3.75, + "step": 24900 + }, + { + "epoch": 0.93, + "learning_rate": 9.073529958716108e-06, + "loss": 1.8756, + "step": 24910 + }, + { + "epoch": 0.93, + "learning_rate": 9.073158031762561e-06, + "loss": 1.7024, + "step": 24920 + }, + { + "epoch": 0.93, + "learning_rate": 9.072786104809017e-06, + "loss": 1.8309, + "step": 24930 + }, + { + "epoch": 0.93, + "learning_rate": 9.07241417785547e-06, + "loss": 1.9027, + "step": 24940 + }, + { + "epoch": 0.93, + "learning_rate": 9.072042250901924e-06, + "loss": 1.7348, + "step": 24950 + }, + { + "epoch": 0.93, + "learning_rate": 9.071670323948377e-06, + "loss": 1.8768, + "step": 24960 + }, + { + "epoch": 0.93, + "learning_rate": 9.07129839699483e-06, + "loss": 1.9224, + "step": 24970 + }, + { + "epoch": 0.93, + "learning_rate": 9.070926470041284e-06, + "loss": 1.9556, + "step": 24980 + }, + { + "epoch": 0.93, + "learning_rate": 9.070554543087739e-06, + "loss": 1.8369, + "step": 24990 + }, + { + "epoch": 0.93, + "learning_rate": 9.070182616134193e-06, + "loss": 1.7995, + "step": 25000 + }, + { + "epoch": 0.93, + "eval_loss": 1.776485562324524, + "eval_runtime": 16.8124, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 25000 + }, + { + "epoch": 0.93, + "learning_rate": 9.069810689180646e-06, + "loss": 1.8999, + "step": 25010 + }, + { + "epoch": 0.93, + "learning_rate": 9.0694387622271e-06, + "loss": 1.7922, + "step": 25020 + }, + { + "epoch": 0.93, + "learning_rate": 9.069066835273553e-06, + "loss": 1.781, + "step": 25030 + }, + { + "epoch": 0.93, + "learning_rate": 9.068694908320006e-06, + "loss": 1.7338, + "step": 25040 + }, + { + "epoch": 0.93, + "learning_rate": 9.068322981366461e-06, + "loss": 1.9914, + "step": 25050 + }, + { + "epoch": 0.93, + "learning_rate": 9.067951054412915e-06, + "loss": 1.9869, + "step": 25060 + }, + { + "epoch": 0.93, + "learning_rate": 9.067579127459367e-06, + "loss": 1.6568, + "step": 25070 + }, + { + "epoch": 0.93, + "learning_rate": 9.06720720050582e-06, + "loss": 1.8, + "step": 25080 + }, + { + "epoch": 0.93, + "learning_rate": 9.066835273552275e-06, + "loss": 1.8599, + "step": 25090 + }, + { + "epoch": 0.93, + "learning_rate": 9.066463346598729e-06, + "loss": 1.902, + "step": 25100 + }, + { + "epoch": 0.93, + "eval_loss": 1.7766227722167969, + "eval_runtime": 16.8245, + "eval_samples_per_second": 59.437, + "eval_steps_per_second": 3.745, + "step": 25100 + }, + { + "epoch": 0.93, + "learning_rate": 9.066091419645182e-06, + "loss": 1.8084, + "step": 25110 + }, + { + "epoch": 0.93, + "learning_rate": 9.065719492691636e-06, + "loss": 1.8064, + "step": 25120 + }, + { + "epoch": 0.93, + "learning_rate": 9.06534756573809e-06, + "loss": 1.8533, + "step": 25130 + }, + { + "epoch": 0.94, + "learning_rate": 9.064975638784543e-06, + "loss": 1.8937, + "step": 25140 + }, + { + "epoch": 0.94, + "learning_rate": 9.064603711830998e-06, + "loss": 1.918, + "step": 25150 + }, + { + "epoch": 0.94, + "learning_rate": 9.064231784877451e-06, + "loss": 1.8869, + "step": 25160 + }, + { + "epoch": 0.94, + "learning_rate": 9.063859857923905e-06, + "loss": 1.9003, + "step": 25170 + }, + { + "epoch": 0.94, + "learning_rate": 9.063487930970358e-06, + "loss": 1.9821, + "step": 25180 + }, + { + "epoch": 0.94, + "learning_rate": 9.063116004016812e-06, + "loss": 1.8571, + "step": 25190 + }, + { + "epoch": 0.94, + "learning_rate": 9.062744077063265e-06, + "loss": 1.8274, + "step": 25200 + }, + { + "epoch": 0.94, + "eval_loss": 1.7753689289093018, + "eval_runtime": 16.801, + "eval_samples_per_second": 59.52, + "eval_steps_per_second": 3.75, + "step": 25200 + }, + { + "epoch": 0.94, + "learning_rate": 9.06237215010972e-06, + "loss": 1.7482, + "step": 25210 + }, + { + "epoch": 0.94, + "learning_rate": 9.062000223156174e-06, + "loss": 1.873, + "step": 25220 + }, + { + "epoch": 0.94, + "learning_rate": 9.061628296202627e-06, + "loss": 1.8493, + "step": 25230 + }, + { + "epoch": 0.94, + "learning_rate": 9.06125636924908e-06, + "loss": 1.8032, + "step": 25240 + }, + { + "epoch": 0.94, + "learning_rate": 9.060884442295534e-06, + "loss": 1.8471, + "step": 25250 + }, + { + "epoch": 0.94, + "learning_rate": 9.060512515341988e-06, + "loss": 1.8025, + "step": 25260 + }, + { + "epoch": 0.94, + "learning_rate": 9.060140588388441e-06, + "loss": 2.0905, + "step": 25270 + }, + { + "epoch": 0.94, + "learning_rate": 9.059768661434894e-06, + "loss": 1.8599, + "step": 25280 + }, + { + "epoch": 0.94, + "learning_rate": 9.059396734481348e-06, + "loss": 1.7936, + "step": 25290 + }, + { + "epoch": 0.94, + "learning_rate": 9.059024807527801e-06, + "loss": 1.8449, + "step": 25300 + }, + { + "epoch": 0.94, + "eval_loss": 1.775295615196228, + "eval_runtime": 16.7942, + "eval_samples_per_second": 59.544, + "eval_steps_per_second": 3.751, + "step": 25300 + }, + { + "epoch": 0.94, + "learning_rate": 9.058652880574257e-06, + "loss": 1.7116, + "step": 25310 + }, + { + "epoch": 0.94, + "learning_rate": 9.05828095362071e-06, + "loss": 1.8589, + "step": 25320 + }, + { + "epoch": 0.94, + "learning_rate": 9.057909026667163e-06, + "loss": 1.8367, + "step": 25330 + }, + { + "epoch": 0.94, + "learning_rate": 9.057537099713617e-06, + "loss": 1.8308, + "step": 25340 + }, + { + "epoch": 0.94, + "learning_rate": 9.05716517276007e-06, + "loss": 1.8911, + "step": 25350 + }, + { + "epoch": 0.94, + "learning_rate": 9.056793245806524e-06, + "loss": 1.9146, + "step": 25360 + }, + { + "epoch": 0.94, + "learning_rate": 9.056421318852979e-06, + "loss": 1.8461, + "step": 25370 + }, + { + "epoch": 0.94, + "learning_rate": 9.056049391899432e-06, + "loss": 1.8973, + "step": 25380 + }, + { + "epoch": 0.94, + "learning_rate": 9.055677464945886e-06, + "loss": 1.854, + "step": 25390 + }, + { + "epoch": 0.94, + "learning_rate": 9.05530553799234e-06, + "loss": 1.9146, + "step": 25400 + }, + { + "epoch": 0.94, + "eval_loss": 1.7740662097930908, + "eval_runtime": 16.8081, + "eval_samples_per_second": 59.495, + "eval_steps_per_second": 3.748, + "step": 25400 + }, + { + "epoch": 0.95, + "learning_rate": 9.054933611038793e-06, + "loss": 1.8199, + "step": 25410 + }, + { + "epoch": 0.95, + "learning_rate": 9.054561684085246e-06, + "loss": 1.9511, + "step": 25420 + }, + { + "epoch": 0.95, + "learning_rate": 9.0541897571317e-06, + "loss": 1.8451, + "step": 25430 + }, + { + "epoch": 0.95, + "learning_rate": 9.053817830178155e-06, + "loss": 1.8334, + "step": 25440 + }, + { + "epoch": 0.95, + "learning_rate": 9.053445903224607e-06, + "loss": 1.8184, + "step": 25450 + }, + { + "epoch": 0.95, + "learning_rate": 9.05307397627106e-06, + "loss": 1.7795, + "step": 25460 + }, + { + "epoch": 0.95, + "learning_rate": 9.052702049317514e-06, + "loss": 1.8722, + "step": 25470 + }, + { + "epoch": 0.95, + "learning_rate": 9.052330122363969e-06, + "loss": 1.8339, + "step": 25480 + }, + { + "epoch": 0.95, + "learning_rate": 9.051958195410422e-06, + "loss": 1.8578, + "step": 25490 + }, + { + "epoch": 0.95, + "learning_rate": 9.051586268456876e-06, + "loss": 1.8986, + "step": 25500 + }, + { + "epoch": 0.95, + "eval_loss": 1.773504614830017, + "eval_runtime": 16.7945, + "eval_samples_per_second": 59.543, + "eval_steps_per_second": 3.751, + "step": 25500 + }, + { + "epoch": 0.95, + "learning_rate": 9.051214341503329e-06, + "loss": 1.8052, + "step": 25510 + }, + { + "epoch": 0.95, + "learning_rate": 9.050842414549783e-06, + "loss": 1.9679, + "step": 25520 + }, + { + "epoch": 0.95, + "learning_rate": 9.050470487596236e-06, + "loss": 1.8798, + "step": 25530 + }, + { + "epoch": 0.95, + "learning_rate": 9.050098560642691e-06, + "loss": 1.8503, + "step": 25540 + }, + { + "epoch": 0.95, + "learning_rate": 9.049726633689145e-06, + "loss": 1.8792, + "step": 25550 + }, + { + "epoch": 0.95, + "learning_rate": 9.049354706735598e-06, + "loss": 1.9491, + "step": 25560 + }, + { + "epoch": 0.95, + "learning_rate": 9.048982779782052e-06, + "loss": 1.8533, + "step": 25570 + }, + { + "epoch": 0.95, + "learning_rate": 9.048610852828505e-06, + "loss": 1.9118, + "step": 25580 + }, + { + "epoch": 0.95, + "learning_rate": 9.048238925874958e-06, + "loss": 1.8387, + "step": 25590 + }, + { + "epoch": 0.95, + "learning_rate": 9.047866998921414e-06, + "loss": 1.7705, + "step": 25600 + }, + { + "epoch": 0.95, + "eval_loss": 1.773317575454712, + "eval_runtime": 16.813, + "eval_samples_per_second": 59.478, + "eval_steps_per_second": 3.747, + "step": 25600 + }, + { + "epoch": 0.95, + "learning_rate": 9.047495071967867e-06, + "loss": 1.8177, + "step": 25610 + }, + { + "epoch": 0.95, + "learning_rate": 9.04712314501432e-06, + "loss": 1.8866, + "step": 25620 + }, + { + "epoch": 0.95, + "learning_rate": 9.046751218060772e-06, + "loss": 1.9098, + "step": 25630 + }, + { + "epoch": 0.95, + "learning_rate": 9.046379291107227e-06, + "loss": 1.9631, + "step": 25640 + }, + { + "epoch": 0.95, + "learning_rate": 9.046007364153681e-06, + "loss": 1.8936, + "step": 25650 + }, + { + "epoch": 0.95, + "learning_rate": 9.045635437200134e-06, + "loss": 1.903, + "step": 25660 + }, + { + "epoch": 0.95, + "learning_rate": 9.045263510246588e-06, + "loss": 1.7844, + "step": 25670 + }, + { + "epoch": 0.96, + "learning_rate": 9.044891583293041e-06, + "loss": 1.8658, + "step": 25680 + }, + { + "epoch": 0.96, + "learning_rate": 9.044519656339495e-06, + "loss": 1.828, + "step": 25690 + }, + { + "epoch": 0.96, + "learning_rate": 9.04414772938595e-06, + "loss": 1.9336, + "step": 25700 + }, + { + "epoch": 0.96, + "eval_loss": 1.7741202116012573, + "eval_runtime": 16.8387, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 25700 + }, + { + "epoch": 0.96, + "learning_rate": 9.043775802432403e-06, + "loss": 2.037, + "step": 25710 + }, + { + "epoch": 0.96, + "learning_rate": 9.043403875478857e-06, + "loss": 1.957, + "step": 25720 + }, + { + "epoch": 0.96, + "learning_rate": 9.04303194852531e-06, + "loss": 1.9246, + "step": 25730 + }, + { + "epoch": 0.96, + "learning_rate": 9.042660021571764e-06, + "loss": 1.7801, + "step": 25740 + }, + { + "epoch": 0.96, + "learning_rate": 9.042288094618217e-06, + "loss": 1.8858, + "step": 25750 + }, + { + "epoch": 0.96, + "learning_rate": 9.041916167664672e-06, + "loss": 1.8668, + "step": 25760 + }, + { + "epoch": 0.96, + "learning_rate": 9.041544240711126e-06, + "loss": 1.8348, + "step": 25770 + }, + { + "epoch": 0.96, + "learning_rate": 9.04117231375758e-06, + "loss": 1.8238, + "step": 25780 + }, + { + "epoch": 0.96, + "learning_rate": 9.040800386804033e-06, + "loss": 1.9945, + "step": 25790 + }, + { + "epoch": 0.96, + "learning_rate": 9.040428459850486e-06, + "loss": 1.8601, + "step": 25800 + }, + { + "epoch": 0.96, + "eval_loss": 1.7722036838531494, + "eval_runtime": 16.8132, + "eval_samples_per_second": 59.477, + "eval_steps_per_second": 3.747, + "step": 25800 + }, + { + "epoch": 0.96, + "learning_rate": 9.04005653289694e-06, + "loss": 1.8841, + "step": 25810 + }, + { + "epoch": 0.96, + "learning_rate": 9.039684605943393e-06, + "loss": 1.805, + "step": 25820 + }, + { + "epoch": 0.96, + "learning_rate": 9.039312678989847e-06, + "loss": 1.7856, + "step": 25830 + }, + { + "epoch": 0.96, + "learning_rate": 9.0389407520363e-06, + "loss": 1.8915, + "step": 25840 + }, + { + "epoch": 0.96, + "learning_rate": 9.038568825082753e-06, + "loss": 1.9093, + "step": 25850 + }, + { + "epoch": 0.96, + "learning_rate": 9.038196898129209e-06, + "loss": 1.8144, + "step": 25860 + }, + { + "epoch": 0.96, + "learning_rate": 9.037824971175662e-06, + "loss": 1.9019, + "step": 25870 + }, + { + "epoch": 0.96, + "learning_rate": 9.037453044222116e-06, + "loss": 1.809, + "step": 25880 + }, + { + "epoch": 0.96, + "learning_rate": 9.037081117268569e-06, + "loss": 1.924, + "step": 25890 + }, + { + "epoch": 0.96, + "learning_rate": 9.036709190315022e-06, + "loss": 1.8773, + "step": 25900 + }, + { + "epoch": 0.96, + "eval_loss": 1.7720520496368408, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 25900 + }, + { + "epoch": 0.96, + "learning_rate": 9.036337263361476e-06, + "loss": 1.968, + "step": 25910 + }, + { + "epoch": 0.96, + "learning_rate": 9.035965336407931e-06, + "loss": 1.8753, + "step": 25920 + }, + { + "epoch": 0.96, + "learning_rate": 9.035593409454385e-06, + "loss": 2.0111, + "step": 25930 + }, + { + "epoch": 0.96, + "learning_rate": 9.035221482500838e-06, + "loss": 1.9047, + "step": 25940 + }, + { + "epoch": 0.97, + "learning_rate": 9.034849555547291e-06, + "loss": 1.8165, + "step": 25950 + }, + { + "epoch": 0.97, + "learning_rate": 9.034477628593745e-06, + "loss": 1.8768, + "step": 25960 + }, + { + "epoch": 0.97, + "learning_rate": 9.034105701640198e-06, + "loss": 1.8686, + "step": 25970 + }, + { + "epoch": 0.97, + "learning_rate": 9.033733774686654e-06, + "loss": 1.9181, + "step": 25980 + }, + { + "epoch": 0.97, + "learning_rate": 9.033361847733107e-06, + "loss": 1.7372, + "step": 25990 + }, + { + "epoch": 0.97, + "learning_rate": 9.03298992077956e-06, + "loss": 1.8276, + "step": 26000 + }, + { + "epoch": 0.97, + "eval_loss": 1.7719711065292358, + "eval_runtime": 16.8187, + "eval_samples_per_second": 59.458, + "eval_steps_per_second": 3.746, + "step": 26000 + }, + { + "epoch": 0.97, + "learning_rate": 9.032617993826012e-06, + "loss": 1.7735, + "step": 26010 + }, + { + "epoch": 0.97, + "learning_rate": 9.032246066872467e-06, + "loss": 1.7193, + "step": 26020 + }, + { + "epoch": 0.97, + "learning_rate": 9.03187413991892e-06, + "loss": 1.9295, + "step": 26030 + }, + { + "epoch": 0.97, + "learning_rate": 9.031502212965374e-06, + "loss": 1.7427, + "step": 26040 + }, + { + "epoch": 0.97, + "learning_rate": 9.031130286011828e-06, + "loss": 1.7461, + "step": 26050 + }, + { + "epoch": 0.97, + "learning_rate": 9.030758359058281e-06, + "loss": 1.8096, + "step": 26060 + }, + { + "epoch": 0.97, + "learning_rate": 9.030386432104735e-06, + "loss": 1.8247, + "step": 26070 + }, + { + "epoch": 0.97, + "learning_rate": 9.030014505151188e-06, + "loss": 1.8936, + "step": 26080 + }, + { + "epoch": 0.97, + "learning_rate": 9.029642578197643e-06, + "loss": 1.9308, + "step": 26090 + }, + { + "epoch": 0.97, + "learning_rate": 9.029270651244097e-06, + "loss": 1.8545, + "step": 26100 + }, + { + "epoch": 0.97, + "eval_loss": 1.7725578546524048, + "eval_runtime": 16.8146, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 26100 + }, + { + "epoch": 0.97, + "learning_rate": 9.02889872429055e-06, + "loss": 1.9473, + "step": 26110 + }, + { + "epoch": 0.97, + "learning_rate": 9.028526797337004e-06, + "loss": 1.747, + "step": 26120 + }, + { + "epoch": 0.97, + "learning_rate": 9.028154870383457e-06, + "loss": 1.7637, + "step": 26130 + }, + { + "epoch": 0.97, + "learning_rate": 9.02778294342991e-06, + "loss": 1.8059, + "step": 26140 + }, + { + "epoch": 0.97, + "learning_rate": 9.027411016476366e-06, + "loss": 1.7974, + "step": 26150 + }, + { + "epoch": 0.97, + "learning_rate": 9.02703908952282e-06, + "loss": 1.8416, + "step": 26160 + }, + { + "epoch": 0.97, + "learning_rate": 9.026667162569273e-06, + "loss": 1.7851, + "step": 26170 + }, + { + "epoch": 0.97, + "learning_rate": 9.026295235615726e-06, + "loss": 1.911, + "step": 26180 + }, + { + "epoch": 0.97, + "learning_rate": 9.02592330866218e-06, + "loss": 1.847, + "step": 26190 + }, + { + "epoch": 0.97, + "learning_rate": 9.025551381708633e-06, + "loss": 1.8815, + "step": 26200 + }, + { + "epoch": 0.97, + "eval_loss": 1.7724350690841675, + "eval_runtime": 16.8171, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 26200 + }, + { + "epoch": 0.97, + "learning_rate": 9.025179454755086e-06, + "loss": 1.8995, + "step": 26210 + }, + { + "epoch": 0.98, + "learning_rate": 9.02480752780154e-06, + "loss": 1.9254, + "step": 26220 + }, + { + "epoch": 0.98, + "learning_rate": 9.024435600847993e-06, + "loss": 1.7781, + "step": 26230 + }, + { + "epoch": 0.98, + "learning_rate": 9.024063673894447e-06, + "loss": 1.9445, + "step": 26240 + }, + { + "epoch": 0.98, + "learning_rate": 9.023691746940902e-06, + "loss": 1.8855, + "step": 26250 + }, + { + "epoch": 0.98, + "learning_rate": 9.023319819987355e-06, + "loss": 1.8362, + "step": 26260 + }, + { + "epoch": 0.98, + "learning_rate": 9.022947893033809e-06, + "loss": 1.8782, + "step": 26270 + }, + { + "epoch": 0.98, + "learning_rate": 9.022575966080262e-06, + "loss": 1.8377, + "step": 26280 + }, + { + "epoch": 0.98, + "learning_rate": 9.022204039126716e-06, + "loss": 1.8624, + "step": 26290 + }, + { + "epoch": 0.98, + "learning_rate": 9.02183211217317e-06, + "loss": 1.9829, + "step": 26300 + }, + { + "epoch": 0.98, + "eval_loss": 1.771094799041748, + "eval_runtime": 16.8188, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 26300 + }, + { + "epoch": 0.98, + "learning_rate": 9.021460185219624e-06, + "loss": 1.9897, + "step": 26310 + }, + { + "epoch": 0.98, + "learning_rate": 9.021088258266078e-06, + "loss": 1.8244, + "step": 26320 + }, + { + "epoch": 0.98, + "learning_rate": 9.020716331312531e-06, + "loss": 1.9329, + "step": 26330 + }, + { + "epoch": 0.98, + "learning_rate": 9.020344404358985e-06, + "loss": 1.8537, + "step": 26340 + }, + { + "epoch": 0.98, + "learning_rate": 9.019972477405438e-06, + "loss": 1.7168, + "step": 26350 + }, + { + "epoch": 0.98, + "learning_rate": 9.019600550451892e-06, + "loss": 1.9796, + "step": 26360 + }, + { + "epoch": 0.98, + "learning_rate": 9.019228623498347e-06, + "loss": 1.7529, + "step": 26370 + }, + { + "epoch": 0.98, + "learning_rate": 9.0188566965448e-06, + "loss": 1.9422, + "step": 26380 + }, + { + "epoch": 0.98, + "learning_rate": 9.018484769591252e-06, + "loss": 1.9935, + "step": 26390 + }, + { + "epoch": 0.98, + "learning_rate": 9.018112842637706e-06, + "loss": 1.8573, + "step": 26400 + }, + { + "epoch": 0.98, + "eval_loss": 1.7701222896575928, + "eval_runtime": 16.8163, + "eval_samples_per_second": 59.466, + "eval_steps_per_second": 3.746, + "step": 26400 + }, + { + "epoch": 0.98, + "learning_rate": 9.01774091568416e-06, + "loss": 1.89, + "step": 26410 + }, + { + "epoch": 0.98, + "learning_rate": 9.017368988730614e-06, + "loss": 1.7158, + "step": 26420 + }, + { + "epoch": 0.98, + "learning_rate": 9.016997061777068e-06, + "loss": 1.8606, + "step": 26430 + }, + { + "epoch": 0.98, + "learning_rate": 9.016625134823521e-06, + "loss": 1.8383, + "step": 26440 + }, + { + "epoch": 0.98, + "learning_rate": 9.016253207869975e-06, + "loss": 1.8441, + "step": 26450 + }, + { + "epoch": 0.98, + "learning_rate": 9.015881280916428e-06, + "loss": 1.8455, + "step": 26460 + }, + { + "epoch": 0.98, + "learning_rate": 9.015509353962883e-06, + "loss": 1.9654, + "step": 26470 + }, + { + "epoch": 0.98, + "learning_rate": 9.015137427009337e-06, + "loss": 1.7682, + "step": 26480 + }, + { + "epoch": 0.99, + "learning_rate": 9.01476550005579e-06, + "loss": 1.7933, + "step": 26490 + }, + { + "epoch": 0.99, + "learning_rate": 9.014393573102244e-06, + "loss": 1.8134, + "step": 26500 + }, + { + "epoch": 0.99, + "eval_loss": 1.7708362340927124, + "eval_runtime": 16.8212, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 26500 + }, + { + "epoch": 0.99, + "learning_rate": 9.014021646148697e-06, + "loss": 1.9065, + "step": 26510 + }, + { + "epoch": 0.99, + "learning_rate": 9.01364971919515e-06, + "loss": 1.854, + "step": 26520 + }, + { + "epoch": 0.99, + "learning_rate": 9.013277792241606e-06, + "loss": 1.8654, + "step": 26530 + }, + { + "epoch": 0.99, + "learning_rate": 9.012905865288059e-06, + "loss": 1.9049, + "step": 26540 + }, + { + "epoch": 0.99, + "learning_rate": 9.012533938334513e-06, + "loss": 1.7157, + "step": 26550 + }, + { + "epoch": 0.99, + "learning_rate": 9.012162011380966e-06, + "loss": 1.8494, + "step": 26560 + }, + { + "epoch": 0.99, + "learning_rate": 9.01179008442742e-06, + "loss": 1.9078, + "step": 26570 + }, + { + "epoch": 0.99, + "learning_rate": 9.011418157473873e-06, + "loss": 2.0033, + "step": 26580 + }, + { + "epoch": 0.99, + "learning_rate": 9.011046230520326e-06, + "loss": 1.8123, + "step": 26590 + }, + { + "epoch": 0.99, + "learning_rate": 9.01067430356678e-06, + "loss": 1.9738, + "step": 26600 + }, + { + "epoch": 0.99, + "eval_loss": 1.7711095809936523, + "eval_runtime": 16.8083, + "eval_samples_per_second": 59.494, + "eval_steps_per_second": 3.748, + "step": 26600 + }, + { + "epoch": 0.99, + "learning_rate": 9.010302376613233e-06, + "loss": 1.8486, + "step": 26610 + }, + { + "epoch": 0.99, + "learning_rate": 9.009930449659687e-06, + "loss": 1.8801, + "step": 26620 + }, + { + "epoch": 0.99, + "learning_rate": 9.00955852270614e-06, + "loss": 1.879, + "step": 26630 + }, + { + "epoch": 0.99, + "learning_rate": 9.009186595752595e-06, + "loss": 1.7235, + "step": 26640 + }, + { + "epoch": 0.99, + "learning_rate": 9.008814668799049e-06, + "loss": 1.9812, + "step": 26650 + }, + { + "epoch": 0.99, + "learning_rate": 9.008442741845502e-06, + "loss": 1.7711, + "step": 26660 + }, + { + "epoch": 0.99, + "learning_rate": 9.008070814891956e-06, + "loss": 1.7433, + "step": 26670 + }, + { + "epoch": 0.99, + "learning_rate": 9.00769888793841e-06, + "loss": 1.8106, + "step": 26680 + }, + { + "epoch": 0.99, + "learning_rate": 9.007326960984863e-06, + "loss": 1.9888, + "step": 26690 + }, + { + "epoch": 0.99, + "learning_rate": 9.006955034031318e-06, + "loss": 1.7793, + "step": 26700 + }, + { + "epoch": 0.99, + "eval_loss": 1.7701685428619385, + "eval_runtime": 16.8091, + "eval_samples_per_second": 59.491, + "eval_steps_per_second": 3.748, + "step": 26700 + }, + { + "epoch": 0.99, + "learning_rate": 9.006583107077771e-06, + "loss": 1.9027, + "step": 26710 + }, + { + "epoch": 0.99, + "learning_rate": 9.006211180124225e-06, + "loss": 1.7072, + "step": 26720 + }, + { + "epoch": 0.99, + "learning_rate": 9.005839253170678e-06, + "loss": 1.7722, + "step": 26730 + }, + { + "epoch": 0.99, + "learning_rate": 9.005467326217132e-06, + "loss": 1.8658, + "step": 26740 + }, + { + "epoch": 0.99, + "learning_rate": 9.005095399263585e-06, + "loss": 1.9324, + "step": 26750 + }, + { + "epoch": 1.0, + "learning_rate": 9.004723472310039e-06, + "loss": 1.8959, + "step": 26760 + }, + { + "epoch": 1.0, + "learning_rate": 9.004351545356492e-06, + "loss": 1.9813, + "step": 26770 + }, + { + "epoch": 1.0, + "learning_rate": 9.003979618402946e-06, + "loss": 1.836, + "step": 26780 + }, + { + "epoch": 1.0, + "learning_rate": 9.003607691449399e-06, + "loss": 1.8955, + "step": 26790 + }, + { + "epoch": 1.0, + "learning_rate": 9.003235764495854e-06, + "loss": 1.8872, + "step": 26800 + }, + { + "epoch": 1.0, + "eval_loss": 1.769727349281311, + "eval_runtime": 16.8143, + "eval_samples_per_second": 59.473, + "eval_steps_per_second": 3.747, + "step": 26800 + }, + { + "epoch": 1.0, + "learning_rate": 9.002863837542308e-06, + "loss": 1.82, + "step": 26810 + }, + { + "epoch": 1.0, + "learning_rate": 9.002491910588761e-06, + "loss": 1.7344, + "step": 26820 + }, + { + "epoch": 1.0, + "learning_rate": 9.002119983635214e-06, + "loss": 1.8685, + "step": 26830 + }, + { + "epoch": 1.0, + "learning_rate": 9.001748056681668e-06, + "loss": 1.9164, + "step": 26840 + }, + { + "epoch": 1.0, + "learning_rate": 9.001376129728121e-06, + "loss": 1.8758, + "step": 26850 + }, + { + "epoch": 1.0, + "learning_rate": 9.001004202774577e-06, + "loss": 1.8523, + "step": 26860 + }, + { + "epoch": 1.0, + "learning_rate": 9.00063227582103e-06, + "loss": 1.8891, + "step": 26870 + }, + { + "epoch": 1.0, + "learning_rate": 9.000260348867483e-06, + "loss": 1.8398, + "step": 26880 + }, + { + "epoch": 1.0, + "learning_rate": 8.999888421913937e-06, + "loss": 1.9021, + "step": 26890 + }, + { + "epoch": 1.0, + "learning_rate": 8.99951649496039e-06, + "loss": 1.8312, + "step": 26900 + }, + { + "epoch": 1.0, + "eval_loss": 1.7690798044204712, + "eval_runtime": 16.7996, + "eval_samples_per_second": 59.525, + "eval_steps_per_second": 3.75, + "step": 26900 + }, + { + "epoch": 1.0, + "learning_rate": 8.999144568006844e-06, + "loss": 1.8793, + "step": 26910 + }, + { + "epoch": 1.0, + "learning_rate": 8.998772641053299e-06, + "loss": 1.7869, + "step": 26920 + }, + { + "epoch": 1.0, + "learning_rate": 8.998400714099752e-06, + "loss": 1.7918, + "step": 26930 + }, + { + "epoch": 1.0, + "learning_rate": 8.998028787146206e-06, + "loss": 1.7454, + "step": 26940 + }, + { + "epoch": 1.0, + "learning_rate": 8.997656860192658e-06, + "loss": 1.7882, + "step": 26950 + }, + { + "epoch": 1.0, + "learning_rate": 8.997284933239113e-06, + "loss": 1.9217, + "step": 26960 + }, + { + "epoch": 1.0, + "learning_rate": 8.996913006285566e-06, + "loss": 1.9427, + "step": 26970 + }, + { + "epoch": 1.0, + "learning_rate": 8.99654107933202e-06, + "loss": 1.8218, + "step": 26980 + }, + { + "epoch": 1.0, + "learning_rate": 8.996169152378473e-06, + "loss": 1.7848, + "step": 26990 + }, + { + "epoch": 1.0, + "learning_rate": 8.995797225424927e-06, + "loss": 1.8011, + "step": 27000 + }, + { + "epoch": 1.0, + "eval_loss": 1.7691428661346436, + "eval_runtime": 16.8255, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 27000 + }, + { + "epoch": 1.0, + "learning_rate": 8.99542529847138e-06, + "loss": 1.7826, + "step": 27010 + }, + { + "epoch": 1.0, + "learning_rate": 8.995053371517835e-06, + "loss": 1.8554, + "step": 27020 + }, + { + "epoch": 1.01, + "learning_rate": 8.994681444564289e-06, + "loss": 1.7793, + "step": 27030 + }, + { + "epoch": 1.01, + "learning_rate": 8.994309517610742e-06, + "loss": 1.7982, + "step": 27040 + }, + { + "epoch": 1.01, + "learning_rate": 8.993937590657196e-06, + "loss": 1.9549, + "step": 27050 + }, + { + "epoch": 1.01, + "learning_rate": 8.993565663703649e-06, + "loss": 1.9408, + "step": 27060 + }, + { + "epoch": 1.01, + "learning_rate": 8.993193736750103e-06, + "loss": 1.7467, + "step": 27070 + }, + { + "epoch": 1.01, + "learning_rate": 8.992821809796558e-06, + "loss": 1.8128, + "step": 27080 + }, + { + "epoch": 1.01, + "learning_rate": 8.992449882843011e-06, + "loss": 1.8625, + "step": 27090 + }, + { + "epoch": 1.01, + "learning_rate": 8.992077955889465e-06, + "loss": 1.776, + "step": 27100 + }, + { + "epoch": 1.01, + "eval_loss": 1.7694528102874756, + "eval_runtime": 16.8084, + "eval_samples_per_second": 59.494, + "eval_steps_per_second": 3.748, + "step": 27100 + }, + { + "epoch": 1.01, + "learning_rate": 8.991706028935918e-06, + "loss": 1.7496, + "step": 27110 + }, + { + "epoch": 1.01, + "learning_rate": 8.991334101982372e-06, + "loss": 1.7616, + "step": 27120 + }, + { + "epoch": 1.01, + "learning_rate": 8.990962175028825e-06, + "loss": 1.7448, + "step": 27130 + }, + { + "epoch": 1.01, + "learning_rate": 8.990590248075279e-06, + "loss": 1.8649, + "step": 27140 + }, + { + "epoch": 1.01, + "learning_rate": 8.990218321121732e-06, + "loss": 1.8103, + "step": 27150 + }, + { + "epoch": 1.01, + "learning_rate": 8.989846394168185e-06, + "loss": 1.7919, + "step": 27160 + }, + { + "epoch": 1.01, + "learning_rate": 8.989474467214639e-06, + "loss": 1.9302, + "step": 27170 + }, + { + "epoch": 1.01, + "learning_rate": 8.989102540261094e-06, + "loss": 1.8264, + "step": 27180 + }, + { + "epoch": 1.01, + "learning_rate": 8.988730613307547e-06, + "loss": 1.8421, + "step": 27190 + }, + { + "epoch": 1.01, + "learning_rate": 8.988358686354001e-06, + "loss": 1.9048, + "step": 27200 + }, + { + "epoch": 1.01, + "eval_loss": 1.768679141998291, + "eval_runtime": 16.7965, + "eval_samples_per_second": 59.536, + "eval_steps_per_second": 3.751, + "step": 27200 + }, + { + "epoch": 1.01, + "learning_rate": 8.987986759400454e-06, + "loss": 1.8204, + "step": 27210 + }, + { + "epoch": 1.01, + "learning_rate": 8.987614832446908e-06, + "loss": 1.9372, + "step": 27220 + }, + { + "epoch": 1.01, + "learning_rate": 8.987242905493361e-06, + "loss": 1.8494, + "step": 27230 + }, + { + "epoch": 1.01, + "learning_rate": 8.986870978539815e-06, + "loss": 1.8598, + "step": 27240 + }, + { + "epoch": 1.01, + "learning_rate": 8.98649905158627e-06, + "loss": 1.8232, + "step": 27250 + }, + { + "epoch": 1.01, + "learning_rate": 8.986127124632723e-06, + "loss": 1.7599, + "step": 27260 + }, + { + "epoch": 1.01, + "learning_rate": 8.985755197679177e-06, + "loss": 1.8195, + "step": 27270 + }, + { + "epoch": 1.01, + "learning_rate": 8.98538327072563e-06, + "loss": 1.7262, + "step": 27280 + }, + { + "epoch": 1.01, + "learning_rate": 8.985011343772084e-06, + "loss": 1.7544, + "step": 27290 + }, + { + "epoch": 1.02, + "learning_rate": 8.984639416818537e-06, + "loss": 1.746, + "step": 27300 + }, + { + "epoch": 1.02, + "eval_loss": 1.7688679695129395, + "eval_runtime": 16.8239, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 27300 + }, + { + "epoch": 1.02, + "learning_rate": 8.984267489864992e-06, + "loss": 1.8193, + "step": 27310 + }, + { + "epoch": 1.02, + "learning_rate": 8.983895562911444e-06, + "loss": 1.9165, + "step": 27320 + }, + { + "epoch": 1.02, + "learning_rate": 8.983523635957898e-06, + "loss": 1.7944, + "step": 27330 + }, + { + "epoch": 1.02, + "learning_rate": 8.983151709004351e-06, + "loss": 1.8506, + "step": 27340 + }, + { + "epoch": 1.02, + "learning_rate": 8.982779782050806e-06, + "loss": 1.9209, + "step": 27350 + }, + { + "epoch": 1.02, + "learning_rate": 8.98240785509726e-06, + "loss": 1.9508, + "step": 27360 + }, + { + "epoch": 1.02, + "learning_rate": 8.982035928143713e-06, + "loss": 1.7752, + "step": 27370 + }, + { + "epoch": 1.02, + "learning_rate": 8.981664001190167e-06, + "loss": 1.7315, + "step": 27380 + }, + { + "epoch": 1.02, + "learning_rate": 8.98129207423662e-06, + "loss": 1.9147, + "step": 27390 + }, + { + "epoch": 1.02, + "learning_rate": 8.980920147283074e-06, + "loss": 1.7967, + "step": 27400 + }, + { + "epoch": 1.02, + "eval_loss": 1.768283724784851, + "eval_runtime": 16.8357, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 27400 + }, + { + "epoch": 1.02, + "learning_rate": 8.980548220329529e-06, + "loss": 1.8829, + "step": 27410 + }, + { + "epoch": 1.02, + "learning_rate": 8.980176293375982e-06, + "loss": 1.7979, + "step": 27420 + }, + { + "epoch": 1.02, + "learning_rate": 8.979804366422436e-06, + "loss": 1.7365, + "step": 27430 + }, + { + "epoch": 1.02, + "learning_rate": 8.979432439468889e-06, + "loss": 1.7456, + "step": 27440 + }, + { + "epoch": 1.02, + "learning_rate": 8.979060512515343e-06, + "loss": 1.7981, + "step": 27450 + }, + { + "epoch": 1.02, + "learning_rate": 8.978688585561796e-06, + "loss": 1.9308, + "step": 27460 + }, + { + "epoch": 1.02, + "learning_rate": 8.978316658608251e-06, + "loss": 1.7298, + "step": 27470 + }, + { + "epoch": 1.02, + "learning_rate": 8.977944731654705e-06, + "loss": 1.8386, + "step": 27480 + }, + { + "epoch": 1.02, + "learning_rate": 8.977572804701158e-06, + "loss": 1.9174, + "step": 27490 + }, + { + "epoch": 1.02, + "learning_rate": 8.977200877747612e-06, + "loss": 1.818, + "step": 27500 + }, + { + "epoch": 1.02, + "eval_loss": 1.7692852020263672, + "eval_runtime": 16.8059, + "eval_samples_per_second": 59.503, + "eval_steps_per_second": 3.749, + "step": 27500 + }, + { + "epoch": 1.02, + "learning_rate": 8.976828950794065e-06, + "loss": 1.7497, + "step": 27510 + }, + { + "epoch": 1.02, + "learning_rate": 8.976457023840518e-06, + "loss": 1.8661, + "step": 27520 + }, + { + "epoch": 1.02, + "learning_rate": 8.976085096886972e-06, + "loss": 1.8905, + "step": 27530 + }, + { + "epoch": 1.02, + "learning_rate": 8.975713169933425e-06, + "loss": 1.88, + "step": 27540 + }, + { + "epoch": 1.02, + "learning_rate": 8.975341242979879e-06, + "loss": 1.9122, + "step": 27550 + }, + { + "epoch": 1.03, + "learning_rate": 8.974969316026332e-06, + "loss": 1.8137, + "step": 27560 + }, + { + "epoch": 1.03, + "learning_rate": 8.974597389072787e-06, + "loss": 1.8794, + "step": 27570 + }, + { + "epoch": 1.03, + "learning_rate": 8.974225462119241e-06, + "loss": 1.8912, + "step": 27580 + }, + { + "epoch": 1.03, + "learning_rate": 8.973853535165694e-06, + "loss": 1.7629, + "step": 27590 + }, + { + "epoch": 1.03, + "learning_rate": 8.973481608212148e-06, + "loss": 1.8514, + "step": 27600 + }, + { + "epoch": 1.03, + "eval_loss": 1.768152117729187, + "eval_runtime": 16.8086, + "eval_samples_per_second": 59.494, + "eval_steps_per_second": 3.748, + "step": 27600 + }, + { + "epoch": 1.03, + "learning_rate": 8.973109681258601e-06, + "loss": 1.7548, + "step": 27610 + }, + { + "epoch": 1.03, + "learning_rate": 8.972737754305055e-06, + "loss": 1.8613, + "step": 27620 + }, + { + "epoch": 1.03, + "learning_rate": 8.97236582735151e-06, + "loss": 1.7866, + "step": 27630 + }, + { + "epoch": 1.03, + "learning_rate": 8.971993900397963e-06, + "loss": 1.8544, + "step": 27640 + }, + { + "epoch": 1.03, + "learning_rate": 8.971621973444417e-06, + "loss": 1.7171, + "step": 27650 + }, + { + "epoch": 1.03, + "learning_rate": 8.97125004649087e-06, + "loss": 1.8402, + "step": 27660 + }, + { + "epoch": 1.03, + "learning_rate": 8.970878119537324e-06, + "loss": 1.7951, + "step": 27670 + }, + { + "epoch": 1.03, + "learning_rate": 8.970506192583777e-06, + "loss": 1.8181, + "step": 27680 + }, + { + "epoch": 1.03, + "learning_rate": 8.970134265630232e-06, + "loss": 1.769, + "step": 27690 + }, + { + "epoch": 1.03, + "learning_rate": 8.969762338676684e-06, + "loss": 1.758, + "step": 27700 + }, + { + "epoch": 1.03, + "eval_loss": 1.767883539199829, + "eval_runtime": 16.8052, + "eval_samples_per_second": 59.506, + "eval_steps_per_second": 3.749, + "step": 27700 + }, + { + "epoch": 1.03, + "learning_rate": 8.969390411723138e-06, + "loss": 1.7894, + "step": 27710 + }, + { + "epoch": 1.03, + "learning_rate": 8.969018484769591e-06, + "loss": 1.7792, + "step": 27720 + }, + { + "epoch": 1.03, + "learning_rate": 8.968646557816046e-06, + "loss": 1.7363, + "step": 27730 + }, + { + "epoch": 1.03, + "learning_rate": 8.9682746308625e-06, + "loss": 1.8986, + "step": 27740 + }, + { + "epoch": 1.03, + "learning_rate": 8.967902703908953e-06, + "loss": 1.8655, + "step": 27750 + }, + { + "epoch": 1.03, + "learning_rate": 8.967530776955407e-06, + "loss": 1.8949, + "step": 27760 + }, + { + "epoch": 1.03, + "learning_rate": 8.96715885000186e-06, + "loss": 1.8183, + "step": 27770 + }, + { + "epoch": 1.03, + "learning_rate": 8.966786923048313e-06, + "loss": 1.7607, + "step": 27780 + }, + { + "epoch": 1.03, + "learning_rate": 8.966414996094767e-06, + "loss": 1.9244, + "step": 27790 + }, + { + "epoch": 1.03, + "learning_rate": 8.966043069141222e-06, + "loss": 1.7977, + "step": 27800 + }, + { + "epoch": 1.03, + "eval_loss": 1.7666078805923462, + "eval_runtime": 16.823, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 27800 + }, + { + "epoch": 1.03, + "learning_rate": 8.965671142187676e-06, + "loss": 1.828, + "step": 27810 + }, + { + "epoch": 1.03, + "learning_rate": 8.965299215234129e-06, + "loss": 1.7688, + "step": 27820 + }, + { + "epoch": 1.04, + "learning_rate": 8.964927288280582e-06, + "loss": 1.8043, + "step": 27830 + }, + { + "epoch": 1.04, + "learning_rate": 8.964555361327036e-06, + "loss": 1.8023, + "step": 27840 + }, + { + "epoch": 1.04, + "learning_rate": 8.96418343437349e-06, + "loss": 1.8399, + "step": 27850 + }, + { + "epoch": 1.04, + "learning_rate": 8.963811507419945e-06, + "loss": 1.9434, + "step": 27860 + }, + { + "epoch": 1.04, + "learning_rate": 8.963439580466398e-06, + "loss": 1.763, + "step": 27870 + }, + { + "epoch": 1.04, + "learning_rate": 8.963067653512851e-06, + "loss": 1.7887, + "step": 27880 + }, + { + "epoch": 1.04, + "learning_rate": 8.962695726559303e-06, + "loss": 1.9009, + "step": 27890 + }, + { + "epoch": 1.04, + "learning_rate": 8.962323799605758e-06, + "loss": 1.7331, + "step": 27900 + }, + { + "epoch": 1.04, + "eval_loss": 1.7676408290863037, + "eval_runtime": 16.8032, + "eval_samples_per_second": 59.512, + "eval_steps_per_second": 3.749, + "step": 27900 + }, + { + "epoch": 1.04, + "learning_rate": 8.961951872652212e-06, + "loss": 1.8459, + "step": 27910 + }, + { + "epoch": 1.04, + "learning_rate": 8.961579945698665e-06, + "loss": 1.8654, + "step": 27920 + }, + { + "epoch": 1.04, + "learning_rate": 8.961208018745119e-06, + "loss": 1.8423, + "step": 27930 + }, + { + "epoch": 1.04, + "learning_rate": 8.960836091791572e-06, + "loss": 1.7395, + "step": 27940 + }, + { + "epoch": 1.04, + "learning_rate": 8.960464164838026e-06, + "loss": 1.9034, + "step": 27950 + }, + { + "epoch": 1.04, + "learning_rate": 8.96009223788448e-06, + "loss": 1.709, + "step": 27960 + }, + { + "epoch": 1.04, + "learning_rate": 8.959720310930934e-06, + "loss": 1.8388, + "step": 27970 + }, + { + "epoch": 1.04, + "learning_rate": 8.959348383977388e-06, + "loss": 1.7848, + "step": 27980 + }, + { + "epoch": 1.04, + "learning_rate": 8.958976457023841e-06, + "loss": 1.7655, + "step": 27990 + }, + { + "epoch": 1.04, + "learning_rate": 8.958604530070295e-06, + "loss": 1.863, + "step": 28000 + }, + { + "epoch": 1.04, + "eval_loss": 1.7673993110656738, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 28000 + }, + { + "epoch": 1.04, + "learning_rate": 8.958232603116748e-06, + "loss": 1.8627, + "step": 28010 + }, + { + "epoch": 1.04, + "learning_rate": 8.957860676163203e-06, + "loss": 1.7604, + "step": 28020 + }, + { + "epoch": 1.04, + "learning_rate": 8.957488749209657e-06, + "loss": 1.6805, + "step": 28030 + }, + { + "epoch": 1.04, + "learning_rate": 8.95711682225611e-06, + "loss": 1.8761, + "step": 28040 + }, + { + "epoch": 1.04, + "learning_rate": 8.956744895302564e-06, + "loss": 1.7611, + "step": 28050 + }, + { + "epoch": 1.04, + "learning_rate": 8.956372968349017e-06, + "loss": 1.7776, + "step": 28060 + }, + { + "epoch": 1.04, + "learning_rate": 8.95600104139547e-06, + "loss": 1.8037, + "step": 28070 + }, + { + "epoch": 1.04, + "learning_rate": 8.955629114441924e-06, + "loss": 1.7945, + "step": 28080 + }, + { + "epoch": 1.04, + "learning_rate": 8.955257187488377e-06, + "loss": 1.8821, + "step": 28090 + }, + { + "epoch": 1.05, + "learning_rate": 8.954885260534831e-06, + "loss": 1.8452, + "step": 28100 + }, + { + "epoch": 1.05, + "eval_loss": 1.76593816280365, + "eval_runtime": 16.7763, + "eval_samples_per_second": 59.608, + "eval_steps_per_second": 3.755, + "step": 28100 + }, + { + "epoch": 1.05, + "learning_rate": 8.954513333581284e-06, + "loss": 1.6878, + "step": 28110 + }, + { + "epoch": 1.05, + "learning_rate": 8.95414140662774e-06, + "loss": 1.8588, + "step": 28120 + }, + { + "epoch": 1.05, + "learning_rate": 8.953769479674193e-06, + "loss": 1.7889, + "step": 28130 + }, + { + "epoch": 1.05, + "learning_rate": 8.953397552720646e-06, + "loss": 1.977, + "step": 28140 + }, + { + "epoch": 1.05, + "learning_rate": 8.9530256257671e-06, + "loss": 1.7206, + "step": 28150 + }, + { + "epoch": 1.05, + "learning_rate": 8.952653698813553e-06, + "loss": 1.8798, + "step": 28160 + }, + { + "epoch": 1.05, + "learning_rate": 8.952281771860007e-06, + "loss": 1.7148, + "step": 28170 + }, + { + "epoch": 1.05, + "learning_rate": 8.951909844906462e-06, + "loss": 1.7143, + "step": 28180 + }, + { + "epoch": 1.05, + "learning_rate": 8.951537917952915e-06, + "loss": 1.6562, + "step": 28190 + }, + { + "epoch": 1.05, + "learning_rate": 8.951165990999369e-06, + "loss": 1.8323, + "step": 28200 + }, + { + "epoch": 1.05, + "eval_loss": 1.765694260597229, + "eval_runtime": 16.8142, + "eval_samples_per_second": 59.474, + "eval_steps_per_second": 3.747, + "step": 28200 + }, + { + "epoch": 1.05, + "learning_rate": 8.950794064045822e-06, + "loss": 1.7679, + "step": 28210 + }, + { + "epoch": 1.05, + "learning_rate": 8.950422137092276e-06, + "loss": 1.7907, + "step": 28220 + }, + { + "epoch": 1.05, + "learning_rate": 8.95005021013873e-06, + "loss": 1.7805, + "step": 28230 + }, + { + "epoch": 1.05, + "learning_rate": 8.949678283185184e-06, + "loss": 1.9568, + "step": 28240 + }, + { + "epoch": 1.05, + "learning_rate": 8.949306356231638e-06, + "loss": 2.0243, + "step": 28250 + }, + { + "epoch": 1.05, + "learning_rate": 8.94893442927809e-06, + "loss": 1.9021, + "step": 28260 + }, + { + "epoch": 1.05, + "learning_rate": 8.948562502324543e-06, + "loss": 1.8133, + "step": 28270 + }, + { + "epoch": 1.05, + "learning_rate": 8.948190575370998e-06, + "loss": 1.7848, + "step": 28280 + }, + { + "epoch": 1.05, + "learning_rate": 8.947818648417452e-06, + "loss": 1.8714, + "step": 28290 + }, + { + "epoch": 1.05, + "learning_rate": 8.947446721463905e-06, + "loss": 1.7361, + "step": 28300 + }, + { + "epoch": 1.05, + "eval_loss": 1.7663342952728271, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 28300 + }, + { + "epoch": 1.05, + "learning_rate": 8.947074794510359e-06, + "loss": 1.8501, + "step": 28310 + }, + { + "epoch": 1.05, + "learning_rate": 8.946702867556812e-06, + "loss": 1.951, + "step": 28320 + }, + { + "epoch": 1.05, + "learning_rate": 8.946330940603266e-06, + "loss": 1.922, + "step": 28330 + }, + { + "epoch": 1.05, + "learning_rate": 8.945959013649719e-06, + "loss": 1.7231, + "step": 28340 + }, + { + "epoch": 1.05, + "learning_rate": 8.945587086696174e-06, + "loss": 1.816, + "step": 28350 + }, + { + "epoch": 1.05, + "learning_rate": 8.945215159742628e-06, + "loss": 1.7876, + "step": 28360 + }, + { + "epoch": 1.06, + "learning_rate": 8.944843232789081e-06, + "loss": 1.7991, + "step": 28370 + }, + { + "epoch": 1.06, + "learning_rate": 8.944471305835535e-06, + "loss": 1.8774, + "step": 28380 + }, + { + "epoch": 1.06, + "learning_rate": 8.944099378881988e-06, + "loss": 1.7747, + "step": 28390 + }, + { + "epoch": 1.06, + "learning_rate": 8.943727451928441e-06, + "loss": 1.8282, + "step": 28400 + }, + { + "epoch": 1.06, + "eval_loss": 1.7654792070388794, + "eval_runtime": 16.8105, + "eval_samples_per_second": 59.487, + "eval_steps_per_second": 3.748, + "step": 28400 + }, + { + "epoch": 1.06, + "learning_rate": 8.943355524974897e-06, + "loss": 1.8018, + "step": 28410 + }, + { + "epoch": 1.06, + "learning_rate": 8.94298359802135e-06, + "loss": 2.09, + "step": 28420 + }, + { + "epoch": 1.06, + "learning_rate": 8.942611671067804e-06, + "loss": 1.8718, + "step": 28430 + }, + { + "epoch": 1.06, + "learning_rate": 8.942239744114257e-06, + "loss": 1.8805, + "step": 28440 + }, + { + "epoch": 1.06, + "learning_rate": 8.94186781716071e-06, + "loss": 1.927, + "step": 28450 + }, + { + "epoch": 1.06, + "learning_rate": 8.941495890207164e-06, + "loss": 1.8248, + "step": 28460 + }, + { + "epoch": 1.06, + "learning_rate": 8.941123963253617e-06, + "loss": 1.767, + "step": 28470 + }, + { + "epoch": 1.06, + "learning_rate": 8.94075203630007e-06, + "loss": 1.8579, + "step": 28480 + }, + { + "epoch": 1.06, + "learning_rate": 8.940380109346524e-06, + "loss": 1.8183, + "step": 28490 + }, + { + "epoch": 1.06, + "learning_rate": 8.940008182392978e-06, + "loss": 1.9188, + "step": 28500 + }, + { + "epoch": 1.06, + "eval_loss": 1.7667958736419678, + "eval_runtime": 16.8107, + "eval_samples_per_second": 59.486, + "eval_steps_per_second": 3.748, + "step": 28500 + }, + { + "epoch": 1.06, + "learning_rate": 8.939636255439433e-06, + "loss": 1.834, + "step": 28510 + }, + { + "epoch": 1.06, + "learning_rate": 8.939264328485886e-06, + "loss": 1.9526, + "step": 28520 + }, + { + "epoch": 1.06, + "learning_rate": 8.93889240153234e-06, + "loss": 1.676, + "step": 28530 + }, + { + "epoch": 1.06, + "learning_rate": 8.938520474578793e-06, + "loss": 1.8924, + "step": 28540 + }, + { + "epoch": 1.06, + "learning_rate": 8.938148547625247e-06, + "loss": 1.8646, + "step": 28550 + }, + { + "epoch": 1.06, + "learning_rate": 8.9377766206717e-06, + "loss": 1.8824, + "step": 28560 + }, + { + "epoch": 1.06, + "learning_rate": 8.937404693718155e-06, + "loss": 1.6995, + "step": 28570 + }, + { + "epoch": 1.06, + "learning_rate": 8.937032766764609e-06, + "loss": 1.7075, + "step": 28580 + }, + { + "epoch": 1.06, + "learning_rate": 8.936660839811062e-06, + "loss": 1.8513, + "step": 28590 + }, + { + "epoch": 1.06, + "learning_rate": 8.936288912857516e-06, + "loss": 1.8446, + "step": 28600 + }, + { + "epoch": 1.06, + "eval_loss": 1.7645734548568726, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 28600 + }, + { + "epoch": 1.06, + "learning_rate": 8.93591698590397e-06, + "loss": 1.9052, + "step": 28610 + }, + { + "epoch": 1.06, + "learning_rate": 8.935545058950423e-06, + "loss": 1.8802, + "step": 28620 + }, + { + "epoch": 1.06, + "learning_rate": 8.935173131996878e-06, + "loss": 1.7631, + "step": 28630 + }, + { + "epoch": 1.07, + "learning_rate": 8.93480120504333e-06, + "loss": 1.7595, + "step": 28640 + }, + { + "epoch": 1.07, + "learning_rate": 8.934429278089783e-06, + "loss": 1.6524, + "step": 28650 + }, + { + "epoch": 1.07, + "learning_rate": 8.934057351136236e-06, + "loss": 1.8123, + "step": 28660 + }, + { + "epoch": 1.07, + "learning_rate": 8.933685424182692e-06, + "loss": 1.9084, + "step": 28670 + }, + { + "epoch": 1.07, + "learning_rate": 8.933313497229145e-06, + "loss": 1.7052, + "step": 28680 + }, + { + "epoch": 1.07, + "learning_rate": 8.932941570275599e-06, + "loss": 1.8712, + "step": 28690 + }, + { + "epoch": 1.07, + "learning_rate": 8.932569643322052e-06, + "loss": 1.7162, + "step": 28700 + }, + { + "epoch": 1.07, + "eval_loss": 1.7649643421173096, + "eval_runtime": 16.823, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 28700 + }, + { + "epoch": 1.07, + "learning_rate": 8.932197716368505e-06, + "loss": 1.8432, + "step": 28710 + }, + { + "epoch": 1.07, + "learning_rate": 8.931825789414959e-06, + "loss": 1.8314, + "step": 28720 + }, + { + "epoch": 1.07, + "learning_rate": 8.931453862461414e-06, + "loss": 1.7838, + "step": 28730 + }, + { + "epoch": 1.07, + "learning_rate": 8.931081935507868e-06, + "loss": 1.765, + "step": 28740 + }, + { + "epoch": 1.07, + "learning_rate": 8.930710008554321e-06, + "loss": 1.8567, + "step": 28750 + }, + { + "epoch": 1.07, + "learning_rate": 8.930338081600774e-06, + "loss": 1.8946, + "step": 28760 + }, + { + "epoch": 1.07, + "learning_rate": 8.929966154647228e-06, + "loss": 1.8612, + "step": 28770 + }, + { + "epoch": 1.07, + "learning_rate": 8.929594227693681e-06, + "loss": 1.7593, + "step": 28780 + }, + { + "epoch": 1.07, + "learning_rate": 8.929222300740137e-06, + "loss": 1.917, + "step": 28790 + }, + { + "epoch": 1.07, + "learning_rate": 8.92885037378659e-06, + "loss": 1.8793, + "step": 28800 + }, + { + "epoch": 1.07, + "eval_loss": 1.7640844583511353, + "eval_runtime": 16.8412, + "eval_samples_per_second": 59.378, + "eval_steps_per_second": 3.741, + "step": 28800 + }, + { + "epoch": 1.07, + "learning_rate": 8.928478446833043e-06, + "loss": 1.7485, + "step": 28810 + }, + { + "epoch": 1.07, + "learning_rate": 8.928106519879497e-06, + "loss": 1.7806, + "step": 28820 + }, + { + "epoch": 1.07, + "learning_rate": 8.92773459292595e-06, + "loss": 1.7962, + "step": 28830 + }, + { + "epoch": 1.07, + "learning_rate": 8.927362665972404e-06, + "loss": 1.9461, + "step": 28840 + }, + { + "epoch": 1.07, + "learning_rate": 8.926990739018857e-06, + "loss": 1.8626, + "step": 28850 + }, + { + "epoch": 1.07, + "learning_rate": 8.92661881206531e-06, + "loss": 1.7141, + "step": 28860 + }, + { + "epoch": 1.07, + "learning_rate": 8.926246885111764e-06, + "loss": 1.862, + "step": 28870 + }, + { + "epoch": 1.07, + "learning_rate": 8.925874958158218e-06, + "loss": 1.8053, + "step": 28880 + }, + { + "epoch": 1.07, + "learning_rate": 8.925503031204673e-06, + "loss": 1.934, + "step": 28890 + }, + { + "epoch": 1.07, + "learning_rate": 8.925131104251126e-06, + "loss": 1.7933, + "step": 28900 + }, + { + "epoch": 1.07, + "eval_loss": 1.7643696069717407, + "eval_runtime": 16.8058, + "eval_samples_per_second": 59.503, + "eval_steps_per_second": 3.749, + "step": 28900 + }, + { + "epoch": 1.08, + "learning_rate": 8.92475917729758e-06, + "loss": 1.8482, + "step": 28910 + }, + { + "epoch": 1.08, + "learning_rate": 8.924387250344033e-06, + "loss": 1.7899, + "step": 28920 + }, + { + "epoch": 1.08, + "learning_rate": 8.924015323390487e-06, + "loss": 1.7699, + "step": 28930 + }, + { + "epoch": 1.08, + "learning_rate": 8.92364339643694e-06, + "loss": 1.814, + "step": 28940 + }, + { + "epoch": 1.08, + "learning_rate": 8.923271469483394e-06, + "loss": 1.7724, + "step": 28950 + }, + { + "epoch": 1.08, + "learning_rate": 8.922899542529849e-06, + "loss": 1.7172, + "step": 28960 + }, + { + "epoch": 1.08, + "learning_rate": 8.922527615576302e-06, + "loss": 1.8859, + "step": 28970 + }, + { + "epoch": 1.08, + "learning_rate": 8.922155688622756e-06, + "loss": 1.774, + "step": 28980 + }, + { + "epoch": 1.08, + "learning_rate": 8.921783761669209e-06, + "loss": 1.9983, + "step": 28990 + }, + { + "epoch": 1.08, + "learning_rate": 8.921411834715663e-06, + "loss": 1.8956, + "step": 29000 + }, + { + "epoch": 1.08, + "eval_loss": 1.7641873359680176, + "eval_runtime": 16.817, + "eval_samples_per_second": 59.464, + "eval_steps_per_second": 3.746, + "step": 29000 + }, + { + "epoch": 1.08, + "learning_rate": 8.921039907762116e-06, + "loss": 1.9032, + "step": 29010 + }, + { + "epoch": 1.08, + "learning_rate": 8.92066798080857e-06, + "loss": 1.7417, + "step": 29020 + }, + { + "epoch": 1.08, + "learning_rate": 8.920296053855023e-06, + "loss": 1.8754, + "step": 29030 + }, + { + "epoch": 1.08, + "learning_rate": 8.919924126901476e-06, + "loss": 1.7843, + "step": 29040 + }, + { + "epoch": 1.08, + "learning_rate": 8.91955219994793e-06, + "loss": 1.8898, + "step": 29050 + }, + { + "epoch": 1.08, + "learning_rate": 8.919180272994385e-06, + "loss": 1.7779, + "step": 29060 + }, + { + "epoch": 1.08, + "learning_rate": 8.918808346040838e-06, + "loss": 1.8719, + "step": 29070 + }, + { + "epoch": 1.08, + "learning_rate": 8.918436419087292e-06, + "loss": 1.806, + "step": 29080 + }, + { + "epoch": 1.08, + "learning_rate": 8.918064492133745e-06, + "loss": 1.7764, + "step": 29090 + }, + { + "epoch": 1.08, + "learning_rate": 8.917692565180199e-06, + "loss": 1.8922, + "step": 29100 + }, + { + "epoch": 1.08, + "eval_loss": 1.764703392982483, + "eval_runtime": 16.8309, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 29100 + }, + { + "epoch": 1.08, + "learning_rate": 8.917320638226652e-06, + "loss": 1.7234, + "step": 29110 + }, + { + "epoch": 1.08, + "learning_rate": 8.916948711273107e-06, + "loss": 1.8564, + "step": 29120 + }, + { + "epoch": 1.08, + "learning_rate": 8.916576784319561e-06, + "loss": 1.8773, + "step": 29130 + }, + { + "epoch": 1.08, + "learning_rate": 8.916204857366014e-06, + "loss": 1.7632, + "step": 29140 + }, + { + "epoch": 1.08, + "learning_rate": 8.915832930412468e-06, + "loss": 1.9469, + "step": 29150 + }, + { + "epoch": 1.08, + "learning_rate": 8.915461003458921e-06, + "loss": 1.8598, + "step": 29160 + }, + { + "epoch": 1.08, + "learning_rate": 8.915089076505375e-06, + "loss": 1.867, + "step": 29170 + }, + { + "epoch": 1.09, + "learning_rate": 8.91471714955183e-06, + "loss": 1.8563, + "step": 29180 + }, + { + "epoch": 1.09, + "learning_rate": 8.914345222598283e-06, + "loss": 1.7669, + "step": 29190 + }, + { + "epoch": 1.09, + "learning_rate": 8.913973295644735e-06, + "loss": 1.7998, + "step": 29200 + }, + { + "epoch": 1.09, + "eval_loss": 1.764904499053955, + "eval_runtime": 16.8274, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 29200 + }, + { + "epoch": 1.09, + "learning_rate": 8.913601368691189e-06, + "loss": 1.9598, + "step": 29210 + }, + { + "epoch": 1.09, + "learning_rate": 8.913229441737644e-06, + "loss": 1.9215, + "step": 29220 + }, + { + "epoch": 1.09, + "learning_rate": 8.912857514784097e-06, + "loss": 1.8186, + "step": 29230 + }, + { + "epoch": 1.09, + "learning_rate": 8.91248558783055e-06, + "loss": 1.8277, + "step": 29240 + }, + { + "epoch": 1.09, + "learning_rate": 8.912113660877004e-06, + "loss": 1.8895, + "step": 29250 + }, + { + "epoch": 1.09, + "learning_rate": 8.911741733923458e-06, + "loss": 1.7548, + "step": 29260 + }, + { + "epoch": 1.09, + "learning_rate": 8.911369806969911e-06, + "loss": 1.8267, + "step": 29270 + }, + { + "epoch": 1.09, + "learning_rate": 8.910997880016366e-06, + "loss": 1.8635, + "step": 29280 + }, + { + "epoch": 1.09, + "learning_rate": 8.91062595306282e-06, + "loss": 1.8159, + "step": 29290 + }, + { + "epoch": 1.09, + "learning_rate": 8.910254026109273e-06, + "loss": 1.8284, + "step": 29300 + }, + { + "epoch": 1.09, + "eval_loss": 1.76500403881073, + "eval_runtime": 16.8073, + "eval_samples_per_second": 59.498, + "eval_steps_per_second": 3.748, + "step": 29300 + }, + { + "epoch": 1.09, + "learning_rate": 8.909882099155727e-06, + "loss": 1.7989, + "step": 29310 + }, + { + "epoch": 1.09, + "learning_rate": 8.90951017220218e-06, + "loss": 1.8747, + "step": 29320 + }, + { + "epoch": 1.09, + "learning_rate": 8.909138245248633e-06, + "loss": 1.7454, + "step": 29330 + }, + { + "epoch": 1.09, + "learning_rate": 8.908766318295089e-06, + "loss": 1.7331, + "step": 29340 + }, + { + "epoch": 1.09, + "learning_rate": 8.908394391341542e-06, + "loss": 1.9928, + "step": 29350 + }, + { + "epoch": 1.09, + "learning_rate": 8.908022464387996e-06, + "loss": 1.7644, + "step": 29360 + }, + { + "epoch": 1.09, + "learning_rate": 8.907650537434449e-06, + "loss": 1.9551, + "step": 29370 + }, + { + "epoch": 1.09, + "learning_rate": 8.907278610480902e-06, + "loss": 1.8186, + "step": 29380 + }, + { + "epoch": 1.09, + "learning_rate": 8.906906683527356e-06, + "loss": 1.8224, + "step": 29390 + }, + { + "epoch": 1.09, + "learning_rate": 8.90653475657381e-06, + "loss": 1.7708, + "step": 29400 + }, + { + "epoch": 1.09, + "eval_loss": 1.7633079290390015, + "eval_runtime": 16.8184, + "eval_samples_per_second": 59.459, + "eval_steps_per_second": 3.746, + "step": 29400 + }, + { + "epoch": 1.09, + "learning_rate": 8.906162829620263e-06, + "loss": 1.9043, + "step": 29410 + }, + { + "epoch": 1.09, + "learning_rate": 8.905790902666716e-06, + "loss": 1.7415, + "step": 29420 + }, + { + "epoch": 1.09, + "learning_rate": 8.90541897571317e-06, + "loss": 1.8844, + "step": 29430 + }, + { + "epoch": 1.09, + "learning_rate": 8.905047048759625e-06, + "loss": 1.8842, + "step": 29440 + }, + { + "epoch": 1.1, + "learning_rate": 8.904675121806078e-06, + "loss": 1.7071, + "step": 29450 + }, + { + "epoch": 1.1, + "learning_rate": 8.904303194852532e-06, + "loss": 1.8671, + "step": 29460 + }, + { + "epoch": 1.1, + "learning_rate": 8.903931267898985e-06, + "loss": 1.9029, + "step": 29470 + }, + { + "epoch": 1.1, + "learning_rate": 8.903559340945439e-06, + "loss": 1.7332, + "step": 29480 + }, + { + "epoch": 1.1, + "learning_rate": 8.903187413991892e-06, + "loss": 1.8873, + "step": 29490 + }, + { + "epoch": 1.1, + "learning_rate": 8.902815487038346e-06, + "loss": 1.6944, + "step": 29500 + }, + { + "epoch": 1.1, + "eval_loss": 1.7638782262802124, + "eval_runtime": 16.8151, + "eval_samples_per_second": 59.47, + "eval_steps_per_second": 3.747, + "step": 29500 + }, + { + "epoch": 1.1, + "learning_rate": 8.9024435600848e-06, + "loss": 1.781, + "step": 29510 + }, + { + "epoch": 1.1, + "learning_rate": 8.902071633131254e-06, + "loss": 1.7375, + "step": 29520 + }, + { + "epoch": 1.1, + "learning_rate": 8.901699706177708e-06, + "loss": 1.8828, + "step": 29530 + }, + { + "epoch": 1.1, + "learning_rate": 8.901327779224161e-06, + "loss": 1.9053, + "step": 29540 + }, + { + "epoch": 1.1, + "learning_rate": 8.900955852270615e-06, + "loss": 1.9297, + "step": 29550 + }, + { + "epoch": 1.1, + "learning_rate": 8.900583925317068e-06, + "loss": 1.9238, + "step": 29560 + }, + { + "epoch": 1.1, + "learning_rate": 8.900211998363523e-06, + "loss": 1.8459, + "step": 29570 + }, + { + "epoch": 1.1, + "learning_rate": 8.899840071409975e-06, + "loss": 1.7428, + "step": 29580 + }, + { + "epoch": 1.1, + "learning_rate": 8.899468144456429e-06, + "loss": 1.7632, + "step": 29590 + }, + { + "epoch": 1.1, + "learning_rate": 8.899096217502882e-06, + "loss": 1.7275, + "step": 29600 + }, + { + "epoch": 1.1, + "eval_loss": 1.7626237869262695, + "eval_runtime": 16.8197, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 29600 + }, + { + "epoch": 1.1, + "learning_rate": 8.898724290549337e-06, + "loss": 1.8356, + "step": 29610 + }, + { + "epoch": 1.1, + "learning_rate": 8.89835236359579e-06, + "loss": 1.7866, + "step": 29620 + }, + { + "epoch": 1.1, + "learning_rate": 8.897980436642244e-06, + "loss": 1.8379, + "step": 29630 + }, + { + "epoch": 1.1, + "learning_rate": 8.897608509688698e-06, + "loss": 1.7506, + "step": 29640 + }, + { + "epoch": 1.1, + "learning_rate": 8.897236582735151e-06, + "loss": 1.7786, + "step": 29650 + }, + { + "epoch": 1.1, + "learning_rate": 8.896864655781604e-06, + "loss": 1.7029, + "step": 29660 + }, + { + "epoch": 1.1, + "learning_rate": 8.89649272882806e-06, + "loss": 1.9137, + "step": 29670 + }, + { + "epoch": 1.1, + "learning_rate": 8.896120801874513e-06, + "loss": 1.8444, + "step": 29680 + }, + { + "epoch": 1.1, + "learning_rate": 8.895748874920966e-06, + "loss": 1.7413, + "step": 29690 + }, + { + "epoch": 1.1, + "learning_rate": 8.89537694796742e-06, + "loss": 1.8235, + "step": 29700 + }, + { + "epoch": 1.1, + "eval_loss": 1.7627605199813843, + "eval_runtime": 16.8019, + "eval_samples_per_second": 59.517, + "eval_steps_per_second": 3.75, + "step": 29700 + }, + { + "epoch": 1.1, + "learning_rate": 8.895005021013873e-06, + "loss": 1.7525, + "step": 29710 + }, + { + "epoch": 1.11, + "learning_rate": 8.894633094060327e-06, + "loss": 1.8202, + "step": 29720 + }, + { + "epoch": 1.11, + "learning_rate": 8.894261167106782e-06, + "loss": 1.784, + "step": 29730 + }, + { + "epoch": 1.11, + "learning_rate": 8.893889240153235e-06, + "loss": 1.934, + "step": 29740 + }, + { + "epoch": 1.11, + "learning_rate": 8.893517313199689e-06, + "loss": 1.707, + "step": 29750 + }, + { + "epoch": 1.11, + "learning_rate": 8.89314538624614e-06, + "loss": 1.7487, + "step": 29760 + }, + { + "epoch": 1.11, + "learning_rate": 8.892773459292596e-06, + "loss": 1.8277, + "step": 29770 + }, + { + "epoch": 1.11, + "learning_rate": 8.89240153233905e-06, + "loss": 1.791, + "step": 29780 + }, + { + "epoch": 1.11, + "learning_rate": 8.892029605385503e-06, + "loss": 1.8034, + "step": 29790 + }, + { + "epoch": 1.11, + "learning_rate": 8.891657678431956e-06, + "loss": 1.7815, + "step": 29800 + }, + { + "epoch": 1.11, + "eval_loss": 1.7621022462844849, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 29800 + }, + { + "epoch": 1.11, + "learning_rate": 8.89128575147841e-06, + "loss": 1.8656, + "step": 29810 + }, + { + "epoch": 1.11, + "learning_rate": 8.890913824524863e-06, + "loss": 1.9008, + "step": 29820 + }, + { + "epoch": 1.11, + "learning_rate": 8.890541897571318e-06, + "loss": 1.6995, + "step": 29830 + }, + { + "epoch": 1.11, + "learning_rate": 8.890169970617772e-06, + "loss": 1.8131, + "step": 29840 + }, + { + "epoch": 1.11, + "learning_rate": 8.889798043664225e-06, + "loss": 1.8653, + "step": 29850 + }, + { + "epoch": 1.11, + "learning_rate": 8.889426116710679e-06, + "loss": 1.8952, + "step": 29860 + }, + { + "epoch": 1.11, + "learning_rate": 8.889054189757132e-06, + "loss": 1.8601, + "step": 29870 + }, + { + "epoch": 1.11, + "learning_rate": 8.888682262803586e-06, + "loss": 1.9432, + "step": 29880 + }, + { + "epoch": 1.11, + "learning_rate": 8.88831033585004e-06, + "loss": 1.8561, + "step": 29890 + }, + { + "epoch": 1.11, + "learning_rate": 8.887938408896494e-06, + "loss": 1.7727, + "step": 29900 + }, + { + "epoch": 1.11, + "eval_loss": 1.7608269453048706, + "eval_runtime": 16.8138, + "eval_samples_per_second": 59.475, + "eval_steps_per_second": 3.747, + "step": 29900 + }, + { + "epoch": 1.11, + "learning_rate": 8.887566481942948e-06, + "loss": 1.8117, + "step": 29910 + }, + { + "epoch": 1.11, + "learning_rate": 8.887194554989401e-06, + "loss": 1.8469, + "step": 29920 + }, + { + "epoch": 1.11, + "learning_rate": 8.886822628035855e-06, + "loss": 1.9632, + "step": 29930 + }, + { + "epoch": 1.11, + "learning_rate": 8.886450701082308e-06, + "loss": 1.7111, + "step": 29940 + }, + { + "epoch": 1.11, + "learning_rate": 8.886078774128762e-06, + "loss": 1.7786, + "step": 29950 + }, + { + "epoch": 1.11, + "learning_rate": 8.885706847175215e-06, + "loss": 1.7612, + "step": 29960 + }, + { + "epoch": 1.11, + "learning_rate": 8.885334920221668e-06, + "loss": 1.767, + "step": 29970 + }, + { + "epoch": 1.12, + "learning_rate": 8.884962993268122e-06, + "loss": 1.8807, + "step": 29980 + }, + { + "epoch": 1.12, + "learning_rate": 8.884591066314577e-06, + "loss": 1.6812, + "step": 29990 + }, + { + "epoch": 1.12, + "learning_rate": 8.88421913936103e-06, + "loss": 1.8085, + "step": 30000 + }, + { + "epoch": 1.12, + "eval_loss": 1.7614699602127075, + "eval_runtime": 16.8394, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 30000 + }, + { + "epoch": 1.12, + "learning_rate": 8.883847212407484e-06, + "loss": 1.8659, + "step": 30010 + }, + { + "epoch": 1.12, + "learning_rate": 8.883475285453937e-06, + "loss": 1.9146, + "step": 30020 + }, + { + "epoch": 1.12, + "learning_rate": 8.883103358500391e-06, + "loss": 1.7704, + "step": 30030 + }, + { + "epoch": 1.12, + "learning_rate": 8.882731431546844e-06, + "loss": 1.8264, + "step": 30040 + }, + { + "epoch": 1.12, + "learning_rate": 8.8823595045933e-06, + "loss": 1.9324, + "step": 30050 + }, + { + "epoch": 1.12, + "learning_rate": 8.881987577639753e-06, + "loss": 1.8071, + "step": 30060 + }, + { + "epoch": 1.12, + "learning_rate": 8.881615650686206e-06, + "loss": 1.9246, + "step": 30070 + }, + { + "epoch": 1.12, + "learning_rate": 8.88124372373266e-06, + "loss": 1.5601, + "step": 30080 + }, + { + "epoch": 1.12, + "learning_rate": 8.880871796779113e-06, + "loss": 1.7881, + "step": 30090 + }, + { + "epoch": 1.12, + "learning_rate": 8.880499869825567e-06, + "loss": 1.7567, + "step": 30100 + }, + { + "epoch": 1.12, + "eval_loss": 1.7615162134170532, + "eval_runtime": 16.8156, + "eval_samples_per_second": 59.469, + "eval_steps_per_second": 3.747, + "step": 30100 + }, + { + "epoch": 1.12, + "learning_rate": 8.88012794287202e-06, + "loss": 1.8044, + "step": 30110 + }, + { + "epoch": 1.12, + "learning_rate": 8.879756015918475e-06, + "loss": 1.836, + "step": 30120 + }, + { + "epoch": 1.12, + "learning_rate": 8.879384088964929e-06, + "loss": 1.8506, + "step": 30130 + }, + { + "epoch": 1.12, + "learning_rate": 8.87901216201138e-06, + "loss": 1.8536, + "step": 30140 + }, + { + "epoch": 1.12, + "learning_rate": 8.878640235057834e-06, + "loss": 1.806, + "step": 30150 + }, + { + "epoch": 1.12, + "learning_rate": 8.87826830810429e-06, + "loss": 1.8405, + "step": 30160 + }, + { + "epoch": 1.12, + "learning_rate": 8.877896381150743e-06, + "loss": 1.9353, + "step": 30170 + }, + { + "epoch": 1.12, + "learning_rate": 8.877524454197196e-06, + "loss": 1.9396, + "step": 30180 + }, + { + "epoch": 1.12, + "learning_rate": 8.87715252724365e-06, + "loss": 1.7293, + "step": 30190 + }, + { + "epoch": 1.12, + "learning_rate": 8.876780600290103e-06, + "loss": 1.8344, + "step": 30200 + }, + { + "epoch": 1.12, + "eval_loss": 1.7605358362197876, + "eval_runtime": 16.8121, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 30200 + }, + { + "epoch": 1.12, + "learning_rate": 8.876408673336557e-06, + "loss": 1.8167, + "step": 30210 + }, + { + "epoch": 1.12, + "learning_rate": 8.876036746383012e-06, + "loss": 1.7641, + "step": 30220 + }, + { + "epoch": 1.12, + "learning_rate": 8.875664819429465e-06, + "loss": 1.9215, + "step": 30230 + }, + { + "epoch": 1.12, + "learning_rate": 8.875292892475919e-06, + "loss": 1.7389, + "step": 30240 + }, + { + "epoch": 1.13, + "learning_rate": 8.874920965522372e-06, + "loss": 1.8993, + "step": 30250 + }, + { + "epoch": 1.13, + "learning_rate": 8.874549038568826e-06, + "loss": 1.7402, + "step": 30260 + }, + { + "epoch": 1.13, + "learning_rate": 8.874177111615279e-06, + "loss": 1.9111, + "step": 30270 + }, + { + "epoch": 1.13, + "learning_rate": 8.873805184661734e-06, + "loss": 1.8217, + "step": 30280 + }, + { + "epoch": 1.13, + "learning_rate": 8.873433257708188e-06, + "loss": 1.931, + "step": 30290 + }, + { + "epoch": 1.13, + "learning_rate": 8.873061330754641e-06, + "loss": 1.8088, + "step": 30300 + }, + { + "epoch": 1.13, + "eval_loss": 1.7594670057296753, + "eval_runtime": 16.8209, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 30300 + }, + { + "epoch": 1.13, + "learning_rate": 8.872689403801095e-06, + "loss": 1.8299, + "step": 30310 + }, + { + "epoch": 1.13, + "learning_rate": 8.872317476847548e-06, + "loss": 1.9163, + "step": 30320 + }, + { + "epoch": 1.13, + "learning_rate": 8.871945549894001e-06, + "loss": 1.7752, + "step": 30330 + }, + { + "epoch": 1.13, + "learning_rate": 8.871573622940455e-06, + "loss": 1.7118, + "step": 30340 + }, + { + "epoch": 1.13, + "learning_rate": 8.871201695986908e-06, + "loss": 1.7761, + "step": 30350 + }, + { + "epoch": 1.13, + "learning_rate": 8.870829769033362e-06, + "loss": 1.812, + "step": 30360 + }, + { + "epoch": 1.13, + "learning_rate": 8.870457842079815e-06, + "loss": 1.7792, + "step": 30370 + }, + { + "epoch": 1.13, + "learning_rate": 8.87008591512627e-06, + "loss": 1.7979, + "step": 30380 + }, + { + "epoch": 1.13, + "learning_rate": 8.869713988172724e-06, + "loss": 1.8994, + "step": 30390 + }, + { + "epoch": 1.13, + "learning_rate": 8.869342061219177e-06, + "loss": 1.8515, + "step": 30400 + }, + { + "epoch": 1.13, + "eval_loss": 1.760168194770813, + "eval_runtime": 16.8054, + "eval_samples_per_second": 59.505, + "eval_steps_per_second": 3.749, + "step": 30400 + }, + { + "epoch": 1.13, + "learning_rate": 8.86897013426563e-06, + "loss": 1.7512, + "step": 30410 + }, + { + "epoch": 1.13, + "learning_rate": 8.868598207312084e-06, + "loss": 1.7391, + "step": 30420 + }, + { + "epoch": 1.13, + "learning_rate": 8.868226280358538e-06, + "loss": 1.8931, + "step": 30430 + }, + { + "epoch": 1.13, + "learning_rate": 8.867854353404993e-06, + "loss": 1.7512, + "step": 30440 + }, + { + "epoch": 1.13, + "learning_rate": 8.867482426451446e-06, + "loss": 1.7051, + "step": 30450 + }, + { + "epoch": 1.13, + "learning_rate": 8.8671104994979e-06, + "loss": 1.8307, + "step": 30460 + }, + { + "epoch": 1.13, + "learning_rate": 8.866738572544353e-06, + "loss": 1.7554, + "step": 30470 + }, + { + "epoch": 1.13, + "learning_rate": 8.866366645590807e-06, + "loss": 1.6639, + "step": 30480 + }, + { + "epoch": 1.13, + "learning_rate": 8.86599471863726e-06, + "loss": 1.7319, + "step": 30490 + }, + { + "epoch": 1.13, + "learning_rate": 8.865622791683715e-06, + "loss": 1.8295, + "step": 30500 + }, + { + "epoch": 1.13, + "eval_loss": 1.7608174085617065, + "eval_runtime": 16.8199, + "eval_samples_per_second": 59.453, + "eval_steps_per_second": 3.746, + "step": 30500 + }, + { + "epoch": 1.13, + "learning_rate": 8.865250864730169e-06, + "loss": 1.8591, + "step": 30510 + }, + { + "epoch": 1.14, + "learning_rate": 8.86487893777662e-06, + "loss": 1.7557, + "step": 30520 + }, + { + "epoch": 1.14, + "learning_rate": 8.864507010823074e-06, + "loss": 1.7936, + "step": 30530 + }, + { + "epoch": 1.14, + "learning_rate": 8.86413508386953e-06, + "loss": 1.8992, + "step": 30540 + }, + { + "epoch": 1.14, + "learning_rate": 8.863763156915983e-06, + "loss": 1.8306, + "step": 30550 + }, + { + "epoch": 1.14, + "learning_rate": 8.863391229962436e-06, + "loss": 1.8276, + "step": 30560 + }, + { + "epoch": 1.14, + "learning_rate": 8.86301930300889e-06, + "loss": 1.8429, + "step": 30570 + }, + { + "epoch": 1.14, + "learning_rate": 8.862647376055343e-06, + "loss": 1.8389, + "step": 30580 + }, + { + "epoch": 1.14, + "learning_rate": 8.862275449101796e-06, + "loss": 1.7269, + "step": 30590 + }, + { + "epoch": 1.14, + "learning_rate": 8.861903522148252e-06, + "loss": 1.8612, + "step": 30600 + }, + { + "epoch": 1.14, + "eval_loss": 1.7595710754394531, + "eval_runtime": 16.7974, + "eval_samples_per_second": 59.533, + "eval_steps_per_second": 3.751, + "step": 30600 + }, + { + "epoch": 1.14, + "learning_rate": 8.861531595194705e-06, + "loss": 1.7897, + "step": 30610 + }, + { + "epoch": 1.14, + "learning_rate": 8.861159668241159e-06, + "loss": 1.8019, + "step": 30620 + }, + { + "epoch": 1.14, + "learning_rate": 8.860787741287612e-06, + "loss": 1.6652, + "step": 30630 + }, + { + "epoch": 1.14, + "learning_rate": 8.860415814334065e-06, + "loss": 1.941, + "step": 30640 + }, + { + "epoch": 1.14, + "learning_rate": 8.860043887380519e-06, + "loss": 1.8419, + "step": 30650 + }, + { + "epoch": 1.14, + "learning_rate": 8.859671960426972e-06, + "loss": 1.9065, + "step": 30660 + }, + { + "epoch": 1.14, + "learning_rate": 8.859300033473428e-06, + "loss": 1.8668, + "step": 30670 + }, + { + "epoch": 1.14, + "learning_rate": 8.858928106519881e-06, + "loss": 1.7158, + "step": 30680 + }, + { + "epoch": 1.14, + "learning_rate": 8.858556179566334e-06, + "loss": 1.9161, + "step": 30690 + }, + { + "epoch": 1.14, + "learning_rate": 8.858184252612786e-06, + "loss": 1.9683, + "step": 30700 + }, + { + "epoch": 1.14, + "eval_loss": 1.7588235139846802, + "eval_runtime": 16.8124, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 30700 + }, + { + "epoch": 1.14, + "learning_rate": 8.857812325659241e-06, + "loss": 1.8057, + "step": 30710 + }, + { + "epoch": 1.14, + "learning_rate": 8.857440398705695e-06, + "loss": 1.7713, + "step": 30720 + }, + { + "epoch": 1.14, + "learning_rate": 8.857068471752148e-06, + "loss": 1.6928, + "step": 30730 + }, + { + "epoch": 1.14, + "learning_rate": 8.856696544798602e-06, + "loss": 1.9, + "step": 30740 + }, + { + "epoch": 1.14, + "learning_rate": 8.856324617845055e-06, + "loss": 1.9316, + "step": 30750 + }, + { + "epoch": 1.14, + "learning_rate": 8.855952690891509e-06, + "loss": 1.7883, + "step": 30760 + }, + { + "epoch": 1.14, + "learning_rate": 8.855580763937964e-06, + "loss": 1.6543, + "step": 30770 + }, + { + "epoch": 1.14, + "learning_rate": 8.855208836984417e-06, + "loss": 1.9026, + "step": 30780 + }, + { + "epoch": 1.15, + "learning_rate": 8.85483691003087e-06, + "loss": 1.69, + "step": 30790 + }, + { + "epoch": 1.15, + "learning_rate": 8.854464983077324e-06, + "loss": 1.8134, + "step": 30800 + }, + { + "epoch": 1.15, + "eval_loss": 1.7585095167160034, + "eval_runtime": 16.8127, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 30800 + }, + { + "epoch": 1.15, + "learning_rate": 8.854093056123778e-06, + "loss": 1.8168, + "step": 30810 + }, + { + "epoch": 1.15, + "learning_rate": 8.853721129170231e-06, + "loss": 1.8563, + "step": 30820 + }, + { + "epoch": 1.15, + "learning_rate": 8.853349202216686e-06, + "loss": 1.8129, + "step": 30830 + }, + { + "epoch": 1.15, + "learning_rate": 8.85297727526314e-06, + "loss": 1.8183, + "step": 30840 + }, + { + "epoch": 1.15, + "learning_rate": 8.852605348309593e-06, + "loss": 1.7947, + "step": 30850 + }, + { + "epoch": 1.15, + "learning_rate": 8.852233421356047e-06, + "loss": 1.7163, + "step": 30860 + }, + { + "epoch": 1.15, + "learning_rate": 8.8518614944025e-06, + "loss": 1.8454, + "step": 30870 + }, + { + "epoch": 1.15, + "learning_rate": 8.851489567448954e-06, + "loss": 1.6892, + "step": 30880 + }, + { + "epoch": 1.15, + "learning_rate": 8.851117640495407e-06, + "loss": 1.6924, + "step": 30890 + }, + { + "epoch": 1.15, + "learning_rate": 8.85074571354186e-06, + "loss": 1.8937, + "step": 30900 + }, + { + "epoch": 1.15, + "eval_loss": 1.7596491575241089, + "eval_runtime": 16.8231, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 30900 + }, + { + "epoch": 1.15, + "learning_rate": 8.850373786588314e-06, + "loss": 1.8017, + "step": 30910 + }, + { + "epoch": 1.15, + "learning_rate": 8.850001859634767e-06, + "loss": 1.8955, + "step": 30920 + }, + { + "epoch": 1.15, + "learning_rate": 8.849629932681223e-06, + "loss": 1.7011, + "step": 30930 + }, + { + "epoch": 1.15, + "learning_rate": 8.849258005727676e-06, + "loss": 1.9366, + "step": 30940 + }, + { + "epoch": 1.15, + "learning_rate": 8.84888607877413e-06, + "loss": 1.8101, + "step": 30950 + }, + { + "epoch": 1.15, + "learning_rate": 8.848514151820583e-06, + "loss": 1.848, + "step": 30960 + }, + { + "epoch": 1.15, + "learning_rate": 8.848142224867036e-06, + "loss": 1.9493, + "step": 30970 + }, + { + "epoch": 1.15, + "learning_rate": 8.84777029791349e-06, + "loss": 1.8016, + "step": 30980 + }, + { + "epoch": 1.15, + "learning_rate": 8.847398370959945e-06, + "loss": 1.8818, + "step": 30990 + }, + { + "epoch": 1.15, + "learning_rate": 8.847026444006398e-06, + "loss": 1.8631, + "step": 31000 + }, + { + "epoch": 1.15, + "eval_loss": 1.758317232131958, + "eval_runtime": 16.8051, + "eval_samples_per_second": 59.506, + "eval_steps_per_second": 3.749, + "step": 31000 + }, + { + "epoch": 1.15, + "learning_rate": 8.846654517052852e-06, + "loss": 1.7743, + "step": 31010 + }, + { + "epoch": 1.15, + "learning_rate": 8.846282590099305e-06, + "loss": 1.846, + "step": 31020 + }, + { + "epoch": 1.15, + "learning_rate": 8.845910663145759e-06, + "loss": 1.7913, + "step": 31030 + }, + { + "epoch": 1.15, + "learning_rate": 8.845538736192212e-06, + "loss": 1.8601, + "step": 31040 + }, + { + "epoch": 1.15, + "learning_rate": 8.845166809238667e-06, + "loss": 1.7927, + "step": 31050 + }, + { + "epoch": 1.16, + "learning_rate": 8.844794882285121e-06, + "loss": 1.8778, + "step": 31060 + }, + { + "epoch": 1.16, + "learning_rate": 8.844422955331574e-06, + "loss": 1.8652, + "step": 31070 + }, + { + "epoch": 1.16, + "learning_rate": 8.844051028378026e-06, + "loss": 1.7254, + "step": 31080 + }, + { + "epoch": 1.16, + "learning_rate": 8.843679101424481e-06, + "loss": 1.8398, + "step": 31090 + }, + { + "epoch": 1.16, + "learning_rate": 8.843307174470935e-06, + "loss": 1.7711, + "step": 31100 + }, + { + "epoch": 1.16, + "eval_loss": 1.7585581541061401, + "eval_runtime": 16.8439, + "eval_samples_per_second": 59.369, + "eval_steps_per_second": 3.74, + "step": 31100 + }, + { + "epoch": 1.16, + "learning_rate": 8.842935247517388e-06, + "loss": 1.9294, + "step": 31110 + }, + { + "epoch": 1.16, + "learning_rate": 8.842563320563842e-06, + "loss": 1.8613, + "step": 31120 + }, + { + "epoch": 1.16, + "learning_rate": 8.842191393610295e-06, + "loss": 1.7944, + "step": 31130 + }, + { + "epoch": 1.16, + "learning_rate": 8.841819466656749e-06, + "loss": 1.8523, + "step": 31140 + }, + { + "epoch": 1.16, + "learning_rate": 8.841447539703204e-06, + "loss": 1.8736, + "step": 31150 + }, + { + "epoch": 1.16, + "learning_rate": 8.841075612749657e-06, + "loss": 1.7983, + "step": 31160 + }, + { + "epoch": 1.16, + "learning_rate": 8.84070368579611e-06, + "loss": 1.7676, + "step": 31170 + }, + { + "epoch": 1.16, + "learning_rate": 8.840331758842564e-06, + "loss": 2.0321, + "step": 31180 + }, + { + "epoch": 1.16, + "learning_rate": 8.839959831889018e-06, + "loss": 1.6837, + "step": 31190 + }, + { + "epoch": 1.16, + "learning_rate": 8.839587904935471e-06, + "loss": 1.8323, + "step": 31200 + }, + { + "epoch": 1.16, + "eval_loss": 1.7582893371582031, + "eval_runtime": 16.8483, + "eval_samples_per_second": 59.353, + "eval_steps_per_second": 3.739, + "step": 31200 + }, + { + "epoch": 1.16, + "learning_rate": 8.839215977981926e-06, + "loss": 1.7807, + "step": 31210 + }, + { + "epoch": 1.16, + "learning_rate": 8.83884405102838e-06, + "loss": 1.8835, + "step": 31220 + }, + { + "epoch": 1.16, + "learning_rate": 8.838472124074833e-06, + "loss": 1.8214, + "step": 31230 + }, + { + "epoch": 1.16, + "learning_rate": 8.838100197121287e-06, + "loss": 1.9055, + "step": 31240 + }, + { + "epoch": 1.16, + "learning_rate": 8.83772827016774e-06, + "loss": 1.6911, + "step": 31250 + }, + { + "epoch": 1.16, + "learning_rate": 8.837356343214193e-06, + "loss": 1.8176, + "step": 31260 + }, + { + "epoch": 1.16, + "learning_rate": 8.836984416260647e-06, + "loss": 1.7783, + "step": 31270 + }, + { + "epoch": 1.16, + "learning_rate": 8.8366124893071e-06, + "loss": 1.8503, + "step": 31280 + }, + { + "epoch": 1.16, + "learning_rate": 8.836240562353554e-06, + "loss": 1.9133, + "step": 31290 + }, + { + "epoch": 1.16, + "learning_rate": 8.835868635400007e-06, + "loss": 1.8493, + "step": 31300 + }, + { + "epoch": 1.16, + "eval_loss": 1.7572355270385742, + "eval_runtime": 16.8404, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 31300 + }, + { + "epoch": 1.16, + "learning_rate": 8.83549670844646e-06, + "loss": 1.7412, + "step": 31310 + }, + { + "epoch": 1.16, + "learning_rate": 8.835124781492916e-06, + "loss": 1.7694, + "step": 31320 + }, + { + "epoch": 1.17, + "learning_rate": 8.83475285453937e-06, + "loss": 1.6711, + "step": 31330 + }, + { + "epoch": 1.17, + "learning_rate": 8.834380927585823e-06, + "loss": 1.8357, + "step": 31340 + }, + { + "epoch": 1.17, + "learning_rate": 8.834009000632276e-06, + "loss": 1.7758, + "step": 31350 + }, + { + "epoch": 1.17, + "learning_rate": 8.83363707367873e-06, + "loss": 1.8594, + "step": 31360 + }, + { + "epoch": 1.17, + "learning_rate": 8.833265146725183e-06, + "loss": 1.7662, + "step": 31370 + }, + { + "epoch": 1.17, + "learning_rate": 8.832893219771638e-06, + "loss": 1.8569, + "step": 31380 + }, + { + "epoch": 1.17, + "learning_rate": 8.832521292818092e-06, + "loss": 1.7889, + "step": 31390 + }, + { + "epoch": 1.17, + "learning_rate": 8.832149365864545e-06, + "loss": 1.652, + "step": 31400 + }, + { + "epoch": 1.17, + "eval_loss": 1.7576346397399902, + "eval_runtime": 16.8309, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 31400 + }, + { + "epoch": 1.17, + "learning_rate": 8.831777438910999e-06, + "loss": 1.7463, + "step": 31410 + }, + { + "epoch": 1.17, + "learning_rate": 8.831405511957452e-06, + "loss": 1.899, + "step": 31420 + }, + { + "epoch": 1.17, + "learning_rate": 8.831033585003906e-06, + "loss": 1.8182, + "step": 31430 + }, + { + "epoch": 1.17, + "learning_rate": 8.83066165805036e-06, + "loss": 1.8108, + "step": 31440 + }, + { + "epoch": 1.17, + "learning_rate": 8.830289731096813e-06, + "loss": 1.8366, + "step": 31450 + }, + { + "epoch": 1.17, + "learning_rate": 8.829917804143266e-06, + "loss": 1.611, + "step": 31460 + }, + { + "epoch": 1.17, + "learning_rate": 8.82954587718972e-06, + "loss": 1.7974, + "step": 31470 + }, + { + "epoch": 1.17, + "learning_rate": 8.829173950236175e-06, + "loss": 1.9605, + "step": 31480 + }, + { + "epoch": 1.17, + "learning_rate": 8.828802023282628e-06, + "loss": 1.842, + "step": 31490 + }, + { + "epoch": 1.17, + "learning_rate": 8.828430096329082e-06, + "loss": 1.8377, + "step": 31500 + }, + { + "epoch": 1.17, + "eval_loss": 1.7576864957809448, + "eval_runtime": 16.8318, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 31500 + }, + { + "epoch": 1.17, + "learning_rate": 8.828058169375535e-06, + "loss": 1.7601, + "step": 31510 + }, + { + "epoch": 1.17, + "learning_rate": 8.827686242421988e-06, + "loss": 1.6935, + "step": 31520 + }, + { + "epoch": 1.17, + "learning_rate": 8.827314315468442e-06, + "loss": 1.7058, + "step": 31530 + }, + { + "epoch": 1.17, + "learning_rate": 8.826942388514897e-06, + "loss": 1.7811, + "step": 31540 + }, + { + "epoch": 1.17, + "learning_rate": 8.82657046156135e-06, + "loss": 1.8061, + "step": 31550 + }, + { + "epoch": 1.17, + "learning_rate": 8.826198534607804e-06, + "loss": 1.8898, + "step": 31560 + }, + { + "epoch": 1.17, + "learning_rate": 8.825826607654257e-06, + "loss": 1.8129, + "step": 31570 + }, + { + "epoch": 1.17, + "learning_rate": 8.825454680700711e-06, + "loss": 1.8683, + "step": 31580 + }, + { + "epoch": 1.17, + "learning_rate": 8.825082753747164e-06, + "loss": 1.8393, + "step": 31590 + }, + { + "epoch": 1.18, + "learning_rate": 8.82471082679362e-06, + "loss": 1.8386, + "step": 31600 + }, + { + "epoch": 1.18, + "eval_loss": 1.758126974105835, + "eval_runtime": 16.8277, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 31600 + }, + { + "epoch": 1.18, + "learning_rate": 8.824338899840073e-06, + "loss": 1.8729, + "step": 31610 + }, + { + "epoch": 1.18, + "learning_rate": 8.823966972886526e-06, + "loss": 1.8657, + "step": 31620 + }, + { + "epoch": 1.18, + "learning_rate": 8.82359504593298e-06, + "loss": 1.7425, + "step": 31630 + }, + { + "epoch": 1.18, + "learning_rate": 8.823223118979433e-06, + "loss": 1.6837, + "step": 31640 + }, + { + "epoch": 1.18, + "learning_rate": 8.822851192025887e-06, + "loss": 1.7687, + "step": 31650 + }, + { + "epoch": 1.18, + "learning_rate": 8.82247926507234e-06, + "loss": 1.7802, + "step": 31660 + }, + { + "epoch": 1.18, + "learning_rate": 8.822107338118794e-06, + "loss": 1.8898, + "step": 31670 + }, + { + "epoch": 1.18, + "learning_rate": 8.821735411165247e-06, + "loss": 1.8314, + "step": 31680 + }, + { + "epoch": 1.18, + "learning_rate": 8.8213634842117e-06, + "loss": 1.8852, + "step": 31690 + }, + { + "epoch": 1.18, + "learning_rate": 8.820991557258156e-06, + "loss": 1.8397, + "step": 31700 + }, + { + "epoch": 1.18, + "eval_loss": 1.7573708295822144, + "eval_runtime": 16.8273, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 31700 + }, + { + "epoch": 1.18, + "learning_rate": 8.82061963030461e-06, + "loss": 1.9022, + "step": 31710 + }, + { + "epoch": 1.18, + "learning_rate": 8.820247703351063e-06, + "loss": 1.7501, + "step": 31720 + }, + { + "epoch": 1.18, + "learning_rate": 8.819875776397516e-06, + "loss": 1.6574, + "step": 31730 + }, + { + "epoch": 1.18, + "learning_rate": 8.81950384944397e-06, + "loss": 1.8282, + "step": 31740 + }, + { + "epoch": 1.18, + "learning_rate": 8.819131922490423e-06, + "loss": 1.9165, + "step": 31750 + }, + { + "epoch": 1.18, + "learning_rate": 8.818759995536878e-06, + "loss": 1.8906, + "step": 31760 + }, + { + "epoch": 1.18, + "learning_rate": 8.818388068583332e-06, + "loss": 1.759, + "step": 31770 + }, + { + "epoch": 1.18, + "learning_rate": 8.818016141629785e-06, + "loss": 1.819, + "step": 31780 + }, + { + "epoch": 1.18, + "learning_rate": 8.817644214676239e-06, + "loss": 1.907, + "step": 31790 + }, + { + "epoch": 1.18, + "learning_rate": 8.817272287722692e-06, + "loss": 1.7188, + "step": 31800 + }, + { + "epoch": 1.18, + "eval_loss": 1.7565218210220337, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 31800 + }, + { + "epoch": 1.18, + "learning_rate": 8.816900360769146e-06, + "loss": 1.8248, + "step": 31810 + }, + { + "epoch": 1.18, + "learning_rate": 8.816528433815599e-06, + "loss": 1.8436, + "step": 31820 + }, + { + "epoch": 1.18, + "learning_rate": 8.816156506862052e-06, + "loss": 1.7302, + "step": 31830 + }, + { + "epoch": 1.18, + "learning_rate": 8.815784579908506e-06, + "loss": 1.8723, + "step": 31840 + }, + { + "epoch": 1.18, + "learning_rate": 8.81541265295496e-06, + "loss": 1.8392, + "step": 31850 + }, + { + "epoch": 1.18, + "learning_rate": 8.815040726001413e-06, + "loss": 1.8441, + "step": 31860 + }, + { + "epoch": 1.19, + "learning_rate": 8.814668799047868e-06, + "loss": 1.7972, + "step": 31870 + }, + { + "epoch": 1.19, + "learning_rate": 8.814296872094321e-06, + "loss": 1.6739, + "step": 31880 + }, + { + "epoch": 1.19, + "learning_rate": 8.813924945140775e-06, + "loss": 1.7266, + "step": 31890 + }, + { + "epoch": 1.19, + "learning_rate": 8.813553018187228e-06, + "loss": 1.7287, + "step": 31900 + }, + { + "epoch": 1.19, + "eval_loss": 1.7562751770019531, + "eval_runtime": 16.8283, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 31900 + }, + { + "epoch": 1.19, + "learning_rate": 8.813181091233682e-06, + "loss": 1.774, + "step": 31910 + }, + { + "epoch": 1.19, + "learning_rate": 8.812809164280135e-06, + "loss": 1.8328, + "step": 31920 + }, + { + "epoch": 1.19, + "learning_rate": 8.81243723732659e-06, + "loss": 1.7884, + "step": 31930 + }, + { + "epoch": 1.19, + "learning_rate": 8.812065310373044e-06, + "loss": 1.7875, + "step": 31940 + }, + { + "epoch": 1.19, + "learning_rate": 8.811693383419497e-06, + "loss": 1.8948, + "step": 31950 + }, + { + "epoch": 1.19, + "learning_rate": 8.811321456465951e-06, + "loss": 1.8378, + "step": 31960 + }, + { + "epoch": 1.19, + "learning_rate": 8.810949529512404e-06, + "loss": 1.8517, + "step": 31970 + }, + { + "epoch": 1.19, + "learning_rate": 8.810577602558858e-06, + "loss": 1.8579, + "step": 31980 + }, + { + "epoch": 1.19, + "learning_rate": 8.810205675605313e-06, + "loss": 1.8216, + "step": 31990 + }, + { + "epoch": 1.19, + "learning_rate": 8.809833748651766e-06, + "loss": 1.724, + "step": 32000 + }, + { + "epoch": 1.19, + "eval_loss": 1.7556935548782349, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 32000 + }, + { + "epoch": 1.19, + "learning_rate": 8.80946182169822e-06, + "loss": 1.8475, + "step": 32010 + }, + { + "epoch": 1.19, + "learning_rate": 8.809089894744672e-06, + "loss": 1.9655, + "step": 32020 + }, + { + "epoch": 1.19, + "learning_rate": 8.808717967791127e-06, + "loss": 1.6628, + "step": 32030 + }, + { + "epoch": 1.19, + "learning_rate": 8.80834604083758e-06, + "loss": 1.8465, + "step": 32040 + }, + { + "epoch": 1.19, + "learning_rate": 8.807974113884034e-06, + "loss": 1.8049, + "step": 32050 + }, + { + "epoch": 1.19, + "learning_rate": 8.807602186930487e-06, + "loss": 1.8011, + "step": 32060 + }, + { + "epoch": 1.19, + "learning_rate": 8.80723025997694e-06, + "loss": 1.7838, + "step": 32070 + }, + { + "epoch": 1.19, + "learning_rate": 8.806858333023394e-06, + "loss": 1.881, + "step": 32080 + }, + { + "epoch": 1.19, + "learning_rate": 8.80648640606985e-06, + "loss": 1.8123, + "step": 32090 + }, + { + "epoch": 1.19, + "learning_rate": 8.806114479116303e-06, + "loss": 1.963, + "step": 32100 + }, + { + "epoch": 1.19, + "eval_loss": 1.755884051322937, + "eval_runtime": 16.7994, + "eval_samples_per_second": 59.526, + "eval_steps_per_second": 3.75, + "step": 32100 + }, + { + "epoch": 1.19, + "learning_rate": 8.805742552162756e-06, + "loss": 1.8265, + "step": 32110 + }, + { + "epoch": 1.19, + "learning_rate": 8.80537062520921e-06, + "loss": 1.8039, + "step": 32120 + }, + { + "epoch": 1.2, + "learning_rate": 8.804998698255663e-06, + "loss": 1.8383, + "step": 32130 + }, + { + "epoch": 1.2, + "learning_rate": 8.804626771302117e-06, + "loss": 1.794, + "step": 32140 + }, + { + "epoch": 1.2, + "learning_rate": 8.804254844348572e-06, + "loss": 1.9747, + "step": 32150 + }, + { + "epoch": 1.2, + "learning_rate": 8.803882917395025e-06, + "loss": 1.7697, + "step": 32160 + }, + { + "epoch": 1.2, + "learning_rate": 8.803510990441479e-06, + "loss": 1.8025, + "step": 32170 + }, + { + "epoch": 1.2, + "learning_rate": 8.803139063487932e-06, + "loss": 1.9631, + "step": 32180 + }, + { + "epoch": 1.2, + "learning_rate": 8.802767136534385e-06, + "loss": 1.9078, + "step": 32190 + }, + { + "epoch": 1.2, + "learning_rate": 8.802395209580839e-06, + "loss": 1.8359, + "step": 32200 + }, + { + "epoch": 1.2, + "eval_loss": 1.7560189962387085, + "eval_runtime": 16.803, + "eval_samples_per_second": 59.513, + "eval_steps_per_second": 3.749, + "step": 32200 + }, + { + "epoch": 1.2, + "learning_rate": 8.802023282627292e-06, + "loss": 1.8499, + "step": 32210 + }, + { + "epoch": 1.2, + "learning_rate": 8.801651355673746e-06, + "loss": 1.7355, + "step": 32220 + }, + { + "epoch": 1.2, + "learning_rate": 8.8012794287202e-06, + "loss": 1.7763, + "step": 32230 + }, + { + "epoch": 1.2, + "learning_rate": 8.800907501766653e-06, + "loss": 1.8326, + "step": 32240 + }, + { + "epoch": 1.2, + "learning_rate": 8.800535574813108e-06, + "loss": 1.7525, + "step": 32250 + }, + { + "epoch": 1.2, + "learning_rate": 8.800163647859561e-06, + "loss": 1.8151, + "step": 32260 + }, + { + "epoch": 1.2, + "learning_rate": 8.799791720906015e-06, + "loss": 1.9217, + "step": 32270 + }, + { + "epoch": 1.2, + "learning_rate": 8.799419793952468e-06, + "loss": 1.948, + "step": 32280 + }, + { + "epoch": 1.2, + "learning_rate": 8.799047866998922e-06, + "loss": 1.855, + "step": 32290 + }, + { + "epoch": 1.2, + "learning_rate": 8.798675940045375e-06, + "loss": 1.7519, + "step": 32300 + }, + { + "epoch": 1.2, + "eval_loss": 1.7549238204956055, + "eval_runtime": 16.7995, + "eval_samples_per_second": 59.525, + "eval_steps_per_second": 3.75, + "step": 32300 + }, + { + "epoch": 1.2, + "learning_rate": 8.79830401309183e-06, + "loss": 1.8451, + "step": 32310 + }, + { + "epoch": 1.2, + "learning_rate": 8.797932086138284e-06, + "loss": 1.7905, + "step": 32320 + }, + { + "epoch": 1.2, + "learning_rate": 8.797560159184737e-06, + "loss": 1.7587, + "step": 32330 + }, + { + "epoch": 1.2, + "learning_rate": 8.79718823223119e-06, + "loss": 1.8727, + "step": 32340 + }, + { + "epoch": 1.2, + "learning_rate": 8.796816305277644e-06, + "loss": 1.799, + "step": 32350 + }, + { + "epoch": 1.2, + "learning_rate": 8.796444378324098e-06, + "loss": 1.7966, + "step": 32360 + }, + { + "epoch": 1.2, + "learning_rate": 8.796072451370551e-06, + "loss": 1.9632, + "step": 32370 + }, + { + "epoch": 1.2, + "learning_rate": 8.795700524417006e-06, + "loss": 1.7558, + "step": 32380 + }, + { + "epoch": 1.2, + "learning_rate": 8.795328597463458e-06, + "loss": 2.007, + "step": 32390 + }, + { + "epoch": 1.21, + "learning_rate": 8.794956670509912e-06, + "loss": 1.8021, + "step": 32400 + }, + { + "epoch": 1.21, + "eval_loss": 1.75496506690979, + "eval_runtime": 16.8165, + "eval_samples_per_second": 59.465, + "eval_steps_per_second": 3.746, + "step": 32400 + }, + { + "epoch": 1.21, + "learning_rate": 8.794584743556365e-06, + "loss": 1.6991, + "step": 32410 + }, + { + "epoch": 1.21, + "learning_rate": 8.79421281660282e-06, + "loss": 1.7995, + "step": 32420 + }, + { + "epoch": 1.21, + "learning_rate": 8.793840889649274e-06, + "loss": 1.7877, + "step": 32430 + }, + { + "epoch": 1.21, + "learning_rate": 8.793468962695727e-06, + "loss": 1.8138, + "step": 32440 + }, + { + "epoch": 1.21, + "learning_rate": 8.79309703574218e-06, + "loss": 1.8185, + "step": 32450 + }, + { + "epoch": 1.21, + "learning_rate": 8.792725108788634e-06, + "loss": 1.7894, + "step": 32460 + }, + { + "epoch": 1.21, + "learning_rate": 8.792353181835087e-06, + "loss": 1.9822, + "step": 32470 + }, + { + "epoch": 1.21, + "learning_rate": 8.791981254881543e-06, + "loss": 1.8204, + "step": 32480 + }, + { + "epoch": 1.21, + "learning_rate": 8.791609327927996e-06, + "loss": 1.7832, + "step": 32490 + }, + { + "epoch": 1.21, + "learning_rate": 8.79123740097445e-06, + "loss": 1.7493, + "step": 32500 + }, + { + "epoch": 1.21, + "eval_loss": 1.7540111541748047, + "eval_runtime": 16.8174, + "eval_samples_per_second": 59.462, + "eval_steps_per_second": 3.746, + "step": 32500 + }, + { + "epoch": 1.21, + "learning_rate": 8.790865474020903e-06, + "loss": 1.7864, + "step": 32510 + }, + { + "epoch": 1.21, + "learning_rate": 8.790493547067356e-06, + "loss": 1.83, + "step": 32520 + }, + { + "epoch": 1.21, + "learning_rate": 8.79012162011381e-06, + "loss": 1.791, + "step": 32530 + }, + { + "epoch": 1.21, + "learning_rate": 8.789749693160265e-06, + "loss": 1.7509, + "step": 32540 + }, + { + "epoch": 1.21, + "learning_rate": 8.789377766206718e-06, + "loss": 1.8728, + "step": 32550 + }, + { + "epoch": 1.21, + "learning_rate": 8.789005839253172e-06, + "loss": 1.8193, + "step": 32560 + }, + { + "epoch": 1.21, + "learning_rate": 8.788633912299625e-06, + "loss": 1.8941, + "step": 32570 + }, + { + "epoch": 1.21, + "learning_rate": 8.788261985346079e-06, + "loss": 1.7268, + "step": 32580 + }, + { + "epoch": 1.21, + "learning_rate": 8.787890058392532e-06, + "loss": 1.9573, + "step": 32590 + }, + { + "epoch": 1.21, + "learning_rate": 8.787518131438986e-06, + "loss": 1.8647, + "step": 32600 + }, + { + "epoch": 1.21, + "eval_loss": 1.7548190355300903, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 32600 + }, + { + "epoch": 1.21, + "learning_rate": 8.78714620448544e-06, + "loss": 1.9246, + "step": 32610 + }, + { + "epoch": 1.21, + "learning_rate": 8.786774277531893e-06, + "loss": 1.7682, + "step": 32620 + }, + { + "epoch": 1.21, + "learning_rate": 8.786402350578346e-06, + "loss": 1.7206, + "step": 32630 + }, + { + "epoch": 1.21, + "learning_rate": 8.786030423624801e-06, + "loss": 1.835, + "step": 32640 + }, + { + "epoch": 1.21, + "learning_rate": 8.785658496671255e-06, + "loss": 1.8536, + "step": 32650 + }, + { + "epoch": 1.21, + "learning_rate": 8.785286569717708e-06, + "loss": 1.7028, + "step": 32660 + }, + { + "epoch": 1.22, + "learning_rate": 8.784914642764162e-06, + "loss": 1.8146, + "step": 32670 + }, + { + "epoch": 1.22, + "learning_rate": 8.784542715810615e-06, + "loss": 1.7812, + "step": 32680 + }, + { + "epoch": 1.22, + "learning_rate": 8.784170788857069e-06, + "loss": 1.9088, + "step": 32690 + }, + { + "epoch": 1.22, + "learning_rate": 8.783798861903524e-06, + "loss": 1.9249, + "step": 32700 + }, + { + "epoch": 1.22, + "eval_loss": 1.754367470741272, + "eval_runtime": 16.8072, + "eval_samples_per_second": 59.498, + "eval_steps_per_second": 3.748, + "step": 32700 + }, + { + "epoch": 1.22, + "learning_rate": 8.783426934949977e-06, + "loss": 1.8224, + "step": 32710 + }, + { + "epoch": 1.22, + "learning_rate": 8.78305500799643e-06, + "loss": 1.7298, + "step": 32720 + }, + { + "epoch": 1.22, + "learning_rate": 8.782683081042884e-06, + "loss": 1.7542, + "step": 32730 + }, + { + "epoch": 1.22, + "learning_rate": 8.782311154089338e-06, + "loss": 1.8712, + "step": 32740 + }, + { + "epoch": 1.22, + "learning_rate": 8.781939227135791e-06, + "loss": 1.7486, + "step": 32750 + }, + { + "epoch": 1.22, + "learning_rate": 8.781567300182246e-06, + "loss": 1.7946, + "step": 32760 + }, + { + "epoch": 1.22, + "learning_rate": 8.781195373228698e-06, + "loss": 1.7517, + "step": 32770 + }, + { + "epoch": 1.22, + "learning_rate": 8.780823446275151e-06, + "loss": 1.8159, + "step": 32780 + }, + { + "epoch": 1.22, + "learning_rate": 8.780451519321605e-06, + "loss": 1.7892, + "step": 32790 + }, + { + "epoch": 1.22, + "learning_rate": 8.78007959236806e-06, + "loss": 1.8052, + "step": 32800 + }, + { + "epoch": 1.22, + "eval_loss": 1.7540792226791382, + "eval_runtime": 16.8182, + "eval_samples_per_second": 59.459, + "eval_steps_per_second": 3.746, + "step": 32800 + }, + { + "epoch": 1.22, + "learning_rate": 8.779707665414514e-06, + "loss": 1.8243, + "step": 32810 + }, + { + "epoch": 1.22, + "learning_rate": 8.779335738460967e-06, + "loss": 1.6871, + "step": 32820 + }, + { + "epoch": 1.22, + "learning_rate": 8.77896381150742e-06, + "loss": 1.8046, + "step": 32830 + }, + { + "epoch": 1.22, + "learning_rate": 8.778591884553874e-06, + "loss": 1.7934, + "step": 32840 + }, + { + "epoch": 1.22, + "learning_rate": 8.778219957600327e-06, + "loss": 1.8525, + "step": 32850 + }, + { + "epoch": 1.22, + "learning_rate": 8.777848030646783e-06, + "loss": 1.7153, + "step": 32860 + }, + { + "epoch": 1.22, + "learning_rate": 8.777476103693236e-06, + "loss": 1.7039, + "step": 32870 + }, + { + "epoch": 1.22, + "learning_rate": 8.77710417673969e-06, + "loss": 1.8997, + "step": 32880 + }, + { + "epoch": 1.22, + "learning_rate": 8.776732249786143e-06, + "loss": 1.8224, + "step": 32890 + }, + { + "epoch": 1.22, + "learning_rate": 8.776360322832596e-06, + "loss": 1.7905, + "step": 32900 + }, + { + "epoch": 1.22, + "eval_loss": 1.7529939413070679, + "eval_runtime": 16.8392, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 32900 + }, + { + "epoch": 1.22, + "learning_rate": 8.77598839587905e-06, + "loss": 1.7959, + "step": 32910 + }, + { + "epoch": 1.22, + "learning_rate": 8.775616468925505e-06, + "loss": 1.7686, + "step": 32920 + }, + { + "epoch": 1.22, + "learning_rate": 8.775244541971958e-06, + "loss": 1.6518, + "step": 32930 + }, + { + "epoch": 1.23, + "learning_rate": 8.774872615018412e-06, + "loss": 1.9596, + "step": 32940 + }, + { + "epoch": 1.23, + "learning_rate": 8.774500688064865e-06, + "loss": 1.8919, + "step": 32950 + }, + { + "epoch": 1.23, + "learning_rate": 8.774128761111319e-06, + "loss": 1.739, + "step": 32960 + }, + { + "epoch": 1.23, + "learning_rate": 8.773756834157772e-06, + "loss": 1.7116, + "step": 32970 + }, + { + "epoch": 1.23, + "learning_rate": 8.773384907204226e-06, + "loss": 1.7331, + "step": 32980 + }, + { + "epoch": 1.23, + "learning_rate": 8.77301298025068e-06, + "loss": 2.0116, + "step": 32990 + }, + { + "epoch": 1.23, + "learning_rate": 8.772641053297133e-06, + "loss": 1.8763, + "step": 33000 + }, + { + "epoch": 1.23, + "eval_loss": 1.7526432275772095, + "eval_runtime": 16.808, + "eval_samples_per_second": 59.495, + "eval_steps_per_second": 3.748, + "step": 33000 + }, + { + "epoch": 1.23, + "learning_rate": 8.772269126343586e-06, + "loss": 1.8185, + "step": 33010 + }, + { + "epoch": 1.23, + "learning_rate": 8.77189719939004e-06, + "loss": 1.8436, + "step": 33020 + }, + { + "epoch": 1.23, + "learning_rate": 8.771525272436495e-06, + "loss": 1.9029, + "step": 33030 + }, + { + "epoch": 1.23, + "learning_rate": 8.771153345482948e-06, + "loss": 1.9445, + "step": 33040 + }, + { + "epoch": 1.23, + "learning_rate": 8.770781418529402e-06, + "loss": 1.9523, + "step": 33050 + }, + { + "epoch": 1.23, + "learning_rate": 8.770409491575855e-06, + "loss": 1.8365, + "step": 33060 + }, + { + "epoch": 1.23, + "learning_rate": 8.770037564622309e-06, + "loss": 1.9518, + "step": 33070 + }, + { + "epoch": 1.23, + "learning_rate": 8.769665637668762e-06, + "loss": 1.8705, + "step": 33080 + }, + { + "epoch": 1.23, + "learning_rate": 8.769293710715217e-06, + "loss": 1.8705, + "step": 33090 + }, + { + "epoch": 1.23, + "learning_rate": 8.76892178376167e-06, + "loss": 1.8234, + "step": 33100 + }, + { + "epoch": 1.23, + "eval_loss": 1.7537662982940674, + "eval_runtime": 16.8375, + "eval_samples_per_second": 59.391, + "eval_steps_per_second": 3.742, + "step": 33100 + }, + { + "epoch": 1.23, + "learning_rate": 8.768549856808124e-06, + "loss": 1.9401, + "step": 33110 + }, + { + "epoch": 1.23, + "learning_rate": 8.768177929854578e-06, + "loss": 1.7917, + "step": 33120 + }, + { + "epoch": 1.23, + "learning_rate": 8.767806002901031e-06, + "loss": 1.8748, + "step": 33130 + }, + { + "epoch": 1.23, + "learning_rate": 8.767434075947484e-06, + "loss": 1.8565, + "step": 33140 + }, + { + "epoch": 1.23, + "learning_rate": 8.767062148993938e-06, + "loss": 1.779, + "step": 33150 + }, + { + "epoch": 1.23, + "learning_rate": 8.766690222040391e-06, + "loss": 1.7943, + "step": 33160 + }, + { + "epoch": 1.23, + "learning_rate": 8.766318295086845e-06, + "loss": 1.7277, + "step": 33170 + }, + { + "epoch": 1.23, + "learning_rate": 8.765946368133298e-06, + "loss": 1.6628, + "step": 33180 + }, + { + "epoch": 1.23, + "learning_rate": 8.765574441179753e-06, + "loss": 1.9165, + "step": 33190 + }, + { + "epoch": 1.23, + "learning_rate": 8.765202514226207e-06, + "loss": 1.7199, + "step": 33200 + }, + { + "epoch": 1.23, + "eval_loss": 1.7529860734939575, + "eval_runtime": 16.8287, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 33200 + }, + { + "epoch": 1.24, + "learning_rate": 8.76483058727266e-06, + "loss": 1.9166, + "step": 33210 + }, + { + "epoch": 1.24, + "learning_rate": 8.764458660319114e-06, + "loss": 1.7671, + "step": 33220 + }, + { + "epoch": 1.24, + "learning_rate": 8.764086733365567e-06, + "loss": 1.9206, + "step": 33230 + }, + { + "epoch": 1.24, + "learning_rate": 8.76371480641202e-06, + "loss": 1.7699, + "step": 33240 + }, + { + "epoch": 1.24, + "learning_rate": 8.763342879458476e-06, + "loss": 1.774, + "step": 33250 + }, + { + "epoch": 1.24, + "learning_rate": 8.76297095250493e-06, + "loss": 1.8494, + "step": 33260 + }, + { + "epoch": 1.24, + "learning_rate": 8.762599025551383e-06, + "loss": 1.8029, + "step": 33270 + }, + { + "epoch": 1.24, + "learning_rate": 8.762227098597836e-06, + "loss": 1.8235, + "step": 33280 + }, + { + "epoch": 1.24, + "learning_rate": 8.76185517164429e-06, + "loss": 1.8397, + "step": 33290 + }, + { + "epoch": 1.24, + "learning_rate": 8.761483244690743e-06, + "loss": 1.7483, + "step": 33300 + }, + { + "epoch": 1.24, + "eval_loss": 1.7524428367614746, + "eval_runtime": 16.8283, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 33300 + }, + { + "epoch": 1.24, + "learning_rate": 8.761111317737198e-06, + "loss": 1.8857, + "step": 33310 + }, + { + "epoch": 1.24, + "learning_rate": 8.760739390783652e-06, + "loss": 1.875, + "step": 33320 + }, + { + "epoch": 1.24, + "learning_rate": 8.760367463830104e-06, + "loss": 1.8538, + "step": 33330 + }, + { + "epoch": 1.24, + "learning_rate": 8.759995536876557e-06, + "loss": 1.8328, + "step": 33340 + }, + { + "epoch": 1.24, + "learning_rate": 8.759623609923012e-06, + "loss": 1.7843, + "step": 33350 + }, + { + "epoch": 1.24, + "learning_rate": 8.759251682969466e-06, + "loss": 1.812, + "step": 33360 + }, + { + "epoch": 1.24, + "learning_rate": 8.758879756015919e-06, + "loss": 1.721, + "step": 33370 + }, + { + "epoch": 1.24, + "learning_rate": 8.758507829062373e-06, + "loss": 1.8073, + "step": 33380 + }, + { + "epoch": 1.24, + "learning_rate": 8.758135902108826e-06, + "loss": 1.7057, + "step": 33390 + }, + { + "epoch": 1.24, + "learning_rate": 8.75776397515528e-06, + "loss": 1.8446, + "step": 33400 + }, + { + "epoch": 1.24, + "eval_loss": 1.7521425485610962, + "eval_runtime": 16.8116, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 33400 + }, + { + "epoch": 1.24, + "learning_rate": 8.757392048201735e-06, + "loss": 1.7289, + "step": 33410 + }, + { + "epoch": 1.24, + "learning_rate": 8.757020121248188e-06, + "loss": 1.8526, + "step": 33420 + }, + { + "epoch": 1.24, + "learning_rate": 8.756648194294642e-06, + "loss": 1.8331, + "step": 33430 + }, + { + "epoch": 1.24, + "learning_rate": 8.756276267341095e-06, + "loss": 1.812, + "step": 33440 + }, + { + "epoch": 1.24, + "learning_rate": 8.755904340387548e-06, + "loss": 1.915, + "step": 33450 + }, + { + "epoch": 1.24, + "learning_rate": 8.755532413434002e-06, + "loss": 1.8434, + "step": 33460 + }, + { + "epoch": 1.24, + "learning_rate": 8.755160486480457e-06, + "loss": 1.7697, + "step": 33470 + }, + { + "epoch": 1.25, + "learning_rate": 8.75478855952691e-06, + "loss": 1.9171, + "step": 33480 + }, + { + "epoch": 1.25, + "learning_rate": 8.754416632573364e-06, + "loss": 1.7956, + "step": 33490 + }, + { + "epoch": 1.25, + "learning_rate": 8.754044705619817e-06, + "loss": 1.8251, + "step": 33500 + }, + { + "epoch": 1.25, + "eval_loss": 1.7532259225845337, + "eval_runtime": 16.8196, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 33500 + }, + { + "epoch": 1.25, + "learning_rate": 8.753672778666271e-06, + "loss": 1.8851, + "step": 33510 + }, + { + "epoch": 1.25, + "learning_rate": 8.753300851712724e-06, + "loss": 1.6508, + "step": 33520 + }, + { + "epoch": 1.25, + "learning_rate": 8.752928924759178e-06, + "loss": 1.8186, + "step": 33530 + }, + { + "epoch": 1.25, + "learning_rate": 8.752556997805631e-06, + "loss": 1.6872, + "step": 33540 + }, + { + "epoch": 1.25, + "learning_rate": 8.752185070852085e-06, + "loss": 1.7254, + "step": 33550 + }, + { + "epoch": 1.25, + "learning_rate": 8.751813143898538e-06, + "loss": 1.8564, + "step": 33560 + }, + { + "epoch": 1.25, + "learning_rate": 8.751441216944992e-06, + "loss": 1.7559, + "step": 33570 + }, + { + "epoch": 1.25, + "learning_rate": 8.751069289991447e-06, + "loss": 1.7415, + "step": 33580 + }, + { + "epoch": 1.25, + "learning_rate": 8.7506973630379e-06, + "loss": 1.8275, + "step": 33590 + }, + { + "epoch": 1.25, + "learning_rate": 8.750325436084354e-06, + "loss": 1.7269, + "step": 33600 + }, + { + "epoch": 1.25, + "eval_loss": 1.751334547996521, + "eval_runtime": 16.7962, + "eval_samples_per_second": 59.537, + "eval_steps_per_second": 3.751, + "step": 33600 + }, + { + "epoch": 1.25, + "learning_rate": 8.749953509130807e-06, + "loss": 1.8598, + "step": 33610 + }, + { + "epoch": 1.25, + "learning_rate": 8.74958158217726e-06, + "loss": 1.8249, + "step": 33620 + }, + { + "epoch": 1.25, + "learning_rate": 8.749209655223714e-06, + "loss": 1.7529, + "step": 33630 + }, + { + "epoch": 1.25, + "learning_rate": 8.74883772827017e-06, + "loss": 1.8805, + "step": 33640 + }, + { + "epoch": 1.25, + "learning_rate": 8.748465801316623e-06, + "loss": 1.7774, + "step": 33650 + }, + { + "epoch": 1.25, + "learning_rate": 8.748093874363076e-06, + "loss": 1.8049, + "step": 33660 + }, + { + "epoch": 1.25, + "learning_rate": 8.74772194740953e-06, + "loss": 1.7585, + "step": 33670 + }, + { + "epoch": 1.25, + "learning_rate": 8.747350020455983e-06, + "loss": 1.7802, + "step": 33680 + }, + { + "epoch": 1.25, + "learning_rate": 8.746978093502437e-06, + "loss": 1.9241, + "step": 33690 + }, + { + "epoch": 1.25, + "learning_rate": 8.746606166548892e-06, + "loss": 1.7992, + "step": 33700 + }, + { + "epoch": 1.25, + "eval_loss": 1.7513197660446167, + "eval_runtime": 16.821, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 33700 + }, + { + "epoch": 1.25, + "learning_rate": 8.746234239595343e-06, + "loss": 1.7182, + "step": 33710 + }, + { + "epoch": 1.25, + "learning_rate": 8.745862312641797e-06, + "loss": 1.8125, + "step": 33720 + }, + { + "epoch": 1.25, + "learning_rate": 8.74549038568825e-06, + "loss": 1.747, + "step": 33730 + }, + { + "epoch": 1.25, + "learning_rate": 8.745118458734706e-06, + "loss": 1.8149, + "step": 33740 + }, + { + "epoch": 1.26, + "learning_rate": 8.744746531781159e-06, + "loss": 1.74, + "step": 33750 + }, + { + "epoch": 1.26, + "learning_rate": 8.744374604827612e-06, + "loss": 1.807, + "step": 33760 + }, + { + "epoch": 1.26, + "learning_rate": 8.744002677874066e-06, + "loss": 1.6791, + "step": 33770 + }, + { + "epoch": 1.26, + "learning_rate": 8.74363075092052e-06, + "loss": 1.7316, + "step": 33780 + }, + { + "epoch": 1.26, + "learning_rate": 8.743258823966973e-06, + "loss": 1.7697, + "step": 33790 + }, + { + "epoch": 1.26, + "learning_rate": 8.742886897013428e-06, + "loss": 1.8832, + "step": 33800 + }, + { + "epoch": 1.26, + "eval_loss": 1.7519599199295044, + "eval_runtime": 16.8269, + "eval_samples_per_second": 59.429, + "eval_steps_per_second": 3.744, + "step": 33800 + }, + { + "epoch": 1.26, + "learning_rate": 8.742514970059881e-06, + "loss": 2.0063, + "step": 33810 + }, + { + "epoch": 1.26, + "learning_rate": 8.742143043106335e-06, + "loss": 1.7246, + "step": 33820 + }, + { + "epoch": 1.26, + "learning_rate": 8.741771116152788e-06, + "loss": 1.8701, + "step": 33830 + }, + { + "epoch": 1.26, + "learning_rate": 8.741399189199242e-06, + "loss": 1.8724, + "step": 33840 + }, + { + "epoch": 1.26, + "learning_rate": 8.741027262245695e-06, + "loss": 1.7644, + "step": 33850 + }, + { + "epoch": 1.26, + "learning_rate": 8.74065533529215e-06, + "loss": 1.8499, + "step": 33860 + }, + { + "epoch": 1.26, + "learning_rate": 8.740283408338604e-06, + "loss": 1.8236, + "step": 33870 + }, + { + "epoch": 1.26, + "learning_rate": 8.739911481385057e-06, + "loss": 1.8289, + "step": 33880 + }, + { + "epoch": 1.26, + "learning_rate": 8.73953955443151e-06, + "loss": 1.9458, + "step": 33890 + }, + { + "epoch": 1.26, + "learning_rate": 8.739167627477964e-06, + "loss": 1.7637, + "step": 33900 + }, + { + "epoch": 1.26, + "eval_loss": 1.7507827281951904, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 33900 + }, + { + "epoch": 1.26, + "learning_rate": 8.738795700524418e-06, + "loss": 2.0177, + "step": 33910 + }, + { + "epoch": 1.26, + "learning_rate": 8.738423773570871e-06, + "loss": 1.8888, + "step": 33920 + }, + { + "epoch": 1.26, + "learning_rate": 8.738051846617325e-06, + "loss": 2.1566, + "step": 33930 + }, + { + "epoch": 1.26, + "learning_rate": 8.737679919663778e-06, + "loss": 1.8907, + "step": 33940 + }, + { + "epoch": 1.26, + "learning_rate": 8.737307992710232e-06, + "loss": 1.8706, + "step": 33950 + }, + { + "epoch": 1.26, + "learning_rate": 8.736936065756687e-06, + "loss": 1.8097, + "step": 33960 + }, + { + "epoch": 1.26, + "learning_rate": 8.73656413880314e-06, + "loss": 1.7636, + "step": 33970 + }, + { + "epoch": 1.26, + "learning_rate": 8.736192211849594e-06, + "loss": 1.8898, + "step": 33980 + }, + { + "epoch": 1.26, + "learning_rate": 8.735820284896047e-06, + "loss": 1.8192, + "step": 33990 + }, + { + "epoch": 1.26, + "learning_rate": 8.7354483579425e-06, + "loss": 1.8002, + "step": 34000 + }, + { + "epoch": 1.26, + "eval_loss": 1.7509299516677856, + "eval_runtime": 16.8175, + "eval_samples_per_second": 59.462, + "eval_steps_per_second": 3.746, + "step": 34000 + }, + { + "epoch": 1.26, + "learning_rate": 8.735076430988954e-06, + "loss": 1.8998, + "step": 34010 + }, + { + "epoch": 1.27, + "learning_rate": 8.73470450403541e-06, + "loss": 1.7828, + "step": 34020 + }, + { + "epoch": 1.27, + "learning_rate": 8.734332577081863e-06, + "loss": 1.8041, + "step": 34030 + }, + { + "epoch": 1.27, + "learning_rate": 8.733960650128316e-06, + "loss": 1.7872, + "step": 34040 + }, + { + "epoch": 1.27, + "learning_rate": 8.73358872317477e-06, + "loss": 1.8565, + "step": 34050 + }, + { + "epoch": 1.27, + "learning_rate": 8.733216796221223e-06, + "loss": 1.676, + "step": 34060 + }, + { + "epoch": 1.27, + "learning_rate": 8.732844869267676e-06, + "loss": 1.8513, + "step": 34070 + }, + { + "epoch": 1.27, + "learning_rate": 8.73247294231413e-06, + "loss": 1.7009, + "step": 34080 + }, + { + "epoch": 1.27, + "learning_rate": 8.732101015360583e-06, + "loss": 1.8468, + "step": 34090 + }, + { + "epoch": 1.27, + "learning_rate": 8.731729088407037e-06, + "loss": 1.7994, + "step": 34100 + }, + { + "epoch": 1.27, + "eval_loss": 1.7500978708267212, + "eval_runtime": 16.8218, + "eval_samples_per_second": 59.447, + "eval_steps_per_second": 3.745, + "step": 34100 + }, + { + "epoch": 1.27, + "learning_rate": 8.73135716145349e-06, + "loss": 1.8929, + "step": 34110 + }, + { + "epoch": 1.27, + "learning_rate": 8.730985234499945e-06, + "loss": 1.7394, + "step": 34120 + }, + { + "epoch": 1.27, + "learning_rate": 8.730613307546399e-06, + "loss": 1.751, + "step": 34130 + }, + { + "epoch": 1.27, + "learning_rate": 8.730241380592852e-06, + "loss": 1.7254, + "step": 34140 + }, + { + "epoch": 1.27, + "learning_rate": 8.729869453639306e-06, + "loss": 1.8289, + "step": 34150 + }, + { + "epoch": 1.27, + "learning_rate": 8.72949752668576e-06, + "loss": 1.8351, + "step": 34160 + }, + { + "epoch": 1.27, + "learning_rate": 8.729125599732213e-06, + "loss": 1.7805, + "step": 34170 + }, + { + "epoch": 1.27, + "learning_rate": 8.728753672778666e-06, + "loss": 1.8127, + "step": 34180 + }, + { + "epoch": 1.27, + "learning_rate": 8.728381745825121e-06, + "loss": 1.7335, + "step": 34190 + }, + { + "epoch": 1.27, + "learning_rate": 8.728009818871575e-06, + "loss": 1.6795, + "step": 34200 + }, + { + "epoch": 1.27, + "eval_loss": 1.7500282526016235, + "eval_runtime": 16.837, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 34200 + }, + { + "epoch": 1.27, + "learning_rate": 8.727637891918028e-06, + "loss": 1.8947, + "step": 34210 + }, + { + "epoch": 1.27, + "learning_rate": 8.727265964964482e-06, + "loss": 1.7922, + "step": 34220 + }, + { + "epoch": 1.27, + "learning_rate": 8.726894038010935e-06, + "loss": 1.7566, + "step": 34230 + }, + { + "epoch": 1.27, + "learning_rate": 8.726522111057389e-06, + "loss": 1.8041, + "step": 34240 + }, + { + "epoch": 1.27, + "learning_rate": 8.726150184103844e-06, + "loss": 1.7756, + "step": 34250 + }, + { + "epoch": 1.27, + "learning_rate": 8.725778257150297e-06, + "loss": 1.6881, + "step": 34260 + }, + { + "epoch": 1.27, + "learning_rate": 8.725406330196749e-06, + "loss": 1.8434, + "step": 34270 + }, + { + "epoch": 1.27, + "learning_rate": 8.725034403243203e-06, + "loss": 1.7819, + "step": 34280 + }, + { + "epoch": 1.28, + "learning_rate": 8.724662476289658e-06, + "loss": 1.8007, + "step": 34290 + }, + { + "epoch": 1.28, + "learning_rate": 8.724290549336111e-06, + "loss": 1.8303, + "step": 34300 + }, + { + "epoch": 1.28, + "eval_loss": 1.7502983808517456, + "eval_runtime": 16.8136, + "eval_samples_per_second": 59.476, + "eval_steps_per_second": 3.747, + "step": 34300 + }, + { + "epoch": 1.28, + "learning_rate": 8.723918622382565e-06, + "loss": 1.8971, + "step": 34310 + }, + { + "epoch": 1.28, + "learning_rate": 8.723546695429018e-06, + "loss": 1.8131, + "step": 34320 + }, + { + "epoch": 1.28, + "learning_rate": 8.723174768475471e-06, + "loss": 1.7532, + "step": 34330 + }, + { + "epoch": 1.28, + "learning_rate": 8.722802841521925e-06, + "loss": 1.7841, + "step": 34340 + }, + { + "epoch": 1.28, + "learning_rate": 8.72243091456838e-06, + "loss": 1.8342, + "step": 34350 + }, + { + "epoch": 1.28, + "learning_rate": 8.722058987614834e-06, + "loss": 1.8208, + "step": 34360 + }, + { + "epoch": 1.28, + "learning_rate": 8.721687060661287e-06, + "loss": 1.954, + "step": 34370 + }, + { + "epoch": 1.28, + "learning_rate": 8.72131513370774e-06, + "loss": 1.8173, + "step": 34380 + }, + { + "epoch": 1.28, + "learning_rate": 8.720943206754194e-06, + "loss": 1.8243, + "step": 34390 + }, + { + "epoch": 1.28, + "learning_rate": 8.720571279800647e-06, + "loss": 1.9615, + "step": 34400 + }, + { + "epoch": 1.28, + "eval_loss": 1.7490496635437012, + "eval_runtime": 16.8149, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 34400 + }, + { + "epoch": 1.28, + "learning_rate": 8.720199352847103e-06, + "loss": 1.8015, + "step": 34410 + }, + { + "epoch": 1.28, + "learning_rate": 8.719827425893556e-06, + "loss": 1.7786, + "step": 34420 + }, + { + "epoch": 1.28, + "learning_rate": 8.71945549894001e-06, + "loss": 1.8585, + "step": 34430 + }, + { + "epoch": 1.28, + "learning_rate": 8.719083571986463e-06, + "loss": 1.7615, + "step": 34440 + }, + { + "epoch": 1.28, + "learning_rate": 8.718711645032916e-06, + "loss": 1.8394, + "step": 34450 + }, + { + "epoch": 1.28, + "learning_rate": 8.71833971807937e-06, + "loss": 1.8576, + "step": 34460 + }, + { + "epoch": 1.28, + "learning_rate": 8.717967791125823e-06, + "loss": 1.9351, + "step": 34470 + }, + { + "epoch": 1.28, + "learning_rate": 8.717595864172277e-06, + "loss": 1.7181, + "step": 34480 + }, + { + "epoch": 1.28, + "learning_rate": 8.71722393721873e-06, + "loss": 1.8567, + "step": 34490 + }, + { + "epoch": 1.28, + "learning_rate": 8.716852010265184e-06, + "loss": 1.8016, + "step": 34500 + }, + { + "epoch": 1.28, + "eval_loss": 1.7489680051803589, + "eval_runtime": 16.8065, + "eval_samples_per_second": 59.501, + "eval_steps_per_second": 3.749, + "step": 34500 + }, + { + "epoch": 1.28, + "learning_rate": 8.716480083311639e-06, + "loss": 1.9537, + "step": 34510 + }, + { + "epoch": 1.28, + "learning_rate": 8.716108156358092e-06, + "loss": 1.8657, + "step": 34520 + }, + { + "epoch": 1.28, + "learning_rate": 8.715736229404546e-06, + "loss": 1.8308, + "step": 34530 + }, + { + "epoch": 1.28, + "learning_rate": 8.715364302451e-06, + "loss": 1.7062, + "step": 34540 + }, + { + "epoch": 1.29, + "learning_rate": 8.714992375497453e-06, + "loss": 1.8429, + "step": 34550 + }, + { + "epoch": 1.29, + "learning_rate": 8.714620448543906e-06, + "loss": 1.8695, + "step": 34560 + }, + { + "epoch": 1.29, + "learning_rate": 8.714248521590361e-06, + "loss": 1.925, + "step": 34570 + }, + { + "epoch": 1.29, + "learning_rate": 8.713876594636815e-06, + "loss": 1.6739, + "step": 34580 + }, + { + "epoch": 1.29, + "learning_rate": 8.713504667683268e-06, + "loss": 1.7942, + "step": 34590 + }, + { + "epoch": 1.29, + "learning_rate": 8.713132740729722e-06, + "loss": 1.9259, + "step": 34600 + }, + { + "epoch": 1.29, + "eval_loss": 1.7492693662643433, + "eval_runtime": 16.8163, + "eval_samples_per_second": 59.466, + "eval_steps_per_second": 3.746, + "step": 34600 + }, + { + "epoch": 1.29, + "learning_rate": 8.712760813776175e-06, + "loss": 1.8574, + "step": 34610 + }, + { + "epoch": 1.29, + "learning_rate": 8.712388886822629e-06, + "loss": 1.9088, + "step": 34620 + }, + { + "epoch": 1.29, + "learning_rate": 8.712016959869084e-06, + "loss": 1.8551, + "step": 34630 + }, + { + "epoch": 1.29, + "learning_rate": 8.711645032915537e-06, + "loss": 1.7997, + "step": 34640 + }, + { + "epoch": 1.29, + "learning_rate": 8.711273105961989e-06, + "loss": 1.8194, + "step": 34650 + }, + { + "epoch": 1.29, + "learning_rate": 8.710901179008442e-06, + "loss": 1.8817, + "step": 34660 + }, + { + "epoch": 1.29, + "learning_rate": 8.710529252054898e-06, + "loss": 1.7161, + "step": 34670 + }, + { + "epoch": 1.29, + "learning_rate": 8.710157325101351e-06, + "loss": 1.6912, + "step": 34680 + }, + { + "epoch": 1.29, + "learning_rate": 8.709785398147804e-06, + "loss": 1.7342, + "step": 34690 + }, + { + "epoch": 1.29, + "learning_rate": 8.709413471194258e-06, + "loss": 1.8237, + "step": 34700 + }, + { + "epoch": 1.29, + "eval_loss": 1.7485339641571045, + "eval_runtime": 16.8132, + "eval_samples_per_second": 59.477, + "eval_steps_per_second": 3.747, + "step": 34700 + }, + { + "epoch": 1.29, + "learning_rate": 8.709041544240711e-06, + "loss": 1.8734, + "step": 34710 + }, + { + "epoch": 1.29, + "learning_rate": 8.708669617287165e-06, + "loss": 1.8456, + "step": 34720 + }, + { + "epoch": 1.29, + "learning_rate": 8.708297690333618e-06, + "loss": 1.7393, + "step": 34730 + }, + { + "epoch": 1.29, + "learning_rate": 8.707925763380073e-06, + "loss": 1.8576, + "step": 34740 + }, + { + "epoch": 1.29, + "learning_rate": 8.707553836426527e-06, + "loss": 1.7772, + "step": 34750 + }, + { + "epoch": 1.29, + "learning_rate": 8.70718190947298e-06, + "loss": 1.7338, + "step": 34760 + }, + { + "epoch": 1.29, + "learning_rate": 8.706809982519434e-06, + "loss": 1.741, + "step": 34770 + }, + { + "epoch": 1.29, + "learning_rate": 8.706438055565887e-06, + "loss": 1.7732, + "step": 34780 + }, + { + "epoch": 1.29, + "learning_rate": 8.70606612861234e-06, + "loss": 1.8524, + "step": 34790 + }, + { + "epoch": 1.29, + "learning_rate": 8.705694201658796e-06, + "loss": 1.6196, + "step": 34800 + }, + { + "epoch": 1.29, + "eval_loss": 1.7474515438079834, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 34800 + }, + { + "epoch": 1.29, + "learning_rate": 8.70532227470525e-06, + "loss": 1.8027, + "step": 34810 + }, + { + "epoch": 1.3, + "learning_rate": 8.704950347751703e-06, + "loss": 1.9027, + "step": 34820 + }, + { + "epoch": 1.3, + "learning_rate": 8.704578420798155e-06, + "loss": 1.7372, + "step": 34830 + }, + { + "epoch": 1.3, + "learning_rate": 8.70420649384461e-06, + "loss": 1.9541, + "step": 34840 + }, + { + "epoch": 1.3, + "learning_rate": 8.703834566891063e-06, + "loss": 1.7652, + "step": 34850 + }, + { + "epoch": 1.3, + "learning_rate": 8.703462639937517e-06, + "loss": 1.7851, + "step": 34860 + }, + { + "epoch": 1.3, + "learning_rate": 8.70309071298397e-06, + "loss": 1.8279, + "step": 34870 + }, + { + "epoch": 1.3, + "learning_rate": 8.702718786030424e-06, + "loss": 1.7127, + "step": 34880 + }, + { + "epoch": 1.3, + "learning_rate": 8.702346859076877e-06, + "loss": 1.7991, + "step": 34890 + }, + { + "epoch": 1.3, + "learning_rate": 8.701974932123332e-06, + "loss": 1.8407, + "step": 34900 + }, + { + "epoch": 1.3, + "eval_loss": 1.7473715543746948, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 34900 + }, + { + "epoch": 1.3, + "learning_rate": 8.701603005169786e-06, + "loss": 1.7152, + "step": 34910 + }, + { + "epoch": 1.3, + "learning_rate": 8.701231078216239e-06, + "loss": 1.7165, + "step": 34920 + }, + { + "epoch": 1.3, + "learning_rate": 8.700859151262693e-06, + "loss": 1.7704, + "step": 34930 + }, + { + "epoch": 1.3, + "learning_rate": 8.700487224309146e-06, + "loss": 1.9051, + "step": 34940 + }, + { + "epoch": 1.3, + "learning_rate": 8.7001152973556e-06, + "loss": 1.769, + "step": 34950 + }, + { + "epoch": 1.3, + "learning_rate": 8.699743370402055e-06, + "loss": 1.7565, + "step": 34960 + }, + { + "epoch": 1.3, + "learning_rate": 8.699371443448508e-06, + "loss": 1.7658, + "step": 34970 + }, + { + "epoch": 1.3, + "learning_rate": 8.698999516494962e-06, + "loss": 1.8534, + "step": 34980 + }, + { + "epoch": 1.3, + "learning_rate": 8.698627589541415e-06, + "loss": 1.8139, + "step": 34990 + }, + { + "epoch": 1.3, + "learning_rate": 8.698255662587869e-06, + "loss": 1.8307, + "step": 35000 + }, + { + "epoch": 1.3, + "eval_loss": 1.748002290725708, + "eval_runtime": 16.8194, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 35000 + }, + { + "epoch": 1.3, + "learning_rate": 8.697883735634322e-06, + "loss": 1.9386, + "step": 35010 + }, + { + "epoch": 1.3, + "learning_rate": 8.697511808680775e-06, + "loss": 1.7373, + "step": 35020 + }, + { + "epoch": 1.3, + "learning_rate": 8.697139881727229e-06, + "loss": 1.8358, + "step": 35030 + }, + { + "epoch": 1.3, + "learning_rate": 8.696767954773682e-06, + "loss": 1.7319, + "step": 35040 + }, + { + "epoch": 1.3, + "learning_rate": 8.696396027820136e-06, + "loss": 1.7327, + "step": 35050 + }, + { + "epoch": 1.3, + "learning_rate": 8.696024100866591e-06, + "loss": 1.8929, + "step": 35060 + }, + { + "epoch": 1.3, + "learning_rate": 8.695652173913044e-06, + "loss": 1.7618, + "step": 35070 + }, + { + "epoch": 1.3, + "learning_rate": 8.695280246959498e-06, + "loss": 1.784, + "step": 35080 + }, + { + "epoch": 1.31, + "learning_rate": 8.694908320005951e-06, + "loss": 1.763, + "step": 35090 + }, + { + "epoch": 1.31, + "learning_rate": 8.694536393052405e-06, + "loss": 1.7915, + "step": 35100 + }, + { + "epoch": 1.31, + "eval_loss": 1.7465955018997192, + "eval_runtime": 16.8099, + "eval_samples_per_second": 59.489, + "eval_steps_per_second": 3.748, + "step": 35100 + }, + { + "epoch": 1.31, + "learning_rate": 8.694164466098858e-06, + "loss": 1.758, + "step": 35110 + }, + { + "epoch": 1.31, + "learning_rate": 8.693792539145313e-06, + "loss": 1.9416, + "step": 35120 + }, + { + "epoch": 1.31, + "learning_rate": 8.693420612191767e-06, + "loss": 1.8995, + "step": 35130 + }, + { + "epoch": 1.31, + "learning_rate": 8.69304868523822e-06, + "loss": 1.8895, + "step": 35140 + }, + { + "epoch": 1.31, + "learning_rate": 8.692676758284674e-06, + "loss": 1.8674, + "step": 35150 + }, + { + "epoch": 1.31, + "learning_rate": 8.692304831331127e-06, + "loss": 1.8622, + "step": 35160 + }, + { + "epoch": 1.31, + "learning_rate": 8.69193290437758e-06, + "loss": 1.7506, + "step": 35170 + }, + { + "epoch": 1.31, + "learning_rate": 8.691560977424036e-06, + "loss": 1.784, + "step": 35180 + }, + { + "epoch": 1.31, + "learning_rate": 8.69118905047049e-06, + "loss": 1.7985, + "step": 35190 + }, + { + "epoch": 1.31, + "learning_rate": 8.690817123516943e-06, + "loss": 1.7892, + "step": 35200 + }, + { + "epoch": 1.31, + "eval_loss": 1.7465145587921143, + "eval_runtime": 16.8191, + "eval_samples_per_second": 59.456, + "eval_steps_per_second": 3.746, + "step": 35200 + }, + { + "epoch": 1.31, + "learning_rate": 8.690445196563395e-06, + "loss": 1.9543, + "step": 35210 + }, + { + "epoch": 1.31, + "learning_rate": 8.69007326960985e-06, + "loss": 1.7831, + "step": 35220 + }, + { + "epoch": 1.31, + "learning_rate": 8.689701342656303e-06, + "loss": 1.7872, + "step": 35230 + }, + { + "epoch": 1.31, + "learning_rate": 8.689329415702757e-06, + "loss": 1.8229, + "step": 35240 + }, + { + "epoch": 1.31, + "learning_rate": 8.68895748874921e-06, + "loss": 1.7944, + "step": 35250 + }, + { + "epoch": 1.31, + "learning_rate": 8.688585561795664e-06, + "loss": 1.8411, + "step": 35260 + }, + { + "epoch": 1.31, + "learning_rate": 8.688213634842117e-06, + "loss": 1.7528, + "step": 35270 + }, + { + "epoch": 1.31, + "learning_rate": 8.68784170788857e-06, + "loss": 1.6756, + "step": 35280 + }, + { + "epoch": 1.31, + "learning_rate": 8.687469780935026e-06, + "loss": 1.7623, + "step": 35290 + }, + { + "epoch": 1.31, + "learning_rate": 8.687097853981479e-06, + "loss": 1.7252, + "step": 35300 + }, + { + "epoch": 1.31, + "eval_loss": 1.7481515407562256, + "eval_runtime": 16.8208, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 35300 + }, + { + "epoch": 1.31, + "learning_rate": 8.686725927027933e-06, + "loss": 1.8095, + "step": 35310 + }, + { + "epoch": 1.31, + "learning_rate": 8.686354000074386e-06, + "loss": 1.8164, + "step": 35320 + }, + { + "epoch": 1.31, + "learning_rate": 8.68598207312084e-06, + "loss": 1.8604, + "step": 35330 + }, + { + "epoch": 1.31, + "learning_rate": 8.685610146167293e-06, + "loss": 1.7743, + "step": 35340 + }, + { + "epoch": 1.31, + "learning_rate": 8.685238219213748e-06, + "loss": 1.7973, + "step": 35350 + }, + { + "epoch": 1.32, + "learning_rate": 8.684866292260202e-06, + "loss": 1.8485, + "step": 35360 + }, + { + "epoch": 1.32, + "learning_rate": 8.684494365306655e-06, + "loss": 1.8146, + "step": 35370 + }, + { + "epoch": 1.32, + "learning_rate": 8.684122438353108e-06, + "loss": 1.7319, + "step": 35380 + }, + { + "epoch": 1.32, + "learning_rate": 8.683750511399562e-06, + "loss": 1.9304, + "step": 35390 + }, + { + "epoch": 1.32, + "learning_rate": 8.683378584446015e-06, + "loss": 1.889, + "step": 35400 + }, + { + "epoch": 1.32, + "eval_loss": 1.7465488910675049, + "eval_runtime": 16.8104, + "eval_samples_per_second": 59.487, + "eval_steps_per_second": 3.748, + "step": 35400 + }, + { + "epoch": 1.32, + "learning_rate": 8.683006657492469e-06, + "loss": 1.8161, + "step": 35410 + }, + { + "epoch": 1.32, + "learning_rate": 8.682634730538922e-06, + "loss": 1.879, + "step": 35420 + }, + { + "epoch": 1.32, + "learning_rate": 8.682262803585376e-06, + "loss": 1.7901, + "step": 35430 + }, + { + "epoch": 1.32, + "learning_rate": 8.68189087663183e-06, + "loss": 1.711, + "step": 35440 + }, + { + "epoch": 1.32, + "learning_rate": 8.681518949678284e-06, + "loss": 1.8591, + "step": 35450 + }, + { + "epoch": 1.32, + "learning_rate": 8.681147022724738e-06, + "loss": 1.9216, + "step": 35460 + }, + { + "epoch": 1.32, + "learning_rate": 8.680775095771191e-06, + "loss": 1.8103, + "step": 35470 + }, + { + "epoch": 1.32, + "learning_rate": 8.680403168817645e-06, + "loss": 1.844, + "step": 35480 + }, + { + "epoch": 1.32, + "learning_rate": 8.680031241864098e-06, + "loss": 1.7279, + "step": 35490 + }, + { + "epoch": 1.32, + "learning_rate": 8.679659314910552e-06, + "loss": 1.7827, + "step": 35500 + }, + { + "epoch": 1.32, + "eval_loss": 1.7467600107192993, + "eval_runtime": 16.8126, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 35500 + }, + { + "epoch": 1.32, + "learning_rate": 8.679287387957007e-06, + "loss": 1.7971, + "step": 35510 + }, + { + "epoch": 1.32, + "learning_rate": 8.67891546100346e-06, + "loss": 1.8826, + "step": 35520 + }, + { + "epoch": 1.32, + "learning_rate": 8.678543534049914e-06, + "loss": 1.8497, + "step": 35530 + }, + { + "epoch": 1.32, + "learning_rate": 8.678171607096367e-06, + "loss": 1.786, + "step": 35540 + }, + { + "epoch": 1.32, + "learning_rate": 8.67779968014282e-06, + "loss": 1.6478, + "step": 35550 + }, + { + "epoch": 1.32, + "learning_rate": 8.677427753189274e-06, + "loss": 1.8904, + "step": 35560 + }, + { + "epoch": 1.32, + "learning_rate": 8.67705582623573e-06, + "loss": 1.8223, + "step": 35570 + }, + { + "epoch": 1.32, + "learning_rate": 8.676683899282183e-06, + "loss": 1.7512, + "step": 35580 + }, + { + "epoch": 1.32, + "learning_rate": 8.676311972328634e-06, + "loss": 1.6235, + "step": 35590 + }, + { + "epoch": 1.32, + "learning_rate": 8.675940045375088e-06, + "loss": 1.8027, + "step": 35600 + }, + { + "epoch": 1.32, + "eval_loss": 1.7468901872634888, + "eval_runtime": 16.8237, + "eval_samples_per_second": 59.44, + "eval_steps_per_second": 3.745, + "step": 35600 + }, + { + "epoch": 1.32, + "learning_rate": 8.675568118421543e-06, + "loss": 1.8303, + "step": 35610 + }, + { + "epoch": 1.32, + "learning_rate": 8.675196191467997e-06, + "loss": 1.7761, + "step": 35620 + }, + { + "epoch": 1.33, + "learning_rate": 8.67482426451445e-06, + "loss": 1.8559, + "step": 35630 + }, + { + "epoch": 1.33, + "learning_rate": 8.674452337560903e-06, + "loss": 1.772, + "step": 35640 + }, + { + "epoch": 1.33, + "learning_rate": 8.674080410607357e-06, + "loss": 1.856, + "step": 35650 + }, + { + "epoch": 1.33, + "learning_rate": 8.67370848365381e-06, + "loss": 1.7498, + "step": 35660 + }, + { + "epoch": 1.33, + "learning_rate": 8.673336556700266e-06, + "loss": 1.7712, + "step": 35670 + }, + { + "epoch": 1.33, + "learning_rate": 8.672964629746719e-06, + "loss": 1.7634, + "step": 35680 + }, + { + "epoch": 1.33, + "learning_rate": 8.672592702793172e-06, + "loss": 1.8058, + "step": 35690 + }, + { + "epoch": 1.33, + "learning_rate": 8.672220775839626e-06, + "loss": 1.613, + "step": 35700 + }, + { + "epoch": 1.33, + "eval_loss": 1.7459224462509155, + "eval_runtime": 16.8128, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 35700 + }, + { + "epoch": 1.33, + "learning_rate": 8.67184884888608e-06, + "loss": 1.8008, + "step": 35710 + }, + { + "epoch": 1.33, + "learning_rate": 8.671476921932533e-06, + "loss": 1.8289, + "step": 35720 + }, + { + "epoch": 1.33, + "learning_rate": 8.671104994978988e-06, + "loss": 1.7568, + "step": 35730 + }, + { + "epoch": 1.33, + "learning_rate": 8.670733068025441e-06, + "loss": 1.8552, + "step": 35740 + }, + { + "epoch": 1.33, + "learning_rate": 8.670361141071895e-06, + "loss": 1.7873, + "step": 35750 + }, + { + "epoch": 1.33, + "learning_rate": 8.669989214118348e-06, + "loss": 1.8594, + "step": 35760 + }, + { + "epoch": 1.33, + "learning_rate": 8.669617287164802e-06, + "loss": 1.8123, + "step": 35770 + }, + { + "epoch": 1.33, + "learning_rate": 8.669245360211255e-06, + "loss": 1.8971, + "step": 35780 + }, + { + "epoch": 1.33, + "learning_rate": 8.668873433257709e-06, + "loss": 1.8325, + "step": 35790 + }, + { + "epoch": 1.33, + "learning_rate": 8.668501506304162e-06, + "loss": 1.783, + "step": 35800 + }, + { + "epoch": 1.33, + "eval_loss": 1.745602011680603, + "eval_runtime": 16.8179, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 35800 + }, + { + "epoch": 1.33, + "learning_rate": 8.668129579350616e-06, + "loss": 1.7055, + "step": 35810 + }, + { + "epoch": 1.33, + "learning_rate": 8.667757652397069e-06, + "loss": 1.7517, + "step": 35820 + }, + { + "epoch": 1.33, + "learning_rate": 8.667385725443524e-06, + "loss": 1.6708, + "step": 35830 + }, + { + "epoch": 1.33, + "learning_rate": 8.667013798489978e-06, + "loss": 1.8056, + "step": 35840 + }, + { + "epoch": 1.33, + "learning_rate": 8.666641871536431e-06, + "loss": 1.7671, + "step": 35850 + }, + { + "epoch": 1.33, + "learning_rate": 8.666269944582885e-06, + "loss": 1.827, + "step": 35860 + }, + { + "epoch": 1.33, + "learning_rate": 8.665898017629338e-06, + "loss": 1.8309, + "step": 35870 + }, + { + "epoch": 1.33, + "learning_rate": 8.665526090675792e-06, + "loss": 1.7958, + "step": 35880 + }, + { + "epoch": 1.33, + "learning_rate": 8.665154163722245e-06, + "loss": 1.7939, + "step": 35890 + }, + { + "epoch": 1.34, + "learning_rate": 8.6647822367687e-06, + "loss": 1.6854, + "step": 35900 + }, + { + "epoch": 1.34, + "eval_loss": 1.7463206052780151, + "eval_runtime": 16.8103, + "eval_samples_per_second": 59.487, + "eval_steps_per_second": 3.748, + "step": 35900 + }, + { + "epoch": 1.34, + "learning_rate": 8.664410309815154e-06, + "loss": 1.8009, + "step": 35910 + }, + { + "epoch": 1.34, + "learning_rate": 8.664038382861607e-06, + "loss": 1.8698, + "step": 35920 + }, + { + "epoch": 1.34, + "learning_rate": 8.66366645590806e-06, + "loss": 1.9357, + "step": 35930 + }, + { + "epoch": 1.34, + "learning_rate": 8.663294528954514e-06, + "loss": 1.8245, + "step": 35940 + }, + { + "epoch": 1.34, + "learning_rate": 8.662922602000967e-06, + "loss": 1.7624, + "step": 35950 + }, + { + "epoch": 1.34, + "learning_rate": 8.662550675047421e-06, + "loss": 1.7791, + "step": 35960 + }, + { + "epoch": 1.34, + "learning_rate": 8.662178748093874e-06, + "loss": 1.8457, + "step": 35970 + }, + { + "epoch": 1.34, + "learning_rate": 8.661806821140328e-06, + "loss": 1.7469, + "step": 35980 + }, + { + "epoch": 1.34, + "learning_rate": 8.661434894186781e-06, + "loss": 1.6773, + "step": 35990 + }, + { + "epoch": 1.34, + "learning_rate": 8.661062967233236e-06, + "loss": 1.7841, + "step": 36000 + }, + { + "epoch": 1.34, + "eval_loss": 1.74503755569458, + "eval_runtime": 16.8275, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 36000 + }, + { + "epoch": 1.34, + "learning_rate": 8.66069104027969e-06, + "loss": 1.7295, + "step": 36010 + }, + { + "epoch": 1.34, + "learning_rate": 8.660319113326143e-06, + "loss": 1.8031, + "step": 36020 + }, + { + "epoch": 1.34, + "learning_rate": 8.659947186372597e-06, + "loss": 1.767, + "step": 36030 + }, + { + "epoch": 1.34, + "learning_rate": 8.65957525941905e-06, + "loss": 1.7477, + "step": 36040 + }, + { + "epoch": 1.34, + "learning_rate": 8.659203332465504e-06, + "loss": 1.8281, + "step": 36050 + }, + { + "epoch": 1.34, + "learning_rate": 8.658831405511959e-06, + "loss": 1.9403, + "step": 36060 + }, + { + "epoch": 1.34, + "learning_rate": 8.658459478558412e-06, + "loss": 1.7362, + "step": 36070 + }, + { + "epoch": 1.34, + "learning_rate": 8.658087551604866e-06, + "loss": 1.8679, + "step": 36080 + }, + { + "epoch": 1.34, + "learning_rate": 8.65771562465132e-06, + "loss": 1.7856, + "step": 36090 + }, + { + "epoch": 1.34, + "learning_rate": 8.657343697697773e-06, + "loss": 1.8804, + "step": 36100 + }, + { + "epoch": 1.34, + "eval_loss": 1.7444746494293213, + "eval_runtime": 16.8199, + "eval_samples_per_second": 59.453, + "eval_steps_per_second": 3.746, + "step": 36100 + }, + { + "epoch": 1.34, + "learning_rate": 8.656971770744226e-06, + "loss": 1.7524, + "step": 36110 + }, + { + "epoch": 1.34, + "learning_rate": 8.656599843790681e-06, + "loss": 1.732, + "step": 36120 + }, + { + "epoch": 1.34, + "learning_rate": 8.656227916837135e-06, + "loss": 1.8076, + "step": 36130 + }, + { + "epoch": 1.34, + "learning_rate": 8.655855989883588e-06, + "loss": 1.7399, + "step": 36140 + }, + { + "epoch": 1.34, + "learning_rate": 8.65548406293004e-06, + "loss": 1.8945, + "step": 36150 + }, + { + "epoch": 1.34, + "learning_rate": 8.655112135976495e-06, + "loss": 1.7072, + "step": 36160 + }, + { + "epoch": 1.35, + "learning_rate": 8.654740209022949e-06, + "loss": 1.7262, + "step": 36170 + }, + { + "epoch": 1.35, + "learning_rate": 8.654368282069402e-06, + "loss": 1.7311, + "step": 36180 + }, + { + "epoch": 1.35, + "learning_rate": 8.653996355115856e-06, + "loss": 1.8708, + "step": 36190 + }, + { + "epoch": 1.35, + "learning_rate": 8.653624428162309e-06, + "loss": 1.8758, + "step": 36200 + }, + { + "epoch": 1.35, + "eval_loss": 1.74403977394104, + "eval_runtime": 16.8074, + "eval_samples_per_second": 59.498, + "eval_steps_per_second": 3.748, + "step": 36200 + }, + { + "epoch": 1.35, + "learning_rate": 8.653252501208762e-06, + "loss": 1.7383, + "step": 36210 + }, + { + "epoch": 1.35, + "learning_rate": 8.652880574255218e-06, + "loss": 1.7625, + "step": 36220 + }, + { + "epoch": 1.35, + "learning_rate": 8.652508647301671e-06, + "loss": 1.8053, + "step": 36230 + }, + { + "epoch": 1.35, + "learning_rate": 8.652136720348125e-06, + "loss": 1.7069, + "step": 36240 + }, + { + "epoch": 1.35, + "learning_rate": 8.651764793394578e-06, + "loss": 1.7653, + "step": 36250 + }, + { + "epoch": 1.35, + "learning_rate": 8.651392866441031e-06, + "loss": 1.7914, + "step": 36260 + }, + { + "epoch": 1.35, + "learning_rate": 8.651020939487485e-06, + "loss": 1.8512, + "step": 36270 + }, + { + "epoch": 1.35, + "learning_rate": 8.65064901253394e-06, + "loss": 1.9523, + "step": 36280 + }, + { + "epoch": 1.35, + "learning_rate": 8.650277085580394e-06, + "loss": 1.9076, + "step": 36290 + }, + { + "epoch": 1.35, + "learning_rate": 8.649905158626847e-06, + "loss": 1.805, + "step": 36300 + }, + { + "epoch": 1.35, + "eval_loss": 1.7422869205474854, + "eval_runtime": 16.8295, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 36300 + }, + { + "epoch": 1.35, + "learning_rate": 8.6495332316733e-06, + "loss": 1.8174, + "step": 36310 + }, + { + "epoch": 1.35, + "learning_rate": 8.649161304719754e-06, + "loss": 1.848, + "step": 36320 + }, + { + "epoch": 1.35, + "learning_rate": 8.648789377766207e-06, + "loss": 1.8064, + "step": 36330 + }, + { + "epoch": 1.35, + "learning_rate": 8.64841745081266e-06, + "loss": 1.7601, + "step": 36340 + }, + { + "epoch": 1.35, + "learning_rate": 8.648045523859114e-06, + "loss": 1.7438, + "step": 36350 + }, + { + "epoch": 1.35, + "learning_rate": 8.647673596905568e-06, + "loss": 1.8303, + "step": 36360 + }, + { + "epoch": 1.35, + "learning_rate": 8.647301669952021e-06, + "loss": 1.8063, + "step": 36370 + }, + { + "epoch": 1.35, + "learning_rate": 8.646929742998476e-06, + "loss": 1.8484, + "step": 36380 + }, + { + "epoch": 1.35, + "learning_rate": 8.64655781604493e-06, + "loss": 1.8073, + "step": 36390 + }, + { + "epoch": 1.35, + "learning_rate": 8.646185889091383e-06, + "loss": 1.7979, + "step": 36400 + }, + { + "epoch": 1.35, + "eval_loss": 1.7418423891067505, + "eval_runtime": 16.7925, + "eval_samples_per_second": 59.55, + "eval_steps_per_second": 3.752, + "step": 36400 + }, + { + "epoch": 1.35, + "learning_rate": 8.645813962137837e-06, + "loss": 1.721, + "step": 36410 + }, + { + "epoch": 1.35, + "learning_rate": 8.64544203518429e-06, + "loss": 1.7589, + "step": 36420 + }, + { + "epoch": 1.35, + "learning_rate": 8.645070108230744e-06, + "loss": 1.8363, + "step": 36430 + }, + { + "epoch": 1.36, + "learning_rate": 8.644698181277197e-06, + "loss": 1.7831, + "step": 36440 + }, + { + "epoch": 1.36, + "learning_rate": 8.644326254323652e-06, + "loss": 1.8053, + "step": 36450 + }, + { + "epoch": 1.36, + "learning_rate": 8.643954327370106e-06, + "loss": 1.859, + "step": 36460 + }, + { + "epoch": 1.36, + "learning_rate": 8.64358240041656e-06, + "loss": 1.8385, + "step": 36470 + }, + { + "epoch": 1.36, + "learning_rate": 8.643210473463013e-06, + "loss": 1.8442, + "step": 36480 + }, + { + "epoch": 1.36, + "learning_rate": 8.642838546509466e-06, + "loss": 1.7675, + "step": 36490 + }, + { + "epoch": 1.36, + "learning_rate": 8.64246661955592e-06, + "loss": 1.7267, + "step": 36500 + }, + { + "epoch": 1.36, + "eval_loss": 1.7424358129501343, + "eval_runtime": 16.8088, + "eval_samples_per_second": 59.493, + "eval_steps_per_second": 3.748, + "step": 36500 + }, + { + "epoch": 1.36, + "learning_rate": 8.642094692602375e-06, + "loss": 1.9479, + "step": 36510 + }, + { + "epoch": 1.36, + "learning_rate": 8.641722765648826e-06, + "loss": 1.7599, + "step": 36520 + }, + { + "epoch": 1.36, + "learning_rate": 8.64135083869528e-06, + "loss": 1.7483, + "step": 36530 + }, + { + "epoch": 1.36, + "learning_rate": 8.640978911741733e-06, + "loss": 1.864, + "step": 36540 + }, + { + "epoch": 1.36, + "learning_rate": 8.640606984788189e-06, + "loss": 1.6483, + "step": 36550 + }, + { + "epoch": 1.36, + "learning_rate": 8.640235057834642e-06, + "loss": 1.7297, + "step": 36560 + }, + { + "epoch": 1.36, + "learning_rate": 8.639863130881095e-06, + "loss": 1.7783, + "step": 36570 + }, + { + "epoch": 1.36, + "learning_rate": 8.639491203927549e-06, + "loss": 1.8995, + "step": 36580 + }, + { + "epoch": 1.36, + "learning_rate": 8.639119276974002e-06, + "loss": 1.7046, + "step": 36590 + }, + { + "epoch": 1.36, + "learning_rate": 8.638747350020456e-06, + "loss": 1.8689, + "step": 36600 + }, + { + "epoch": 1.36, + "eval_loss": 1.7406935691833496, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 36600 + }, + { + "epoch": 1.36, + "learning_rate": 8.638375423066911e-06, + "loss": 1.8359, + "step": 36610 + }, + { + "epoch": 1.36, + "learning_rate": 8.638003496113364e-06, + "loss": 1.7695, + "step": 36620 + }, + { + "epoch": 1.36, + "learning_rate": 8.637631569159818e-06, + "loss": 1.9118, + "step": 36630 + }, + { + "epoch": 1.36, + "learning_rate": 8.637259642206271e-06, + "loss": 1.7986, + "step": 36640 + }, + { + "epoch": 1.36, + "learning_rate": 8.636887715252725e-06, + "loss": 1.7526, + "step": 36650 + }, + { + "epoch": 1.36, + "learning_rate": 8.636515788299178e-06, + "loss": 1.8295, + "step": 36660 + }, + { + "epoch": 1.36, + "learning_rate": 8.636143861345633e-06, + "loss": 1.8437, + "step": 36670 + }, + { + "epoch": 1.36, + "learning_rate": 8.635771934392087e-06, + "loss": 1.7473, + "step": 36680 + }, + { + "epoch": 1.36, + "learning_rate": 8.63540000743854e-06, + "loss": 2.0315, + "step": 36690 + }, + { + "epoch": 1.36, + "learning_rate": 8.635028080484994e-06, + "loss": 1.6919, + "step": 36700 + }, + { + "epoch": 1.36, + "eval_loss": 1.741946816444397, + "eval_runtime": 16.8089, + "eval_samples_per_second": 59.492, + "eval_steps_per_second": 3.748, + "step": 36700 + }, + { + "epoch": 1.37, + "learning_rate": 8.634656153531447e-06, + "loss": 1.7177, + "step": 36710 + }, + { + "epoch": 1.37, + "learning_rate": 8.6342842265779e-06, + "loss": 1.6969, + "step": 36720 + }, + { + "epoch": 1.37, + "learning_rate": 8.633912299624354e-06, + "loss": 1.8579, + "step": 36730 + }, + { + "epoch": 1.37, + "learning_rate": 8.633540372670808e-06, + "loss": 1.7303, + "step": 36740 + }, + { + "epoch": 1.37, + "learning_rate": 8.633168445717261e-06, + "loss": 1.9946, + "step": 36750 + }, + { + "epoch": 1.37, + "learning_rate": 8.632796518763715e-06, + "loss": 1.7667, + "step": 36760 + }, + { + "epoch": 1.37, + "learning_rate": 8.63242459181017e-06, + "loss": 1.9025, + "step": 36770 + }, + { + "epoch": 1.37, + "learning_rate": 8.632052664856623e-06, + "loss": 1.7442, + "step": 36780 + }, + { + "epoch": 1.37, + "learning_rate": 8.631680737903077e-06, + "loss": 1.753, + "step": 36790 + }, + { + "epoch": 1.37, + "learning_rate": 8.63130881094953e-06, + "loss": 1.8197, + "step": 36800 + }, + { + "epoch": 1.37, + "eval_loss": 1.7418075799942017, + "eval_runtime": 16.8284, + "eval_samples_per_second": 59.423, + "eval_steps_per_second": 3.744, + "step": 36800 + }, + { + "epoch": 1.37, + "learning_rate": 8.630936883995984e-06, + "loss": 1.7837, + "step": 36810 + }, + { + "epoch": 1.37, + "learning_rate": 8.630564957042437e-06, + "loss": 1.7634, + "step": 36820 + }, + { + "epoch": 1.37, + "learning_rate": 8.630193030088892e-06, + "loss": 1.8804, + "step": 36830 + }, + { + "epoch": 1.37, + "learning_rate": 8.629821103135346e-06, + "loss": 1.7866, + "step": 36840 + }, + { + "epoch": 1.37, + "learning_rate": 8.629449176181799e-06, + "loss": 1.8622, + "step": 36850 + }, + { + "epoch": 1.37, + "learning_rate": 8.629077249228253e-06, + "loss": 1.8188, + "step": 36860 + }, + { + "epoch": 1.37, + "learning_rate": 8.628705322274706e-06, + "loss": 1.8865, + "step": 36870 + }, + { + "epoch": 1.37, + "learning_rate": 8.62833339532116e-06, + "loss": 1.7914, + "step": 36880 + }, + { + "epoch": 1.37, + "learning_rate": 8.627961468367615e-06, + "loss": 1.8876, + "step": 36890 + }, + { + "epoch": 1.37, + "learning_rate": 8.627589541414066e-06, + "loss": 1.8571, + "step": 36900 + }, + { + "epoch": 1.37, + "eval_loss": 1.743058443069458, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 36900 + }, + { + "epoch": 1.37, + "learning_rate": 8.62721761446052e-06, + "loss": 1.697, + "step": 36910 + }, + { + "epoch": 1.37, + "learning_rate": 8.626845687506973e-06, + "loss": 1.9543, + "step": 36920 + }, + { + "epoch": 1.37, + "learning_rate": 8.626473760553428e-06, + "loss": 1.8493, + "step": 36930 + }, + { + "epoch": 1.37, + "learning_rate": 8.626101833599882e-06, + "loss": 1.6708, + "step": 36940 + }, + { + "epoch": 1.37, + "learning_rate": 8.625729906646335e-06, + "loss": 1.8122, + "step": 36950 + }, + { + "epoch": 1.37, + "learning_rate": 8.625357979692789e-06, + "loss": 1.7041, + "step": 36960 + }, + { + "epoch": 1.38, + "learning_rate": 8.624986052739242e-06, + "loss": 1.8028, + "step": 36970 + }, + { + "epoch": 1.38, + "learning_rate": 8.624614125785696e-06, + "loss": 1.7832, + "step": 36980 + }, + { + "epoch": 1.38, + "learning_rate": 8.624242198832151e-06, + "loss": 1.7064, + "step": 36990 + }, + { + "epoch": 1.38, + "learning_rate": 8.623870271878604e-06, + "loss": 1.6946, + "step": 37000 + }, + { + "epoch": 1.38, + "eval_loss": 1.7414793968200684, + "eval_runtime": 16.8353, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 37000 + }, + { + "epoch": 1.38, + "learning_rate": 8.623498344925058e-06, + "loss": 1.7269, + "step": 37010 + }, + { + "epoch": 1.38, + "learning_rate": 8.623126417971511e-06, + "loss": 1.8208, + "step": 37020 + }, + { + "epoch": 1.38, + "learning_rate": 8.622754491017965e-06, + "loss": 1.7371, + "step": 37030 + }, + { + "epoch": 1.38, + "learning_rate": 8.622382564064418e-06, + "loss": 1.6948, + "step": 37040 + }, + { + "epoch": 1.38, + "learning_rate": 8.622010637110872e-06, + "loss": 1.7277, + "step": 37050 + }, + { + "epoch": 1.38, + "learning_rate": 8.621638710157327e-06, + "loss": 1.8659, + "step": 37060 + }, + { + "epoch": 1.38, + "learning_rate": 8.62126678320378e-06, + "loss": 1.8208, + "step": 37070 + }, + { + "epoch": 1.38, + "learning_rate": 8.620894856250234e-06, + "loss": 1.849, + "step": 37080 + }, + { + "epoch": 1.38, + "learning_rate": 8.620522929296686e-06, + "loss": 1.7706, + "step": 37090 + }, + { + "epoch": 1.38, + "learning_rate": 8.62015100234314e-06, + "loss": 1.8433, + "step": 37100 + }, + { + "epoch": 1.38, + "eval_loss": 1.7402839660644531, + "eval_runtime": 16.837, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 37100 + }, + { + "epoch": 1.38, + "learning_rate": 8.619779075389594e-06, + "loss": 1.7445, + "step": 37110 + }, + { + "epoch": 1.38, + "learning_rate": 8.619407148436048e-06, + "loss": 1.8078, + "step": 37120 + }, + { + "epoch": 1.38, + "learning_rate": 8.619035221482501e-06, + "loss": 1.7879, + "step": 37130 + }, + { + "epoch": 1.38, + "learning_rate": 8.618663294528955e-06, + "loss": 1.7917, + "step": 37140 + }, + { + "epoch": 1.38, + "learning_rate": 8.618291367575408e-06, + "loss": 1.6207, + "step": 37150 + }, + { + "epoch": 1.38, + "learning_rate": 8.617919440621863e-06, + "loss": 2.1106, + "step": 37160 + }, + { + "epoch": 1.38, + "learning_rate": 8.617547513668317e-06, + "loss": 1.8195, + "step": 37170 + }, + { + "epoch": 1.38, + "learning_rate": 8.61717558671477e-06, + "loss": 1.8292, + "step": 37180 + }, + { + "epoch": 1.38, + "learning_rate": 8.616803659761223e-06, + "loss": 1.7299, + "step": 37190 + }, + { + "epoch": 1.38, + "learning_rate": 8.616431732807677e-06, + "loss": 1.7236, + "step": 37200 + }, + { + "epoch": 1.38, + "eval_loss": 1.7398024797439575, + "eval_runtime": 16.8309, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 37200 + }, + { + "epoch": 1.38, + "learning_rate": 8.61605980585413e-06, + "loss": 1.7932, + "step": 37210 + }, + { + "epoch": 1.38, + "learning_rate": 8.615687878900586e-06, + "loss": 1.7055, + "step": 37220 + }, + { + "epoch": 1.38, + "learning_rate": 8.615315951947039e-06, + "loss": 1.7997, + "step": 37230 + }, + { + "epoch": 1.39, + "learning_rate": 8.614944024993492e-06, + "loss": 1.8687, + "step": 37240 + }, + { + "epoch": 1.39, + "learning_rate": 8.614572098039946e-06, + "loss": 1.5871, + "step": 37250 + }, + { + "epoch": 1.39, + "learning_rate": 8.6142001710864e-06, + "loss": 1.7896, + "step": 37260 + }, + { + "epoch": 1.39, + "learning_rate": 8.613828244132853e-06, + "loss": 1.8295, + "step": 37270 + }, + { + "epoch": 1.39, + "learning_rate": 8.613456317179306e-06, + "loss": 1.7784, + "step": 37280 + }, + { + "epoch": 1.39, + "learning_rate": 8.61308439022576e-06, + "loss": 1.7819, + "step": 37290 + }, + { + "epoch": 1.39, + "learning_rate": 8.612712463272213e-06, + "loss": 1.8367, + "step": 37300 + }, + { + "epoch": 1.39, + "eval_loss": 1.739717960357666, + "eval_runtime": 16.8334, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 37300 + }, + { + "epoch": 1.39, + "learning_rate": 8.612340536318667e-06, + "loss": 1.6927, + "step": 37310 + }, + { + "epoch": 1.39, + "learning_rate": 8.611968609365122e-06, + "loss": 1.8603, + "step": 37320 + }, + { + "epoch": 1.39, + "learning_rate": 8.611596682411575e-06, + "loss": 1.7333, + "step": 37330 + }, + { + "epoch": 1.39, + "learning_rate": 8.611224755458029e-06, + "loss": 1.7786, + "step": 37340 + }, + { + "epoch": 1.39, + "learning_rate": 8.610852828504482e-06, + "loss": 1.8015, + "step": 37350 + }, + { + "epoch": 1.39, + "learning_rate": 8.610480901550936e-06, + "loss": 1.79, + "step": 37360 + }, + { + "epoch": 1.39, + "learning_rate": 8.610108974597389e-06, + "loss": 1.7935, + "step": 37370 + }, + { + "epoch": 1.39, + "learning_rate": 8.609737047643844e-06, + "loss": 1.8017, + "step": 37380 + }, + { + "epoch": 1.39, + "learning_rate": 8.609365120690298e-06, + "loss": 1.7811, + "step": 37390 + }, + { + "epoch": 1.39, + "learning_rate": 8.608993193736751e-06, + "loss": 1.8679, + "step": 37400 + }, + { + "epoch": 1.39, + "eval_loss": 1.740112066268921, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 37400 + }, + { + "epoch": 1.39, + "learning_rate": 8.608621266783205e-06, + "loss": 1.8987, + "step": 37410 + }, + { + "epoch": 1.39, + "learning_rate": 8.608249339829658e-06, + "loss": 1.8583, + "step": 37420 + }, + { + "epoch": 1.39, + "learning_rate": 8.607877412876112e-06, + "loss": 1.8577, + "step": 37430 + }, + { + "epoch": 1.39, + "learning_rate": 8.607505485922567e-06, + "loss": 1.8862, + "step": 37440 + }, + { + "epoch": 1.39, + "learning_rate": 8.60713355896902e-06, + "loss": 1.8053, + "step": 37450 + }, + { + "epoch": 1.39, + "learning_rate": 8.606761632015472e-06, + "loss": 1.9903, + "step": 37460 + }, + { + "epoch": 1.39, + "learning_rate": 8.606389705061925e-06, + "loss": 1.7132, + "step": 37470 + }, + { + "epoch": 1.39, + "learning_rate": 8.60601777810838e-06, + "loss": 1.7829, + "step": 37480 + }, + { + "epoch": 1.39, + "learning_rate": 8.605645851154834e-06, + "loss": 1.9521, + "step": 37490 + }, + { + "epoch": 1.39, + "learning_rate": 8.605273924201288e-06, + "loss": 1.7985, + "step": 37500 + }, + { + "epoch": 1.39, + "eval_loss": 1.7412558794021606, + "eval_runtime": 16.8222, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 37500 + }, + { + "epoch": 1.4, + "learning_rate": 8.604901997247741e-06, + "loss": 1.9083, + "step": 37510 + }, + { + "epoch": 1.4, + "learning_rate": 8.604530070294194e-06, + "loss": 1.7656, + "step": 37520 + }, + { + "epoch": 1.4, + "learning_rate": 8.604158143340648e-06, + "loss": 1.9091, + "step": 37530 + }, + { + "epoch": 1.4, + "learning_rate": 8.603786216387103e-06, + "loss": 1.8086, + "step": 37540 + }, + { + "epoch": 1.4, + "learning_rate": 8.603414289433556e-06, + "loss": 1.8853, + "step": 37550 + }, + { + "epoch": 1.4, + "learning_rate": 8.60304236248001e-06, + "loss": 1.7346, + "step": 37560 + }, + { + "epoch": 1.4, + "learning_rate": 8.602670435526463e-06, + "loss": 1.8534, + "step": 37570 + }, + { + "epoch": 1.4, + "learning_rate": 8.602298508572917e-06, + "loss": 2.0343, + "step": 37580 + }, + { + "epoch": 1.4, + "learning_rate": 8.60192658161937e-06, + "loss": 1.9664, + "step": 37590 + }, + { + "epoch": 1.4, + "learning_rate": 8.601554654665824e-06, + "loss": 1.8461, + "step": 37600 + }, + { + "epoch": 1.4, + "eval_loss": 1.7400128841400146, + "eval_runtime": 16.822, + "eval_samples_per_second": 59.446, + "eval_steps_per_second": 3.745, + "step": 37600 + }, + { + "epoch": 1.4, + "learning_rate": 8.601182727712279e-06, + "loss": 1.7668, + "step": 37610 + }, + { + "epoch": 1.4, + "learning_rate": 8.600810800758732e-06, + "loss": 1.7929, + "step": 37620 + }, + { + "epoch": 1.4, + "learning_rate": 8.600438873805186e-06, + "loss": 1.8991, + "step": 37630 + }, + { + "epoch": 1.4, + "learning_rate": 8.60006694685164e-06, + "loss": 1.7319, + "step": 37640 + }, + { + "epoch": 1.4, + "learning_rate": 8.599695019898093e-06, + "loss": 1.8032, + "step": 37650 + }, + { + "epoch": 1.4, + "learning_rate": 8.599323092944546e-06, + "loss": 1.8653, + "step": 37660 + }, + { + "epoch": 1.4, + "learning_rate": 8.598951165991e-06, + "loss": 1.7778, + "step": 37670 + }, + { + "epoch": 1.4, + "learning_rate": 8.598579239037453e-06, + "loss": 1.9338, + "step": 37680 + }, + { + "epoch": 1.4, + "learning_rate": 8.598207312083907e-06, + "loss": 1.8166, + "step": 37690 + }, + { + "epoch": 1.4, + "learning_rate": 8.59783538513036e-06, + "loss": 1.8117, + "step": 37700 + }, + { + "epoch": 1.4, + "eval_loss": 1.7397315502166748, + "eval_runtime": 16.827, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 37700 + }, + { + "epoch": 1.4, + "learning_rate": 8.597463458176815e-06, + "loss": 1.702, + "step": 37710 + }, + { + "epoch": 1.4, + "learning_rate": 8.597091531223269e-06, + "loss": 1.805, + "step": 37720 + }, + { + "epoch": 1.4, + "learning_rate": 8.596719604269722e-06, + "loss": 1.8022, + "step": 37730 + }, + { + "epoch": 1.4, + "learning_rate": 8.596347677316176e-06, + "loss": 1.8833, + "step": 37740 + }, + { + "epoch": 1.4, + "learning_rate": 8.595975750362629e-06, + "loss": 1.7018, + "step": 37750 + }, + { + "epoch": 1.4, + "learning_rate": 8.595603823409083e-06, + "loss": 1.7721, + "step": 37760 + }, + { + "epoch": 1.4, + "learning_rate": 8.595231896455538e-06, + "loss": 1.8442, + "step": 37770 + }, + { + "epoch": 1.41, + "learning_rate": 8.594859969501991e-06, + "loss": 1.8465, + "step": 37780 + }, + { + "epoch": 1.41, + "learning_rate": 8.594488042548445e-06, + "loss": 1.7966, + "step": 37790 + }, + { + "epoch": 1.41, + "learning_rate": 8.594116115594898e-06, + "loss": 1.7815, + "step": 37800 + }, + { + "epoch": 1.41, + "eval_loss": 1.7398022413253784, + "eval_runtime": 16.8215, + "eval_samples_per_second": 59.448, + "eval_steps_per_second": 3.745, + "step": 37800 + }, + { + "epoch": 1.41, + "learning_rate": 8.593744188641352e-06, + "loss": 1.6742, + "step": 37810 + }, + { + "epoch": 1.41, + "learning_rate": 8.593372261687805e-06, + "loss": 1.6688, + "step": 37820 + }, + { + "epoch": 1.41, + "learning_rate": 8.59300033473426e-06, + "loss": 1.7888, + "step": 37830 + }, + { + "epoch": 1.41, + "learning_rate": 8.592628407780712e-06, + "loss": 1.8281, + "step": 37840 + }, + { + "epoch": 1.41, + "learning_rate": 8.592256480827165e-06, + "loss": 1.9381, + "step": 37850 + }, + { + "epoch": 1.41, + "learning_rate": 8.591884553873619e-06, + "loss": 1.8478, + "step": 37860 + }, + { + "epoch": 1.41, + "learning_rate": 8.591512626920074e-06, + "loss": 1.7749, + "step": 37870 + }, + { + "epoch": 1.41, + "learning_rate": 8.591140699966527e-06, + "loss": 1.8713, + "step": 37880 + }, + { + "epoch": 1.41, + "learning_rate": 8.590768773012981e-06, + "loss": 1.8703, + "step": 37890 + }, + { + "epoch": 1.41, + "learning_rate": 8.590396846059434e-06, + "loss": 1.7185, + "step": 37900 + }, + { + "epoch": 1.41, + "eval_loss": 1.7394315004348755, + "eval_runtime": 16.8159, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.746, + "step": 37900 + }, + { + "epoch": 1.41, + "learning_rate": 8.590024919105888e-06, + "loss": 1.7697, + "step": 37910 + }, + { + "epoch": 1.41, + "learning_rate": 8.589652992152341e-06, + "loss": 1.9645, + "step": 37920 + }, + { + "epoch": 1.41, + "learning_rate": 8.589281065198796e-06, + "loss": 1.8578, + "step": 37930 + }, + { + "epoch": 1.41, + "learning_rate": 8.58890913824525e-06, + "loss": 1.8541, + "step": 37940 + }, + { + "epoch": 1.41, + "learning_rate": 8.588537211291703e-06, + "loss": 1.6972, + "step": 37950 + }, + { + "epoch": 1.41, + "learning_rate": 8.588165284338157e-06, + "loss": 1.8308, + "step": 37960 + }, + { + "epoch": 1.41, + "learning_rate": 8.58779335738461e-06, + "loss": 1.8839, + "step": 37970 + }, + { + "epoch": 1.41, + "learning_rate": 8.587421430431064e-06, + "loss": 1.9021, + "step": 37980 + }, + { + "epoch": 1.41, + "learning_rate": 8.587049503477519e-06, + "loss": 1.7447, + "step": 37990 + }, + { + "epoch": 1.41, + "learning_rate": 8.586677576523972e-06, + "loss": 1.8517, + "step": 38000 + }, + { + "epoch": 1.41, + "eval_loss": 1.7403720617294312, + "eval_runtime": 16.8352, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 38000 + }, + { + "epoch": 1.41, + "learning_rate": 8.586305649570426e-06, + "loss": 1.8637, + "step": 38010 + }, + { + "epoch": 1.41, + "learning_rate": 8.58593372261688e-06, + "loss": 1.8473, + "step": 38020 + }, + { + "epoch": 1.41, + "learning_rate": 8.585561795663333e-06, + "loss": 1.7909, + "step": 38030 + }, + { + "epoch": 1.41, + "learning_rate": 8.585189868709786e-06, + "loss": 1.8986, + "step": 38040 + }, + { + "epoch": 1.42, + "learning_rate": 8.58481794175624e-06, + "loss": 1.9684, + "step": 38050 + }, + { + "epoch": 1.42, + "learning_rate": 8.584446014802693e-06, + "loss": 1.7032, + "step": 38060 + }, + { + "epoch": 1.42, + "learning_rate": 8.584074087849147e-06, + "loss": 1.7743, + "step": 38070 + }, + { + "epoch": 1.42, + "learning_rate": 8.5837021608956e-06, + "loss": 1.747, + "step": 38080 + }, + { + "epoch": 1.42, + "learning_rate": 8.583330233942055e-06, + "loss": 1.723, + "step": 38090 + }, + { + "epoch": 1.42, + "learning_rate": 8.582958306988509e-06, + "loss": 1.881, + "step": 38100 + }, + { + "epoch": 1.42, + "eval_loss": 1.739778995513916, + "eval_runtime": 16.8063, + "eval_samples_per_second": 59.501, + "eval_steps_per_second": 3.749, + "step": 38100 + }, + { + "epoch": 1.42, + "learning_rate": 8.582586380034962e-06, + "loss": 1.7705, + "step": 38110 + }, + { + "epoch": 1.42, + "learning_rate": 8.582214453081416e-06, + "loss": 1.7293, + "step": 38120 + }, + { + "epoch": 1.42, + "learning_rate": 8.581842526127869e-06, + "loss": 1.9506, + "step": 38130 + }, + { + "epoch": 1.42, + "learning_rate": 8.581470599174322e-06, + "loss": 1.7576, + "step": 38140 + }, + { + "epoch": 1.42, + "learning_rate": 8.581098672220778e-06, + "loss": 1.876, + "step": 38150 + }, + { + "epoch": 1.42, + "learning_rate": 8.580726745267231e-06, + "loss": 1.8871, + "step": 38160 + }, + { + "epoch": 1.42, + "learning_rate": 8.580354818313685e-06, + "loss": 1.7485, + "step": 38170 + }, + { + "epoch": 1.42, + "learning_rate": 8.579982891360138e-06, + "loss": 1.8117, + "step": 38180 + }, + { + "epoch": 1.42, + "learning_rate": 8.579610964406591e-06, + "loss": 1.8618, + "step": 38190 + }, + { + "epoch": 1.42, + "learning_rate": 8.579239037453045e-06, + "loss": 1.928, + "step": 38200 + }, + { + "epoch": 1.42, + "eval_loss": 1.7379621267318726, + "eval_runtime": 16.8119, + "eval_samples_per_second": 59.482, + "eval_steps_per_second": 3.747, + "step": 38200 + }, + { + "epoch": 1.42, + "learning_rate": 8.578867110499498e-06, + "loss": 1.7575, + "step": 38210 + }, + { + "epoch": 1.42, + "learning_rate": 8.578495183545952e-06, + "loss": 1.7413, + "step": 38220 + }, + { + "epoch": 1.42, + "learning_rate": 8.578123256592405e-06, + "loss": 1.7348, + "step": 38230 + }, + { + "epoch": 1.42, + "learning_rate": 8.577751329638859e-06, + "loss": 1.8355, + "step": 38240 + }, + { + "epoch": 1.42, + "learning_rate": 8.577379402685312e-06, + "loss": 1.8273, + "step": 38250 + }, + { + "epoch": 1.42, + "learning_rate": 8.577007475731767e-06, + "loss": 1.8279, + "step": 38260 + }, + { + "epoch": 1.42, + "learning_rate": 8.57663554877822e-06, + "loss": 1.8622, + "step": 38270 + }, + { + "epoch": 1.42, + "learning_rate": 8.576263621824674e-06, + "loss": 1.7648, + "step": 38280 + }, + { + "epoch": 1.42, + "learning_rate": 8.575891694871128e-06, + "loss": 1.7668, + "step": 38290 + }, + { + "epoch": 1.42, + "learning_rate": 8.575519767917581e-06, + "loss": 1.8016, + "step": 38300 + }, + { + "epoch": 1.42, + "eval_loss": 1.73819100856781, + "eval_runtime": 16.8322, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 38300 + }, + { + "epoch": 1.42, + "learning_rate": 8.575147840964035e-06, + "loss": 1.7047, + "step": 38310 + }, + { + "epoch": 1.43, + "learning_rate": 8.57477591401049e-06, + "loss": 1.779, + "step": 38320 + }, + { + "epoch": 1.43, + "learning_rate": 8.574403987056943e-06, + "loss": 1.7036, + "step": 38330 + }, + { + "epoch": 1.43, + "learning_rate": 8.574032060103397e-06, + "loss": 1.6744, + "step": 38340 + }, + { + "epoch": 1.43, + "learning_rate": 8.57366013314985e-06, + "loss": 1.7698, + "step": 38350 + }, + { + "epoch": 1.43, + "learning_rate": 8.573288206196304e-06, + "loss": 1.8084, + "step": 38360 + }, + { + "epoch": 1.43, + "learning_rate": 8.572916279242757e-06, + "loss": 1.729, + "step": 38370 + }, + { + "epoch": 1.43, + "learning_rate": 8.572544352289212e-06, + "loss": 1.8078, + "step": 38380 + }, + { + "epoch": 1.43, + "learning_rate": 8.572172425335666e-06, + "loss": 1.7388, + "step": 38390 + }, + { + "epoch": 1.43, + "learning_rate": 8.571800498382117e-06, + "loss": 1.8035, + "step": 38400 + }, + { + "epoch": 1.43, + "eval_loss": 1.7371269464492798, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 38400 + }, + { + "epoch": 1.43, + "learning_rate": 8.571428571428571e-06, + "loss": 1.8061, + "step": 38410 + }, + { + "epoch": 1.43, + "learning_rate": 8.571056644475026e-06, + "loss": 1.7904, + "step": 38420 + }, + { + "epoch": 1.43, + "learning_rate": 8.57068471752148e-06, + "loss": 1.9713, + "step": 38430 + }, + { + "epoch": 1.43, + "learning_rate": 8.570312790567933e-06, + "loss": 1.8114, + "step": 38440 + }, + { + "epoch": 1.43, + "learning_rate": 8.569940863614386e-06, + "loss": 1.7724, + "step": 38450 + }, + { + "epoch": 1.43, + "learning_rate": 8.56956893666084e-06, + "loss": 1.7219, + "step": 38460 + }, + { + "epoch": 1.43, + "learning_rate": 8.569197009707293e-06, + "loss": 1.8454, + "step": 38470 + }, + { + "epoch": 1.43, + "learning_rate": 8.568825082753749e-06, + "loss": 1.72, + "step": 38480 + }, + { + "epoch": 1.43, + "learning_rate": 8.568453155800202e-06, + "loss": 1.7453, + "step": 38490 + }, + { + "epoch": 1.43, + "learning_rate": 8.568081228846655e-06, + "loss": 1.7695, + "step": 38500 + }, + { + "epoch": 1.43, + "eval_loss": 1.7370373010635376, + "eval_runtime": 16.8011, + "eval_samples_per_second": 59.52, + "eval_steps_per_second": 3.75, + "step": 38500 + }, + { + "epoch": 1.43, + "learning_rate": 8.567709301893109e-06, + "loss": 1.8718, + "step": 38510 + }, + { + "epoch": 1.43, + "learning_rate": 8.567337374939562e-06, + "loss": 1.6846, + "step": 38520 + }, + { + "epoch": 1.43, + "learning_rate": 8.566965447986016e-06, + "loss": 1.781, + "step": 38530 + }, + { + "epoch": 1.43, + "learning_rate": 8.566593521032471e-06, + "loss": 1.7748, + "step": 38540 + }, + { + "epoch": 1.43, + "learning_rate": 8.566221594078924e-06, + "loss": 1.7421, + "step": 38550 + }, + { + "epoch": 1.43, + "learning_rate": 8.565849667125378e-06, + "loss": 1.9033, + "step": 38560 + }, + { + "epoch": 1.43, + "learning_rate": 8.565477740171831e-06, + "loss": 1.7818, + "step": 38570 + }, + { + "epoch": 1.43, + "learning_rate": 8.565105813218285e-06, + "loss": 1.7577, + "step": 38580 + }, + { + "epoch": 1.44, + "learning_rate": 8.564733886264738e-06, + "loss": 1.8905, + "step": 38590 + }, + { + "epoch": 1.44, + "learning_rate": 8.564361959311192e-06, + "loss": 1.7199, + "step": 38600 + }, + { + "epoch": 1.44, + "eval_loss": 1.7372485399246216, + "eval_runtime": 16.8098, + "eval_samples_per_second": 59.489, + "eval_steps_per_second": 3.748, + "step": 38600 + }, + { + "epoch": 1.44, + "learning_rate": 8.563990032357645e-06, + "loss": 1.8444, + "step": 38610 + }, + { + "epoch": 1.44, + "learning_rate": 8.563618105404099e-06, + "loss": 1.8247, + "step": 38620 + }, + { + "epoch": 1.44, + "learning_rate": 8.563246178450552e-06, + "loss": 1.9082, + "step": 38630 + }, + { + "epoch": 1.44, + "learning_rate": 8.562874251497007e-06, + "loss": 1.7537, + "step": 38640 + }, + { + "epoch": 1.44, + "learning_rate": 8.56250232454346e-06, + "loss": 1.7203, + "step": 38650 + }, + { + "epoch": 1.44, + "learning_rate": 8.562130397589914e-06, + "loss": 1.9788, + "step": 38660 + }, + { + "epoch": 1.44, + "learning_rate": 8.561758470636368e-06, + "loss": 1.8102, + "step": 38670 + }, + { + "epoch": 1.44, + "learning_rate": 8.561386543682821e-06, + "loss": 1.814, + "step": 38680 + }, + { + "epoch": 1.44, + "learning_rate": 8.561014616729275e-06, + "loss": 1.8073, + "step": 38690 + }, + { + "epoch": 1.44, + "learning_rate": 8.56064268977573e-06, + "loss": 1.7127, + "step": 38700 + }, + { + "epoch": 1.44, + "eval_loss": 1.7362797260284424, + "eval_runtime": 16.8113, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.747, + "step": 38700 + }, + { + "epoch": 1.44, + "learning_rate": 8.560270762822183e-06, + "loss": 1.7861, + "step": 38710 + }, + { + "epoch": 1.44, + "learning_rate": 8.559898835868637e-06, + "loss": 1.7987, + "step": 38720 + }, + { + "epoch": 1.44, + "learning_rate": 8.55952690891509e-06, + "loss": 1.8524, + "step": 38730 + }, + { + "epoch": 1.44, + "learning_rate": 8.559154981961544e-06, + "loss": 1.8456, + "step": 38740 + }, + { + "epoch": 1.44, + "learning_rate": 8.558783055007997e-06, + "loss": 1.8435, + "step": 38750 + }, + { + "epoch": 1.44, + "learning_rate": 8.55841112805445e-06, + "loss": 1.7818, + "step": 38760 + }, + { + "epoch": 1.44, + "learning_rate": 8.558039201100906e-06, + "loss": 1.8299, + "step": 38770 + }, + { + "epoch": 1.44, + "learning_rate": 8.557667274147357e-06, + "loss": 1.6692, + "step": 38780 + }, + { + "epoch": 1.44, + "learning_rate": 8.55729534719381e-06, + "loss": 1.9212, + "step": 38790 + }, + { + "epoch": 1.44, + "learning_rate": 8.556923420240264e-06, + "loss": 1.8909, + "step": 38800 + }, + { + "epoch": 1.44, + "eval_loss": 1.7367039918899536, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 38800 + }, + { + "epoch": 1.44, + "learning_rate": 8.55655149328672e-06, + "loss": 1.7574, + "step": 38810 + }, + { + "epoch": 1.44, + "learning_rate": 8.556179566333173e-06, + "loss": 1.7895, + "step": 38820 + }, + { + "epoch": 1.44, + "learning_rate": 8.555807639379626e-06, + "loss": 1.8558, + "step": 38830 + }, + { + "epoch": 1.44, + "learning_rate": 8.55543571242608e-06, + "loss": 1.7565, + "step": 38840 + }, + { + "epoch": 1.44, + "learning_rate": 8.555063785472533e-06, + "loss": 1.7684, + "step": 38850 + }, + { + "epoch": 1.45, + "learning_rate": 8.554691858518987e-06, + "loss": 1.8555, + "step": 38860 + }, + { + "epoch": 1.45, + "learning_rate": 8.554319931565442e-06, + "loss": 1.7799, + "step": 38870 + }, + { + "epoch": 1.45, + "learning_rate": 8.553948004611895e-06, + "loss": 1.6442, + "step": 38880 + }, + { + "epoch": 1.45, + "learning_rate": 8.553576077658349e-06, + "loss": 1.8027, + "step": 38890 + }, + { + "epoch": 1.45, + "learning_rate": 8.553204150704802e-06, + "loss": 1.7449, + "step": 38900 + }, + { + "epoch": 1.45, + "eval_loss": 1.735575556755066, + "eval_runtime": 16.8142, + "eval_samples_per_second": 59.474, + "eval_steps_per_second": 3.747, + "step": 38900 + }, + { + "epoch": 1.45, + "learning_rate": 8.552832223751256e-06, + "loss": 1.8097, + "step": 38910 + }, + { + "epoch": 1.45, + "learning_rate": 8.55246029679771e-06, + "loss": 1.7251, + "step": 38920 + }, + { + "epoch": 1.45, + "learning_rate": 8.552088369844164e-06, + "loss": 1.8155, + "step": 38930 + }, + { + "epoch": 1.45, + "learning_rate": 8.551716442890618e-06, + "loss": 1.924, + "step": 38940 + }, + { + "epoch": 1.45, + "learning_rate": 8.551344515937071e-06, + "loss": 1.7442, + "step": 38950 + }, + { + "epoch": 1.45, + "learning_rate": 8.550972588983523e-06, + "loss": 1.6911, + "step": 38960 + }, + { + "epoch": 1.45, + "learning_rate": 8.550600662029978e-06, + "loss": 1.9471, + "step": 38970 + }, + { + "epoch": 1.45, + "learning_rate": 8.550228735076432e-06, + "loss": 1.9495, + "step": 38980 + }, + { + "epoch": 1.45, + "learning_rate": 8.549856808122885e-06, + "loss": 1.876, + "step": 38990 + }, + { + "epoch": 1.45, + "learning_rate": 8.549484881169339e-06, + "loss": 1.7618, + "step": 39000 + }, + { + "epoch": 1.45, + "eval_loss": 1.735635757446289, + "eval_runtime": 16.822, + "eval_samples_per_second": 59.446, + "eval_steps_per_second": 3.745, + "step": 39000 + }, + { + "epoch": 1.45, + "learning_rate": 8.549112954215792e-06, + "loss": 1.7674, + "step": 39010 + }, + { + "epoch": 1.45, + "learning_rate": 8.548741027262245e-06, + "loss": 1.9594, + "step": 39020 + }, + { + "epoch": 1.45, + "learning_rate": 8.5483691003087e-06, + "loss": 1.6604, + "step": 39030 + }, + { + "epoch": 1.45, + "learning_rate": 8.547997173355154e-06, + "loss": 1.7893, + "step": 39040 + }, + { + "epoch": 1.45, + "learning_rate": 8.547625246401608e-06, + "loss": 1.7274, + "step": 39050 + }, + { + "epoch": 1.45, + "learning_rate": 8.547253319448061e-06, + "loss": 1.77, + "step": 39060 + }, + { + "epoch": 1.45, + "learning_rate": 8.546881392494514e-06, + "loss": 1.7212, + "step": 39070 + }, + { + "epoch": 1.45, + "learning_rate": 8.546509465540968e-06, + "loss": 1.8287, + "step": 39080 + }, + { + "epoch": 1.45, + "learning_rate": 8.546137538587423e-06, + "loss": 1.7201, + "step": 39090 + }, + { + "epoch": 1.45, + "learning_rate": 8.545765611633877e-06, + "loss": 1.6891, + "step": 39100 + }, + { + "epoch": 1.45, + "eval_loss": 1.7352875471115112, + "eval_runtime": 16.8124, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 39100 + }, + { + "epoch": 1.45, + "learning_rate": 8.54539368468033e-06, + "loss": 1.9087, + "step": 39110 + }, + { + "epoch": 1.45, + "learning_rate": 8.545021757726783e-06, + "loss": 1.6993, + "step": 39120 + }, + { + "epoch": 1.46, + "learning_rate": 8.544649830773237e-06, + "loss": 1.615, + "step": 39130 + }, + { + "epoch": 1.46, + "learning_rate": 8.54427790381969e-06, + "loss": 1.899, + "step": 39140 + }, + { + "epoch": 1.46, + "learning_rate": 8.543905976866144e-06, + "loss": 1.7555, + "step": 39150 + }, + { + "epoch": 1.46, + "learning_rate": 8.543534049912597e-06, + "loss": 1.7491, + "step": 39160 + }, + { + "epoch": 1.46, + "learning_rate": 8.54316212295905e-06, + "loss": 1.7214, + "step": 39170 + }, + { + "epoch": 1.46, + "learning_rate": 8.542790196005504e-06, + "loss": 1.7549, + "step": 39180 + }, + { + "epoch": 1.46, + "learning_rate": 8.54241826905196e-06, + "loss": 1.7908, + "step": 39190 + }, + { + "epoch": 1.46, + "learning_rate": 8.542046342098413e-06, + "loss": 1.927, + "step": 39200 + }, + { + "epoch": 1.46, + "eval_loss": 1.7349416017532349, + "eval_runtime": 16.8098, + "eval_samples_per_second": 59.489, + "eval_steps_per_second": 3.748, + "step": 39200 + }, + { + "epoch": 1.46, + "learning_rate": 8.541674415144866e-06, + "loss": 1.6554, + "step": 39210 + }, + { + "epoch": 1.46, + "learning_rate": 8.54130248819132e-06, + "loss": 1.8361, + "step": 39220 + }, + { + "epoch": 1.46, + "learning_rate": 8.540930561237773e-06, + "loss": 1.8428, + "step": 39230 + }, + { + "epoch": 1.46, + "learning_rate": 8.540558634284227e-06, + "loss": 1.7977, + "step": 39240 + }, + { + "epoch": 1.46, + "learning_rate": 8.540186707330682e-06, + "loss": 1.8221, + "step": 39250 + }, + { + "epoch": 1.46, + "learning_rate": 8.539814780377135e-06, + "loss": 1.9343, + "step": 39260 + }, + { + "epoch": 1.46, + "learning_rate": 8.539442853423589e-06, + "loss": 1.9957, + "step": 39270 + }, + { + "epoch": 1.46, + "learning_rate": 8.539070926470042e-06, + "loss": 1.8181, + "step": 39280 + }, + { + "epoch": 1.46, + "learning_rate": 8.538698999516496e-06, + "loss": 1.8308, + "step": 39290 + }, + { + "epoch": 1.46, + "learning_rate": 8.538327072562949e-06, + "loss": 1.8101, + "step": 39300 + }, + { + "epoch": 1.46, + "eval_loss": 1.735397219657898, + "eval_runtime": 16.8205, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 39300 + }, + { + "epoch": 1.46, + "learning_rate": 8.537955145609403e-06, + "loss": 1.7974, + "step": 39310 + }, + { + "epoch": 1.46, + "learning_rate": 8.537583218655858e-06, + "loss": 1.7778, + "step": 39320 + }, + { + "epoch": 1.46, + "learning_rate": 8.537211291702311e-06, + "loss": 1.7346, + "step": 39330 + }, + { + "epoch": 1.46, + "learning_rate": 8.536839364748763e-06, + "loss": 1.9199, + "step": 39340 + }, + { + "epoch": 1.46, + "learning_rate": 8.536467437795216e-06, + "loss": 1.8492, + "step": 39350 + }, + { + "epoch": 1.46, + "learning_rate": 8.536095510841672e-06, + "loss": 1.74, + "step": 39360 + }, + { + "epoch": 1.46, + "learning_rate": 8.535723583888125e-06, + "loss": 1.6839, + "step": 39370 + }, + { + "epoch": 1.46, + "learning_rate": 8.535351656934578e-06, + "loss": 1.8502, + "step": 39380 + }, + { + "epoch": 1.47, + "learning_rate": 8.534979729981032e-06, + "loss": 1.8493, + "step": 39390 + }, + { + "epoch": 1.47, + "learning_rate": 8.534607803027485e-06, + "loss": 1.7916, + "step": 39400 + }, + { + "epoch": 1.47, + "eval_loss": 1.7347898483276367, + "eval_runtime": 16.809, + "eval_samples_per_second": 59.492, + "eval_steps_per_second": 3.748, + "step": 39400 + }, + { + "epoch": 1.47, + "learning_rate": 8.534235876073939e-06, + "loss": 1.8678, + "step": 39410 + }, + { + "epoch": 1.47, + "learning_rate": 8.533863949120394e-06, + "loss": 1.7709, + "step": 39420 + }, + { + "epoch": 1.47, + "learning_rate": 8.533492022166847e-06, + "loss": 1.779, + "step": 39430 + }, + { + "epoch": 1.47, + "learning_rate": 8.533120095213301e-06, + "loss": 1.8621, + "step": 39440 + }, + { + "epoch": 1.47, + "learning_rate": 8.532748168259754e-06, + "loss": 1.8098, + "step": 39450 + }, + { + "epoch": 1.47, + "learning_rate": 8.532376241306208e-06, + "loss": 1.7861, + "step": 39460 + }, + { + "epoch": 1.47, + "learning_rate": 8.532004314352661e-06, + "loss": 1.9089, + "step": 39470 + }, + { + "epoch": 1.47, + "learning_rate": 8.531632387399116e-06, + "loss": 1.8602, + "step": 39480 + }, + { + "epoch": 1.47, + "learning_rate": 8.53126046044557e-06, + "loss": 1.6905, + "step": 39490 + }, + { + "epoch": 1.47, + "learning_rate": 8.530888533492023e-06, + "loss": 1.7868, + "step": 39500 + }, + { + "epoch": 1.47, + "eval_loss": 1.7346025705337524, + "eval_runtime": 16.8128, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 39500 + }, + { + "epoch": 1.47, + "learning_rate": 8.530516606538477e-06, + "loss": 1.7676, + "step": 39510 + }, + { + "epoch": 1.47, + "learning_rate": 8.53014467958493e-06, + "loss": 2.1928, + "step": 39520 + }, + { + "epoch": 1.47, + "learning_rate": 8.529772752631384e-06, + "loss": 1.8849, + "step": 39530 + }, + { + "epoch": 1.47, + "learning_rate": 8.529400825677837e-06, + "loss": 1.814, + "step": 39540 + }, + { + "epoch": 1.47, + "learning_rate": 8.52902889872429e-06, + "loss": 1.6285, + "step": 39550 + }, + { + "epoch": 1.47, + "learning_rate": 8.528656971770744e-06, + "loss": 1.7347, + "step": 39560 + }, + { + "epoch": 1.47, + "learning_rate": 8.528285044817198e-06, + "loss": 1.9513, + "step": 39570 + }, + { + "epoch": 1.47, + "learning_rate": 8.527913117863653e-06, + "loss": 1.8001, + "step": 39580 + }, + { + "epoch": 1.47, + "learning_rate": 8.527541190910106e-06, + "loss": 1.8769, + "step": 39590 + }, + { + "epoch": 1.47, + "learning_rate": 8.52716926395656e-06, + "loss": 1.8872, + "step": 39600 + }, + { + "epoch": 1.47, + "eval_loss": 1.7355339527130127, + "eval_runtime": 16.8067, + "eval_samples_per_second": 59.5, + "eval_steps_per_second": 3.749, + "step": 39600 + }, + { + "epoch": 1.47, + "learning_rate": 8.526797337003013e-06, + "loss": 1.7802, + "step": 39610 + }, + { + "epoch": 1.47, + "learning_rate": 8.526425410049467e-06, + "loss": 1.8025, + "step": 39620 + }, + { + "epoch": 1.47, + "learning_rate": 8.52605348309592e-06, + "loss": 1.8834, + "step": 39630 + }, + { + "epoch": 1.47, + "learning_rate": 8.525681556142375e-06, + "loss": 1.8053, + "step": 39640 + }, + { + "epoch": 1.47, + "learning_rate": 8.525309629188829e-06, + "loss": 1.8427, + "step": 39650 + }, + { + "epoch": 1.48, + "learning_rate": 8.524937702235282e-06, + "loss": 1.7185, + "step": 39660 + }, + { + "epoch": 1.48, + "learning_rate": 8.524565775281736e-06, + "loss": 1.7339, + "step": 39670 + }, + { + "epoch": 1.48, + "learning_rate": 8.524193848328189e-06, + "loss": 1.7681, + "step": 39680 + }, + { + "epoch": 1.48, + "learning_rate": 8.523821921374642e-06, + "loss": 1.7064, + "step": 39690 + }, + { + "epoch": 1.48, + "learning_rate": 8.523449994421098e-06, + "loss": 1.7737, + "step": 39700 + }, + { + "epoch": 1.48, + "eval_loss": 1.734574794769287, + "eval_runtime": 16.8131, + "eval_samples_per_second": 59.478, + "eval_steps_per_second": 3.747, + "step": 39700 + }, + { + "epoch": 1.48, + "learning_rate": 8.523078067467551e-06, + "loss": 1.8157, + "step": 39710 + }, + { + "epoch": 1.48, + "learning_rate": 8.522706140514003e-06, + "loss": 1.7978, + "step": 39720 + }, + { + "epoch": 1.48, + "learning_rate": 8.522334213560456e-06, + "loss": 1.7713, + "step": 39730 + }, + { + "epoch": 1.48, + "learning_rate": 8.521962286606911e-06, + "loss": 1.7711, + "step": 39740 + }, + { + "epoch": 1.48, + "learning_rate": 8.521590359653365e-06, + "loss": 1.8344, + "step": 39750 + }, + { + "epoch": 1.48, + "learning_rate": 8.521218432699818e-06, + "loss": 1.9488, + "step": 39760 + }, + { + "epoch": 1.48, + "learning_rate": 8.520846505746272e-06, + "loss": 1.8719, + "step": 39770 + }, + { + "epoch": 1.48, + "learning_rate": 8.520474578792725e-06, + "loss": 1.7178, + "step": 39780 + }, + { + "epoch": 1.48, + "learning_rate": 8.520102651839179e-06, + "loss": 1.7619, + "step": 39790 + }, + { + "epoch": 1.48, + "learning_rate": 8.519730724885634e-06, + "loss": 1.7978, + "step": 39800 + }, + { + "epoch": 1.48, + "eval_loss": 1.734641671180725, + "eval_runtime": 16.823, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 39800 + }, + { + "epoch": 1.48, + "learning_rate": 8.519358797932087e-06, + "loss": 1.9639, + "step": 39810 + }, + { + "epoch": 1.48, + "learning_rate": 8.518986870978541e-06, + "loss": 1.728, + "step": 39820 + }, + { + "epoch": 1.48, + "learning_rate": 8.518614944024994e-06, + "loss": 1.8219, + "step": 39830 + }, + { + "epoch": 1.48, + "learning_rate": 8.518243017071448e-06, + "loss": 1.8326, + "step": 39840 + }, + { + "epoch": 1.48, + "learning_rate": 8.517871090117901e-06, + "loss": 1.761, + "step": 39850 + }, + { + "epoch": 1.48, + "learning_rate": 8.517499163164356e-06, + "loss": 1.9071, + "step": 39860 + }, + { + "epoch": 1.48, + "learning_rate": 8.51712723621081e-06, + "loss": 1.8133, + "step": 39870 + }, + { + "epoch": 1.48, + "learning_rate": 8.516755309257263e-06, + "loss": 1.7811, + "step": 39880 + }, + { + "epoch": 1.48, + "learning_rate": 8.516383382303717e-06, + "loss": 1.7299, + "step": 39890 + }, + { + "epoch": 1.48, + "learning_rate": 8.51601145535017e-06, + "loss": 1.6835, + "step": 39900 + }, + { + "epoch": 1.48, + "eval_loss": 1.7349793910980225, + "eval_runtime": 16.8343, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 39900 + }, + { + "epoch": 1.48, + "learning_rate": 8.515639528396624e-06, + "loss": 1.7722, + "step": 39910 + }, + { + "epoch": 1.48, + "learning_rate": 8.515267601443077e-06, + "loss": 1.8298, + "step": 39920 + }, + { + "epoch": 1.49, + "learning_rate": 8.51489567448953e-06, + "loss": 1.8618, + "step": 39930 + }, + { + "epoch": 1.49, + "learning_rate": 8.514523747535984e-06, + "loss": 1.7869, + "step": 39940 + }, + { + "epoch": 1.49, + "learning_rate": 8.514151820582438e-06, + "loss": 1.8402, + "step": 39950 + }, + { + "epoch": 1.49, + "learning_rate": 8.513779893628891e-06, + "loss": 1.8916, + "step": 39960 + }, + { + "epoch": 1.49, + "learning_rate": 8.513407966675346e-06, + "loss": 1.8028, + "step": 39970 + }, + { + "epoch": 1.49, + "learning_rate": 8.5130360397218e-06, + "loss": 1.7794, + "step": 39980 + }, + { + "epoch": 1.49, + "learning_rate": 8.512664112768253e-06, + "loss": 1.7854, + "step": 39990 + }, + { + "epoch": 1.49, + "learning_rate": 8.512292185814707e-06, + "loss": 1.807, + "step": 40000 + }, + { + "epoch": 1.49, + "eval_loss": 1.7345820665359497, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 40000 + }, + { + "epoch": 1.49, + "learning_rate": 8.51192025886116e-06, + "loss": 1.6909, + "step": 40010 + }, + { + "epoch": 1.49, + "learning_rate": 8.511548331907613e-06, + "loss": 1.8313, + "step": 40020 + }, + { + "epoch": 1.49, + "learning_rate": 8.511176404954069e-06, + "loss": 1.7851, + "step": 40030 + }, + { + "epoch": 1.49, + "learning_rate": 8.510804478000522e-06, + "loss": 1.8909, + "step": 40040 + }, + { + "epoch": 1.49, + "learning_rate": 8.510432551046975e-06, + "loss": 1.7031, + "step": 40050 + }, + { + "epoch": 1.49, + "learning_rate": 8.510060624093429e-06, + "loss": 1.9088, + "step": 40060 + }, + { + "epoch": 1.49, + "learning_rate": 8.509688697139882e-06, + "loss": 1.8038, + "step": 40070 + }, + { + "epoch": 1.49, + "learning_rate": 8.509316770186336e-06, + "loss": 1.8113, + "step": 40080 + }, + { + "epoch": 1.49, + "learning_rate": 8.50894484323279e-06, + "loss": 1.8584, + "step": 40090 + }, + { + "epoch": 1.49, + "learning_rate": 8.508572916279243e-06, + "loss": 1.7639, + "step": 40100 + }, + { + "epoch": 1.49, + "eval_loss": 1.7336865663528442, + "eval_runtime": 16.8389, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 40100 + }, + { + "epoch": 1.49, + "learning_rate": 8.508200989325696e-06, + "loss": 1.8123, + "step": 40110 + }, + { + "epoch": 1.49, + "learning_rate": 8.50782906237215e-06, + "loss": 1.7238, + "step": 40120 + }, + { + "epoch": 1.49, + "learning_rate": 8.507457135418605e-06, + "loss": 1.838, + "step": 40130 + }, + { + "epoch": 1.49, + "learning_rate": 8.507085208465058e-06, + "loss": 1.8098, + "step": 40140 + }, + { + "epoch": 1.49, + "learning_rate": 8.506713281511512e-06, + "loss": 1.8138, + "step": 40150 + }, + { + "epoch": 1.49, + "learning_rate": 8.506341354557965e-06, + "loss": 1.7379, + "step": 40160 + }, + { + "epoch": 1.49, + "learning_rate": 8.505969427604419e-06, + "loss": 1.7453, + "step": 40170 + }, + { + "epoch": 1.49, + "learning_rate": 8.505597500650872e-06, + "loss": 1.7151, + "step": 40180 + }, + { + "epoch": 1.49, + "learning_rate": 8.505225573697327e-06, + "loss": 1.8259, + "step": 40190 + }, + { + "epoch": 1.5, + "learning_rate": 8.50485364674378e-06, + "loss": 1.7724, + "step": 40200 + }, + { + "epoch": 1.5, + "eval_loss": 1.734347939491272, + "eval_runtime": 16.8295, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 40200 + }, + { + "epoch": 1.5, + "learning_rate": 8.504481719790234e-06, + "loss": 1.7272, + "step": 40210 + }, + { + "epoch": 1.5, + "learning_rate": 8.504109792836688e-06, + "loss": 1.825, + "step": 40220 + }, + { + "epoch": 1.5, + "learning_rate": 8.503737865883141e-06, + "loss": 1.92, + "step": 40230 + }, + { + "epoch": 1.5, + "learning_rate": 8.503365938929595e-06, + "loss": 1.6164, + "step": 40240 + }, + { + "epoch": 1.5, + "learning_rate": 8.50299401197605e-06, + "loss": 1.7346, + "step": 40250 + }, + { + "epoch": 1.5, + "learning_rate": 8.502622085022503e-06, + "loss": 1.7658, + "step": 40260 + }, + { + "epoch": 1.5, + "learning_rate": 8.502250158068957e-06, + "loss": 1.9462, + "step": 40270 + }, + { + "epoch": 1.5, + "learning_rate": 8.501878231115408e-06, + "loss": 2.0018, + "step": 40280 + }, + { + "epoch": 1.5, + "learning_rate": 8.501506304161864e-06, + "loss": 1.7538, + "step": 40290 + }, + { + "epoch": 1.5, + "learning_rate": 8.501134377208317e-06, + "loss": 1.7122, + "step": 40300 + }, + { + "epoch": 1.5, + "eval_loss": 1.7321808338165283, + "eval_runtime": 16.8419, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 40300 + }, + { + "epoch": 1.5, + "learning_rate": 8.50076245025477e-06, + "loss": 1.8015, + "step": 40310 + }, + { + "epoch": 1.5, + "learning_rate": 8.500390523301224e-06, + "loss": 1.8319, + "step": 40320 + }, + { + "epoch": 1.5, + "learning_rate": 8.500018596347677e-06, + "loss": 1.7798, + "step": 40330 + }, + { + "epoch": 1.5, + "learning_rate": 8.499646669394131e-06, + "loss": 1.7635, + "step": 40340 + }, + { + "epoch": 1.5, + "learning_rate": 8.499274742440586e-06, + "loss": 1.8032, + "step": 40350 + }, + { + "epoch": 1.5, + "learning_rate": 8.49890281548704e-06, + "loss": 1.8102, + "step": 40360 + }, + { + "epoch": 1.5, + "learning_rate": 8.498530888533493e-06, + "loss": 1.8516, + "step": 40370 + }, + { + "epoch": 1.5, + "learning_rate": 8.498158961579946e-06, + "loss": 1.7883, + "step": 40380 + }, + { + "epoch": 1.5, + "learning_rate": 8.4977870346264e-06, + "loss": 1.7912, + "step": 40390 + }, + { + "epoch": 1.5, + "learning_rate": 8.497415107672853e-06, + "loss": 1.7949, + "step": 40400 + }, + { + "epoch": 1.5, + "eval_loss": 1.7326602935791016, + "eval_runtime": 16.832, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 40400 + }, + { + "epoch": 1.5, + "learning_rate": 8.497043180719308e-06, + "loss": 1.803, + "step": 40410 + }, + { + "epoch": 1.5, + "learning_rate": 8.496671253765762e-06, + "loss": 1.7024, + "step": 40420 + }, + { + "epoch": 1.5, + "learning_rate": 8.496299326812215e-06, + "loss": 1.9167, + "step": 40430 + }, + { + "epoch": 1.5, + "learning_rate": 8.495927399858669e-06, + "loss": 1.7733, + "step": 40440 + }, + { + "epoch": 1.5, + "learning_rate": 8.495555472905122e-06, + "loss": 1.724, + "step": 40450 + }, + { + "epoch": 1.5, + "learning_rate": 8.495183545951576e-06, + "loss": 1.8885, + "step": 40460 + }, + { + "epoch": 1.51, + "learning_rate": 8.49481161899803e-06, + "loss": 1.8311, + "step": 40470 + }, + { + "epoch": 1.51, + "learning_rate": 8.494439692044483e-06, + "loss": 1.7687, + "step": 40480 + }, + { + "epoch": 1.51, + "learning_rate": 8.494067765090936e-06, + "loss": 1.7817, + "step": 40490 + }, + { + "epoch": 1.51, + "learning_rate": 8.49369583813739e-06, + "loss": 1.7887, + "step": 40500 + }, + { + "epoch": 1.51, + "eval_loss": 1.7329816818237305, + "eval_runtime": 16.8216, + "eval_samples_per_second": 59.447, + "eval_steps_per_second": 3.745, + "step": 40500 + }, + { + "epoch": 1.51, + "learning_rate": 8.493323911183843e-06, + "loss": 1.7723, + "step": 40510 + }, + { + "epoch": 1.51, + "learning_rate": 8.492951984230298e-06, + "loss": 1.7802, + "step": 40520 + }, + { + "epoch": 1.51, + "learning_rate": 8.492580057276752e-06, + "loss": 1.7333, + "step": 40530 + }, + { + "epoch": 1.51, + "learning_rate": 8.492208130323205e-06, + "loss": 1.7383, + "step": 40540 + }, + { + "epoch": 1.51, + "learning_rate": 8.491836203369659e-06, + "loss": 1.8004, + "step": 40550 + }, + { + "epoch": 1.51, + "learning_rate": 8.491464276416112e-06, + "loss": 1.7498, + "step": 40560 + }, + { + "epoch": 1.51, + "learning_rate": 8.491092349462566e-06, + "loss": 1.8298, + "step": 40570 + }, + { + "epoch": 1.51, + "learning_rate": 8.49072042250902e-06, + "loss": 1.8055, + "step": 40580 + }, + { + "epoch": 1.51, + "learning_rate": 8.490348495555474e-06, + "loss": 1.8286, + "step": 40590 + }, + { + "epoch": 1.51, + "learning_rate": 8.489976568601928e-06, + "loss": 1.7689, + "step": 40600 + }, + { + "epoch": 1.51, + "eval_loss": 1.7321631908416748, + "eval_runtime": 16.8234, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 40600 + }, + { + "epoch": 1.51, + "learning_rate": 8.489604641648381e-06, + "loss": 1.8274, + "step": 40610 + }, + { + "epoch": 1.51, + "learning_rate": 8.489232714694835e-06, + "loss": 1.7504, + "step": 40620 + }, + { + "epoch": 1.51, + "learning_rate": 8.488860787741288e-06, + "loss": 1.8176, + "step": 40630 + }, + { + "epoch": 1.51, + "learning_rate": 8.488488860787743e-06, + "loss": 1.8742, + "step": 40640 + }, + { + "epoch": 1.51, + "learning_rate": 8.488116933834195e-06, + "loss": 1.7595, + "step": 40650 + }, + { + "epoch": 1.51, + "learning_rate": 8.487745006880648e-06, + "loss": 1.7007, + "step": 40660 + }, + { + "epoch": 1.51, + "learning_rate": 8.487373079927102e-06, + "loss": 1.9444, + "step": 40670 + }, + { + "epoch": 1.51, + "learning_rate": 8.487001152973557e-06, + "loss": 1.7452, + "step": 40680 + }, + { + "epoch": 1.51, + "learning_rate": 8.48662922602001e-06, + "loss": 1.7751, + "step": 40690 + }, + { + "epoch": 1.51, + "learning_rate": 8.486257299066464e-06, + "loss": 1.8599, + "step": 40700 + }, + { + "epoch": 1.51, + "eval_loss": 1.7319841384887695, + "eval_runtime": 16.8205, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 40700 + }, + { + "epoch": 1.51, + "learning_rate": 8.485885372112917e-06, + "loss": 1.8798, + "step": 40710 + }, + { + "epoch": 1.51, + "learning_rate": 8.48551344515937e-06, + "loss": 1.7211, + "step": 40720 + }, + { + "epoch": 1.51, + "learning_rate": 8.485141518205824e-06, + "loss": 1.827, + "step": 40730 + }, + { + "epoch": 1.52, + "learning_rate": 8.48476959125228e-06, + "loss": 1.7404, + "step": 40740 + }, + { + "epoch": 1.52, + "learning_rate": 8.484397664298733e-06, + "loss": 1.8947, + "step": 40750 + }, + { + "epoch": 1.52, + "learning_rate": 8.484025737345186e-06, + "loss": 1.785, + "step": 40760 + }, + { + "epoch": 1.52, + "learning_rate": 8.48365381039164e-06, + "loss": 1.8706, + "step": 40770 + }, + { + "epoch": 1.52, + "learning_rate": 8.483281883438093e-06, + "loss": 1.8027, + "step": 40780 + }, + { + "epoch": 1.52, + "learning_rate": 8.482909956484547e-06, + "loss": 1.7576, + "step": 40790 + }, + { + "epoch": 1.52, + "learning_rate": 8.482538029531002e-06, + "loss": 1.6302, + "step": 40800 + }, + { + "epoch": 1.52, + "eval_loss": 1.731594443321228, + "eval_runtime": 16.8115, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 40800 + }, + { + "epoch": 1.52, + "learning_rate": 8.482166102577455e-06, + "loss": 1.834, + "step": 40810 + }, + { + "epoch": 1.52, + "learning_rate": 8.481794175623909e-06, + "loss": 1.7533, + "step": 40820 + }, + { + "epoch": 1.52, + "learning_rate": 8.481422248670362e-06, + "loss": 1.6861, + "step": 40830 + }, + { + "epoch": 1.52, + "learning_rate": 8.481050321716816e-06, + "loss": 1.8249, + "step": 40840 + }, + { + "epoch": 1.52, + "learning_rate": 8.48067839476327e-06, + "loss": 1.7183, + "step": 40850 + }, + { + "epoch": 1.52, + "learning_rate": 8.480306467809723e-06, + "loss": 1.828, + "step": 40860 + }, + { + "epoch": 1.52, + "learning_rate": 8.479934540856176e-06, + "loss": 1.7216, + "step": 40870 + }, + { + "epoch": 1.52, + "learning_rate": 8.47956261390263e-06, + "loss": 1.7683, + "step": 40880 + }, + { + "epoch": 1.52, + "learning_rate": 8.479190686949083e-06, + "loss": 1.7699, + "step": 40890 + }, + { + "epoch": 1.52, + "learning_rate": 8.478818759995538e-06, + "loss": 1.8372, + "step": 40900 + }, + { + "epoch": 1.52, + "eval_loss": 1.7310887575149536, + "eval_runtime": 16.8405, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 40900 + }, + { + "epoch": 1.52, + "learning_rate": 8.478446833041992e-06, + "loss": 1.7323, + "step": 40910 + }, + { + "epoch": 1.52, + "learning_rate": 8.478074906088445e-06, + "loss": 1.905, + "step": 40920 + }, + { + "epoch": 1.52, + "learning_rate": 8.477702979134899e-06, + "loss": 1.8906, + "step": 40930 + }, + { + "epoch": 1.52, + "learning_rate": 8.477331052181352e-06, + "loss": 1.7806, + "step": 40940 + }, + { + "epoch": 1.52, + "learning_rate": 8.476959125227805e-06, + "loss": 1.7507, + "step": 40950 + }, + { + "epoch": 1.52, + "learning_rate": 8.47658719827426e-06, + "loss": 1.9574, + "step": 40960 + }, + { + "epoch": 1.52, + "learning_rate": 8.476215271320714e-06, + "loss": 1.7118, + "step": 40970 + }, + { + "epoch": 1.52, + "learning_rate": 8.475843344367168e-06, + "loss": 1.7523, + "step": 40980 + }, + { + "epoch": 1.52, + "learning_rate": 8.475471417413621e-06, + "loss": 1.8109, + "step": 40990 + }, + { + "epoch": 1.52, + "learning_rate": 8.475099490460074e-06, + "loss": 1.8044, + "step": 41000 + }, + { + "epoch": 1.52, + "eval_loss": 1.731567144393921, + "eval_runtime": 16.8311, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 41000 + }, + { + "epoch": 1.53, + "learning_rate": 8.474727563506528e-06, + "loss": 1.8754, + "step": 41010 + }, + { + "epoch": 1.53, + "learning_rate": 8.474355636552983e-06, + "loss": 1.7849, + "step": 41020 + }, + { + "epoch": 1.53, + "learning_rate": 8.473983709599435e-06, + "loss": 1.8609, + "step": 41030 + }, + { + "epoch": 1.53, + "learning_rate": 8.473611782645888e-06, + "loss": 1.7652, + "step": 41040 + }, + { + "epoch": 1.53, + "learning_rate": 8.473239855692342e-06, + "loss": 1.8357, + "step": 41050 + }, + { + "epoch": 1.53, + "learning_rate": 8.472867928738797e-06, + "loss": 1.7441, + "step": 41060 + }, + { + "epoch": 1.53, + "learning_rate": 8.47249600178525e-06, + "loss": 1.7643, + "step": 41070 + }, + { + "epoch": 1.53, + "learning_rate": 8.472124074831704e-06, + "loss": 1.7855, + "step": 41080 + }, + { + "epoch": 1.53, + "learning_rate": 8.471752147878157e-06, + "loss": 1.7643, + "step": 41090 + }, + { + "epoch": 1.53, + "learning_rate": 8.47138022092461e-06, + "loss": 1.8036, + "step": 41100 + }, + { + "epoch": 1.53, + "eval_loss": 1.7303202152252197, + "eval_runtime": 16.8148, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 41100 + }, + { + "epoch": 1.53, + "learning_rate": 8.471008293971064e-06, + "loss": 1.7897, + "step": 41110 + }, + { + "epoch": 1.53, + "learning_rate": 8.470636367017518e-06, + "loss": 1.9113, + "step": 41120 + }, + { + "epoch": 1.53, + "learning_rate": 8.470264440063973e-06, + "loss": 1.7402, + "step": 41130 + }, + { + "epoch": 1.53, + "learning_rate": 8.469892513110426e-06, + "loss": 1.8337, + "step": 41140 + }, + { + "epoch": 1.53, + "learning_rate": 8.46952058615688e-06, + "loss": 1.9405, + "step": 41150 + }, + { + "epoch": 1.53, + "learning_rate": 8.469148659203333e-06, + "loss": 1.7234, + "step": 41160 + }, + { + "epoch": 1.53, + "learning_rate": 8.468776732249787e-06, + "loss": 1.713, + "step": 41170 + }, + { + "epoch": 1.53, + "learning_rate": 8.46840480529624e-06, + "loss": 1.802, + "step": 41180 + }, + { + "epoch": 1.53, + "learning_rate": 8.468032878342695e-06, + "loss": 1.816, + "step": 41190 + }, + { + "epoch": 1.53, + "learning_rate": 8.467660951389149e-06, + "loss": 1.6975, + "step": 41200 + }, + { + "epoch": 1.53, + "eval_loss": 1.7305443286895752, + "eval_runtime": 16.8141, + "eval_samples_per_second": 59.474, + "eval_steps_per_second": 3.747, + "step": 41200 + }, + { + "epoch": 1.53, + "learning_rate": 8.467289024435602e-06, + "loss": 1.8081, + "step": 41210 + }, + { + "epoch": 1.53, + "learning_rate": 8.466917097482054e-06, + "loss": 1.8688, + "step": 41220 + }, + { + "epoch": 1.53, + "learning_rate": 8.466545170528509e-06, + "loss": 1.7917, + "step": 41230 + }, + { + "epoch": 1.53, + "learning_rate": 8.466173243574963e-06, + "loss": 1.8393, + "step": 41240 + }, + { + "epoch": 1.53, + "learning_rate": 8.465801316621416e-06, + "loss": 1.7368, + "step": 41250 + }, + { + "epoch": 1.53, + "learning_rate": 8.46542938966787e-06, + "loss": 1.7954, + "step": 41260 + }, + { + "epoch": 1.53, + "learning_rate": 8.465057462714323e-06, + "loss": 1.7732, + "step": 41270 + }, + { + "epoch": 1.54, + "learning_rate": 8.464685535760776e-06, + "loss": 1.7359, + "step": 41280 + }, + { + "epoch": 1.54, + "learning_rate": 8.464313608807232e-06, + "loss": 1.7994, + "step": 41290 + }, + { + "epoch": 1.54, + "learning_rate": 8.463941681853685e-06, + "loss": 1.7102, + "step": 41300 + }, + { + "epoch": 1.54, + "eval_loss": 1.73006272315979, + "eval_runtime": 16.8123, + "eval_samples_per_second": 59.48, + "eval_steps_per_second": 3.747, + "step": 41300 + }, + { + "epoch": 1.54, + "learning_rate": 8.463569754900138e-06, + "loss": 1.7597, + "step": 41310 + }, + { + "epoch": 1.54, + "learning_rate": 8.463197827946592e-06, + "loss": 1.742, + "step": 41320 + }, + { + "epoch": 1.54, + "learning_rate": 8.462825900993045e-06, + "loss": 1.823, + "step": 41330 + }, + { + "epoch": 1.54, + "learning_rate": 8.462453974039499e-06, + "loss": 1.7046, + "step": 41340 + }, + { + "epoch": 1.54, + "learning_rate": 8.462082047085954e-06, + "loss": 1.7967, + "step": 41350 + }, + { + "epoch": 1.54, + "learning_rate": 8.461710120132407e-06, + "loss": 1.771, + "step": 41360 + }, + { + "epoch": 1.54, + "learning_rate": 8.461338193178861e-06, + "loss": 1.7589, + "step": 41370 + }, + { + "epoch": 1.54, + "learning_rate": 8.460966266225314e-06, + "loss": 1.6895, + "step": 41380 + }, + { + "epoch": 1.54, + "learning_rate": 8.460594339271768e-06, + "loss": 1.7422, + "step": 41390 + }, + { + "epoch": 1.54, + "learning_rate": 8.460222412318221e-06, + "loss": 1.6836, + "step": 41400 + }, + { + "epoch": 1.54, + "eval_loss": 1.7301387786865234, + "eval_runtime": 16.8143, + "eval_samples_per_second": 59.473, + "eval_steps_per_second": 3.747, + "step": 41400 + }, + { + "epoch": 1.54, + "learning_rate": 8.459850485364675e-06, + "loss": 1.6947, + "step": 41410 + }, + { + "epoch": 1.54, + "learning_rate": 8.459478558411128e-06, + "loss": 1.6922, + "step": 41420 + }, + { + "epoch": 1.54, + "learning_rate": 8.459106631457582e-06, + "loss": 1.7121, + "step": 41430 + }, + { + "epoch": 1.54, + "learning_rate": 8.458734704504035e-06, + "loss": 1.7482, + "step": 41440 + }, + { + "epoch": 1.54, + "learning_rate": 8.45836277755049e-06, + "loss": 1.875, + "step": 41450 + }, + { + "epoch": 1.54, + "learning_rate": 8.457990850596944e-06, + "loss": 1.7816, + "step": 41460 + }, + { + "epoch": 1.54, + "learning_rate": 8.457618923643397e-06, + "loss": 1.7706, + "step": 41470 + }, + { + "epoch": 1.54, + "learning_rate": 8.45724699668985e-06, + "loss": 1.7737, + "step": 41480 + }, + { + "epoch": 1.54, + "learning_rate": 8.456875069736304e-06, + "loss": 1.716, + "step": 41490 + }, + { + "epoch": 1.54, + "learning_rate": 8.456503142782758e-06, + "loss": 1.706, + "step": 41500 + }, + { + "epoch": 1.54, + "eval_loss": 1.7303050756454468, + "eval_runtime": 16.8153, + "eval_samples_per_second": 59.47, + "eval_steps_per_second": 3.747, + "step": 41500 + }, + { + "epoch": 1.54, + "learning_rate": 8.456131215829213e-06, + "loss": 1.8483, + "step": 41510 + }, + { + "epoch": 1.54, + "learning_rate": 8.455759288875666e-06, + "loss": 1.808, + "step": 41520 + }, + { + "epoch": 1.54, + "learning_rate": 8.45538736192212e-06, + "loss": 1.8257, + "step": 41530 + }, + { + "epoch": 1.54, + "learning_rate": 8.455015434968573e-06, + "loss": 1.9616, + "step": 41540 + }, + { + "epoch": 1.55, + "learning_rate": 8.454643508015027e-06, + "loss": 1.79, + "step": 41550 + }, + { + "epoch": 1.55, + "learning_rate": 8.45427158106148e-06, + "loss": 1.8356, + "step": 41560 + }, + { + "epoch": 1.55, + "learning_rate": 8.453899654107935e-06, + "loss": 1.8026, + "step": 41570 + }, + { + "epoch": 1.55, + "learning_rate": 8.453527727154389e-06, + "loss": 1.7693, + "step": 41580 + }, + { + "epoch": 1.55, + "learning_rate": 8.45315580020084e-06, + "loss": 1.7299, + "step": 41590 + }, + { + "epoch": 1.55, + "learning_rate": 8.452783873247294e-06, + "loss": 1.8164, + "step": 41600 + }, + { + "epoch": 1.55, + "eval_loss": 1.729177713394165, + "eval_runtime": 16.824, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 41600 + }, + { + "epoch": 1.55, + "learning_rate": 8.452411946293749e-06, + "loss": 1.7838, + "step": 41610 + }, + { + "epoch": 1.55, + "learning_rate": 8.452040019340202e-06, + "loss": 1.8314, + "step": 41620 + }, + { + "epoch": 1.55, + "learning_rate": 8.451668092386656e-06, + "loss": 1.7213, + "step": 41630 + }, + { + "epoch": 1.55, + "learning_rate": 8.45129616543311e-06, + "loss": 1.8747, + "step": 41640 + }, + { + "epoch": 1.55, + "learning_rate": 8.450924238479563e-06, + "loss": 1.9705, + "step": 41650 + }, + { + "epoch": 1.55, + "learning_rate": 8.450552311526016e-06, + "loss": 1.7914, + "step": 41660 + }, + { + "epoch": 1.55, + "learning_rate": 8.45018038457247e-06, + "loss": 1.6554, + "step": 41670 + }, + { + "epoch": 1.55, + "learning_rate": 8.449808457618925e-06, + "loss": 1.7665, + "step": 41680 + }, + { + "epoch": 1.55, + "learning_rate": 8.449436530665378e-06, + "loss": 1.8617, + "step": 41690 + }, + { + "epoch": 1.55, + "learning_rate": 8.449064603711832e-06, + "loss": 1.7749, + "step": 41700 + }, + { + "epoch": 1.55, + "eval_loss": 1.7287592887878418, + "eval_runtime": 16.8156, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.747, + "step": 41700 + }, + { + "epoch": 1.55, + "learning_rate": 8.448692676758285e-06, + "loss": 1.7366, + "step": 41710 + }, + { + "epoch": 1.55, + "learning_rate": 8.448320749804739e-06, + "loss": 1.814, + "step": 41720 + }, + { + "epoch": 1.55, + "learning_rate": 8.447948822851192e-06, + "loss": 1.6523, + "step": 41730 + }, + { + "epoch": 1.55, + "learning_rate": 8.447576895897647e-06, + "loss": 1.7146, + "step": 41740 + }, + { + "epoch": 1.55, + "learning_rate": 8.4472049689441e-06, + "loss": 1.784, + "step": 41750 + }, + { + "epoch": 1.55, + "learning_rate": 8.446833041990554e-06, + "loss": 1.713, + "step": 41760 + }, + { + "epoch": 1.55, + "learning_rate": 8.446461115037008e-06, + "loss": 1.7679, + "step": 41770 + }, + { + "epoch": 1.55, + "learning_rate": 8.446089188083461e-06, + "loss": 1.9151, + "step": 41780 + }, + { + "epoch": 1.55, + "learning_rate": 8.445717261129915e-06, + "loss": 1.7795, + "step": 41790 + }, + { + "epoch": 1.55, + "learning_rate": 8.445345334176368e-06, + "loss": 1.6433, + "step": 41800 + }, + { + "epoch": 1.55, + "eval_loss": 1.728570818901062, + "eval_runtime": 16.8274, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 41800 + }, + { + "epoch": 1.56, + "learning_rate": 8.444973407222822e-06, + "loss": 1.7692, + "step": 41810 + }, + { + "epoch": 1.56, + "learning_rate": 8.444601480269275e-06, + "loss": 1.8236, + "step": 41820 + }, + { + "epoch": 1.56, + "learning_rate": 8.444229553315728e-06, + "loss": 1.7656, + "step": 41830 + }, + { + "epoch": 1.56, + "learning_rate": 8.443857626362184e-06, + "loss": 1.8176, + "step": 41840 + }, + { + "epoch": 1.56, + "learning_rate": 8.443485699408637e-06, + "loss": 1.9113, + "step": 41850 + }, + { + "epoch": 1.56, + "learning_rate": 8.44311377245509e-06, + "loss": 1.8174, + "step": 41860 + }, + { + "epoch": 1.56, + "learning_rate": 8.442741845501544e-06, + "loss": 1.9515, + "step": 41870 + }, + { + "epoch": 1.56, + "learning_rate": 8.442369918547997e-06, + "loss": 1.848, + "step": 41880 + }, + { + "epoch": 1.56, + "learning_rate": 8.441997991594451e-06, + "loss": 1.8865, + "step": 41890 + }, + { + "epoch": 1.56, + "learning_rate": 8.441626064640906e-06, + "loss": 1.7561, + "step": 41900 + }, + { + "epoch": 1.56, + "eval_loss": 1.7271533012390137, + "eval_runtime": 16.8432, + "eval_samples_per_second": 59.371, + "eval_steps_per_second": 3.74, + "step": 41900 + }, + { + "epoch": 1.56, + "learning_rate": 8.44125413768736e-06, + "loss": 1.8064, + "step": 41910 + }, + { + "epoch": 1.56, + "learning_rate": 8.440882210733813e-06, + "loss": 1.9347, + "step": 41920 + }, + { + "epoch": 1.56, + "learning_rate": 8.440510283780266e-06, + "loss": 1.8706, + "step": 41930 + }, + { + "epoch": 1.56, + "learning_rate": 8.44013835682672e-06, + "loss": 1.8626, + "step": 41940 + }, + { + "epoch": 1.56, + "learning_rate": 8.439766429873173e-06, + "loss": 1.7368, + "step": 41950 + }, + { + "epoch": 1.56, + "learning_rate": 8.439394502919629e-06, + "loss": 1.8615, + "step": 41960 + }, + { + "epoch": 1.56, + "learning_rate": 8.43902257596608e-06, + "loss": 1.8005, + "step": 41970 + }, + { + "epoch": 1.56, + "learning_rate": 8.438650649012534e-06, + "loss": 1.7837, + "step": 41980 + }, + { + "epoch": 1.56, + "learning_rate": 8.438278722058987e-06, + "loss": 1.7585, + "step": 41990 + }, + { + "epoch": 1.56, + "learning_rate": 8.437906795105442e-06, + "loss": 1.8314, + "step": 42000 + }, + { + "epoch": 1.56, + "eval_loss": 1.7282896041870117, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 42000 + }, + { + "epoch": 1.56, + "learning_rate": 8.437534868151896e-06, + "loss": 1.8527, + "step": 42010 + }, + { + "epoch": 1.56, + "learning_rate": 8.43716294119835e-06, + "loss": 1.9541, + "step": 42020 + }, + { + "epoch": 1.56, + "learning_rate": 8.436791014244803e-06, + "loss": 1.8363, + "step": 42030 + }, + { + "epoch": 1.56, + "learning_rate": 8.436419087291256e-06, + "loss": 1.8611, + "step": 42040 + }, + { + "epoch": 1.56, + "learning_rate": 8.43604716033771e-06, + "loss": 1.6508, + "step": 42050 + }, + { + "epoch": 1.56, + "learning_rate": 8.435675233384165e-06, + "loss": 1.8059, + "step": 42060 + }, + { + "epoch": 1.56, + "learning_rate": 8.435303306430618e-06, + "loss": 1.6642, + "step": 42070 + }, + { + "epoch": 1.57, + "learning_rate": 8.434931379477072e-06, + "loss": 1.7367, + "step": 42080 + }, + { + "epoch": 1.57, + "learning_rate": 8.434559452523525e-06, + "loss": 1.7792, + "step": 42090 + }, + { + "epoch": 1.57, + "learning_rate": 8.434187525569979e-06, + "loss": 1.8566, + "step": 42100 + }, + { + "epoch": 1.57, + "eval_loss": 1.728359580039978, + "eval_runtime": 16.8445, + "eval_samples_per_second": 59.367, + "eval_steps_per_second": 3.74, + "step": 42100 + }, + { + "epoch": 1.57, + "learning_rate": 8.433815598616432e-06, + "loss": 1.723, + "step": 42110 + }, + { + "epoch": 1.57, + "learning_rate": 8.433443671662887e-06, + "loss": 1.7799, + "step": 42120 + }, + { + "epoch": 1.57, + "learning_rate": 8.43307174470934e-06, + "loss": 1.7041, + "step": 42130 + }, + { + "epoch": 1.57, + "learning_rate": 8.432699817755794e-06, + "loss": 1.721, + "step": 42140 + }, + { + "epoch": 1.57, + "learning_rate": 8.432327890802248e-06, + "loss": 1.9215, + "step": 42150 + }, + { + "epoch": 1.57, + "learning_rate": 8.431955963848701e-06, + "loss": 1.7886, + "step": 42160 + }, + { + "epoch": 1.57, + "learning_rate": 8.431584036895155e-06, + "loss": 1.7838, + "step": 42170 + }, + { + "epoch": 1.57, + "learning_rate": 8.431212109941608e-06, + "loss": 1.7326, + "step": 42180 + }, + { + "epoch": 1.57, + "learning_rate": 8.430840182988061e-06, + "loss": 1.7323, + "step": 42190 + }, + { + "epoch": 1.57, + "learning_rate": 8.430468256034515e-06, + "loss": 1.5983, + "step": 42200 + }, + { + "epoch": 1.57, + "eval_loss": 1.728378176689148, + "eval_runtime": 16.8368, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 42200 + }, + { + "epoch": 1.57, + "learning_rate": 8.430096329080968e-06, + "loss": 1.9153, + "step": 42210 + }, + { + "epoch": 1.57, + "learning_rate": 8.429724402127422e-06, + "loss": 1.724, + "step": 42220 + }, + { + "epoch": 1.57, + "learning_rate": 8.429352475173877e-06, + "loss": 1.8077, + "step": 42230 + }, + { + "epoch": 1.57, + "learning_rate": 8.42898054822033e-06, + "loss": 1.8204, + "step": 42240 + }, + { + "epoch": 1.57, + "learning_rate": 8.428608621266784e-06, + "loss": 1.7944, + "step": 42250 + }, + { + "epoch": 1.57, + "learning_rate": 8.428236694313237e-06, + "loss": 1.8009, + "step": 42260 + }, + { + "epoch": 1.57, + "learning_rate": 8.427864767359691e-06, + "loss": 1.8486, + "step": 42270 + }, + { + "epoch": 1.57, + "learning_rate": 8.427492840406144e-06, + "loss": 1.8169, + "step": 42280 + }, + { + "epoch": 1.57, + "learning_rate": 8.4271209134526e-06, + "loss": 1.8332, + "step": 42290 + }, + { + "epoch": 1.57, + "learning_rate": 8.426748986499053e-06, + "loss": 1.6749, + "step": 42300 + }, + { + "epoch": 1.57, + "eval_loss": 1.726884126663208, + "eval_runtime": 16.8191, + "eval_samples_per_second": 59.456, + "eval_steps_per_second": 3.746, + "step": 42300 + }, + { + "epoch": 1.57, + "learning_rate": 8.426377059545506e-06, + "loss": 1.9246, + "step": 42310 + }, + { + "epoch": 1.57, + "learning_rate": 8.42600513259196e-06, + "loss": 1.8878, + "step": 42320 + }, + { + "epoch": 1.57, + "learning_rate": 8.425633205638413e-06, + "loss": 1.6323, + "step": 42330 + }, + { + "epoch": 1.57, + "learning_rate": 8.425261278684867e-06, + "loss": 1.781, + "step": 42340 + }, + { + "epoch": 1.58, + "learning_rate": 8.42488935173132e-06, + "loss": 1.785, + "step": 42350 + }, + { + "epoch": 1.58, + "learning_rate": 8.424517424777774e-06, + "loss": 1.8789, + "step": 42360 + }, + { + "epoch": 1.58, + "learning_rate": 8.424145497824227e-06, + "loss": 1.8383, + "step": 42370 + }, + { + "epoch": 1.58, + "learning_rate": 8.42377357087068e-06, + "loss": 1.8181, + "step": 42380 + }, + { + "epoch": 1.58, + "learning_rate": 8.423401643917136e-06, + "loss": 1.8071, + "step": 42390 + }, + { + "epoch": 1.58, + "learning_rate": 8.42302971696359e-06, + "loss": 1.734, + "step": 42400 + }, + { + "epoch": 1.58, + "eval_loss": 1.7271087169647217, + "eval_runtime": 16.8276, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 42400 + }, + { + "epoch": 1.58, + "learning_rate": 8.422657790010043e-06, + "loss": 1.7805, + "step": 42410 + }, + { + "epoch": 1.58, + "learning_rate": 8.422285863056496e-06, + "loss": 1.9023, + "step": 42420 + }, + { + "epoch": 1.58, + "learning_rate": 8.42191393610295e-06, + "loss": 1.7682, + "step": 42430 + }, + { + "epoch": 1.58, + "learning_rate": 8.421542009149403e-06, + "loss": 1.8198, + "step": 42440 + }, + { + "epoch": 1.58, + "learning_rate": 8.421170082195858e-06, + "loss": 1.845, + "step": 42450 + }, + { + "epoch": 1.58, + "learning_rate": 8.420798155242312e-06, + "loss": 1.6557, + "step": 42460 + }, + { + "epoch": 1.58, + "learning_rate": 8.420426228288765e-06, + "loss": 1.8073, + "step": 42470 + }, + { + "epoch": 1.58, + "learning_rate": 8.420054301335219e-06, + "loss": 1.7752, + "step": 42480 + }, + { + "epoch": 1.58, + "learning_rate": 8.419682374381672e-06, + "loss": 1.8394, + "step": 42490 + }, + { + "epoch": 1.58, + "learning_rate": 8.419310447428126e-06, + "loss": 1.7065, + "step": 42500 + }, + { + "epoch": 1.58, + "eval_loss": 1.7276030778884888, + "eval_runtime": 16.8406, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 42500 + }, + { + "epoch": 1.58, + "learning_rate": 8.41893852047458e-06, + "loss": 1.7671, + "step": 42510 + }, + { + "epoch": 1.58, + "learning_rate": 8.418566593521034e-06, + "loss": 1.9404, + "step": 42520 + }, + { + "epoch": 1.58, + "learning_rate": 8.418194666567486e-06, + "loss": 1.6931, + "step": 42530 + }, + { + "epoch": 1.58, + "learning_rate": 8.41782273961394e-06, + "loss": 1.6798, + "step": 42540 + }, + { + "epoch": 1.58, + "learning_rate": 8.417450812660394e-06, + "loss": 1.635, + "step": 42550 + }, + { + "epoch": 1.58, + "learning_rate": 8.417078885706848e-06, + "loss": 1.6418, + "step": 42560 + }, + { + "epoch": 1.58, + "learning_rate": 8.416706958753301e-06, + "loss": 1.6842, + "step": 42570 + }, + { + "epoch": 1.58, + "learning_rate": 8.416335031799755e-06, + "loss": 1.7091, + "step": 42580 + }, + { + "epoch": 1.58, + "learning_rate": 8.415963104846208e-06, + "loss": 1.8782, + "step": 42590 + }, + { + "epoch": 1.58, + "learning_rate": 8.415591177892662e-06, + "loss": 1.7602, + "step": 42600 + }, + { + "epoch": 1.58, + "eval_loss": 1.727020502090454, + "eval_runtime": 16.8264, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 42600 + }, + { + "epoch": 1.58, + "learning_rate": 8.415219250939117e-06, + "loss": 1.7059, + "step": 42610 + }, + { + "epoch": 1.59, + "learning_rate": 8.41484732398557e-06, + "loss": 1.8329, + "step": 42620 + }, + { + "epoch": 1.59, + "learning_rate": 8.414475397032024e-06, + "loss": 1.8057, + "step": 42630 + }, + { + "epoch": 1.59, + "learning_rate": 8.414103470078477e-06, + "loss": 1.7459, + "step": 42640 + }, + { + "epoch": 1.59, + "learning_rate": 8.41373154312493e-06, + "loss": 1.6776, + "step": 42650 + }, + { + "epoch": 1.59, + "learning_rate": 8.413359616171384e-06, + "loss": 1.7986, + "step": 42660 + }, + { + "epoch": 1.59, + "learning_rate": 8.41298768921784e-06, + "loss": 1.7231, + "step": 42670 + }, + { + "epoch": 1.59, + "learning_rate": 8.412615762264293e-06, + "loss": 1.666, + "step": 42680 + }, + { + "epoch": 1.59, + "learning_rate": 8.412243835310746e-06, + "loss": 1.7066, + "step": 42690 + }, + { + "epoch": 1.59, + "learning_rate": 8.4118719083572e-06, + "loss": 1.9595, + "step": 42700 + }, + { + "epoch": 1.59, + "eval_loss": 1.726917028427124, + "eval_runtime": 16.8392, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 42700 + }, + { + "epoch": 1.59, + "learning_rate": 8.411499981403653e-06, + "loss": 1.7777, + "step": 42710 + }, + { + "epoch": 1.59, + "learning_rate": 8.411128054450107e-06, + "loss": 1.7861, + "step": 42720 + }, + { + "epoch": 1.59, + "learning_rate": 8.41075612749656e-06, + "loss": 1.6967, + "step": 42730 + }, + { + "epoch": 1.59, + "learning_rate": 8.410384200543014e-06, + "loss": 1.7319, + "step": 42740 + }, + { + "epoch": 1.59, + "learning_rate": 8.410012273589467e-06, + "loss": 1.8636, + "step": 42750 + }, + { + "epoch": 1.59, + "learning_rate": 8.40964034663592e-06, + "loss": 1.7155, + "step": 42760 + }, + { + "epoch": 1.59, + "learning_rate": 8.409268419682376e-06, + "loss": 1.8391, + "step": 42770 + }, + { + "epoch": 1.59, + "learning_rate": 8.408896492728829e-06, + "loss": 1.7892, + "step": 42780 + }, + { + "epoch": 1.59, + "learning_rate": 8.408524565775283e-06, + "loss": 1.7675, + "step": 42790 + }, + { + "epoch": 1.59, + "learning_rate": 8.408152638821736e-06, + "loss": 1.8015, + "step": 42800 + }, + { + "epoch": 1.59, + "eval_loss": 1.7262223958969116, + "eval_runtime": 16.8211, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 42800 + }, + { + "epoch": 1.59, + "learning_rate": 8.40778071186819e-06, + "loss": 1.752, + "step": 42810 + }, + { + "epoch": 1.59, + "learning_rate": 8.407408784914643e-06, + "loss": 1.6816, + "step": 42820 + }, + { + "epoch": 1.59, + "learning_rate": 8.407036857961096e-06, + "loss": 1.7884, + "step": 42830 + }, + { + "epoch": 1.59, + "learning_rate": 8.406664931007552e-06, + "loss": 1.7001, + "step": 42840 + }, + { + "epoch": 1.59, + "learning_rate": 8.406293004054005e-06, + "loss": 1.7657, + "step": 42850 + }, + { + "epoch": 1.59, + "learning_rate": 8.405921077100459e-06, + "loss": 1.8171, + "step": 42860 + }, + { + "epoch": 1.59, + "learning_rate": 8.405549150146912e-06, + "loss": 1.8042, + "step": 42870 + }, + { + "epoch": 1.59, + "learning_rate": 8.405177223193365e-06, + "loss": 1.7034, + "step": 42880 + }, + { + "epoch": 1.6, + "learning_rate": 8.404805296239819e-06, + "loss": 1.9394, + "step": 42890 + }, + { + "epoch": 1.6, + "learning_rate": 8.404433369286274e-06, + "loss": 1.9092, + "step": 42900 + }, + { + "epoch": 1.6, + "eval_loss": 1.7255291938781738, + "eval_runtime": 16.843, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 42900 + }, + { + "epoch": 1.6, + "learning_rate": 8.404061442332726e-06, + "loss": 1.8222, + "step": 42910 + }, + { + "epoch": 1.6, + "learning_rate": 8.40368951537918e-06, + "loss": 1.7954, + "step": 42920 + }, + { + "epoch": 1.6, + "learning_rate": 8.403317588425633e-06, + "loss": 1.6993, + "step": 42930 + }, + { + "epoch": 1.6, + "learning_rate": 8.402945661472088e-06, + "loss": 1.7142, + "step": 42940 + }, + { + "epoch": 1.6, + "learning_rate": 8.402573734518541e-06, + "loss": 1.896, + "step": 42950 + }, + { + "epoch": 1.6, + "learning_rate": 8.402201807564995e-06, + "loss": 1.7615, + "step": 42960 + }, + { + "epoch": 1.6, + "learning_rate": 8.401829880611448e-06, + "loss": 1.8225, + "step": 42970 + }, + { + "epoch": 1.6, + "learning_rate": 8.401457953657902e-06, + "loss": 1.6741, + "step": 42980 + }, + { + "epoch": 1.6, + "learning_rate": 8.401086026704355e-06, + "loss": 1.6318, + "step": 42990 + }, + { + "epoch": 1.6, + "learning_rate": 8.40071409975081e-06, + "loss": 1.7792, + "step": 43000 + }, + { + "epoch": 1.6, + "eval_loss": 1.7258208990097046, + "eval_runtime": 16.817, + "eval_samples_per_second": 59.464, + "eval_steps_per_second": 3.746, + "step": 43000 + }, + { + "epoch": 1.6, + "learning_rate": 8.400342172797264e-06, + "loss": 1.8916, + "step": 43010 + }, + { + "epoch": 1.6, + "learning_rate": 8.399970245843717e-06, + "loss": 1.7511, + "step": 43020 + }, + { + "epoch": 1.6, + "learning_rate": 8.39959831889017e-06, + "loss": 1.7601, + "step": 43030 + }, + { + "epoch": 1.6, + "learning_rate": 8.399226391936624e-06, + "loss": 1.9845, + "step": 43040 + }, + { + "epoch": 1.6, + "learning_rate": 8.398854464983078e-06, + "loss": 1.6764, + "step": 43050 + }, + { + "epoch": 1.6, + "learning_rate": 8.398482538029533e-06, + "loss": 1.7762, + "step": 43060 + }, + { + "epoch": 1.6, + "learning_rate": 8.398110611075986e-06, + "loss": 1.7646, + "step": 43070 + }, + { + "epoch": 1.6, + "learning_rate": 8.39773868412244e-06, + "loss": 1.6865, + "step": 43080 + }, + { + "epoch": 1.6, + "learning_rate": 8.397366757168893e-06, + "loss": 1.7583, + "step": 43090 + }, + { + "epoch": 1.6, + "learning_rate": 8.396994830215347e-06, + "loss": 2.0061, + "step": 43100 + }, + { + "epoch": 1.6, + "eval_loss": 1.7261110544204712, + "eval_runtime": 16.8307, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 43100 + }, + { + "epoch": 1.6, + "learning_rate": 8.3966229032618e-06, + "loss": 1.8012, + "step": 43110 + }, + { + "epoch": 1.6, + "learning_rate": 8.396250976308254e-06, + "loss": 1.8083, + "step": 43120 + }, + { + "epoch": 1.6, + "learning_rate": 8.395879049354707e-06, + "loss": 1.8078, + "step": 43130 + }, + { + "epoch": 1.6, + "learning_rate": 8.39550712240116e-06, + "loss": 1.7305, + "step": 43140 + }, + { + "epoch": 1.6, + "learning_rate": 8.395135195447614e-06, + "loss": 1.8809, + "step": 43150 + }, + { + "epoch": 1.61, + "learning_rate": 8.394763268494069e-06, + "loss": 1.7597, + "step": 43160 + }, + { + "epoch": 1.61, + "learning_rate": 8.394391341540523e-06, + "loss": 1.7816, + "step": 43170 + }, + { + "epoch": 1.61, + "learning_rate": 8.394019414586976e-06, + "loss": 1.8408, + "step": 43180 + }, + { + "epoch": 1.61, + "learning_rate": 8.39364748763343e-06, + "loss": 1.9, + "step": 43190 + }, + { + "epoch": 1.61, + "learning_rate": 8.393275560679883e-06, + "loss": 1.7003, + "step": 43200 + }, + { + "epoch": 1.61, + "eval_loss": 1.7238296270370483, + "eval_runtime": 16.8361, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 43200 + }, + { + "epoch": 1.61, + "learning_rate": 8.392903633726336e-06, + "loss": 1.7127, + "step": 43210 + }, + { + "epoch": 1.61, + "learning_rate": 8.392531706772792e-06, + "loss": 1.8287, + "step": 43220 + }, + { + "epoch": 1.61, + "learning_rate": 8.392159779819245e-06, + "loss": 1.8942, + "step": 43230 + }, + { + "epoch": 1.61, + "learning_rate": 8.391787852865698e-06, + "loss": 1.6738, + "step": 43240 + }, + { + "epoch": 1.61, + "learning_rate": 8.391415925912152e-06, + "loss": 1.7694, + "step": 43250 + }, + { + "epoch": 1.61, + "learning_rate": 8.391043998958605e-06, + "loss": 1.645, + "step": 43260 + }, + { + "epoch": 1.61, + "learning_rate": 8.390672072005059e-06, + "loss": 1.8565, + "step": 43270 + }, + { + "epoch": 1.61, + "learning_rate": 8.390300145051512e-06, + "loss": 1.8619, + "step": 43280 + }, + { + "epoch": 1.61, + "learning_rate": 8.389928218097966e-06, + "loss": 1.8339, + "step": 43290 + }, + { + "epoch": 1.61, + "learning_rate": 8.38955629114442e-06, + "loss": 1.7525, + "step": 43300 + }, + { + "epoch": 1.61, + "eval_loss": 1.7241909503936768, + "eval_runtime": 16.838, + "eval_samples_per_second": 59.39, + "eval_steps_per_second": 3.742, + "step": 43300 + }, + { + "epoch": 1.61, + "learning_rate": 8.389184364190873e-06, + "loss": 1.7298, + "step": 43310 + }, + { + "epoch": 1.61, + "learning_rate": 8.388812437237328e-06, + "loss": 1.833, + "step": 43320 + }, + { + "epoch": 1.61, + "learning_rate": 8.388440510283781e-06, + "loss": 1.8704, + "step": 43330 + }, + { + "epoch": 1.61, + "learning_rate": 8.388068583330235e-06, + "loss": 1.8754, + "step": 43340 + }, + { + "epoch": 1.61, + "learning_rate": 8.387696656376688e-06, + "loss": 1.6874, + "step": 43350 + }, + { + "epoch": 1.61, + "learning_rate": 8.387324729423142e-06, + "loss": 1.8573, + "step": 43360 + }, + { + "epoch": 1.61, + "learning_rate": 8.386952802469595e-06, + "loss": 1.8342, + "step": 43370 + }, + { + "epoch": 1.61, + "learning_rate": 8.386580875516049e-06, + "loss": 1.9266, + "step": 43380 + }, + { + "epoch": 1.61, + "learning_rate": 8.386208948562504e-06, + "loss": 1.7655, + "step": 43390 + }, + { + "epoch": 1.61, + "learning_rate": 8.385837021608957e-06, + "loss": 1.6629, + "step": 43400 + }, + { + "epoch": 1.61, + "eval_loss": 1.724420189857483, + "eval_runtime": 16.8315, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 43400 + }, + { + "epoch": 1.61, + "learning_rate": 8.38546509465541e-06, + "loss": 1.7795, + "step": 43410 + }, + { + "epoch": 1.61, + "learning_rate": 8.385093167701864e-06, + "loss": 1.8158, + "step": 43420 + }, + { + "epoch": 1.62, + "learning_rate": 8.384721240748318e-06, + "loss": 1.7075, + "step": 43430 + }, + { + "epoch": 1.62, + "learning_rate": 8.384349313794771e-06, + "loss": 1.7984, + "step": 43440 + }, + { + "epoch": 1.62, + "learning_rate": 8.383977386841226e-06, + "loss": 1.7196, + "step": 43450 + }, + { + "epoch": 1.62, + "learning_rate": 8.38360545988768e-06, + "loss": 1.8545, + "step": 43460 + }, + { + "epoch": 1.62, + "learning_rate": 8.383233532934131e-06, + "loss": 1.7557, + "step": 43470 + }, + { + "epoch": 1.62, + "learning_rate": 8.382861605980585e-06, + "loss": 1.7995, + "step": 43480 + }, + { + "epoch": 1.62, + "learning_rate": 8.38248967902704e-06, + "loss": 1.8048, + "step": 43490 + }, + { + "epoch": 1.62, + "learning_rate": 8.382117752073493e-06, + "loss": 1.8186, + "step": 43500 + }, + { + "epoch": 1.62, + "eval_loss": 1.7234582901000977, + "eval_runtime": 16.8309, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 43500 + }, + { + "epoch": 1.62, + "learning_rate": 8.381745825119947e-06, + "loss": 1.8225, + "step": 43510 + }, + { + "epoch": 1.62, + "learning_rate": 8.3813738981664e-06, + "loss": 1.7508, + "step": 43520 + }, + { + "epoch": 1.62, + "learning_rate": 8.381001971212854e-06, + "loss": 1.736, + "step": 43530 + }, + { + "epoch": 1.62, + "learning_rate": 8.380630044259307e-06, + "loss": 1.7311, + "step": 43540 + }, + { + "epoch": 1.62, + "learning_rate": 8.380258117305762e-06, + "loss": 1.7226, + "step": 43550 + }, + { + "epoch": 1.62, + "learning_rate": 8.379886190352216e-06, + "loss": 1.6792, + "step": 43560 + }, + { + "epoch": 1.62, + "learning_rate": 8.37951426339867e-06, + "loss": 1.8725, + "step": 43570 + }, + { + "epoch": 1.62, + "learning_rate": 8.379142336445123e-06, + "loss": 1.7633, + "step": 43580 + }, + { + "epoch": 1.62, + "learning_rate": 8.378770409491576e-06, + "loss": 1.8493, + "step": 43590 + }, + { + "epoch": 1.62, + "learning_rate": 8.37839848253803e-06, + "loss": 1.7132, + "step": 43600 + }, + { + "epoch": 1.62, + "eval_loss": 1.723241925239563, + "eval_runtime": 16.8251, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 43600 + }, + { + "epoch": 1.62, + "learning_rate": 8.378026555584485e-06, + "loss": 1.6906, + "step": 43610 + }, + { + "epoch": 1.62, + "learning_rate": 8.377654628630938e-06, + "loss": 1.7698, + "step": 43620 + }, + { + "epoch": 1.62, + "learning_rate": 8.377282701677392e-06, + "loss": 1.8512, + "step": 43630 + }, + { + "epoch": 1.62, + "learning_rate": 8.376910774723845e-06, + "loss": 1.7551, + "step": 43640 + }, + { + "epoch": 1.62, + "learning_rate": 8.376538847770299e-06, + "loss": 1.8062, + "step": 43650 + }, + { + "epoch": 1.62, + "learning_rate": 8.376166920816752e-06, + "loss": 1.7347, + "step": 43660 + }, + { + "epoch": 1.62, + "learning_rate": 8.375794993863206e-06, + "loss": 1.8029, + "step": 43670 + }, + { + "epoch": 1.62, + "learning_rate": 8.375423066909659e-06, + "loss": 2.1015, + "step": 43680 + }, + { + "epoch": 1.62, + "learning_rate": 8.375051139956113e-06, + "loss": 1.7598, + "step": 43690 + }, + { + "epoch": 1.63, + "learning_rate": 8.374679213002566e-06, + "loss": 1.8327, + "step": 43700 + }, + { + "epoch": 1.63, + "eval_loss": 1.7224345207214355, + "eval_runtime": 16.824, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 43700 + }, + { + "epoch": 1.63, + "learning_rate": 8.374307286049021e-06, + "loss": 1.7097, + "step": 43710 + }, + { + "epoch": 1.63, + "learning_rate": 8.373935359095475e-06, + "loss": 1.8834, + "step": 43720 + }, + { + "epoch": 1.63, + "learning_rate": 8.373563432141928e-06, + "loss": 1.8087, + "step": 43730 + }, + { + "epoch": 1.63, + "learning_rate": 8.373191505188382e-06, + "loss": 1.8353, + "step": 43740 + }, + { + "epoch": 1.63, + "learning_rate": 8.372819578234835e-06, + "loss": 1.7045, + "step": 43750 + }, + { + "epoch": 1.63, + "learning_rate": 8.372447651281288e-06, + "loss": 1.8879, + "step": 43760 + }, + { + "epoch": 1.63, + "learning_rate": 8.372075724327744e-06, + "loss": 1.857, + "step": 43770 + }, + { + "epoch": 1.63, + "learning_rate": 8.371703797374197e-06, + "loss": 1.7761, + "step": 43780 + }, + { + "epoch": 1.63, + "learning_rate": 8.37133187042065e-06, + "loss": 1.7956, + "step": 43790 + }, + { + "epoch": 1.63, + "learning_rate": 8.370959943467104e-06, + "loss": 1.6472, + "step": 43800 + }, + { + "epoch": 1.63, + "eval_loss": 1.7240800857543945, + "eval_runtime": 16.817, + "eval_samples_per_second": 59.464, + "eval_steps_per_second": 3.746, + "step": 43800 + }, + { + "epoch": 1.63, + "learning_rate": 8.370588016513557e-06, + "loss": 1.8639, + "step": 43810 + }, + { + "epoch": 1.63, + "learning_rate": 8.370216089560011e-06, + "loss": 1.7399, + "step": 43820 + }, + { + "epoch": 1.63, + "learning_rate": 8.369844162606466e-06, + "loss": 1.834, + "step": 43830 + }, + { + "epoch": 1.63, + "learning_rate": 8.36947223565292e-06, + "loss": 1.8032, + "step": 43840 + }, + { + "epoch": 1.63, + "learning_rate": 8.369100308699371e-06, + "loss": 1.7557, + "step": 43850 + }, + { + "epoch": 1.63, + "learning_rate": 8.368728381745825e-06, + "loss": 1.9038, + "step": 43860 + }, + { + "epoch": 1.63, + "learning_rate": 8.36835645479228e-06, + "loss": 1.8677, + "step": 43870 + }, + { + "epoch": 1.63, + "learning_rate": 8.367984527838733e-06, + "loss": 1.8257, + "step": 43880 + }, + { + "epoch": 1.63, + "learning_rate": 8.367612600885187e-06, + "loss": 1.8052, + "step": 43890 + }, + { + "epoch": 1.63, + "learning_rate": 8.36724067393164e-06, + "loss": 1.9198, + "step": 43900 + }, + { + "epoch": 1.63, + "eval_loss": 1.72263765335083, + "eval_runtime": 16.8459, + "eval_samples_per_second": 59.362, + "eval_steps_per_second": 3.74, + "step": 43900 + }, + { + "epoch": 1.63, + "learning_rate": 8.366868746978094e-06, + "loss": 1.7475, + "step": 43910 + }, + { + "epoch": 1.63, + "learning_rate": 8.366496820024547e-06, + "loss": 1.75, + "step": 43920 + }, + { + "epoch": 1.63, + "learning_rate": 8.366124893071002e-06, + "loss": 1.7787, + "step": 43930 + }, + { + "epoch": 1.63, + "learning_rate": 8.365752966117456e-06, + "loss": 1.8218, + "step": 43940 + }, + { + "epoch": 1.63, + "learning_rate": 8.36538103916391e-06, + "loss": 1.8079, + "step": 43950 + }, + { + "epoch": 1.63, + "learning_rate": 8.365009112210363e-06, + "loss": 1.7472, + "step": 43960 + }, + { + "epoch": 1.64, + "learning_rate": 8.364637185256816e-06, + "loss": 1.6732, + "step": 43970 + }, + { + "epoch": 1.64, + "learning_rate": 8.36426525830327e-06, + "loss": 1.8388, + "step": 43980 + }, + { + "epoch": 1.64, + "learning_rate": 8.363893331349723e-06, + "loss": 1.7338, + "step": 43990 + }, + { + "epoch": 1.64, + "learning_rate": 8.363521404396178e-06, + "loss": 1.8107, + "step": 44000 + }, + { + "epoch": 1.64, + "eval_loss": 1.7227109670639038, + "eval_runtime": 16.8455, + "eval_samples_per_second": 59.363, + "eval_steps_per_second": 3.74, + "step": 44000 + }, + { + "epoch": 1.64, + "learning_rate": 8.363149477442632e-06, + "loss": 1.7899, + "step": 44010 + }, + { + "epoch": 1.64, + "learning_rate": 8.362777550489085e-06, + "loss": 1.8282, + "step": 44020 + }, + { + "epoch": 1.64, + "learning_rate": 8.362405623535537e-06, + "loss": 1.7641, + "step": 44030 + }, + { + "epoch": 1.64, + "learning_rate": 8.362033696581992e-06, + "loss": 1.8776, + "step": 44040 + }, + { + "epoch": 1.64, + "learning_rate": 8.361661769628446e-06, + "loss": 1.7704, + "step": 44050 + }, + { + "epoch": 1.64, + "learning_rate": 8.361289842674899e-06, + "loss": 1.7962, + "step": 44060 + }, + { + "epoch": 1.64, + "learning_rate": 8.360917915721352e-06, + "loss": 1.8631, + "step": 44070 + }, + { + "epoch": 1.64, + "learning_rate": 8.360545988767806e-06, + "loss": 1.8372, + "step": 44080 + }, + { + "epoch": 1.64, + "learning_rate": 8.36017406181426e-06, + "loss": 1.816, + "step": 44090 + }, + { + "epoch": 1.64, + "learning_rate": 8.359802134860715e-06, + "loss": 1.8716, + "step": 44100 + }, + { + "epoch": 1.64, + "eval_loss": 1.7234643697738647, + "eval_runtime": 16.8354, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 44100 + }, + { + "epoch": 1.64, + "learning_rate": 8.359430207907168e-06, + "loss": 1.8422, + "step": 44110 + }, + { + "epoch": 1.64, + "learning_rate": 8.359058280953621e-06, + "loss": 1.802, + "step": 44120 + }, + { + "epoch": 1.64, + "learning_rate": 8.358686354000075e-06, + "loss": 1.8377, + "step": 44130 + }, + { + "epoch": 1.64, + "learning_rate": 8.358314427046528e-06, + "loss": 1.8646, + "step": 44140 + }, + { + "epoch": 1.64, + "learning_rate": 8.357942500092982e-06, + "loss": 1.7528, + "step": 44150 + }, + { + "epoch": 1.64, + "learning_rate": 8.357570573139437e-06, + "loss": 1.7177, + "step": 44160 + }, + { + "epoch": 1.64, + "learning_rate": 8.35719864618589e-06, + "loss": 1.8663, + "step": 44170 + }, + { + "epoch": 1.64, + "learning_rate": 8.356826719232344e-06, + "loss": 1.8999, + "step": 44180 + }, + { + "epoch": 1.64, + "learning_rate": 8.356454792278797e-06, + "loss": 1.8422, + "step": 44190 + }, + { + "epoch": 1.64, + "learning_rate": 8.35608286532525e-06, + "loss": 1.6789, + "step": 44200 + }, + { + "epoch": 1.64, + "eval_loss": 1.723744511604309, + "eval_runtime": 16.8304, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 44200 + }, + { + "epoch": 1.64, + "learning_rate": 8.355710938371704e-06, + "loss": 1.8072, + "step": 44210 + }, + { + "epoch": 1.64, + "learning_rate": 8.355339011418158e-06, + "loss": 1.8277, + "step": 44220 + }, + { + "epoch": 1.65, + "learning_rate": 8.354967084464611e-06, + "loss": 1.7557, + "step": 44230 + }, + { + "epoch": 1.65, + "learning_rate": 8.354595157511065e-06, + "loss": 1.699, + "step": 44240 + }, + { + "epoch": 1.65, + "learning_rate": 8.354223230557518e-06, + "loss": 1.7792, + "step": 44250 + }, + { + "epoch": 1.65, + "learning_rate": 8.353851303603973e-06, + "loss": 1.8297, + "step": 44260 + }, + { + "epoch": 1.65, + "learning_rate": 8.353479376650427e-06, + "loss": 1.7617, + "step": 44270 + }, + { + "epoch": 1.65, + "learning_rate": 8.35310744969688e-06, + "loss": 1.8683, + "step": 44280 + }, + { + "epoch": 1.65, + "learning_rate": 8.352735522743334e-06, + "loss": 1.7257, + "step": 44290 + }, + { + "epoch": 1.65, + "learning_rate": 8.352363595789787e-06, + "loss": 1.7735, + "step": 44300 + }, + { + "epoch": 1.65, + "eval_loss": 1.7229053974151611, + "eval_runtime": 16.8424, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 44300 + }, + { + "epoch": 1.65, + "learning_rate": 8.35199166883624e-06, + "loss": 1.7337, + "step": 44310 + }, + { + "epoch": 1.65, + "learning_rate": 8.351619741882696e-06, + "loss": 1.853, + "step": 44320 + }, + { + "epoch": 1.65, + "learning_rate": 8.35124781492915e-06, + "loss": 1.8399, + "step": 44330 + }, + { + "epoch": 1.65, + "learning_rate": 8.350875887975603e-06, + "loss": 1.7907, + "step": 44340 + }, + { + "epoch": 1.65, + "learning_rate": 8.350503961022056e-06, + "loss": 1.8243, + "step": 44350 + }, + { + "epoch": 1.65, + "learning_rate": 8.35013203406851e-06, + "loss": 1.8191, + "step": 44360 + }, + { + "epoch": 1.65, + "learning_rate": 8.349760107114963e-06, + "loss": 1.7943, + "step": 44370 + }, + { + "epoch": 1.65, + "learning_rate": 8.349388180161418e-06, + "loss": 1.8018, + "step": 44380 + }, + { + "epoch": 1.65, + "learning_rate": 8.349016253207872e-06, + "loss": 1.8301, + "step": 44390 + }, + { + "epoch": 1.65, + "learning_rate": 8.348644326254325e-06, + "loss": 1.8386, + "step": 44400 + }, + { + "epoch": 1.65, + "eval_loss": 1.7225981950759888, + "eval_runtime": 16.8332, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 44400 + }, + { + "epoch": 1.65, + "learning_rate": 8.348272399300777e-06, + "loss": 1.7748, + "step": 44410 + }, + { + "epoch": 1.65, + "learning_rate": 8.347900472347232e-06, + "loss": 1.7661, + "step": 44420 + }, + { + "epoch": 1.65, + "learning_rate": 8.347528545393685e-06, + "loss": 1.7659, + "step": 44430 + }, + { + "epoch": 1.65, + "learning_rate": 8.347156618440139e-06, + "loss": 1.739, + "step": 44440 + }, + { + "epoch": 1.65, + "learning_rate": 8.346784691486592e-06, + "loss": 1.8021, + "step": 44450 + }, + { + "epoch": 1.65, + "learning_rate": 8.346412764533046e-06, + "loss": 1.856, + "step": 44460 + }, + { + "epoch": 1.65, + "learning_rate": 8.3460408375795e-06, + "loss": 1.9167, + "step": 44470 + }, + { + "epoch": 1.65, + "learning_rate": 8.345668910625954e-06, + "loss": 1.8298, + "step": 44480 + }, + { + "epoch": 1.65, + "learning_rate": 8.345296983672408e-06, + "loss": 1.7846, + "step": 44490 + }, + { + "epoch": 1.66, + "learning_rate": 8.344925056718861e-06, + "loss": 1.749, + "step": 44500 + }, + { + "epoch": 1.66, + "eval_loss": 1.7224148511886597, + "eval_runtime": 16.8765, + "eval_samples_per_second": 59.254, + "eval_steps_per_second": 3.733, + "step": 44500 + }, + { + "epoch": 1.66, + "learning_rate": 8.344553129765315e-06, + "loss": 1.9309, + "step": 44510 + }, + { + "epoch": 1.66, + "learning_rate": 8.344181202811768e-06, + "loss": 1.7202, + "step": 44520 + }, + { + "epoch": 1.66, + "learning_rate": 8.343809275858222e-06, + "loss": 1.8806, + "step": 44530 + }, + { + "epoch": 1.66, + "learning_rate": 8.343437348904675e-06, + "loss": 1.9713, + "step": 44540 + }, + { + "epoch": 1.66, + "learning_rate": 8.34306542195113e-06, + "loss": 1.7621, + "step": 44550 + }, + { + "epoch": 1.66, + "learning_rate": 8.342693494997584e-06, + "loss": 1.8318, + "step": 44560 + }, + { + "epoch": 1.66, + "learning_rate": 8.342321568044037e-06, + "loss": 1.8101, + "step": 44570 + }, + { + "epoch": 1.66, + "learning_rate": 8.34194964109049e-06, + "loss": 1.7015, + "step": 44580 + }, + { + "epoch": 1.66, + "learning_rate": 8.341577714136944e-06, + "loss": 1.644, + "step": 44590 + }, + { + "epoch": 1.66, + "learning_rate": 8.341205787183398e-06, + "loss": 1.6952, + "step": 44600 + }, + { + "epoch": 1.66, + "eval_loss": 1.721551537513733, + "eval_runtime": 16.8538, + "eval_samples_per_second": 59.334, + "eval_steps_per_second": 3.738, + "step": 44600 + }, + { + "epoch": 1.66, + "learning_rate": 8.340833860229851e-06, + "loss": 1.9558, + "step": 44610 + }, + { + "epoch": 1.66, + "learning_rate": 8.340461933276305e-06, + "loss": 1.7028, + "step": 44620 + }, + { + "epoch": 1.66, + "learning_rate": 8.340090006322758e-06, + "loss": 1.7412, + "step": 44630 + }, + { + "epoch": 1.66, + "learning_rate": 8.339718079369211e-06, + "loss": 1.7161, + "step": 44640 + }, + { + "epoch": 1.66, + "learning_rate": 8.339346152415667e-06, + "loss": 1.8787, + "step": 44650 + }, + { + "epoch": 1.66, + "learning_rate": 8.33897422546212e-06, + "loss": 1.7458, + "step": 44660 + }, + { + "epoch": 1.66, + "learning_rate": 8.338602298508574e-06, + "loss": 1.7829, + "step": 44670 + }, + { + "epoch": 1.66, + "learning_rate": 8.338230371555027e-06, + "loss": 1.8545, + "step": 44680 + }, + { + "epoch": 1.66, + "learning_rate": 8.33785844460148e-06, + "loss": 1.8437, + "step": 44690 + }, + { + "epoch": 1.66, + "learning_rate": 8.337486517647934e-06, + "loss": 1.8658, + "step": 44700 + }, + { + "epoch": 1.66, + "eval_loss": 1.7210524082183838, + "eval_runtime": 16.8353, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 44700 + }, + { + "epoch": 1.66, + "learning_rate": 8.337114590694389e-06, + "loss": 1.7823, + "step": 44710 + }, + { + "epoch": 1.66, + "learning_rate": 8.336742663740843e-06, + "loss": 1.76, + "step": 44720 + }, + { + "epoch": 1.66, + "learning_rate": 8.336370736787296e-06, + "loss": 1.8826, + "step": 44730 + }, + { + "epoch": 1.66, + "learning_rate": 8.33599880983375e-06, + "loss": 1.827, + "step": 44740 + }, + { + "epoch": 1.66, + "learning_rate": 8.335626882880203e-06, + "loss": 1.8813, + "step": 44750 + }, + { + "epoch": 1.66, + "learning_rate": 8.335254955926656e-06, + "loss": 1.8279, + "step": 44760 + }, + { + "epoch": 1.67, + "learning_rate": 8.334883028973112e-06, + "loss": 1.9056, + "step": 44770 + }, + { + "epoch": 1.67, + "learning_rate": 8.334511102019565e-06, + "loss": 1.7587, + "step": 44780 + }, + { + "epoch": 1.67, + "learning_rate": 8.334139175066017e-06, + "loss": 1.7165, + "step": 44790 + }, + { + "epoch": 1.67, + "learning_rate": 8.33376724811247e-06, + "loss": 1.7069, + "step": 44800 + }, + { + "epoch": 1.67, + "eval_loss": 1.7230949401855469, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 44800 + }, + { + "epoch": 1.67, + "learning_rate": 8.333395321158925e-06, + "loss": 1.6907, + "step": 44810 + }, + { + "epoch": 1.67, + "learning_rate": 8.333023394205379e-06, + "loss": 1.69, + "step": 44820 + }, + { + "epoch": 1.67, + "learning_rate": 8.332651467251832e-06, + "loss": 1.761, + "step": 44830 + }, + { + "epoch": 1.67, + "learning_rate": 8.332279540298286e-06, + "loss": 1.7374, + "step": 44840 + }, + { + "epoch": 1.67, + "learning_rate": 8.33190761334474e-06, + "loss": 1.7226, + "step": 44850 + }, + { + "epoch": 1.67, + "learning_rate": 8.331535686391193e-06, + "loss": 1.8898, + "step": 44860 + }, + { + "epoch": 1.67, + "learning_rate": 8.331163759437648e-06, + "loss": 1.7845, + "step": 44870 + }, + { + "epoch": 1.67, + "learning_rate": 8.330791832484101e-06, + "loss": 1.7776, + "step": 44880 + }, + { + "epoch": 1.67, + "learning_rate": 8.330419905530555e-06, + "loss": 1.8061, + "step": 44890 + }, + { + "epoch": 1.67, + "learning_rate": 8.330047978577008e-06, + "loss": 1.8784, + "step": 44900 + }, + { + "epoch": 1.67, + "eval_loss": 1.7214919328689575, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 44900 + }, + { + "epoch": 1.67, + "learning_rate": 8.329676051623462e-06, + "loss": 1.8183, + "step": 44910 + }, + { + "epoch": 1.67, + "learning_rate": 8.329304124669915e-06, + "loss": 1.7599, + "step": 44920 + }, + { + "epoch": 1.67, + "learning_rate": 8.32893219771637e-06, + "loss": 1.7845, + "step": 44930 + }, + { + "epoch": 1.67, + "learning_rate": 8.328560270762824e-06, + "loss": 1.8296, + "step": 44940 + }, + { + "epoch": 1.67, + "learning_rate": 8.328188343809277e-06, + "loss": 1.8437, + "step": 44950 + }, + { + "epoch": 1.67, + "learning_rate": 8.32781641685573e-06, + "loss": 1.7272, + "step": 44960 + }, + { + "epoch": 1.67, + "learning_rate": 8.327444489902184e-06, + "loss": 1.7446, + "step": 44970 + }, + { + "epoch": 1.67, + "learning_rate": 8.327072562948638e-06, + "loss": 1.7138, + "step": 44980 + }, + { + "epoch": 1.67, + "learning_rate": 8.326700635995091e-06, + "loss": 1.7689, + "step": 44990 + }, + { + "epoch": 1.67, + "learning_rate": 8.326328709041544e-06, + "loss": 1.6676, + "step": 45000 + }, + { + "epoch": 1.67, + "eval_loss": 1.7217692136764526, + "eval_runtime": 16.8229, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 45000 + }, + { + "epoch": 1.67, + "learning_rate": 8.325956782087998e-06, + "loss": 1.7854, + "step": 45010 + }, + { + "epoch": 1.67, + "learning_rate": 8.325584855134451e-06, + "loss": 1.7817, + "step": 45020 + }, + { + "epoch": 1.67, + "learning_rate": 8.325212928180907e-06, + "loss": 1.7377, + "step": 45030 + }, + { + "epoch": 1.68, + "learning_rate": 8.32484100122736e-06, + "loss": 1.7973, + "step": 45040 + }, + { + "epoch": 1.68, + "learning_rate": 8.324469074273813e-06, + "loss": 1.7, + "step": 45050 + }, + { + "epoch": 1.68, + "learning_rate": 8.324097147320267e-06, + "loss": 1.9585, + "step": 45060 + }, + { + "epoch": 1.68, + "learning_rate": 8.32372522036672e-06, + "loss": 1.8388, + "step": 45070 + }, + { + "epoch": 1.68, + "learning_rate": 8.323353293413174e-06, + "loss": 1.8583, + "step": 45080 + }, + { + "epoch": 1.68, + "learning_rate": 8.322981366459629e-06, + "loss": 1.6723, + "step": 45090 + }, + { + "epoch": 1.68, + "learning_rate": 8.322609439506082e-06, + "loss": 1.8275, + "step": 45100 + }, + { + "epoch": 1.68, + "eval_loss": 1.7219014167785645, + "eval_runtime": 16.8047, + "eval_samples_per_second": 59.507, + "eval_steps_per_second": 3.749, + "step": 45100 + }, + { + "epoch": 1.68, + "learning_rate": 8.322237512552536e-06, + "loss": 1.7882, + "step": 45110 + }, + { + "epoch": 1.68, + "learning_rate": 8.32186558559899e-06, + "loss": 1.8115, + "step": 45120 + }, + { + "epoch": 1.68, + "learning_rate": 8.321493658645443e-06, + "loss": 1.7541, + "step": 45130 + }, + { + "epoch": 1.68, + "learning_rate": 8.321121731691896e-06, + "loss": 1.8356, + "step": 45140 + }, + { + "epoch": 1.68, + "learning_rate": 8.32074980473835e-06, + "loss": 1.8118, + "step": 45150 + }, + { + "epoch": 1.68, + "learning_rate": 8.320377877784803e-06, + "loss": 1.794, + "step": 45160 + }, + { + "epoch": 1.68, + "learning_rate": 8.320005950831257e-06, + "loss": 1.8009, + "step": 45170 + }, + { + "epoch": 1.68, + "learning_rate": 8.31963402387771e-06, + "loss": 1.9446, + "step": 45180 + }, + { + "epoch": 1.68, + "learning_rate": 8.319262096924164e-06, + "loss": 1.8657, + "step": 45190 + }, + { + "epoch": 1.68, + "learning_rate": 8.318890169970619e-06, + "loss": 1.7327, + "step": 45200 + }, + { + "epoch": 1.68, + "eval_loss": 1.7219470739364624, + "eval_runtime": 16.8126, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 45200 + }, + { + "epoch": 1.68, + "learning_rate": 8.318518243017072e-06, + "loss": 1.8052, + "step": 45210 + }, + { + "epoch": 1.68, + "learning_rate": 8.318146316063526e-06, + "loss": 1.8411, + "step": 45220 + }, + { + "epoch": 1.68, + "learning_rate": 8.317774389109979e-06, + "loss": 1.6759, + "step": 45230 + }, + { + "epoch": 1.68, + "learning_rate": 8.317402462156433e-06, + "loss": 1.7746, + "step": 45240 + }, + { + "epoch": 1.68, + "learning_rate": 8.317030535202886e-06, + "loss": 1.8367, + "step": 45250 + }, + { + "epoch": 1.68, + "learning_rate": 8.316658608249341e-06, + "loss": 1.7607, + "step": 45260 + }, + { + "epoch": 1.68, + "learning_rate": 8.316286681295795e-06, + "loss": 1.7857, + "step": 45270 + }, + { + "epoch": 1.68, + "learning_rate": 8.315914754342248e-06, + "loss": 1.9197, + "step": 45280 + }, + { + "epoch": 1.68, + "learning_rate": 8.315542827388702e-06, + "loss": 1.7404, + "step": 45290 + }, + { + "epoch": 1.68, + "learning_rate": 8.315170900435155e-06, + "loss": 1.6889, + "step": 45300 + }, + { + "epoch": 1.68, + "eval_loss": 1.7210490703582764, + "eval_runtime": 16.8401, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 45300 + }, + { + "epoch": 1.69, + "learning_rate": 8.314798973481609e-06, + "loss": 1.7418, + "step": 45310 + }, + { + "epoch": 1.69, + "learning_rate": 8.314427046528064e-06, + "loss": 1.7331, + "step": 45320 + }, + { + "epoch": 1.69, + "learning_rate": 8.314055119574517e-06, + "loss": 1.8924, + "step": 45330 + }, + { + "epoch": 1.69, + "learning_rate": 8.31368319262097e-06, + "loss": 1.7078, + "step": 45340 + }, + { + "epoch": 1.69, + "learning_rate": 8.313311265667422e-06, + "loss": 1.7969, + "step": 45350 + }, + { + "epoch": 1.69, + "learning_rate": 8.312939338713877e-06, + "loss": 1.8484, + "step": 45360 + }, + { + "epoch": 1.69, + "learning_rate": 8.312567411760331e-06, + "loss": 1.8827, + "step": 45370 + }, + { + "epoch": 1.69, + "learning_rate": 8.312195484806784e-06, + "loss": 1.9307, + "step": 45380 + }, + { + "epoch": 1.69, + "learning_rate": 8.311823557853238e-06, + "loss": 1.6601, + "step": 45390 + }, + { + "epoch": 1.69, + "learning_rate": 8.311451630899691e-06, + "loss": 1.7665, + "step": 45400 + }, + { + "epoch": 1.69, + "eval_loss": 1.7209850549697876, + "eval_runtime": 16.8216, + "eval_samples_per_second": 59.447, + "eval_steps_per_second": 3.745, + "step": 45400 + }, + { + "epoch": 1.69, + "learning_rate": 8.311079703946145e-06, + "loss": 1.718, + "step": 45410 + }, + { + "epoch": 1.69, + "learning_rate": 8.3107077769926e-06, + "loss": 1.7413, + "step": 45420 + }, + { + "epoch": 1.69, + "learning_rate": 8.310335850039053e-06, + "loss": 1.8654, + "step": 45430 + }, + { + "epoch": 1.69, + "learning_rate": 8.309963923085507e-06, + "loss": 1.9432, + "step": 45440 + }, + { + "epoch": 1.69, + "learning_rate": 8.30959199613196e-06, + "loss": 1.6739, + "step": 45450 + }, + { + "epoch": 1.69, + "learning_rate": 8.309220069178414e-06, + "loss": 1.8001, + "step": 45460 + }, + { + "epoch": 1.69, + "learning_rate": 8.308848142224867e-06, + "loss": 1.7555, + "step": 45470 + }, + { + "epoch": 1.69, + "learning_rate": 8.308476215271322e-06, + "loss": 1.8906, + "step": 45480 + }, + { + "epoch": 1.69, + "learning_rate": 8.308104288317776e-06, + "loss": 1.7266, + "step": 45490 + }, + { + "epoch": 1.69, + "learning_rate": 8.30773236136423e-06, + "loss": 1.7529, + "step": 45500 + }, + { + "epoch": 1.69, + "eval_loss": 1.7207609415054321, + "eval_runtime": 16.8239, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 45500 + }, + { + "epoch": 1.69, + "learning_rate": 8.307360434410683e-06, + "loss": 1.8052, + "step": 45510 + }, + { + "epoch": 1.69, + "learning_rate": 8.306988507457136e-06, + "loss": 1.7976, + "step": 45520 + }, + { + "epoch": 1.69, + "learning_rate": 8.30661658050359e-06, + "loss": 1.7651, + "step": 45530 + }, + { + "epoch": 1.69, + "learning_rate": 8.306244653550043e-06, + "loss": 1.7018, + "step": 45540 + }, + { + "epoch": 1.69, + "learning_rate": 8.305872726596497e-06, + "loss": 1.9689, + "step": 45550 + }, + { + "epoch": 1.69, + "learning_rate": 8.30550079964295e-06, + "loss": 1.7183, + "step": 45560 + }, + { + "epoch": 1.69, + "learning_rate": 8.305128872689404e-06, + "loss": 1.8106, + "step": 45570 + }, + { + "epoch": 1.7, + "learning_rate": 8.304756945735859e-06, + "loss": 1.7649, + "step": 45580 + }, + { + "epoch": 1.7, + "learning_rate": 8.304385018782312e-06, + "loss": 1.8393, + "step": 45590 + }, + { + "epoch": 1.7, + "learning_rate": 8.304013091828766e-06, + "loss": 1.8049, + "step": 45600 + }, + { + "epoch": 1.7, + "eval_loss": 1.7202495336532593, + "eval_runtime": 16.8163, + "eval_samples_per_second": 59.466, + "eval_steps_per_second": 3.746, + "step": 45600 + }, + { + "epoch": 1.7, + "learning_rate": 8.303641164875219e-06, + "loss": 1.7592, + "step": 45610 + }, + { + "epoch": 1.7, + "learning_rate": 8.303269237921673e-06, + "loss": 1.9301, + "step": 45620 + }, + { + "epoch": 1.7, + "learning_rate": 8.302897310968126e-06, + "loss": 1.8273, + "step": 45630 + }, + { + "epoch": 1.7, + "learning_rate": 8.302525384014581e-06, + "loss": 1.8272, + "step": 45640 + }, + { + "epoch": 1.7, + "learning_rate": 8.302153457061035e-06, + "loss": 1.7259, + "step": 45650 + }, + { + "epoch": 1.7, + "learning_rate": 8.301781530107488e-06, + "loss": 1.8286, + "step": 45660 + }, + { + "epoch": 1.7, + "learning_rate": 8.301409603153942e-06, + "loss": 1.9251, + "step": 45670 + }, + { + "epoch": 1.7, + "learning_rate": 8.301037676200395e-06, + "loss": 1.8326, + "step": 45680 + }, + { + "epoch": 1.7, + "learning_rate": 8.300665749246848e-06, + "loss": 1.7396, + "step": 45690 + }, + { + "epoch": 1.7, + "learning_rate": 8.300293822293302e-06, + "loss": 1.6918, + "step": 45700 + }, + { + "epoch": 1.7, + "eval_loss": 1.721152901649475, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 45700 + }, + { + "epoch": 1.7, + "learning_rate": 8.299921895339757e-06, + "loss": 1.8393, + "step": 45710 + }, + { + "epoch": 1.7, + "learning_rate": 8.299549968386209e-06, + "loss": 1.6896, + "step": 45720 + }, + { + "epoch": 1.7, + "learning_rate": 8.299178041432662e-06, + "loss": 1.702, + "step": 45730 + }, + { + "epoch": 1.7, + "learning_rate": 8.298806114479116e-06, + "loss": 1.8562, + "step": 45740 + }, + { + "epoch": 1.7, + "learning_rate": 8.298434187525571e-06, + "loss": 1.8404, + "step": 45750 + }, + { + "epoch": 1.7, + "learning_rate": 8.298062260572024e-06, + "loss": 1.6927, + "step": 45760 + }, + { + "epoch": 1.7, + "learning_rate": 8.297690333618478e-06, + "loss": 1.7208, + "step": 45770 + }, + { + "epoch": 1.7, + "learning_rate": 8.297318406664931e-06, + "loss": 1.7423, + "step": 45780 + }, + { + "epoch": 1.7, + "learning_rate": 8.296946479711385e-06, + "loss": 1.6985, + "step": 45790 + }, + { + "epoch": 1.7, + "learning_rate": 8.296574552757838e-06, + "loss": 1.6888, + "step": 45800 + }, + { + "epoch": 1.7, + "eval_loss": 1.7193831205368042, + "eval_runtime": 16.8428, + "eval_samples_per_second": 59.373, + "eval_steps_per_second": 3.74, + "step": 45800 + }, + { + "epoch": 1.7, + "learning_rate": 8.296202625804293e-06, + "loss": 1.7901, + "step": 45810 + }, + { + "epoch": 1.7, + "learning_rate": 8.295830698850747e-06, + "loss": 1.8894, + "step": 45820 + }, + { + "epoch": 1.7, + "learning_rate": 8.2954587718972e-06, + "loss": 1.8538, + "step": 45830 + }, + { + "epoch": 1.7, + "learning_rate": 8.295086844943654e-06, + "loss": 1.712, + "step": 45840 + }, + { + "epoch": 1.71, + "learning_rate": 8.294714917990107e-06, + "loss": 1.8257, + "step": 45850 + }, + { + "epoch": 1.71, + "learning_rate": 8.29434299103656e-06, + "loss": 1.8381, + "step": 45860 + }, + { + "epoch": 1.71, + "learning_rate": 8.293971064083016e-06, + "loss": 1.6905, + "step": 45870 + }, + { + "epoch": 1.71, + "learning_rate": 8.29359913712947e-06, + "loss": 1.8192, + "step": 45880 + }, + { + "epoch": 1.71, + "learning_rate": 8.293227210175923e-06, + "loss": 1.7643, + "step": 45890 + }, + { + "epoch": 1.71, + "learning_rate": 8.292855283222376e-06, + "loss": 1.6961, + "step": 45900 + }, + { + "epoch": 1.71, + "eval_loss": 1.7195650339126587, + "eval_runtime": 16.8251, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 45900 + }, + { + "epoch": 1.71, + "learning_rate": 8.29248335626883e-06, + "loss": 1.663, + "step": 45910 + }, + { + "epoch": 1.71, + "learning_rate": 8.292111429315283e-06, + "loss": 1.8185, + "step": 45920 + }, + { + "epoch": 1.71, + "learning_rate": 8.291739502361737e-06, + "loss": 1.6522, + "step": 45930 + }, + { + "epoch": 1.71, + "learning_rate": 8.29136757540819e-06, + "loss": 1.7202, + "step": 45940 + }, + { + "epoch": 1.71, + "learning_rate": 8.290995648454643e-06, + "loss": 1.841, + "step": 45950 + }, + { + "epoch": 1.71, + "learning_rate": 8.290623721501097e-06, + "loss": 1.6963, + "step": 45960 + }, + { + "epoch": 1.71, + "learning_rate": 8.290251794547552e-06, + "loss": 1.8415, + "step": 45970 + }, + { + "epoch": 1.71, + "learning_rate": 8.289879867594006e-06, + "loss": 1.7565, + "step": 45980 + }, + { + "epoch": 1.71, + "learning_rate": 8.289507940640459e-06, + "loss": 1.7887, + "step": 45990 + }, + { + "epoch": 1.71, + "learning_rate": 8.289136013686912e-06, + "loss": 1.7272, + "step": 46000 + }, + { + "epoch": 1.71, + "eval_loss": 1.718932867050171, + "eval_runtime": 16.8235, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 46000 + }, + { + "epoch": 1.71, + "learning_rate": 8.288764086733366e-06, + "loss": 1.8045, + "step": 46010 + }, + { + "epoch": 1.71, + "learning_rate": 8.28839215977982e-06, + "loss": 1.7405, + "step": 46020 + }, + { + "epoch": 1.71, + "learning_rate": 8.288020232826275e-06, + "loss": 1.7985, + "step": 46030 + }, + { + "epoch": 1.71, + "learning_rate": 8.287648305872728e-06, + "loss": 1.9051, + "step": 46040 + }, + { + "epoch": 1.71, + "learning_rate": 8.287276378919181e-06, + "loss": 1.8101, + "step": 46050 + }, + { + "epoch": 1.71, + "learning_rate": 8.286904451965635e-06, + "loss": 1.7309, + "step": 46060 + }, + { + "epoch": 1.71, + "learning_rate": 8.286532525012088e-06, + "loss": 1.9329, + "step": 46070 + }, + { + "epoch": 1.71, + "learning_rate": 8.286160598058542e-06, + "loss": 1.7777, + "step": 46080 + }, + { + "epoch": 1.71, + "learning_rate": 8.285788671104997e-06, + "loss": 1.8747, + "step": 46090 + }, + { + "epoch": 1.71, + "learning_rate": 8.285416744151449e-06, + "loss": 1.6236, + "step": 46100 + }, + { + "epoch": 1.71, + "eval_loss": 1.7195583581924438, + "eval_runtime": 16.8258, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 46100 + }, + { + "epoch": 1.71, + "learning_rate": 8.285044817197902e-06, + "loss": 1.8775, + "step": 46110 + }, + { + "epoch": 1.72, + "learning_rate": 8.284672890244356e-06, + "loss": 1.8384, + "step": 46120 + }, + { + "epoch": 1.72, + "learning_rate": 8.28430096329081e-06, + "loss": 1.7904, + "step": 46130 + }, + { + "epoch": 1.72, + "learning_rate": 8.283929036337264e-06, + "loss": 1.7372, + "step": 46140 + }, + { + "epoch": 1.72, + "learning_rate": 8.283557109383718e-06, + "loss": 1.8071, + "step": 46150 + }, + { + "epoch": 1.72, + "learning_rate": 8.283185182430171e-06, + "loss": 1.854, + "step": 46160 + }, + { + "epoch": 1.72, + "learning_rate": 8.282813255476625e-06, + "loss": 1.9074, + "step": 46170 + }, + { + "epoch": 1.72, + "learning_rate": 8.282441328523078e-06, + "loss": 1.7837, + "step": 46180 + }, + { + "epoch": 1.72, + "learning_rate": 8.282069401569533e-06, + "loss": 1.8486, + "step": 46190 + }, + { + "epoch": 1.72, + "learning_rate": 8.281697474615987e-06, + "loss": 1.7806, + "step": 46200 + }, + { + "epoch": 1.72, + "eval_loss": 1.7181934118270874, + "eval_runtime": 16.8116, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 46200 + }, + { + "epoch": 1.72, + "learning_rate": 8.28132554766244e-06, + "loss": 1.8286, + "step": 46210 + }, + { + "epoch": 1.72, + "learning_rate": 8.280953620708894e-06, + "loss": 1.7827, + "step": 46220 + }, + { + "epoch": 1.72, + "learning_rate": 8.280581693755347e-06, + "loss": 1.8815, + "step": 46230 + }, + { + "epoch": 1.72, + "learning_rate": 8.2802097668018e-06, + "loss": 1.8022, + "step": 46240 + }, + { + "epoch": 1.72, + "learning_rate": 8.279837839848254e-06, + "loss": 1.7409, + "step": 46250 + }, + { + "epoch": 1.72, + "learning_rate": 8.279465912894709e-06, + "loss": 1.7874, + "step": 46260 + }, + { + "epoch": 1.72, + "learning_rate": 8.279093985941163e-06, + "loss": 1.9232, + "step": 46270 + }, + { + "epoch": 1.72, + "learning_rate": 8.278722058987616e-06, + "loss": 1.8185, + "step": 46280 + }, + { + "epoch": 1.72, + "learning_rate": 8.278350132034068e-06, + "loss": 1.8012, + "step": 46290 + }, + { + "epoch": 1.72, + "learning_rate": 8.277978205080523e-06, + "loss": 1.74, + "step": 46300 + }, + { + "epoch": 1.72, + "eval_loss": 1.7182563543319702, + "eval_runtime": 16.8334, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 46300 + }, + { + "epoch": 1.72, + "learning_rate": 8.277606278126976e-06, + "loss": 1.8339, + "step": 46310 + }, + { + "epoch": 1.72, + "learning_rate": 8.27723435117343e-06, + "loss": 1.8038, + "step": 46320 + }, + { + "epoch": 1.72, + "learning_rate": 8.276862424219883e-06, + "loss": 1.8302, + "step": 46330 + }, + { + "epoch": 1.72, + "learning_rate": 8.276490497266337e-06, + "loss": 1.7541, + "step": 46340 + }, + { + "epoch": 1.72, + "learning_rate": 8.27611857031279e-06, + "loss": 1.7886, + "step": 46350 + }, + { + "epoch": 1.72, + "learning_rate": 8.275746643359245e-06, + "loss": 1.61, + "step": 46360 + }, + { + "epoch": 1.72, + "learning_rate": 8.275374716405699e-06, + "loss": 1.754, + "step": 46370 + }, + { + "epoch": 1.72, + "learning_rate": 8.275002789452152e-06, + "loss": 1.7784, + "step": 46380 + }, + { + "epoch": 1.73, + "learning_rate": 8.274630862498606e-06, + "loss": 1.8344, + "step": 46390 + }, + { + "epoch": 1.73, + "learning_rate": 8.27425893554506e-06, + "loss": 1.7695, + "step": 46400 + }, + { + "epoch": 1.73, + "eval_loss": 1.718205451965332, + "eval_runtime": 16.8362, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 46400 + }, + { + "epoch": 1.73, + "learning_rate": 8.273887008591513e-06, + "loss": 1.8434, + "step": 46410 + }, + { + "epoch": 1.73, + "learning_rate": 8.273515081637968e-06, + "loss": 1.8885, + "step": 46420 + }, + { + "epoch": 1.73, + "learning_rate": 8.273143154684421e-06, + "loss": 1.7997, + "step": 46430 + }, + { + "epoch": 1.73, + "learning_rate": 8.272771227730875e-06, + "loss": 1.8016, + "step": 46440 + }, + { + "epoch": 1.73, + "learning_rate": 8.272399300777328e-06, + "loss": 1.8612, + "step": 46450 + }, + { + "epoch": 1.73, + "learning_rate": 8.272027373823782e-06, + "loss": 1.8145, + "step": 46460 + }, + { + "epoch": 1.73, + "learning_rate": 8.271655446870235e-06, + "loss": 1.7202, + "step": 46470 + }, + { + "epoch": 1.73, + "learning_rate": 8.271283519916689e-06, + "loss": 1.8401, + "step": 46480 + }, + { + "epoch": 1.73, + "learning_rate": 8.270911592963142e-06, + "loss": 1.8022, + "step": 46490 + }, + { + "epoch": 1.73, + "learning_rate": 8.270539666009596e-06, + "loss": 1.5419, + "step": 46500 + }, + { + "epoch": 1.73, + "eval_loss": 1.7191686630249023, + "eval_runtime": 16.8146, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 46500 + }, + { + "epoch": 1.73, + "learning_rate": 8.270167739056049e-06, + "loss": 1.7806, + "step": 46510 + }, + { + "epoch": 1.73, + "learning_rate": 8.269795812102504e-06, + "loss": 1.6974, + "step": 46520 + }, + { + "epoch": 1.73, + "learning_rate": 8.269423885148958e-06, + "loss": 1.7808, + "step": 46530 + }, + { + "epoch": 1.73, + "learning_rate": 8.269051958195411e-06, + "loss": 1.6761, + "step": 46540 + }, + { + "epoch": 1.73, + "learning_rate": 8.268680031241865e-06, + "loss": 1.6731, + "step": 46550 + }, + { + "epoch": 1.73, + "learning_rate": 8.268308104288318e-06, + "loss": 1.7375, + "step": 46560 + }, + { + "epoch": 1.73, + "learning_rate": 8.267936177334771e-06, + "loss": 1.6577, + "step": 46570 + }, + { + "epoch": 1.73, + "learning_rate": 8.267564250381227e-06, + "loss": 1.7902, + "step": 46580 + }, + { + "epoch": 1.73, + "learning_rate": 8.26719232342768e-06, + "loss": 1.738, + "step": 46590 + }, + { + "epoch": 1.73, + "learning_rate": 8.266820396474134e-06, + "loss": 1.8083, + "step": 46600 + }, + { + "epoch": 1.73, + "eval_loss": 1.7181987762451172, + "eval_runtime": 16.8155, + "eval_samples_per_second": 59.469, + "eval_steps_per_second": 3.747, + "step": 46600 + }, + { + "epoch": 1.73, + "learning_rate": 8.266448469520587e-06, + "loss": 1.8177, + "step": 46610 + }, + { + "epoch": 1.73, + "learning_rate": 8.26607654256704e-06, + "loss": 1.7522, + "step": 46620 + }, + { + "epoch": 1.73, + "learning_rate": 8.265704615613494e-06, + "loss": 1.7669, + "step": 46630 + }, + { + "epoch": 1.73, + "learning_rate": 8.265332688659949e-06, + "loss": 1.818, + "step": 46640 + }, + { + "epoch": 1.74, + "learning_rate": 8.264960761706403e-06, + "loss": 1.7681, + "step": 46650 + }, + { + "epoch": 1.74, + "learning_rate": 8.264588834752854e-06, + "loss": 1.8113, + "step": 46660 + }, + { + "epoch": 1.74, + "learning_rate": 8.264216907799308e-06, + "loss": 1.7555, + "step": 46670 + }, + { + "epoch": 1.74, + "learning_rate": 8.263844980845763e-06, + "loss": 1.7744, + "step": 46680 + }, + { + "epoch": 1.74, + "learning_rate": 8.263473053892216e-06, + "loss": 1.866, + "step": 46690 + }, + { + "epoch": 1.74, + "learning_rate": 8.26310112693867e-06, + "loss": 1.7034, + "step": 46700 + }, + { + "epoch": 1.74, + "eval_loss": 1.7168010473251343, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 46700 + }, + { + "epoch": 1.74, + "learning_rate": 8.262729199985123e-06, + "loss": 1.8773, + "step": 46710 + }, + { + "epoch": 1.74, + "learning_rate": 8.262357273031577e-06, + "loss": 1.9253, + "step": 46720 + }, + { + "epoch": 1.74, + "learning_rate": 8.26198534607803e-06, + "loss": 1.8905, + "step": 46730 + }, + { + "epoch": 1.74, + "learning_rate": 8.261613419124485e-06, + "loss": 1.8265, + "step": 46740 + }, + { + "epoch": 1.74, + "learning_rate": 8.261241492170939e-06, + "loss": 1.7739, + "step": 46750 + }, + { + "epoch": 1.74, + "learning_rate": 8.260869565217392e-06, + "loss": 1.8616, + "step": 46760 + }, + { + "epoch": 1.74, + "learning_rate": 8.260497638263846e-06, + "loss": 1.8108, + "step": 46770 + }, + { + "epoch": 1.74, + "learning_rate": 8.2601257113103e-06, + "loss": 1.9803, + "step": 46780 + }, + { + "epoch": 1.74, + "learning_rate": 8.259753784356753e-06, + "loss": 1.7558, + "step": 46790 + }, + { + "epoch": 1.74, + "learning_rate": 8.259381857403208e-06, + "loss": 2.0439, + "step": 46800 + }, + { + "epoch": 1.74, + "eval_loss": 1.7174417972564697, + "eval_runtime": 16.8394, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 46800 + }, + { + "epoch": 1.74, + "learning_rate": 8.259009930449661e-06, + "loss": 1.7332, + "step": 46810 + }, + { + "epoch": 1.74, + "learning_rate": 8.258638003496115e-06, + "loss": 1.8193, + "step": 46820 + }, + { + "epoch": 1.74, + "learning_rate": 8.258266076542568e-06, + "loss": 1.77, + "step": 46830 + }, + { + "epoch": 1.74, + "learning_rate": 8.257894149589022e-06, + "loss": 1.832, + "step": 46840 + }, + { + "epoch": 1.74, + "learning_rate": 8.257522222635475e-06, + "loss": 1.7754, + "step": 46850 + }, + { + "epoch": 1.74, + "learning_rate": 8.257150295681929e-06, + "loss": 1.8277, + "step": 46860 + }, + { + "epoch": 1.74, + "learning_rate": 8.256778368728382e-06, + "loss": 1.7709, + "step": 46870 + }, + { + "epoch": 1.74, + "learning_rate": 8.256406441774835e-06, + "loss": 1.7557, + "step": 46880 + }, + { + "epoch": 1.74, + "learning_rate": 8.256034514821289e-06, + "loss": 1.7797, + "step": 46890 + }, + { + "epoch": 1.74, + "learning_rate": 8.255662587867742e-06, + "loss": 1.6615, + "step": 46900 + }, + { + "epoch": 1.74, + "eval_loss": 1.7173336744308472, + "eval_runtime": 16.8361, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 46900 + }, + { + "epoch": 1.74, + "learning_rate": 8.255290660914198e-06, + "loss": 1.733, + "step": 46910 + }, + { + "epoch": 1.75, + "learning_rate": 8.254918733960651e-06, + "loss": 1.817, + "step": 46920 + }, + { + "epoch": 1.75, + "learning_rate": 8.254546807007104e-06, + "loss": 1.7991, + "step": 46930 + }, + { + "epoch": 1.75, + "learning_rate": 8.254174880053558e-06, + "loss": 1.7428, + "step": 46940 + }, + { + "epoch": 1.75, + "learning_rate": 8.253802953100011e-06, + "loss": 1.9143, + "step": 46950 + }, + { + "epoch": 1.75, + "learning_rate": 8.253431026146465e-06, + "loss": 1.7768, + "step": 46960 + }, + { + "epoch": 1.75, + "learning_rate": 8.25305909919292e-06, + "loss": 1.5864, + "step": 46970 + }, + { + "epoch": 1.75, + "learning_rate": 8.252687172239373e-06, + "loss": 1.6869, + "step": 46980 + }, + { + "epoch": 1.75, + "learning_rate": 8.252315245285827e-06, + "loss": 1.8055, + "step": 46990 + }, + { + "epoch": 1.75, + "learning_rate": 8.25194331833228e-06, + "loss": 1.8808, + "step": 47000 + }, + { + "epoch": 1.75, + "eval_loss": 1.7179330587387085, + "eval_runtime": 16.8303, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 47000 + }, + { + "epoch": 1.75, + "learning_rate": 8.251571391378734e-06, + "loss": 1.8108, + "step": 47010 + }, + { + "epoch": 1.75, + "learning_rate": 8.251199464425187e-06, + "loss": 1.7848, + "step": 47020 + }, + { + "epoch": 1.75, + "learning_rate": 8.250827537471642e-06, + "loss": 1.7718, + "step": 47030 + }, + { + "epoch": 1.75, + "learning_rate": 8.250455610518094e-06, + "loss": 1.827, + "step": 47040 + }, + { + "epoch": 1.75, + "learning_rate": 8.250083683564548e-06, + "loss": 1.8081, + "step": 47050 + }, + { + "epoch": 1.75, + "learning_rate": 8.249711756611001e-06, + "loss": 1.7919, + "step": 47060 + }, + { + "epoch": 1.75, + "learning_rate": 8.249339829657456e-06, + "loss": 1.705, + "step": 47070 + }, + { + "epoch": 1.75, + "learning_rate": 8.24896790270391e-06, + "loss": 1.7646, + "step": 47080 + }, + { + "epoch": 1.75, + "learning_rate": 8.248595975750363e-06, + "loss": 1.8164, + "step": 47090 + }, + { + "epoch": 1.75, + "learning_rate": 8.248224048796817e-06, + "loss": 1.7072, + "step": 47100 + }, + { + "epoch": 1.75, + "eval_loss": 1.7169231176376343, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 47100 + }, + { + "epoch": 1.75, + "learning_rate": 8.24785212184327e-06, + "loss": 1.8419, + "step": 47110 + }, + { + "epoch": 1.75, + "learning_rate": 8.247480194889724e-06, + "loss": 1.6711, + "step": 47120 + }, + { + "epoch": 1.75, + "learning_rate": 8.247108267936179e-06, + "loss": 1.6873, + "step": 47130 + }, + { + "epoch": 1.75, + "learning_rate": 8.246736340982632e-06, + "loss": 1.8379, + "step": 47140 + }, + { + "epoch": 1.75, + "learning_rate": 8.246364414029086e-06, + "loss": 1.8826, + "step": 47150 + }, + { + "epoch": 1.75, + "learning_rate": 8.245992487075539e-06, + "loss": 1.8032, + "step": 47160 + }, + { + "epoch": 1.75, + "learning_rate": 8.245620560121993e-06, + "loss": 1.7641, + "step": 47170 + }, + { + "epoch": 1.75, + "learning_rate": 8.245248633168446e-06, + "loss": 1.8014, + "step": 47180 + }, + { + "epoch": 1.76, + "learning_rate": 8.244876706214901e-06, + "loss": 1.8863, + "step": 47190 + }, + { + "epoch": 1.76, + "learning_rate": 8.244504779261355e-06, + "loss": 1.6412, + "step": 47200 + }, + { + "epoch": 1.76, + "eval_loss": 1.7176753282546997, + "eval_runtime": 16.8255, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 47200 + }, + { + "epoch": 1.76, + "learning_rate": 8.244132852307808e-06, + "loss": 1.853, + "step": 47210 + }, + { + "epoch": 1.76, + "learning_rate": 8.243760925354262e-06, + "loss": 1.7434, + "step": 47220 + }, + { + "epoch": 1.76, + "learning_rate": 8.243388998400715e-06, + "loss": 1.6993, + "step": 47230 + }, + { + "epoch": 1.76, + "learning_rate": 8.243017071447168e-06, + "loss": 1.8647, + "step": 47240 + }, + { + "epoch": 1.76, + "learning_rate": 8.242645144493622e-06, + "loss": 1.65, + "step": 47250 + }, + { + "epoch": 1.76, + "learning_rate": 8.242273217540075e-06, + "loss": 1.8067, + "step": 47260 + }, + { + "epoch": 1.76, + "learning_rate": 8.241901290586529e-06, + "loss": 1.7729, + "step": 47270 + }, + { + "epoch": 1.76, + "learning_rate": 8.241529363632982e-06, + "loss": 1.8546, + "step": 47280 + }, + { + "epoch": 1.76, + "learning_rate": 8.241157436679437e-06, + "loss": 1.7269, + "step": 47290 + }, + { + "epoch": 1.76, + "learning_rate": 8.240785509725891e-06, + "loss": 1.8166, + "step": 47300 + }, + { + "epoch": 1.76, + "eval_loss": 1.7170039415359497, + "eval_runtime": 16.8352, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 47300 + }, + { + "epoch": 1.76, + "learning_rate": 8.240413582772344e-06, + "loss": 1.7345, + "step": 47310 + }, + { + "epoch": 1.76, + "learning_rate": 8.240041655818798e-06, + "loss": 1.7255, + "step": 47320 + }, + { + "epoch": 1.76, + "learning_rate": 8.239669728865251e-06, + "loss": 1.8189, + "step": 47330 + }, + { + "epoch": 1.76, + "learning_rate": 8.239297801911705e-06, + "loss": 1.8116, + "step": 47340 + }, + { + "epoch": 1.76, + "learning_rate": 8.23892587495816e-06, + "loss": 1.7625, + "step": 47350 + }, + { + "epoch": 1.76, + "learning_rate": 8.238553948004613e-06, + "loss": 1.8175, + "step": 47360 + }, + { + "epoch": 1.76, + "learning_rate": 8.238182021051067e-06, + "loss": 1.9384, + "step": 47370 + }, + { + "epoch": 1.76, + "learning_rate": 8.23781009409752e-06, + "loss": 1.8164, + "step": 47380 + }, + { + "epoch": 1.76, + "learning_rate": 8.237438167143974e-06, + "loss": 1.7072, + "step": 47390 + }, + { + "epoch": 1.76, + "learning_rate": 8.237066240190427e-06, + "loss": 1.8443, + "step": 47400 + }, + { + "epoch": 1.76, + "eval_loss": 1.7162153720855713, + "eval_runtime": 16.8307, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 47400 + }, + { + "epoch": 1.76, + "learning_rate": 8.23669431323688e-06, + "loss": 1.9612, + "step": 47410 + }, + { + "epoch": 1.76, + "learning_rate": 8.236322386283334e-06, + "loss": 1.7927, + "step": 47420 + }, + { + "epoch": 1.76, + "learning_rate": 8.235950459329788e-06, + "loss": 1.7585, + "step": 47430 + }, + { + "epoch": 1.76, + "learning_rate": 8.235578532376241e-06, + "loss": 1.7032, + "step": 47440 + }, + { + "epoch": 1.76, + "learning_rate": 8.235206605422695e-06, + "loss": 1.7266, + "step": 47450 + }, + { + "epoch": 1.77, + "learning_rate": 8.23483467846915e-06, + "loss": 1.7845, + "step": 47460 + }, + { + "epoch": 1.77, + "learning_rate": 8.234462751515603e-06, + "loss": 1.9828, + "step": 47470 + }, + { + "epoch": 1.77, + "learning_rate": 8.234090824562057e-06, + "loss": 1.8712, + "step": 47480 + }, + { + "epoch": 1.77, + "learning_rate": 8.23371889760851e-06, + "loss": 1.7333, + "step": 47490 + }, + { + "epoch": 1.77, + "learning_rate": 8.233346970654963e-06, + "loss": 1.7035, + "step": 47500 + }, + { + "epoch": 1.77, + "eval_loss": 1.7164381742477417, + "eval_runtime": 16.842, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 47500 + }, + { + "epoch": 1.77, + "learning_rate": 8.232975043701417e-06, + "loss": 1.6957, + "step": 47510 + }, + { + "epoch": 1.77, + "learning_rate": 8.232603116747872e-06, + "loss": 1.7026, + "step": 47520 + }, + { + "epoch": 1.77, + "learning_rate": 8.232231189794326e-06, + "loss": 1.7562, + "step": 47530 + }, + { + "epoch": 1.77, + "learning_rate": 8.231859262840779e-06, + "loss": 1.749, + "step": 47540 + }, + { + "epoch": 1.77, + "learning_rate": 8.231487335887232e-06, + "loss": 1.7223, + "step": 47550 + }, + { + "epoch": 1.77, + "learning_rate": 8.231115408933686e-06, + "loss": 1.8602, + "step": 47560 + }, + { + "epoch": 1.77, + "learning_rate": 8.23074348198014e-06, + "loss": 1.8011, + "step": 47570 + }, + { + "epoch": 1.77, + "learning_rate": 8.230371555026595e-06, + "loss": 1.8927, + "step": 47580 + }, + { + "epoch": 1.77, + "learning_rate": 8.229999628073048e-06, + "loss": 1.7145, + "step": 47590 + }, + { + "epoch": 1.77, + "learning_rate": 8.2296277011195e-06, + "loss": 1.8511, + "step": 47600 + }, + { + "epoch": 1.77, + "eval_loss": 1.7153019905090332, + "eval_runtime": 16.8433, + "eval_samples_per_second": 59.371, + "eval_steps_per_second": 3.74, + "step": 47600 + }, + { + "epoch": 1.77, + "learning_rate": 8.229255774165953e-06, + "loss": 1.6436, + "step": 47610 + }, + { + "epoch": 1.77, + "learning_rate": 8.228883847212408e-06, + "loss": 1.8304, + "step": 47620 + }, + { + "epoch": 1.77, + "learning_rate": 8.228511920258862e-06, + "loss": 1.7199, + "step": 47630 + }, + { + "epoch": 1.77, + "learning_rate": 8.228139993305315e-06, + "loss": 1.8398, + "step": 47640 + }, + { + "epoch": 1.77, + "learning_rate": 8.227768066351769e-06, + "loss": 1.7307, + "step": 47650 + }, + { + "epoch": 1.77, + "learning_rate": 8.227396139398222e-06, + "loss": 1.6855, + "step": 47660 + }, + { + "epoch": 1.77, + "learning_rate": 8.227024212444676e-06, + "loss": 1.6618, + "step": 47670 + }, + { + "epoch": 1.77, + "learning_rate": 8.22665228549113e-06, + "loss": 1.7785, + "step": 47680 + }, + { + "epoch": 1.77, + "learning_rate": 8.226280358537584e-06, + "loss": 1.7331, + "step": 47690 + }, + { + "epoch": 1.77, + "learning_rate": 8.225908431584038e-06, + "loss": 1.7263, + "step": 47700 + }, + { + "epoch": 1.77, + "eval_loss": 1.7162526845932007, + "eval_runtime": 16.8164, + "eval_samples_per_second": 59.466, + "eval_steps_per_second": 3.746, + "step": 47700 + }, + { + "epoch": 1.77, + "learning_rate": 8.225536504630491e-06, + "loss": 1.7843, + "step": 47710 + }, + { + "epoch": 1.77, + "learning_rate": 8.225164577676945e-06, + "loss": 1.7286, + "step": 47720 + }, + { + "epoch": 1.78, + "learning_rate": 8.224792650723398e-06, + "loss": 1.7908, + "step": 47730 + }, + { + "epoch": 1.78, + "learning_rate": 8.224420723769853e-06, + "loss": 1.7702, + "step": 47740 + }, + { + "epoch": 1.78, + "learning_rate": 8.224048796816307e-06, + "loss": 1.6756, + "step": 47750 + }, + { + "epoch": 1.78, + "learning_rate": 8.22367686986276e-06, + "loss": 1.9398, + "step": 47760 + }, + { + "epoch": 1.78, + "learning_rate": 8.223304942909214e-06, + "loss": 1.8248, + "step": 47770 + }, + { + "epoch": 1.78, + "learning_rate": 8.222933015955667e-06, + "loss": 1.7244, + "step": 47780 + }, + { + "epoch": 1.78, + "learning_rate": 8.22256108900212e-06, + "loss": 1.7028, + "step": 47790 + }, + { + "epoch": 1.78, + "learning_rate": 8.222189162048574e-06, + "loss": 1.8496, + "step": 47800 + }, + { + "epoch": 1.78, + "eval_loss": 1.7151044607162476, + "eval_runtime": 16.8202, + "eval_samples_per_second": 59.453, + "eval_steps_per_second": 3.746, + "step": 47800 + }, + { + "epoch": 1.78, + "learning_rate": 8.221817235095028e-06, + "loss": 1.803, + "step": 47810 + }, + { + "epoch": 1.78, + "learning_rate": 8.221445308141481e-06, + "loss": 1.7582, + "step": 47820 + }, + { + "epoch": 1.78, + "learning_rate": 8.221073381187934e-06, + "loss": 1.8333, + "step": 47830 + }, + { + "epoch": 1.78, + "learning_rate": 8.22070145423439e-06, + "loss": 1.8334, + "step": 47840 + }, + { + "epoch": 1.78, + "learning_rate": 8.220329527280843e-06, + "loss": 1.7811, + "step": 47850 + }, + { + "epoch": 1.78, + "learning_rate": 8.219957600327296e-06, + "loss": 1.7774, + "step": 47860 + }, + { + "epoch": 1.78, + "learning_rate": 8.21958567337375e-06, + "loss": 1.8879, + "step": 47870 + }, + { + "epoch": 1.78, + "learning_rate": 8.219213746420203e-06, + "loss": 1.8212, + "step": 47880 + }, + { + "epoch": 1.78, + "learning_rate": 8.218841819466657e-06, + "loss": 1.6736, + "step": 47890 + }, + { + "epoch": 1.78, + "learning_rate": 8.218469892513112e-06, + "loss": 1.7798, + "step": 47900 + }, + { + "epoch": 1.78, + "eval_loss": 1.7142382860183716, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 47900 + }, + { + "epoch": 1.78, + "learning_rate": 8.218097965559565e-06, + "loss": 1.8129, + "step": 47910 + }, + { + "epoch": 1.78, + "learning_rate": 8.217726038606019e-06, + "loss": 1.7904, + "step": 47920 + }, + { + "epoch": 1.78, + "learning_rate": 8.217354111652472e-06, + "loss": 1.6702, + "step": 47930 + }, + { + "epoch": 1.78, + "learning_rate": 8.216982184698926e-06, + "loss": 1.8007, + "step": 47940 + }, + { + "epoch": 1.78, + "learning_rate": 8.21661025774538e-06, + "loss": 1.7372, + "step": 47950 + }, + { + "epoch": 1.78, + "learning_rate": 8.216238330791834e-06, + "loss": 1.7471, + "step": 47960 + }, + { + "epoch": 1.78, + "learning_rate": 8.215866403838288e-06, + "loss": 1.7818, + "step": 47970 + }, + { + "epoch": 1.78, + "learning_rate": 8.21549447688474e-06, + "loss": 1.929, + "step": 47980 + }, + { + "epoch": 1.78, + "learning_rate": 8.215122549931193e-06, + "loss": 1.7353, + "step": 47990 + }, + { + "epoch": 1.79, + "learning_rate": 8.214750622977648e-06, + "loss": 1.7345, + "step": 48000 + }, + { + "epoch": 1.79, + "eval_loss": 1.7153398990631104, + "eval_runtime": 16.8185, + "eval_samples_per_second": 59.458, + "eval_steps_per_second": 3.746, + "step": 48000 + }, + { + "epoch": 1.79, + "learning_rate": 8.214378696024102e-06, + "loss": 1.8323, + "step": 48010 + }, + { + "epoch": 1.79, + "learning_rate": 8.214006769070555e-06, + "loss": 1.6697, + "step": 48020 + }, + { + "epoch": 1.79, + "learning_rate": 8.213634842117009e-06, + "loss": 1.7863, + "step": 48030 + }, + { + "epoch": 1.79, + "learning_rate": 8.213262915163462e-06, + "loss": 1.8738, + "step": 48040 + }, + { + "epoch": 1.79, + "learning_rate": 8.212890988209916e-06, + "loss": 1.7649, + "step": 48050 + }, + { + "epoch": 1.79, + "learning_rate": 8.212519061256369e-06, + "loss": 1.8713, + "step": 48060 + }, + { + "epoch": 1.79, + "learning_rate": 8.212147134302824e-06, + "loss": 1.7594, + "step": 48070 + }, + { + "epoch": 1.79, + "learning_rate": 8.211775207349278e-06, + "loss": 1.7235, + "step": 48080 + }, + { + "epoch": 1.79, + "learning_rate": 8.211403280395731e-06, + "loss": 1.804, + "step": 48090 + }, + { + "epoch": 1.79, + "learning_rate": 8.211031353442185e-06, + "loss": 1.7902, + "step": 48100 + }, + { + "epoch": 1.79, + "eval_loss": 1.715395450592041, + "eval_runtime": 16.8367, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 48100 + }, + { + "epoch": 1.79, + "learning_rate": 8.210659426488638e-06, + "loss": 1.8354, + "step": 48110 + }, + { + "epoch": 1.79, + "learning_rate": 8.210287499535092e-06, + "loss": 1.825, + "step": 48120 + }, + { + "epoch": 1.79, + "learning_rate": 8.209915572581547e-06, + "loss": 1.6894, + "step": 48130 + }, + { + "epoch": 1.79, + "learning_rate": 8.209543645628e-06, + "loss": 1.7585, + "step": 48140 + }, + { + "epoch": 1.79, + "learning_rate": 8.209171718674454e-06, + "loss": 1.8208, + "step": 48150 + }, + { + "epoch": 1.79, + "learning_rate": 8.208799791720907e-06, + "loss": 1.8812, + "step": 48160 + }, + { + "epoch": 1.79, + "learning_rate": 8.20842786476736e-06, + "loss": 1.7584, + "step": 48170 + }, + { + "epoch": 1.79, + "learning_rate": 8.208055937813814e-06, + "loss": 1.7263, + "step": 48180 + }, + { + "epoch": 1.79, + "learning_rate": 8.207684010860267e-06, + "loss": 1.9201, + "step": 48190 + }, + { + "epoch": 1.79, + "learning_rate": 8.207312083906721e-06, + "loss": 1.7621, + "step": 48200 + }, + { + "epoch": 1.79, + "eval_loss": 1.7153695821762085, + "eval_runtime": 16.8171, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 48200 + }, + { + "epoch": 1.79, + "learning_rate": 8.206940156953174e-06, + "loss": 1.8116, + "step": 48210 + }, + { + "epoch": 1.79, + "learning_rate": 8.206568229999628e-06, + "loss": 1.7977, + "step": 48220 + }, + { + "epoch": 1.79, + "learning_rate": 8.206196303046083e-06, + "loss": 1.6666, + "step": 48230 + }, + { + "epoch": 1.79, + "learning_rate": 8.205824376092536e-06, + "loss": 1.8954, + "step": 48240 + }, + { + "epoch": 1.79, + "learning_rate": 8.20545244913899e-06, + "loss": 1.6658, + "step": 48250 + }, + { + "epoch": 1.79, + "learning_rate": 8.205080522185443e-06, + "loss": 1.9006, + "step": 48260 + }, + { + "epoch": 1.8, + "learning_rate": 8.204708595231897e-06, + "loss": 1.8147, + "step": 48270 + }, + { + "epoch": 1.8, + "learning_rate": 8.20433666827835e-06, + "loss": 1.7572, + "step": 48280 + }, + { + "epoch": 1.8, + "learning_rate": 8.203964741324805e-06, + "loss": 1.8597, + "step": 48290 + }, + { + "epoch": 1.8, + "learning_rate": 8.203592814371259e-06, + "loss": 1.914, + "step": 48300 + }, + { + "epoch": 1.8, + "eval_loss": 1.7144321203231812, + "eval_runtime": 16.8181, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 48300 + }, + { + "epoch": 1.8, + "learning_rate": 8.203220887417712e-06, + "loss": 1.7576, + "step": 48310 + }, + { + "epoch": 1.8, + "learning_rate": 8.202848960464166e-06, + "loss": 1.6747, + "step": 48320 + }, + { + "epoch": 1.8, + "learning_rate": 8.20247703351062e-06, + "loss": 1.6625, + "step": 48330 + }, + { + "epoch": 1.8, + "learning_rate": 8.202105106557073e-06, + "loss": 1.8869, + "step": 48340 + }, + { + "epoch": 1.8, + "learning_rate": 8.201733179603526e-06, + "loss": 1.773, + "step": 48350 + }, + { + "epoch": 1.8, + "learning_rate": 8.20136125264998e-06, + "loss": 1.7024, + "step": 48360 + }, + { + "epoch": 1.8, + "learning_rate": 8.200989325696433e-06, + "loss": 1.7431, + "step": 48370 + }, + { + "epoch": 1.8, + "learning_rate": 8.200617398742887e-06, + "loss": 1.6885, + "step": 48380 + }, + { + "epoch": 1.8, + "learning_rate": 8.200245471789342e-06, + "loss": 1.7839, + "step": 48390 + }, + { + "epoch": 1.8, + "learning_rate": 8.199873544835795e-06, + "loss": 1.7661, + "step": 48400 + }, + { + "epoch": 1.8, + "eval_loss": 1.7137947082519531, + "eval_runtime": 16.8322, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 48400 + }, + { + "epoch": 1.8, + "learning_rate": 8.199501617882249e-06, + "loss": 1.8375, + "step": 48410 + }, + { + "epoch": 1.8, + "learning_rate": 8.199129690928702e-06, + "loss": 1.8692, + "step": 48420 + }, + { + "epoch": 1.8, + "learning_rate": 8.198757763975156e-06, + "loss": 1.708, + "step": 48430 + }, + { + "epoch": 1.8, + "learning_rate": 8.198385837021609e-06, + "loss": 1.6711, + "step": 48440 + }, + { + "epoch": 1.8, + "learning_rate": 8.198013910068064e-06, + "loss": 1.7725, + "step": 48450 + }, + { + "epoch": 1.8, + "learning_rate": 8.197641983114518e-06, + "loss": 2.0603, + "step": 48460 + }, + { + "epoch": 1.8, + "learning_rate": 8.197270056160971e-06, + "loss": 1.6671, + "step": 48470 + }, + { + "epoch": 1.8, + "learning_rate": 8.196898129207425e-06, + "loss": 1.7463, + "step": 48480 + }, + { + "epoch": 1.8, + "learning_rate": 8.196526202253878e-06, + "loss": 1.7318, + "step": 48490 + }, + { + "epoch": 1.8, + "learning_rate": 8.196154275300331e-06, + "loss": 1.7826, + "step": 48500 + }, + { + "epoch": 1.8, + "eval_loss": 1.714715838432312, + "eval_runtime": 16.816, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 48500 + }, + { + "epoch": 1.8, + "learning_rate": 8.195782348346787e-06, + "loss": 1.8352, + "step": 48510 + }, + { + "epoch": 1.8, + "learning_rate": 8.19541042139324e-06, + "loss": 1.8589, + "step": 48520 + }, + { + "epoch": 1.8, + "learning_rate": 8.195038494439694e-06, + "loss": 1.7764, + "step": 48530 + }, + { + "epoch": 1.81, + "learning_rate": 8.194666567486145e-06, + "loss": 1.7827, + "step": 48540 + }, + { + "epoch": 1.81, + "learning_rate": 8.1942946405326e-06, + "loss": 1.6974, + "step": 48550 + }, + { + "epoch": 1.81, + "learning_rate": 8.193922713579054e-06, + "loss": 1.7566, + "step": 48560 + }, + { + "epoch": 1.81, + "learning_rate": 8.193550786625507e-06, + "loss": 1.8576, + "step": 48570 + }, + { + "epoch": 1.81, + "learning_rate": 8.19317885967196e-06, + "loss": 1.7558, + "step": 48580 + }, + { + "epoch": 1.81, + "learning_rate": 8.192806932718414e-06, + "loss": 1.6999, + "step": 48590 + }, + { + "epoch": 1.81, + "learning_rate": 8.192435005764868e-06, + "loss": 1.7844, + "step": 48600 + }, + { + "epoch": 1.81, + "eval_loss": 1.7143700122833252, + "eval_runtime": 16.814, + "eval_samples_per_second": 59.474, + "eval_steps_per_second": 3.747, + "step": 48600 + }, + { + "epoch": 1.81, + "learning_rate": 8.192063078811321e-06, + "loss": 1.7786, + "step": 48610 + }, + { + "epoch": 1.81, + "learning_rate": 8.191691151857776e-06, + "loss": 1.7517, + "step": 48620 + }, + { + "epoch": 1.81, + "learning_rate": 8.19131922490423e-06, + "loss": 1.745, + "step": 48630 + }, + { + "epoch": 1.81, + "learning_rate": 8.190947297950683e-06, + "loss": 1.8511, + "step": 48640 + }, + { + "epoch": 1.81, + "learning_rate": 8.190575370997137e-06, + "loss": 1.8424, + "step": 48650 + }, + { + "epoch": 1.81, + "learning_rate": 8.19020344404359e-06, + "loss": 1.9311, + "step": 48660 + }, + { + "epoch": 1.81, + "learning_rate": 8.189831517090044e-06, + "loss": 1.8425, + "step": 48670 + }, + { + "epoch": 1.81, + "learning_rate": 8.189459590136499e-06, + "loss": 1.7327, + "step": 48680 + }, + { + "epoch": 1.81, + "learning_rate": 8.189087663182952e-06, + "loss": 1.6043, + "step": 48690 + }, + { + "epoch": 1.81, + "learning_rate": 8.188715736229406e-06, + "loss": 1.6931, + "step": 48700 + }, + { + "epoch": 1.81, + "eval_loss": 1.7135536670684814, + "eval_runtime": 16.8106, + "eval_samples_per_second": 59.486, + "eval_steps_per_second": 3.748, + "step": 48700 + }, + { + "epoch": 1.81, + "learning_rate": 8.18834380927586e-06, + "loss": 1.6413, + "step": 48710 + }, + { + "epoch": 1.81, + "learning_rate": 8.187971882322313e-06, + "loss": 1.6826, + "step": 48720 + }, + { + "epoch": 1.81, + "learning_rate": 8.187599955368766e-06, + "loss": 1.6976, + "step": 48730 + }, + { + "epoch": 1.81, + "learning_rate": 8.18722802841522e-06, + "loss": 1.83, + "step": 48740 + }, + { + "epoch": 1.81, + "learning_rate": 8.186856101461673e-06, + "loss": 1.8504, + "step": 48750 + }, + { + "epoch": 1.81, + "learning_rate": 8.186484174508126e-06, + "loss": 1.695, + "step": 48760 + }, + { + "epoch": 1.81, + "learning_rate": 8.18611224755458e-06, + "loss": 1.714, + "step": 48770 + }, + { + "epoch": 1.81, + "learning_rate": 8.185740320601035e-06, + "loss": 1.8989, + "step": 48780 + }, + { + "epoch": 1.81, + "learning_rate": 8.185368393647489e-06, + "loss": 1.819, + "step": 48790 + }, + { + "epoch": 1.82, + "learning_rate": 8.184996466693942e-06, + "loss": 1.8067, + "step": 48800 + }, + { + "epoch": 1.82, + "eval_loss": 1.7138704061508179, + "eval_runtime": 16.81, + "eval_samples_per_second": 59.488, + "eval_steps_per_second": 3.748, + "step": 48800 + }, + { + "epoch": 1.82, + "learning_rate": 8.184624539740395e-06, + "loss": 1.7029, + "step": 48810 + }, + { + "epoch": 1.82, + "learning_rate": 8.184252612786849e-06, + "loss": 2.0155, + "step": 48820 + }, + { + "epoch": 1.82, + "learning_rate": 8.183880685833302e-06, + "loss": 1.6943, + "step": 48830 + }, + { + "epoch": 1.82, + "learning_rate": 8.183508758879758e-06, + "loss": 1.6937, + "step": 48840 + }, + { + "epoch": 1.82, + "learning_rate": 8.183136831926211e-06, + "loss": 1.7997, + "step": 48850 + }, + { + "epoch": 1.82, + "learning_rate": 8.182764904972664e-06, + "loss": 1.705, + "step": 48860 + }, + { + "epoch": 1.82, + "learning_rate": 8.182392978019118e-06, + "loss": 1.8313, + "step": 48870 + }, + { + "epoch": 1.82, + "learning_rate": 8.182021051065571e-06, + "loss": 1.8579, + "step": 48880 + }, + { + "epoch": 1.82, + "learning_rate": 8.181649124112025e-06, + "loss": 1.8719, + "step": 48890 + }, + { + "epoch": 1.82, + "learning_rate": 8.18127719715848e-06, + "loss": 1.7972, + "step": 48900 + }, + { + "epoch": 1.82, + "eval_loss": 1.7136342525482178, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 48900 + }, + { + "epoch": 1.82, + "learning_rate": 8.180905270204933e-06, + "loss": 1.8419, + "step": 48910 + }, + { + "epoch": 1.82, + "learning_rate": 8.180533343251385e-06, + "loss": 1.6945, + "step": 48920 + }, + { + "epoch": 1.82, + "learning_rate": 8.180161416297839e-06, + "loss": 1.8431, + "step": 48930 + }, + { + "epoch": 1.82, + "learning_rate": 8.179789489344294e-06, + "loss": 1.7632, + "step": 48940 + }, + { + "epoch": 1.82, + "learning_rate": 8.179417562390747e-06, + "loss": 1.7863, + "step": 48950 + }, + { + "epoch": 1.82, + "learning_rate": 8.1790456354372e-06, + "loss": 1.8545, + "step": 48960 + }, + { + "epoch": 1.82, + "learning_rate": 8.178673708483654e-06, + "loss": 1.7294, + "step": 48970 + }, + { + "epoch": 1.82, + "learning_rate": 8.178301781530108e-06, + "loss": 1.666, + "step": 48980 + }, + { + "epoch": 1.82, + "learning_rate": 8.177929854576561e-06, + "loss": 1.7707, + "step": 48990 + }, + { + "epoch": 1.82, + "learning_rate": 8.177557927623016e-06, + "loss": 1.8266, + "step": 49000 + }, + { + "epoch": 1.82, + "eval_loss": 1.7133804559707642, + "eval_runtime": 16.8355, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 49000 + }, + { + "epoch": 1.82, + "learning_rate": 8.17718600066947e-06, + "loss": 1.7153, + "step": 49010 + }, + { + "epoch": 1.82, + "learning_rate": 8.176814073715923e-06, + "loss": 1.8276, + "step": 49020 + }, + { + "epoch": 1.82, + "learning_rate": 8.176442146762377e-06, + "loss": 1.8207, + "step": 49030 + }, + { + "epoch": 1.82, + "learning_rate": 8.17607021980883e-06, + "loss": 1.9318, + "step": 49040 + }, + { + "epoch": 1.82, + "learning_rate": 8.175698292855284e-06, + "loss": 1.7324, + "step": 49050 + }, + { + "epoch": 1.82, + "learning_rate": 8.175326365901739e-06, + "loss": 1.707, + "step": 49060 + }, + { + "epoch": 1.83, + "learning_rate": 8.174954438948192e-06, + "loss": 1.67, + "step": 49070 + }, + { + "epoch": 1.83, + "learning_rate": 8.174582511994646e-06, + "loss": 1.6733, + "step": 49080 + }, + { + "epoch": 1.83, + "learning_rate": 8.174210585041099e-06, + "loss": 1.7397, + "step": 49090 + }, + { + "epoch": 1.83, + "learning_rate": 8.173838658087553e-06, + "loss": 1.7079, + "step": 49100 + }, + { + "epoch": 1.83, + "eval_loss": 1.71298086643219, + "eval_runtime": 16.8081, + "eval_samples_per_second": 59.495, + "eval_steps_per_second": 3.748, + "step": 49100 + }, + { + "epoch": 1.83, + "learning_rate": 8.173466731134006e-06, + "loss": 1.7888, + "step": 49110 + }, + { + "epoch": 1.83, + "learning_rate": 8.17309480418046e-06, + "loss": 1.7924, + "step": 49120 + }, + { + "epoch": 1.83, + "learning_rate": 8.172722877226913e-06, + "loss": 1.7479, + "step": 49130 + }, + { + "epoch": 1.83, + "learning_rate": 8.172350950273366e-06, + "loss": 1.7317, + "step": 49140 + }, + { + "epoch": 1.83, + "learning_rate": 8.17197902331982e-06, + "loss": 1.8051, + "step": 49150 + }, + { + "epoch": 1.83, + "learning_rate": 8.171607096366273e-06, + "loss": 1.7248, + "step": 49160 + }, + { + "epoch": 1.83, + "learning_rate": 8.171235169412728e-06, + "loss": 1.8687, + "step": 49170 + }, + { + "epoch": 1.83, + "learning_rate": 8.170863242459182e-06, + "loss": 1.9129, + "step": 49180 + }, + { + "epoch": 1.83, + "learning_rate": 8.170491315505635e-06, + "loss": 1.7669, + "step": 49190 + }, + { + "epoch": 1.83, + "learning_rate": 8.170119388552089e-06, + "loss": 1.9413, + "step": 49200 + }, + { + "epoch": 1.83, + "eval_loss": 1.7127944231033325, + "eval_runtime": 16.8156, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.747, + "step": 49200 + }, + { + "epoch": 1.83, + "learning_rate": 8.169747461598542e-06, + "loss": 1.7502, + "step": 49210 + }, + { + "epoch": 1.83, + "learning_rate": 8.169375534644996e-06, + "loss": 1.6753, + "step": 49220 + }, + { + "epoch": 1.83, + "learning_rate": 8.169003607691451e-06, + "loss": 1.7958, + "step": 49230 + }, + { + "epoch": 1.83, + "learning_rate": 8.168631680737904e-06, + "loss": 1.7704, + "step": 49240 + }, + { + "epoch": 1.83, + "learning_rate": 8.168259753784358e-06, + "loss": 1.7893, + "step": 49250 + }, + { + "epoch": 1.83, + "learning_rate": 8.167887826830811e-06, + "loss": 1.7518, + "step": 49260 + }, + { + "epoch": 1.83, + "learning_rate": 8.167515899877265e-06, + "loss": 1.8274, + "step": 49270 + }, + { + "epoch": 1.83, + "learning_rate": 8.167143972923718e-06, + "loss": 1.7563, + "step": 49280 + }, + { + "epoch": 1.83, + "learning_rate": 8.166772045970172e-06, + "loss": 1.7064, + "step": 49290 + }, + { + "epoch": 1.83, + "learning_rate": 8.166400119016625e-06, + "loss": 1.8135, + "step": 49300 + }, + { + "epoch": 1.83, + "eval_loss": 1.7118183374404907, + "eval_runtime": 16.8757, + "eval_samples_per_second": 59.257, + "eval_steps_per_second": 3.733, + "step": 49300 + }, + { + "epoch": 1.83, + "learning_rate": 8.166028192063079e-06, + "loss": 1.8331, + "step": 49310 + }, + { + "epoch": 1.83, + "learning_rate": 8.165656265109532e-06, + "loss": 1.8253, + "step": 49320 + }, + { + "epoch": 1.83, + "learning_rate": 8.165284338155987e-06, + "loss": 1.7631, + "step": 49330 + }, + { + "epoch": 1.84, + "learning_rate": 8.16491241120244e-06, + "loss": 1.8122, + "step": 49340 + }, + { + "epoch": 1.84, + "learning_rate": 8.164540484248894e-06, + "loss": 1.7764, + "step": 49350 + }, + { + "epoch": 1.84, + "learning_rate": 8.164168557295348e-06, + "loss": 1.779, + "step": 49360 + }, + { + "epoch": 1.84, + "learning_rate": 8.163796630341801e-06, + "loss": 1.8774, + "step": 49370 + }, + { + "epoch": 1.84, + "learning_rate": 8.163424703388254e-06, + "loss": 1.9312, + "step": 49380 + }, + { + "epoch": 1.84, + "learning_rate": 8.16305277643471e-06, + "loss": 1.7258, + "step": 49390 + }, + { + "epoch": 1.84, + "learning_rate": 8.162680849481163e-06, + "loss": 1.7425, + "step": 49400 + }, + { + "epoch": 1.84, + "eval_loss": 1.7122591733932495, + "eval_runtime": 16.8147, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 49400 + }, + { + "epoch": 1.84, + "learning_rate": 8.162308922527617e-06, + "loss": 1.7342, + "step": 49410 + }, + { + "epoch": 1.84, + "learning_rate": 8.16193699557407e-06, + "loss": 1.7643, + "step": 49420 + }, + { + "epoch": 1.84, + "learning_rate": 8.161565068620523e-06, + "loss": 1.8, + "step": 49430 + }, + { + "epoch": 1.84, + "learning_rate": 8.161193141666977e-06, + "loss": 1.7297, + "step": 49440 + }, + { + "epoch": 1.84, + "learning_rate": 8.160821214713432e-06, + "loss": 1.7797, + "step": 49450 + }, + { + "epoch": 1.84, + "learning_rate": 8.160449287759886e-06, + "loss": 1.6993, + "step": 49460 + }, + { + "epoch": 1.84, + "learning_rate": 8.160077360806339e-06, + "loss": 1.7552, + "step": 49470 + }, + { + "epoch": 1.84, + "learning_rate": 8.15970543385279e-06, + "loss": 1.912, + "step": 49480 + }, + { + "epoch": 1.84, + "learning_rate": 8.159333506899246e-06, + "loss": 1.8281, + "step": 49490 + }, + { + "epoch": 1.84, + "learning_rate": 8.1589615799457e-06, + "loss": 1.7664, + "step": 49500 + }, + { + "epoch": 1.84, + "eval_loss": 1.7118715047836304, + "eval_runtime": 16.8298, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 49500 + }, + { + "epoch": 1.84, + "learning_rate": 8.158589652992153e-06, + "loss": 1.7279, + "step": 49510 + }, + { + "epoch": 1.84, + "learning_rate": 8.158217726038606e-06, + "loss": 1.6911, + "step": 49520 + }, + { + "epoch": 1.84, + "learning_rate": 8.15784579908506e-06, + "loss": 1.7063, + "step": 49530 + }, + { + "epoch": 1.84, + "learning_rate": 8.157473872131513e-06, + "loss": 1.7575, + "step": 49540 + }, + { + "epoch": 1.84, + "learning_rate": 8.157101945177968e-06, + "loss": 1.8051, + "step": 49550 + }, + { + "epoch": 1.84, + "learning_rate": 8.156730018224422e-06, + "loss": 1.8997, + "step": 49560 + }, + { + "epoch": 1.84, + "learning_rate": 8.156358091270875e-06, + "loss": 1.7294, + "step": 49570 + }, + { + "epoch": 1.84, + "learning_rate": 8.155986164317329e-06, + "loss": 1.7638, + "step": 49580 + }, + { + "epoch": 1.84, + "learning_rate": 8.155614237363782e-06, + "loss": 1.7648, + "step": 49590 + }, + { + "epoch": 1.84, + "learning_rate": 8.155242310410236e-06, + "loss": 1.7538, + "step": 49600 + }, + { + "epoch": 1.84, + "eval_loss": 1.7107561826705933, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 49600 + }, + { + "epoch": 1.85, + "learning_rate": 8.15487038345669e-06, + "loss": 1.6623, + "step": 49610 + }, + { + "epoch": 1.85, + "learning_rate": 8.154498456503144e-06, + "loss": 1.7592, + "step": 49620 + }, + { + "epoch": 1.85, + "learning_rate": 8.154126529549598e-06, + "loss": 1.7016, + "step": 49630 + }, + { + "epoch": 1.85, + "learning_rate": 8.153754602596051e-06, + "loss": 1.784, + "step": 49640 + }, + { + "epoch": 1.85, + "learning_rate": 8.153382675642505e-06, + "loss": 1.7442, + "step": 49650 + }, + { + "epoch": 1.85, + "learning_rate": 8.153010748688958e-06, + "loss": 1.703, + "step": 49660 + }, + { + "epoch": 1.85, + "learning_rate": 8.152638821735412e-06, + "loss": 1.8057, + "step": 49670 + }, + { + "epoch": 1.85, + "learning_rate": 8.152266894781865e-06, + "loss": 1.7242, + "step": 49680 + }, + { + "epoch": 1.85, + "learning_rate": 8.151894967828318e-06, + "loss": 1.7328, + "step": 49690 + }, + { + "epoch": 1.85, + "learning_rate": 8.151523040874772e-06, + "loss": 1.7518, + "step": 49700 + }, + { + "epoch": 1.85, + "eval_loss": 1.7107694149017334, + "eval_runtime": 16.8245, + "eval_samples_per_second": 59.437, + "eval_steps_per_second": 3.745, + "step": 49700 + }, + { + "epoch": 1.85, + "learning_rate": 8.151151113921227e-06, + "loss": 1.804, + "step": 49710 + }, + { + "epoch": 1.85, + "learning_rate": 8.15077918696768e-06, + "loss": 1.9328, + "step": 49720 + }, + { + "epoch": 1.85, + "learning_rate": 8.150407260014134e-06, + "loss": 1.9077, + "step": 49730 + }, + { + "epoch": 1.85, + "learning_rate": 8.150035333060587e-06, + "loss": 1.764, + "step": 49740 + }, + { + "epoch": 1.85, + "learning_rate": 8.149663406107041e-06, + "loss": 1.6962, + "step": 49750 + }, + { + "epoch": 1.85, + "learning_rate": 8.149291479153494e-06, + "loss": 1.8659, + "step": 49760 + }, + { + "epoch": 1.85, + "learning_rate": 8.148919552199948e-06, + "loss": 1.7377, + "step": 49770 + }, + { + "epoch": 1.85, + "learning_rate": 8.148547625246403e-06, + "loss": 1.7572, + "step": 49780 + }, + { + "epoch": 1.85, + "learning_rate": 8.148175698292856e-06, + "loss": 1.8561, + "step": 49790 + }, + { + "epoch": 1.85, + "learning_rate": 8.14780377133931e-06, + "loss": 1.7542, + "step": 49800 + }, + { + "epoch": 1.85, + "eval_loss": 1.7112133502960205, + "eval_runtime": 16.8243, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 49800 + }, + { + "epoch": 1.85, + "learning_rate": 8.147431844385763e-06, + "loss": 1.8331, + "step": 49810 + }, + { + "epoch": 1.85, + "learning_rate": 8.147059917432217e-06, + "loss": 1.8337, + "step": 49820 + }, + { + "epoch": 1.85, + "learning_rate": 8.14668799047867e-06, + "loss": 1.6954, + "step": 49830 + }, + { + "epoch": 1.85, + "learning_rate": 8.146316063525125e-06, + "loss": 1.5631, + "step": 49840 + }, + { + "epoch": 1.85, + "learning_rate": 8.145944136571577e-06, + "loss": 1.7067, + "step": 49850 + }, + { + "epoch": 1.85, + "learning_rate": 8.14557220961803e-06, + "loss": 1.8534, + "step": 49860 + }, + { + "epoch": 1.85, + "learning_rate": 8.145200282664484e-06, + "loss": 1.8277, + "step": 49870 + }, + { + "epoch": 1.86, + "learning_rate": 8.14482835571094e-06, + "loss": 1.8232, + "step": 49880 + }, + { + "epoch": 1.86, + "learning_rate": 8.144456428757393e-06, + "loss": 1.8571, + "step": 49890 + }, + { + "epoch": 1.86, + "learning_rate": 8.144084501803846e-06, + "loss": 1.7157, + "step": 49900 + }, + { + "epoch": 1.86, + "eval_loss": 1.7111989259719849, + "eval_runtime": 16.8231, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 49900 + }, + { + "epoch": 1.86, + "learning_rate": 8.1437125748503e-06, + "loss": 1.7653, + "step": 49910 + }, + { + "epoch": 1.86, + "learning_rate": 8.143340647896753e-06, + "loss": 1.7698, + "step": 49920 + }, + { + "epoch": 1.86, + "learning_rate": 8.142968720943207e-06, + "loss": 1.7186, + "step": 49930 + }, + { + "epoch": 1.86, + "learning_rate": 8.142596793989662e-06, + "loss": 1.7321, + "step": 49940 + }, + { + "epoch": 1.86, + "learning_rate": 8.142224867036115e-06, + "loss": 1.7112, + "step": 49950 + }, + { + "epoch": 1.86, + "learning_rate": 8.141852940082569e-06, + "loss": 1.7772, + "step": 49960 + }, + { + "epoch": 1.86, + "learning_rate": 8.141481013129022e-06, + "loss": 1.9298, + "step": 49970 + }, + { + "epoch": 1.86, + "learning_rate": 8.141109086175476e-06, + "loss": 1.809, + "step": 49980 + }, + { + "epoch": 1.86, + "learning_rate": 8.140737159221929e-06, + "loss": 1.7745, + "step": 49990 + }, + { + "epoch": 1.86, + "learning_rate": 8.140365232268384e-06, + "loss": 1.873, + "step": 50000 + }, + { + "epoch": 1.86, + "eval_loss": 1.711060643196106, + "eval_runtime": 16.8189, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 50000 + }, + { + "epoch": 1.86, + "learning_rate": 8.139993305314838e-06, + "loss": 1.8685, + "step": 50010 + }, + { + "epoch": 1.86, + "learning_rate": 8.139621378361291e-06, + "loss": 1.803, + "step": 50020 + }, + { + "epoch": 1.86, + "learning_rate": 8.139249451407745e-06, + "loss": 1.8051, + "step": 50030 + }, + { + "epoch": 1.86, + "learning_rate": 8.138877524454198e-06, + "loss": 1.7095, + "step": 50040 + }, + { + "epoch": 1.86, + "learning_rate": 8.138505597500651e-06, + "loss": 1.8032, + "step": 50050 + }, + { + "epoch": 1.86, + "learning_rate": 8.138133670547105e-06, + "loss": 1.72, + "step": 50060 + }, + { + "epoch": 1.86, + "learning_rate": 8.137761743593558e-06, + "loss": 1.7239, + "step": 50070 + }, + { + "epoch": 1.86, + "learning_rate": 8.137389816640012e-06, + "loss": 1.7854, + "step": 50080 + }, + { + "epoch": 1.86, + "learning_rate": 8.137017889686465e-06, + "loss": 1.8293, + "step": 50090 + }, + { + "epoch": 1.86, + "learning_rate": 8.13664596273292e-06, + "loss": 1.7111, + "step": 50100 + }, + { + "epoch": 1.86, + "eval_loss": 1.7111413478851318, + "eval_runtime": 16.8109, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 50100 + }, + { + "epoch": 1.86, + "learning_rate": 8.136274035779374e-06, + "loss": 1.6683, + "step": 50110 + }, + { + "epoch": 1.86, + "learning_rate": 8.135902108825827e-06, + "loss": 1.8255, + "step": 50120 + }, + { + "epoch": 1.86, + "learning_rate": 8.135530181872281e-06, + "loss": 1.7788, + "step": 50130 + }, + { + "epoch": 1.86, + "learning_rate": 8.135158254918734e-06, + "loss": 1.7673, + "step": 50140 + }, + { + "epoch": 1.87, + "learning_rate": 8.134786327965188e-06, + "loss": 1.786, + "step": 50150 + }, + { + "epoch": 1.87, + "learning_rate": 8.134414401011643e-06, + "loss": 1.8983, + "step": 50160 + }, + { + "epoch": 1.87, + "learning_rate": 8.134042474058096e-06, + "loss": 1.8602, + "step": 50170 + }, + { + "epoch": 1.87, + "learning_rate": 8.13367054710455e-06, + "loss": 1.7863, + "step": 50180 + }, + { + "epoch": 1.87, + "learning_rate": 8.133298620151003e-06, + "loss": 1.8211, + "step": 50190 + }, + { + "epoch": 1.87, + "learning_rate": 8.132926693197457e-06, + "loss": 1.9177, + "step": 50200 + }, + { + "epoch": 1.87, + "eval_loss": 1.7101033926010132, + "eval_runtime": 16.8223, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 50200 + }, + { + "epoch": 1.87, + "learning_rate": 8.13255476624391e-06, + "loss": 1.8076, + "step": 50210 + }, + { + "epoch": 1.87, + "learning_rate": 8.132182839290365e-06, + "loss": 1.8183, + "step": 50220 + }, + { + "epoch": 1.87, + "learning_rate": 8.131810912336817e-06, + "loss": 1.8693, + "step": 50230 + }, + { + "epoch": 1.87, + "learning_rate": 8.13143898538327e-06, + "loss": 1.8672, + "step": 50240 + }, + { + "epoch": 1.87, + "learning_rate": 8.131067058429724e-06, + "loss": 1.8079, + "step": 50250 + }, + { + "epoch": 1.87, + "learning_rate": 8.13069513147618e-06, + "loss": 1.748, + "step": 50260 + }, + { + "epoch": 1.87, + "learning_rate": 8.130323204522633e-06, + "loss": 1.752, + "step": 50270 + }, + { + "epoch": 1.87, + "learning_rate": 8.129951277569086e-06, + "loss": 1.7653, + "step": 50280 + }, + { + "epoch": 1.87, + "learning_rate": 8.12957935061554e-06, + "loss": 1.8603, + "step": 50290 + }, + { + "epoch": 1.87, + "learning_rate": 8.129207423661993e-06, + "loss": 1.643, + "step": 50300 + }, + { + "epoch": 1.87, + "eval_loss": 1.7106444835662842, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 50300 + }, + { + "epoch": 1.87, + "learning_rate": 8.128835496708447e-06, + "loss": 1.7974, + "step": 50310 + }, + { + "epoch": 1.87, + "learning_rate": 8.1284635697549e-06, + "loss": 1.7683, + "step": 50320 + }, + { + "epoch": 1.87, + "learning_rate": 8.128091642801355e-06, + "loss": 1.8399, + "step": 50330 + }, + { + "epoch": 1.87, + "learning_rate": 8.127719715847809e-06, + "loss": 2.0242, + "step": 50340 + }, + { + "epoch": 1.87, + "learning_rate": 8.127347788894262e-06, + "loss": 1.7292, + "step": 50350 + }, + { + "epoch": 1.87, + "learning_rate": 8.126975861940715e-06, + "loss": 1.8738, + "step": 50360 + }, + { + "epoch": 1.87, + "learning_rate": 8.126603934987169e-06, + "loss": 1.6767, + "step": 50370 + }, + { + "epoch": 1.87, + "learning_rate": 8.126232008033622e-06, + "loss": 1.8435, + "step": 50380 + }, + { + "epoch": 1.87, + "learning_rate": 8.125860081080078e-06, + "loss": 1.7827, + "step": 50390 + }, + { + "epoch": 1.87, + "learning_rate": 8.125488154126531e-06, + "loss": 1.8561, + "step": 50400 + }, + { + "epoch": 1.87, + "eval_loss": 1.7099369764328003, + "eval_runtime": 16.835, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 50400 + }, + { + "epoch": 1.87, + "learning_rate": 8.125116227172984e-06, + "loss": 1.8073, + "step": 50410 + }, + { + "epoch": 1.88, + "learning_rate": 8.124744300219436e-06, + "loss": 1.8242, + "step": 50420 + }, + { + "epoch": 1.88, + "learning_rate": 8.124372373265891e-06, + "loss": 1.8162, + "step": 50430 + }, + { + "epoch": 1.88, + "learning_rate": 8.124000446312345e-06, + "loss": 1.9111, + "step": 50440 + }, + { + "epoch": 1.88, + "learning_rate": 8.123628519358798e-06, + "loss": 1.6422, + "step": 50450 + }, + { + "epoch": 1.88, + "learning_rate": 8.123256592405252e-06, + "loss": 1.7929, + "step": 50460 + }, + { + "epoch": 1.88, + "learning_rate": 8.122884665451705e-06, + "loss": 1.7763, + "step": 50470 + }, + { + "epoch": 1.88, + "learning_rate": 8.122512738498159e-06, + "loss": 1.8976, + "step": 50480 + }, + { + "epoch": 1.88, + "learning_rate": 8.122140811544614e-06, + "loss": 1.8347, + "step": 50490 + }, + { + "epoch": 1.88, + "learning_rate": 8.121768884591067e-06, + "loss": 1.7704, + "step": 50500 + }, + { + "epoch": 1.88, + "eval_loss": 1.7089282274246216, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 50500 + }, + { + "epoch": 1.88, + "learning_rate": 8.12139695763752e-06, + "loss": 1.8188, + "step": 50510 + }, + { + "epoch": 1.88, + "learning_rate": 8.121025030683974e-06, + "loss": 1.8166, + "step": 50520 + }, + { + "epoch": 1.88, + "learning_rate": 8.120653103730428e-06, + "loss": 1.8312, + "step": 50530 + }, + { + "epoch": 1.88, + "learning_rate": 8.120281176776881e-06, + "loss": 1.7529, + "step": 50540 + }, + { + "epoch": 1.88, + "learning_rate": 8.119909249823336e-06, + "loss": 1.7273, + "step": 50550 + }, + { + "epoch": 1.88, + "learning_rate": 8.11953732286979e-06, + "loss": 1.671, + "step": 50560 + }, + { + "epoch": 1.88, + "learning_rate": 8.119165395916243e-06, + "loss": 1.7126, + "step": 50570 + }, + { + "epoch": 1.88, + "learning_rate": 8.118793468962697e-06, + "loss": 1.828, + "step": 50580 + }, + { + "epoch": 1.88, + "learning_rate": 8.11842154200915e-06, + "loss": 1.7021, + "step": 50590 + }, + { + "epoch": 1.88, + "learning_rate": 8.118049615055604e-06, + "loss": 1.7178, + "step": 50600 + }, + { + "epoch": 1.88, + "eval_loss": 1.7106621265411377, + "eval_runtime": 16.8178, + "eval_samples_per_second": 59.461, + "eval_steps_per_second": 3.746, + "step": 50600 + }, + { + "epoch": 1.88, + "learning_rate": 8.117677688102057e-06, + "loss": 1.6903, + "step": 50610 + }, + { + "epoch": 1.88, + "learning_rate": 8.11730576114851e-06, + "loss": 1.7939, + "step": 50620 + }, + { + "epoch": 1.88, + "learning_rate": 8.116933834194964e-06, + "loss": 1.889, + "step": 50630 + }, + { + "epoch": 1.88, + "learning_rate": 8.116561907241417e-06, + "loss": 1.8598, + "step": 50640 + }, + { + "epoch": 1.88, + "learning_rate": 8.116189980287873e-06, + "loss": 1.957, + "step": 50650 + }, + { + "epoch": 1.88, + "learning_rate": 8.115818053334326e-06, + "loss": 1.819, + "step": 50660 + }, + { + "epoch": 1.88, + "learning_rate": 8.11544612638078e-06, + "loss": 1.8363, + "step": 50670 + }, + { + "epoch": 1.88, + "learning_rate": 8.115074199427233e-06, + "loss": 1.6184, + "step": 50680 + }, + { + "epoch": 1.89, + "learning_rate": 8.114702272473686e-06, + "loss": 1.8222, + "step": 50690 + }, + { + "epoch": 1.89, + "learning_rate": 8.11433034552014e-06, + "loss": 1.6695, + "step": 50700 + }, + { + "epoch": 1.89, + "eval_loss": 1.7101964950561523, + "eval_runtime": 16.8326, + "eval_samples_per_second": 59.409, + "eval_steps_per_second": 3.743, + "step": 50700 + }, + { + "epoch": 1.89, + "learning_rate": 8.113958418566595e-06, + "loss": 1.7776, + "step": 50710 + }, + { + "epoch": 1.89, + "learning_rate": 8.113586491613048e-06, + "loss": 1.7865, + "step": 50720 + }, + { + "epoch": 1.89, + "learning_rate": 8.113214564659502e-06, + "loss": 1.7667, + "step": 50730 + }, + { + "epoch": 1.89, + "learning_rate": 8.112842637705955e-06, + "loss": 1.7935, + "step": 50740 + }, + { + "epoch": 1.89, + "learning_rate": 8.112470710752409e-06, + "loss": 1.7341, + "step": 50750 + }, + { + "epoch": 1.89, + "learning_rate": 8.112098783798862e-06, + "loss": 1.6059, + "step": 50760 + }, + { + "epoch": 1.89, + "learning_rate": 8.111726856845317e-06, + "loss": 1.7347, + "step": 50770 + }, + { + "epoch": 1.89, + "learning_rate": 8.111354929891771e-06, + "loss": 1.8363, + "step": 50780 + }, + { + "epoch": 1.89, + "learning_rate": 8.110983002938223e-06, + "loss": 1.7075, + "step": 50790 + }, + { + "epoch": 1.89, + "learning_rate": 8.110611075984676e-06, + "loss": 1.7212, + "step": 50800 + }, + { + "epoch": 1.89, + "eval_loss": 1.710638165473938, + "eval_runtime": 16.8487, + "eval_samples_per_second": 59.352, + "eval_steps_per_second": 3.739, + "step": 50800 + }, + { + "epoch": 1.89, + "learning_rate": 8.110239149031131e-06, + "loss": 1.6998, + "step": 50810 + }, + { + "epoch": 1.89, + "learning_rate": 8.109867222077585e-06, + "loss": 1.7358, + "step": 50820 + }, + { + "epoch": 1.89, + "learning_rate": 8.109495295124038e-06, + "loss": 1.8081, + "step": 50830 + }, + { + "epoch": 1.89, + "learning_rate": 8.109123368170492e-06, + "loss": 1.8087, + "step": 50840 + }, + { + "epoch": 1.89, + "learning_rate": 8.108751441216945e-06, + "loss": 1.7527, + "step": 50850 + }, + { + "epoch": 1.89, + "learning_rate": 8.108379514263399e-06, + "loss": 1.8172, + "step": 50860 + }, + { + "epoch": 1.89, + "learning_rate": 8.108007587309854e-06, + "loss": 1.7738, + "step": 50870 + }, + { + "epoch": 1.89, + "learning_rate": 8.107635660356307e-06, + "loss": 1.8295, + "step": 50880 + }, + { + "epoch": 1.89, + "learning_rate": 8.10726373340276e-06, + "loss": 1.8405, + "step": 50890 + }, + { + "epoch": 1.89, + "learning_rate": 8.106891806449214e-06, + "loss": 1.9084, + "step": 50900 + }, + { + "epoch": 1.89, + "eval_loss": 1.7103240489959717, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.437, + "eval_steps_per_second": 3.745, + "step": 50900 + }, + { + "epoch": 1.89, + "learning_rate": 8.106519879495668e-06, + "loss": 1.8531, + "step": 50910 + }, + { + "epoch": 1.89, + "learning_rate": 8.106147952542121e-06, + "loss": 1.7343, + "step": 50920 + }, + { + "epoch": 1.89, + "learning_rate": 8.105776025588575e-06, + "loss": 1.7229, + "step": 50930 + }, + { + "epoch": 1.89, + "learning_rate": 8.10540409863503e-06, + "loss": 1.7598, + "step": 50940 + }, + { + "epoch": 1.89, + "learning_rate": 8.105032171681483e-06, + "loss": 1.7885, + "step": 50950 + }, + { + "epoch": 1.9, + "learning_rate": 8.104660244727937e-06, + "loss": 1.9025, + "step": 50960 + }, + { + "epoch": 1.9, + "learning_rate": 8.10428831777439e-06, + "loss": 1.6825, + "step": 50970 + }, + { + "epoch": 1.9, + "learning_rate": 8.103916390820844e-06, + "loss": 1.8576, + "step": 50980 + }, + { + "epoch": 1.9, + "learning_rate": 8.103544463867297e-06, + "loss": 1.8328, + "step": 50990 + }, + { + "epoch": 1.9, + "learning_rate": 8.10317253691375e-06, + "loss": 1.7613, + "step": 51000 + }, + { + "epoch": 1.9, + "eval_loss": 1.7096501588821411, + "eval_runtime": 16.8336, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 51000 + }, + { + "epoch": 1.9, + "learning_rate": 8.102800609960204e-06, + "loss": 1.7477, + "step": 51010 + }, + { + "epoch": 1.9, + "learning_rate": 8.102428683006657e-06, + "loss": 1.8014, + "step": 51020 + }, + { + "epoch": 1.9, + "learning_rate": 8.10205675605311e-06, + "loss": 1.7325, + "step": 51030 + }, + { + "epoch": 1.9, + "learning_rate": 8.101684829099566e-06, + "loss": 1.7948, + "step": 51040 + }, + { + "epoch": 1.9, + "learning_rate": 8.10131290214602e-06, + "loss": 1.8002, + "step": 51050 + }, + { + "epoch": 1.9, + "learning_rate": 8.100940975192473e-06, + "loss": 1.7584, + "step": 51060 + }, + { + "epoch": 1.9, + "learning_rate": 8.100569048238926e-06, + "loss": 1.8711, + "step": 51070 + }, + { + "epoch": 1.9, + "learning_rate": 8.10019712128538e-06, + "loss": 1.7959, + "step": 51080 + }, + { + "epoch": 1.9, + "learning_rate": 8.099825194331833e-06, + "loss": 1.7582, + "step": 51090 + }, + { + "epoch": 1.9, + "learning_rate": 8.099453267378288e-06, + "loss": 1.687, + "step": 51100 + }, + { + "epoch": 1.9, + "eval_loss": 1.7094581127166748, + "eval_runtime": 16.8331, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 51100 + }, + { + "epoch": 1.9, + "learning_rate": 8.099081340424742e-06, + "loss": 1.7429, + "step": 51110 + }, + { + "epoch": 1.9, + "learning_rate": 8.098709413471195e-06, + "loss": 1.7843, + "step": 51120 + }, + { + "epoch": 1.9, + "learning_rate": 8.098337486517649e-06, + "loss": 1.7447, + "step": 51130 + }, + { + "epoch": 1.9, + "learning_rate": 8.097965559564102e-06, + "loss": 1.7321, + "step": 51140 + }, + { + "epoch": 1.9, + "learning_rate": 8.097593632610556e-06, + "loss": 1.8297, + "step": 51150 + }, + { + "epoch": 1.9, + "learning_rate": 8.097221705657011e-06, + "loss": 1.8071, + "step": 51160 + }, + { + "epoch": 1.9, + "learning_rate": 8.096849778703463e-06, + "loss": 1.7625, + "step": 51170 + }, + { + "epoch": 1.9, + "learning_rate": 8.096477851749916e-06, + "loss": 1.7253, + "step": 51180 + }, + { + "epoch": 1.9, + "learning_rate": 8.09610592479637e-06, + "loss": 1.783, + "step": 51190 + }, + { + "epoch": 1.9, + "learning_rate": 8.095733997842825e-06, + "loss": 1.9009, + "step": 51200 + }, + { + "epoch": 1.9, + "eval_loss": 1.709505558013916, + "eval_runtime": 16.8358, + "eval_samples_per_second": 59.397, + "eval_steps_per_second": 3.742, + "step": 51200 + }, + { + "epoch": 1.9, + "learning_rate": 8.095362070889278e-06, + "loss": 1.8148, + "step": 51210 + }, + { + "epoch": 1.91, + "learning_rate": 8.094990143935732e-06, + "loss": 1.7612, + "step": 51220 + }, + { + "epoch": 1.91, + "learning_rate": 8.094618216982185e-06, + "loss": 1.8874, + "step": 51230 + }, + { + "epoch": 1.91, + "learning_rate": 8.094246290028639e-06, + "loss": 1.7794, + "step": 51240 + }, + { + "epoch": 1.91, + "learning_rate": 8.093874363075092e-06, + "loss": 1.8214, + "step": 51250 + }, + { + "epoch": 1.91, + "learning_rate": 8.093502436121547e-06, + "loss": 1.6619, + "step": 51260 + }, + { + "epoch": 1.91, + "learning_rate": 8.093130509168e-06, + "loss": 1.8295, + "step": 51270 + }, + { + "epoch": 1.91, + "learning_rate": 8.092758582214454e-06, + "loss": 1.7755, + "step": 51280 + }, + { + "epoch": 1.91, + "learning_rate": 8.092386655260908e-06, + "loss": 1.7361, + "step": 51290 + }, + { + "epoch": 1.91, + "learning_rate": 8.092014728307361e-06, + "loss": 1.7572, + "step": 51300 + }, + { + "epoch": 1.91, + "eval_loss": 1.7096024751663208, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 51300 + }, + { + "epoch": 1.91, + "learning_rate": 8.091642801353814e-06, + "loss": 1.8516, + "step": 51310 + }, + { + "epoch": 1.91, + "learning_rate": 8.09127087440027e-06, + "loss": 1.7682, + "step": 51320 + }, + { + "epoch": 1.91, + "learning_rate": 8.090898947446723e-06, + "loss": 1.8964, + "step": 51330 + }, + { + "epoch": 1.91, + "learning_rate": 8.090527020493177e-06, + "loss": 1.7499, + "step": 51340 + }, + { + "epoch": 1.91, + "learning_rate": 8.09015509353963e-06, + "loss": 1.8479, + "step": 51350 + }, + { + "epoch": 1.91, + "learning_rate": 8.089783166586083e-06, + "loss": 1.7542, + "step": 51360 + }, + { + "epoch": 1.91, + "learning_rate": 8.089411239632537e-06, + "loss": 1.6953, + "step": 51370 + }, + { + "epoch": 1.91, + "learning_rate": 8.08903931267899e-06, + "loss": 1.6755, + "step": 51380 + }, + { + "epoch": 1.91, + "learning_rate": 8.088667385725444e-06, + "loss": 1.7095, + "step": 51390 + }, + { + "epoch": 1.91, + "learning_rate": 8.088295458771897e-06, + "loss": 1.7427, + "step": 51400 + }, + { + "epoch": 1.91, + "eval_loss": 1.7090519666671753, + "eval_runtime": 16.8305, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 51400 + }, + { + "epoch": 1.91, + "learning_rate": 8.08792353181835e-06, + "loss": 1.9716, + "step": 51410 + }, + { + "epoch": 1.91, + "learning_rate": 8.087551604864806e-06, + "loss": 1.8068, + "step": 51420 + }, + { + "epoch": 1.91, + "learning_rate": 8.08717967791126e-06, + "loss": 1.712, + "step": 51430 + }, + { + "epoch": 1.91, + "learning_rate": 8.086807750957713e-06, + "loss": 1.6306, + "step": 51440 + }, + { + "epoch": 1.91, + "learning_rate": 8.086435824004166e-06, + "loss": 1.7553, + "step": 51450 + }, + { + "epoch": 1.91, + "learning_rate": 8.08606389705062e-06, + "loss": 1.7925, + "step": 51460 + }, + { + "epoch": 1.91, + "learning_rate": 8.085691970097073e-06, + "loss": 1.6805, + "step": 51470 + }, + { + "epoch": 1.91, + "learning_rate": 8.085320043143527e-06, + "loss": 1.7939, + "step": 51480 + }, + { + "epoch": 1.92, + "learning_rate": 8.084948116189982e-06, + "loss": 1.7315, + "step": 51490 + }, + { + "epoch": 1.92, + "learning_rate": 8.084576189236435e-06, + "loss": 1.7511, + "step": 51500 + }, + { + "epoch": 1.92, + "eval_loss": 1.7092134952545166, + "eval_runtime": 16.8383, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 51500 + }, + { + "epoch": 1.92, + "learning_rate": 8.084204262282889e-06, + "loss": 2.0685, + "step": 51510 + }, + { + "epoch": 1.92, + "learning_rate": 8.083832335329342e-06, + "loss": 1.7199, + "step": 51520 + }, + { + "epoch": 1.92, + "learning_rate": 8.083460408375796e-06, + "loss": 1.8041, + "step": 51530 + }, + { + "epoch": 1.92, + "learning_rate": 8.083088481422249e-06, + "loss": 1.8329, + "step": 51540 + }, + { + "epoch": 1.92, + "learning_rate": 8.082716554468703e-06, + "loss": 1.8959, + "step": 51550 + }, + { + "epoch": 1.92, + "learning_rate": 8.082344627515156e-06, + "loss": 1.721, + "step": 51560 + }, + { + "epoch": 1.92, + "learning_rate": 8.08197270056161e-06, + "loss": 1.7251, + "step": 51570 + }, + { + "epoch": 1.92, + "learning_rate": 8.081600773608063e-06, + "loss": 1.816, + "step": 51580 + }, + { + "epoch": 1.92, + "learning_rate": 8.081228846654518e-06, + "loss": 1.8475, + "step": 51590 + }, + { + "epoch": 1.92, + "learning_rate": 8.080856919700972e-06, + "loss": 1.9446, + "step": 51600 + }, + { + "epoch": 1.92, + "eval_loss": 1.7086989879608154, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 51600 + }, + { + "epoch": 1.92, + "learning_rate": 8.080484992747425e-06, + "loss": 1.9238, + "step": 51610 + }, + { + "epoch": 1.92, + "learning_rate": 8.080113065793878e-06, + "loss": 1.8806, + "step": 51620 + }, + { + "epoch": 1.92, + "learning_rate": 8.079741138840332e-06, + "loss": 1.7922, + "step": 51630 + }, + { + "epoch": 1.92, + "learning_rate": 8.079369211886785e-06, + "loss": 1.7022, + "step": 51640 + }, + { + "epoch": 1.92, + "learning_rate": 8.07899728493324e-06, + "loss": 1.7171, + "step": 51650 + }, + { + "epoch": 1.92, + "learning_rate": 8.078625357979694e-06, + "loss": 1.6937, + "step": 51660 + }, + { + "epoch": 1.92, + "learning_rate": 8.078253431026147e-06, + "loss": 1.6737, + "step": 51670 + }, + { + "epoch": 1.92, + "learning_rate": 8.077881504072601e-06, + "loss": 1.8288, + "step": 51680 + }, + { + "epoch": 1.92, + "learning_rate": 8.077509577119054e-06, + "loss": 1.8347, + "step": 51690 + }, + { + "epoch": 1.92, + "learning_rate": 8.077137650165508e-06, + "loss": 1.7957, + "step": 51700 + }, + { + "epoch": 1.92, + "eval_loss": 1.7083338499069214, + "eval_runtime": 16.823, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 51700 + }, + { + "epoch": 1.92, + "learning_rate": 8.076765723211963e-06, + "loss": 1.7361, + "step": 51710 + }, + { + "epoch": 1.92, + "learning_rate": 8.076393796258416e-06, + "loss": 1.6666, + "step": 51720 + }, + { + "epoch": 1.92, + "learning_rate": 8.076021869304868e-06, + "loss": 1.7556, + "step": 51730 + }, + { + "epoch": 1.92, + "learning_rate": 8.075649942351322e-06, + "loss": 1.6817, + "step": 51740 + }, + { + "epoch": 1.92, + "learning_rate": 8.075278015397777e-06, + "loss": 1.7985, + "step": 51750 + }, + { + "epoch": 1.93, + "learning_rate": 8.07490608844423e-06, + "loss": 1.8488, + "step": 51760 + }, + { + "epoch": 1.93, + "learning_rate": 8.074534161490684e-06, + "loss": 1.962, + "step": 51770 + }, + { + "epoch": 1.93, + "learning_rate": 8.074162234537137e-06, + "loss": 1.7921, + "step": 51780 + }, + { + "epoch": 1.93, + "learning_rate": 8.07379030758359e-06, + "loss": 1.7765, + "step": 51790 + }, + { + "epoch": 1.93, + "learning_rate": 8.073418380630044e-06, + "loss": 1.717, + "step": 51800 + }, + { + "epoch": 1.93, + "eval_loss": 1.7084228992462158, + "eval_runtime": 16.8402, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 51800 + }, + { + "epoch": 1.93, + "learning_rate": 8.0730464536765e-06, + "loss": 1.7388, + "step": 51810 + }, + { + "epoch": 1.93, + "learning_rate": 8.072674526722953e-06, + "loss": 2.0376, + "step": 51820 + }, + { + "epoch": 1.93, + "learning_rate": 8.072302599769406e-06, + "loss": 1.8692, + "step": 51830 + }, + { + "epoch": 1.93, + "learning_rate": 8.07193067281586e-06, + "loss": 1.8993, + "step": 51840 + }, + { + "epoch": 1.93, + "learning_rate": 8.071558745862313e-06, + "loss": 1.7615, + "step": 51850 + }, + { + "epoch": 1.93, + "learning_rate": 8.071186818908767e-06, + "loss": 1.8293, + "step": 51860 + }, + { + "epoch": 1.93, + "learning_rate": 8.070814891955222e-06, + "loss": 1.805, + "step": 51870 + }, + { + "epoch": 1.93, + "learning_rate": 8.070442965001675e-06, + "loss": 1.7748, + "step": 51880 + }, + { + "epoch": 1.93, + "learning_rate": 8.070071038048129e-06, + "loss": 1.8218, + "step": 51890 + }, + { + "epoch": 1.93, + "learning_rate": 8.069699111094582e-06, + "loss": 1.7024, + "step": 51900 + }, + { + "epoch": 1.93, + "eval_loss": 1.7087172269821167, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 51900 + }, + { + "epoch": 1.93, + "learning_rate": 8.069327184141036e-06, + "loss": 1.8552, + "step": 51910 + }, + { + "epoch": 1.93, + "learning_rate": 8.068955257187489e-06, + "loss": 1.7209, + "step": 51920 + }, + { + "epoch": 1.93, + "learning_rate": 8.068583330233942e-06, + "loss": 1.8357, + "step": 51930 + }, + { + "epoch": 1.93, + "learning_rate": 8.068211403280396e-06, + "loss": 1.7134, + "step": 51940 + }, + { + "epoch": 1.93, + "learning_rate": 8.06783947632685e-06, + "loss": 1.6543, + "step": 51950 + }, + { + "epoch": 1.93, + "learning_rate": 8.067467549373303e-06, + "loss": 1.6406, + "step": 51960 + }, + { + "epoch": 1.93, + "learning_rate": 8.067095622419758e-06, + "loss": 1.7042, + "step": 51970 + }, + { + "epoch": 1.93, + "learning_rate": 8.066723695466211e-06, + "loss": 1.8283, + "step": 51980 + }, + { + "epoch": 1.93, + "learning_rate": 8.066351768512665e-06, + "loss": 1.6384, + "step": 51990 + }, + { + "epoch": 1.93, + "learning_rate": 8.065979841559118e-06, + "loss": 1.9438, + "step": 52000 + }, + { + "epoch": 1.93, + "eval_loss": 1.7082403898239136, + "eval_runtime": 16.8143, + "eval_samples_per_second": 59.473, + "eval_steps_per_second": 3.747, + "step": 52000 + }, + { + "epoch": 1.93, + "learning_rate": 8.065607914605572e-06, + "loss": 1.7459, + "step": 52010 + }, + { + "epoch": 1.93, + "learning_rate": 8.065235987652025e-06, + "loss": 1.7923, + "step": 52020 + }, + { + "epoch": 1.94, + "learning_rate": 8.06486406069848e-06, + "loss": 1.8269, + "step": 52030 + }, + { + "epoch": 1.94, + "learning_rate": 8.064492133744934e-06, + "loss": 1.8585, + "step": 52040 + }, + { + "epoch": 1.94, + "learning_rate": 8.064120206791387e-06, + "loss": 1.7207, + "step": 52050 + }, + { + "epoch": 1.94, + "learning_rate": 8.06374827983784e-06, + "loss": 1.7608, + "step": 52060 + }, + { + "epoch": 1.94, + "learning_rate": 8.063376352884294e-06, + "loss": 1.8446, + "step": 52070 + }, + { + "epoch": 1.94, + "learning_rate": 8.063004425930748e-06, + "loss": 1.7995, + "step": 52080 + }, + { + "epoch": 1.94, + "learning_rate": 8.062632498977201e-06, + "loss": 1.7977, + "step": 52090 + }, + { + "epoch": 1.94, + "learning_rate": 8.062260572023656e-06, + "loss": 1.6865, + "step": 52100 + }, + { + "epoch": 1.94, + "eval_loss": 1.7089396715164185, + "eval_runtime": 16.8161, + "eval_samples_per_second": 59.467, + "eval_steps_per_second": 3.746, + "step": 52100 + }, + { + "epoch": 1.94, + "learning_rate": 8.061888645070108e-06, + "loss": 1.9005, + "step": 52110 + }, + { + "epoch": 1.94, + "learning_rate": 8.061516718116562e-06, + "loss": 1.9474, + "step": 52120 + }, + { + "epoch": 1.94, + "learning_rate": 8.061144791163015e-06, + "loss": 1.82, + "step": 52130 + }, + { + "epoch": 1.94, + "learning_rate": 8.06077286420947e-06, + "loss": 1.6607, + "step": 52140 + }, + { + "epoch": 1.94, + "learning_rate": 8.060400937255924e-06, + "loss": 1.9892, + "step": 52150 + }, + { + "epoch": 1.94, + "learning_rate": 8.060029010302377e-06, + "loss": 1.8436, + "step": 52160 + }, + { + "epoch": 1.94, + "learning_rate": 8.05965708334883e-06, + "loss": 1.6683, + "step": 52170 + }, + { + "epoch": 1.94, + "learning_rate": 8.059285156395284e-06, + "loss": 1.7162, + "step": 52180 + }, + { + "epoch": 1.94, + "learning_rate": 8.058913229441737e-06, + "loss": 1.7935, + "step": 52190 + }, + { + "epoch": 1.94, + "learning_rate": 8.058541302488193e-06, + "loss": 1.7481, + "step": 52200 + }, + { + "epoch": 1.94, + "eval_loss": 1.7078992128372192, + "eval_runtime": 16.8205, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 52200 + }, + { + "epoch": 1.94, + "learning_rate": 8.058169375534646e-06, + "loss": 1.7673, + "step": 52210 + }, + { + "epoch": 1.94, + "learning_rate": 8.0577974485811e-06, + "loss": 1.7909, + "step": 52220 + }, + { + "epoch": 1.94, + "learning_rate": 8.057425521627553e-06, + "loss": 1.8068, + "step": 52230 + }, + { + "epoch": 1.94, + "learning_rate": 8.057053594674006e-06, + "loss": 1.7521, + "step": 52240 + }, + { + "epoch": 1.94, + "learning_rate": 8.05668166772046e-06, + "loss": 1.7796, + "step": 52250 + }, + { + "epoch": 1.94, + "learning_rate": 8.056309740766915e-06, + "loss": 1.9083, + "step": 52260 + }, + { + "epoch": 1.94, + "learning_rate": 8.055937813813369e-06, + "loss": 1.7753, + "step": 52270 + }, + { + "epoch": 1.94, + "learning_rate": 8.055565886859822e-06, + "loss": 1.6205, + "step": 52280 + }, + { + "epoch": 1.94, + "learning_rate": 8.055193959906275e-06, + "loss": 1.7602, + "step": 52290 + }, + { + "epoch": 1.95, + "learning_rate": 8.054822032952729e-06, + "loss": 1.8489, + "step": 52300 + }, + { + "epoch": 1.95, + "eval_loss": 1.7074986696243286, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 52300 + }, + { + "epoch": 1.95, + "learning_rate": 8.054450105999182e-06, + "loss": 1.7245, + "step": 52310 + }, + { + "epoch": 1.95, + "learning_rate": 8.054078179045636e-06, + "loss": 1.7746, + "step": 52320 + }, + { + "epoch": 1.95, + "learning_rate": 8.05370625209209e-06, + "loss": 1.8569, + "step": 52330 + }, + { + "epoch": 1.95, + "learning_rate": 8.053334325138543e-06, + "loss": 1.7595, + "step": 52340 + }, + { + "epoch": 1.95, + "learning_rate": 8.052962398184996e-06, + "loss": 1.9159, + "step": 52350 + }, + { + "epoch": 1.95, + "learning_rate": 8.052590471231451e-06, + "loss": 1.7361, + "step": 52360 + }, + { + "epoch": 1.95, + "learning_rate": 8.052218544277905e-06, + "loss": 1.761, + "step": 52370 + }, + { + "epoch": 1.95, + "learning_rate": 8.051846617324358e-06, + "loss": 1.9885, + "step": 52380 + }, + { + "epoch": 1.95, + "learning_rate": 8.051474690370812e-06, + "loss": 1.7589, + "step": 52390 + }, + { + "epoch": 1.95, + "learning_rate": 8.051102763417265e-06, + "loss": 1.6754, + "step": 52400 + }, + { + "epoch": 1.95, + "eval_loss": 1.7078135013580322, + "eval_runtime": 16.8264, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 52400 + }, + { + "epoch": 1.95, + "learning_rate": 8.050730836463719e-06, + "loss": 1.7076, + "step": 52410 + }, + { + "epoch": 1.95, + "learning_rate": 8.050358909510174e-06, + "loss": 1.7472, + "step": 52420 + }, + { + "epoch": 1.95, + "learning_rate": 8.049986982556627e-06, + "loss": 1.6707, + "step": 52430 + }, + { + "epoch": 1.95, + "learning_rate": 8.04961505560308e-06, + "loss": 1.8557, + "step": 52440 + }, + { + "epoch": 1.95, + "learning_rate": 8.049243128649534e-06, + "loss": 1.8517, + "step": 52450 + }, + { + "epoch": 1.95, + "learning_rate": 8.048871201695988e-06, + "loss": 1.7583, + "step": 52460 + }, + { + "epoch": 1.95, + "learning_rate": 8.048499274742441e-06, + "loss": 1.7979, + "step": 52470 + }, + { + "epoch": 1.95, + "learning_rate": 8.048127347788895e-06, + "loss": 1.7277, + "step": 52480 + }, + { + "epoch": 1.95, + "learning_rate": 8.047755420835348e-06, + "loss": 1.6853, + "step": 52490 + }, + { + "epoch": 1.95, + "learning_rate": 8.047383493881801e-06, + "loss": 1.832, + "step": 52500 + }, + { + "epoch": 1.95, + "eval_loss": 1.7076877355575562, + "eval_runtime": 16.8091, + "eval_samples_per_second": 59.492, + "eval_steps_per_second": 3.748, + "step": 52500 + }, + { + "epoch": 1.95, + "learning_rate": 8.047011566928255e-06, + "loss": 1.6476, + "step": 52510 + }, + { + "epoch": 1.95, + "learning_rate": 8.04663963997471e-06, + "loss": 1.7758, + "step": 52520 + }, + { + "epoch": 1.95, + "learning_rate": 8.046267713021164e-06, + "loss": 1.6158, + "step": 52530 + }, + { + "epoch": 1.95, + "learning_rate": 8.045895786067617e-06, + "loss": 1.743, + "step": 52540 + }, + { + "epoch": 1.95, + "learning_rate": 8.04552385911407e-06, + "loss": 1.6885, + "step": 52550 + }, + { + "epoch": 1.95, + "learning_rate": 8.045151932160524e-06, + "loss": 1.7405, + "step": 52560 + }, + { + "epoch": 1.96, + "learning_rate": 8.044780005206977e-06, + "loss": 1.8775, + "step": 52570 + }, + { + "epoch": 1.96, + "learning_rate": 8.044408078253433e-06, + "loss": 1.8144, + "step": 52580 + }, + { + "epoch": 1.96, + "learning_rate": 8.044036151299886e-06, + "loss": 1.8317, + "step": 52590 + }, + { + "epoch": 1.96, + "learning_rate": 8.04366422434634e-06, + "loss": 1.8122, + "step": 52600 + }, + { + "epoch": 1.96, + "eval_loss": 1.706859827041626, + "eval_runtime": 16.8122, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 52600 + }, + { + "epoch": 1.96, + "learning_rate": 8.043292297392793e-06, + "loss": 1.6849, + "step": 52610 + }, + { + "epoch": 1.96, + "learning_rate": 8.042920370439246e-06, + "loss": 1.789, + "step": 52620 + }, + { + "epoch": 1.96, + "learning_rate": 8.0425484434857e-06, + "loss": 1.9121, + "step": 52630 + }, + { + "epoch": 1.96, + "learning_rate": 8.042176516532153e-06, + "loss": 1.7905, + "step": 52640 + }, + { + "epoch": 1.96, + "learning_rate": 8.041804589578608e-06, + "loss": 1.79, + "step": 52650 + }, + { + "epoch": 1.96, + "learning_rate": 8.041432662625062e-06, + "loss": 1.8886, + "step": 52660 + }, + { + "epoch": 1.96, + "learning_rate": 8.041060735671514e-06, + "loss": 1.7188, + "step": 52670 + }, + { + "epoch": 1.96, + "learning_rate": 8.040688808717967e-06, + "loss": 1.9026, + "step": 52680 + }, + { + "epoch": 1.96, + "learning_rate": 8.040316881764422e-06, + "loss": 1.875, + "step": 52690 + }, + { + "epoch": 1.96, + "learning_rate": 8.039944954810876e-06, + "loss": 1.8508, + "step": 52700 + }, + { + "epoch": 1.96, + "eval_loss": 1.7072104215621948, + "eval_runtime": 16.8134, + "eval_samples_per_second": 59.476, + "eval_steps_per_second": 3.747, + "step": 52700 + }, + { + "epoch": 1.96, + "learning_rate": 8.03957302785733e-06, + "loss": 1.6355, + "step": 52710 + }, + { + "epoch": 1.96, + "learning_rate": 8.039201100903783e-06, + "loss": 1.7642, + "step": 52720 + }, + { + "epoch": 1.96, + "learning_rate": 8.038829173950236e-06, + "loss": 1.7317, + "step": 52730 + }, + { + "epoch": 1.96, + "learning_rate": 8.03845724699669e-06, + "loss": 1.8159, + "step": 52740 + }, + { + "epoch": 1.96, + "learning_rate": 8.038085320043145e-06, + "loss": 1.7887, + "step": 52750 + }, + { + "epoch": 1.96, + "learning_rate": 8.037713393089598e-06, + "loss": 1.8426, + "step": 52760 + }, + { + "epoch": 1.96, + "learning_rate": 8.037341466136052e-06, + "loss": 1.7125, + "step": 52770 + }, + { + "epoch": 1.96, + "learning_rate": 8.036969539182505e-06, + "loss": 1.758, + "step": 52780 + }, + { + "epoch": 1.96, + "learning_rate": 8.036597612228959e-06, + "loss": 1.8073, + "step": 52790 + }, + { + "epoch": 1.96, + "learning_rate": 8.036225685275412e-06, + "loss": 1.7086, + "step": 52800 + }, + { + "epoch": 1.96, + "eval_loss": 1.7071949243545532, + "eval_runtime": 16.8189, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 52800 + }, + { + "epoch": 1.96, + "learning_rate": 8.035853758321867e-06, + "loss": 1.7973, + "step": 52810 + }, + { + "epoch": 1.96, + "learning_rate": 8.03548183136832e-06, + "loss": 1.7023, + "step": 52820 + }, + { + "epoch": 1.96, + "learning_rate": 8.035109904414774e-06, + "loss": 1.9576, + "step": 52830 + }, + { + "epoch": 1.97, + "learning_rate": 8.034737977461228e-06, + "loss": 1.7257, + "step": 52840 + }, + { + "epoch": 1.97, + "learning_rate": 8.034366050507681e-06, + "loss": 1.6753, + "step": 52850 + }, + { + "epoch": 1.97, + "learning_rate": 8.033994123554134e-06, + "loss": 1.8963, + "step": 52860 + }, + { + "epoch": 1.97, + "learning_rate": 8.033622196600588e-06, + "loss": 1.8001, + "step": 52870 + }, + { + "epoch": 1.97, + "learning_rate": 8.033250269647041e-06, + "loss": 1.7726, + "step": 52880 + }, + { + "epoch": 1.97, + "learning_rate": 8.032878342693495e-06, + "loss": 1.7513, + "step": 52890 + }, + { + "epoch": 1.97, + "learning_rate": 8.032506415739948e-06, + "loss": 1.8545, + "step": 52900 + }, + { + "epoch": 1.97, + "eval_loss": 1.7057515382766724, + "eval_runtime": 16.8206, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 52900 + }, + { + "epoch": 1.97, + "learning_rate": 8.032134488786403e-06, + "loss": 1.7657, + "step": 52910 + }, + { + "epoch": 1.97, + "learning_rate": 8.031762561832857e-06, + "loss": 1.6659, + "step": 52920 + }, + { + "epoch": 1.97, + "learning_rate": 8.03139063487931e-06, + "loss": 1.8779, + "step": 52930 + }, + { + "epoch": 1.97, + "learning_rate": 8.031018707925764e-06, + "loss": 1.8979, + "step": 52940 + }, + { + "epoch": 1.97, + "learning_rate": 8.030646780972217e-06, + "loss": 1.7138, + "step": 52950 + }, + { + "epoch": 1.97, + "learning_rate": 8.03027485401867e-06, + "loss": 1.7006, + "step": 52960 + }, + { + "epoch": 1.97, + "learning_rate": 8.029902927065126e-06, + "loss": 1.7312, + "step": 52970 + }, + { + "epoch": 1.97, + "learning_rate": 8.02953100011158e-06, + "loss": 1.7251, + "step": 52980 + }, + { + "epoch": 1.97, + "learning_rate": 8.029159073158033e-06, + "loss": 1.8959, + "step": 52990 + }, + { + "epoch": 1.97, + "learning_rate": 8.028787146204486e-06, + "loss": 1.6649, + "step": 53000 + }, + { + "epoch": 1.97, + "eval_loss": 1.7068825960159302, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 53000 + }, + { + "epoch": 1.97, + "learning_rate": 8.02841521925094e-06, + "loss": 1.7599, + "step": 53010 + }, + { + "epoch": 1.97, + "learning_rate": 8.028043292297393e-06, + "loss": 1.8383, + "step": 53020 + }, + { + "epoch": 1.97, + "learning_rate": 8.027671365343848e-06, + "loss": 1.8155, + "step": 53030 + }, + { + "epoch": 1.97, + "learning_rate": 8.027299438390302e-06, + "loss": 1.9097, + "step": 53040 + }, + { + "epoch": 1.97, + "learning_rate": 8.026927511436754e-06, + "loss": 1.7549, + "step": 53050 + }, + { + "epoch": 1.97, + "learning_rate": 8.026555584483207e-06, + "loss": 1.6656, + "step": 53060 + }, + { + "epoch": 1.97, + "learning_rate": 8.026183657529662e-06, + "loss": 1.8829, + "step": 53070 + }, + { + "epoch": 1.97, + "learning_rate": 8.025811730576116e-06, + "loss": 1.7725, + "step": 53080 + }, + { + "epoch": 1.97, + "learning_rate": 8.025439803622569e-06, + "loss": 1.7912, + "step": 53090 + }, + { + "epoch": 1.97, + "learning_rate": 8.025067876669023e-06, + "loss": 1.7845, + "step": 53100 + }, + { + "epoch": 1.97, + "eval_loss": 1.706842064857483, + "eval_runtime": 16.832, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 53100 + }, + { + "epoch": 1.98, + "learning_rate": 8.024695949715476e-06, + "loss": 1.7766, + "step": 53110 + }, + { + "epoch": 1.98, + "learning_rate": 8.02432402276193e-06, + "loss": 1.6177, + "step": 53120 + }, + { + "epoch": 1.98, + "learning_rate": 8.023952095808385e-06, + "loss": 1.8018, + "step": 53130 + }, + { + "epoch": 1.98, + "learning_rate": 8.023580168854838e-06, + "loss": 1.8543, + "step": 53140 + }, + { + "epoch": 1.98, + "learning_rate": 8.023208241901292e-06, + "loss": 1.7046, + "step": 53150 + }, + { + "epoch": 1.98, + "learning_rate": 8.022836314947745e-06, + "loss": 1.6814, + "step": 53160 + }, + { + "epoch": 1.98, + "learning_rate": 8.022464387994199e-06, + "loss": 1.6814, + "step": 53170 + }, + { + "epoch": 1.98, + "learning_rate": 8.022092461040652e-06, + "loss": 1.7973, + "step": 53180 + }, + { + "epoch": 1.98, + "learning_rate": 8.021720534087105e-06, + "loss": 1.7716, + "step": 53190 + }, + { + "epoch": 1.98, + "learning_rate": 8.02134860713356e-06, + "loss": 1.7602, + "step": 53200 + }, + { + "epoch": 1.98, + "eval_loss": 1.7065280675888062, + "eval_runtime": 16.8301, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 53200 + }, + { + "epoch": 1.98, + "learning_rate": 8.020976680180014e-06, + "loss": 1.7343, + "step": 53210 + }, + { + "epoch": 1.98, + "learning_rate": 8.020604753226467e-06, + "loss": 1.7981, + "step": 53220 + }, + { + "epoch": 1.98, + "learning_rate": 8.02023282627292e-06, + "loss": 1.7267, + "step": 53230 + }, + { + "epoch": 1.98, + "learning_rate": 8.019860899319374e-06, + "loss": 1.752, + "step": 53240 + }, + { + "epoch": 1.98, + "learning_rate": 8.019488972365828e-06, + "loss": 1.6383, + "step": 53250 + }, + { + "epoch": 1.98, + "learning_rate": 8.019117045412281e-06, + "loss": 1.7994, + "step": 53260 + }, + { + "epoch": 1.98, + "learning_rate": 8.018745118458735e-06, + "loss": 1.7244, + "step": 53270 + }, + { + "epoch": 1.98, + "learning_rate": 8.018373191505188e-06, + "loss": 1.8705, + "step": 53280 + }, + { + "epoch": 1.98, + "learning_rate": 8.018001264551642e-06, + "loss": 1.7655, + "step": 53290 + }, + { + "epoch": 1.98, + "learning_rate": 8.017629337598097e-06, + "loss": 2.0212, + "step": 53300 + }, + { + "epoch": 1.98, + "eval_loss": 1.7063637971878052, + "eval_runtime": 16.8278, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 53300 + }, + { + "epoch": 1.98, + "learning_rate": 8.01725741064455e-06, + "loss": 1.852, + "step": 53310 + }, + { + "epoch": 1.98, + "learning_rate": 8.016885483691004e-06, + "loss": 1.6382, + "step": 53320 + }, + { + "epoch": 1.98, + "learning_rate": 8.016513556737457e-06, + "loss": 1.7069, + "step": 53330 + }, + { + "epoch": 1.98, + "learning_rate": 8.01614162978391e-06, + "loss": 1.7313, + "step": 53340 + }, + { + "epoch": 1.98, + "learning_rate": 8.015769702830364e-06, + "loss": 1.6579, + "step": 53350 + }, + { + "epoch": 1.98, + "learning_rate": 8.01539777587682e-06, + "loss": 1.8672, + "step": 53360 + }, + { + "epoch": 1.98, + "learning_rate": 8.015025848923273e-06, + "loss": 1.7928, + "step": 53370 + }, + { + "epoch": 1.99, + "learning_rate": 8.014653921969726e-06, + "loss": 1.9904, + "step": 53380 + }, + { + "epoch": 1.99, + "learning_rate": 8.01428199501618e-06, + "loss": 1.7741, + "step": 53390 + }, + { + "epoch": 1.99, + "learning_rate": 8.013910068062633e-06, + "loss": 1.756, + "step": 53400 + }, + { + "epoch": 1.99, + "eval_loss": 1.7056500911712646, + "eval_runtime": 16.8369, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 53400 + }, + { + "epoch": 1.99, + "learning_rate": 8.013538141109087e-06, + "loss": 1.732, + "step": 53410 + }, + { + "epoch": 1.99, + "learning_rate": 8.01316621415554e-06, + "loss": 1.742, + "step": 53420 + }, + { + "epoch": 1.99, + "learning_rate": 8.012794287201994e-06, + "loss": 1.726, + "step": 53430 + }, + { + "epoch": 1.99, + "learning_rate": 8.012422360248447e-06, + "loss": 1.7276, + "step": 53440 + }, + { + "epoch": 1.99, + "learning_rate": 8.0120504332949e-06, + "loss": 1.8521, + "step": 53450 + }, + { + "epoch": 1.99, + "learning_rate": 8.011678506341356e-06, + "loss": 1.6971, + "step": 53460 + }, + { + "epoch": 1.99, + "learning_rate": 8.011306579387809e-06, + "loss": 1.7257, + "step": 53470 + }, + { + "epoch": 1.99, + "learning_rate": 8.010934652434263e-06, + "loss": 1.8508, + "step": 53480 + }, + { + "epoch": 1.99, + "learning_rate": 8.010562725480716e-06, + "loss": 1.7995, + "step": 53490 + }, + { + "epoch": 1.99, + "learning_rate": 8.01019079852717e-06, + "loss": 1.8496, + "step": 53500 + }, + { + "epoch": 1.99, + "eval_loss": 1.7067700624465942, + "eval_runtime": 16.8112, + "eval_samples_per_second": 59.484, + "eval_steps_per_second": 3.748, + "step": 53500 + }, + { + "epoch": 1.99, + "learning_rate": 8.009818871573623e-06, + "loss": 1.7482, + "step": 53510 + }, + { + "epoch": 1.99, + "learning_rate": 8.009446944620078e-06, + "loss": 1.9093, + "step": 53520 + }, + { + "epoch": 1.99, + "learning_rate": 8.009075017666532e-06, + "loss": 1.7168, + "step": 53530 + }, + { + "epoch": 1.99, + "learning_rate": 8.008703090712985e-06, + "loss": 1.8143, + "step": 53540 + }, + { + "epoch": 1.99, + "learning_rate": 8.008331163759438e-06, + "loss": 1.7651, + "step": 53550 + }, + { + "epoch": 1.99, + "learning_rate": 8.007959236805892e-06, + "loss": 1.7368, + "step": 53560 + }, + { + "epoch": 1.99, + "learning_rate": 8.007587309852345e-06, + "loss": 1.6512, + "step": 53570 + }, + { + "epoch": 1.99, + "learning_rate": 8.0072153828988e-06, + "loss": 1.8065, + "step": 53580 + }, + { + "epoch": 1.99, + "learning_rate": 8.006843455945254e-06, + "loss": 1.8089, + "step": 53590 + }, + { + "epoch": 1.99, + "learning_rate": 8.006471528991707e-06, + "loss": 1.6949, + "step": 53600 + }, + { + "epoch": 1.99, + "eval_loss": 1.7058730125427246, + "eval_runtime": 16.8149, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 53600 + }, + { + "epoch": 1.99, + "learning_rate": 8.00609960203816e-06, + "loss": 1.8921, + "step": 53610 + }, + { + "epoch": 1.99, + "learning_rate": 8.005727675084614e-06, + "loss": 1.8021, + "step": 53620 + }, + { + "epoch": 1.99, + "learning_rate": 8.005355748131068e-06, + "loss": 1.7609, + "step": 53630 + }, + { + "epoch": 2.0, + "learning_rate": 8.004983821177521e-06, + "loss": 1.8058, + "step": 53640 + }, + { + "epoch": 2.0, + "learning_rate": 8.004611894223975e-06, + "loss": 1.716, + "step": 53650 + }, + { + "epoch": 2.0, + "learning_rate": 8.004239967270428e-06, + "loss": 1.7557, + "step": 53660 + }, + { + "epoch": 2.0, + "learning_rate": 8.003868040316882e-06, + "loss": 1.7451, + "step": 53670 + }, + { + "epoch": 2.0, + "learning_rate": 8.003496113363337e-06, + "loss": 1.8573, + "step": 53680 + }, + { + "epoch": 2.0, + "learning_rate": 8.00312418640979e-06, + "loss": 1.6612, + "step": 53690 + }, + { + "epoch": 2.0, + "learning_rate": 8.002752259456244e-06, + "loss": 1.787, + "step": 53700 + }, + { + "epoch": 2.0, + "eval_loss": 1.7055505514144897, + "eval_runtime": 16.8087, + "eval_samples_per_second": 59.493, + "eval_steps_per_second": 3.748, + "step": 53700 + }, + { + "epoch": 2.0, + "learning_rate": 8.002380332502697e-06, + "loss": 1.7677, + "step": 53710 + }, + { + "epoch": 2.0, + "learning_rate": 8.00200840554915e-06, + "loss": 1.7634, + "step": 53720 + }, + { + "epoch": 2.0, + "learning_rate": 8.001636478595604e-06, + "loss": 1.8714, + "step": 53730 + }, + { + "epoch": 2.0, + "learning_rate": 8.00126455164206e-06, + "loss": 1.797, + "step": 53740 + }, + { + "epoch": 2.0, + "learning_rate": 8.000892624688513e-06, + "loss": 1.7416, + "step": 53750 + }, + { + "epoch": 2.0, + "learning_rate": 8.000520697734966e-06, + "loss": 1.7537, + "step": 53760 + }, + { + "epoch": 2.0, + "learning_rate": 8.00014877078142e-06, + "loss": 1.891, + "step": 53770 + }, + { + "epoch": 2.0, + "learning_rate": 7.999776843827873e-06, + "loss": 1.7425, + "step": 53780 + }, + { + "epoch": 2.0, + "learning_rate": 7.999404916874327e-06, + "loss": 1.7264, + "step": 53790 + }, + { + "epoch": 2.0, + "learning_rate": 7.99903298992078e-06, + "loss": 1.753, + "step": 53800 + }, + { + "epoch": 2.0, + "eval_loss": 1.705356240272522, + "eval_runtime": 16.832, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 53800 + }, + { + "epoch": 2.0, + "learning_rate": 7.998661062967233e-06, + "loss": 1.8672, + "step": 53810 + }, + { + "epoch": 2.0, + "learning_rate": 7.998289136013687e-06, + "loss": 1.8652, + "step": 53820 + }, + { + "epoch": 2.0, + "learning_rate": 7.99791720906014e-06, + "loss": 1.7935, + "step": 53830 + }, + { + "epoch": 2.0, + "learning_rate": 7.997545282106594e-06, + "loss": 1.8024, + "step": 53840 + }, + { + "epoch": 2.0, + "learning_rate": 7.997173355153049e-06, + "loss": 1.8332, + "step": 53850 + }, + { + "epoch": 2.0, + "learning_rate": 7.996801428199502e-06, + "loss": 1.8425, + "step": 53860 + }, + { + "epoch": 2.0, + "learning_rate": 7.996429501245956e-06, + "loss": 1.7397, + "step": 53870 + }, + { + "epoch": 2.0, + "learning_rate": 7.99605757429241e-06, + "loss": 1.732, + "step": 53880 + }, + { + "epoch": 2.0, + "learning_rate": 7.995685647338863e-06, + "loss": 1.56, + "step": 53890 + }, + { + "epoch": 2.0, + "learning_rate": 7.995313720385316e-06, + "loss": 1.696, + "step": 53900 + }, + { + "epoch": 2.0, + "eval_loss": 1.7049376964569092, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 53900 + }, + { + "epoch": 2.01, + "learning_rate": 7.994941793431771e-06, + "loss": 1.8017, + "step": 53910 + }, + { + "epoch": 2.01, + "learning_rate": 7.994569866478225e-06, + "loss": 1.7229, + "step": 53920 + }, + { + "epoch": 2.01, + "learning_rate": 7.994197939524678e-06, + "loss": 1.6425, + "step": 53930 + }, + { + "epoch": 2.01, + "learning_rate": 7.993826012571132e-06, + "loss": 1.7702, + "step": 53940 + }, + { + "epoch": 2.01, + "learning_rate": 7.993454085617585e-06, + "loss": 1.8501, + "step": 53950 + }, + { + "epoch": 2.01, + "learning_rate": 7.993082158664039e-06, + "loss": 1.8227, + "step": 53960 + }, + { + "epoch": 2.01, + "learning_rate": 7.992710231710494e-06, + "loss": 1.8573, + "step": 53970 + }, + { + "epoch": 2.01, + "learning_rate": 7.992338304756947e-06, + "loss": 1.6218, + "step": 53980 + }, + { + "epoch": 2.01, + "learning_rate": 7.991966377803399e-06, + "loss": 1.7399, + "step": 53990 + }, + { + "epoch": 2.01, + "learning_rate": 7.991594450849853e-06, + "loss": 1.7847, + "step": 54000 + }, + { + "epoch": 2.01, + "eval_loss": 1.7058383226394653, + "eval_runtime": 16.8252, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 54000 + }, + { + "epoch": 2.01, + "learning_rate": 7.991222523896308e-06, + "loss": 1.7501, + "step": 54010 + }, + { + "epoch": 2.01, + "learning_rate": 7.990850596942761e-06, + "loss": 1.7735, + "step": 54020 + }, + { + "epoch": 2.01, + "learning_rate": 7.990478669989215e-06, + "loss": 1.8959, + "step": 54030 + }, + { + "epoch": 2.01, + "learning_rate": 7.990106743035668e-06, + "loss": 1.8205, + "step": 54040 + }, + { + "epoch": 2.01, + "learning_rate": 7.989734816082122e-06, + "loss": 1.6492, + "step": 54050 + }, + { + "epoch": 2.01, + "learning_rate": 7.989362889128575e-06, + "loss": 1.8749, + "step": 54060 + }, + { + "epoch": 2.01, + "learning_rate": 7.98899096217503e-06, + "loss": 1.7871, + "step": 54070 + }, + { + "epoch": 2.01, + "learning_rate": 7.988619035221484e-06, + "loss": 1.9153, + "step": 54080 + }, + { + "epoch": 2.01, + "learning_rate": 7.988247108267937e-06, + "loss": 1.7424, + "step": 54090 + }, + { + "epoch": 2.01, + "learning_rate": 7.98787518131439e-06, + "loss": 1.6884, + "step": 54100 + }, + { + "epoch": 2.01, + "eval_loss": 1.7055760622024536, + "eval_runtime": 16.8424, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 54100 + }, + { + "epoch": 2.01, + "learning_rate": 7.987503254360844e-06, + "loss": 1.9315, + "step": 54110 + }, + { + "epoch": 2.01, + "learning_rate": 7.987131327407297e-06, + "loss": 1.8831, + "step": 54120 + }, + { + "epoch": 2.01, + "learning_rate": 7.986759400453753e-06, + "loss": 1.6581, + "step": 54130 + }, + { + "epoch": 2.01, + "learning_rate": 7.986387473500206e-06, + "loss": 1.777, + "step": 54140 + }, + { + "epoch": 2.01, + "learning_rate": 7.98601554654666e-06, + "loss": 1.7718, + "step": 54150 + }, + { + "epoch": 2.01, + "learning_rate": 7.985643619593113e-06, + "loss": 1.8592, + "step": 54160 + }, + { + "epoch": 2.01, + "learning_rate": 7.985271692639566e-06, + "loss": 1.6693, + "step": 54170 + }, + { + "epoch": 2.02, + "learning_rate": 7.98489976568602e-06, + "loss": 1.7603, + "step": 54180 + }, + { + "epoch": 2.02, + "learning_rate": 7.984527838732473e-06, + "loss": 1.7664, + "step": 54190 + }, + { + "epoch": 2.02, + "learning_rate": 7.984155911778927e-06, + "loss": 1.8872, + "step": 54200 + }, + { + "epoch": 2.02, + "eval_loss": 1.704709768295288, + "eval_runtime": 16.8331, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 54200 + }, + { + "epoch": 2.02, + "learning_rate": 7.98378398482538e-06, + "loss": 1.5785, + "step": 54210 + }, + { + "epoch": 2.02, + "learning_rate": 7.983412057871834e-06, + "loss": 1.728, + "step": 54220 + }, + { + "epoch": 2.02, + "learning_rate": 7.983040130918289e-06, + "loss": 1.6016, + "step": 54230 + }, + { + "epoch": 2.02, + "learning_rate": 7.982668203964742e-06, + "loss": 1.6583, + "step": 54240 + }, + { + "epoch": 2.02, + "learning_rate": 7.982296277011196e-06, + "loss": 1.7345, + "step": 54250 + }, + { + "epoch": 2.02, + "learning_rate": 7.98192435005765e-06, + "loss": 1.7271, + "step": 54260 + }, + { + "epoch": 2.02, + "learning_rate": 7.981552423104103e-06, + "loss": 1.7165, + "step": 54270 + }, + { + "epoch": 2.02, + "learning_rate": 7.981180496150556e-06, + "loss": 1.7877, + "step": 54280 + }, + { + "epoch": 2.02, + "learning_rate": 7.980808569197011e-06, + "loss": 1.8272, + "step": 54290 + }, + { + "epoch": 2.02, + "learning_rate": 7.980436642243465e-06, + "loss": 1.6698, + "step": 54300 + }, + { + "epoch": 2.02, + "eval_loss": 1.704797625541687, + "eval_runtime": 16.8213, + "eval_samples_per_second": 59.448, + "eval_steps_per_second": 3.745, + "step": 54300 + }, + { + "epoch": 2.02, + "learning_rate": 7.980064715289918e-06, + "loss": 1.7826, + "step": 54310 + }, + { + "epoch": 2.02, + "learning_rate": 7.979692788336372e-06, + "loss": 1.7508, + "step": 54320 + }, + { + "epoch": 2.02, + "learning_rate": 7.979320861382825e-06, + "loss": 1.6403, + "step": 54330 + }, + { + "epoch": 2.02, + "learning_rate": 7.978948934429279e-06, + "loss": 1.673, + "step": 54340 + }, + { + "epoch": 2.02, + "learning_rate": 7.978577007475732e-06, + "loss": 1.6447, + "step": 54350 + }, + { + "epoch": 2.02, + "learning_rate": 7.978205080522186e-06, + "loss": 1.7893, + "step": 54360 + }, + { + "epoch": 2.02, + "learning_rate": 7.977833153568639e-06, + "loss": 1.8416, + "step": 54370 + }, + { + "epoch": 2.02, + "learning_rate": 7.977461226615092e-06, + "loss": 1.7243, + "step": 54380 + }, + { + "epoch": 2.02, + "learning_rate": 7.977089299661546e-06, + "loss": 1.7755, + "step": 54390 + }, + { + "epoch": 2.02, + "learning_rate": 7.976717372708001e-06, + "loss": 1.8238, + "step": 54400 + }, + { + "epoch": 2.02, + "eval_loss": 1.7052838802337646, + "eval_runtime": 16.8122, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 54400 + }, + { + "epoch": 2.02, + "learning_rate": 7.976345445754455e-06, + "loss": 1.623, + "step": 54410 + }, + { + "epoch": 2.02, + "learning_rate": 7.975973518800908e-06, + "loss": 1.6745, + "step": 54420 + }, + { + "epoch": 2.02, + "learning_rate": 7.975601591847361e-06, + "loss": 1.7983, + "step": 54430 + }, + { + "epoch": 2.02, + "learning_rate": 7.975229664893815e-06, + "loss": 1.7941, + "step": 54440 + }, + { + "epoch": 2.03, + "learning_rate": 7.974857737940268e-06, + "loss": 1.7487, + "step": 54450 + }, + { + "epoch": 2.03, + "learning_rate": 7.974485810986724e-06, + "loss": 1.7599, + "step": 54460 + }, + { + "epoch": 2.03, + "learning_rate": 7.974113884033177e-06, + "loss": 1.783, + "step": 54470 + }, + { + "epoch": 2.03, + "learning_rate": 7.97374195707963e-06, + "loss": 1.6064, + "step": 54480 + }, + { + "epoch": 2.03, + "learning_rate": 7.973370030126084e-06, + "loss": 1.7882, + "step": 54490 + }, + { + "epoch": 2.03, + "learning_rate": 7.972998103172537e-06, + "loss": 1.6897, + "step": 54500 + }, + { + "epoch": 2.03, + "eval_loss": 1.70528244972229, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 54500 + }, + { + "epoch": 2.03, + "learning_rate": 7.97262617621899e-06, + "loss": 1.7703, + "step": 54510 + }, + { + "epoch": 2.03, + "learning_rate": 7.972254249265446e-06, + "loss": 1.6857, + "step": 54520 + }, + { + "epoch": 2.03, + "learning_rate": 7.9718823223119e-06, + "loss": 1.7218, + "step": 54530 + }, + { + "epoch": 2.03, + "learning_rate": 7.971510395358353e-06, + "loss": 1.7192, + "step": 54540 + }, + { + "epoch": 2.03, + "learning_rate": 7.971138468404805e-06, + "loss": 1.7759, + "step": 54550 + }, + { + "epoch": 2.03, + "learning_rate": 7.97076654145126e-06, + "loss": 1.7208, + "step": 54560 + }, + { + "epoch": 2.03, + "learning_rate": 7.970394614497713e-06, + "loss": 1.8003, + "step": 54570 + }, + { + "epoch": 2.03, + "learning_rate": 7.970022687544167e-06, + "loss": 1.7735, + "step": 54580 + }, + { + "epoch": 2.03, + "learning_rate": 7.96965076059062e-06, + "loss": 1.8598, + "step": 54590 + }, + { + "epoch": 2.03, + "learning_rate": 7.969278833637074e-06, + "loss": 1.8759, + "step": 54600 + }, + { + "epoch": 2.03, + "eval_loss": 1.7048120498657227, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 54600 + }, + { + "epoch": 2.03, + "learning_rate": 7.968906906683527e-06, + "loss": 1.7403, + "step": 54610 + }, + { + "epoch": 2.03, + "learning_rate": 7.968534979729982e-06, + "loss": 1.7681, + "step": 54620 + }, + { + "epoch": 2.03, + "learning_rate": 7.968163052776436e-06, + "loss": 1.8649, + "step": 54630 + }, + { + "epoch": 2.03, + "learning_rate": 7.96779112582289e-06, + "loss": 1.8107, + "step": 54640 + }, + { + "epoch": 2.03, + "learning_rate": 7.967419198869343e-06, + "loss": 1.8111, + "step": 54650 + }, + { + "epoch": 2.03, + "learning_rate": 7.967047271915796e-06, + "loss": 1.7354, + "step": 54660 + }, + { + "epoch": 2.03, + "learning_rate": 7.96667534496225e-06, + "loss": 1.7151, + "step": 54670 + }, + { + "epoch": 2.03, + "learning_rate": 7.966303418008705e-06, + "loss": 1.7364, + "step": 54680 + }, + { + "epoch": 2.03, + "learning_rate": 7.965931491055158e-06, + "loss": 1.7317, + "step": 54690 + }, + { + "epoch": 2.03, + "learning_rate": 7.965559564101612e-06, + "loss": 1.7212, + "step": 54700 + }, + { + "epoch": 2.03, + "eval_loss": 1.703863263130188, + "eval_runtime": 16.8166, + "eval_samples_per_second": 59.465, + "eval_steps_per_second": 3.746, + "step": 54700 + }, + { + "epoch": 2.03, + "learning_rate": 7.965187637148065e-06, + "loss": 1.9381, + "step": 54710 + }, + { + "epoch": 2.04, + "learning_rate": 7.964815710194519e-06, + "loss": 1.6968, + "step": 54720 + }, + { + "epoch": 2.04, + "learning_rate": 7.964443783240972e-06, + "loss": 1.8028, + "step": 54730 + }, + { + "epoch": 2.04, + "learning_rate": 7.964071856287425e-06, + "loss": 1.638, + "step": 54740 + }, + { + "epoch": 2.04, + "learning_rate": 7.963699929333879e-06, + "loss": 1.7376, + "step": 54750 + }, + { + "epoch": 2.04, + "learning_rate": 7.963328002380332e-06, + "loss": 1.7408, + "step": 54760 + }, + { + "epoch": 2.04, + "learning_rate": 7.962956075426786e-06, + "loss": 1.9175, + "step": 54770 + }, + { + "epoch": 2.04, + "learning_rate": 7.962584148473241e-06, + "loss": 1.6799, + "step": 54780 + }, + { + "epoch": 2.04, + "learning_rate": 7.962212221519694e-06, + "loss": 1.6861, + "step": 54790 + }, + { + "epoch": 2.04, + "learning_rate": 7.961840294566148e-06, + "loss": 1.7176, + "step": 54800 + }, + { + "epoch": 2.04, + "eval_loss": 1.7032802104949951, + "eval_runtime": 16.8263, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 54800 + }, + { + "epoch": 2.04, + "learning_rate": 7.961468367612601e-06, + "loss": 1.6925, + "step": 54810 + }, + { + "epoch": 2.04, + "learning_rate": 7.961096440659055e-06, + "loss": 1.8058, + "step": 54820 + }, + { + "epoch": 2.04, + "learning_rate": 7.960724513705508e-06, + "loss": 1.7441, + "step": 54830 + }, + { + "epoch": 2.04, + "learning_rate": 7.960352586751963e-06, + "loss": 1.7766, + "step": 54840 + }, + { + "epoch": 2.04, + "learning_rate": 7.959980659798417e-06, + "loss": 1.7269, + "step": 54850 + }, + { + "epoch": 2.04, + "learning_rate": 7.95960873284487e-06, + "loss": 1.8202, + "step": 54860 + }, + { + "epoch": 2.04, + "learning_rate": 7.959236805891324e-06, + "loss": 1.734, + "step": 54870 + }, + { + "epoch": 2.04, + "learning_rate": 7.958864878937777e-06, + "loss": 1.6368, + "step": 54880 + }, + { + "epoch": 2.04, + "learning_rate": 7.95849295198423e-06, + "loss": 1.8282, + "step": 54890 + }, + { + "epoch": 2.04, + "learning_rate": 7.958121025030686e-06, + "loss": 1.7974, + "step": 54900 + }, + { + "epoch": 2.04, + "eval_loss": 1.7040822505950928, + "eval_runtime": 16.8175, + "eval_samples_per_second": 59.462, + "eval_steps_per_second": 3.746, + "step": 54900 + }, + { + "epoch": 2.04, + "learning_rate": 7.95774909807714e-06, + "loss": 1.7187, + "step": 54910 + }, + { + "epoch": 2.04, + "learning_rate": 7.957377171123591e-06, + "loss": 1.6496, + "step": 54920 + }, + { + "epoch": 2.04, + "learning_rate": 7.957005244170045e-06, + "loss": 1.7948, + "step": 54930 + }, + { + "epoch": 2.04, + "learning_rate": 7.9566333172165e-06, + "loss": 1.6496, + "step": 54940 + }, + { + "epoch": 2.04, + "learning_rate": 7.956261390262953e-06, + "loss": 1.6664, + "step": 54950 + }, + { + "epoch": 2.04, + "learning_rate": 7.955889463309407e-06, + "loss": 1.6715, + "step": 54960 + }, + { + "epoch": 2.04, + "learning_rate": 7.95551753635586e-06, + "loss": 1.6243, + "step": 54970 + }, + { + "epoch": 2.04, + "learning_rate": 7.955145609402314e-06, + "loss": 1.774, + "step": 54980 + }, + { + "epoch": 2.05, + "learning_rate": 7.954773682448767e-06, + "loss": 1.735, + "step": 54990 + }, + { + "epoch": 2.05, + "learning_rate": 7.95440175549522e-06, + "loss": 1.973, + "step": 55000 + }, + { + "epoch": 2.05, + "eval_loss": 1.7039140462875366, + "eval_runtime": 16.8164, + "eval_samples_per_second": 59.466, + "eval_steps_per_second": 3.746, + "step": 55000 + }, + { + "epoch": 2.05, + "learning_rate": 7.954029828541676e-06, + "loss": 1.7067, + "step": 55010 + }, + { + "epoch": 2.05, + "learning_rate": 7.953657901588129e-06, + "loss": 1.808, + "step": 55020 + }, + { + "epoch": 2.05, + "learning_rate": 7.953285974634583e-06, + "loss": 1.6806, + "step": 55030 + }, + { + "epoch": 2.05, + "learning_rate": 7.952914047681036e-06, + "loss": 1.7201, + "step": 55040 + }, + { + "epoch": 2.05, + "learning_rate": 7.95254212072749e-06, + "loss": 1.9192, + "step": 55050 + }, + { + "epoch": 2.05, + "learning_rate": 7.952170193773943e-06, + "loss": 1.752, + "step": 55060 + }, + { + "epoch": 2.05, + "learning_rate": 7.951798266820398e-06, + "loss": 1.8593, + "step": 55070 + }, + { + "epoch": 2.05, + "learning_rate": 7.951426339866852e-06, + "loss": 1.8287, + "step": 55080 + }, + { + "epoch": 2.05, + "learning_rate": 7.951054412913305e-06, + "loss": 1.6172, + "step": 55090 + }, + { + "epoch": 2.05, + "learning_rate": 7.950682485959758e-06, + "loss": 1.8218, + "step": 55100 + }, + { + "epoch": 2.05, + "eval_loss": 1.7022632360458374, + "eval_runtime": 16.8213, + "eval_samples_per_second": 59.448, + "eval_steps_per_second": 3.745, + "step": 55100 + }, + { + "epoch": 2.05, + "learning_rate": 7.950310559006212e-06, + "loss": 1.8461, + "step": 55110 + }, + { + "epoch": 2.05, + "learning_rate": 7.949938632052665e-06, + "loss": 1.7321, + "step": 55120 + }, + { + "epoch": 2.05, + "learning_rate": 7.949566705099119e-06, + "loss": 1.8265, + "step": 55130 + }, + { + "epoch": 2.05, + "learning_rate": 7.949194778145572e-06, + "loss": 1.6754, + "step": 55140 + }, + { + "epoch": 2.05, + "learning_rate": 7.948822851192026e-06, + "loss": 1.782, + "step": 55150 + }, + { + "epoch": 2.05, + "learning_rate": 7.94845092423848e-06, + "loss": 1.6795, + "step": 55160 + }, + { + "epoch": 2.05, + "learning_rate": 7.948078997284934e-06, + "loss": 1.8885, + "step": 55170 + }, + { + "epoch": 2.05, + "learning_rate": 7.947707070331388e-06, + "loss": 1.7875, + "step": 55180 + }, + { + "epoch": 2.05, + "learning_rate": 7.947335143377841e-06, + "loss": 1.8877, + "step": 55190 + }, + { + "epoch": 2.05, + "learning_rate": 7.946963216424295e-06, + "loss": 1.7505, + "step": 55200 + }, + { + "epoch": 2.05, + "eval_loss": 1.7021161317825317, + "eval_runtime": 16.8121, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 55200 + }, + { + "epoch": 2.05, + "learning_rate": 7.946591289470748e-06, + "loss": 1.7465, + "step": 55210 + }, + { + "epoch": 2.05, + "learning_rate": 7.946219362517202e-06, + "loss": 1.7585, + "step": 55220 + }, + { + "epoch": 2.05, + "learning_rate": 7.945847435563657e-06, + "loss": 1.6439, + "step": 55230 + }, + { + "epoch": 2.05, + "learning_rate": 7.94547550861011e-06, + "loss": 1.7631, + "step": 55240 + }, + { + "epoch": 2.05, + "learning_rate": 7.945103581656564e-06, + "loss": 1.8014, + "step": 55250 + }, + { + "epoch": 2.06, + "learning_rate": 7.944731654703017e-06, + "loss": 1.6263, + "step": 55260 + }, + { + "epoch": 2.06, + "learning_rate": 7.94435972774947e-06, + "loss": 1.7597, + "step": 55270 + }, + { + "epoch": 2.06, + "learning_rate": 7.943987800795924e-06, + "loss": 1.796, + "step": 55280 + }, + { + "epoch": 2.06, + "learning_rate": 7.94361587384238e-06, + "loss": 1.7263, + "step": 55290 + }, + { + "epoch": 2.06, + "learning_rate": 7.943243946888831e-06, + "loss": 1.74, + "step": 55300 + }, + { + "epoch": 2.06, + "eval_loss": 1.7029248476028442, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 55300 + }, + { + "epoch": 2.06, + "learning_rate": 7.942872019935285e-06, + "loss": 1.7221, + "step": 55310 + }, + { + "epoch": 2.06, + "learning_rate": 7.942500092981738e-06, + "loss": 1.6717, + "step": 55320 + }, + { + "epoch": 2.06, + "learning_rate": 7.942128166028193e-06, + "loss": 1.6839, + "step": 55330 + }, + { + "epoch": 2.06, + "learning_rate": 7.941756239074647e-06, + "loss": 1.6918, + "step": 55340 + }, + { + "epoch": 2.06, + "learning_rate": 7.9413843121211e-06, + "loss": 1.8113, + "step": 55350 + }, + { + "epoch": 2.06, + "learning_rate": 7.941012385167553e-06, + "loss": 1.7047, + "step": 55360 + }, + { + "epoch": 2.06, + "learning_rate": 7.940640458214007e-06, + "loss": 1.6241, + "step": 55370 + }, + { + "epoch": 2.06, + "learning_rate": 7.94026853126046e-06, + "loss": 1.7192, + "step": 55380 + }, + { + "epoch": 2.06, + "learning_rate": 7.939896604306916e-06, + "loss": 1.6808, + "step": 55390 + }, + { + "epoch": 2.06, + "learning_rate": 7.939524677353369e-06, + "loss": 1.6806, + "step": 55400 + }, + { + "epoch": 2.06, + "eval_loss": 1.702683448791504, + "eval_runtime": 16.8128, + "eval_samples_per_second": 59.479, + "eval_steps_per_second": 3.747, + "step": 55400 + }, + { + "epoch": 2.06, + "learning_rate": 7.939152750399822e-06, + "loss": 1.6432, + "step": 55410 + }, + { + "epoch": 2.06, + "learning_rate": 7.938780823446276e-06, + "loss": 1.6939, + "step": 55420 + }, + { + "epoch": 2.06, + "learning_rate": 7.93840889649273e-06, + "loss": 1.809, + "step": 55430 + }, + { + "epoch": 2.06, + "learning_rate": 7.938036969539183e-06, + "loss": 1.7387, + "step": 55440 + }, + { + "epoch": 2.06, + "learning_rate": 7.937665042585638e-06, + "loss": 1.657, + "step": 55450 + }, + { + "epoch": 2.06, + "learning_rate": 7.937293115632091e-06, + "loss": 1.6795, + "step": 55460 + }, + { + "epoch": 2.06, + "learning_rate": 7.936921188678545e-06, + "loss": 1.7306, + "step": 55470 + }, + { + "epoch": 2.06, + "learning_rate": 7.936549261724998e-06, + "loss": 1.8435, + "step": 55480 + }, + { + "epoch": 2.06, + "learning_rate": 7.936177334771452e-06, + "loss": 1.8023, + "step": 55490 + }, + { + "epoch": 2.06, + "learning_rate": 7.935805407817905e-06, + "loss": 1.8186, + "step": 55500 + }, + { + "epoch": 2.06, + "eval_loss": 1.701500654220581, + "eval_runtime": 16.8018, + "eval_samples_per_second": 59.517, + "eval_steps_per_second": 3.75, + "step": 55500 + }, + { + "epoch": 2.06, + "learning_rate": 7.935433480864359e-06, + "loss": 1.7027, + "step": 55510 + }, + { + "epoch": 2.06, + "learning_rate": 7.935061553910812e-06, + "loss": 1.6331, + "step": 55520 + }, + { + "epoch": 2.07, + "learning_rate": 7.934689626957266e-06, + "loss": 1.7427, + "step": 55530 + }, + { + "epoch": 2.07, + "learning_rate": 7.934317700003719e-06, + "loss": 1.7012, + "step": 55540 + }, + { + "epoch": 2.07, + "learning_rate": 7.933945773050173e-06, + "loss": 1.7842, + "step": 55550 + }, + { + "epoch": 2.07, + "learning_rate": 7.933573846096628e-06, + "loss": 1.8123, + "step": 55560 + }, + { + "epoch": 2.07, + "learning_rate": 7.933201919143081e-06, + "loss": 1.7253, + "step": 55570 + }, + { + "epoch": 2.07, + "learning_rate": 7.932829992189535e-06, + "loss": 1.5891, + "step": 55580 + }, + { + "epoch": 2.07, + "learning_rate": 7.932458065235988e-06, + "loss": 1.7005, + "step": 55590 + }, + { + "epoch": 2.07, + "learning_rate": 7.932086138282442e-06, + "loss": 1.7645, + "step": 55600 + }, + { + "epoch": 2.07, + "eval_loss": 1.7019710540771484, + "eval_runtime": 16.8202, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.746, + "step": 55600 + }, + { + "epoch": 2.07, + "learning_rate": 7.931714211328895e-06, + "loss": 1.7214, + "step": 55610 + }, + { + "epoch": 2.07, + "learning_rate": 7.93134228437535e-06, + "loss": 1.7984, + "step": 55620 + }, + { + "epoch": 2.07, + "learning_rate": 7.930970357421804e-06, + "loss": 1.9077, + "step": 55630 + }, + { + "epoch": 2.07, + "learning_rate": 7.930598430468257e-06, + "loss": 1.6458, + "step": 55640 + }, + { + "epoch": 2.07, + "learning_rate": 7.93022650351471e-06, + "loss": 1.703, + "step": 55650 + }, + { + "epoch": 2.07, + "learning_rate": 7.929854576561164e-06, + "loss": 1.6928, + "step": 55660 + }, + { + "epoch": 2.07, + "learning_rate": 7.929482649607618e-06, + "loss": 1.7577, + "step": 55670 + }, + { + "epoch": 2.07, + "learning_rate": 7.929110722654071e-06, + "loss": 1.8031, + "step": 55680 + }, + { + "epoch": 2.07, + "learning_rate": 7.928738795700524e-06, + "loss": 1.7738, + "step": 55690 + }, + { + "epoch": 2.07, + "learning_rate": 7.928366868746978e-06, + "loss": 1.7829, + "step": 55700 + }, + { + "epoch": 2.07, + "eval_loss": 1.7018392086029053, + "eval_runtime": 16.8264, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 55700 + }, + { + "epoch": 2.07, + "learning_rate": 7.927994941793431e-06, + "loss": 1.7966, + "step": 55710 + }, + { + "epoch": 2.07, + "learning_rate": 7.927623014839886e-06, + "loss": 1.7564, + "step": 55720 + }, + { + "epoch": 2.07, + "learning_rate": 7.92725108788634e-06, + "loss": 1.8102, + "step": 55730 + }, + { + "epoch": 2.07, + "learning_rate": 7.926879160932793e-06, + "loss": 1.6857, + "step": 55740 + }, + { + "epoch": 2.07, + "learning_rate": 7.926507233979247e-06, + "loss": 1.8008, + "step": 55750 + }, + { + "epoch": 2.07, + "learning_rate": 7.9261353070257e-06, + "loss": 1.7141, + "step": 55760 + }, + { + "epoch": 2.07, + "learning_rate": 7.925763380072154e-06, + "loss": 1.6033, + "step": 55770 + }, + { + "epoch": 2.07, + "learning_rate": 7.925391453118609e-06, + "loss": 1.5791, + "step": 55780 + }, + { + "epoch": 2.07, + "learning_rate": 7.925019526165062e-06, + "loss": 1.7675, + "step": 55790 + }, + { + "epoch": 2.08, + "learning_rate": 7.924647599211516e-06, + "loss": 1.7613, + "step": 55800 + }, + { + "epoch": 2.08, + "eval_loss": 1.7012368440628052, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 55800 + }, + { + "epoch": 2.08, + "learning_rate": 7.92427567225797e-06, + "loss": 1.7204, + "step": 55810 + }, + { + "epoch": 2.08, + "learning_rate": 7.923903745304423e-06, + "loss": 1.889, + "step": 55820 + }, + { + "epoch": 2.08, + "learning_rate": 7.923531818350876e-06, + "loss": 1.7203, + "step": 55830 + }, + { + "epoch": 2.08, + "learning_rate": 7.923159891397331e-06, + "loss": 1.8331, + "step": 55840 + }, + { + "epoch": 2.08, + "learning_rate": 7.922787964443785e-06, + "loss": 1.8089, + "step": 55850 + }, + { + "epoch": 2.08, + "learning_rate": 7.922416037490237e-06, + "loss": 1.73, + "step": 55860 + }, + { + "epoch": 2.08, + "learning_rate": 7.92204411053669e-06, + "loss": 1.7211, + "step": 55870 + }, + { + "epoch": 2.08, + "learning_rate": 7.921672183583145e-06, + "loss": 1.7634, + "step": 55880 + }, + { + "epoch": 2.08, + "learning_rate": 7.921300256629599e-06, + "loss": 1.9516, + "step": 55890 + }, + { + "epoch": 2.08, + "learning_rate": 7.920928329676052e-06, + "loss": 1.6422, + "step": 55900 + }, + { + "epoch": 2.08, + "eval_loss": 1.7007081508636475, + "eval_runtime": 16.8253, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 55900 + }, + { + "epoch": 2.08, + "learning_rate": 7.920556402722506e-06, + "loss": 1.6709, + "step": 55910 + }, + { + "epoch": 2.08, + "learning_rate": 7.920184475768959e-06, + "loss": 1.7859, + "step": 55920 + }, + { + "epoch": 2.08, + "learning_rate": 7.919812548815413e-06, + "loss": 1.7892, + "step": 55930 + }, + { + "epoch": 2.08, + "learning_rate": 7.919440621861868e-06, + "loss": 1.7436, + "step": 55940 + }, + { + "epoch": 2.08, + "learning_rate": 7.919068694908321e-06, + "loss": 1.868, + "step": 55950 + }, + { + "epoch": 2.08, + "learning_rate": 7.918696767954775e-06, + "loss": 1.7636, + "step": 55960 + }, + { + "epoch": 2.08, + "learning_rate": 7.918324841001228e-06, + "loss": 1.8335, + "step": 55970 + }, + { + "epoch": 2.08, + "learning_rate": 7.917952914047682e-06, + "loss": 1.7854, + "step": 55980 + }, + { + "epoch": 2.08, + "learning_rate": 7.917580987094135e-06, + "loss": 1.8495, + "step": 55990 + }, + { + "epoch": 2.08, + "learning_rate": 7.91720906014059e-06, + "loss": 1.9244, + "step": 56000 + }, + { + "epoch": 2.08, + "eval_loss": 1.700069785118103, + "eval_runtime": 16.8336, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 56000 + }, + { + "epoch": 2.08, + "learning_rate": 7.916837133187044e-06, + "loss": 1.704, + "step": 56010 + }, + { + "epoch": 2.08, + "learning_rate": 7.916465206233497e-06, + "loss": 1.9341, + "step": 56020 + }, + { + "epoch": 2.08, + "learning_rate": 7.91609327927995e-06, + "loss": 1.6539, + "step": 56030 + }, + { + "epoch": 2.08, + "learning_rate": 7.915721352326404e-06, + "loss": 1.7939, + "step": 56040 + }, + { + "epoch": 2.08, + "learning_rate": 7.915349425372857e-06, + "loss": 1.7919, + "step": 56050 + }, + { + "epoch": 2.09, + "learning_rate": 7.914977498419311e-06, + "loss": 1.664, + "step": 56060 + }, + { + "epoch": 2.09, + "learning_rate": 7.914605571465764e-06, + "loss": 1.6838, + "step": 56070 + }, + { + "epoch": 2.09, + "learning_rate": 7.914233644512218e-06, + "loss": 1.6784, + "step": 56080 + }, + { + "epoch": 2.09, + "learning_rate": 7.913861717558671e-06, + "loss": 1.7877, + "step": 56090 + }, + { + "epoch": 2.09, + "learning_rate": 7.913489790605125e-06, + "loss": 1.7743, + "step": 56100 + }, + { + "epoch": 2.09, + "eval_loss": 1.7002629041671753, + "eval_runtime": 16.8173, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 56100 + }, + { + "epoch": 2.09, + "learning_rate": 7.91311786365158e-06, + "loss": 1.7269, + "step": 56110 + }, + { + "epoch": 2.09, + "learning_rate": 7.912745936698033e-06, + "loss": 1.7673, + "step": 56120 + }, + { + "epoch": 2.09, + "learning_rate": 7.912374009744487e-06, + "loss": 1.8557, + "step": 56130 + }, + { + "epoch": 2.09, + "learning_rate": 7.91200208279094e-06, + "loss": 1.7313, + "step": 56140 + }, + { + "epoch": 2.09, + "learning_rate": 7.911630155837394e-06, + "loss": 1.7636, + "step": 56150 + }, + { + "epoch": 2.09, + "learning_rate": 7.911258228883847e-06, + "loss": 1.7189, + "step": 56160 + }, + { + "epoch": 2.09, + "learning_rate": 7.910886301930302e-06, + "loss": 1.7092, + "step": 56170 + }, + { + "epoch": 2.09, + "learning_rate": 7.910514374976756e-06, + "loss": 1.6869, + "step": 56180 + }, + { + "epoch": 2.09, + "learning_rate": 7.91014244802321e-06, + "loss": 1.7812, + "step": 56190 + }, + { + "epoch": 2.09, + "learning_rate": 7.909770521069663e-06, + "loss": 1.7065, + "step": 56200 + }, + { + "epoch": 2.09, + "eval_loss": 1.701092004776001, + "eval_runtime": 16.8338, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 56200 + }, + { + "epoch": 2.09, + "learning_rate": 7.909398594116116e-06, + "loss": 1.932, + "step": 56210 + }, + { + "epoch": 2.09, + "learning_rate": 7.90902666716257e-06, + "loss": 1.767, + "step": 56220 + }, + { + "epoch": 2.09, + "learning_rate": 7.908654740209025e-06, + "loss": 1.6273, + "step": 56230 + }, + { + "epoch": 2.09, + "learning_rate": 7.908282813255477e-06, + "loss": 1.6233, + "step": 56240 + }, + { + "epoch": 2.09, + "learning_rate": 7.90791088630193e-06, + "loss": 1.7477, + "step": 56250 + }, + { + "epoch": 2.09, + "learning_rate": 7.907538959348383e-06, + "loss": 1.6771, + "step": 56260 + }, + { + "epoch": 2.09, + "learning_rate": 7.907167032394839e-06, + "loss": 1.8114, + "step": 56270 + }, + { + "epoch": 2.09, + "learning_rate": 7.906795105441292e-06, + "loss": 1.7464, + "step": 56280 + }, + { + "epoch": 2.09, + "learning_rate": 7.906423178487746e-06, + "loss": 1.756, + "step": 56290 + }, + { + "epoch": 2.09, + "learning_rate": 7.906051251534199e-06, + "loss": 1.7511, + "step": 56300 + }, + { + "epoch": 2.09, + "eval_loss": 1.699889063835144, + "eval_runtime": 16.807, + "eval_samples_per_second": 59.499, + "eval_steps_per_second": 3.748, + "step": 56300 + }, + { + "epoch": 2.09, + "learning_rate": 7.905679324580652e-06, + "loss": 1.7833, + "step": 56310 + }, + { + "epoch": 2.09, + "learning_rate": 7.905307397627106e-06, + "loss": 1.8381, + "step": 56320 + }, + { + "epoch": 2.1, + "learning_rate": 7.904935470673561e-06, + "loss": 1.7049, + "step": 56330 + }, + { + "epoch": 2.1, + "learning_rate": 7.904563543720015e-06, + "loss": 1.6515, + "step": 56340 + }, + { + "epoch": 2.1, + "learning_rate": 7.904191616766468e-06, + "loss": 1.8266, + "step": 56350 + }, + { + "epoch": 2.1, + "learning_rate": 7.903819689812921e-06, + "loss": 1.7253, + "step": 56360 + }, + { + "epoch": 2.1, + "learning_rate": 7.903447762859375e-06, + "loss": 1.6857, + "step": 56370 + }, + { + "epoch": 2.1, + "learning_rate": 7.903075835905828e-06, + "loss": 1.6535, + "step": 56380 + }, + { + "epoch": 2.1, + "learning_rate": 7.902703908952284e-06, + "loss": 1.6328, + "step": 56390 + }, + { + "epoch": 2.1, + "learning_rate": 7.902331981998737e-06, + "loss": 1.8174, + "step": 56400 + }, + { + "epoch": 2.1, + "eval_loss": 1.7004708051681519, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 56400 + }, + { + "epoch": 2.1, + "learning_rate": 7.90196005504519e-06, + "loss": 1.6782, + "step": 56410 + }, + { + "epoch": 2.1, + "learning_rate": 7.901588128091644e-06, + "loss": 1.8618, + "step": 56420 + }, + { + "epoch": 2.1, + "learning_rate": 7.901216201138097e-06, + "loss": 1.7598, + "step": 56430 + }, + { + "epoch": 2.1, + "learning_rate": 7.90084427418455e-06, + "loss": 1.7646, + "step": 56440 + }, + { + "epoch": 2.1, + "learning_rate": 7.900472347231004e-06, + "loss": 1.6837, + "step": 56450 + }, + { + "epoch": 2.1, + "learning_rate": 7.900100420277458e-06, + "loss": 1.7795, + "step": 56460 + }, + { + "epoch": 2.1, + "learning_rate": 7.899728493323911e-06, + "loss": 1.7465, + "step": 56470 + }, + { + "epoch": 2.1, + "learning_rate": 7.899356566370365e-06, + "loss": 1.6905, + "step": 56480 + }, + { + "epoch": 2.1, + "learning_rate": 7.89898463941682e-06, + "loss": 1.7141, + "step": 56490 + }, + { + "epoch": 2.1, + "learning_rate": 7.898612712463273e-06, + "loss": 1.8105, + "step": 56500 + }, + { + "epoch": 2.1, + "eval_loss": 1.7001069784164429, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 56500 + }, + { + "epoch": 2.1, + "learning_rate": 7.898240785509727e-06, + "loss": 1.8332, + "step": 56510 + }, + { + "epoch": 2.1, + "learning_rate": 7.89786885855618e-06, + "loss": 1.7817, + "step": 56520 + }, + { + "epoch": 2.1, + "learning_rate": 7.897496931602634e-06, + "loss": 1.8297, + "step": 56530 + }, + { + "epoch": 2.1, + "learning_rate": 7.897125004649087e-06, + "loss": 1.8114, + "step": 56540 + }, + { + "epoch": 2.1, + "learning_rate": 7.896753077695542e-06, + "loss": 1.7352, + "step": 56550 + }, + { + "epoch": 2.1, + "learning_rate": 7.896381150741996e-06, + "loss": 1.845, + "step": 56560 + }, + { + "epoch": 2.1, + "learning_rate": 7.89600922378845e-06, + "loss": 1.7106, + "step": 56570 + }, + { + "epoch": 2.1, + "learning_rate": 7.895637296834903e-06, + "loss": 1.8036, + "step": 56580 + }, + { + "epoch": 2.1, + "learning_rate": 7.895265369881356e-06, + "loss": 1.649, + "step": 56590 + }, + { + "epoch": 2.11, + "learning_rate": 7.89489344292781e-06, + "loss": 1.6924, + "step": 56600 + }, + { + "epoch": 2.11, + "eval_loss": 1.7008845806121826, + "eval_runtime": 16.8225, + "eval_samples_per_second": 59.444, + "eval_steps_per_second": 3.745, + "step": 56600 + }, + { + "epoch": 2.11, + "learning_rate": 7.894521515974263e-06, + "loss": 1.7358, + "step": 56610 + }, + { + "epoch": 2.11, + "learning_rate": 7.894149589020716e-06, + "loss": 1.7961, + "step": 56620 + }, + { + "epoch": 2.11, + "learning_rate": 7.89377766206717e-06, + "loss": 1.7439, + "step": 56630 + }, + { + "epoch": 2.11, + "learning_rate": 7.893405735113623e-06, + "loss": 1.8377, + "step": 56640 + }, + { + "epoch": 2.11, + "learning_rate": 7.893033808160079e-06, + "loss": 1.7276, + "step": 56650 + }, + { + "epoch": 2.11, + "learning_rate": 7.892661881206532e-06, + "loss": 1.7118, + "step": 56660 + }, + { + "epoch": 2.11, + "learning_rate": 7.892289954252985e-06, + "loss": 1.7672, + "step": 56670 + }, + { + "epoch": 2.11, + "learning_rate": 7.891918027299439e-06, + "loss": 1.8796, + "step": 56680 + }, + { + "epoch": 2.11, + "learning_rate": 7.891546100345892e-06, + "loss": 1.7337, + "step": 56690 + }, + { + "epoch": 2.11, + "learning_rate": 7.891174173392346e-06, + "loss": 1.8353, + "step": 56700 + }, + { + "epoch": 2.11, + "eval_loss": 1.7007173299789429, + "eval_runtime": 16.8196, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 56700 + }, + { + "epoch": 2.11, + "learning_rate": 7.8908022464388e-06, + "loss": 1.8383, + "step": 56710 + }, + { + "epoch": 2.11, + "learning_rate": 7.890430319485254e-06, + "loss": 1.8226, + "step": 56720 + }, + { + "epoch": 2.11, + "learning_rate": 7.890058392531708e-06, + "loss": 1.6089, + "step": 56730 + }, + { + "epoch": 2.11, + "learning_rate": 7.889686465578161e-06, + "loss": 1.6586, + "step": 56740 + }, + { + "epoch": 2.11, + "learning_rate": 7.889314538624615e-06, + "loss": 1.6263, + "step": 56750 + }, + { + "epoch": 2.11, + "learning_rate": 7.888942611671068e-06, + "loss": 1.7127, + "step": 56760 + }, + { + "epoch": 2.11, + "learning_rate": 7.888570684717522e-06, + "loss": 1.9373, + "step": 56770 + }, + { + "epoch": 2.11, + "learning_rate": 7.888198757763977e-06, + "loss": 1.7542, + "step": 56780 + }, + { + "epoch": 2.11, + "learning_rate": 7.88782683081043e-06, + "loss": 1.8024, + "step": 56790 + }, + { + "epoch": 2.11, + "learning_rate": 7.887454903856882e-06, + "loss": 1.5972, + "step": 56800 + }, + { + "epoch": 2.11, + "eval_loss": 1.6999399662017822, + "eval_runtime": 16.8466, + "eval_samples_per_second": 59.359, + "eval_steps_per_second": 3.74, + "step": 56800 + }, + { + "epoch": 2.11, + "learning_rate": 7.887082976903336e-06, + "loss": 1.7806, + "step": 56810 + }, + { + "epoch": 2.11, + "learning_rate": 7.88671104994979e-06, + "loss": 1.718, + "step": 56820 + }, + { + "epoch": 2.11, + "learning_rate": 7.886339122996244e-06, + "loss": 1.8007, + "step": 56830 + }, + { + "epoch": 2.11, + "learning_rate": 7.885967196042698e-06, + "loss": 1.6322, + "step": 56840 + }, + { + "epoch": 2.11, + "learning_rate": 7.885595269089151e-06, + "loss": 1.6688, + "step": 56850 + }, + { + "epoch": 2.11, + "learning_rate": 7.885223342135605e-06, + "loss": 1.6555, + "step": 56860 + }, + { + "epoch": 2.12, + "learning_rate": 7.884851415182058e-06, + "loss": 1.8195, + "step": 56870 + }, + { + "epoch": 2.12, + "learning_rate": 7.884479488228513e-06, + "loss": 1.7923, + "step": 56880 + }, + { + "epoch": 2.12, + "learning_rate": 7.884107561274967e-06, + "loss": 1.7763, + "step": 56890 + }, + { + "epoch": 2.12, + "learning_rate": 7.88373563432142e-06, + "loss": 1.6745, + "step": 56900 + }, + { + "epoch": 2.12, + "eval_loss": 1.699627161026001, + "eval_runtime": 16.829, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.744, + "step": 56900 + }, + { + "epoch": 2.12, + "learning_rate": 7.883363707367874e-06, + "loss": 1.6605, + "step": 56910 + }, + { + "epoch": 2.12, + "learning_rate": 7.882991780414327e-06, + "loss": 1.7357, + "step": 56920 + }, + { + "epoch": 2.12, + "learning_rate": 7.88261985346078e-06, + "loss": 1.8063, + "step": 56930 + }, + { + "epoch": 2.12, + "learning_rate": 7.882247926507236e-06, + "loss": 1.8705, + "step": 56940 + }, + { + "epoch": 2.12, + "learning_rate": 7.881875999553689e-06, + "loss": 1.782, + "step": 56950 + }, + { + "epoch": 2.12, + "learning_rate": 7.881504072600143e-06, + "loss": 1.6896, + "step": 56960 + }, + { + "epoch": 2.12, + "learning_rate": 7.881132145646596e-06, + "loss": 1.6297, + "step": 56970 + }, + { + "epoch": 2.12, + "learning_rate": 7.88076021869305e-06, + "loss": 1.8329, + "step": 56980 + }, + { + "epoch": 2.12, + "learning_rate": 7.880388291739503e-06, + "loss": 1.7066, + "step": 56990 + }, + { + "epoch": 2.12, + "learning_rate": 7.880016364785956e-06, + "loss": 1.8788, + "step": 57000 + }, + { + "epoch": 2.12, + "eval_loss": 1.6990208625793457, + "eval_runtime": 16.8265, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 57000 + }, + { + "epoch": 2.12, + "learning_rate": 7.87964443783241e-06, + "loss": 1.714, + "step": 57010 + }, + { + "epoch": 2.12, + "learning_rate": 7.879272510878863e-06, + "loss": 1.7346, + "step": 57020 + }, + { + "epoch": 2.12, + "learning_rate": 7.878900583925317e-06, + "loss": 1.8621, + "step": 57030 + }, + { + "epoch": 2.12, + "learning_rate": 7.878528656971772e-06, + "loss": 1.7704, + "step": 57040 + }, + { + "epoch": 2.12, + "learning_rate": 7.878156730018225e-06, + "loss": 1.7315, + "step": 57050 + }, + { + "epoch": 2.12, + "learning_rate": 7.877784803064679e-06, + "loss": 1.7254, + "step": 57060 + }, + { + "epoch": 2.12, + "learning_rate": 7.877412876111132e-06, + "loss": 1.7783, + "step": 57070 + }, + { + "epoch": 2.12, + "learning_rate": 7.877040949157586e-06, + "loss": 1.7999, + "step": 57080 + }, + { + "epoch": 2.12, + "learning_rate": 7.87666902220404e-06, + "loss": 1.8038, + "step": 57090 + }, + { + "epoch": 2.12, + "learning_rate": 7.876297095250494e-06, + "loss": 1.7884, + "step": 57100 + }, + { + "epoch": 2.12, + "eval_loss": 1.6990562677383423, + "eval_runtime": 16.8259, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 57100 + }, + { + "epoch": 2.12, + "learning_rate": 7.875925168296948e-06, + "loss": 1.7878, + "step": 57110 + }, + { + "epoch": 2.12, + "learning_rate": 7.875553241343401e-06, + "loss": 1.7401, + "step": 57120 + }, + { + "epoch": 2.12, + "learning_rate": 7.875181314389855e-06, + "loss": 1.6994, + "step": 57130 + }, + { + "epoch": 2.13, + "learning_rate": 7.874809387436308e-06, + "loss": 1.7632, + "step": 57140 + }, + { + "epoch": 2.13, + "learning_rate": 7.874437460482762e-06, + "loss": 1.8068, + "step": 57150 + }, + { + "epoch": 2.13, + "learning_rate": 7.874065533529217e-06, + "loss": 1.6177, + "step": 57160 + }, + { + "epoch": 2.13, + "learning_rate": 7.87369360657567e-06, + "loss": 1.7789, + "step": 57170 + }, + { + "epoch": 2.13, + "learning_rate": 7.873321679622122e-06, + "loss": 1.7606, + "step": 57180 + }, + { + "epoch": 2.13, + "learning_rate": 7.872949752668575e-06, + "loss": 1.7524, + "step": 57190 + }, + { + "epoch": 2.13, + "learning_rate": 7.87257782571503e-06, + "loss": 1.7327, + "step": 57200 + }, + { + "epoch": 2.13, + "eval_loss": 1.699295163154602, + "eval_runtime": 16.8194, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 57200 + }, + { + "epoch": 2.13, + "learning_rate": 7.872205898761484e-06, + "loss": 1.6211, + "step": 57210 + }, + { + "epoch": 2.13, + "learning_rate": 7.871833971807938e-06, + "loss": 1.6909, + "step": 57220 + }, + { + "epoch": 2.13, + "learning_rate": 7.871462044854391e-06, + "loss": 1.6332, + "step": 57230 + }, + { + "epoch": 2.13, + "learning_rate": 7.871090117900844e-06, + "loss": 1.7412, + "step": 57240 + }, + { + "epoch": 2.13, + "learning_rate": 7.870718190947298e-06, + "loss": 1.6858, + "step": 57250 + }, + { + "epoch": 2.13, + "learning_rate": 7.870346263993751e-06, + "loss": 1.8136, + "step": 57260 + }, + { + "epoch": 2.13, + "learning_rate": 7.869974337040207e-06, + "loss": 1.7509, + "step": 57270 + }, + { + "epoch": 2.13, + "learning_rate": 7.86960241008666e-06, + "loss": 1.7496, + "step": 57280 + }, + { + "epoch": 2.13, + "learning_rate": 7.869230483133113e-06, + "loss": 1.7254, + "step": 57290 + }, + { + "epoch": 2.13, + "learning_rate": 7.868858556179567e-06, + "loss": 1.7371, + "step": 57300 + }, + { + "epoch": 2.13, + "eval_loss": 1.700499415397644, + "eval_runtime": 16.812, + "eval_samples_per_second": 59.481, + "eval_steps_per_second": 3.747, + "step": 57300 + }, + { + "epoch": 2.13, + "learning_rate": 7.86848662922602e-06, + "loss": 1.714, + "step": 57310 + }, + { + "epoch": 2.13, + "learning_rate": 7.868114702272474e-06, + "loss": 1.731, + "step": 57320 + }, + { + "epoch": 2.13, + "learning_rate": 7.867742775318929e-06, + "loss": 1.7526, + "step": 57330 + }, + { + "epoch": 2.13, + "learning_rate": 7.867370848365382e-06, + "loss": 1.53, + "step": 57340 + }, + { + "epoch": 2.13, + "learning_rate": 7.866998921411836e-06, + "loss": 1.8098, + "step": 57350 + }, + { + "epoch": 2.13, + "learning_rate": 7.86662699445829e-06, + "loss": 1.6533, + "step": 57360 + }, + { + "epoch": 2.13, + "learning_rate": 7.866255067504743e-06, + "loss": 1.7883, + "step": 57370 + }, + { + "epoch": 2.13, + "learning_rate": 7.865883140551196e-06, + "loss": 1.6846, + "step": 57380 + }, + { + "epoch": 2.13, + "learning_rate": 7.86551121359765e-06, + "loss": 1.8065, + "step": 57390 + }, + { + "epoch": 2.13, + "learning_rate": 7.865139286644103e-06, + "loss": 1.7356, + "step": 57400 + }, + { + "epoch": 2.13, + "eval_loss": 1.6988798379898071, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 57400 + }, + { + "epoch": 2.14, + "learning_rate": 7.864767359690557e-06, + "loss": 1.7051, + "step": 57410 + }, + { + "epoch": 2.14, + "learning_rate": 7.86439543273701e-06, + "loss": 1.8204, + "step": 57420 + }, + { + "epoch": 2.14, + "learning_rate": 7.864023505783465e-06, + "loss": 1.772, + "step": 57430 + }, + { + "epoch": 2.14, + "learning_rate": 7.863651578829919e-06, + "loss": 1.786, + "step": 57440 + }, + { + "epoch": 2.14, + "learning_rate": 7.863279651876372e-06, + "loss": 1.6889, + "step": 57450 + }, + { + "epoch": 2.14, + "learning_rate": 7.862907724922826e-06, + "loss": 1.685, + "step": 57460 + }, + { + "epoch": 2.14, + "learning_rate": 7.862535797969279e-06, + "loss": 1.75, + "step": 57470 + }, + { + "epoch": 2.14, + "learning_rate": 7.862163871015733e-06, + "loss": 1.7175, + "step": 57480 + }, + { + "epoch": 2.14, + "learning_rate": 7.861791944062188e-06, + "loss": 1.5578, + "step": 57490 + }, + { + "epoch": 2.14, + "learning_rate": 7.861420017108641e-06, + "loss": 1.8654, + "step": 57500 + }, + { + "epoch": 2.14, + "eval_loss": 1.697805404663086, + "eval_runtime": 16.828, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 57500 + }, + { + "epoch": 2.14, + "learning_rate": 7.861048090155095e-06, + "loss": 1.6673, + "step": 57510 + }, + { + "epoch": 2.14, + "learning_rate": 7.860676163201548e-06, + "loss": 1.8501, + "step": 57520 + }, + { + "epoch": 2.14, + "learning_rate": 7.860304236248002e-06, + "loss": 1.8032, + "step": 57530 + }, + { + "epoch": 2.14, + "learning_rate": 7.859932309294455e-06, + "loss": 1.9261, + "step": 57540 + }, + { + "epoch": 2.14, + "learning_rate": 7.859560382340908e-06, + "loss": 1.7383, + "step": 57550 + }, + { + "epoch": 2.14, + "learning_rate": 7.859188455387362e-06, + "loss": 1.71, + "step": 57560 + }, + { + "epoch": 2.14, + "learning_rate": 7.858816528433815e-06, + "loss": 1.7346, + "step": 57570 + }, + { + "epoch": 2.14, + "learning_rate": 7.858444601480269e-06, + "loss": 1.74, + "step": 57580 + }, + { + "epoch": 2.14, + "learning_rate": 7.858072674526724e-06, + "loss": 1.6192, + "step": 57590 + }, + { + "epoch": 2.14, + "learning_rate": 7.857700747573177e-06, + "loss": 1.8609, + "step": 57600 + }, + { + "epoch": 2.14, + "eval_loss": 1.6986491680145264, + "eval_runtime": 16.8268, + "eval_samples_per_second": 59.429, + "eval_steps_per_second": 3.744, + "step": 57600 + }, + { + "epoch": 2.14, + "learning_rate": 7.857328820619631e-06, + "loss": 1.7661, + "step": 57610 + }, + { + "epoch": 2.14, + "learning_rate": 7.856956893666084e-06, + "loss": 1.9076, + "step": 57620 + }, + { + "epoch": 2.14, + "learning_rate": 7.856584966712538e-06, + "loss": 1.8105, + "step": 57630 + }, + { + "epoch": 2.14, + "learning_rate": 7.856213039758991e-06, + "loss": 1.6925, + "step": 57640 + }, + { + "epoch": 2.14, + "learning_rate": 7.855841112805446e-06, + "loss": 1.6114, + "step": 57650 + }, + { + "epoch": 2.14, + "learning_rate": 7.8554691858519e-06, + "loss": 1.6867, + "step": 57660 + }, + { + "epoch": 2.14, + "learning_rate": 7.855097258898353e-06, + "loss": 1.6071, + "step": 57670 + }, + { + "epoch": 2.15, + "learning_rate": 7.854725331944807e-06, + "loss": 1.7602, + "step": 57680 + }, + { + "epoch": 2.15, + "learning_rate": 7.85435340499126e-06, + "loss": 1.6714, + "step": 57690 + }, + { + "epoch": 2.15, + "learning_rate": 7.853981478037714e-06, + "loss": 1.6106, + "step": 57700 + }, + { + "epoch": 2.15, + "eval_loss": 1.6982232332229614, + "eval_runtime": 16.8145, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 57700 + }, + { + "epoch": 2.15, + "learning_rate": 7.853609551084169e-06, + "loss": 1.7505, + "step": 57710 + }, + { + "epoch": 2.15, + "learning_rate": 7.853237624130622e-06, + "loss": 1.7693, + "step": 57720 + }, + { + "epoch": 2.15, + "learning_rate": 7.852865697177076e-06, + "loss": 1.6975, + "step": 57730 + }, + { + "epoch": 2.15, + "learning_rate": 7.852493770223528e-06, + "loss": 1.6931, + "step": 57740 + }, + { + "epoch": 2.15, + "learning_rate": 7.852121843269983e-06, + "loss": 1.7711, + "step": 57750 + }, + { + "epoch": 2.15, + "learning_rate": 7.851749916316436e-06, + "loss": 1.7611, + "step": 57760 + }, + { + "epoch": 2.15, + "learning_rate": 7.85137798936289e-06, + "loss": 1.7397, + "step": 57770 + }, + { + "epoch": 2.15, + "learning_rate": 7.851006062409343e-06, + "loss": 1.707, + "step": 57780 + }, + { + "epoch": 2.15, + "learning_rate": 7.850634135455797e-06, + "loss": 1.6894, + "step": 57790 + }, + { + "epoch": 2.15, + "learning_rate": 7.85026220850225e-06, + "loss": 1.5403, + "step": 57800 + }, + { + "epoch": 2.15, + "eval_loss": 1.6988375186920166, + "eval_runtime": 16.8301, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 57800 + }, + { + "epoch": 2.15, + "learning_rate": 7.849890281548705e-06, + "loss": 1.6648, + "step": 57810 + }, + { + "epoch": 2.15, + "learning_rate": 7.849518354595159e-06, + "loss": 1.7364, + "step": 57820 + }, + { + "epoch": 2.15, + "learning_rate": 7.849146427641612e-06, + "loss": 1.6645, + "step": 57830 + }, + { + "epoch": 2.15, + "learning_rate": 7.848774500688066e-06, + "loss": 1.7276, + "step": 57840 + }, + { + "epoch": 2.15, + "learning_rate": 7.848402573734519e-06, + "loss": 1.7439, + "step": 57850 + }, + { + "epoch": 2.15, + "learning_rate": 7.848030646780972e-06, + "loss": 1.7992, + "step": 57860 + }, + { + "epoch": 2.15, + "learning_rate": 7.847658719827426e-06, + "loss": 1.7451, + "step": 57870 + }, + { + "epoch": 2.15, + "learning_rate": 7.847286792873881e-06, + "loss": 1.7717, + "step": 57880 + }, + { + "epoch": 2.15, + "learning_rate": 7.846914865920335e-06, + "loss": 1.7014, + "step": 57890 + }, + { + "epoch": 2.15, + "learning_rate": 7.846542938966788e-06, + "loss": 1.6974, + "step": 57900 + }, + { + "epoch": 2.15, + "eval_loss": 1.6977609395980835, + "eval_runtime": 16.8277, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 57900 + }, + { + "epoch": 2.15, + "learning_rate": 7.846171012013241e-06, + "loss": 1.7448, + "step": 57910 + }, + { + "epoch": 2.15, + "learning_rate": 7.845799085059695e-06, + "loss": 1.7683, + "step": 57920 + }, + { + "epoch": 2.15, + "learning_rate": 7.845427158106148e-06, + "loss": 1.7185, + "step": 57930 + }, + { + "epoch": 2.15, + "learning_rate": 7.845055231152602e-06, + "loss": 1.7692, + "step": 57940 + }, + { + "epoch": 2.16, + "learning_rate": 7.844683304199055e-06, + "loss": 1.6571, + "step": 57950 + }, + { + "epoch": 2.16, + "learning_rate": 7.844311377245509e-06, + "loss": 1.553, + "step": 57960 + }, + { + "epoch": 2.16, + "learning_rate": 7.843939450291962e-06, + "loss": 1.7284, + "step": 57970 + }, + { + "epoch": 2.16, + "learning_rate": 7.843567523338417e-06, + "loss": 1.767, + "step": 57980 + }, + { + "epoch": 2.16, + "learning_rate": 7.843195596384871e-06, + "loss": 1.8025, + "step": 57990 + }, + { + "epoch": 2.16, + "learning_rate": 7.842823669431324e-06, + "loss": 1.7228, + "step": 58000 + }, + { + "epoch": 2.16, + "eval_loss": 1.6975178718566895, + "eval_runtime": 16.8328, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 58000 + }, + { + "epoch": 2.16, + "learning_rate": 7.842451742477778e-06, + "loss": 1.7319, + "step": 58010 + }, + { + "epoch": 2.16, + "learning_rate": 7.842079815524231e-06, + "loss": 1.7738, + "step": 58020 + }, + { + "epoch": 2.16, + "learning_rate": 7.841707888570685e-06, + "loss": 1.8166, + "step": 58030 + }, + { + "epoch": 2.16, + "learning_rate": 7.84133596161714e-06, + "loss": 1.7804, + "step": 58040 + }, + { + "epoch": 2.16, + "learning_rate": 7.840964034663593e-06, + "loss": 1.7904, + "step": 58050 + }, + { + "epoch": 2.16, + "learning_rate": 7.840592107710047e-06, + "loss": 1.6534, + "step": 58060 + }, + { + "epoch": 2.16, + "learning_rate": 7.8402201807565e-06, + "loss": 1.7275, + "step": 58070 + }, + { + "epoch": 2.16, + "learning_rate": 7.839848253802954e-06, + "loss": 1.8174, + "step": 58080 + }, + { + "epoch": 2.16, + "learning_rate": 7.839476326849407e-06, + "loss": 1.5845, + "step": 58090 + }, + { + "epoch": 2.16, + "learning_rate": 7.839104399895862e-06, + "loss": 1.6478, + "step": 58100 + }, + { + "epoch": 2.16, + "eval_loss": 1.696785807609558, + "eval_runtime": 16.8342, + "eval_samples_per_second": 59.403, + "eval_steps_per_second": 3.742, + "step": 58100 + }, + { + "epoch": 2.16, + "learning_rate": 7.838732472942316e-06, + "loss": 1.8094, + "step": 58110 + }, + { + "epoch": 2.16, + "learning_rate": 7.838360545988768e-06, + "loss": 1.7471, + "step": 58120 + }, + { + "epoch": 2.16, + "learning_rate": 7.837988619035221e-06, + "loss": 1.7395, + "step": 58130 + }, + { + "epoch": 2.16, + "learning_rate": 7.837616692081676e-06, + "loss": 1.7731, + "step": 58140 + }, + { + "epoch": 2.16, + "learning_rate": 7.83724476512813e-06, + "loss": 1.7503, + "step": 58150 + }, + { + "epoch": 2.16, + "learning_rate": 7.836872838174583e-06, + "loss": 1.7461, + "step": 58160 + }, + { + "epoch": 2.16, + "learning_rate": 7.836500911221037e-06, + "loss": 1.7387, + "step": 58170 + }, + { + "epoch": 2.16, + "learning_rate": 7.83612898426749e-06, + "loss": 1.6796, + "step": 58180 + }, + { + "epoch": 2.16, + "learning_rate": 7.835757057313943e-06, + "loss": 1.7633, + "step": 58190 + }, + { + "epoch": 2.16, + "learning_rate": 7.835385130360399e-06, + "loss": 1.6933, + "step": 58200 + }, + { + "epoch": 2.16, + "eval_loss": 1.6976828575134277, + "eval_runtime": 16.8188, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 58200 + }, + { + "epoch": 2.16, + "learning_rate": 7.835013203406852e-06, + "loss": 1.7094, + "step": 58210 + }, + { + "epoch": 2.17, + "learning_rate": 7.834641276453305e-06, + "loss": 1.7461, + "step": 58220 + }, + { + "epoch": 2.17, + "learning_rate": 7.834269349499759e-06, + "loss": 1.8643, + "step": 58230 + }, + { + "epoch": 2.17, + "learning_rate": 7.833897422546212e-06, + "loss": 1.7072, + "step": 58240 + }, + { + "epoch": 2.17, + "learning_rate": 7.833525495592666e-06, + "loss": 1.7713, + "step": 58250 + }, + { + "epoch": 2.17, + "learning_rate": 7.833153568639121e-06, + "loss": 1.8621, + "step": 58260 + }, + { + "epoch": 2.17, + "learning_rate": 7.832781641685574e-06, + "loss": 1.6142, + "step": 58270 + }, + { + "epoch": 2.17, + "learning_rate": 7.832409714732028e-06, + "loss": 1.8469, + "step": 58280 + }, + { + "epoch": 2.17, + "learning_rate": 7.832037787778481e-06, + "loss": 1.6902, + "step": 58290 + }, + { + "epoch": 2.17, + "learning_rate": 7.831665860824935e-06, + "loss": 1.6504, + "step": 58300 + }, + { + "epoch": 2.17, + "eval_loss": 1.6975009441375732, + "eval_runtime": 16.803, + "eval_samples_per_second": 59.513, + "eval_steps_per_second": 3.749, + "step": 58300 + }, + { + "epoch": 2.17, + "learning_rate": 7.831293933871388e-06, + "loss": 1.6602, + "step": 58310 + }, + { + "epoch": 2.17, + "learning_rate": 7.830922006917842e-06, + "loss": 1.6384, + "step": 58320 + }, + { + "epoch": 2.17, + "learning_rate": 7.830550079964295e-06, + "loss": 1.8675, + "step": 58330 + }, + { + "epoch": 2.17, + "learning_rate": 7.830178153010749e-06, + "loss": 1.8018, + "step": 58340 + }, + { + "epoch": 2.17, + "learning_rate": 7.829806226057202e-06, + "loss": 1.75, + "step": 58350 + }, + { + "epoch": 2.17, + "learning_rate": 7.829434299103657e-06, + "loss": 1.6958, + "step": 58360 + }, + { + "epoch": 2.17, + "learning_rate": 7.82906237215011e-06, + "loss": 1.8152, + "step": 58370 + }, + { + "epoch": 2.17, + "learning_rate": 7.828690445196564e-06, + "loss": 1.7972, + "step": 58380 + }, + { + "epoch": 2.17, + "learning_rate": 7.828318518243018e-06, + "loss": 1.9258, + "step": 58390 + }, + { + "epoch": 2.17, + "learning_rate": 7.827946591289471e-06, + "loss": 1.693, + "step": 58400 + }, + { + "epoch": 2.17, + "eval_loss": 1.6972291469573975, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 58400 + }, + { + "epoch": 2.17, + "learning_rate": 7.827574664335925e-06, + "loss": 1.727, + "step": 58410 + }, + { + "epoch": 2.17, + "learning_rate": 7.827202737382378e-06, + "loss": 1.7263, + "step": 58420 + }, + { + "epoch": 2.17, + "learning_rate": 7.826830810428833e-06, + "loss": 1.7147, + "step": 58430 + }, + { + "epoch": 2.17, + "learning_rate": 7.826458883475287e-06, + "loss": 1.7299, + "step": 58440 + }, + { + "epoch": 2.17, + "learning_rate": 7.82608695652174e-06, + "loss": 1.6933, + "step": 58450 + }, + { + "epoch": 2.17, + "learning_rate": 7.825715029568194e-06, + "loss": 1.6698, + "step": 58460 + }, + { + "epoch": 2.17, + "learning_rate": 7.825343102614647e-06, + "loss": 1.8647, + "step": 58470 + }, + { + "epoch": 2.18, + "learning_rate": 7.8249711756611e-06, + "loss": 1.7273, + "step": 58480 + }, + { + "epoch": 2.18, + "learning_rate": 7.824599248707554e-06, + "loss": 1.6455, + "step": 58490 + }, + { + "epoch": 2.18, + "learning_rate": 7.824227321754007e-06, + "loss": 1.7648, + "step": 58500 + }, + { + "epoch": 2.18, + "eval_loss": 1.696212887763977, + "eval_runtime": 16.8191, + "eval_samples_per_second": 59.456, + "eval_steps_per_second": 3.746, + "step": 58500 + }, + { + "epoch": 2.18, + "learning_rate": 7.823855394800461e-06, + "loss": 1.7589, + "step": 58510 + }, + { + "epoch": 2.18, + "learning_rate": 7.823483467846914e-06, + "loss": 1.8472, + "step": 58520 + }, + { + "epoch": 2.18, + "learning_rate": 7.82311154089337e-06, + "loss": 1.8575, + "step": 58530 + }, + { + "epoch": 2.18, + "learning_rate": 7.822739613939823e-06, + "loss": 1.7031, + "step": 58540 + }, + { + "epoch": 2.18, + "learning_rate": 7.822367686986276e-06, + "loss": 1.8661, + "step": 58550 + }, + { + "epoch": 2.18, + "learning_rate": 7.82199576003273e-06, + "loss": 1.8258, + "step": 58560 + }, + { + "epoch": 2.18, + "learning_rate": 7.821623833079183e-06, + "loss": 1.6946, + "step": 58570 + }, + { + "epoch": 2.18, + "learning_rate": 7.821251906125637e-06, + "loss": 1.7423, + "step": 58580 + }, + { + "epoch": 2.18, + "learning_rate": 7.820879979172092e-06, + "loss": 1.6759, + "step": 58590 + }, + { + "epoch": 2.18, + "learning_rate": 7.820508052218545e-06, + "loss": 1.6803, + "step": 58600 + }, + { + "epoch": 2.18, + "eval_loss": 1.6956839561462402, + "eval_runtime": 16.862, + "eval_samples_per_second": 59.305, + "eval_steps_per_second": 3.736, + "step": 58600 + }, + { + "epoch": 2.18, + "learning_rate": 7.820136125264999e-06, + "loss": 1.7599, + "step": 58610 + }, + { + "epoch": 2.18, + "learning_rate": 7.819764198311452e-06, + "loss": 1.7535, + "step": 58620 + }, + { + "epoch": 2.18, + "learning_rate": 7.819392271357906e-06, + "loss": 1.6939, + "step": 58630 + }, + { + "epoch": 2.18, + "learning_rate": 7.81902034440436e-06, + "loss": 1.7566, + "step": 58640 + }, + { + "epoch": 2.18, + "learning_rate": 7.818648417450814e-06, + "loss": 1.7331, + "step": 58650 + }, + { + "epoch": 2.18, + "learning_rate": 7.818276490497268e-06, + "loss": 1.7371, + "step": 58660 + }, + { + "epoch": 2.18, + "learning_rate": 7.817904563543721e-06, + "loss": 1.8246, + "step": 58670 + }, + { + "epoch": 2.18, + "learning_rate": 7.817532636590173e-06, + "loss": 1.643, + "step": 58680 + }, + { + "epoch": 2.18, + "learning_rate": 7.817160709636628e-06, + "loss": 1.6641, + "step": 58690 + }, + { + "epoch": 2.18, + "learning_rate": 7.816788782683082e-06, + "loss": 1.6919, + "step": 58700 + }, + { + "epoch": 2.18, + "eval_loss": 1.6961742639541626, + "eval_runtime": 16.8612, + "eval_samples_per_second": 59.308, + "eval_steps_per_second": 3.736, + "step": 58700 + }, + { + "epoch": 2.18, + "learning_rate": 7.816416855729535e-06, + "loss": 1.7776, + "step": 58710 + }, + { + "epoch": 2.18, + "learning_rate": 7.816044928775989e-06, + "loss": 1.9053, + "step": 58720 + }, + { + "epoch": 2.18, + "learning_rate": 7.815673001822442e-06, + "loss": 1.7752, + "step": 58730 + }, + { + "epoch": 2.18, + "learning_rate": 7.815301074868896e-06, + "loss": 1.813, + "step": 58740 + }, + { + "epoch": 2.19, + "learning_rate": 7.81492914791535e-06, + "loss": 1.8847, + "step": 58750 + }, + { + "epoch": 2.19, + "learning_rate": 7.814557220961804e-06, + "loss": 1.7637, + "step": 58760 + }, + { + "epoch": 2.19, + "learning_rate": 7.814185294008258e-06, + "loss": 1.7069, + "step": 58770 + }, + { + "epoch": 2.19, + "learning_rate": 7.813813367054711e-06, + "loss": 1.8955, + "step": 58780 + }, + { + "epoch": 2.19, + "learning_rate": 7.813441440101165e-06, + "loss": 1.6275, + "step": 58790 + }, + { + "epoch": 2.19, + "learning_rate": 7.813069513147618e-06, + "loss": 1.7551, + "step": 58800 + }, + { + "epoch": 2.19, + "eval_loss": 1.6952905654907227, + "eval_runtime": 16.8395, + "eval_samples_per_second": 59.384, + "eval_steps_per_second": 3.741, + "step": 58800 + }, + { + "epoch": 2.19, + "learning_rate": 7.812697586194073e-06, + "loss": 1.6436, + "step": 58810 + }, + { + "epoch": 2.19, + "learning_rate": 7.812325659240527e-06, + "loss": 1.7945, + "step": 58820 + }, + { + "epoch": 2.19, + "learning_rate": 7.81195373228698e-06, + "loss": 1.7824, + "step": 58830 + }, + { + "epoch": 2.19, + "learning_rate": 7.811581805333434e-06, + "loss": 1.7856, + "step": 58840 + }, + { + "epoch": 2.19, + "learning_rate": 7.811209878379887e-06, + "loss": 1.7408, + "step": 58850 + }, + { + "epoch": 2.19, + "learning_rate": 7.81083795142634e-06, + "loss": 1.6367, + "step": 58860 + }, + { + "epoch": 2.19, + "learning_rate": 7.810466024472794e-06, + "loss": 1.8042, + "step": 58870 + }, + { + "epoch": 2.19, + "learning_rate": 7.810094097519247e-06, + "loss": 1.7231, + "step": 58880 + }, + { + "epoch": 2.19, + "learning_rate": 7.8097221705657e-06, + "loss": 1.6112, + "step": 58890 + }, + { + "epoch": 2.19, + "learning_rate": 7.809350243612154e-06, + "loss": 1.6153, + "step": 58900 + }, + { + "epoch": 2.19, + "eval_loss": 1.6957318782806396, + "eval_runtime": 16.8111, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 58900 + }, + { + "epoch": 2.19, + "learning_rate": 7.80897831665861e-06, + "loss": 1.851, + "step": 58910 + }, + { + "epoch": 2.19, + "learning_rate": 7.808606389705063e-06, + "loss": 1.688, + "step": 58920 + }, + { + "epoch": 2.19, + "learning_rate": 7.808234462751516e-06, + "loss": 1.6421, + "step": 58930 + }, + { + "epoch": 2.19, + "learning_rate": 7.80786253579797e-06, + "loss": 1.6903, + "step": 58940 + }, + { + "epoch": 2.19, + "learning_rate": 7.807490608844423e-06, + "loss": 1.7554, + "step": 58950 + }, + { + "epoch": 2.19, + "learning_rate": 7.807118681890877e-06, + "loss": 1.6113, + "step": 58960 + }, + { + "epoch": 2.19, + "learning_rate": 7.806746754937332e-06, + "loss": 1.6373, + "step": 58970 + }, + { + "epoch": 2.19, + "learning_rate": 7.806374827983785e-06, + "loss": 1.6688, + "step": 58980 + }, + { + "epoch": 2.19, + "learning_rate": 7.806002901030239e-06, + "loss": 1.6874, + "step": 58990 + }, + { + "epoch": 2.19, + "learning_rate": 7.805630974076692e-06, + "loss": 1.7707, + "step": 59000 + }, + { + "epoch": 2.19, + "eval_loss": 1.6950836181640625, + "eval_runtime": 16.8391, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 59000 + }, + { + "epoch": 2.19, + "learning_rate": 7.805259047123146e-06, + "loss": 1.6928, + "step": 59010 + }, + { + "epoch": 2.2, + "learning_rate": 7.8048871201696e-06, + "loss": 1.7738, + "step": 59020 + }, + { + "epoch": 2.2, + "learning_rate": 7.804515193216053e-06, + "loss": 1.6721, + "step": 59030 + }, + { + "epoch": 2.2, + "learning_rate": 7.804143266262508e-06, + "loss": 1.8587, + "step": 59040 + }, + { + "epoch": 2.2, + "learning_rate": 7.803771339308961e-06, + "loss": 1.791, + "step": 59050 + }, + { + "epoch": 2.2, + "learning_rate": 7.803399412355413e-06, + "loss": 1.7366, + "step": 59060 + }, + { + "epoch": 2.2, + "learning_rate": 7.803027485401866e-06, + "loss": 1.6355, + "step": 59070 + }, + { + "epoch": 2.2, + "learning_rate": 7.802655558448322e-06, + "loss": 1.7696, + "step": 59080 + }, + { + "epoch": 2.2, + "learning_rate": 7.802283631494775e-06, + "loss": 1.6723, + "step": 59090 + }, + { + "epoch": 2.2, + "learning_rate": 7.801911704541229e-06, + "loss": 1.7487, + "step": 59100 + }, + { + "epoch": 2.2, + "eval_loss": 1.6956578493118286, + "eval_runtime": 16.8211, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 59100 + }, + { + "epoch": 2.2, + "learning_rate": 7.801539777587682e-06, + "loss": 1.7248, + "step": 59110 + }, + { + "epoch": 2.2, + "learning_rate": 7.801167850634135e-06, + "loss": 1.6361, + "step": 59120 + }, + { + "epoch": 2.2, + "learning_rate": 7.800795923680589e-06, + "loss": 1.7581, + "step": 59130 + }, + { + "epoch": 2.2, + "learning_rate": 7.800423996727044e-06, + "loss": 1.7663, + "step": 59140 + }, + { + "epoch": 2.2, + "learning_rate": 7.800052069773498e-06, + "loss": 1.6444, + "step": 59150 + }, + { + "epoch": 2.2, + "learning_rate": 7.799680142819951e-06, + "loss": 1.7926, + "step": 59160 + }, + { + "epoch": 2.2, + "learning_rate": 7.799308215866404e-06, + "loss": 1.7616, + "step": 59170 + }, + { + "epoch": 2.2, + "learning_rate": 7.798936288912858e-06, + "loss": 1.7679, + "step": 59180 + }, + { + "epoch": 2.2, + "learning_rate": 7.798564361959311e-06, + "loss": 1.764, + "step": 59190 + }, + { + "epoch": 2.2, + "learning_rate": 7.798192435005767e-06, + "loss": 1.8495, + "step": 59200 + }, + { + "epoch": 2.2, + "eval_loss": 1.6964040994644165, + "eval_runtime": 16.8171, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 59200 + }, + { + "epoch": 2.2, + "learning_rate": 7.79782050805222e-06, + "loss": 1.7932, + "step": 59210 + }, + { + "epoch": 2.2, + "learning_rate": 7.797448581098673e-06, + "loss": 1.7594, + "step": 59220 + }, + { + "epoch": 2.2, + "learning_rate": 7.797076654145127e-06, + "loss": 1.7562, + "step": 59230 + }, + { + "epoch": 2.2, + "learning_rate": 7.79670472719158e-06, + "loss": 1.5573, + "step": 59240 + }, + { + "epoch": 2.2, + "learning_rate": 7.796332800238034e-06, + "loss": 1.6786, + "step": 59250 + }, + { + "epoch": 2.2, + "learning_rate": 7.795960873284487e-06, + "loss": 1.8121, + "step": 59260 + }, + { + "epoch": 2.2, + "learning_rate": 7.79558894633094e-06, + "loss": 1.7753, + "step": 59270 + }, + { + "epoch": 2.2, + "learning_rate": 7.795217019377394e-06, + "loss": 1.752, + "step": 59280 + }, + { + "epoch": 2.21, + "learning_rate": 7.794845092423848e-06, + "loss": 1.8218, + "step": 59290 + }, + { + "epoch": 2.21, + "learning_rate": 7.794473165470303e-06, + "loss": 1.6963, + "step": 59300 + }, + { + "epoch": 2.21, + "eval_loss": 1.695420503616333, + "eval_runtime": 16.8274, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 59300 + }, + { + "epoch": 2.21, + "learning_rate": 7.794101238516756e-06, + "loss": 1.711, + "step": 59310 + }, + { + "epoch": 2.21, + "learning_rate": 7.79372931156321e-06, + "loss": 1.7448, + "step": 59320 + }, + { + "epoch": 2.21, + "learning_rate": 7.793357384609663e-06, + "loss": 1.6901, + "step": 59330 + }, + { + "epoch": 2.21, + "learning_rate": 7.792985457656117e-06, + "loss": 1.8461, + "step": 59340 + }, + { + "epoch": 2.21, + "learning_rate": 7.79261353070257e-06, + "loss": 1.8205, + "step": 59350 + }, + { + "epoch": 2.21, + "learning_rate": 7.792241603749025e-06, + "loss": 1.6845, + "step": 59360 + }, + { + "epoch": 2.21, + "learning_rate": 7.791869676795479e-06, + "loss": 1.6494, + "step": 59370 + }, + { + "epoch": 2.21, + "learning_rate": 7.791497749841932e-06, + "loss": 1.6738, + "step": 59380 + }, + { + "epoch": 2.21, + "learning_rate": 7.791125822888386e-06, + "loss": 1.7403, + "step": 59390 + }, + { + "epoch": 2.21, + "learning_rate": 7.790753895934839e-06, + "loss": 1.7231, + "step": 59400 + }, + { + "epoch": 2.21, + "eval_loss": 1.695499062538147, + "eval_runtime": 16.8234, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 59400 + }, + { + "epoch": 2.21, + "learning_rate": 7.790381968981293e-06, + "loss": 1.7024, + "step": 59410 + }, + { + "epoch": 2.21, + "learning_rate": 7.790010042027748e-06, + "loss": 1.7059, + "step": 59420 + }, + { + "epoch": 2.21, + "learning_rate": 7.7896381150742e-06, + "loss": 1.8156, + "step": 59430 + }, + { + "epoch": 2.21, + "learning_rate": 7.789266188120653e-06, + "loss": 1.771, + "step": 59440 + }, + { + "epoch": 2.21, + "learning_rate": 7.788894261167106e-06, + "loss": 1.8683, + "step": 59450 + }, + { + "epoch": 2.21, + "learning_rate": 7.788522334213562e-06, + "loss": 1.7331, + "step": 59460 + }, + { + "epoch": 2.21, + "learning_rate": 7.788150407260015e-06, + "loss": 1.7449, + "step": 59470 + }, + { + "epoch": 2.21, + "learning_rate": 7.787778480306468e-06, + "loss": 1.7713, + "step": 59480 + }, + { + "epoch": 2.21, + "learning_rate": 7.787406553352922e-06, + "loss": 1.7502, + "step": 59490 + }, + { + "epoch": 2.21, + "learning_rate": 7.787034626399375e-06, + "loss": 1.6449, + "step": 59500 + }, + { + "epoch": 2.21, + "eval_loss": 1.6952303647994995, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 59500 + }, + { + "epoch": 2.21, + "learning_rate": 7.786662699445829e-06, + "loss": 1.7719, + "step": 59510 + }, + { + "epoch": 2.21, + "learning_rate": 7.786290772492284e-06, + "loss": 1.6944, + "step": 59520 + }, + { + "epoch": 2.21, + "learning_rate": 7.785918845538737e-06, + "loss": 1.7042, + "step": 59530 + }, + { + "epoch": 2.21, + "learning_rate": 7.785546918585191e-06, + "loss": 1.6887, + "step": 59540 + }, + { + "epoch": 2.21, + "learning_rate": 7.785174991631644e-06, + "loss": 1.6647, + "step": 59550 + }, + { + "epoch": 2.22, + "learning_rate": 7.784803064678098e-06, + "loss": 1.7656, + "step": 59560 + }, + { + "epoch": 2.22, + "learning_rate": 7.784431137724551e-06, + "loss": 1.7082, + "step": 59570 + }, + { + "epoch": 2.22, + "learning_rate": 7.784059210771005e-06, + "loss": 1.827, + "step": 59580 + }, + { + "epoch": 2.22, + "learning_rate": 7.78368728381746e-06, + "loss": 1.7948, + "step": 59590 + }, + { + "epoch": 2.22, + "learning_rate": 7.783315356863913e-06, + "loss": 1.6718, + "step": 59600 + }, + { + "epoch": 2.22, + "eval_loss": 1.6947680711746216, + "eval_runtime": 16.8109, + "eval_samples_per_second": 59.485, + "eval_steps_per_second": 3.748, + "step": 59600 + }, + { + "epoch": 2.22, + "learning_rate": 7.782943429910367e-06, + "loss": 1.7026, + "step": 59610 + }, + { + "epoch": 2.22, + "learning_rate": 7.782571502956819e-06, + "loss": 1.7558, + "step": 59620 + }, + { + "epoch": 2.22, + "learning_rate": 7.782199576003274e-06, + "loss": 1.7468, + "step": 59630 + }, + { + "epoch": 2.22, + "learning_rate": 7.781827649049727e-06, + "loss": 1.7206, + "step": 59640 + }, + { + "epoch": 2.22, + "learning_rate": 7.78145572209618e-06, + "loss": 1.8833, + "step": 59650 + }, + { + "epoch": 2.22, + "learning_rate": 7.781083795142634e-06, + "loss": 1.6647, + "step": 59660 + }, + { + "epoch": 2.22, + "learning_rate": 7.780711868189088e-06, + "loss": 1.8306, + "step": 59670 + }, + { + "epoch": 2.22, + "learning_rate": 7.780339941235541e-06, + "loss": 1.8575, + "step": 59680 + }, + { + "epoch": 2.22, + "learning_rate": 7.779968014281996e-06, + "loss": 1.7886, + "step": 59690 + }, + { + "epoch": 2.22, + "learning_rate": 7.77959608732845e-06, + "loss": 1.7931, + "step": 59700 + }, + { + "epoch": 2.22, + "eval_loss": 1.6937663555145264, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 59700 + }, + { + "epoch": 2.22, + "learning_rate": 7.779224160374903e-06, + "loss": 1.7382, + "step": 59710 + }, + { + "epoch": 2.22, + "learning_rate": 7.778852233421357e-06, + "loss": 1.6707, + "step": 59720 + }, + { + "epoch": 2.22, + "learning_rate": 7.77848030646781e-06, + "loss": 1.749, + "step": 59730 + }, + { + "epoch": 2.22, + "learning_rate": 7.778108379514263e-06, + "loss": 1.6982, + "step": 59740 + }, + { + "epoch": 2.22, + "learning_rate": 7.777736452560719e-06, + "loss": 1.7851, + "step": 59750 + }, + { + "epoch": 2.22, + "learning_rate": 7.777364525607172e-06, + "loss": 1.7416, + "step": 59760 + }, + { + "epoch": 2.22, + "learning_rate": 7.776992598653626e-06, + "loss": 1.9468, + "step": 59770 + }, + { + "epoch": 2.22, + "learning_rate": 7.776620671700079e-06, + "loss": 1.6668, + "step": 59780 + }, + { + "epoch": 2.22, + "learning_rate": 7.776248744746532e-06, + "loss": 1.7172, + "step": 59790 + }, + { + "epoch": 2.22, + "learning_rate": 7.775876817792986e-06, + "loss": 1.6923, + "step": 59800 + }, + { + "epoch": 2.22, + "eval_loss": 1.6944752931594849, + "eval_runtime": 16.8268, + "eval_samples_per_second": 59.429, + "eval_steps_per_second": 3.744, + "step": 59800 + }, + { + "epoch": 2.22, + "learning_rate": 7.77550489083944e-06, + "loss": 1.6414, + "step": 59810 + }, + { + "epoch": 2.22, + "learning_rate": 7.775132963885893e-06, + "loss": 1.6381, + "step": 59820 + }, + { + "epoch": 2.23, + "learning_rate": 7.774761036932346e-06, + "loss": 1.7379, + "step": 59830 + }, + { + "epoch": 2.23, + "learning_rate": 7.7743891099788e-06, + "loss": 1.7284, + "step": 59840 + }, + { + "epoch": 2.23, + "learning_rate": 7.774017183025255e-06, + "loss": 1.7517, + "step": 59850 + }, + { + "epoch": 2.23, + "learning_rate": 7.773645256071708e-06, + "loss": 1.6749, + "step": 59860 + }, + { + "epoch": 2.23, + "learning_rate": 7.773273329118162e-06, + "loss": 1.7811, + "step": 59870 + }, + { + "epoch": 2.23, + "learning_rate": 7.772901402164615e-06, + "loss": 1.6847, + "step": 59880 + }, + { + "epoch": 2.23, + "learning_rate": 7.772529475211069e-06, + "loss": 1.8184, + "step": 59890 + }, + { + "epoch": 2.23, + "learning_rate": 7.772157548257522e-06, + "loss": 1.8402, + "step": 59900 + }, + { + "epoch": 2.23, + "eval_loss": 1.6944780349731445, + "eval_runtime": 16.8336, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 59900 + }, + { + "epoch": 2.23, + "learning_rate": 7.771785621303977e-06, + "loss": 1.8003, + "step": 59910 + }, + { + "epoch": 2.23, + "learning_rate": 7.77141369435043e-06, + "loss": 1.7606, + "step": 59920 + }, + { + "epoch": 2.23, + "learning_rate": 7.771041767396884e-06, + "loss": 1.722, + "step": 59930 + }, + { + "epoch": 2.23, + "learning_rate": 7.770669840443338e-06, + "loss": 1.7829, + "step": 59940 + }, + { + "epoch": 2.23, + "learning_rate": 7.770297913489791e-06, + "loss": 1.7633, + "step": 59950 + }, + { + "epoch": 2.23, + "learning_rate": 7.769925986536245e-06, + "loss": 1.7824, + "step": 59960 + }, + { + "epoch": 2.23, + "learning_rate": 7.7695540595827e-06, + "loss": 1.7787, + "step": 59970 + }, + { + "epoch": 2.23, + "learning_rate": 7.769182132629153e-06, + "loss": 1.7751, + "step": 59980 + }, + { + "epoch": 2.23, + "learning_rate": 7.768810205675605e-06, + "loss": 1.8262, + "step": 59990 + }, + { + "epoch": 2.23, + "learning_rate": 7.768438278722058e-06, + "loss": 1.8234, + "step": 60000 + }, + { + "epoch": 2.23, + "eval_loss": 1.6939507722854614, + "eval_runtime": 16.8256, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 60000 + }, + { + "epoch": 2.23, + "learning_rate": 7.768066351768514e-06, + "loss": 1.7545, + "step": 60010 + }, + { + "epoch": 2.23, + "learning_rate": 7.767694424814967e-06, + "loss": 1.7028, + "step": 60020 + }, + { + "epoch": 2.23, + "learning_rate": 7.76732249786142e-06, + "loss": 1.8603, + "step": 60030 + }, + { + "epoch": 2.23, + "learning_rate": 7.766950570907874e-06, + "loss": 1.8603, + "step": 60040 + }, + { + "epoch": 2.23, + "learning_rate": 7.766578643954327e-06, + "loss": 1.7375, + "step": 60050 + }, + { + "epoch": 2.23, + "learning_rate": 7.766206717000781e-06, + "loss": 1.8026, + "step": 60060 + }, + { + "epoch": 2.23, + "learning_rate": 7.765834790047236e-06, + "loss": 1.7697, + "step": 60070 + }, + { + "epoch": 2.23, + "learning_rate": 7.76546286309369e-06, + "loss": 1.8031, + "step": 60080 + }, + { + "epoch": 2.23, + "learning_rate": 7.765090936140143e-06, + "loss": 1.7027, + "step": 60090 + }, + { + "epoch": 2.24, + "learning_rate": 7.764719009186596e-06, + "loss": 1.8395, + "step": 60100 + }, + { + "epoch": 2.24, + "eval_loss": 1.6936750411987305, + "eval_runtime": 16.8236, + "eval_samples_per_second": 59.44, + "eval_steps_per_second": 3.745, + "step": 60100 + }, + { + "epoch": 2.24, + "learning_rate": 7.76434708223305e-06, + "loss": 1.6453, + "step": 60110 + }, + { + "epoch": 2.24, + "learning_rate": 7.763975155279503e-06, + "loss": 1.7118, + "step": 60120 + }, + { + "epoch": 2.24, + "learning_rate": 7.763603228325957e-06, + "loss": 1.6483, + "step": 60130 + }, + { + "epoch": 2.24, + "learning_rate": 7.763231301372412e-06, + "loss": 1.8574, + "step": 60140 + }, + { + "epoch": 2.24, + "learning_rate": 7.762859374418865e-06, + "loss": 1.7519, + "step": 60150 + }, + { + "epoch": 2.24, + "learning_rate": 7.762487447465319e-06, + "loss": 1.8048, + "step": 60160 + }, + { + "epoch": 2.24, + "learning_rate": 7.762115520511772e-06, + "loss": 1.6052, + "step": 60170 + }, + { + "epoch": 2.24, + "learning_rate": 7.761743593558226e-06, + "loss": 1.8342, + "step": 60180 + }, + { + "epoch": 2.24, + "learning_rate": 7.76137166660468e-06, + "loss": 1.7234, + "step": 60190 + }, + { + "epoch": 2.24, + "learning_rate": 7.760999739651133e-06, + "loss": 1.7624, + "step": 60200 + }, + { + "epoch": 2.24, + "eval_loss": 1.6937978267669678, + "eval_runtime": 16.8359, + "eval_samples_per_second": 59.397, + "eval_steps_per_second": 3.742, + "step": 60200 + }, + { + "epoch": 2.24, + "learning_rate": 7.760627812697586e-06, + "loss": 1.6778, + "step": 60210 + }, + { + "epoch": 2.24, + "learning_rate": 7.76025588574404e-06, + "loss": 1.8501, + "step": 60220 + }, + { + "epoch": 2.24, + "learning_rate": 7.759883958790493e-06, + "loss": 1.9042, + "step": 60230 + }, + { + "epoch": 2.24, + "learning_rate": 7.759512031836948e-06, + "loss": 1.653, + "step": 60240 + }, + { + "epoch": 2.24, + "learning_rate": 7.759140104883402e-06, + "loss": 1.7196, + "step": 60250 + }, + { + "epoch": 2.24, + "learning_rate": 7.758768177929855e-06, + "loss": 1.5985, + "step": 60260 + }, + { + "epoch": 2.24, + "learning_rate": 7.758396250976309e-06, + "loss": 1.6756, + "step": 60270 + }, + { + "epoch": 2.24, + "learning_rate": 7.758024324022762e-06, + "loss": 1.7463, + "step": 60280 + }, + { + "epoch": 2.24, + "learning_rate": 7.757652397069216e-06, + "loss": 1.8294, + "step": 60290 + }, + { + "epoch": 2.24, + "learning_rate": 7.75728047011567e-06, + "loss": 1.7083, + "step": 60300 + }, + { + "epoch": 2.24, + "eval_loss": 1.6941887140274048, + "eval_runtime": 16.8349, + "eval_samples_per_second": 59.401, + "eval_steps_per_second": 3.742, + "step": 60300 + }, + { + "epoch": 2.24, + "learning_rate": 7.756908543162124e-06, + "loss": 1.7722, + "step": 60310 + }, + { + "epoch": 2.24, + "learning_rate": 7.756536616208578e-06, + "loss": 1.7678, + "step": 60320 + }, + { + "epoch": 2.24, + "learning_rate": 7.756164689255031e-06, + "loss": 1.7058, + "step": 60330 + }, + { + "epoch": 2.24, + "learning_rate": 7.755792762301485e-06, + "loss": 1.677, + "step": 60340 + }, + { + "epoch": 2.24, + "learning_rate": 7.755420835347938e-06, + "loss": 1.6981, + "step": 60350 + }, + { + "epoch": 2.24, + "learning_rate": 7.755048908394393e-06, + "loss": 1.7807, + "step": 60360 + }, + { + "epoch": 2.25, + "learning_rate": 7.754676981440845e-06, + "loss": 1.6136, + "step": 60370 + }, + { + "epoch": 2.25, + "learning_rate": 7.754305054487298e-06, + "loss": 1.7733, + "step": 60380 + }, + { + "epoch": 2.25, + "learning_rate": 7.753933127533752e-06, + "loss": 1.7868, + "step": 60390 + }, + { + "epoch": 2.25, + "learning_rate": 7.753561200580207e-06, + "loss": 1.7962, + "step": 60400 + }, + { + "epoch": 2.25, + "eval_loss": 1.6948754787445068, + "eval_runtime": 16.8362, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 60400 + }, + { + "epoch": 2.25, + "learning_rate": 7.75318927362666e-06, + "loss": 1.5865, + "step": 60410 + }, + { + "epoch": 2.25, + "learning_rate": 7.752817346673114e-06, + "loss": 1.7876, + "step": 60420 + }, + { + "epoch": 2.25, + "learning_rate": 7.752445419719567e-06, + "loss": 1.707, + "step": 60430 + }, + { + "epoch": 2.25, + "learning_rate": 7.752073492766021e-06, + "loss": 1.6275, + "step": 60440 + }, + { + "epoch": 2.25, + "learning_rate": 7.751701565812474e-06, + "loss": 1.6628, + "step": 60450 + }, + { + "epoch": 2.25, + "learning_rate": 7.75132963885893e-06, + "loss": 1.7637, + "step": 60460 + }, + { + "epoch": 2.25, + "learning_rate": 7.750957711905383e-06, + "loss": 1.9554, + "step": 60470 + }, + { + "epoch": 2.25, + "learning_rate": 7.750585784951836e-06, + "loss": 1.825, + "step": 60480 + }, + { + "epoch": 2.25, + "learning_rate": 7.75021385799829e-06, + "loss": 1.645, + "step": 60490 + }, + { + "epoch": 2.25, + "learning_rate": 7.749841931044743e-06, + "loss": 1.6679, + "step": 60500 + }, + { + "epoch": 2.25, + "eval_loss": 1.6930561065673828, + "eval_runtime": 16.8196, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 60500 + }, + { + "epoch": 2.25, + "learning_rate": 7.749470004091197e-06, + "loss": 1.7744, + "step": 60510 + }, + { + "epoch": 2.25, + "learning_rate": 7.749098077137652e-06, + "loss": 1.8001, + "step": 60520 + }, + { + "epoch": 2.25, + "learning_rate": 7.748726150184105e-06, + "loss": 1.5935, + "step": 60530 + }, + { + "epoch": 2.25, + "learning_rate": 7.748354223230559e-06, + "loss": 1.6542, + "step": 60540 + }, + { + "epoch": 2.25, + "learning_rate": 7.747982296277012e-06, + "loss": 1.7607, + "step": 60550 + }, + { + "epoch": 2.25, + "learning_rate": 7.747610369323466e-06, + "loss": 1.7793, + "step": 60560 + }, + { + "epoch": 2.25, + "learning_rate": 7.74723844236992e-06, + "loss": 1.9041, + "step": 60570 + }, + { + "epoch": 2.25, + "learning_rate": 7.746866515416373e-06, + "loss": 1.7424, + "step": 60580 + }, + { + "epoch": 2.25, + "learning_rate": 7.746494588462826e-06, + "loss": 1.785, + "step": 60590 + }, + { + "epoch": 2.25, + "learning_rate": 7.74612266150928e-06, + "loss": 1.7514, + "step": 60600 + }, + { + "epoch": 2.25, + "eval_loss": 1.6930607557296753, + "eval_runtime": 16.8326, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 60600 + }, + { + "epoch": 2.25, + "learning_rate": 7.745750734555733e-06, + "loss": 1.6685, + "step": 60610 + }, + { + "epoch": 2.25, + "learning_rate": 7.745378807602188e-06, + "loss": 1.6717, + "step": 60620 + }, + { + "epoch": 2.25, + "learning_rate": 7.745006880648642e-06, + "loss": 1.8006, + "step": 60630 + }, + { + "epoch": 2.26, + "learning_rate": 7.744634953695095e-06, + "loss": 1.82, + "step": 60640 + }, + { + "epoch": 2.26, + "learning_rate": 7.744263026741549e-06, + "loss": 1.8909, + "step": 60650 + }, + { + "epoch": 2.26, + "learning_rate": 7.743891099788002e-06, + "loss": 1.7436, + "step": 60660 + }, + { + "epoch": 2.26, + "learning_rate": 7.743519172834456e-06, + "loss": 1.7933, + "step": 60670 + }, + { + "epoch": 2.26, + "learning_rate": 7.74314724588091e-06, + "loss": 1.8101, + "step": 60680 + }, + { + "epoch": 2.26, + "learning_rate": 7.742775318927364e-06, + "loss": 1.7791, + "step": 60690 + }, + { + "epoch": 2.26, + "learning_rate": 7.742403391973818e-06, + "loss": 1.6984, + "step": 60700 + }, + { + "epoch": 2.26, + "eval_loss": 1.693002462387085, + "eval_runtime": 16.8114, + "eval_samples_per_second": 59.483, + "eval_steps_per_second": 3.747, + "step": 60700 + }, + { + "epoch": 2.26, + "learning_rate": 7.742031465020271e-06, + "loss": 1.7436, + "step": 60710 + }, + { + "epoch": 2.26, + "learning_rate": 7.741659538066724e-06, + "loss": 1.8257, + "step": 60720 + }, + { + "epoch": 2.26, + "learning_rate": 7.741287611113178e-06, + "loss": 1.7706, + "step": 60730 + }, + { + "epoch": 2.26, + "learning_rate": 7.740915684159631e-06, + "loss": 1.7661, + "step": 60740 + }, + { + "epoch": 2.26, + "learning_rate": 7.740543757206085e-06, + "loss": 1.7241, + "step": 60750 + }, + { + "epoch": 2.26, + "learning_rate": 7.740171830252538e-06, + "loss": 1.7902, + "step": 60760 + }, + { + "epoch": 2.26, + "learning_rate": 7.739799903298992e-06, + "loss": 1.658, + "step": 60770 + }, + { + "epoch": 2.26, + "learning_rate": 7.739427976345445e-06, + "loss": 1.8516, + "step": 60780 + }, + { + "epoch": 2.26, + "learning_rate": 7.7390560493919e-06, + "loss": 1.7086, + "step": 60790 + }, + { + "epoch": 2.26, + "learning_rate": 7.738684122438354e-06, + "loss": 1.6411, + "step": 60800 + }, + { + "epoch": 2.26, + "eval_loss": 1.6940724849700928, + "eval_runtime": 16.8223, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 60800 + }, + { + "epoch": 2.26, + "learning_rate": 7.738312195484807e-06, + "loss": 1.7819, + "step": 60810 + }, + { + "epoch": 2.26, + "learning_rate": 7.73794026853126e-06, + "loss": 1.6966, + "step": 60820 + }, + { + "epoch": 2.26, + "learning_rate": 7.737568341577714e-06, + "loss": 1.7463, + "step": 60830 + }, + { + "epoch": 2.26, + "learning_rate": 7.737196414624168e-06, + "loss": 1.7343, + "step": 60840 + }, + { + "epoch": 2.26, + "learning_rate": 7.736824487670623e-06, + "loss": 1.7909, + "step": 60850 + }, + { + "epoch": 2.26, + "learning_rate": 7.736452560717076e-06, + "loss": 1.8012, + "step": 60860 + }, + { + "epoch": 2.26, + "learning_rate": 7.73608063376353e-06, + "loss": 1.7007, + "step": 60870 + }, + { + "epoch": 2.26, + "learning_rate": 7.735708706809983e-06, + "loss": 1.6614, + "step": 60880 + }, + { + "epoch": 2.26, + "learning_rate": 7.735336779856437e-06, + "loss": 1.7471, + "step": 60890 + }, + { + "epoch": 2.27, + "learning_rate": 7.73496485290289e-06, + "loss": 1.9289, + "step": 60900 + }, + { + "epoch": 2.27, + "eval_loss": 1.694024682044983, + "eval_runtime": 16.8321, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 60900 + }, + { + "epoch": 2.27, + "learning_rate": 7.734592925949345e-06, + "loss": 1.7255, + "step": 60910 + }, + { + "epoch": 2.27, + "learning_rate": 7.734220998995799e-06, + "loss": 1.6193, + "step": 60920 + }, + { + "epoch": 2.27, + "learning_rate": 7.73384907204225e-06, + "loss": 1.7711, + "step": 60930 + }, + { + "epoch": 2.27, + "learning_rate": 7.733477145088704e-06, + "loss": 1.6417, + "step": 60940 + }, + { + "epoch": 2.27, + "learning_rate": 7.733105218135159e-06, + "loss": 1.8213, + "step": 60950 + }, + { + "epoch": 2.27, + "learning_rate": 7.732733291181613e-06, + "loss": 1.7271, + "step": 60960 + }, + { + "epoch": 2.27, + "learning_rate": 7.732361364228066e-06, + "loss": 1.6122, + "step": 60970 + }, + { + "epoch": 2.27, + "learning_rate": 7.73198943727452e-06, + "loss": 1.7624, + "step": 60980 + }, + { + "epoch": 2.27, + "learning_rate": 7.731617510320973e-06, + "loss": 1.7733, + "step": 60990 + }, + { + "epoch": 2.27, + "learning_rate": 7.731245583367426e-06, + "loss": 1.6693, + "step": 61000 + }, + { + "epoch": 2.27, + "eval_loss": 1.6928789615631104, + "eval_runtime": 16.828, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 61000 + }, + { + "epoch": 2.27, + "learning_rate": 7.730873656413882e-06, + "loss": 1.8679, + "step": 61010 + }, + { + "epoch": 2.27, + "learning_rate": 7.730501729460335e-06, + "loss": 1.8319, + "step": 61020 + }, + { + "epoch": 2.27, + "learning_rate": 7.730129802506789e-06, + "loss": 1.7721, + "step": 61030 + }, + { + "epoch": 2.27, + "learning_rate": 7.729757875553242e-06, + "loss": 1.717, + "step": 61040 + }, + { + "epoch": 2.27, + "learning_rate": 7.729385948599695e-06, + "loss": 1.7793, + "step": 61050 + }, + { + "epoch": 2.27, + "learning_rate": 7.729014021646149e-06, + "loss": 1.6113, + "step": 61060 + }, + { + "epoch": 2.27, + "learning_rate": 7.728642094692604e-06, + "loss": 1.7852, + "step": 61070 + }, + { + "epoch": 2.27, + "learning_rate": 7.728270167739057e-06, + "loss": 1.7155, + "step": 61080 + }, + { + "epoch": 2.27, + "learning_rate": 7.727898240785511e-06, + "loss": 1.65, + "step": 61090 + }, + { + "epoch": 2.27, + "learning_rate": 7.727526313831964e-06, + "loss": 1.72, + "step": 61100 + }, + { + "epoch": 2.27, + "eval_loss": 1.6924692392349243, + "eval_runtime": 16.8472, + "eval_samples_per_second": 59.357, + "eval_steps_per_second": 3.739, + "step": 61100 + }, + { + "epoch": 2.27, + "learning_rate": 7.727154386878418e-06, + "loss": 1.6708, + "step": 61110 + }, + { + "epoch": 2.27, + "learning_rate": 7.726782459924871e-06, + "loss": 1.7598, + "step": 61120 + }, + { + "epoch": 2.27, + "learning_rate": 7.726410532971325e-06, + "loss": 1.6917, + "step": 61130 + }, + { + "epoch": 2.27, + "learning_rate": 7.726038606017778e-06, + "loss": 1.8602, + "step": 61140 + }, + { + "epoch": 2.27, + "learning_rate": 7.725666679064232e-06, + "loss": 1.8763, + "step": 61150 + }, + { + "epoch": 2.27, + "learning_rate": 7.725294752110685e-06, + "loss": 1.6605, + "step": 61160 + }, + { + "epoch": 2.28, + "learning_rate": 7.72492282515714e-06, + "loss": 1.6645, + "step": 61170 + }, + { + "epoch": 2.28, + "learning_rate": 7.724550898203594e-06, + "loss": 1.7435, + "step": 61180 + }, + { + "epoch": 2.28, + "learning_rate": 7.724178971250047e-06, + "loss": 1.7781, + "step": 61190 + }, + { + "epoch": 2.28, + "learning_rate": 7.7238070442965e-06, + "loss": 1.6735, + "step": 61200 + }, + { + "epoch": 2.28, + "eval_loss": 1.6931252479553223, + "eval_runtime": 16.8536, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 61200 + }, + { + "epoch": 2.28, + "learning_rate": 7.723435117342954e-06, + "loss": 1.7277, + "step": 61210 + }, + { + "epoch": 2.28, + "learning_rate": 7.723063190389408e-06, + "loss": 1.7458, + "step": 61220 + }, + { + "epoch": 2.28, + "learning_rate": 7.722691263435863e-06, + "loss": 1.7317, + "step": 61230 + }, + { + "epoch": 2.28, + "learning_rate": 7.722319336482316e-06, + "loss": 1.7899, + "step": 61240 + }, + { + "epoch": 2.28, + "learning_rate": 7.72194740952877e-06, + "loss": 1.7704, + "step": 61250 + }, + { + "epoch": 2.28, + "learning_rate": 7.721575482575223e-06, + "loss": 1.6865, + "step": 61260 + }, + { + "epoch": 2.28, + "learning_rate": 7.721203555621677e-06, + "loss": 1.7147, + "step": 61270 + }, + { + "epoch": 2.28, + "learning_rate": 7.72083162866813e-06, + "loss": 1.7325, + "step": 61280 + }, + { + "epoch": 2.28, + "learning_rate": 7.720459701714584e-06, + "loss": 1.785, + "step": 61290 + }, + { + "epoch": 2.28, + "learning_rate": 7.720087774761039e-06, + "loss": 1.8866, + "step": 61300 + }, + { + "epoch": 2.28, + "eval_loss": 1.6933881044387817, + "eval_runtime": 16.8384, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 61300 + }, + { + "epoch": 2.28, + "learning_rate": 7.71971584780749e-06, + "loss": 1.7774, + "step": 61310 + }, + { + "epoch": 2.28, + "learning_rate": 7.719343920853944e-06, + "loss": 1.6772, + "step": 61320 + }, + { + "epoch": 2.28, + "learning_rate": 7.718971993900397e-06, + "loss": 1.7177, + "step": 61330 + }, + { + "epoch": 2.28, + "learning_rate": 7.718600066946853e-06, + "loss": 1.7468, + "step": 61340 + }, + { + "epoch": 2.28, + "learning_rate": 7.718228139993306e-06, + "loss": 1.7609, + "step": 61350 + }, + { + "epoch": 2.28, + "learning_rate": 7.71785621303976e-06, + "loss": 1.7738, + "step": 61360 + }, + { + "epoch": 2.28, + "learning_rate": 7.717484286086213e-06, + "loss": 1.724, + "step": 61370 + }, + { + "epoch": 2.28, + "learning_rate": 7.717112359132666e-06, + "loss": 1.7534, + "step": 61380 + }, + { + "epoch": 2.28, + "learning_rate": 7.71674043217912e-06, + "loss": 1.816, + "step": 61390 + }, + { + "epoch": 2.28, + "learning_rate": 7.716368505225575e-06, + "loss": 1.892, + "step": 61400 + }, + { + "epoch": 2.28, + "eval_loss": 1.6934465169906616, + "eval_runtime": 16.8305, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 61400 + }, + { + "epoch": 2.28, + "learning_rate": 7.715996578272028e-06, + "loss": 1.7005, + "step": 61410 + }, + { + "epoch": 2.28, + "learning_rate": 7.715624651318482e-06, + "loss": 1.7691, + "step": 61420 + }, + { + "epoch": 2.28, + "learning_rate": 7.715252724364935e-06, + "loss": 1.7399, + "step": 61430 + }, + { + "epoch": 2.29, + "learning_rate": 7.714880797411389e-06, + "loss": 1.766, + "step": 61440 + }, + { + "epoch": 2.29, + "learning_rate": 7.714508870457842e-06, + "loss": 1.7068, + "step": 61450 + }, + { + "epoch": 2.29, + "learning_rate": 7.714136943504297e-06, + "loss": 1.8002, + "step": 61460 + }, + { + "epoch": 2.29, + "learning_rate": 7.713765016550751e-06, + "loss": 1.7611, + "step": 61470 + }, + { + "epoch": 2.29, + "learning_rate": 7.713393089597204e-06, + "loss": 1.7007, + "step": 61480 + }, + { + "epoch": 2.29, + "learning_rate": 7.713021162643658e-06, + "loss": 1.7953, + "step": 61490 + }, + { + "epoch": 2.29, + "learning_rate": 7.712649235690111e-06, + "loss": 1.6984, + "step": 61500 + }, + { + "epoch": 2.29, + "eval_loss": 1.692766547203064, + "eval_runtime": 16.8527, + "eval_samples_per_second": 59.338, + "eval_steps_per_second": 3.738, + "step": 61500 + }, + { + "epoch": 2.29, + "learning_rate": 7.712277308736565e-06, + "loss": 1.6389, + "step": 61510 + }, + { + "epoch": 2.29, + "learning_rate": 7.711905381783018e-06, + "loss": 1.7295, + "step": 61520 + }, + { + "epoch": 2.29, + "learning_rate": 7.711533454829472e-06, + "loss": 1.6461, + "step": 61530 + }, + { + "epoch": 2.29, + "learning_rate": 7.711161527875925e-06, + "loss": 1.75, + "step": 61540 + }, + { + "epoch": 2.29, + "learning_rate": 7.710789600922379e-06, + "loss": 1.783, + "step": 61550 + }, + { + "epoch": 2.29, + "learning_rate": 7.710417673968834e-06, + "loss": 1.6441, + "step": 61560 + }, + { + "epoch": 2.29, + "learning_rate": 7.710045747015287e-06, + "loss": 1.7539, + "step": 61570 + }, + { + "epoch": 2.29, + "learning_rate": 7.70967382006174e-06, + "loss": 1.7671, + "step": 61580 + }, + { + "epoch": 2.29, + "learning_rate": 7.709301893108194e-06, + "loss": 1.81, + "step": 61590 + }, + { + "epoch": 2.29, + "learning_rate": 7.708929966154648e-06, + "loss": 1.7462, + "step": 61600 + }, + { + "epoch": 2.29, + "eval_loss": 1.692940592765808, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 61600 + }, + { + "epoch": 2.29, + "learning_rate": 7.708558039201101e-06, + "loss": 1.5772, + "step": 61610 + }, + { + "epoch": 2.29, + "learning_rate": 7.708186112247556e-06, + "loss": 1.756, + "step": 61620 + }, + { + "epoch": 2.29, + "learning_rate": 7.70781418529401e-06, + "loss": 1.7633, + "step": 61630 + }, + { + "epoch": 2.29, + "learning_rate": 7.707442258340463e-06, + "loss": 1.7171, + "step": 61640 + }, + { + "epoch": 2.29, + "learning_rate": 7.707070331386917e-06, + "loss": 1.6478, + "step": 61650 + }, + { + "epoch": 2.29, + "learning_rate": 7.70669840443337e-06, + "loss": 1.7496, + "step": 61660 + }, + { + "epoch": 2.29, + "learning_rate": 7.706326477479823e-06, + "loss": 1.8063, + "step": 61670 + }, + { + "epoch": 2.29, + "learning_rate": 7.705954550526277e-06, + "loss": 1.6728, + "step": 61680 + }, + { + "epoch": 2.29, + "learning_rate": 7.70558262357273e-06, + "loss": 1.7044, + "step": 61690 + }, + { + "epoch": 2.29, + "learning_rate": 7.705210696619184e-06, + "loss": 1.8349, + "step": 61700 + }, + { + "epoch": 2.29, + "eval_loss": 1.692649483680725, + "eval_runtime": 16.8408, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 61700 + }, + { + "epoch": 2.3, + "learning_rate": 7.704838769665637e-06, + "loss": 1.7244, + "step": 61710 + }, + { + "epoch": 2.3, + "learning_rate": 7.704466842712092e-06, + "loss": 1.694, + "step": 61720 + }, + { + "epoch": 2.3, + "learning_rate": 7.704094915758546e-06, + "loss": 1.6531, + "step": 61730 + }, + { + "epoch": 2.3, + "learning_rate": 7.703722988805e-06, + "loss": 1.7805, + "step": 61740 + }, + { + "epoch": 2.3, + "learning_rate": 7.703351061851453e-06, + "loss": 1.6525, + "step": 61750 + }, + { + "epoch": 2.3, + "learning_rate": 7.702979134897906e-06, + "loss": 1.7478, + "step": 61760 + }, + { + "epoch": 2.3, + "learning_rate": 7.70260720794436e-06, + "loss": 1.713, + "step": 61770 + }, + { + "epoch": 2.3, + "learning_rate": 7.702235280990815e-06, + "loss": 1.773, + "step": 61780 + }, + { + "epoch": 2.3, + "learning_rate": 7.701863354037268e-06, + "loss": 1.7566, + "step": 61790 + }, + { + "epoch": 2.3, + "learning_rate": 7.701491427083722e-06, + "loss": 1.7416, + "step": 61800 + }, + { + "epoch": 2.3, + "eval_loss": 1.6924259662628174, + "eval_runtime": 16.8374, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 61800 + }, + { + "epoch": 2.3, + "learning_rate": 7.701119500130175e-06, + "loss": 1.6635, + "step": 61810 + }, + { + "epoch": 2.3, + "learning_rate": 7.700747573176629e-06, + "loss": 1.7774, + "step": 61820 + }, + { + "epoch": 2.3, + "learning_rate": 7.700375646223082e-06, + "loss": 1.6924, + "step": 61830 + }, + { + "epoch": 2.3, + "learning_rate": 7.700003719269537e-06, + "loss": 1.7475, + "step": 61840 + }, + { + "epoch": 2.3, + "learning_rate": 7.69963179231599e-06, + "loss": 1.842, + "step": 61850 + }, + { + "epoch": 2.3, + "learning_rate": 7.699259865362444e-06, + "loss": 1.8588, + "step": 61860 + }, + { + "epoch": 2.3, + "learning_rate": 7.698887938408896e-06, + "loss": 1.7444, + "step": 61870 + }, + { + "epoch": 2.3, + "learning_rate": 7.698516011455351e-06, + "loss": 1.7557, + "step": 61880 + }, + { + "epoch": 2.3, + "learning_rate": 7.698144084501805e-06, + "loss": 1.9259, + "step": 61890 + }, + { + "epoch": 2.3, + "learning_rate": 7.697772157548258e-06, + "loss": 1.8902, + "step": 61900 + }, + { + "epoch": 2.3, + "eval_loss": 1.691928505897522, + "eval_runtime": 16.8376, + "eval_samples_per_second": 59.391, + "eval_steps_per_second": 3.742, + "step": 61900 + }, + { + "epoch": 2.3, + "learning_rate": 7.697400230594712e-06, + "loss": 1.8897, + "step": 61910 + }, + { + "epoch": 2.3, + "learning_rate": 7.697028303641165e-06, + "loss": 1.7961, + "step": 61920 + }, + { + "epoch": 2.3, + "learning_rate": 7.696656376687618e-06, + "loss": 1.7338, + "step": 61930 + }, + { + "epoch": 2.3, + "learning_rate": 7.696284449734072e-06, + "loss": 1.7119, + "step": 61940 + }, + { + "epoch": 2.3, + "learning_rate": 7.695912522780527e-06, + "loss": 1.8006, + "step": 61950 + }, + { + "epoch": 2.3, + "learning_rate": 7.69554059582698e-06, + "loss": 1.6535, + "step": 61960 + }, + { + "epoch": 2.3, + "learning_rate": 7.695168668873434e-06, + "loss": 1.8063, + "step": 61970 + }, + { + "epoch": 2.31, + "learning_rate": 7.694796741919887e-06, + "loss": 1.6712, + "step": 61980 + }, + { + "epoch": 2.31, + "learning_rate": 7.694424814966341e-06, + "loss": 1.6537, + "step": 61990 + }, + { + "epoch": 2.31, + "learning_rate": 7.694052888012794e-06, + "loss": 1.7422, + "step": 62000 + }, + { + "epoch": 2.31, + "eval_loss": 1.6920740604400635, + "eval_runtime": 16.8424, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 62000 + }, + { + "epoch": 2.31, + "learning_rate": 7.69368096105925e-06, + "loss": 1.7084, + "step": 62010 + }, + { + "epoch": 2.31, + "learning_rate": 7.693309034105703e-06, + "loss": 1.8709, + "step": 62020 + }, + { + "epoch": 2.31, + "learning_rate": 7.692937107152156e-06, + "loss": 1.6119, + "step": 62030 + }, + { + "epoch": 2.31, + "learning_rate": 7.69256518019861e-06, + "loss": 1.8026, + "step": 62040 + }, + { + "epoch": 2.31, + "learning_rate": 7.692193253245063e-06, + "loss": 1.7251, + "step": 62050 + }, + { + "epoch": 2.31, + "learning_rate": 7.691821326291517e-06, + "loss": 1.7163, + "step": 62060 + }, + { + "epoch": 2.31, + "learning_rate": 7.69144939933797e-06, + "loss": 1.7013, + "step": 62070 + }, + { + "epoch": 2.31, + "learning_rate": 7.691077472384424e-06, + "loss": 1.7747, + "step": 62080 + }, + { + "epoch": 2.31, + "learning_rate": 7.690705545430877e-06, + "loss": 1.8108, + "step": 62090 + }, + { + "epoch": 2.31, + "learning_rate": 7.69033361847733e-06, + "loss": 1.8055, + "step": 62100 + }, + { + "epoch": 2.31, + "eval_loss": 1.6931674480438232, + "eval_runtime": 16.8329, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 62100 + }, + { + "epoch": 2.31, + "learning_rate": 7.689961691523786e-06, + "loss": 1.6496, + "step": 62110 + }, + { + "epoch": 2.31, + "learning_rate": 7.68958976457024e-06, + "loss": 1.7312, + "step": 62120 + }, + { + "epoch": 2.31, + "learning_rate": 7.689217837616693e-06, + "loss": 1.7774, + "step": 62130 + }, + { + "epoch": 2.31, + "learning_rate": 7.688845910663146e-06, + "loss": 1.6129, + "step": 62140 + }, + { + "epoch": 2.31, + "learning_rate": 7.6884739837096e-06, + "loss": 1.8137, + "step": 62150 + }, + { + "epoch": 2.31, + "learning_rate": 7.688102056756053e-06, + "loss": 1.8264, + "step": 62160 + }, + { + "epoch": 2.31, + "learning_rate": 7.687730129802508e-06, + "loss": 1.6992, + "step": 62170 + }, + { + "epoch": 2.31, + "learning_rate": 7.687358202848962e-06, + "loss": 1.7136, + "step": 62180 + }, + { + "epoch": 2.31, + "learning_rate": 7.686986275895415e-06, + "loss": 1.7088, + "step": 62190 + }, + { + "epoch": 2.31, + "learning_rate": 7.686614348941869e-06, + "loss": 1.8374, + "step": 62200 + }, + { + "epoch": 2.31, + "eval_loss": 1.691945195198059, + "eval_runtime": 16.83, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 62200 + }, + { + "epoch": 2.31, + "learning_rate": 7.686242421988322e-06, + "loss": 1.7466, + "step": 62210 + }, + { + "epoch": 2.31, + "learning_rate": 7.685870495034776e-06, + "loss": 1.7866, + "step": 62220 + }, + { + "epoch": 2.31, + "learning_rate": 7.68549856808123e-06, + "loss": 1.9082, + "step": 62230 + }, + { + "epoch": 2.31, + "learning_rate": 7.685126641127684e-06, + "loss": 1.8163, + "step": 62240 + }, + { + "epoch": 2.32, + "learning_rate": 7.684754714174136e-06, + "loss": 1.7207, + "step": 62250 + }, + { + "epoch": 2.32, + "learning_rate": 7.68438278722059e-06, + "loss": 1.7937, + "step": 62260 + }, + { + "epoch": 2.32, + "learning_rate": 7.684010860267045e-06, + "loss": 1.7004, + "step": 62270 + }, + { + "epoch": 2.32, + "learning_rate": 7.683638933313498e-06, + "loss": 1.7303, + "step": 62280 + }, + { + "epoch": 2.32, + "learning_rate": 7.683267006359951e-06, + "loss": 1.8649, + "step": 62290 + }, + { + "epoch": 2.32, + "learning_rate": 7.682895079406405e-06, + "loss": 1.7427, + "step": 62300 + }, + { + "epoch": 2.32, + "eval_loss": 1.6918059587478638, + "eval_runtime": 16.8401, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 62300 + }, + { + "epoch": 2.32, + "learning_rate": 7.682523152452858e-06, + "loss": 1.7735, + "step": 62310 + }, + { + "epoch": 2.32, + "learning_rate": 7.682151225499312e-06, + "loss": 1.7571, + "step": 62320 + }, + { + "epoch": 2.32, + "learning_rate": 7.681779298545767e-06, + "loss": 1.739, + "step": 62330 + }, + { + "epoch": 2.32, + "learning_rate": 7.68140737159222e-06, + "loss": 1.7569, + "step": 62340 + }, + { + "epoch": 2.32, + "learning_rate": 7.681035444638674e-06, + "loss": 1.659, + "step": 62350 + }, + { + "epoch": 2.32, + "learning_rate": 7.680663517685127e-06, + "loss": 1.699, + "step": 62360 + }, + { + "epoch": 2.32, + "learning_rate": 7.68029159073158e-06, + "loss": 1.7772, + "step": 62370 + }, + { + "epoch": 2.32, + "learning_rate": 7.679919663778034e-06, + "loss": 1.7104, + "step": 62380 + }, + { + "epoch": 2.32, + "learning_rate": 7.67954773682449e-06, + "loss": 1.6978, + "step": 62390 + }, + { + "epoch": 2.32, + "learning_rate": 7.679175809870943e-06, + "loss": 1.7073, + "step": 62400 + }, + { + "epoch": 2.32, + "eval_loss": 1.692428469657898, + "eval_runtime": 16.8361, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 62400 + }, + { + "epoch": 2.32, + "learning_rate": 7.678803882917396e-06, + "loss": 1.8009, + "step": 62410 + }, + { + "epoch": 2.32, + "learning_rate": 7.67843195596385e-06, + "loss": 1.736, + "step": 62420 + }, + { + "epoch": 2.32, + "learning_rate": 7.678060029010303e-06, + "loss": 1.7773, + "step": 62430 + }, + { + "epoch": 2.32, + "learning_rate": 7.677688102056757e-06, + "loss": 1.7116, + "step": 62440 + }, + { + "epoch": 2.32, + "learning_rate": 7.67731617510321e-06, + "loss": 1.5779, + "step": 62450 + }, + { + "epoch": 2.32, + "learning_rate": 7.676944248149664e-06, + "loss": 1.8302, + "step": 62460 + }, + { + "epoch": 2.32, + "learning_rate": 7.676572321196117e-06, + "loss": 1.8187, + "step": 62470 + }, + { + "epoch": 2.32, + "learning_rate": 7.67620039424257e-06, + "loss": 1.652, + "step": 62480 + }, + { + "epoch": 2.32, + "learning_rate": 7.675828467289024e-06, + "loss": 1.6587, + "step": 62490 + }, + { + "epoch": 2.32, + "learning_rate": 7.67545654033548e-06, + "loss": 1.8317, + "step": 62500 + }, + { + "epoch": 2.32, + "eval_loss": 1.6912035942077637, + "eval_runtime": 16.8561, + "eval_samples_per_second": 59.326, + "eval_steps_per_second": 3.738, + "step": 62500 + }, + { + "epoch": 2.32, + "learning_rate": 7.675084613381933e-06, + "loss": 1.6891, + "step": 62510 + }, + { + "epoch": 2.33, + "learning_rate": 7.674712686428386e-06, + "loss": 1.8627, + "step": 62520 + }, + { + "epoch": 2.33, + "learning_rate": 7.67434075947484e-06, + "loss": 1.8123, + "step": 62530 + }, + { + "epoch": 2.33, + "learning_rate": 7.673968832521293e-06, + "loss": 1.612, + "step": 62540 + }, + { + "epoch": 2.33, + "learning_rate": 7.673596905567746e-06, + "loss": 1.7204, + "step": 62550 + }, + { + "epoch": 2.33, + "learning_rate": 7.673224978614202e-06, + "loss": 1.7208, + "step": 62560 + }, + { + "epoch": 2.33, + "learning_rate": 7.672853051660655e-06, + "loss": 1.7739, + "step": 62570 + }, + { + "epoch": 2.33, + "learning_rate": 7.672481124707109e-06, + "loss": 1.7951, + "step": 62580 + }, + { + "epoch": 2.33, + "learning_rate": 7.672109197753562e-06, + "loss": 1.7423, + "step": 62590 + }, + { + "epoch": 2.33, + "learning_rate": 7.671737270800015e-06, + "loss": 1.5998, + "step": 62600 + }, + { + "epoch": 2.33, + "eval_loss": 1.6921757459640503, + "eval_runtime": 16.8402, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 62600 + }, + { + "epoch": 2.33, + "learning_rate": 7.671365343846469e-06, + "loss": 1.7323, + "step": 62610 + }, + { + "epoch": 2.33, + "learning_rate": 7.670993416892922e-06, + "loss": 1.8229, + "step": 62620 + }, + { + "epoch": 2.33, + "learning_rate": 7.670621489939376e-06, + "loss": 1.7603, + "step": 62630 + }, + { + "epoch": 2.33, + "learning_rate": 7.67024956298583e-06, + "loss": 1.7692, + "step": 62640 + }, + { + "epoch": 2.33, + "learning_rate": 7.669877636032283e-06, + "loss": 1.7135, + "step": 62650 + }, + { + "epoch": 2.33, + "learning_rate": 7.669505709078738e-06, + "loss": 1.8262, + "step": 62660 + }, + { + "epoch": 2.33, + "learning_rate": 7.669133782125191e-06, + "loss": 1.7342, + "step": 62670 + }, + { + "epoch": 2.33, + "learning_rate": 7.668761855171645e-06, + "loss": 1.7425, + "step": 62680 + }, + { + "epoch": 2.33, + "learning_rate": 7.668389928218098e-06, + "loss": 1.904, + "step": 62690 + }, + { + "epoch": 2.33, + "learning_rate": 7.668018001264552e-06, + "loss": 1.8297, + "step": 62700 + }, + { + "epoch": 2.33, + "eval_loss": 1.6921831369400024, + "eval_runtime": 16.82, + "eval_samples_per_second": 59.453, + "eval_steps_per_second": 3.746, + "step": 62700 + }, + { + "epoch": 2.33, + "learning_rate": 7.667646074311005e-06, + "loss": 1.696, + "step": 62710 + }, + { + "epoch": 2.33, + "learning_rate": 7.66727414735746e-06, + "loss": 1.693, + "step": 62720 + }, + { + "epoch": 2.33, + "learning_rate": 7.666902220403914e-06, + "loss": 1.6138, + "step": 62730 + }, + { + "epoch": 2.33, + "learning_rate": 7.666530293450367e-06, + "loss": 1.7073, + "step": 62740 + }, + { + "epoch": 2.33, + "learning_rate": 7.66615836649682e-06, + "loss": 1.7842, + "step": 62750 + }, + { + "epoch": 2.33, + "learning_rate": 7.665786439543274e-06, + "loss": 1.8477, + "step": 62760 + }, + { + "epoch": 2.33, + "learning_rate": 7.665414512589728e-06, + "loss": 1.6657, + "step": 62770 + }, + { + "epoch": 2.33, + "learning_rate": 7.665042585636183e-06, + "loss": 1.6643, + "step": 62780 + }, + { + "epoch": 2.34, + "learning_rate": 7.664670658682636e-06, + "loss": 1.674, + "step": 62790 + }, + { + "epoch": 2.34, + "learning_rate": 7.66429873172909e-06, + "loss": 1.8416, + "step": 62800 + }, + { + "epoch": 2.34, + "eval_loss": 1.6916979551315308, + "eval_runtime": 16.8495, + "eval_samples_per_second": 59.349, + "eval_steps_per_second": 3.739, + "step": 62800 + }, + { + "epoch": 2.34, + "learning_rate": 7.663926804775542e-06, + "loss": 1.651, + "step": 62810 + }, + { + "epoch": 2.34, + "learning_rate": 7.663554877821997e-06, + "loss": 1.9452, + "step": 62820 + }, + { + "epoch": 2.34, + "learning_rate": 7.66318295086845e-06, + "loss": 1.7818, + "step": 62830 + }, + { + "epoch": 2.34, + "learning_rate": 7.662811023914904e-06, + "loss": 1.6377, + "step": 62840 + }, + { + "epoch": 2.34, + "learning_rate": 7.662439096961357e-06, + "loss": 1.6964, + "step": 62850 + }, + { + "epoch": 2.34, + "learning_rate": 7.66206717000781e-06, + "loss": 1.8571, + "step": 62860 + }, + { + "epoch": 2.34, + "learning_rate": 7.661695243054264e-06, + "loss": 1.6687, + "step": 62870 + }, + { + "epoch": 2.34, + "learning_rate": 7.661323316100719e-06, + "loss": 1.8407, + "step": 62880 + }, + { + "epoch": 2.34, + "learning_rate": 7.660951389147173e-06, + "loss": 1.816, + "step": 62890 + }, + { + "epoch": 2.34, + "learning_rate": 7.660579462193626e-06, + "loss": 1.8441, + "step": 62900 + }, + { + "epoch": 2.34, + "eval_loss": 1.691356897354126, + "eval_runtime": 16.8516, + "eval_samples_per_second": 59.341, + "eval_steps_per_second": 3.739, + "step": 62900 + }, + { + "epoch": 2.34, + "learning_rate": 7.66020753524008e-06, + "loss": 1.7472, + "step": 62910 + }, + { + "epoch": 2.34, + "learning_rate": 7.659835608286533e-06, + "loss": 1.7696, + "step": 62920 + }, + { + "epoch": 2.34, + "learning_rate": 7.659463681332986e-06, + "loss": 1.6898, + "step": 62930 + }, + { + "epoch": 2.34, + "learning_rate": 7.659091754379442e-06, + "loss": 1.6435, + "step": 62940 + }, + { + "epoch": 2.34, + "learning_rate": 7.658719827425895e-06, + "loss": 1.7911, + "step": 62950 + }, + { + "epoch": 2.34, + "learning_rate": 7.658347900472348e-06, + "loss": 1.6895, + "step": 62960 + }, + { + "epoch": 2.34, + "learning_rate": 7.657975973518802e-06, + "loss": 1.7897, + "step": 62970 + }, + { + "epoch": 2.34, + "learning_rate": 7.657604046565255e-06, + "loss": 1.6269, + "step": 62980 + }, + { + "epoch": 2.34, + "learning_rate": 7.657232119611709e-06, + "loss": 1.9173, + "step": 62990 + }, + { + "epoch": 2.34, + "learning_rate": 7.656860192658162e-06, + "loss": 1.6524, + "step": 63000 + }, + { + "epoch": 2.34, + "eval_loss": 1.6907802820205688, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 63000 + }, + { + "epoch": 2.34, + "learning_rate": 7.656488265704616e-06, + "loss": 1.7639, + "step": 63010 + }, + { + "epoch": 2.34, + "learning_rate": 7.65611633875107e-06, + "loss": 1.6815, + "step": 63020 + }, + { + "epoch": 2.34, + "learning_rate": 7.655744411797523e-06, + "loss": 1.6652, + "step": 63030 + }, + { + "epoch": 2.34, + "learning_rate": 7.655372484843976e-06, + "loss": 1.8068, + "step": 63040 + }, + { + "epoch": 2.34, + "learning_rate": 7.655000557890431e-06, + "loss": 1.7844, + "step": 63050 + }, + { + "epoch": 2.35, + "learning_rate": 7.654628630936885e-06, + "loss": 1.6606, + "step": 63060 + }, + { + "epoch": 2.35, + "learning_rate": 7.654256703983338e-06, + "loss": 1.7806, + "step": 63070 + }, + { + "epoch": 2.35, + "learning_rate": 7.653884777029792e-06, + "loss": 1.5732, + "step": 63080 + }, + { + "epoch": 2.35, + "learning_rate": 7.653512850076245e-06, + "loss": 1.7306, + "step": 63090 + }, + { + "epoch": 2.35, + "learning_rate": 7.653140923122699e-06, + "loss": 1.7827, + "step": 63100 + }, + { + "epoch": 2.35, + "eval_loss": 1.6909382343292236, + "eval_runtime": 16.8425, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 63100 + }, + { + "epoch": 2.35, + "learning_rate": 7.652768996169154e-06, + "loss": 1.7284, + "step": 63110 + }, + { + "epoch": 2.35, + "learning_rate": 7.652397069215607e-06, + "loss": 1.6525, + "step": 63120 + }, + { + "epoch": 2.35, + "learning_rate": 7.65202514226206e-06, + "loss": 1.6229, + "step": 63130 + }, + { + "epoch": 2.35, + "learning_rate": 7.651653215308514e-06, + "loss": 1.7627, + "step": 63140 + }, + { + "epoch": 2.35, + "learning_rate": 7.651281288354968e-06, + "loss": 1.6256, + "step": 63150 + }, + { + "epoch": 2.35, + "learning_rate": 7.650909361401421e-06, + "loss": 1.7151, + "step": 63160 + }, + { + "epoch": 2.35, + "learning_rate": 7.650537434447876e-06, + "loss": 1.7358, + "step": 63170 + }, + { + "epoch": 2.35, + "learning_rate": 7.65016550749433e-06, + "loss": 1.7135, + "step": 63180 + }, + { + "epoch": 2.35, + "learning_rate": 7.649793580540781e-06, + "loss": 1.7213, + "step": 63190 + }, + { + "epoch": 2.35, + "learning_rate": 7.649421653587235e-06, + "loss": 1.7294, + "step": 63200 + }, + { + "epoch": 2.35, + "eval_loss": 1.6903800964355469, + "eval_runtime": 16.8314, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 63200 + }, + { + "epoch": 2.35, + "learning_rate": 7.64904972663369e-06, + "loss": 1.7606, + "step": 63210 + }, + { + "epoch": 2.35, + "learning_rate": 7.648677799680143e-06, + "loss": 1.7656, + "step": 63220 + }, + { + "epoch": 2.35, + "learning_rate": 7.648305872726597e-06, + "loss": 1.7865, + "step": 63230 + }, + { + "epoch": 2.35, + "learning_rate": 7.64793394577305e-06, + "loss": 1.7093, + "step": 63240 + }, + { + "epoch": 2.35, + "learning_rate": 7.647562018819504e-06, + "loss": 1.7425, + "step": 63250 + }, + { + "epoch": 2.35, + "learning_rate": 7.647190091865957e-06, + "loss": 1.6902, + "step": 63260 + }, + { + "epoch": 2.35, + "learning_rate": 7.646818164912412e-06, + "loss": 1.7602, + "step": 63270 + }, + { + "epoch": 2.35, + "learning_rate": 7.646446237958866e-06, + "loss": 1.6433, + "step": 63280 + }, + { + "epoch": 2.35, + "learning_rate": 7.64607431100532e-06, + "loss": 1.7582, + "step": 63290 + }, + { + "epoch": 2.35, + "learning_rate": 7.645702384051773e-06, + "loss": 1.8047, + "step": 63300 + }, + { + "epoch": 2.35, + "eval_loss": 1.6903176307678223, + "eval_runtime": 16.8399, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 63300 + }, + { + "epoch": 2.35, + "learning_rate": 7.645330457098226e-06, + "loss": 1.8182, + "step": 63310 + }, + { + "epoch": 2.36, + "learning_rate": 7.64495853014468e-06, + "loss": 1.7952, + "step": 63320 + }, + { + "epoch": 2.36, + "learning_rate": 7.644586603191135e-06, + "loss": 1.6911, + "step": 63330 + }, + { + "epoch": 2.36, + "learning_rate": 7.644214676237588e-06, + "loss": 1.7111, + "step": 63340 + }, + { + "epoch": 2.36, + "learning_rate": 7.643842749284042e-06, + "loss": 1.6188, + "step": 63350 + }, + { + "epoch": 2.36, + "learning_rate": 7.643470822330495e-06, + "loss": 1.662, + "step": 63360 + }, + { + "epoch": 2.36, + "learning_rate": 7.643098895376949e-06, + "loss": 1.7238, + "step": 63370 + }, + { + "epoch": 2.36, + "learning_rate": 7.642726968423402e-06, + "loss": 1.5767, + "step": 63380 + }, + { + "epoch": 2.36, + "learning_rate": 7.642355041469856e-06, + "loss": 1.6997, + "step": 63390 + }, + { + "epoch": 2.36, + "learning_rate": 7.641983114516309e-06, + "loss": 1.7352, + "step": 63400 + }, + { + "epoch": 2.36, + "eval_loss": 1.6914747953414917, + "eval_runtime": 16.8419, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 63400 + }, + { + "epoch": 2.36, + "learning_rate": 7.641611187562763e-06, + "loss": 1.7751, + "step": 63410 + }, + { + "epoch": 2.36, + "learning_rate": 7.641239260609216e-06, + "loss": 1.7553, + "step": 63420 + }, + { + "epoch": 2.36, + "learning_rate": 7.640867333655671e-06, + "loss": 1.831, + "step": 63430 + }, + { + "epoch": 2.36, + "learning_rate": 7.640495406702125e-06, + "loss": 1.9109, + "step": 63440 + }, + { + "epoch": 2.36, + "learning_rate": 7.640123479748578e-06, + "loss": 1.7528, + "step": 63450 + }, + { + "epoch": 2.36, + "learning_rate": 7.639751552795032e-06, + "loss": 1.7879, + "step": 63460 + }, + { + "epoch": 2.36, + "learning_rate": 7.639379625841485e-06, + "loss": 1.7049, + "step": 63470 + }, + { + "epoch": 2.36, + "learning_rate": 7.639007698887939e-06, + "loss": 1.717, + "step": 63480 + }, + { + "epoch": 2.36, + "learning_rate": 7.638635771934394e-06, + "loss": 1.8004, + "step": 63490 + }, + { + "epoch": 2.36, + "learning_rate": 7.638263844980847e-06, + "loss": 1.645, + "step": 63500 + }, + { + "epoch": 2.36, + "eval_loss": 1.6903761625289917, + "eval_runtime": 16.8369, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 63500 + }, + { + "epoch": 2.36, + "learning_rate": 7.6378919180273e-06, + "loss": 1.7963, + "step": 63510 + }, + { + "epoch": 2.36, + "learning_rate": 7.637519991073754e-06, + "loss": 1.7195, + "step": 63520 + }, + { + "epoch": 2.36, + "learning_rate": 7.637148064120208e-06, + "loss": 1.8562, + "step": 63530 + }, + { + "epoch": 2.36, + "learning_rate": 7.636776137166661e-06, + "loss": 1.9084, + "step": 63540 + }, + { + "epoch": 2.36, + "learning_rate": 7.636404210213116e-06, + "loss": 1.5941, + "step": 63550 + }, + { + "epoch": 2.36, + "learning_rate": 7.636032283259568e-06, + "loss": 1.6274, + "step": 63560 + }, + { + "epoch": 2.36, + "learning_rate": 7.635660356306021e-06, + "loss": 1.8635, + "step": 63570 + }, + { + "epoch": 2.36, + "learning_rate": 7.635288429352475e-06, + "loss": 1.7927, + "step": 63580 + }, + { + "epoch": 2.37, + "learning_rate": 7.63491650239893e-06, + "loss": 1.6288, + "step": 63590 + }, + { + "epoch": 2.37, + "learning_rate": 7.634544575445383e-06, + "loss": 1.8068, + "step": 63600 + }, + { + "epoch": 2.37, + "eval_loss": 1.688947319984436, + "eval_runtime": 16.857, + "eval_samples_per_second": 59.322, + "eval_steps_per_second": 3.737, + "step": 63600 + }, + { + "epoch": 2.37, + "learning_rate": 7.634172648491837e-06, + "loss": 1.7024, + "step": 63610 + }, + { + "epoch": 2.37, + "learning_rate": 7.63380072153829e-06, + "loss": 1.7497, + "step": 63620 + }, + { + "epoch": 2.37, + "learning_rate": 7.633428794584744e-06, + "loss": 1.7216, + "step": 63630 + }, + { + "epoch": 2.37, + "learning_rate": 7.633056867631197e-06, + "loss": 1.6332, + "step": 63640 + }, + { + "epoch": 2.37, + "learning_rate": 7.63268494067765e-06, + "loss": 1.7271, + "step": 63650 + }, + { + "epoch": 2.37, + "learning_rate": 7.632313013724106e-06, + "loss": 1.6627, + "step": 63660 + }, + { + "epoch": 2.37, + "learning_rate": 7.63194108677056e-06, + "loss": 1.677, + "step": 63670 + }, + { + "epoch": 2.37, + "learning_rate": 7.631569159817013e-06, + "loss": 1.8576, + "step": 63680 + }, + { + "epoch": 2.37, + "learning_rate": 7.631197232863466e-06, + "loss": 1.962, + "step": 63690 + }, + { + "epoch": 2.37, + "learning_rate": 7.63082530590992e-06, + "loss": 1.6897, + "step": 63700 + }, + { + "epoch": 2.37, + "eval_loss": 1.6900107860565186, + "eval_runtime": 16.8547, + "eval_samples_per_second": 59.331, + "eval_steps_per_second": 3.738, + "step": 63700 + }, + { + "epoch": 2.37, + "learning_rate": 7.630453378956373e-06, + "loss": 1.728, + "step": 63710 + }, + { + "epoch": 2.37, + "learning_rate": 7.630081452002828e-06, + "loss": 1.9109, + "step": 63720 + }, + { + "epoch": 2.37, + "learning_rate": 7.629709525049282e-06, + "loss": 1.8361, + "step": 63730 + }, + { + "epoch": 2.37, + "learning_rate": 7.629337598095735e-06, + "loss": 1.6632, + "step": 63740 + }, + { + "epoch": 2.37, + "learning_rate": 7.628965671142188e-06, + "loss": 1.7699, + "step": 63750 + }, + { + "epoch": 2.37, + "learning_rate": 7.628593744188641e-06, + "loss": 1.7639, + "step": 63760 + }, + { + "epoch": 2.37, + "learning_rate": 7.628221817235096e-06, + "loss": 1.7009, + "step": 63770 + }, + { + "epoch": 2.37, + "learning_rate": 7.627849890281549e-06, + "loss": 1.9334, + "step": 63780 + }, + { + "epoch": 2.37, + "learning_rate": 7.6274779633280025e-06, + "loss": 1.766, + "step": 63790 + }, + { + "epoch": 2.37, + "learning_rate": 7.627106036374457e-06, + "loss": 1.7383, + "step": 63800 + }, + { + "epoch": 2.37, + "eval_loss": 1.689112663269043, + "eval_runtime": 16.8238, + "eval_samples_per_second": 59.44, + "eval_steps_per_second": 3.745, + "step": 63800 + }, + { + "epoch": 2.37, + "learning_rate": 7.62673410942091e-06, + "loss": 1.6894, + "step": 63810 + }, + { + "epoch": 2.37, + "learning_rate": 7.626362182467364e-06, + "loss": 1.653, + "step": 63820 + }, + { + "epoch": 2.37, + "learning_rate": 7.625990255513818e-06, + "loss": 1.7262, + "step": 63830 + }, + { + "epoch": 2.37, + "learning_rate": 7.6256183285602715e-06, + "loss": 1.746, + "step": 63840 + }, + { + "epoch": 2.37, + "learning_rate": 7.625246401606725e-06, + "loss": 1.7244, + "step": 63850 + }, + { + "epoch": 2.38, + "learning_rate": 7.624874474653179e-06, + "loss": 1.5989, + "step": 63860 + }, + { + "epoch": 2.38, + "learning_rate": 7.624502547699633e-06, + "loss": 1.8811, + "step": 63870 + }, + { + "epoch": 2.38, + "learning_rate": 7.624130620746086e-06, + "loss": 1.6978, + "step": 63880 + }, + { + "epoch": 2.38, + "learning_rate": 7.62375869379254e-06, + "loss": 1.7599, + "step": 63890 + }, + { + "epoch": 2.38, + "learning_rate": 7.623386766838994e-06, + "loss": 1.8489, + "step": 63900 + }, + { + "epoch": 2.38, + "eval_loss": 1.6894108057022095, + "eval_runtime": 16.8516, + "eval_samples_per_second": 59.342, + "eval_steps_per_second": 3.739, + "step": 63900 + }, + { + "epoch": 2.38, + "learning_rate": 7.623014839885447e-06, + "loss": 1.7702, + "step": 63910 + }, + { + "epoch": 2.38, + "learning_rate": 7.622642912931901e-06, + "loss": 1.7284, + "step": 63920 + }, + { + "epoch": 2.38, + "learning_rate": 7.622270985978355e-06, + "loss": 1.6573, + "step": 63930 + }, + { + "epoch": 2.38, + "learning_rate": 7.621899059024808e-06, + "loss": 1.6817, + "step": 63940 + }, + { + "epoch": 2.38, + "learning_rate": 7.621527132071261e-06, + "loss": 1.7141, + "step": 63950 + }, + { + "epoch": 2.38, + "learning_rate": 7.621155205117715e-06, + "loss": 1.7035, + "step": 63960 + }, + { + "epoch": 2.38, + "learning_rate": 7.620783278164169e-06, + "loss": 1.829, + "step": 63970 + }, + { + "epoch": 2.38, + "learning_rate": 7.6204113512106225e-06, + "loss": 1.7678, + "step": 63980 + }, + { + "epoch": 2.38, + "learning_rate": 7.620039424257076e-06, + "loss": 1.8415, + "step": 63990 + }, + { + "epoch": 2.38, + "learning_rate": 7.61966749730353e-06, + "loss": 1.6877, + "step": 64000 + }, + { + "epoch": 2.38, + "eval_loss": 1.6895976066589355, + "eval_runtime": 16.8449, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 64000 + }, + { + "epoch": 2.38, + "learning_rate": 7.619295570349984e-06, + "loss": 1.6565, + "step": 64010 + }, + { + "epoch": 2.38, + "learning_rate": 7.618923643396437e-06, + "loss": 1.6782, + "step": 64020 + }, + { + "epoch": 2.38, + "learning_rate": 7.6185517164428915e-06, + "loss": 2.0762, + "step": 64030 + }, + { + "epoch": 2.38, + "learning_rate": 7.618179789489345e-06, + "loss": 1.8017, + "step": 64040 + }, + { + "epoch": 2.38, + "learning_rate": 7.617807862535798e-06, + "loss": 1.7599, + "step": 64050 + }, + { + "epoch": 2.38, + "learning_rate": 7.617435935582253e-06, + "loss": 1.6523, + "step": 64060 + }, + { + "epoch": 2.38, + "learning_rate": 7.617064008628706e-06, + "loss": 1.7866, + "step": 64070 + }, + { + "epoch": 2.38, + "learning_rate": 7.61669208167516e-06, + "loss": 1.8201, + "step": 64080 + }, + { + "epoch": 2.38, + "learning_rate": 7.616320154721614e-06, + "loss": 1.7763, + "step": 64090 + }, + { + "epoch": 2.38, + "learning_rate": 7.615948227768067e-06, + "loss": 1.674, + "step": 64100 + }, + { + "epoch": 2.38, + "eval_loss": 1.688915491104126, + "eval_runtime": 16.8443, + "eval_samples_per_second": 59.367, + "eval_steps_per_second": 3.74, + "step": 64100 + }, + { + "epoch": 2.38, + "learning_rate": 7.615576300814521e-06, + "loss": 1.6638, + "step": 64110 + }, + { + "epoch": 2.38, + "learning_rate": 7.6152043738609735e-06, + "loss": 1.7496, + "step": 64120 + }, + { + "epoch": 2.39, + "learning_rate": 7.614832446907428e-06, + "loss": 1.8305, + "step": 64130 + }, + { + "epoch": 2.39, + "learning_rate": 7.614460519953881e-06, + "loss": 1.6169, + "step": 64140 + }, + { + "epoch": 2.39, + "learning_rate": 7.614088593000335e-06, + "loss": 1.6739, + "step": 64150 + }, + { + "epoch": 2.39, + "learning_rate": 7.613716666046789e-06, + "loss": 1.6131, + "step": 64160 + }, + { + "epoch": 2.39, + "learning_rate": 7.6133447390932424e-06, + "loss": 1.8913, + "step": 64170 + }, + { + "epoch": 2.39, + "learning_rate": 7.612972812139696e-06, + "loss": 1.6758, + "step": 64180 + }, + { + "epoch": 2.39, + "learning_rate": 7.61260088518615e-06, + "loss": 1.7465, + "step": 64190 + }, + { + "epoch": 2.39, + "learning_rate": 7.612228958232604e-06, + "loss": 1.7618, + "step": 64200 + }, + { + "epoch": 2.39, + "eval_loss": 1.6900428533554077, + "eval_runtime": 16.8507, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 64200 + }, + { + "epoch": 2.39, + "learning_rate": 7.611857031279057e-06, + "loss": 1.7879, + "step": 64210 + }, + { + "epoch": 2.39, + "learning_rate": 7.6114851043255114e-06, + "loss": 1.9758, + "step": 64220 + }, + { + "epoch": 2.39, + "learning_rate": 7.611113177371965e-06, + "loss": 1.798, + "step": 64230 + }, + { + "epoch": 2.39, + "learning_rate": 7.610741250418418e-06, + "loss": 1.6806, + "step": 64240 + }, + { + "epoch": 2.39, + "learning_rate": 7.610369323464873e-06, + "loss": 1.7523, + "step": 64250 + }, + { + "epoch": 2.39, + "learning_rate": 7.609997396511326e-06, + "loss": 1.6739, + "step": 64260 + }, + { + "epoch": 2.39, + "learning_rate": 7.6096254695577796e-06, + "loss": 1.6498, + "step": 64270 + }, + { + "epoch": 2.39, + "learning_rate": 7.609253542604234e-06, + "loss": 1.7144, + "step": 64280 + }, + { + "epoch": 2.39, + "learning_rate": 7.608881615650687e-06, + "loss": 1.992, + "step": 64290 + }, + { + "epoch": 2.39, + "learning_rate": 7.608509688697141e-06, + "loss": 1.7427, + "step": 64300 + }, + { + "epoch": 2.39, + "eval_loss": 1.6891499757766724, + "eval_runtime": 16.8446, + "eval_samples_per_second": 59.366, + "eval_steps_per_second": 3.74, + "step": 64300 + }, + { + "epoch": 2.39, + "learning_rate": 7.608137761743593e-06, + "loss": 1.6501, + "step": 64310 + }, + { + "epoch": 2.39, + "learning_rate": 7.607765834790048e-06, + "loss": 1.8299, + "step": 64320 + }, + { + "epoch": 2.39, + "learning_rate": 7.607393907836501e-06, + "loss": 1.7295, + "step": 64330 + }, + { + "epoch": 2.39, + "learning_rate": 7.607021980882955e-06, + "loss": 1.7838, + "step": 64340 + }, + { + "epoch": 2.39, + "learning_rate": 7.606650053929409e-06, + "loss": 1.793, + "step": 64350 + }, + { + "epoch": 2.39, + "learning_rate": 7.606278126975862e-06, + "loss": 1.8941, + "step": 64360 + }, + { + "epoch": 2.39, + "learning_rate": 7.605906200022316e-06, + "loss": 1.6675, + "step": 64370 + }, + { + "epoch": 2.39, + "learning_rate": 7.60553427306877e-06, + "loss": 1.7739, + "step": 64380 + }, + { + "epoch": 2.39, + "learning_rate": 7.605162346115224e-06, + "loss": 1.5746, + "step": 64390 + }, + { + "epoch": 2.4, + "learning_rate": 7.604790419161677e-06, + "loss": 1.7065, + "step": 64400 + }, + { + "epoch": 2.4, + "eval_loss": 1.6881874799728394, + "eval_runtime": 16.8353, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 64400 + }, + { + "epoch": 2.4, + "learning_rate": 7.604418492208131e-06, + "loss": 1.8269, + "step": 64410 + }, + { + "epoch": 2.4, + "learning_rate": 7.604046565254585e-06, + "loss": 1.6758, + "step": 64420 + }, + { + "epoch": 2.4, + "learning_rate": 7.603674638301038e-06, + "loss": 1.6808, + "step": 64430 + }, + { + "epoch": 2.4, + "learning_rate": 7.603302711347493e-06, + "loss": 1.8036, + "step": 64440 + }, + { + "epoch": 2.4, + "learning_rate": 7.602930784393946e-06, + "loss": 1.671, + "step": 64450 + }, + { + "epoch": 2.4, + "learning_rate": 7.6025588574403995e-06, + "loss": 1.771, + "step": 64460 + }, + { + "epoch": 2.4, + "learning_rate": 7.602186930486853e-06, + "loss": 1.7234, + "step": 64470 + }, + { + "epoch": 2.4, + "learning_rate": 7.601815003533307e-06, + "loss": 1.7495, + "step": 64480 + }, + { + "epoch": 2.4, + "learning_rate": 7.601443076579761e-06, + "loss": 1.7937, + "step": 64490 + }, + { + "epoch": 2.4, + "learning_rate": 7.601071149626213e-06, + "loss": 1.6976, + "step": 64500 + }, + { + "epoch": 2.4, + "eval_loss": 1.6885833740234375, + "eval_runtime": 16.8454, + "eval_samples_per_second": 59.363, + "eval_steps_per_second": 3.74, + "step": 64500 + }, + { + "epoch": 2.4, + "learning_rate": 7.600699222672667e-06, + "loss": 1.7545, + "step": 64510 + }, + { + "epoch": 2.4, + "learning_rate": 7.600327295719121e-06, + "loss": 1.7343, + "step": 64520 + }, + { + "epoch": 2.4, + "learning_rate": 7.599955368765575e-06, + "loss": 1.831, + "step": 64530 + }, + { + "epoch": 2.4, + "learning_rate": 7.599583441812028e-06, + "loss": 1.7829, + "step": 64540 + }, + { + "epoch": 2.4, + "learning_rate": 7.599211514858482e-06, + "loss": 1.9261, + "step": 64550 + }, + { + "epoch": 2.4, + "learning_rate": 7.598839587904936e-06, + "loss": 1.8906, + "step": 64560 + }, + { + "epoch": 2.4, + "learning_rate": 7.598467660951389e-06, + "loss": 1.7055, + "step": 64570 + }, + { + "epoch": 2.4, + "learning_rate": 7.598095733997844e-06, + "loss": 1.774, + "step": 64580 + }, + { + "epoch": 2.4, + "learning_rate": 7.597723807044297e-06, + "loss": 1.726, + "step": 64590 + }, + { + "epoch": 2.4, + "learning_rate": 7.5973518800907505e-06, + "loss": 1.5738, + "step": 64600 + }, + { + "epoch": 2.4, + "eval_loss": 1.6891143321990967, + "eval_runtime": 16.8478, + "eval_samples_per_second": 59.355, + "eval_steps_per_second": 3.739, + "step": 64600 + }, + { + "epoch": 2.4, + "learning_rate": 7.596979953137205e-06, + "loss": 1.686, + "step": 64610 + }, + { + "epoch": 2.4, + "learning_rate": 7.596608026183658e-06, + "loss": 1.7965, + "step": 64620 + }, + { + "epoch": 2.4, + "learning_rate": 7.596236099230112e-06, + "loss": 1.7323, + "step": 64630 + }, + { + "epoch": 2.4, + "learning_rate": 7.595864172276566e-06, + "loss": 1.8729, + "step": 64640 + }, + { + "epoch": 2.4, + "learning_rate": 7.5954922453230195e-06, + "loss": 1.7471, + "step": 64650 + }, + { + "epoch": 2.4, + "learning_rate": 7.595120318369473e-06, + "loss": 1.6583, + "step": 64660 + }, + { + "epoch": 2.41, + "learning_rate": 7.594748391415927e-06, + "loss": 1.6396, + "step": 64670 + }, + { + "epoch": 2.41, + "learning_rate": 7.594376464462381e-06, + "loss": 1.6644, + "step": 64680 + }, + { + "epoch": 2.41, + "learning_rate": 7.594004537508833e-06, + "loss": 1.7472, + "step": 64690 + }, + { + "epoch": 2.41, + "learning_rate": 7.593632610555287e-06, + "loss": 1.8007, + "step": 64700 + }, + { + "epoch": 2.41, + "eval_loss": 1.6879645586013794, + "eval_runtime": 16.8465, + "eval_samples_per_second": 59.359, + "eval_steps_per_second": 3.74, + "step": 64700 + }, + { + "epoch": 2.41, + "learning_rate": 7.593260683601741e-06, + "loss": 1.6933, + "step": 64710 + }, + { + "epoch": 2.41, + "learning_rate": 7.5928887566481946e-06, + "loss": 1.7791, + "step": 64720 + }, + { + "epoch": 2.41, + "learning_rate": 7.592516829694648e-06, + "loss": 1.7335, + "step": 64730 + }, + { + "epoch": 2.41, + "learning_rate": 7.592144902741102e-06, + "loss": 1.5846, + "step": 64740 + }, + { + "epoch": 2.41, + "learning_rate": 7.591772975787556e-06, + "loss": 1.6997, + "step": 64750 + }, + { + "epoch": 2.41, + "learning_rate": 7.591401048834009e-06, + "loss": 1.7325, + "step": 64760 + }, + { + "epoch": 2.41, + "learning_rate": 7.5910291218804635e-06, + "loss": 1.6728, + "step": 64770 + }, + { + "epoch": 2.41, + "learning_rate": 7.590657194926917e-06, + "loss": 1.7408, + "step": 64780 + }, + { + "epoch": 2.41, + "learning_rate": 7.5902852679733705e-06, + "loss": 1.7004, + "step": 64790 + }, + { + "epoch": 2.41, + "learning_rate": 7.589913341019825e-06, + "loss": 1.689, + "step": 64800 + }, + { + "epoch": 2.41, + "eval_loss": 1.6890382766723633, + "eval_runtime": 16.8599, + "eval_samples_per_second": 59.312, + "eval_steps_per_second": 3.737, + "step": 64800 + }, + { + "epoch": 2.41, + "learning_rate": 7.589541414066278e-06, + "loss": 1.725, + "step": 64810 + }, + { + "epoch": 2.41, + "learning_rate": 7.589169487112732e-06, + "loss": 1.7503, + "step": 64820 + }, + { + "epoch": 2.41, + "learning_rate": 7.588797560159186e-06, + "loss": 1.8383, + "step": 64830 + }, + { + "epoch": 2.41, + "learning_rate": 7.5884256332056395e-06, + "loss": 1.7434, + "step": 64840 + }, + { + "epoch": 2.41, + "learning_rate": 7.588053706252093e-06, + "loss": 1.742, + "step": 64850 + }, + { + "epoch": 2.41, + "learning_rate": 7.587681779298547e-06, + "loss": 1.5913, + "step": 64860 + }, + { + "epoch": 2.41, + "learning_rate": 7.587309852345001e-06, + "loss": 1.8153, + "step": 64870 + }, + { + "epoch": 2.41, + "learning_rate": 7.586937925391453e-06, + "loss": 1.7021, + "step": 64880 + }, + { + "epoch": 2.41, + "learning_rate": 7.586565998437907e-06, + "loss": 1.6319, + "step": 64890 + }, + { + "epoch": 2.41, + "learning_rate": 7.586194071484361e-06, + "loss": 1.7841, + "step": 64900 + }, + { + "epoch": 2.41, + "eval_loss": 1.6888974905014038, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 64900 + }, + { + "epoch": 2.41, + "learning_rate": 7.5858221445308145e-06, + "loss": 1.6682, + "step": 64910 + }, + { + "epoch": 2.41, + "learning_rate": 7.585450217577268e-06, + "loss": 1.7878, + "step": 64920 + }, + { + "epoch": 2.41, + "learning_rate": 7.585078290623722e-06, + "loss": 1.7278, + "step": 64930 + }, + { + "epoch": 2.42, + "learning_rate": 7.584706363670176e-06, + "loss": 1.7108, + "step": 64940 + }, + { + "epoch": 2.42, + "learning_rate": 7.584334436716629e-06, + "loss": 1.9271, + "step": 64950 + }, + { + "epoch": 2.42, + "learning_rate": 7.5839625097630835e-06, + "loss": 1.8345, + "step": 64960 + }, + { + "epoch": 2.42, + "learning_rate": 7.583590582809537e-06, + "loss": 1.8235, + "step": 64970 + }, + { + "epoch": 2.42, + "learning_rate": 7.58321865585599e-06, + "loss": 1.6532, + "step": 64980 + }, + { + "epoch": 2.42, + "learning_rate": 7.582846728902445e-06, + "loss": 1.76, + "step": 64990 + }, + { + "epoch": 2.42, + "learning_rate": 7.582474801948898e-06, + "loss": 1.6373, + "step": 65000 + }, + { + "epoch": 2.42, + "eval_loss": 1.6879466772079468, + "eval_runtime": 16.8339, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 65000 + }, + { + "epoch": 2.42, + "learning_rate": 7.582102874995352e-06, + "loss": 1.6793, + "step": 65010 + }, + { + "epoch": 2.42, + "learning_rate": 7.581730948041806e-06, + "loss": 1.7739, + "step": 65020 + }, + { + "epoch": 2.42, + "learning_rate": 7.581359021088259e-06, + "loss": 1.7402, + "step": 65030 + }, + { + "epoch": 2.42, + "learning_rate": 7.580987094134713e-06, + "loss": 1.8254, + "step": 65040 + }, + { + "epoch": 2.42, + "learning_rate": 7.580615167181166e-06, + "loss": 1.7203, + "step": 65050 + }, + { + "epoch": 2.42, + "learning_rate": 7.58024324022762e-06, + "loss": 1.7211, + "step": 65060 + }, + { + "epoch": 2.42, + "learning_rate": 7.579871313274073e-06, + "loss": 1.7439, + "step": 65070 + }, + { + "epoch": 2.42, + "learning_rate": 7.579499386320527e-06, + "loss": 1.8071, + "step": 65080 + }, + { + "epoch": 2.42, + "learning_rate": 7.57912745936698e-06, + "loss": 1.6034, + "step": 65090 + }, + { + "epoch": 2.42, + "learning_rate": 7.5787555324134345e-06, + "loss": 1.8271, + "step": 65100 + }, + { + "epoch": 2.42, + "eval_loss": 1.6881800889968872, + "eval_runtime": 16.8411, + "eval_samples_per_second": 59.378, + "eval_steps_per_second": 3.741, + "step": 65100 + }, + { + "epoch": 2.42, + "learning_rate": 7.578383605459888e-06, + "loss": 1.7169, + "step": 65110 + }, + { + "epoch": 2.42, + "learning_rate": 7.578011678506341e-06, + "loss": 1.6889, + "step": 65120 + }, + { + "epoch": 2.42, + "learning_rate": 7.577639751552796e-06, + "loss": 1.8214, + "step": 65130 + }, + { + "epoch": 2.42, + "learning_rate": 7.577267824599249e-06, + "loss": 1.6907, + "step": 65140 + }, + { + "epoch": 2.42, + "learning_rate": 7.576895897645703e-06, + "loss": 1.9133, + "step": 65150 + }, + { + "epoch": 2.42, + "learning_rate": 7.576523970692157e-06, + "loss": 1.8309, + "step": 65160 + }, + { + "epoch": 2.42, + "learning_rate": 7.57615204373861e-06, + "loss": 1.7608, + "step": 65170 + }, + { + "epoch": 2.42, + "learning_rate": 7.575780116785064e-06, + "loss": 1.66, + "step": 65180 + }, + { + "epoch": 2.42, + "learning_rate": 7.575408189831518e-06, + "loss": 1.778, + "step": 65190 + }, + { + "epoch": 2.42, + "learning_rate": 7.575036262877972e-06, + "loss": 1.6634, + "step": 65200 + }, + { + "epoch": 2.42, + "eval_loss": 1.6874154806137085, + "eval_runtime": 16.8366, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 65200 + }, + { + "epoch": 2.43, + "learning_rate": 7.574664335924425e-06, + "loss": 1.6529, + "step": 65210 + }, + { + "epoch": 2.43, + "learning_rate": 7.574292408970879e-06, + "loss": 1.9119, + "step": 65220 + }, + { + "epoch": 2.43, + "learning_rate": 7.573920482017333e-06, + "loss": 1.699, + "step": 65230 + }, + { + "epoch": 2.43, + "learning_rate": 7.573548555063786e-06, + "loss": 1.6772, + "step": 65240 + }, + { + "epoch": 2.43, + "learning_rate": 7.573176628110239e-06, + "loss": 1.729, + "step": 65250 + }, + { + "epoch": 2.43, + "learning_rate": 7.572804701156693e-06, + "loss": 1.709, + "step": 65260 + }, + { + "epoch": 2.43, + "learning_rate": 7.572432774203147e-06, + "loss": 1.891, + "step": 65270 + }, + { + "epoch": 2.43, + "learning_rate": 7.5720608472496e-06, + "loss": 1.7028, + "step": 65280 + }, + { + "epoch": 2.43, + "learning_rate": 7.5716889202960544e-06, + "loss": 1.8434, + "step": 65290 + }, + { + "epoch": 2.43, + "learning_rate": 7.571316993342508e-06, + "loss": 1.7089, + "step": 65300 + }, + { + "epoch": 2.43, + "eval_loss": 1.6872700452804565, + "eval_runtime": 16.8553, + "eval_samples_per_second": 59.328, + "eval_steps_per_second": 3.738, + "step": 65300 + }, + { + "epoch": 2.43, + "learning_rate": 7.570945066388961e-06, + "loss": 1.7234, + "step": 65310 + }, + { + "epoch": 2.43, + "learning_rate": 7.570573139435416e-06, + "loss": 1.7144, + "step": 65320 + }, + { + "epoch": 2.43, + "learning_rate": 7.570201212481869e-06, + "loss": 1.6419, + "step": 65330 + }, + { + "epoch": 2.43, + "learning_rate": 7.5698292855283226e-06, + "loss": 1.6451, + "step": 65340 + }, + { + "epoch": 2.43, + "learning_rate": 7.569457358574777e-06, + "loss": 1.7226, + "step": 65350 + }, + { + "epoch": 2.43, + "learning_rate": 7.56908543162123e-06, + "loss": 1.8013, + "step": 65360 + }, + { + "epoch": 2.43, + "learning_rate": 7.568713504667684e-06, + "loss": 1.6998, + "step": 65370 + }, + { + "epoch": 2.43, + "learning_rate": 7.568341577714138e-06, + "loss": 1.7061, + "step": 65380 + }, + { + "epoch": 2.43, + "learning_rate": 7.5679696507605916e-06, + "loss": 1.7647, + "step": 65390 + }, + { + "epoch": 2.43, + "learning_rate": 7.567597723807045e-06, + "loss": 1.7465, + "step": 65400 + }, + { + "epoch": 2.43, + "eval_loss": 1.6875652074813843, + "eval_runtime": 16.8424, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 65400 + }, + { + "epoch": 2.43, + "learning_rate": 7.567225796853499e-06, + "loss": 1.8039, + "step": 65410 + }, + { + "epoch": 2.43, + "learning_rate": 7.566853869899953e-06, + "loss": 1.7243, + "step": 65420 + }, + { + "epoch": 2.43, + "learning_rate": 7.566481942946406e-06, + "loss": 1.7379, + "step": 65430 + }, + { + "epoch": 2.43, + "learning_rate": 7.566110015992859e-06, + "loss": 1.6179, + "step": 65440 + }, + { + "epoch": 2.43, + "learning_rate": 7.565738089039313e-06, + "loss": 1.6126, + "step": 65450 + }, + { + "epoch": 2.43, + "learning_rate": 7.565366162085767e-06, + "loss": 1.6771, + "step": 65460 + }, + { + "epoch": 2.44, + "learning_rate": 7.56499423513222e-06, + "loss": 1.8606, + "step": 65470 + }, + { + "epoch": 2.44, + "learning_rate": 7.564622308178674e-06, + "loss": 1.8346, + "step": 65480 + }, + { + "epoch": 2.44, + "learning_rate": 7.564250381225128e-06, + "loss": 1.7433, + "step": 65490 + }, + { + "epoch": 2.44, + "learning_rate": 7.563878454271581e-06, + "loss": 1.5848, + "step": 65500 + }, + { + "epoch": 2.44, + "eval_loss": 1.6874223947525024, + "eval_runtime": 16.8233, + "eval_samples_per_second": 59.441, + "eval_steps_per_second": 3.745, + "step": 65500 + }, + { + "epoch": 2.44, + "learning_rate": 7.563506527318036e-06, + "loss": 1.7499, + "step": 65510 + }, + { + "epoch": 2.44, + "learning_rate": 7.563134600364489e-06, + "loss": 1.7259, + "step": 65520 + }, + { + "epoch": 2.44, + "learning_rate": 7.5627626734109425e-06, + "loss": 1.7846, + "step": 65530 + }, + { + "epoch": 2.44, + "learning_rate": 7.562390746457397e-06, + "loss": 1.7712, + "step": 65540 + }, + { + "epoch": 2.44, + "learning_rate": 7.56201881950385e-06, + "loss": 1.699, + "step": 65550 + }, + { + "epoch": 2.44, + "learning_rate": 7.561646892550304e-06, + "loss": 1.7657, + "step": 65560 + }, + { + "epoch": 2.44, + "learning_rate": 7.561274965596758e-06, + "loss": 1.7063, + "step": 65570 + }, + { + "epoch": 2.44, + "learning_rate": 7.5609030386432115e-06, + "loss": 1.6502, + "step": 65580 + }, + { + "epoch": 2.44, + "learning_rate": 7.560531111689665e-06, + "loss": 1.6752, + "step": 65590 + }, + { + "epoch": 2.44, + "learning_rate": 7.560159184736119e-06, + "loss": 1.7586, + "step": 65600 + }, + { + "epoch": 2.44, + "eval_loss": 1.6858915090560913, + "eval_runtime": 16.8399, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 65600 + }, + { + "epoch": 2.44, + "learning_rate": 7.559787257782573e-06, + "loss": 1.7546, + "step": 65610 + }, + { + "epoch": 2.44, + "learning_rate": 7.559415330829026e-06, + "loss": 1.7744, + "step": 65620 + }, + { + "epoch": 2.44, + "learning_rate": 7.559043403875479e-06, + "loss": 1.8066, + "step": 65630 + }, + { + "epoch": 2.44, + "learning_rate": 7.558671476921933e-06, + "loss": 1.7545, + "step": 65640 + }, + { + "epoch": 2.44, + "learning_rate": 7.558299549968387e-06, + "loss": 1.7221, + "step": 65650 + }, + { + "epoch": 2.44, + "learning_rate": 7.55792762301484e-06, + "loss": 1.7312, + "step": 65660 + }, + { + "epoch": 2.44, + "learning_rate": 7.5575556960612935e-06, + "loss": 1.7201, + "step": 65670 + }, + { + "epoch": 2.44, + "learning_rate": 7.557183769107748e-06, + "loss": 1.7518, + "step": 65680 + }, + { + "epoch": 2.44, + "learning_rate": 7.556811842154201e-06, + "loss": 1.7182, + "step": 65690 + }, + { + "epoch": 2.44, + "learning_rate": 7.556439915200655e-06, + "loss": 1.6529, + "step": 65700 + }, + { + "epoch": 2.44, + "eval_loss": 1.6868915557861328, + "eval_runtime": 16.8733, + "eval_samples_per_second": 59.265, + "eval_steps_per_second": 3.734, + "step": 65700 + }, + { + "epoch": 2.44, + "learning_rate": 7.556067988247109e-06, + "loss": 1.8359, + "step": 65710 + }, + { + "epoch": 2.44, + "learning_rate": 7.5556960612935625e-06, + "loss": 1.7489, + "step": 65720 + }, + { + "epoch": 2.44, + "learning_rate": 7.555324134340016e-06, + "loss": 1.7532, + "step": 65730 + }, + { + "epoch": 2.45, + "learning_rate": 7.55495220738647e-06, + "loss": 1.7399, + "step": 65740 + }, + { + "epoch": 2.45, + "learning_rate": 7.554580280432924e-06, + "loss": 1.7493, + "step": 65750 + }, + { + "epoch": 2.45, + "learning_rate": 7.554208353479377e-06, + "loss": 1.6671, + "step": 65760 + }, + { + "epoch": 2.45, + "learning_rate": 7.5538364265258315e-06, + "loss": 1.7173, + "step": 65770 + }, + { + "epoch": 2.45, + "learning_rate": 7.553464499572285e-06, + "loss": 1.8699, + "step": 65780 + }, + { + "epoch": 2.45, + "learning_rate": 7.553092572618738e-06, + "loss": 1.8572, + "step": 65790 + }, + { + "epoch": 2.45, + "learning_rate": 7.552720645665193e-06, + "loss": 1.9865, + "step": 65800 + }, + { + "epoch": 2.45, + "eval_loss": 1.6858271360397339, + "eval_runtime": 16.8347, + "eval_samples_per_second": 59.401, + "eval_steps_per_second": 3.742, + "step": 65800 + }, + { + "epoch": 2.45, + "learning_rate": 7.552348718711645e-06, + "loss": 1.8561, + "step": 65810 + }, + { + "epoch": 2.45, + "learning_rate": 7.551976791758099e-06, + "loss": 1.7662, + "step": 65820 + }, + { + "epoch": 2.45, + "learning_rate": 7.551604864804552e-06, + "loss": 1.7886, + "step": 65830 + }, + { + "epoch": 2.45, + "learning_rate": 7.5512329378510065e-06, + "loss": 1.8307, + "step": 65840 + }, + { + "epoch": 2.45, + "learning_rate": 7.55086101089746e-06, + "loss": 1.7387, + "step": 65850 + }, + { + "epoch": 2.45, + "learning_rate": 7.5504890839439135e-06, + "loss": 1.6516, + "step": 65860 + }, + { + "epoch": 2.45, + "learning_rate": 7.550117156990368e-06, + "loss": 1.7558, + "step": 65870 + }, + { + "epoch": 2.45, + "learning_rate": 7.549745230036821e-06, + "loss": 1.7159, + "step": 65880 + }, + { + "epoch": 2.45, + "learning_rate": 7.549373303083275e-06, + "loss": 1.6835, + "step": 65890 + }, + { + "epoch": 2.45, + "learning_rate": 7.549001376129729e-06, + "loss": 1.6604, + "step": 65900 + }, + { + "epoch": 2.45, + "eval_loss": 1.685881495475769, + "eval_runtime": 16.8313, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 65900 + }, + { + "epoch": 2.45, + "learning_rate": 7.5486294491761825e-06, + "loss": 1.7324, + "step": 65910 + }, + { + "epoch": 2.45, + "learning_rate": 7.548257522222636e-06, + "loss": 1.7458, + "step": 65920 + }, + { + "epoch": 2.45, + "learning_rate": 7.54788559526909e-06, + "loss": 1.8252, + "step": 65930 + }, + { + "epoch": 2.45, + "learning_rate": 7.547513668315544e-06, + "loss": 1.8326, + "step": 65940 + }, + { + "epoch": 2.45, + "learning_rate": 7.547141741361997e-06, + "loss": 1.7136, + "step": 65950 + }, + { + "epoch": 2.45, + "learning_rate": 7.5467698144084514e-06, + "loss": 1.6312, + "step": 65960 + }, + { + "epoch": 2.45, + "learning_rate": 7.546397887454905e-06, + "loss": 1.6164, + "step": 65970 + }, + { + "epoch": 2.45, + "learning_rate": 7.546025960501358e-06, + "loss": 1.8656, + "step": 65980 + }, + { + "epoch": 2.45, + "learning_rate": 7.545654033547813e-06, + "loss": 1.8436, + "step": 65990 + }, + { + "epoch": 2.45, + "learning_rate": 7.545282106594265e-06, + "loss": 1.7038, + "step": 66000 + }, + { + "epoch": 2.45, + "eval_loss": 1.6862406730651855, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 66000 + }, + { + "epoch": 2.46, + "learning_rate": 7.544910179640719e-06, + "loss": 1.7514, + "step": 66010 + }, + { + "epoch": 2.46, + "learning_rate": 7.544538252687172e-06, + "loss": 1.6316, + "step": 66020 + }, + { + "epoch": 2.46, + "learning_rate": 7.5441663257336265e-06, + "loss": 1.7517, + "step": 66030 + }, + { + "epoch": 2.46, + "learning_rate": 7.54379439878008e-06, + "loss": 1.718, + "step": 66040 + }, + { + "epoch": 2.46, + "learning_rate": 7.543422471826533e-06, + "loss": 1.7855, + "step": 66050 + }, + { + "epoch": 2.46, + "learning_rate": 7.543050544872988e-06, + "loss": 1.6928, + "step": 66060 + }, + { + "epoch": 2.46, + "learning_rate": 7.542678617919441e-06, + "loss": 1.7159, + "step": 66070 + }, + { + "epoch": 2.46, + "learning_rate": 7.542306690965895e-06, + "loss": 1.798, + "step": 66080 + }, + { + "epoch": 2.46, + "learning_rate": 7.541934764012349e-06, + "loss": 1.7765, + "step": 66090 + }, + { + "epoch": 2.46, + "learning_rate": 7.541562837058802e-06, + "loss": 1.639, + "step": 66100 + }, + { + "epoch": 2.46, + "eval_loss": 1.685675024986267, + "eval_runtime": 16.8355, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 66100 + }, + { + "epoch": 2.46, + "learning_rate": 7.541190910105256e-06, + "loss": 1.6783, + "step": 66110 + }, + { + "epoch": 2.46, + "learning_rate": 7.54081898315171e-06, + "loss": 1.7336, + "step": 66120 + }, + { + "epoch": 2.46, + "learning_rate": 7.540447056198164e-06, + "loss": 1.783, + "step": 66130 + }, + { + "epoch": 2.46, + "learning_rate": 7.540075129244617e-06, + "loss": 1.6161, + "step": 66140 + }, + { + "epoch": 2.46, + "learning_rate": 7.539703202291071e-06, + "loss": 1.9002, + "step": 66150 + }, + { + "epoch": 2.46, + "learning_rate": 7.539331275337525e-06, + "loss": 1.7117, + "step": 66160 + }, + { + "epoch": 2.46, + "learning_rate": 7.538959348383978e-06, + "loss": 1.8759, + "step": 66170 + }, + { + "epoch": 2.46, + "learning_rate": 7.538587421430433e-06, + "loss": 1.74, + "step": 66180 + }, + { + "epoch": 2.46, + "learning_rate": 7.538215494476885e-06, + "loss": 1.7667, + "step": 66190 + }, + { + "epoch": 2.46, + "learning_rate": 7.537843567523339e-06, + "loss": 1.7094, + "step": 66200 + }, + { + "epoch": 2.46, + "eval_loss": 1.6854233741760254, + "eval_runtime": 16.8574, + "eval_samples_per_second": 59.321, + "eval_steps_per_second": 3.737, + "step": 66200 + }, + { + "epoch": 2.46, + "learning_rate": 7.537471640569792e-06, + "loss": 1.6334, + "step": 66210 + }, + { + "epoch": 2.46, + "learning_rate": 7.537099713616246e-06, + "loss": 1.5872, + "step": 66220 + }, + { + "epoch": 2.46, + "learning_rate": 7.5367277866627e-06, + "loss": 1.6379, + "step": 66230 + }, + { + "epoch": 2.46, + "learning_rate": 7.536355859709153e-06, + "loss": 1.8023, + "step": 66240 + }, + { + "epoch": 2.46, + "learning_rate": 7.535983932755607e-06, + "loss": 1.7507, + "step": 66250 + }, + { + "epoch": 2.46, + "learning_rate": 7.535612005802061e-06, + "loss": 1.7409, + "step": 66260 + }, + { + "epoch": 2.46, + "learning_rate": 7.535240078848515e-06, + "loss": 1.714, + "step": 66270 + }, + { + "epoch": 2.47, + "learning_rate": 7.534868151894968e-06, + "loss": 1.7408, + "step": 66280 + }, + { + "epoch": 2.47, + "learning_rate": 7.534496224941422e-06, + "loss": 1.7681, + "step": 66290 + }, + { + "epoch": 2.47, + "learning_rate": 7.534124297987876e-06, + "loss": 1.7988, + "step": 66300 + }, + { + "epoch": 2.47, + "eval_loss": 1.6855217218399048, + "eval_runtime": 16.8512, + "eval_samples_per_second": 59.343, + "eval_steps_per_second": 3.739, + "step": 66300 + }, + { + "epoch": 2.47, + "learning_rate": 7.533752371034329e-06, + "loss": 1.716, + "step": 66310 + }, + { + "epoch": 2.47, + "learning_rate": 7.533380444080784e-06, + "loss": 1.8581, + "step": 66320 + }, + { + "epoch": 2.47, + "learning_rate": 7.533008517127237e-06, + "loss": 1.8605, + "step": 66330 + }, + { + "epoch": 2.47, + "learning_rate": 7.5326365901736905e-06, + "loss": 1.6805, + "step": 66340 + }, + { + "epoch": 2.47, + "learning_rate": 7.532264663220145e-06, + "loss": 1.9215, + "step": 66350 + }, + { + "epoch": 2.47, + "learning_rate": 7.531892736266598e-06, + "loss": 1.7379, + "step": 66360 + }, + { + "epoch": 2.47, + "learning_rate": 7.531520809313052e-06, + "loss": 1.7936, + "step": 66370 + }, + { + "epoch": 2.47, + "learning_rate": 7.531148882359504e-06, + "loss": 1.7406, + "step": 66380 + }, + { + "epoch": 2.47, + "learning_rate": 7.530776955405959e-06, + "loss": 1.8472, + "step": 66390 + }, + { + "epoch": 2.47, + "learning_rate": 7.530405028452412e-06, + "loss": 1.7228, + "step": 66400 + }, + { + "epoch": 2.47, + "eval_loss": 1.6851645708084106, + "eval_runtime": 16.8505, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 66400 + }, + { + "epoch": 2.47, + "learning_rate": 7.5300331014988656e-06, + "loss": 1.5773, + "step": 66410 + }, + { + "epoch": 2.47, + "learning_rate": 7.52966117454532e-06, + "loss": 1.6687, + "step": 66420 + }, + { + "epoch": 2.47, + "learning_rate": 7.529289247591773e-06, + "loss": 1.7908, + "step": 66430 + }, + { + "epoch": 2.47, + "learning_rate": 7.528917320638227e-06, + "loss": 1.7422, + "step": 66440 + }, + { + "epoch": 2.47, + "learning_rate": 7.528545393684681e-06, + "loss": 1.6228, + "step": 66450 + }, + { + "epoch": 2.47, + "learning_rate": 7.5281734667311346e-06, + "loss": 1.8393, + "step": 66460 + }, + { + "epoch": 2.47, + "learning_rate": 7.527801539777588e-06, + "loss": 1.6805, + "step": 66470 + }, + { + "epoch": 2.47, + "learning_rate": 7.527429612824042e-06, + "loss": 1.6802, + "step": 66480 + }, + { + "epoch": 2.47, + "learning_rate": 7.527057685870496e-06, + "loss": 1.6383, + "step": 66490 + }, + { + "epoch": 2.47, + "learning_rate": 7.526685758916949e-06, + "loss": 1.6714, + "step": 66500 + }, + { + "epoch": 2.47, + "eval_loss": 1.685623288154602, + "eval_runtime": 16.8384, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 66500 + }, + { + "epoch": 2.47, + "learning_rate": 7.5263138319634036e-06, + "loss": 1.8531, + "step": 66510 + }, + { + "epoch": 2.47, + "learning_rate": 7.525941905009857e-06, + "loss": 1.6815, + "step": 66520 + }, + { + "epoch": 2.47, + "learning_rate": 7.5255699780563105e-06, + "loss": 1.7302, + "step": 66530 + }, + { + "epoch": 2.47, + "learning_rate": 7.525198051102765e-06, + "loss": 1.6819, + "step": 66540 + }, + { + "epoch": 2.48, + "learning_rate": 7.524826124149218e-06, + "loss": 1.6444, + "step": 66550 + }, + { + "epoch": 2.48, + "learning_rate": 7.524454197195672e-06, + "loss": 1.7218, + "step": 66560 + }, + { + "epoch": 2.48, + "learning_rate": 7.524082270242124e-06, + "loss": 1.5833, + "step": 66570 + }, + { + "epoch": 2.48, + "learning_rate": 7.523710343288579e-06, + "loss": 1.8263, + "step": 66580 + }, + { + "epoch": 2.48, + "learning_rate": 7.523338416335032e-06, + "loss": 1.6759, + "step": 66590 + }, + { + "epoch": 2.48, + "learning_rate": 7.5229664893814855e-06, + "loss": 1.9002, + "step": 66600 + }, + { + "epoch": 2.48, + "eval_loss": 1.6845818758010864, + "eval_runtime": 16.8497, + "eval_samples_per_second": 59.348, + "eval_steps_per_second": 3.739, + "step": 66600 + }, + { + "epoch": 2.48, + "learning_rate": 7.52259456242794e-06, + "loss": 1.7431, + "step": 66610 + }, + { + "epoch": 2.48, + "learning_rate": 7.522222635474393e-06, + "loss": 1.8282, + "step": 66620 + }, + { + "epoch": 2.48, + "learning_rate": 7.521850708520847e-06, + "loss": 1.7625, + "step": 66630 + }, + { + "epoch": 2.48, + "learning_rate": 7.521478781567301e-06, + "loss": 1.6953, + "step": 66640 + }, + { + "epoch": 2.48, + "learning_rate": 7.5211068546137545e-06, + "loss": 1.6587, + "step": 66650 + }, + { + "epoch": 2.48, + "learning_rate": 7.520734927660208e-06, + "loss": 1.6996, + "step": 66660 + }, + { + "epoch": 2.48, + "learning_rate": 7.520363000706662e-06, + "loss": 1.6757, + "step": 66670 + }, + { + "epoch": 2.48, + "learning_rate": 7.519991073753116e-06, + "loss": 1.7873, + "step": 66680 + }, + { + "epoch": 2.48, + "learning_rate": 7.519619146799569e-06, + "loss": 1.6898, + "step": 66690 + }, + { + "epoch": 2.48, + "learning_rate": 7.5192472198460235e-06, + "loss": 1.7376, + "step": 66700 + }, + { + "epoch": 2.48, + "eval_loss": 1.6860891580581665, + "eval_runtime": 16.8525, + "eval_samples_per_second": 59.338, + "eval_steps_per_second": 3.738, + "step": 66700 + }, + { + "epoch": 2.48, + "learning_rate": 7.518875292892477e-06, + "loss": 1.6307, + "step": 66710 + }, + { + "epoch": 2.48, + "learning_rate": 7.5185033659389304e-06, + "loss": 1.6651, + "step": 66720 + }, + { + "epoch": 2.48, + "learning_rate": 7.518131438985385e-06, + "loss": 1.8139, + "step": 66730 + }, + { + "epoch": 2.48, + "learning_rate": 7.517759512031838e-06, + "loss": 1.7488, + "step": 66740 + }, + { + "epoch": 2.48, + "learning_rate": 7.517387585078291e-06, + "loss": 1.576, + "step": 66750 + }, + { + "epoch": 2.48, + "learning_rate": 7.517015658124744e-06, + "loss": 1.6586, + "step": 66760 + }, + { + "epoch": 2.48, + "learning_rate": 7.5166437311711986e-06, + "loss": 1.6508, + "step": 66770 + }, + { + "epoch": 2.48, + "learning_rate": 7.516271804217652e-06, + "loss": 1.7795, + "step": 66780 + }, + { + "epoch": 2.48, + "learning_rate": 7.5158998772641055e-06, + "loss": 1.8042, + "step": 66790 + }, + { + "epoch": 2.48, + "learning_rate": 7.515527950310559e-06, + "loss": 1.6478, + "step": 66800 + }, + { + "epoch": 2.48, + "eval_loss": 1.6841731071472168, + "eval_runtime": 16.8524, + "eval_samples_per_second": 59.339, + "eval_steps_per_second": 3.738, + "step": 66800 + }, + { + "epoch": 2.48, + "learning_rate": 7.515156023357013e-06, + "loss": 1.7727, + "step": 66810 + }, + { + "epoch": 2.49, + "learning_rate": 7.514784096403467e-06, + "loss": 1.7218, + "step": 66820 + }, + { + "epoch": 2.49, + "learning_rate": 7.51441216944992e-06, + "loss": 1.7297, + "step": 66830 + }, + { + "epoch": 2.49, + "learning_rate": 7.5140402424963745e-06, + "loss": 1.7102, + "step": 66840 + }, + { + "epoch": 2.49, + "learning_rate": 7.513668315542828e-06, + "loss": 1.9471, + "step": 66850 + }, + { + "epoch": 2.49, + "learning_rate": 7.513296388589281e-06, + "loss": 1.7113, + "step": 66860 + }, + { + "epoch": 2.49, + "learning_rate": 7.512924461635736e-06, + "loss": 1.7742, + "step": 66870 + }, + { + "epoch": 2.49, + "learning_rate": 7.512552534682189e-06, + "loss": 1.8118, + "step": 66880 + }, + { + "epoch": 2.49, + "learning_rate": 7.512180607728643e-06, + "loss": 1.8063, + "step": 66890 + }, + { + "epoch": 2.49, + "learning_rate": 7.511808680775097e-06, + "loss": 1.6366, + "step": 66900 + }, + { + "epoch": 2.49, + "eval_loss": 1.6848491430282593, + "eval_runtime": 16.8529, + "eval_samples_per_second": 59.337, + "eval_steps_per_second": 3.738, + "step": 66900 + }, + { + "epoch": 2.49, + "learning_rate": 7.51143675382155e-06, + "loss": 1.6893, + "step": 66910 + }, + { + "epoch": 2.49, + "learning_rate": 7.511064826868004e-06, + "loss": 1.7167, + "step": 66920 + }, + { + "epoch": 2.49, + "learning_rate": 7.510692899914458e-06, + "loss": 1.6496, + "step": 66930 + }, + { + "epoch": 2.49, + "learning_rate": 7.510320972960911e-06, + "loss": 1.7113, + "step": 66940 + }, + { + "epoch": 2.49, + "learning_rate": 7.509949046007364e-06, + "loss": 1.8414, + "step": 66950 + }, + { + "epoch": 2.49, + "learning_rate": 7.509577119053818e-06, + "loss": 1.6683, + "step": 66960 + }, + { + "epoch": 2.49, + "learning_rate": 7.509205192100272e-06, + "loss": 1.7546, + "step": 66970 + }, + { + "epoch": 2.49, + "learning_rate": 7.5088332651467255e-06, + "loss": 1.7123, + "step": 66980 + }, + { + "epoch": 2.49, + "learning_rate": 7.508461338193179e-06, + "loss": 1.7782, + "step": 66990 + }, + { + "epoch": 2.49, + "learning_rate": 7.508089411239633e-06, + "loss": 1.9912, + "step": 67000 + }, + { + "epoch": 2.49, + "eval_loss": 1.6835581064224243, + "eval_runtime": 16.8416, + "eval_samples_per_second": 59.377, + "eval_steps_per_second": 3.741, + "step": 67000 + }, + { + "epoch": 2.49, + "learning_rate": 7.507717484286087e-06, + "loss": 1.6216, + "step": 67010 + }, + { + "epoch": 2.49, + "learning_rate": 7.50734555733254e-06, + "loss": 1.6473, + "step": 67020 + }, + { + "epoch": 2.49, + "learning_rate": 7.5069736303789944e-06, + "loss": 1.7244, + "step": 67030 + }, + { + "epoch": 2.49, + "learning_rate": 7.506601703425448e-06, + "loss": 1.9319, + "step": 67040 + }, + { + "epoch": 2.49, + "learning_rate": 7.506229776471901e-06, + "loss": 1.8479, + "step": 67050 + }, + { + "epoch": 2.49, + "learning_rate": 7.505857849518356e-06, + "loss": 1.7866, + "step": 67060 + }, + { + "epoch": 2.49, + "learning_rate": 7.505485922564809e-06, + "loss": 1.6913, + "step": 67070 + }, + { + "epoch": 2.49, + "learning_rate": 7.505113995611263e-06, + "loss": 1.7775, + "step": 67080 + }, + { + "epoch": 2.5, + "learning_rate": 7.504742068657717e-06, + "loss": 1.6951, + "step": 67090 + }, + { + "epoch": 2.5, + "learning_rate": 7.50437014170417e-06, + "loss": 1.6558, + "step": 67100 + }, + { + "epoch": 2.5, + "eval_loss": 1.6837866306304932, + "eval_runtime": 16.8401, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 67100 + }, + { + "epoch": 2.5, + "learning_rate": 7.503998214750624e-06, + "loss": 1.6157, + "step": 67110 + }, + { + "epoch": 2.5, + "learning_rate": 7.503626287797078e-06, + "loss": 1.7391, + "step": 67120 + }, + { + "epoch": 2.5, + "learning_rate": 7.503254360843531e-06, + "loss": 1.7702, + "step": 67130 + }, + { + "epoch": 2.5, + "learning_rate": 7.502882433889984e-06, + "loss": 1.684, + "step": 67140 + }, + { + "epoch": 2.5, + "learning_rate": 7.502510506936438e-06, + "loss": 1.7097, + "step": 67150 + }, + { + "epoch": 2.5, + "learning_rate": 7.502138579982892e-06, + "loss": 1.7437, + "step": 67160 + }, + { + "epoch": 2.5, + "learning_rate": 7.501766653029345e-06, + "loss": 1.7571, + "step": 67170 + }, + { + "epoch": 2.5, + "learning_rate": 7.501394726075799e-06, + "loss": 1.6508, + "step": 67180 + }, + { + "epoch": 2.5, + "learning_rate": 7.501022799122253e-06, + "loss": 1.781, + "step": 67190 + }, + { + "epoch": 2.5, + "learning_rate": 7.500650872168707e-06, + "loss": 1.7383, + "step": 67200 + }, + { + "epoch": 2.5, + "eval_loss": 1.685034990310669, + "eval_runtime": 16.8402, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 67200 + }, + { + "epoch": 2.5, + "learning_rate": 7.50027894521516e-06, + "loss": 1.7245, + "step": 67210 + }, + { + "epoch": 2.5, + "learning_rate": 7.499907018261614e-06, + "loss": 1.6165, + "step": 67220 + }, + { + "epoch": 2.5, + "learning_rate": 7.499535091308068e-06, + "loss": 1.8723, + "step": 67230 + }, + { + "epoch": 2.5, + "learning_rate": 7.499163164354521e-06, + "loss": 1.8225, + "step": 67240 + }, + { + "epoch": 2.5, + "learning_rate": 7.498791237400976e-06, + "loss": 1.8324, + "step": 67250 + }, + { + "epoch": 2.5, + "learning_rate": 7.498419310447429e-06, + "loss": 1.7552, + "step": 67260 + }, + { + "epoch": 2.5, + "learning_rate": 7.4980473834938825e-06, + "loss": 1.9442, + "step": 67270 + }, + { + "epoch": 2.5, + "learning_rate": 7.497675456540337e-06, + "loss": 1.808, + "step": 67280 + }, + { + "epoch": 2.5, + "learning_rate": 7.49730352958679e-06, + "loss": 1.6652, + "step": 67290 + }, + { + "epoch": 2.5, + "learning_rate": 7.496931602633244e-06, + "loss": 1.6552, + "step": 67300 + }, + { + "epoch": 2.5, + "eval_loss": 1.6835092306137085, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.743, + "step": 67300 + }, + { + "epoch": 2.5, + "learning_rate": 7.496559675679698e-06, + "loss": 1.8839, + "step": 67310 + }, + { + "epoch": 2.5, + "learning_rate": 7.496187748726151e-06, + "loss": 1.7319, + "step": 67320 + }, + { + "epoch": 2.5, + "learning_rate": 7.495815821772604e-06, + "loss": 1.726, + "step": 67330 + }, + { + "epoch": 2.5, + "learning_rate": 7.495443894819058e-06, + "loss": 1.7778, + "step": 67340 + }, + { + "epoch": 2.5, + "learning_rate": 7.495071967865512e-06, + "loss": 1.7384, + "step": 67350 + }, + { + "epoch": 2.51, + "learning_rate": 7.494700040911965e-06, + "loss": 1.692, + "step": 67360 + }, + { + "epoch": 2.51, + "learning_rate": 7.494328113958419e-06, + "loss": 1.603, + "step": 67370 + }, + { + "epoch": 2.51, + "learning_rate": 7.493956187004872e-06, + "loss": 1.769, + "step": 67380 + }, + { + "epoch": 2.51, + "learning_rate": 7.493584260051327e-06, + "loss": 2.0034, + "step": 67390 + }, + { + "epoch": 2.51, + "learning_rate": 7.49321233309778e-06, + "loss": 1.8007, + "step": 67400 + }, + { + "epoch": 2.51, + "eval_loss": 1.6838910579681396, + "eval_runtime": 16.8469, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 67400 + }, + { + "epoch": 2.51, + "learning_rate": 7.4928404061442335e-06, + "loss": 1.6937, + "step": 67410 + }, + { + "epoch": 2.51, + "learning_rate": 7.492468479190688e-06, + "loss": 1.6351, + "step": 67420 + }, + { + "epoch": 2.51, + "learning_rate": 7.492096552237141e-06, + "loss": 1.7593, + "step": 67430 + }, + { + "epoch": 2.51, + "learning_rate": 7.491724625283595e-06, + "loss": 1.6337, + "step": 67440 + }, + { + "epoch": 2.51, + "learning_rate": 7.491352698330049e-06, + "loss": 1.7942, + "step": 67450 + }, + { + "epoch": 2.51, + "learning_rate": 7.4909807713765025e-06, + "loss": 1.808, + "step": 67460 + }, + { + "epoch": 2.51, + "learning_rate": 7.490608844422956e-06, + "loss": 1.5828, + "step": 67470 + }, + { + "epoch": 2.51, + "learning_rate": 7.49023691746941e-06, + "loss": 1.757, + "step": 67480 + }, + { + "epoch": 2.51, + "learning_rate": 7.489864990515864e-06, + "loss": 1.7659, + "step": 67490 + }, + { + "epoch": 2.51, + "learning_rate": 7.489493063562316e-06, + "loss": 1.7336, + "step": 67500 + }, + { + "epoch": 2.51, + "eval_loss": 1.6840741634368896, + "eval_runtime": 16.842, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 67500 + }, + { + "epoch": 2.51, + "learning_rate": 7.48912113660877e-06, + "loss": 1.7601, + "step": 67510 + }, + { + "epoch": 2.51, + "learning_rate": 7.488749209655224e-06, + "loss": 1.7728, + "step": 67520 + }, + { + "epoch": 2.51, + "learning_rate": 7.4883772827016776e-06, + "loss": 1.6621, + "step": 67530 + }, + { + "epoch": 2.51, + "learning_rate": 7.488005355748131e-06, + "loss": 1.9596, + "step": 67540 + }, + { + "epoch": 2.51, + "learning_rate": 7.487633428794585e-06, + "loss": 1.8614, + "step": 67550 + }, + { + "epoch": 2.51, + "learning_rate": 7.487261501841039e-06, + "loss": 1.7635, + "step": 67560 + }, + { + "epoch": 2.51, + "learning_rate": 7.486889574887492e-06, + "loss": 1.6442, + "step": 67570 + }, + { + "epoch": 2.51, + "learning_rate": 7.4865176479339466e-06, + "loss": 1.7059, + "step": 67580 + }, + { + "epoch": 2.51, + "learning_rate": 7.4861457209804e-06, + "loss": 1.859, + "step": 67590 + }, + { + "epoch": 2.51, + "learning_rate": 7.4857737940268535e-06, + "loss": 1.83, + "step": 67600 + }, + { + "epoch": 2.51, + "eval_loss": 1.6844761371612549, + "eval_runtime": 16.8408, + "eval_samples_per_second": 59.379, + "eval_steps_per_second": 3.741, + "step": 67600 + }, + { + "epoch": 2.51, + "learning_rate": 7.485401867073308e-06, + "loss": 1.8084, + "step": 67610 + }, + { + "epoch": 2.51, + "learning_rate": 7.485029940119761e-06, + "loss": 1.7115, + "step": 67620 + }, + { + "epoch": 2.52, + "learning_rate": 7.484658013166215e-06, + "loss": 1.7306, + "step": 67630 + }, + { + "epoch": 2.52, + "learning_rate": 7.484286086212669e-06, + "loss": 1.768, + "step": 67640 + }, + { + "epoch": 2.52, + "learning_rate": 7.4839141592591225e-06, + "loss": 1.7028, + "step": 67650 + }, + { + "epoch": 2.52, + "learning_rate": 7.483542232305576e-06, + "loss": 1.8053, + "step": 67660 + }, + { + "epoch": 2.52, + "learning_rate": 7.48317030535203e-06, + "loss": 1.7199, + "step": 67670 + }, + { + "epoch": 2.52, + "learning_rate": 7.482798378398484e-06, + "loss": 1.6995, + "step": 67680 + }, + { + "epoch": 2.52, + "learning_rate": 7.482426451444936e-06, + "loss": 1.6626, + "step": 67690 + }, + { + "epoch": 2.52, + "learning_rate": 7.48205452449139e-06, + "loss": 1.5932, + "step": 67700 + }, + { + "epoch": 2.52, + "eval_loss": 1.682551622390747, + "eval_runtime": 16.8436, + "eval_samples_per_second": 59.37, + "eval_steps_per_second": 3.74, + "step": 67700 + }, + { + "epoch": 2.52, + "learning_rate": 7.481682597537844e-06, + "loss": 1.7439, + "step": 67710 + }, + { + "epoch": 2.52, + "learning_rate": 7.4813106705842975e-06, + "loss": 1.829, + "step": 67720 + }, + { + "epoch": 2.52, + "learning_rate": 7.480938743630751e-06, + "loss": 1.733, + "step": 67730 + }, + { + "epoch": 2.52, + "learning_rate": 7.480566816677205e-06, + "loss": 1.6445, + "step": 67740 + }, + { + "epoch": 2.52, + "learning_rate": 7.480194889723659e-06, + "loss": 1.7272, + "step": 67750 + }, + { + "epoch": 2.52, + "learning_rate": 7.479822962770112e-06, + "loss": 1.7383, + "step": 67760 + }, + { + "epoch": 2.52, + "learning_rate": 7.4794510358165665e-06, + "loss": 1.7537, + "step": 67770 + }, + { + "epoch": 2.52, + "learning_rate": 7.47907910886302e-06, + "loss": 1.6634, + "step": 67780 + }, + { + "epoch": 2.52, + "learning_rate": 7.4787071819094734e-06, + "loss": 1.638, + "step": 67790 + }, + { + "epoch": 2.52, + "learning_rate": 7.478335254955928e-06, + "loss": 1.7948, + "step": 67800 + }, + { + "epoch": 2.52, + "eval_loss": 1.6837698221206665, + "eval_runtime": 16.8632, + "eval_samples_per_second": 59.301, + "eval_steps_per_second": 3.736, + "step": 67800 + }, + { + "epoch": 2.52, + "learning_rate": 7.477963328002381e-06, + "loss": 1.6917, + "step": 67810 + }, + { + "epoch": 2.52, + "learning_rate": 7.477591401048835e-06, + "loss": 1.7107, + "step": 67820 + }, + { + "epoch": 2.52, + "learning_rate": 7.477219474095289e-06, + "loss": 1.8614, + "step": 67830 + }, + { + "epoch": 2.52, + "learning_rate": 7.476847547141742e-06, + "loss": 1.6821, + "step": 67840 + }, + { + "epoch": 2.52, + "learning_rate": 7.476475620188196e-06, + "loss": 1.5915, + "step": 67850 + }, + { + "epoch": 2.52, + "learning_rate": 7.47610369323465e-06, + "loss": 1.6413, + "step": 67860 + }, + { + "epoch": 2.52, + "learning_rate": 7.475731766281104e-06, + "loss": 1.7197, + "step": 67870 + }, + { + "epoch": 2.52, + "learning_rate": 7.475359839327556e-06, + "loss": 1.7695, + "step": 67880 + }, + { + "epoch": 2.53, + "learning_rate": 7.47498791237401e-06, + "loss": 1.7335, + "step": 67890 + }, + { + "epoch": 2.53, + "learning_rate": 7.474615985420464e-06, + "loss": 1.6675, + "step": 67900 + }, + { + "epoch": 2.53, + "eval_loss": 1.6830129623413086, + "eval_runtime": 16.8454, + "eval_samples_per_second": 59.363, + "eval_steps_per_second": 3.74, + "step": 67900 + }, + { + "epoch": 2.53, + "learning_rate": 7.4742440584669175e-06, + "loss": 1.6936, + "step": 67910 + }, + { + "epoch": 2.53, + "learning_rate": 7.473872131513371e-06, + "loss": 1.7771, + "step": 67920 + }, + { + "epoch": 2.53, + "learning_rate": 7.473500204559825e-06, + "loss": 1.7491, + "step": 67930 + }, + { + "epoch": 2.53, + "learning_rate": 7.473128277606279e-06, + "loss": 1.8084, + "step": 67940 + }, + { + "epoch": 2.53, + "learning_rate": 7.472756350652732e-06, + "loss": 1.6187, + "step": 67950 + }, + { + "epoch": 2.53, + "learning_rate": 7.472384423699186e-06, + "loss": 1.6876, + "step": 67960 + }, + { + "epoch": 2.53, + "learning_rate": 7.47201249674564e-06, + "loss": 1.7786, + "step": 67970 + }, + { + "epoch": 2.53, + "learning_rate": 7.471640569792093e-06, + "loss": 1.8101, + "step": 67980 + }, + { + "epoch": 2.53, + "learning_rate": 7.471268642838547e-06, + "loss": 1.7774, + "step": 67990 + }, + { + "epoch": 2.53, + "learning_rate": 7.470896715885001e-06, + "loss": 1.7607, + "step": 68000 + }, + { + "epoch": 2.53, + "eval_loss": 1.6823432445526123, + "eval_runtime": 16.8395, + "eval_samples_per_second": 59.384, + "eval_steps_per_second": 3.741, + "step": 68000 + }, + { + "epoch": 2.53, + "learning_rate": 7.470524788931455e-06, + "loss": 1.8143, + "step": 68010 + }, + { + "epoch": 2.53, + "learning_rate": 7.470152861977908e-06, + "loss": 1.7488, + "step": 68020 + }, + { + "epoch": 2.53, + "learning_rate": 7.469780935024362e-06, + "loss": 1.8691, + "step": 68030 + }, + { + "epoch": 2.53, + "learning_rate": 7.469409008070816e-06, + "loss": 1.8083, + "step": 68040 + }, + { + "epoch": 2.53, + "learning_rate": 7.469037081117269e-06, + "loss": 1.7837, + "step": 68050 + }, + { + "epoch": 2.53, + "learning_rate": 7.468665154163724e-06, + "loss": 1.8047, + "step": 68060 + }, + { + "epoch": 2.53, + "learning_rate": 7.468293227210176e-06, + "loss": 1.7356, + "step": 68070 + }, + { + "epoch": 2.53, + "learning_rate": 7.46792130025663e-06, + "loss": 1.6867, + "step": 68080 + }, + { + "epoch": 2.53, + "learning_rate": 7.467549373303083e-06, + "loss": 1.7944, + "step": 68090 + }, + { + "epoch": 2.53, + "learning_rate": 7.4671774463495374e-06, + "loss": 1.7278, + "step": 68100 + }, + { + "epoch": 2.53, + "eval_loss": 1.6816935539245605, + "eval_runtime": 16.856, + "eval_samples_per_second": 59.326, + "eval_steps_per_second": 3.738, + "step": 68100 + }, + { + "epoch": 2.53, + "learning_rate": 7.466805519395991e-06, + "loss": 1.809, + "step": 68110 + }, + { + "epoch": 2.53, + "learning_rate": 7.466433592442444e-06, + "loss": 1.839, + "step": 68120 + }, + { + "epoch": 2.53, + "learning_rate": 7.466061665488899e-06, + "loss": 1.7423, + "step": 68130 + }, + { + "epoch": 2.53, + "learning_rate": 7.465689738535352e-06, + "loss": 1.7099, + "step": 68140 + }, + { + "epoch": 2.53, + "learning_rate": 7.465317811581806e-06, + "loss": 1.675, + "step": 68150 + }, + { + "epoch": 2.54, + "learning_rate": 7.46494588462826e-06, + "loss": 1.6282, + "step": 68160 + }, + { + "epoch": 2.54, + "learning_rate": 7.464573957674713e-06, + "loss": 1.6122, + "step": 68170 + }, + { + "epoch": 2.54, + "learning_rate": 7.464202030721167e-06, + "loss": 1.7423, + "step": 68180 + }, + { + "epoch": 2.54, + "learning_rate": 7.463830103767621e-06, + "loss": 1.6624, + "step": 68190 + }, + { + "epoch": 2.54, + "learning_rate": 7.4634581768140746e-06, + "loss": 1.6841, + "step": 68200 + }, + { + "epoch": 2.54, + "eval_loss": 1.6823245286941528, + "eval_runtime": 16.8535, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 68200 + }, + { + "epoch": 2.54, + "learning_rate": 7.463086249860528e-06, + "loss": 1.6352, + "step": 68210 + }, + { + "epoch": 2.54, + "learning_rate": 7.462714322906982e-06, + "loss": 1.8283, + "step": 68220 + }, + { + "epoch": 2.54, + "learning_rate": 7.462342395953436e-06, + "loss": 1.7075, + "step": 68230 + }, + { + "epoch": 2.54, + "learning_rate": 7.461970468999889e-06, + "loss": 1.6839, + "step": 68240 + }, + { + "epoch": 2.54, + "learning_rate": 7.4615985420463436e-06, + "loss": 1.7964, + "step": 68250 + }, + { + "epoch": 2.54, + "learning_rate": 7.461226615092796e-06, + "loss": 1.6605, + "step": 68260 + }, + { + "epoch": 2.54, + "learning_rate": 7.46085468813925e-06, + "loss": 1.7409, + "step": 68270 + }, + { + "epoch": 2.54, + "learning_rate": 7.460482761185703e-06, + "loss": 1.8231, + "step": 68280 + }, + { + "epoch": 2.54, + "learning_rate": 7.460110834232157e-06, + "loss": 1.7901, + "step": 68290 + }, + { + "epoch": 2.54, + "learning_rate": 7.459738907278611e-06, + "loss": 1.7944, + "step": 68300 + }, + { + "epoch": 2.54, + "eval_loss": 1.6826202869415283, + "eval_runtime": 16.8321, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 68300 + }, + { + "epoch": 2.54, + "learning_rate": 7.459366980325064e-06, + "loss": 1.7034, + "step": 68310 + }, + { + "epoch": 2.54, + "learning_rate": 7.458995053371519e-06, + "loss": 1.7385, + "step": 68320 + }, + { + "epoch": 2.54, + "learning_rate": 7.458623126417972e-06, + "loss": 1.682, + "step": 68330 + }, + { + "epoch": 2.54, + "learning_rate": 7.4582511994644255e-06, + "loss": 1.7381, + "step": 68340 + }, + { + "epoch": 2.54, + "learning_rate": 7.45787927251088e-06, + "loss": 1.7151, + "step": 68350 + }, + { + "epoch": 2.54, + "learning_rate": 7.457507345557333e-06, + "loss": 1.7701, + "step": 68360 + }, + { + "epoch": 2.54, + "learning_rate": 7.457135418603787e-06, + "loss": 1.6696, + "step": 68370 + }, + { + "epoch": 2.54, + "learning_rate": 7.456763491650241e-06, + "loss": 1.7219, + "step": 68380 + }, + { + "epoch": 2.54, + "learning_rate": 7.4563915646966945e-06, + "loss": 1.6197, + "step": 68390 + }, + { + "epoch": 2.54, + "learning_rate": 7.456019637743148e-06, + "loss": 1.7055, + "step": 68400 + }, + { + "epoch": 2.54, + "eval_loss": 1.6837319135665894, + "eval_runtime": 16.856, + "eval_samples_per_second": 59.326, + "eval_steps_per_second": 3.738, + "step": 68400 + }, + { + "epoch": 2.54, + "learning_rate": 7.455647710789602e-06, + "loss": 1.7305, + "step": 68410 + }, + { + "epoch": 2.54, + "learning_rate": 7.455275783836056e-06, + "loss": 1.6736, + "step": 68420 + }, + { + "epoch": 2.55, + "learning_rate": 7.454903856882509e-06, + "loss": 1.7548, + "step": 68430 + }, + { + "epoch": 2.55, + "learning_rate": 7.454531929928962e-06, + "loss": 1.7231, + "step": 68440 + }, + { + "epoch": 2.55, + "learning_rate": 7.454160002975416e-06, + "loss": 1.6633, + "step": 68450 + }, + { + "epoch": 2.55, + "learning_rate": 7.45378807602187e-06, + "loss": 1.6298, + "step": 68460 + }, + { + "epoch": 2.55, + "learning_rate": 7.453416149068323e-06, + "loss": 1.8051, + "step": 68470 + }, + { + "epoch": 2.55, + "learning_rate": 7.453044222114777e-06, + "loss": 1.7429, + "step": 68480 + }, + { + "epoch": 2.55, + "learning_rate": 7.452672295161231e-06, + "loss": 1.7098, + "step": 68490 + }, + { + "epoch": 2.55, + "learning_rate": 7.452300368207684e-06, + "loss": 1.6881, + "step": 68500 + }, + { + "epoch": 2.55, + "eval_loss": 1.6825830936431885, + "eval_runtime": 16.8513, + "eval_samples_per_second": 59.343, + "eval_steps_per_second": 3.739, + "step": 68500 + }, + { + "epoch": 2.55, + "learning_rate": 7.451928441254139e-06, + "loss": 1.8768, + "step": 68510 + }, + { + "epoch": 2.55, + "learning_rate": 7.451556514300592e-06, + "loss": 1.6641, + "step": 68520 + }, + { + "epoch": 2.55, + "learning_rate": 7.4511845873470455e-06, + "loss": 1.6266, + "step": 68530 + }, + { + "epoch": 2.55, + "learning_rate": 7.450812660393499e-06, + "loss": 1.6176, + "step": 68540 + }, + { + "epoch": 2.55, + "learning_rate": 7.450440733439953e-06, + "loss": 1.6812, + "step": 68550 + }, + { + "epoch": 2.55, + "learning_rate": 7.450068806486407e-06, + "loss": 1.7292, + "step": 68560 + }, + { + "epoch": 2.55, + "learning_rate": 7.44969687953286e-06, + "loss": 1.8919, + "step": 68570 + }, + { + "epoch": 2.55, + "learning_rate": 7.4493249525793145e-06, + "loss": 1.7062, + "step": 68580 + }, + { + "epoch": 2.55, + "learning_rate": 7.448953025625768e-06, + "loss": 1.7712, + "step": 68590 + }, + { + "epoch": 2.55, + "learning_rate": 7.448581098672221e-06, + "loss": 1.6187, + "step": 68600 + }, + { + "epoch": 2.55, + "eval_loss": 1.6818830966949463, + "eval_runtime": 16.8507, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 68600 + }, + { + "epoch": 2.55, + "learning_rate": 7.448209171718676e-06, + "loss": 1.7823, + "step": 68610 + }, + { + "epoch": 2.55, + "learning_rate": 7.447837244765129e-06, + "loss": 1.7667, + "step": 68620 + }, + { + "epoch": 2.55, + "learning_rate": 7.447465317811582e-06, + "loss": 1.7313, + "step": 68630 + }, + { + "epoch": 2.55, + "learning_rate": 7.447093390858035e-06, + "loss": 1.7695, + "step": 68640 + }, + { + "epoch": 2.55, + "learning_rate": 7.4467214639044896e-06, + "loss": 1.6782, + "step": 68650 + }, + { + "epoch": 2.55, + "learning_rate": 7.446349536950943e-06, + "loss": 1.7718, + "step": 68660 + }, + { + "epoch": 2.55, + "learning_rate": 7.4459776099973965e-06, + "loss": 1.6854, + "step": 68670 + }, + { + "epoch": 2.55, + "learning_rate": 7.445605683043851e-06, + "loss": 1.6854, + "step": 68680 + }, + { + "epoch": 2.55, + "learning_rate": 7.445233756090304e-06, + "loss": 1.7982, + "step": 68690 + }, + { + "epoch": 2.56, + "learning_rate": 7.444861829136758e-06, + "loss": 1.6759, + "step": 68700 + }, + { + "epoch": 2.56, + "eval_loss": 1.682189702987671, + "eval_runtime": 16.8587, + "eval_samples_per_second": 59.316, + "eval_steps_per_second": 3.737, + "step": 68700 + }, + { + "epoch": 2.56, + "learning_rate": 7.444489902183212e-06, + "loss": 1.7848, + "step": 68710 + }, + { + "epoch": 2.56, + "learning_rate": 7.4441179752296655e-06, + "loss": 1.9141, + "step": 68720 + }, + { + "epoch": 2.56, + "learning_rate": 7.443746048276119e-06, + "loss": 1.6085, + "step": 68730 + }, + { + "epoch": 2.56, + "learning_rate": 7.443374121322573e-06, + "loss": 1.6195, + "step": 68740 + }, + { + "epoch": 2.56, + "learning_rate": 7.443002194369027e-06, + "loss": 1.8399, + "step": 68750 + }, + { + "epoch": 2.56, + "learning_rate": 7.44263026741548e-06, + "loss": 1.7801, + "step": 68760 + }, + { + "epoch": 2.56, + "learning_rate": 7.4422583404619345e-06, + "loss": 1.6648, + "step": 68770 + }, + { + "epoch": 2.56, + "learning_rate": 7.441886413508388e-06, + "loss": 1.711, + "step": 68780 + }, + { + "epoch": 2.56, + "learning_rate": 7.441514486554841e-06, + "loss": 1.7455, + "step": 68790 + }, + { + "epoch": 2.56, + "learning_rate": 7.441142559601296e-06, + "loss": 1.6752, + "step": 68800 + }, + { + "epoch": 2.56, + "eval_loss": 1.6818273067474365, + "eval_runtime": 16.8469, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 68800 + }, + { + "epoch": 2.56, + "learning_rate": 7.440770632647749e-06, + "loss": 1.6682, + "step": 68810 + }, + { + "epoch": 2.56, + "learning_rate": 7.440398705694202e-06, + "loss": 1.749, + "step": 68820 + }, + { + "epoch": 2.56, + "learning_rate": 7.440026778740655e-06, + "loss": 1.6946, + "step": 68830 + }, + { + "epoch": 2.56, + "learning_rate": 7.4396548517871095e-06, + "loss": 1.7262, + "step": 68840 + }, + { + "epoch": 2.56, + "learning_rate": 7.439282924833563e-06, + "loss": 1.7198, + "step": 68850 + }, + { + "epoch": 2.56, + "learning_rate": 7.4389109978800164e-06, + "loss": 1.6934, + "step": 68860 + }, + { + "epoch": 2.56, + "learning_rate": 7.438539070926471e-06, + "loss": 1.7818, + "step": 68870 + }, + { + "epoch": 2.56, + "learning_rate": 7.438167143972924e-06, + "loss": 1.7793, + "step": 68880 + }, + { + "epoch": 2.56, + "learning_rate": 7.437795217019378e-06, + "loss": 1.742, + "step": 68890 + }, + { + "epoch": 2.56, + "learning_rate": 7.437423290065832e-06, + "loss": 1.7912, + "step": 68900 + }, + { + "epoch": 2.56, + "eval_loss": 1.6815544366836548, + "eval_runtime": 16.8475, + "eval_samples_per_second": 59.356, + "eval_steps_per_second": 3.739, + "step": 68900 + }, + { + "epoch": 2.56, + "learning_rate": 7.437051363112285e-06, + "loss": 1.7156, + "step": 68910 + }, + { + "epoch": 2.56, + "learning_rate": 7.436679436158739e-06, + "loss": 1.7039, + "step": 68920 + }, + { + "epoch": 2.56, + "learning_rate": 7.436307509205193e-06, + "loss": 1.8249, + "step": 68930 + }, + { + "epoch": 2.56, + "learning_rate": 7.435935582251647e-06, + "loss": 1.8156, + "step": 68940 + }, + { + "epoch": 2.56, + "learning_rate": 7.4355636552981e-06, + "loss": 1.8611, + "step": 68950 + }, + { + "epoch": 2.56, + "learning_rate": 7.435191728344554e-06, + "loss": 1.7921, + "step": 68960 + }, + { + "epoch": 2.57, + "learning_rate": 7.434819801391008e-06, + "loss": 1.7259, + "step": 68970 + }, + { + "epoch": 2.57, + "learning_rate": 7.434447874437461e-06, + "loss": 1.9076, + "step": 68980 + }, + { + "epoch": 2.57, + "learning_rate": 7.434075947483916e-06, + "loss": 1.7486, + "step": 68990 + }, + { + "epoch": 2.57, + "learning_rate": 7.433704020530369e-06, + "loss": 1.6203, + "step": 69000 + }, + { + "epoch": 2.57, + "eval_loss": 1.6810303926467896, + "eval_runtime": 16.8587, + "eval_samples_per_second": 59.316, + "eval_steps_per_second": 3.737, + "step": 69000 + }, + { + "epoch": 2.57, + "learning_rate": 7.433332093576822e-06, + "loss": 1.7462, + "step": 69010 + }, + { + "epoch": 2.57, + "learning_rate": 7.432960166623275e-06, + "loss": 1.6331, + "step": 69020 + }, + { + "epoch": 2.57, + "learning_rate": 7.4325882396697295e-06, + "loss": 1.6738, + "step": 69030 + }, + { + "epoch": 2.57, + "learning_rate": 7.432216312716183e-06, + "loss": 1.7493, + "step": 69040 + }, + { + "epoch": 2.57, + "learning_rate": 7.431844385762636e-06, + "loss": 1.8987, + "step": 69050 + }, + { + "epoch": 2.57, + "learning_rate": 7.431472458809091e-06, + "loss": 1.8677, + "step": 69060 + }, + { + "epoch": 2.57, + "learning_rate": 7.431100531855544e-06, + "loss": 1.7439, + "step": 69070 + }, + { + "epoch": 2.57, + "learning_rate": 7.430728604901998e-06, + "loss": 1.793, + "step": 69080 + }, + { + "epoch": 2.57, + "learning_rate": 7.430356677948452e-06, + "loss": 1.7682, + "step": 69090 + }, + { + "epoch": 2.57, + "learning_rate": 7.429984750994905e-06, + "loss": 1.7027, + "step": 69100 + }, + { + "epoch": 2.57, + "eval_loss": 1.6829833984375, + "eval_runtime": 16.848, + "eval_samples_per_second": 59.354, + "eval_steps_per_second": 3.739, + "step": 69100 + }, + { + "epoch": 2.57, + "learning_rate": 7.429612824041359e-06, + "loss": 1.6428, + "step": 69110 + }, + { + "epoch": 2.57, + "learning_rate": 7.429240897087812e-06, + "loss": 1.7918, + "step": 69120 + }, + { + "epoch": 2.57, + "learning_rate": 7.428868970134267e-06, + "loss": 1.7153, + "step": 69130 + }, + { + "epoch": 2.57, + "learning_rate": 7.42849704318072e-06, + "loss": 1.6447, + "step": 69140 + }, + { + "epoch": 2.57, + "learning_rate": 7.4281251162271735e-06, + "loss": 1.63, + "step": 69150 + }, + { + "epoch": 2.57, + "learning_rate": 7.427753189273628e-06, + "loss": 1.8972, + "step": 69160 + }, + { + "epoch": 2.57, + "learning_rate": 7.427381262320081e-06, + "loss": 1.7969, + "step": 69170 + }, + { + "epoch": 2.57, + "learning_rate": 7.427009335366535e-06, + "loss": 1.8344, + "step": 69180 + }, + { + "epoch": 2.57, + "learning_rate": 7.426637408412987e-06, + "loss": 1.8203, + "step": 69190 + }, + { + "epoch": 2.57, + "learning_rate": 7.426265481459442e-06, + "loss": 1.7476, + "step": 69200 + }, + { + "epoch": 2.57, + "eval_loss": 1.6811165809631348, + "eval_runtime": 16.8462, + "eval_samples_per_second": 59.361, + "eval_steps_per_second": 3.74, + "step": 69200 + }, + { + "epoch": 2.57, + "learning_rate": 7.425893554505895e-06, + "loss": 1.7786, + "step": 69210 + }, + { + "epoch": 2.57, + "learning_rate": 7.425521627552349e-06, + "loss": 1.8339, + "step": 69220 + }, + { + "epoch": 2.57, + "learning_rate": 7.425149700598803e-06, + "loss": 1.7293, + "step": 69230 + }, + { + "epoch": 2.58, + "learning_rate": 7.424777773645256e-06, + "loss": 1.6806, + "step": 69240 + }, + { + "epoch": 2.58, + "learning_rate": 7.42440584669171e-06, + "loss": 1.8881, + "step": 69250 + }, + { + "epoch": 2.58, + "learning_rate": 7.424033919738164e-06, + "loss": 1.7816, + "step": 69260 + }, + { + "epoch": 2.58, + "learning_rate": 7.4236619927846176e-06, + "loss": 1.8107, + "step": 69270 + }, + { + "epoch": 2.58, + "learning_rate": 7.423290065831071e-06, + "loss": 1.8021, + "step": 69280 + }, + { + "epoch": 2.58, + "learning_rate": 7.422918138877525e-06, + "loss": 1.6663, + "step": 69290 + }, + { + "epoch": 2.58, + "learning_rate": 7.422546211923979e-06, + "loss": 1.7735, + "step": 69300 + }, + { + "epoch": 2.58, + "eval_loss": 1.681123971939087, + "eval_runtime": 16.8418, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 69300 + }, + { + "epoch": 2.58, + "learning_rate": 7.422174284970432e-06, + "loss": 1.7467, + "step": 69310 + }, + { + "epoch": 2.58, + "learning_rate": 7.4218023580168866e-06, + "loss": 1.7789, + "step": 69320 + }, + { + "epoch": 2.58, + "learning_rate": 7.42143043106334e-06, + "loss": 1.7243, + "step": 69330 + }, + { + "epoch": 2.58, + "learning_rate": 7.4210585041097935e-06, + "loss": 1.7855, + "step": 69340 + }, + { + "epoch": 2.58, + "learning_rate": 7.420686577156248e-06, + "loss": 1.7518, + "step": 69350 + }, + { + "epoch": 2.58, + "learning_rate": 7.420314650202701e-06, + "loss": 1.6605, + "step": 69360 + }, + { + "epoch": 2.58, + "learning_rate": 7.419942723249155e-06, + "loss": 1.6758, + "step": 69370 + }, + { + "epoch": 2.58, + "learning_rate": 7.419570796295607e-06, + "loss": 1.5973, + "step": 69380 + }, + { + "epoch": 2.58, + "learning_rate": 7.419198869342062e-06, + "loss": 1.6632, + "step": 69390 + }, + { + "epoch": 2.58, + "learning_rate": 7.418826942388515e-06, + "loss": 1.7216, + "step": 69400 + }, + { + "epoch": 2.58, + "eval_loss": 1.6810544729232788, + "eval_runtime": 16.8679, + "eval_samples_per_second": 59.284, + "eval_steps_per_second": 3.735, + "step": 69400 + }, + { + "epoch": 2.58, + "learning_rate": 7.4184550154349685e-06, + "loss": 1.7628, + "step": 69410 + }, + { + "epoch": 2.58, + "learning_rate": 7.418083088481423e-06, + "loss": 1.6194, + "step": 69420 + }, + { + "epoch": 2.58, + "learning_rate": 7.417711161527876e-06, + "loss": 1.7021, + "step": 69430 + }, + { + "epoch": 2.58, + "learning_rate": 7.41733923457433e-06, + "loss": 1.7302, + "step": 69440 + }, + { + "epoch": 2.58, + "learning_rate": 7.416967307620784e-06, + "loss": 1.6538, + "step": 69450 + }, + { + "epoch": 2.58, + "learning_rate": 7.4165953806672375e-06, + "loss": 1.8367, + "step": 69460 + }, + { + "epoch": 2.58, + "learning_rate": 7.416223453713691e-06, + "loss": 1.581, + "step": 69470 + }, + { + "epoch": 2.58, + "learning_rate": 7.415851526760145e-06, + "loss": 1.7771, + "step": 69480 + }, + { + "epoch": 2.58, + "learning_rate": 7.415479599806599e-06, + "loss": 1.7307, + "step": 69490 + }, + { + "epoch": 2.58, + "learning_rate": 7.415107672853052e-06, + "loss": 1.5819, + "step": 69500 + }, + { + "epoch": 2.58, + "eval_loss": 1.680793046951294, + "eval_runtime": 16.8529, + "eval_samples_per_second": 59.337, + "eval_steps_per_second": 3.738, + "step": 69500 + }, + { + "epoch": 2.59, + "learning_rate": 7.4147357458995065e-06, + "loss": 1.6713, + "step": 69510 + }, + { + "epoch": 2.59, + "learning_rate": 7.41436381894596e-06, + "loss": 1.9834, + "step": 69520 + }, + { + "epoch": 2.59, + "learning_rate": 7.4139918919924134e-06, + "loss": 1.7421, + "step": 69530 + }, + { + "epoch": 2.59, + "learning_rate": 7.413619965038868e-06, + "loss": 1.6984, + "step": 69540 + }, + { + "epoch": 2.59, + "learning_rate": 7.413248038085321e-06, + "loss": 1.8055, + "step": 69550 + }, + { + "epoch": 2.59, + "learning_rate": 7.412876111131775e-06, + "loss": 1.7656, + "step": 69560 + }, + { + "epoch": 2.59, + "learning_rate": 7.412504184178227e-06, + "loss": 1.6475, + "step": 69570 + }, + { + "epoch": 2.59, + "learning_rate": 7.412132257224682e-06, + "loss": 1.56, + "step": 69580 + }, + { + "epoch": 2.59, + "learning_rate": 7.411760330271135e-06, + "loss": 1.8368, + "step": 69590 + }, + { + "epoch": 2.59, + "learning_rate": 7.4113884033175885e-06, + "loss": 1.8029, + "step": 69600 + }, + { + "epoch": 2.59, + "eval_loss": 1.6807746887207031, + "eval_runtime": 16.848, + "eval_samples_per_second": 59.354, + "eval_steps_per_second": 3.739, + "step": 69600 + }, + { + "epoch": 2.59, + "learning_rate": 7.411016476364043e-06, + "loss": 1.7571, + "step": 69610 + }, + { + "epoch": 2.59, + "learning_rate": 7.410644549410496e-06, + "loss": 1.6467, + "step": 69620 + }, + { + "epoch": 2.59, + "learning_rate": 7.41027262245695e-06, + "loss": 1.6809, + "step": 69630 + }, + { + "epoch": 2.59, + "learning_rate": 7.409900695503404e-06, + "loss": 1.7103, + "step": 69640 + }, + { + "epoch": 2.59, + "learning_rate": 7.4095287685498575e-06, + "loss": 1.8128, + "step": 69650 + }, + { + "epoch": 2.59, + "learning_rate": 7.409156841596311e-06, + "loss": 1.7434, + "step": 69660 + }, + { + "epoch": 2.59, + "learning_rate": 7.408784914642765e-06, + "loss": 1.7873, + "step": 69670 + }, + { + "epoch": 2.59, + "learning_rate": 7.408412987689219e-06, + "loss": 1.8747, + "step": 69680 + }, + { + "epoch": 2.59, + "learning_rate": 7.408041060735672e-06, + "loss": 1.7583, + "step": 69690 + }, + { + "epoch": 2.59, + "learning_rate": 7.407669133782126e-06, + "loss": 1.7717, + "step": 69700 + }, + { + "epoch": 2.59, + "eval_loss": 1.6806609630584717, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.743, + "step": 69700 + }, + { + "epoch": 2.59, + "learning_rate": 7.40729720682858e-06, + "loss": 1.7827, + "step": 69710 + }, + { + "epoch": 2.59, + "learning_rate": 7.406925279875033e-06, + "loss": 1.6979, + "step": 69720 + }, + { + "epoch": 2.59, + "learning_rate": 7.406553352921487e-06, + "loss": 1.787, + "step": 69730 + }, + { + "epoch": 2.59, + "learning_rate": 7.406181425967941e-06, + "loss": 1.6446, + "step": 69740 + }, + { + "epoch": 2.59, + "learning_rate": 7.405809499014395e-06, + "loss": 1.6863, + "step": 69750 + }, + { + "epoch": 2.59, + "learning_rate": 7.405437572060847e-06, + "loss": 1.8315, + "step": 69760 + }, + { + "epoch": 2.59, + "learning_rate": 7.405065645107301e-06, + "loss": 1.657, + "step": 69770 + }, + { + "epoch": 2.6, + "learning_rate": 7.404693718153755e-06, + "loss": 1.7226, + "step": 69780 + }, + { + "epoch": 2.6, + "learning_rate": 7.4043217912002085e-06, + "loss": 1.6922, + "step": 69790 + }, + { + "epoch": 2.6, + "learning_rate": 7.403949864246662e-06, + "loss": 1.7608, + "step": 69800 + }, + { + "epoch": 2.6, + "eval_loss": 1.6801854372024536, + "eval_runtime": 16.8355, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 69800 + }, + { + "epoch": 2.6, + "learning_rate": 7.403577937293116e-06, + "loss": 1.819, + "step": 69810 + }, + { + "epoch": 2.6, + "learning_rate": 7.40320601033957e-06, + "loss": 1.8287, + "step": 69820 + }, + { + "epoch": 2.6, + "learning_rate": 7.402834083386023e-06, + "loss": 1.784, + "step": 69830 + }, + { + "epoch": 2.6, + "learning_rate": 7.4024621564324775e-06, + "loss": 1.7188, + "step": 69840 + }, + { + "epoch": 2.6, + "learning_rate": 7.402090229478931e-06, + "loss": 1.801, + "step": 69850 + }, + { + "epoch": 2.6, + "learning_rate": 7.401718302525384e-06, + "loss": 1.6621, + "step": 69860 + }, + { + "epoch": 2.6, + "learning_rate": 7.401346375571839e-06, + "loss": 1.6389, + "step": 69870 + }, + { + "epoch": 2.6, + "learning_rate": 7.400974448618292e-06, + "loss": 1.7062, + "step": 69880 + }, + { + "epoch": 2.6, + "learning_rate": 7.400602521664746e-06, + "loss": 1.7703, + "step": 69890 + }, + { + "epoch": 2.6, + "learning_rate": 7.4002305947112e-06, + "loss": 1.7463, + "step": 69900 + }, + { + "epoch": 2.6, + "eval_loss": 1.6814407110214233, + "eval_runtime": 16.8466, + "eval_samples_per_second": 59.359, + "eval_steps_per_second": 3.74, + "step": 69900 + }, + { + "epoch": 2.6, + "learning_rate": 7.399858667757653e-06, + "loss": 1.6863, + "step": 69910 + }, + { + "epoch": 2.6, + "learning_rate": 7.399486740804107e-06, + "loss": 1.7464, + "step": 69920 + }, + { + "epoch": 2.6, + "learning_rate": 7.399114813850561e-06, + "loss": 1.7825, + "step": 69930 + }, + { + "epoch": 2.6, + "learning_rate": 7.398742886897014e-06, + "loss": 1.6496, + "step": 69940 + }, + { + "epoch": 2.6, + "learning_rate": 7.398370959943467e-06, + "loss": 1.6881, + "step": 69950 + }, + { + "epoch": 2.6, + "learning_rate": 7.397999032989921e-06, + "loss": 1.8037, + "step": 69960 + }, + { + "epoch": 2.6, + "learning_rate": 7.397627106036375e-06, + "loss": 1.6612, + "step": 69970 + }, + { + "epoch": 2.6, + "learning_rate": 7.397255179082828e-06, + "loss": 1.5979, + "step": 69980 + }, + { + "epoch": 2.6, + "learning_rate": 7.396883252129282e-06, + "loss": 1.8527, + "step": 69990 + }, + { + "epoch": 2.6, + "learning_rate": 7.396511325175736e-06, + "loss": 1.6752, + "step": 70000 + }, + { + "epoch": 2.6, + "eval_loss": 1.6807435750961304, + "eval_runtime": 16.8507, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 70000 + }, + { + "epoch": 2.6, + "learning_rate": 7.39613939822219e-06, + "loss": 1.6783, + "step": 70010 + }, + { + "epoch": 2.6, + "learning_rate": 7.395767471268643e-06, + "loss": 1.6246, + "step": 70020 + }, + { + "epoch": 2.6, + "learning_rate": 7.395395544315097e-06, + "loss": 1.6633, + "step": 70030 + }, + { + "epoch": 2.6, + "learning_rate": 7.395023617361551e-06, + "loss": 1.8027, + "step": 70040 + }, + { + "epoch": 2.61, + "learning_rate": 7.394651690408004e-06, + "loss": 1.7012, + "step": 70050 + }, + { + "epoch": 2.61, + "learning_rate": 7.394279763454459e-06, + "loss": 1.7737, + "step": 70060 + }, + { + "epoch": 2.61, + "learning_rate": 7.393907836500912e-06, + "loss": 1.7913, + "step": 70070 + }, + { + "epoch": 2.61, + "learning_rate": 7.3935359095473656e-06, + "loss": 1.7984, + "step": 70080 + }, + { + "epoch": 2.61, + "learning_rate": 7.39316398259382e-06, + "loss": 1.6917, + "step": 70090 + }, + { + "epoch": 2.61, + "learning_rate": 7.392792055640273e-06, + "loss": 1.5854, + "step": 70100 + }, + { + "epoch": 2.61, + "eval_loss": 1.6802802085876465, + "eval_runtime": 16.8571, + "eval_samples_per_second": 59.322, + "eval_steps_per_second": 3.737, + "step": 70100 + }, + { + "epoch": 2.61, + "learning_rate": 7.392420128686727e-06, + "loss": 1.746, + "step": 70110 + }, + { + "epoch": 2.61, + "learning_rate": 7.392048201733181e-06, + "loss": 1.5245, + "step": 70120 + }, + { + "epoch": 2.61, + "learning_rate": 7.391676274779634e-06, + "loss": 1.7901, + "step": 70130 + }, + { + "epoch": 2.61, + "learning_rate": 7.391304347826087e-06, + "loss": 1.7111, + "step": 70140 + }, + { + "epoch": 2.61, + "learning_rate": 7.390932420872541e-06, + "loss": 1.8149, + "step": 70150 + }, + { + "epoch": 2.61, + "learning_rate": 7.390560493918995e-06, + "loss": 1.8839, + "step": 70160 + }, + { + "epoch": 2.61, + "learning_rate": 7.390188566965448e-06, + "loss": 1.6982, + "step": 70170 + }, + { + "epoch": 2.61, + "learning_rate": 7.389816640011902e-06, + "loss": 1.7524, + "step": 70180 + }, + { + "epoch": 2.61, + "learning_rate": 7.389444713058356e-06, + "loss": 1.7883, + "step": 70190 + }, + { + "epoch": 2.61, + "learning_rate": 7.38907278610481e-06, + "loss": 1.7518, + "step": 70200 + }, + { + "epoch": 2.61, + "eval_loss": 1.6802237033843994, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 70200 + }, + { + "epoch": 2.61, + "learning_rate": 7.388700859151263e-06, + "loss": 1.7019, + "step": 70210 + }, + { + "epoch": 2.61, + "learning_rate": 7.388328932197717e-06, + "loss": 1.8725, + "step": 70220 + }, + { + "epoch": 2.61, + "learning_rate": 7.387957005244171e-06, + "loss": 1.6609, + "step": 70230 + }, + { + "epoch": 2.61, + "learning_rate": 7.387585078290624e-06, + "loss": 1.6604, + "step": 70240 + }, + { + "epoch": 2.61, + "learning_rate": 7.387213151337078e-06, + "loss": 1.7794, + "step": 70250 + }, + { + "epoch": 2.61, + "learning_rate": 7.386841224383532e-06, + "loss": 1.772, + "step": 70260 + }, + { + "epoch": 2.61, + "learning_rate": 7.3864692974299855e-06, + "loss": 1.7509, + "step": 70270 + }, + { + "epoch": 2.61, + "learning_rate": 7.386097370476439e-06, + "loss": 1.6671, + "step": 70280 + }, + { + "epoch": 2.61, + "learning_rate": 7.385725443522893e-06, + "loss": 1.6604, + "step": 70290 + }, + { + "epoch": 2.61, + "learning_rate": 7.385353516569347e-06, + "loss": 1.6629, + "step": 70300 + }, + { + "epoch": 2.61, + "eval_loss": 1.679196834564209, + "eval_runtime": 16.8311, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 70300 + }, + { + "epoch": 2.62, + "learning_rate": 7.3849815896158e-06, + "loss": 1.7062, + "step": 70310 + }, + { + "epoch": 2.62, + "learning_rate": 7.384609662662253e-06, + "loss": 1.5974, + "step": 70320 + }, + { + "epoch": 2.62, + "learning_rate": 7.384237735708707e-06, + "loss": 1.7365, + "step": 70330 + }, + { + "epoch": 2.62, + "learning_rate": 7.3838658087551606e-06, + "loss": 1.7015, + "step": 70340 + }, + { + "epoch": 2.62, + "learning_rate": 7.383493881801614e-06, + "loss": 1.8631, + "step": 70350 + }, + { + "epoch": 2.62, + "learning_rate": 7.383121954848068e-06, + "loss": 1.7321, + "step": 70360 + }, + { + "epoch": 2.62, + "learning_rate": 7.382750027894522e-06, + "loss": 1.8356, + "step": 70370 + }, + { + "epoch": 2.62, + "learning_rate": 7.382378100940975e-06, + "loss": 1.7043, + "step": 70380 + }, + { + "epoch": 2.62, + "learning_rate": 7.3820061739874296e-06, + "loss": 1.712, + "step": 70390 + }, + { + "epoch": 2.62, + "learning_rate": 7.381634247033883e-06, + "loss": 1.7347, + "step": 70400 + }, + { + "epoch": 2.62, + "eval_loss": 1.679925799369812, + "eval_runtime": 16.8351, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 70400 + }, + { + "epoch": 2.62, + "learning_rate": 7.3812623200803365e-06, + "loss": 1.6454, + "step": 70410 + }, + { + "epoch": 2.62, + "learning_rate": 7.380890393126791e-06, + "loss": 1.6552, + "step": 70420 + }, + { + "epoch": 2.62, + "learning_rate": 7.380518466173244e-06, + "loss": 1.7692, + "step": 70430 + }, + { + "epoch": 2.62, + "learning_rate": 7.380146539219698e-06, + "loss": 1.7155, + "step": 70440 + }, + { + "epoch": 2.62, + "learning_rate": 7.379774612266152e-06, + "loss": 1.7328, + "step": 70450 + }, + { + "epoch": 2.62, + "learning_rate": 7.3794026853126055e-06, + "loss": 1.5804, + "step": 70460 + }, + { + "epoch": 2.62, + "learning_rate": 7.379030758359059e-06, + "loss": 1.8199, + "step": 70470 + }, + { + "epoch": 2.62, + "learning_rate": 7.378658831405513e-06, + "loss": 1.7013, + "step": 70480 + }, + { + "epoch": 2.62, + "learning_rate": 7.378286904451967e-06, + "loss": 1.803, + "step": 70490 + }, + { + "epoch": 2.62, + "learning_rate": 7.37791497749842e-06, + "loss": 1.6811, + "step": 70500 + }, + { + "epoch": 2.62, + "eval_loss": 1.679651141166687, + "eval_runtime": 16.8409, + "eval_samples_per_second": 59.379, + "eval_steps_per_second": 3.741, + "step": 70500 + }, + { + "epoch": 2.62, + "learning_rate": 7.377543050544873e-06, + "loss": 1.6894, + "step": 70510 + }, + { + "epoch": 2.62, + "learning_rate": 7.377171123591327e-06, + "loss": 1.6158, + "step": 70520 + }, + { + "epoch": 2.62, + "learning_rate": 7.3767991966377805e-06, + "loss": 1.6727, + "step": 70530 + }, + { + "epoch": 2.62, + "learning_rate": 7.376427269684234e-06, + "loss": 1.5841, + "step": 70540 + }, + { + "epoch": 2.62, + "learning_rate": 7.376055342730688e-06, + "loss": 1.6822, + "step": 70550 + }, + { + "epoch": 2.62, + "learning_rate": 7.375683415777142e-06, + "loss": 1.7073, + "step": 70560 + }, + { + "epoch": 2.62, + "learning_rate": 7.375311488823595e-06, + "loss": 1.818, + "step": 70570 + }, + { + "epoch": 2.63, + "learning_rate": 7.3749395618700495e-06, + "loss": 1.785, + "step": 70580 + }, + { + "epoch": 2.63, + "learning_rate": 7.374567634916503e-06, + "loss": 1.8298, + "step": 70590 + }, + { + "epoch": 2.63, + "learning_rate": 7.3741957079629564e-06, + "loss": 1.5653, + "step": 70600 + }, + { + "epoch": 2.63, + "eval_loss": 1.6791139841079712, + "eval_runtime": 16.8343, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 70600 + }, + { + "epoch": 2.63, + "learning_rate": 7.373823781009411e-06, + "loss": 1.6435, + "step": 70610 + }, + { + "epoch": 2.63, + "learning_rate": 7.373451854055864e-06, + "loss": 1.6562, + "step": 70620 + }, + { + "epoch": 2.63, + "learning_rate": 7.373079927102318e-06, + "loss": 1.5334, + "step": 70630 + }, + { + "epoch": 2.63, + "learning_rate": 7.372708000148772e-06, + "loss": 1.7168, + "step": 70640 + }, + { + "epoch": 2.63, + "learning_rate": 7.3723360731952254e-06, + "loss": 1.7625, + "step": 70650 + }, + { + "epoch": 2.63, + "learning_rate": 7.371964146241679e-06, + "loss": 1.8355, + "step": 70660 + }, + { + "epoch": 2.63, + "learning_rate": 7.371592219288133e-06, + "loss": 1.7395, + "step": 70670 + }, + { + "epoch": 2.63, + "learning_rate": 7.371220292334587e-06, + "loss": 1.7003, + "step": 70680 + }, + { + "epoch": 2.63, + "learning_rate": 7.37084836538104e-06, + "loss": 1.629, + "step": 70690 + }, + { + "epoch": 2.63, + "learning_rate": 7.370476438427493e-06, + "loss": 1.6181, + "step": 70700 + }, + { + "epoch": 2.63, + "eval_loss": 1.6788055896759033, + "eval_runtime": 16.8543, + "eval_samples_per_second": 59.332, + "eval_steps_per_second": 3.738, + "step": 70700 + }, + { + "epoch": 2.63, + "learning_rate": 7.370104511473947e-06, + "loss": 1.8448, + "step": 70710 + }, + { + "epoch": 2.63, + "learning_rate": 7.3697325845204005e-06, + "loss": 1.7392, + "step": 70720 + }, + { + "epoch": 2.63, + "learning_rate": 7.369360657566854e-06, + "loss": 1.9713, + "step": 70730 + }, + { + "epoch": 2.63, + "learning_rate": 7.368988730613308e-06, + "loss": 1.6325, + "step": 70740 + }, + { + "epoch": 2.63, + "learning_rate": 7.368616803659762e-06, + "loss": 1.7618, + "step": 70750 + }, + { + "epoch": 2.63, + "learning_rate": 7.368244876706215e-06, + "loss": 1.7144, + "step": 70760 + }, + { + "epoch": 2.63, + "learning_rate": 7.3678729497526695e-06, + "loss": 1.7951, + "step": 70770 + }, + { + "epoch": 2.63, + "learning_rate": 7.367501022799123e-06, + "loss": 1.7413, + "step": 70780 + }, + { + "epoch": 2.63, + "learning_rate": 7.367129095845576e-06, + "loss": 1.6891, + "step": 70790 + }, + { + "epoch": 2.63, + "learning_rate": 7.366757168892031e-06, + "loss": 1.7353, + "step": 70800 + }, + { + "epoch": 2.63, + "eval_loss": 1.6795800924301147, + "eval_runtime": 16.8414, + "eval_samples_per_second": 59.377, + "eval_steps_per_second": 3.741, + "step": 70800 + }, + { + "epoch": 2.63, + "learning_rate": 7.366385241938484e-06, + "loss": 1.5885, + "step": 70810 + }, + { + "epoch": 2.63, + "learning_rate": 7.366013314984938e-06, + "loss": 1.7538, + "step": 70820 + }, + { + "epoch": 2.63, + "learning_rate": 7.365641388031391e-06, + "loss": 1.6801, + "step": 70830 + }, + { + "epoch": 2.63, + "learning_rate": 7.365269461077845e-06, + "loss": 1.8336, + "step": 70840 + }, + { + "epoch": 2.64, + "learning_rate": 7.364897534124299e-06, + "loss": 1.6896, + "step": 70850 + }, + { + "epoch": 2.64, + "learning_rate": 7.364525607170752e-06, + "loss": 1.7894, + "step": 70860 + }, + { + "epoch": 2.64, + "learning_rate": 7.364153680217207e-06, + "loss": 1.783, + "step": 70870 + }, + { + "epoch": 2.64, + "learning_rate": 7.363781753263659e-06, + "loss": 1.7463, + "step": 70880 + }, + { + "epoch": 2.64, + "learning_rate": 7.363409826310113e-06, + "loss": 1.7165, + "step": 70890 + }, + { + "epoch": 2.64, + "learning_rate": 7.363037899356566e-06, + "loss": 1.8161, + "step": 70900 + }, + { + "epoch": 2.64, + "eval_loss": 1.6783955097198486, + "eval_runtime": 16.8647, + "eval_samples_per_second": 59.296, + "eval_steps_per_second": 3.736, + "step": 70900 + }, + { + "epoch": 2.64, + "learning_rate": 7.3626659724030205e-06, + "loss": 1.5933, + "step": 70910 + }, + { + "epoch": 2.64, + "learning_rate": 7.362294045449474e-06, + "loss": 1.7256, + "step": 70920 + }, + { + "epoch": 2.64, + "learning_rate": 7.361922118495927e-06, + "loss": 1.8708, + "step": 70930 + }, + { + "epoch": 2.64, + "learning_rate": 7.361550191542382e-06, + "loss": 1.6453, + "step": 70940 + }, + { + "epoch": 2.64, + "learning_rate": 7.361178264588835e-06, + "loss": 1.7323, + "step": 70950 + }, + { + "epoch": 2.64, + "learning_rate": 7.360806337635289e-06, + "loss": 1.708, + "step": 70960 + }, + { + "epoch": 2.64, + "learning_rate": 7.360434410681743e-06, + "loss": 1.7072, + "step": 70970 + }, + { + "epoch": 2.64, + "learning_rate": 7.360062483728196e-06, + "loss": 1.6354, + "step": 70980 + }, + { + "epoch": 2.64, + "learning_rate": 7.35969055677465e-06, + "loss": 1.6512, + "step": 70990 + }, + { + "epoch": 2.64, + "learning_rate": 7.359318629821104e-06, + "loss": 1.7458, + "step": 71000 + }, + { + "epoch": 2.64, + "eval_loss": 1.6776562929153442, + "eval_runtime": 16.8595, + "eval_samples_per_second": 59.314, + "eval_steps_per_second": 3.737, + "step": 71000 + }, + { + "epoch": 2.64, + "learning_rate": 7.358946702867558e-06, + "loss": 1.8002, + "step": 71010 + }, + { + "epoch": 2.64, + "learning_rate": 7.358574775914011e-06, + "loss": 1.7418, + "step": 71020 + }, + { + "epoch": 2.64, + "learning_rate": 7.358202848960465e-06, + "loss": 1.9107, + "step": 71030 + }, + { + "epoch": 2.64, + "learning_rate": 7.357830922006919e-06, + "loss": 1.6603, + "step": 71040 + }, + { + "epoch": 2.64, + "learning_rate": 7.357458995053372e-06, + "loss": 1.7466, + "step": 71050 + }, + { + "epoch": 2.64, + "learning_rate": 7.3570870680998266e-06, + "loss": 1.7695, + "step": 71060 + }, + { + "epoch": 2.64, + "learning_rate": 7.356715141146279e-06, + "loss": 1.8106, + "step": 71070 + }, + { + "epoch": 2.64, + "learning_rate": 7.356343214192733e-06, + "loss": 1.8168, + "step": 71080 + }, + { + "epoch": 2.64, + "learning_rate": 7.355971287239186e-06, + "loss": 1.6942, + "step": 71090 + }, + { + "epoch": 2.64, + "learning_rate": 7.35559936028564e-06, + "loss": 1.7551, + "step": 71100 + }, + { + "epoch": 2.64, + "eval_loss": 1.6790019273757935, + "eval_runtime": 16.8399, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 71100 + }, + { + "epoch": 2.64, + "learning_rate": 7.355227433332094e-06, + "loss": 1.7074, + "step": 71110 + }, + { + "epoch": 2.65, + "learning_rate": 7.354855506378547e-06, + "loss": 1.7135, + "step": 71120 + }, + { + "epoch": 2.65, + "learning_rate": 7.354483579425002e-06, + "loss": 1.8414, + "step": 71130 + }, + { + "epoch": 2.65, + "learning_rate": 7.354111652471455e-06, + "loss": 1.7822, + "step": 71140 + }, + { + "epoch": 2.65, + "learning_rate": 7.3537397255179086e-06, + "loss": 1.7898, + "step": 71150 + }, + { + "epoch": 2.65, + "learning_rate": 7.353367798564363e-06, + "loss": 1.7599, + "step": 71160 + }, + { + "epoch": 2.65, + "learning_rate": 7.352995871610816e-06, + "loss": 1.6549, + "step": 71170 + }, + { + "epoch": 2.65, + "learning_rate": 7.35262394465727e-06, + "loss": 1.7557, + "step": 71180 + }, + { + "epoch": 2.65, + "learning_rate": 7.352252017703724e-06, + "loss": 1.7049, + "step": 71190 + }, + { + "epoch": 2.65, + "learning_rate": 7.3518800907501775e-06, + "loss": 1.7688, + "step": 71200 + }, + { + "epoch": 2.65, + "eval_loss": 1.6780771017074585, + "eval_runtime": 16.852, + "eval_samples_per_second": 59.34, + "eval_steps_per_second": 3.738, + "step": 71200 + }, + { + "epoch": 2.65, + "learning_rate": 7.351508163796631e-06, + "loss": 1.6043, + "step": 71210 + }, + { + "epoch": 2.65, + "learning_rate": 7.351136236843085e-06, + "loss": 1.7387, + "step": 71220 + }, + { + "epoch": 2.65, + "learning_rate": 7.350764309889539e-06, + "loss": 1.7222, + "step": 71230 + }, + { + "epoch": 2.65, + "learning_rate": 7.350392382935992e-06, + "loss": 1.7475, + "step": 71240 + }, + { + "epoch": 2.65, + "learning_rate": 7.3500204559824465e-06, + "loss": 1.7303, + "step": 71250 + }, + { + "epoch": 2.65, + "learning_rate": 7.349648529028899e-06, + "loss": 1.6612, + "step": 71260 + }, + { + "epoch": 2.65, + "learning_rate": 7.349276602075353e-06, + "loss": 1.6897, + "step": 71270 + }, + { + "epoch": 2.65, + "learning_rate": 7.348904675121806e-06, + "loss": 1.6911, + "step": 71280 + }, + { + "epoch": 2.65, + "learning_rate": 7.34853274816826e-06, + "loss": 1.8761, + "step": 71290 + }, + { + "epoch": 2.65, + "learning_rate": 7.348160821214714e-06, + "loss": 1.8035, + "step": 71300 + }, + { + "epoch": 2.65, + "eval_loss": 1.6789860725402832, + "eval_runtime": 16.8412, + "eval_samples_per_second": 59.378, + "eval_steps_per_second": 3.741, + "step": 71300 + }, + { + "epoch": 2.65, + "learning_rate": 7.347788894261167e-06, + "loss": 1.6927, + "step": 71310 + }, + { + "epoch": 2.65, + "learning_rate": 7.347416967307622e-06, + "loss": 1.6729, + "step": 71320 + }, + { + "epoch": 2.65, + "learning_rate": 7.347045040354075e-06, + "loss": 1.7208, + "step": 71330 + }, + { + "epoch": 2.65, + "learning_rate": 7.3466731134005285e-06, + "loss": 1.9011, + "step": 71340 + }, + { + "epoch": 2.65, + "learning_rate": 7.346301186446983e-06, + "loss": 1.7494, + "step": 71350 + }, + { + "epoch": 2.65, + "learning_rate": 7.345929259493436e-06, + "loss": 1.6692, + "step": 71360 + }, + { + "epoch": 2.65, + "learning_rate": 7.34555733253989e-06, + "loss": 1.7244, + "step": 71370 + }, + { + "epoch": 2.65, + "learning_rate": 7.345185405586344e-06, + "loss": 1.8583, + "step": 71380 + }, + { + "epoch": 2.66, + "learning_rate": 7.3448134786327975e-06, + "loss": 1.725, + "step": 71390 + }, + { + "epoch": 2.66, + "learning_rate": 7.344441551679251e-06, + "loss": 1.8211, + "step": 71400 + }, + { + "epoch": 2.66, + "eval_loss": 1.677371621131897, + "eval_runtime": 16.8491, + "eval_samples_per_second": 59.35, + "eval_steps_per_second": 3.739, + "step": 71400 + }, + { + "epoch": 2.66, + "learning_rate": 7.344069624725704e-06, + "loss": 1.6206, + "step": 71410 + }, + { + "epoch": 2.66, + "learning_rate": 7.343697697772159e-06, + "loss": 1.806, + "step": 71420 + }, + { + "epoch": 2.66, + "learning_rate": 7.343325770818612e-06, + "loss": 1.6521, + "step": 71430 + }, + { + "epoch": 2.66, + "learning_rate": 7.342953843865066e-06, + "loss": 1.7762, + "step": 71440 + }, + { + "epoch": 2.66, + "learning_rate": 7.342581916911518e-06, + "loss": 1.9162, + "step": 71450 + }, + { + "epoch": 2.66, + "learning_rate": 7.3422099899579726e-06, + "loss": 1.7291, + "step": 71460 + }, + { + "epoch": 2.66, + "learning_rate": 7.341838063004426e-06, + "loss": 1.7775, + "step": 71470 + }, + { + "epoch": 2.66, + "learning_rate": 7.3414661360508795e-06, + "loss": 1.7378, + "step": 71480 + }, + { + "epoch": 2.66, + "learning_rate": 7.341094209097334e-06, + "loss": 1.7596, + "step": 71490 + }, + { + "epoch": 2.66, + "learning_rate": 7.340722282143787e-06, + "loss": 1.7908, + "step": 71500 + }, + { + "epoch": 2.66, + "eval_loss": 1.6787978410720825, + "eval_runtime": 16.8504, + "eval_samples_per_second": 59.346, + "eval_steps_per_second": 3.739, + "step": 71500 + }, + { + "epoch": 2.66, + "learning_rate": 7.340350355190241e-06, + "loss": 1.6816, + "step": 71510 + }, + { + "epoch": 2.66, + "learning_rate": 7.339978428236695e-06, + "loss": 1.7127, + "step": 71520 + }, + { + "epoch": 2.66, + "learning_rate": 7.3396065012831485e-06, + "loss": 1.652, + "step": 71530 + }, + { + "epoch": 2.66, + "learning_rate": 7.339234574329602e-06, + "loss": 1.7868, + "step": 71540 + }, + { + "epoch": 2.66, + "learning_rate": 7.338862647376056e-06, + "loss": 1.8136, + "step": 71550 + }, + { + "epoch": 2.66, + "learning_rate": 7.33849072042251e-06, + "loss": 1.8308, + "step": 71560 + }, + { + "epoch": 2.66, + "learning_rate": 7.338118793468963e-06, + "loss": 1.5808, + "step": 71570 + }, + { + "epoch": 2.66, + "learning_rate": 7.3377468665154175e-06, + "loss": 1.7772, + "step": 71580 + }, + { + "epoch": 2.66, + "learning_rate": 7.337374939561871e-06, + "loss": 1.7908, + "step": 71590 + }, + { + "epoch": 2.66, + "learning_rate": 7.337003012608324e-06, + "loss": 1.8603, + "step": 71600 + }, + { + "epoch": 2.66, + "eval_loss": 1.6784764528274536, + "eval_runtime": 16.8385, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 71600 + }, + { + "epoch": 2.66, + "learning_rate": 7.336631085654779e-06, + "loss": 1.7186, + "step": 71610 + }, + { + "epoch": 2.66, + "learning_rate": 7.336259158701232e-06, + "loss": 1.6695, + "step": 71620 + }, + { + "epoch": 2.66, + "learning_rate": 7.335887231747685e-06, + "loss": 1.8026, + "step": 71630 + }, + { + "epoch": 2.66, + "learning_rate": 7.335515304794138e-06, + "loss": 1.6551, + "step": 71640 + }, + { + "epoch": 2.66, + "learning_rate": 7.3351433778405925e-06, + "loss": 1.8786, + "step": 71650 + }, + { + "epoch": 2.67, + "learning_rate": 7.334771450887046e-06, + "loss": 1.7345, + "step": 71660 + }, + { + "epoch": 2.67, + "learning_rate": 7.3343995239334994e-06, + "loss": 2.0416, + "step": 71670 + }, + { + "epoch": 2.67, + "learning_rate": 7.334027596979954e-06, + "loss": 1.6942, + "step": 71680 + }, + { + "epoch": 2.67, + "learning_rate": 7.333655670026407e-06, + "loss": 1.7672, + "step": 71690 + }, + { + "epoch": 2.67, + "learning_rate": 7.333283743072861e-06, + "loss": 1.6965, + "step": 71700 + }, + { + "epoch": 2.67, + "eval_loss": 1.6784790754318237, + "eval_runtime": 16.8312, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 71700 + }, + { + "epoch": 2.67, + "learning_rate": 7.332911816119315e-06, + "loss": 1.8342, + "step": 71710 + }, + { + "epoch": 2.67, + "learning_rate": 7.3325398891657684e-06, + "loss": 1.7207, + "step": 71720 + }, + { + "epoch": 2.67, + "learning_rate": 7.332167962212222e-06, + "loss": 1.696, + "step": 71730 + }, + { + "epoch": 2.67, + "learning_rate": 7.331796035258676e-06, + "loss": 1.68, + "step": 71740 + }, + { + "epoch": 2.67, + "learning_rate": 7.33142410830513e-06, + "loss": 1.7099, + "step": 71750 + }, + { + "epoch": 2.67, + "learning_rate": 7.331052181351583e-06, + "loss": 1.6979, + "step": 71760 + }, + { + "epoch": 2.67, + "learning_rate": 7.330680254398037e-06, + "loss": 1.6313, + "step": 71770 + }, + { + "epoch": 2.67, + "learning_rate": 7.330308327444491e-06, + "loss": 1.7236, + "step": 71780 + }, + { + "epoch": 2.67, + "learning_rate": 7.329936400490944e-06, + "loss": 1.823, + "step": 71790 + }, + { + "epoch": 2.67, + "learning_rate": 7.329564473537399e-06, + "loss": 1.7035, + "step": 71800 + }, + { + "epoch": 2.67, + "eval_loss": 1.6784037351608276, + "eval_runtime": 16.8502, + "eval_samples_per_second": 59.346, + "eval_steps_per_second": 3.739, + "step": 71800 + }, + { + "epoch": 2.67, + "learning_rate": 7.329192546583852e-06, + "loss": 1.775, + "step": 71810 + }, + { + "epoch": 2.67, + "learning_rate": 7.328820619630305e-06, + "loss": 1.7137, + "step": 71820 + }, + { + "epoch": 2.67, + "learning_rate": 7.328448692676758e-06, + "loss": 1.6771, + "step": 71830 + }, + { + "epoch": 2.67, + "learning_rate": 7.3280767657232125e-06, + "loss": 1.7249, + "step": 71840 + }, + { + "epoch": 2.67, + "learning_rate": 7.327704838769666e-06, + "loss": 1.5654, + "step": 71850 + }, + { + "epoch": 2.67, + "learning_rate": 7.327332911816119e-06, + "loss": 1.7834, + "step": 71860 + }, + { + "epoch": 2.67, + "learning_rate": 7.326960984862574e-06, + "loss": 1.7245, + "step": 71870 + }, + { + "epoch": 2.67, + "learning_rate": 7.326589057909027e-06, + "loss": 1.6766, + "step": 71880 + }, + { + "epoch": 2.67, + "learning_rate": 7.326217130955481e-06, + "loss": 1.7775, + "step": 71890 + }, + { + "epoch": 2.67, + "learning_rate": 7.325845204001935e-06, + "loss": 1.7015, + "step": 71900 + }, + { + "epoch": 2.67, + "eval_loss": 1.6776823997497559, + "eval_runtime": 16.8443, + "eval_samples_per_second": 59.367, + "eval_steps_per_second": 3.74, + "step": 71900 + }, + { + "epoch": 2.67, + "learning_rate": 7.325473277048388e-06, + "loss": 1.763, + "step": 71910 + }, + { + "epoch": 2.67, + "learning_rate": 7.325101350094842e-06, + "loss": 1.8264, + "step": 71920 + }, + { + "epoch": 2.68, + "learning_rate": 7.324729423141296e-06, + "loss": 1.6693, + "step": 71930 + }, + { + "epoch": 2.68, + "learning_rate": 7.32435749618775e-06, + "loss": 1.6696, + "step": 71940 + }, + { + "epoch": 2.68, + "learning_rate": 7.323985569234203e-06, + "loss": 1.5874, + "step": 71950 + }, + { + "epoch": 2.68, + "learning_rate": 7.323613642280657e-06, + "loss": 1.6958, + "step": 71960 + }, + { + "epoch": 2.68, + "learning_rate": 7.323241715327111e-06, + "loss": 1.8404, + "step": 71970 + }, + { + "epoch": 2.68, + "learning_rate": 7.322869788373564e-06, + "loss": 1.5443, + "step": 71980 + }, + { + "epoch": 2.68, + "learning_rate": 7.322497861420018e-06, + "loss": 1.7718, + "step": 71990 + }, + { + "epoch": 2.68, + "learning_rate": 7.322125934466472e-06, + "loss": 1.6945, + "step": 72000 + }, + { + "epoch": 2.68, + "eval_loss": 1.6767802238464355, + "eval_runtime": 16.8589, + "eval_samples_per_second": 59.316, + "eval_steps_per_second": 3.737, + "step": 72000 + }, + { + "epoch": 2.68, + "learning_rate": 7.321754007512925e-06, + "loss": 1.7468, + "step": 72010 + }, + { + "epoch": 2.68, + "learning_rate": 7.321382080559378e-06, + "loss": 1.6912, + "step": 72020 + }, + { + "epoch": 2.68, + "learning_rate": 7.321010153605832e-06, + "loss": 1.7923, + "step": 72030 + }, + { + "epoch": 2.68, + "learning_rate": 7.320638226652286e-06, + "loss": 1.7215, + "step": 72040 + }, + { + "epoch": 2.68, + "learning_rate": 7.320266299698739e-06, + "loss": 1.8376, + "step": 72050 + }, + { + "epoch": 2.68, + "learning_rate": 7.319894372745193e-06, + "loss": 1.6937, + "step": 72060 + }, + { + "epoch": 2.68, + "learning_rate": 7.319522445791647e-06, + "loss": 1.7035, + "step": 72070 + }, + { + "epoch": 2.68, + "learning_rate": 7.319150518838101e-06, + "loss": 1.7678, + "step": 72080 + }, + { + "epoch": 2.68, + "learning_rate": 7.318778591884554e-06, + "loss": 1.6525, + "step": 72090 + }, + { + "epoch": 2.68, + "learning_rate": 7.318406664931008e-06, + "loss": 1.706, + "step": 72100 + }, + { + "epoch": 2.68, + "eval_loss": 1.6768231391906738, + "eval_runtime": 16.8388, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 72100 + }, + { + "epoch": 2.68, + "learning_rate": 7.318034737977462e-06, + "loss": 1.7639, + "step": 72110 + }, + { + "epoch": 2.68, + "learning_rate": 7.317662811023915e-06, + "loss": 1.7294, + "step": 72120 + }, + { + "epoch": 2.68, + "learning_rate": 7.3172908840703696e-06, + "loss": 1.6948, + "step": 72130 + }, + { + "epoch": 2.68, + "learning_rate": 7.316918957116823e-06, + "loss": 1.6112, + "step": 72140 + }, + { + "epoch": 2.68, + "learning_rate": 7.3165470301632765e-06, + "loss": 1.818, + "step": 72150 + }, + { + "epoch": 2.68, + "learning_rate": 7.316175103209731e-06, + "loss": 1.6934, + "step": 72160 + }, + { + "epoch": 2.68, + "learning_rate": 7.315803176256184e-06, + "loss": 1.7368, + "step": 72170 + }, + { + "epoch": 2.68, + "learning_rate": 7.315431249302638e-06, + "loss": 1.5533, + "step": 72180 + }, + { + "epoch": 2.68, + "learning_rate": 7.315059322349092e-06, + "loss": 1.7544, + "step": 72190 + }, + { + "epoch": 2.69, + "learning_rate": 7.314687395395545e-06, + "loss": 1.7418, + "step": 72200 + }, + { + "epoch": 2.69, + "eval_loss": 1.6776076555252075, + "eval_runtime": 16.8541, + "eval_samples_per_second": 59.333, + "eval_steps_per_second": 3.738, + "step": 72200 + }, + { + "epoch": 2.69, + "learning_rate": 7.314315468441998e-06, + "loss": 1.7776, + "step": 72210 + }, + { + "epoch": 2.69, + "learning_rate": 7.3139435414884516e-06, + "loss": 1.7323, + "step": 72220 + }, + { + "epoch": 2.69, + "learning_rate": 7.313571614534906e-06, + "loss": 1.8505, + "step": 72230 + }, + { + "epoch": 2.69, + "learning_rate": 7.313199687581359e-06, + "loss": 1.843, + "step": 72240 + }, + { + "epoch": 2.69, + "learning_rate": 7.312827760627813e-06, + "loss": 1.6361, + "step": 72250 + }, + { + "epoch": 2.69, + "learning_rate": 7.312455833674267e-06, + "loss": 1.6685, + "step": 72260 + }, + { + "epoch": 2.69, + "learning_rate": 7.3120839067207205e-06, + "loss": 1.9453, + "step": 72270 + }, + { + "epoch": 2.69, + "learning_rate": 7.311711979767174e-06, + "loss": 1.7065, + "step": 72280 + }, + { + "epoch": 2.69, + "learning_rate": 7.311340052813628e-06, + "loss": 1.6543, + "step": 72290 + }, + { + "epoch": 2.69, + "learning_rate": 7.310968125860082e-06, + "loss": 1.7239, + "step": 72300 + }, + { + "epoch": 2.69, + "eval_loss": 1.6766276359558105, + "eval_runtime": 16.8406, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 72300 + }, + { + "epoch": 2.69, + "learning_rate": 7.310596198906535e-06, + "loss": 1.8867, + "step": 72310 + }, + { + "epoch": 2.69, + "learning_rate": 7.3102242719529895e-06, + "loss": 1.6782, + "step": 72320 + }, + { + "epoch": 2.69, + "learning_rate": 7.309852344999443e-06, + "loss": 1.6367, + "step": 72330 + }, + { + "epoch": 2.69, + "learning_rate": 7.3094804180458965e-06, + "loss": 1.8168, + "step": 72340 + }, + { + "epoch": 2.69, + "learning_rate": 7.309108491092351e-06, + "loss": 1.7406, + "step": 72350 + }, + { + "epoch": 2.69, + "learning_rate": 7.308736564138804e-06, + "loss": 1.7409, + "step": 72360 + }, + { + "epoch": 2.69, + "learning_rate": 7.308364637185258e-06, + "loss": 1.6574, + "step": 72370 + }, + { + "epoch": 2.69, + "learning_rate": 7.307992710231712e-06, + "loss": 1.8639, + "step": 72380 + }, + { + "epoch": 2.69, + "learning_rate": 7.307620783278165e-06, + "loss": 1.7706, + "step": 72390 + }, + { + "epoch": 2.69, + "learning_rate": 7.307248856324618e-06, + "loss": 1.9126, + "step": 72400 + }, + { + "epoch": 2.69, + "eval_loss": 1.67607581615448, + "eval_runtime": 16.8318, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 72400 + }, + { + "epoch": 2.69, + "learning_rate": 7.3068769293710715e-06, + "loss": 1.5986, + "step": 72410 + }, + { + "epoch": 2.69, + "learning_rate": 7.306505002417526e-06, + "loss": 1.845, + "step": 72420 + }, + { + "epoch": 2.69, + "learning_rate": 7.306133075463979e-06, + "loss": 1.762, + "step": 72430 + }, + { + "epoch": 2.69, + "learning_rate": 7.305761148510433e-06, + "loss": 1.8037, + "step": 72440 + }, + { + "epoch": 2.69, + "learning_rate": 7.305389221556887e-06, + "loss": 1.7511, + "step": 72450 + }, + { + "epoch": 2.69, + "learning_rate": 7.3050172946033405e-06, + "loss": 1.6149, + "step": 72460 + }, + { + "epoch": 2.7, + "learning_rate": 7.304645367649794e-06, + "loss": 1.8828, + "step": 72470 + }, + { + "epoch": 2.7, + "learning_rate": 7.304273440696248e-06, + "loss": 1.6257, + "step": 72480 + }, + { + "epoch": 2.7, + "learning_rate": 7.303901513742702e-06, + "loss": 1.7632, + "step": 72490 + }, + { + "epoch": 2.7, + "learning_rate": 7.303529586789155e-06, + "loss": 1.6398, + "step": 72500 + }, + { + "epoch": 2.7, + "eval_loss": 1.6763784885406494, + "eval_runtime": 16.8386, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 72500 + }, + { + "epoch": 2.7, + "learning_rate": 7.3031576598356095e-06, + "loss": 1.8036, + "step": 72510 + }, + { + "epoch": 2.7, + "learning_rate": 7.302785732882063e-06, + "loss": 1.8503, + "step": 72520 + }, + { + "epoch": 2.7, + "learning_rate": 7.302413805928516e-06, + "loss": 1.7049, + "step": 72530 + }, + { + "epoch": 2.7, + "learning_rate": 7.302041878974971e-06, + "loss": 1.754, + "step": 72540 + }, + { + "epoch": 2.7, + "learning_rate": 7.301669952021424e-06, + "loss": 1.7181, + "step": 72550 + }, + { + "epoch": 2.7, + "learning_rate": 7.301298025067878e-06, + "loss": 1.7554, + "step": 72560 + }, + { + "epoch": 2.7, + "learning_rate": 7.30092609811433e-06, + "loss": 1.6721, + "step": 72570 + }, + { + "epoch": 2.7, + "learning_rate": 7.3005541711607846e-06, + "loss": 1.6762, + "step": 72580 + }, + { + "epoch": 2.7, + "learning_rate": 7.300182244207238e-06, + "loss": 1.6556, + "step": 72590 + }, + { + "epoch": 2.7, + "learning_rate": 7.2998103172536915e-06, + "loss": 1.603, + "step": 72600 + }, + { + "epoch": 2.7, + "eval_loss": 1.6775414943695068, + "eval_runtime": 16.8446, + "eval_samples_per_second": 59.366, + "eval_steps_per_second": 3.74, + "step": 72600 + }, + { + "epoch": 2.7, + "learning_rate": 7.299438390300145e-06, + "loss": 1.6591, + "step": 72610 + }, + { + "epoch": 2.7, + "learning_rate": 7.299066463346599e-06, + "loss": 1.6884, + "step": 72620 + }, + { + "epoch": 2.7, + "learning_rate": 7.298694536393053e-06, + "loss": 1.6781, + "step": 72630 + }, + { + "epoch": 2.7, + "learning_rate": 7.298322609439506e-06, + "loss": 1.6369, + "step": 72640 + }, + { + "epoch": 2.7, + "learning_rate": 7.2979506824859605e-06, + "loss": 1.7177, + "step": 72650 + }, + { + "epoch": 2.7, + "learning_rate": 7.297578755532414e-06, + "loss": 1.7699, + "step": 72660 + }, + { + "epoch": 2.7, + "learning_rate": 7.297206828578867e-06, + "loss": 1.727, + "step": 72670 + }, + { + "epoch": 2.7, + "learning_rate": 7.296834901625322e-06, + "loss": 1.5997, + "step": 72680 + }, + { + "epoch": 2.7, + "learning_rate": 7.296462974671775e-06, + "loss": 1.7405, + "step": 72690 + }, + { + "epoch": 2.7, + "learning_rate": 7.296091047718229e-06, + "loss": 1.6603, + "step": 72700 + }, + { + "epoch": 2.7, + "eval_loss": 1.6766068935394287, + "eval_runtime": 16.8615, + "eval_samples_per_second": 59.307, + "eval_steps_per_second": 3.736, + "step": 72700 + }, + { + "epoch": 2.7, + "learning_rate": 7.295719120764683e-06, + "loss": 1.7683, + "step": 72710 + }, + { + "epoch": 2.7, + "learning_rate": 7.295347193811136e-06, + "loss": 1.6658, + "step": 72720 + }, + { + "epoch": 2.71, + "learning_rate": 7.29497526685759e-06, + "loss": 1.5799, + "step": 72730 + }, + { + "epoch": 2.71, + "learning_rate": 7.294603339904044e-06, + "loss": 1.7621, + "step": 72740 + }, + { + "epoch": 2.71, + "learning_rate": 7.294231412950498e-06, + "loss": 1.7958, + "step": 72750 + }, + { + "epoch": 2.71, + "learning_rate": 7.29385948599695e-06, + "loss": 1.6026, + "step": 72760 + }, + { + "epoch": 2.71, + "learning_rate": 7.293487559043404e-06, + "loss": 1.6446, + "step": 72770 + }, + { + "epoch": 2.71, + "learning_rate": 7.293115632089858e-06, + "loss": 1.7213, + "step": 72780 + }, + { + "epoch": 2.71, + "learning_rate": 7.2927437051363114e-06, + "loss": 1.6311, + "step": 72790 + }, + { + "epoch": 2.71, + "learning_rate": 7.292371778182765e-06, + "loss": 1.7191, + "step": 72800 + }, + { + "epoch": 2.71, + "eval_loss": 1.6768057346343994, + "eval_runtime": 16.8387, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 72800 + }, + { + "epoch": 2.71, + "learning_rate": 7.291999851229219e-06, + "loss": 1.6684, + "step": 72810 + }, + { + "epoch": 2.71, + "learning_rate": 7.291627924275673e-06, + "loss": 1.6398, + "step": 72820 + }, + { + "epoch": 2.71, + "learning_rate": 7.291255997322126e-06, + "loss": 1.8484, + "step": 72830 + }, + { + "epoch": 2.71, + "learning_rate": 7.29088407036858e-06, + "loss": 1.9154, + "step": 72840 + }, + { + "epoch": 2.71, + "learning_rate": 7.290512143415034e-06, + "loss": 1.6503, + "step": 72850 + }, + { + "epoch": 2.71, + "learning_rate": 7.290140216461487e-06, + "loss": 1.7207, + "step": 72860 + }, + { + "epoch": 2.71, + "learning_rate": 7.289768289507942e-06, + "loss": 1.676, + "step": 72870 + }, + { + "epoch": 2.71, + "learning_rate": 7.289396362554395e-06, + "loss": 1.9465, + "step": 72880 + }, + { + "epoch": 2.71, + "learning_rate": 7.2890244356008486e-06, + "loss": 1.7821, + "step": 72890 + }, + { + "epoch": 2.71, + "learning_rate": 7.288652508647303e-06, + "loss": 1.6537, + "step": 72900 + }, + { + "epoch": 2.71, + "eval_loss": 1.6762820482254028, + "eval_runtime": 16.8362, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 72900 + }, + { + "epoch": 2.71, + "learning_rate": 7.288280581693756e-06, + "loss": 1.6079, + "step": 72910 + }, + { + "epoch": 2.71, + "learning_rate": 7.28790865474021e-06, + "loss": 1.7952, + "step": 72920 + }, + { + "epoch": 2.71, + "learning_rate": 7.287536727786664e-06, + "loss": 1.6626, + "step": 72930 + }, + { + "epoch": 2.71, + "learning_rate": 7.2871648008331176e-06, + "loss": 1.6425, + "step": 72940 + }, + { + "epoch": 2.71, + "learning_rate": 7.28679287387957e-06, + "loss": 1.7133, + "step": 72950 + }, + { + "epoch": 2.71, + "learning_rate": 7.286420946926024e-06, + "loss": 1.8181, + "step": 72960 + }, + { + "epoch": 2.71, + "learning_rate": 7.286049019972478e-06, + "loss": 1.8654, + "step": 72970 + }, + { + "epoch": 2.71, + "learning_rate": 7.285677093018931e-06, + "loss": 1.8478, + "step": 72980 + }, + { + "epoch": 2.71, + "learning_rate": 7.285305166065385e-06, + "loss": 1.8148, + "step": 72990 + }, + { + "epoch": 2.72, + "learning_rate": 7.284933239111839e-06, + "loss": 1.6813, + "step": 73000 + }, + { + "epoch": 2.72, + "eval_loss": 1.6767030954360962, + "eval_runtime": 16.8478, + "eval_samples_per_second": 59.355, + "eval_steps_per_second": 3.739, + "step": 73000 + }, + { + "epoch": 2.72, + "learning_rate": 7.284561312158293e-06, + "loss": 1.705, + "step": 73010 + }, + { + "epoch": 2.72, + "learning_rate": 7.284189385204746e-06, + "loss": 1.8673, + "step": 73020 + }, + { + "epoch": 2.72, + "learning_rate": 7.2838174582512e-06, + "loss": 1.6783, + "step": 73030 + }, + { + "epoch": 2.72, + "learning_rate": 7.283445531297654e-06, + "loss": 1.655, + "step": 73040 + }, + { + "epoch": 2.72, + "learning_rate": 7.283073604344107e-06, + "loss": 1.72, + "step": 73050 + }, + { + "epoch": 2.72, + "learning_rate": 7.282701677390562e-06, + "loss": 1.7415, + "step": 73060 + }, + { + "epoch": 2.72, + "learning_rate": 7.282329750437015e-06, + "loss": 1.8566, + "step": 73070 + }, + { + "epoch": 2.72, + "learning_rate": 7.2819578234834685e-06, + "loss": 1.7327, + "step": 73080 + }, + { + "epoch": 2.72, + "learning_rate": 7.281585896529923e-06, + "loss": 1.6496, + "step": 73090 + }, + { + "epoch": 2.72, + "learning_rate": 7.281213969576376e-06, + "loss": 1.7099, + "step": 73100 + }, + { + "epoch": 2.72, + "eval_loss": 1.6760475635528564, + "eval_runtime": 16.8432, + "eval_samples_per_second": 59.371, + "eval_steps_per_second": 3.74, + "step": 73100 + }, + { + "epoch": 2.72, + "learning_rate": 7.28084204262283e-06, + "loss": 1.7855, + "step": 73110 + }, + { + "epoch": 2.72, + "learning_rate": 7.280470115669284e-06, + "loss": 1.7642, + "step": 73120 + }, + { + "epoch": 2.72, + "learning_rate": 7.2800981887157375e-06, + "loss": 1.824, + "step": 73130 + }, + { + "epoch": 2.72, + "learning_rate": 7.27972626176219e-06, + "loss": 1.6816, + "step": 73140 + }, + { + "epoch": 2.72, + "learning_rate": 7.279354334808644e-06, + "loss": 1.8824, + "step": 73150 + }, + { + "epoch": 2.72, + "learning_rate": 7.278982407855097e-06, + "loss": 1.8, + "step": 73160 + }, + { + "epoch": 2.72, + "learning_rate": 7.278610480901551e-06, + "loss": 1.634, + "step": 73170 + }, + { + "epoch": 2.72, + "learning_rate": 7.278238553948005e-06, + "loss": 1.7999, + "step": 73180 + }, + { + "epoch": 2.72, + "learning_rate": 7.277866626994458e-06, + "loss": 1.7589, + "step": 73190 + }, + { + "epoch": 2.72, + "learning_rate": 7.2774947000409126e-06, + "loss": 1.6771, + "step": 73200 + }, + { + "epoch": 2.72, + "eval_loss": 1.6761178970336914, + "eval_runtime": 16.8386, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 73200 + }, + { + "epoch": 2.72, + "learning_rate": 7.277122773087366e-06, + "loss": 1.706, + "step": 73210 + }, + { + "epoch": 2.72, + "learning_rate": 7.2767508461338195e-06, + "loss": 1.8858, + "step": 73220 + }, + { + "epoch": 2.72, + "learning_rate": 7.276378919180274e-06, + "loss": 1.7293, + "step": 73230 + }, + { + "epoch": 2.72, + "learning_rate": 7.276006992226727e-06, + "loss": 1.6619, + "step": 73240 + }, + { + "epoch": 2.72, + "learning_rate": 7.275635065273181e-06, + "loss": 1.7063, + "step": 73250 + }, + { + "epoch": 2.72, + "learning_rate": 7.275263138319635e-06, + "loss": 1.7652, + "step": 73260 + }, + { + "epoch": 2.73, + "learning_rate": 7.2748912113660885e-06, + "loss": 1.6674, + "step": 73270 + }, + { + "epoch": 2.73, + "learning_rate": 7.274519284412542e-06, + "loss": 1.6995, + "step": 73280 + }, + { + "epoch": 2.73, + "learning_rate": 7.274147357458996e-06, + "loss": 1.7099, + "step": 73290 + }, + { + "epoch": 2.73, + "learning_rate": 7.27377543050545e-06, + "loss": 1.7805, + "step": 73300 + }, + { + "epoch": 2.73, + "eval_loss": 1.6751413345336914, + "eval_runtime": 16.8404, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 73300 + }, + { + "epoch": 2.73, + "learning_rate": 7.273403503551903e-06, + "loss": 1.6078, + "step": 73310 + }, + { + "epoch": 2.73, + "learning_rate": 7.273031576598356e-06, + "loss": 1.7602, + "step": 73320 + }, + { + "epoch": 2.73, + "learning_rate": 7.27265964964481e-06, + "loss": 1.7494, + "step": 73330 + }, + { + "epoch": 2.73, + "learning_rate": 7.2722877226912635e-06, + "loss": 1.7616, + "step": 73340 + }, + { + "epoch": 2.73, + "learning_rate": 7.271915795737717e-06, + "loss": 1.7147, + "step": 73350 + }, + { + "epoch": 2.73, + "learning_rate": 7.271543868784171e-06, + "loss": 1.7524, + "step": 73360 + }, + { + "epoch": 2.73, + "learning_rate": 7.271171941830625e-06, + "loss": 1.7082, + "step": 73370 + }, + { + "epoch": 2.73, + "learning_rate": 7.270800014877078e-06, + "loss": 1.9675, + "step": 73380 + }, + { + "epoch": 2.73, + "learning_rate": 7.2704280879235325e-06, + "loss": 1.8991, + "step": 73390 + }, + { + "epoch": 2.73, + "learning_rate": 7.270056160969986e-06, + "loss": 1.5621, + "step": 73400 + }, + { + "epoch": 2.73, + "eval_loss": 1.675374984741211, + "eval_runtime": 16.8369, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 73400 + }, + { + "epoch": 2.73, + "learning_rate": 7.2696842340164395e-06, + "loss": 1.7675, + "step": 73410 + }, + { + "epoch": 2.73, + "learning_rate": 7.269312307062894e-06, + "loss": 1.6723, + "step": 73420 + }, + { + "epoch": 2.73, + "learning_rate": 7.268940380109347e-06, + "loss": 1.6385, + "step": 73430 + }, + { + "epoch": 2.73, + "learning_rate": 7.268568453155801e-06, + "loss": 1.7147, + "step": 73440 + }, + { + "epoch": 2.73, + "learning_rate": 7.268196526202255e-06, + "loss": 1.8698, + "step": 73450 + }, + { + "epoch": 2.73, + "learning_rate": 7.2678245992487084e-06, + "loss": 1.91, + "step": 73460 + }, + { + "epoch": 2.73, + "learning_rate": 7.267452672295162e-06, + "loss": 1.6907, + "step": 73470 + }, + { + "epoch": 2.73, + "learning_rate": 7.267080745341616e-06, + "loss": 1.7613, + "step": 73480 + }, + { + "epoch": 2.73, + "learning_rate": 7.26670881838807e-06, + "loss": 1.6456, + "step": 73490 + }, + { + "epoch": 2.73, + "learning_rate": 7.266336891434523e-06, + "loss": 1.7238, + "step": 73500 + }, + { + "epoch": 2.73, + "eval_loss": 1.6752272844314575, + "eval_runtime": 16.8483, + "eval_samples_per_second": 59.353, + "eval_steps_per_second": 3.739, + "step": 73500 + }, + { + "epoch": 2.73, + "learning_rate": 7.265964964480976e-06, + "loss": 1.7261, + "step": 73510 + }, + { + "epoch": 2.73, + "learning_rate": 7.26559303752743e-06, + "loss": 1.6486, + "step": 73520 + }, + { + "epoch": 2.73, + "learning_rate": 7.2652211105738835e-06, + "loss": 1.7134, + "step": 73530 + }, + { + "epoch": 2.74, + "learning_rate": 7.264849183620337e-06, + "loss": 1.7598, + "step": 73540 + }, + { + "epoch": 2.74, + "learning_rate": 7.264477256666791e-06, + "loss": 1.7231, + "step": 73550 + }, + { + "epoch": 2.74, + "learning_rate": 7.264105329713245e-06, + "loss": 1.7294, + "step": 73560 + }, + { + "epoch": 2.74, + "learning_rate": 7.263733402759698e-06, + "loss": 1.8222, + "step": 73570 + }, + { + "epoch": 2.74, + "learning_rate": 7.2633614758061525e-06, + "loss": 1.8775, + "step": 73580 + }, + { + "epoch": 2.74, + "learning_rate": 7.262989548852606e-06, + "loss": 1.7351, + "step": 73590 + }, + { + "epoch": 2.74, + "learning_rate": 7.262617621899059e-06, + "loss": 1.6543, + "step": 73600 + }, + { + "epoch": 2.74, + "eval_loss": 1.6764109134674072, + "eval_runtime": 16.8369, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 73600 + }, + { + "epoch": 2.74, + "learning_rate": 7.262245694945514e-06, + "loss": 1.6838, + "step": 73610 + }, + { + "epoch": 2.74, + "learning_rate": 7.261873767991967e-06, + "loss": 1.7106, + "step": 73620 + }, + { + "epoch": 2.74, + "learning_rate": 7.261501841038421e-06, + "loss": 1.7758, + "step": 73630 + }, + { + "epoch": 2.74, + "learning_rate": 7.261129914084875e-06, + "loss": 1.7063, + "step": 73640 + }, + { + "epoch": 2.74, + "learning_rate": 7.260757987131328e-06, + "loss": 1.6922, + "step": 73650 + }, + { + "epoch": 2.74, + "learning_rate": 7.260386060177782e-06, + "loss": 1.6653, + "step": 73660 + }, + { + "epoch": 2.74, + "learning_rate": 7.260014133224236e-06, + "loss": 1.8271, + "step": 73670 + }, + { + "epoch": 2.74, + "learning_rate": 7.25964220627069e-06, + "loss": 1.727, + "step": 73680 + }, + { + "epoch": 2.74, + "learning_rate": 7.259270279317143e-06, + "loss": 1.7785, + "step": 73690 + }, + { + "epoch": 2.74, + "learning_rate": 7.258898352363596e-06, + "loss": 1.6515, + "step": 73700 + }, + { + "epoch": 2.74, + "eval_loss": 1.6760014295578003, + "eval_runtime": 16.844, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 73700 + }, + { + "epoch": 2.74, + "learning_rate": 7.25852642541005e-06, + "loss": 1.7267, + "step": 73710 + }, + { + "epoch": 2.74, + "learning_rate": 7.2581544984565035e-06, + "loss": 1.733, + "step": 73720 + }, + { + "epoch": 2.74, + "learning_rate": 7.257782571502957e-06, + "loss": 1.6609, + "step": 73730 + }, + { + "epoch": 2.74, + "learning_rate": 7.25741064454941e-06, + "loss": 1.7583, + "step": 73740 + }, + { + "epoch": 2.74, + "learning_rate": 7.257038717595865e-06, + "loss": 1.733, + "step": 73750 + }, + { + "epoch": 2.74, + "learning_rate": 7.256666790642318e-06, + "loss": 1.7596, + "step": 73760 + }, + { + "epoch": 2.74, + "learning_rate": 7.256294863688772e-06, + "loss": 1.6256, + "step": 73770 + }, + { + "epoch": 2.74, + "learning_rate": 7.255922936735226e-06, + "loss": 1.628, + "step": 73780 + }, + { + "epoch": 2.74, + "learning_rate": 7.255551009781679e-06, + "loss": 1.639, + "step": 73790 + }, + { + "epoch": 2.74, + "learning_rate": 7.255179082828133e-06, + "loss": 1.6364, + "step": 73800 + }, + { + "epoch": 2.74, + "eval_loss": 1.6752939224243164, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 73800 + }, + { + "epoch": 2.75, + "learning_rate": 7.254807155874587e-06, + "loss": 1.826, + "step": 73810 + }, + { + "epoch": 2.75, + "learning_rate": 7.254435228921041e-06, + "loss": 1.7673, + "step": 73820 + }, + { + "epoch": 2.75, + "learning_rate": 7.254063301967494e-06, + "loss": 1.6734, + "step": 73830 + }, + { + "epoch": 2.75, + "learning_rate": 7.253691375013948e-06, + "loss": 1.8775, + "step": 73840 + }, + { + "epoch": 2.75, + "learning_rate": 7.253319448060402e-06, + "loss": 1.6774, + "step": 73850 + }, + { + "epoch": 2.75, + "learning_rate": 7.252947521106855e-06, + "loss": 1.7271, + "step": 73860 + }, + { + "epoch": 2.75, + "learning_rate": 7.25257559415331e-06, + "loss": 1.8388, + "step": 73870 + }, + { + "epoch": 2.75, + "learning_rate": 7.252203667199763e-06, + "loss": 1.6397, + "step": 73880 + }, + { + "epoch": 2.75, + "learning_rate": 7.251831740246216e-06, + "loss": 1.7357, + "step": 73890 + }, + { + "epoch": 2.75, + "learning_rate": 7.251459813292669e-06, + "loss": 1.6051, + "step": 73900 + }, + { + "epoch": 2.75, + "eval_loss": 1.676387071609497, + "eval_runtime": 16.8327, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 73900 + }, + { + "epoch": 2.75, + "learning_rate": 7.251087886339123e-06, + "loss": 1.6821, + "step": 73910 + }, + { + "epoch": 2.75, + "learning_rate": 7.250715959385577e-06, + "loss": 1.7907, + "step": 73920 + }, + { + "epoch": 2.75, + "learning_rate": 7.25034403243203e-06, + "loss": 1.6196, + "step": 73930 + }, + { + "epoch": 2.75, + "learning_rate": 7.249972105478485e-06, + "loss": 1.8585, + "step": 73940 + }, + { + "epoch": 2.75, + "learning_rate": 7.249600178524938e-06, + "loss": 1.6346, + "step": 73950 + }, + { + "epoch": 2.75, + "learning_rate": 7.2492282515713916e-06, + "loss": 1.7408, + "step": 73960 + }, + { + "epoch": 2.75, + "learning_rate": 7.248856324617846e-06, + "loss": 1.7255, + "step": 73970 + }, + { + "epoch": 2.75, + "learning_rate": 7.248484397664299e-06, + "loss": 1.651, + "step": 73980 + }, + { + "epoch": 2.75, + "learning_rate": 7.248112470710753e-06, + "loss": 1.8278, + "step": 73990 + }, + { + "epoch": 2.75, + "learning_rate": 7.247740543757207e-06, + "loss": 1.7143, + "step": 74000 + }, + { + "epoch": 2.75, + "eval_loss": 1.6753872632980347, + "eval_runtime": 16.8249, + "eval_samples_per_second": 59.436, + "eval_steps_per_second": 3.744, + "step": 74000 + }, + { + "epoch": 2.75, + "learning_rate": 7.2473686168036606e-06, + "loss": 1.7209, + "step": 74010 + }, + { + "epoch": 2.75, + "learning_rate": 7.246996689850114e-06, + "loss": 1.672, + "step": 74020 + }, + { + "epoch": 2.75, + "learning_rate": 7.246624762896568e-06, + "loss": 1.8357, + "step": 74030 + }, + { + "epoch": 2.75, + "learning_rate": 7.246252835943022e-06, + "loss": 1.7532, + "step": 74040 + }, + { + "epoch": 2.75, + "learning_rate": 7.245880908989475e-06, + "loss": 1.6837, + "step": 74050 + }, + { + "epoch": 2.75, + "learning_rate": 7.2455089820359295e-06, + "loss": 1.7623, + "step": 74060 + }, + { + "epoch": 2.75, + "learning_rate": 7.245137055082383e-06, + "loss": 1.678, + "step": 74070 + }, + { + "epoch": 2.76, + "learning_rate": 7.244765128128836e-06, + "loss": 1.5596, + "step": 74080 + }, + { + "epoch": 2.76, + "learning_rate": 7.244393201175289e-06, + "loss": 1.806, + "step": 74090 + }, + { + "epoch": 2.76, + "learning_rate": 7.244021274221743e-06, + "loss": 1.8176, + "step": 74100 + }, + { + "epoch": 2.76, + "eval_loss": 1.6753093004226685, + "eval_runtime": 16.8576, + "eval_samples_per_second": 59.321, + "eval_steps_per_second": 3.737, + "step": 74100 + }, + { + "epoch": 2.76, + "learning_rate": 7.243649347268197e-06, + "loss": 1.6085, + "step": 74110 + }, + { + "epoch": 2.76, + "learning_rate": 7.24327742031465e-06, + "loss": 1.7045, + "step": 74120 + }, + { + "epoch": 2.76, + "learning_rate": 7.242905493361105e-06, + "loss": 1.7897, + "step": 74130 + }, + { + "epoch": 2.76, + "learning_rate": 7.242533566407558e-06, + "loss": 1.6732, + "step": 74140 + }, + { + "epoch": 2.76, + "learning_rate": 7.2421616394540115e-06, + "loss": 1.8746, + "step": 74150 + }, + { + "epoch": 2.76, + "learning_rate": 7.241789712500466e-06, + "loss": 1.682, + "step": 74160 + }, + { + "epoch": 2.76, + "learning_rate": 7.241417785546919e-06, + "loss": 1.623, + "step": 74170 + }, + { + "epoch": 2.76, + "learning_rate": 7.241045858593373e-06, + "loss": 1.6884, + "step": 74180 + }, + { + "epoch": 2.76, + "learning_rate": 7.240673931639827e-06, + "loss": 1.7795, + "step": 74190 + }, + { + "epoch": 2.76, + "learning_rate": 7.2403020046862805e-06, + "loss": 1.776, + "step": 74200 + }, + { + "epoch": 2.76, + "eval_loss": 1.6754587888717651, + "eval_runtime": 16.8535, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 74200 + }, + { + "epoch": 2.76, + "learning_rate": 7.239930077732734e-06, + "loss": 1.8891, + "step": 74210 + }, + { + "epoch": 2.76, + "learning_rate": 7.239558150779188e-06, + "loss": 1.7506, + "step": 74220 + }, + { + "epoch": 2.76, + "learning_rate": 7.239186223825642e-06, + "loss": 1.8114, + "step": 74230 + }, + { + "epoch": 2.76, + "learning_rate": 7.238814296872095e-06, + "loss": 1.9401, + "step": 74240 + }, + { + "epoch": 2.76, + "learning_rate": 7.2384423699185495e-06, + "loss": 1.7821, + "step": 74250 + }, + { + "epoch": 2.76, + "learning_rate": 7.238070442965002e-06, + "loss": 1.7278, + "step": 74260 + }, + { + "epoch": 2.76, + "learning_rate": 7.2376985160114556e-06, + "loss": 1.7912, + "step": 74270 + }, + { + "epoch": 2.76, + "learning_rate": 7.237326589057909e-06, + "loss": 1.8031, + "step": 74280 + }, + { + "epoch": 2.76, + "learning_rate": 7.236954662104363e-06, + "loss": 1.6559, + "step": 74290 + }, + { + "epoch": 2.76, + "learning_rate": 7.236582735150817e-06, + "loss": 1.6735, + "step": 74300 + }, + { + "epoch": 2.76, + "eval_loss": 1.6750752925872803, + "eval_runtime": 16.831, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 74300 + }, + { + "epoch": 2.76, + "learning_rate": 7.23621080819727e-06, + "loss": 1.9367, + "step": 74310 + }, + { + "epoch": 2.76, + "learning_rate": 7.235838881243724e-06, + "loss": 1.8625, + "step": 74320 + }, + { + "epoch": 2.76, + "learning_rate": 7.235466954290178e-06, + "loss": 1.7077, + "step": 74330 + }, + { + "epoch": 2.76, + "learning_rate": 7.2350950273366315e-06, + "loss": 1.6483, + "step": 74340 + }, + { + "epoch": 2.77, + "learning_rate": 7.234723100383085e-06, + "loss": 1.6449, + "step": 74350 + }, + { + "epoch": 2.77, + "learning_rate": 7.234351173429539e-06, + "loss": 1.7254, + "step": 74360 + }, + { + "epoch": 2.77, + "learning_rate": 7.233979246475993e-06, + "loss": 1.5597, + "step": 74370 + }, + { + "epoch": 2.77, + "learning_rate": 7.233607319522446e-06, + "loss": 1.9322, + "step": 74380 + }, + { + "epoch": 2.77, + "learning_rate": 7.2332353925689005e-06, + "loss": 1.6638, + "step": 74390 + }, + { + "epoch": 2.77, + "learning_rate": 7.232863465615354e-06, + "loss": 1.7589, + "step": 74400 + }, + { + "epoch": 2.77, + "eval_loss": 1.6764644384384155, + "eval_runtime": 16.8294, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 74400 + }, + { + "epoch": 2.77, + "learning_rate": 7.232491538661807e-06, + "loss": 1.8716, + "step": 74410 + }, + { + "epoch": 2.77, + "learning_rate": 7.232119611708262e-06, + "loss": 1.7617, + "step": 74420 + }, + { + "epoch": 2.77, + "learning_rate": 7.231747684754715e-06, + "loss": 1.7643, + "step": 74430 + }, + { + "epoch": 2.77, + "learning_rate": 7.231375757801169e-06, + "loss": 1.8911, + "step": 74440 + }, + { + "epoch": 2.77, + "learning_rate": 7.231003830847621e-06, + "loss": 1.72, + "step": 74450 + }, + { + "epoch": 2.77, + "learning_rate": 7.2306319038940755e-06, + "loss": 1.6875, + "step": 74460 + }, + { + "epoch": 2.77, + "learning_rate": 7.230259976940529e-06, + "loss": 1.6414, + "step": 74470 + }, + { + "epoch": 2.77, + "learning_rate": 7.2298880499869825e-06, + "loss": 1.639, + "step": 74480 + }, + { + "epoch": 2.77, + "learning_rate": 7.229516123033437e-06, + "loss": 1.6034, + "step": 74490 + }, + { + "epoch": 2.77, + "learning_rate": 7.22914419607989e-06, + "loss": 1.8007, + "step": 74500 + }, + { + "epoch": 2.77, + "eval_loss": 1.6757732629776, + "eval_runtime": 16.853, + "eval_samples_per_second": 59.337, + "eval_steps_per_second": 3.738, + "step": 74500 + }, + { + "epoch": 2.77, + "learning_rate": 7.228772269126344e-06, + "loss": 1.6483, + "step": 74510 + }, + { + "epoch": 2.77, + "learning_rate": 7.228400342172798e-06, + "loss": 1.7413, + "step": 74520 + }, + { + "epoch": 2.77, + "learning_rate": 7.2280284152192514e-06, + "loss": 1.6414, + "step": 74530 + }, + { + "epoch": 2.77, + "learning_rate": 7.227656488265705e-06, + "loss": 1.7183, + "step": 74540 + }, + { + "epoch": 2.77, + "learning_rate": 7.227284561312159e-06, + "loss": 1.7156, + "step": 74550 + }, + { + "epoch": 2.77, + "learning_rate": 7.226912634358613e-06, + "loss": 1.7668, + "step": 74560 + }, + { + "epoch": 2.77, + "learning_rate": 7.226540707405066e-06, + "loss": 1.6722, + "step": 74570 + }, + { + "epoch": 2.77, + "learning_rate": 7.2261687804515204e-06, + "loss": 1.7034, + "step": 74580 + }, + { + "epoch": 2.77, + "learning_rate": 7.225796853497974e-06, + "loss": 1.7582, + "step": 74590 + }, + { + "epoch": 2.77, + "learning_rate": 7.225424926544427e-06, + "loss": 1.6552, + "step": 74600 + }, + { + "epoch": 2.77, + "eval_loss": 1.6753547191619873, + "eval_runtime": 16.8463, + "eval_samples_per_second": 59.36, + "eval_steps_per_second": 3.74, + "step": 74600 + }, + { + "epoch": 2.77, + "learning_rate": 7.225052999590882e-06, + "loss": 1.7266, + "step": 74610 + }, + { + "epoch": 2.78, + "learning_rate": 7.224681072637335e-06, + "loss": 1.7166, + "step": 74620 + }, + { + "epoch": 2.78, + "learning_rate": 7.2243091456837886e-06, + "loss": 1.6276, + "step": 74630 + }, + { + "epoch": 2.78, + "learning_rate": 7.223937218730241e-06, + "loss": 1.7245, + "step": 74640 + }, + { + "epoch": 2.78, + "learning_rate": 7.2235652917766955e-06, + "loss": 1.578, + "step": 74650 + }, + { + "epoch": 2.78, + "learning_rate": 7.223193364823149e-06, + "loss": 1.64, + "step": 74660 + }, + { + "epoch": 2.78, + "learning_rate": 7.222821437869602e-06, + "loss": 1.625, + "step": 74670 + }, + { + "epoch": 2.78, + "learning_rate": 7.222449510916057e-06, + "loss": 1.7168, + "step": 74680 + }, + { + "epoch": 2.78, + "learning_rate": 7.22207758396251e-06, + "loss": 1.6079, + "step": 74690 + }, + { + "epoch": 2.78, + "learning_rate": 7.221705657008964e-06, + "loss": 1.5941, + "step": 74700 + }, + { + "epoch": 2.78, + "eval_loss": 1.6744145154953003, + "eval_runtime": 16.826, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 74700 + }, + { + "epoch": 2.78, + "learning_rate": 7.221333730055418e-06, + "loss": 1.7293, + "step": 74710 + }, + { + "epoch": 2.78, + "learning_rate": 7.220961803101871e-06, + "loss": 1.6915, + "step": 74720 + }, + { + "epoch": 2.78, + "learning_rate": 7.220589876148325e-06, + "loss": 1.6603, + "step": 74730 + }, + { + "epoch": 2.78, + "learning_rate": 7.220217949194779e-06, + "loss": 1.7873, + "step": 74740 + }, + { + "epoch": 2.78, + "learning_rate": 7.219846022241233e-06, + "loss": 1.8999, + "step": 74750 + }, + { + "epoch": 2.78, + "learning_rate": 7.219474095287686e-06, + "loss": 1.7115, + "step": 74760 + }, + { + "epoch": 2.78, + "learning_rate": 7.21910216833414e-06, + "loss": 1.6898, + "step": 74770 + }, + { + "epoch": 2.78, + "learning_rate": 7.218730241380594e-06, + "loss": 1.7026, + "step": 74780 + }, + { + "epoch": 2.78, + "learning_rate": 7.218358314427047e-06, + "loss": 1.7217, + "step": 74790 + }, + { + "epoch": 2.78, + "learning_rate": 7.217986387473502e-06, + "loss": 1.9491, + "step": 74800 + }, + { + "epoch": 2.78, + "eval_loss": 1.6748279333114624, + "eval_runtime": 16.8295, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 74800 + }, + { + "epoch": 2.78, + "learning_rate": 7.217614460519955e-06, + "loss": 1.6117, + "step": 74810 + }, + { + "epoch": 2.78, + "learning_rate": 7.2172425335664085e-06, + "loss": 1.7295, + "step": 74820 + }, + { + "epoch": 2.78, + "learning_rate": 7.216870606612861e-06, + "loss": 1.7459, + "step": 74830 + }, + { + "epoch": 2.78, + "learning_rate": 7.2164986796593155e-06, + "loss": 1.6356, + "step": 74840 + }, + { + "epoch": 2.78, + "learning_rate": 7.216126752705769e-06, + "loss": 1.7209, + "step": 74850 + }, + { + "epoch": 2.78, + "learning_rate": 7.215754825752222e-06, + "loss": 1.671, + "step": 74860 + }, + { + "epoch": 2.78, + "learning_rate": 7.215382898798677e-06, + "loss": 1.7053, + "step": 74870 + }, + { + "epoch": 2.78, + "learning_rate": 7.21501097184513e-06, + "loss": 1.7016, + "step": 74880 + }, + { + "epoch": 2.79, + "learning_rate": 7.214639044891584e-06, + "loss": 1.7162, + "step": 74890 + }, + { + "epoch": 2.79, + "learning_rate": 7.214267117938037e-06, + "loss": 1.7215, + "step": 74900 + }, + { + "epoch": 2.79, + "eval_loss": 1.673883318901062, + "eval_runtime": 16.8347, + "eval_samples_per_second": 59.401, + "eval_steps_per_second": 3.742, + "step": 74900 + }, + { + "epoch": 2.79, + "learning_rate": 7.213895190984491e-06, + "loss": 1.7411, + "step": 74910 + }, + { + "epoch": 2.79, + "learning_rate": 7.213523264030945e-06, + "loss": 1.781, + "step": 74920 + }, + { + "epoch": 2.79, + "learning_rate": 7.213151337077398e-06, + "loss": 1.6552, + "step": 74930 + }, + { + "epoch": 2.79, + "learning_rate": 7.212779410123853e-06, + "loss": 1.7102, + "step": 74940 + }, + { + "epoch": 2.79, + "learning_rate": 7.212407483170306e-06, + "loss": 1.6588, + "step": 74950 + }, + { + "epoch": 2.79, + "learning_rate": 7.2120355562167595e-06, + "loss": 1.7465, + "step": 74960 + }, + { + "epoch": 2.79, + "learning_rate": 7.211663629263214e-06, + "loss": 1.763, + "step": 74970 + }, + { + "epoch": 2.79, + "learning_rate": 7.211291702309667e-06, + "loss": 1.7122, + "step": 74980 + }, + { + "epoch": 2.79, + "learning_rate": 7.210919775356121e-06, + "loss": 1.8118, + "step": 74990 + }, + { + "epoch": 2.79, + "learning_rate": 7.210547848402575e-06, + "loss": 1.7703, + "step": 75000 + }, + { + "epoch": 2.79, + "eval_loss": 1.6751567125320435, + "eval_runtime": 16.8497, + "eval_samples_per_second": 59.348, + "eval_steps_per_second": 3.739, + "step": 75000 + }, + { + "epoch": 2.79, + "learning_rate": 7.210175921449028e-06, + "loss": 1.7248, + "step": 75010 + }, + { + "epoch": 2.79, + "learning_rate": 7.209803994495481e-06, + "loss": 1.6715, + "step": 75020 + }, + { + "epoch": 2.79, + "learning_rate": 7.2094320675419346e-06, + "loss": 1.798, + "step": 75030 + }, + { + "epoch": 2.79, + "learning_rate": 7.209060140588389e-06, + "loss": 1.7533, + "step": 75040 + }, + { + "epoch": 2.79, + "learning_rate": 7.208688213634842e-06, + "loss": 1.7517, + "step": 75050 + }, + { + "epoch": 2.79, + "learning_rate": 7.208316286681296e-06, + "loss": 1.6888, + "step": 75060 + }, + { + "epoch": 2.79, + "learning_rate": 7.20794435972775e-06, + "loss": 1.8246, + "step": 75070 + }, + { + "epoch": 2.79, + "learning_rate": 7.2075724327742036e-06, + "loss": 1.6527, + "step": 75080 + }, + { + "epoch": 2.79, + "learning_rate": 7.207200505820657e-06, + "loss": 1.6575, + "step": 75090 + }, + { + "epoch": 2.79, + "learning_rate": 7.206828578867111e-06, + "loss": 1.7241, + "step": 75100 + }, + { + "epoch": 2.79, + "eval_loss": 1.6736159324645996, + "eval_runtime": 16.8323, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 75100 + }, + { + "epoch": 2.79, + "learning_rate": 7.206456651913565e-06, + "loss": 1.6511, + "step": 75110 + }, + { + "epoch": 2.79, + "learning_rate": 7.206084724960018e-06, + "loss": 1.7024, + "step": 75120 + }, + { + "epoch": 2.79, + "learning_rate": 7.2057127980064725e-06, + "loss": 1.6344, + "step": 75130 + }, + { + "epoch": 2.79, + "learning_rate": 7.205340871052926e-06, + "loss": 1.6955, + "step": 75140 + }, + { + "epoch": 2.8, + "learning_rate": 7.2049689440993795e-06, + "loss": 1.5988, + "step": 75150 + }, + { + "epoch": 2.8, + "learning_rate": 7.204597017145834e-06, + "loss": 1.6904, + "step": 75160 + }, + { + "epoch": 2.8, + "learning_rate": 7.204225090192287e-06, + "loss": 1.6359, + "step": 75170 + }, + { + "epoch": 2.8, + "learning_rate": 7.203853163238741e-06, + "loss": 1.8974, + "step": 75180 + }, + { + "epoch": 2.8, + "learning_rate": 7.203481236285195e-06, + "loss": 1.6647, + "step": 75190 + }, + { + "epoch": 2.8, + "learning_rate": 7.203109309331648e-06, + "loss": 1.607, + "step": 75200 + }, + { + "epoch": 2.8, + "eval_loss": 1.6742209196090698, + "eval_runtime": 16.8419, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 75200 + }, + { + "epoch": 2.8, + "learning_rate": 7.202737382378101e-06, + "loss": 1.7231, + "step": 75210 + }, + { + "epoch": 2.8, + "learning_rate": 7.2023654554245545e-06, + "loss": 1.6719, + "step": 75220 + }, + { + "epoch": 2.8, + "learning_rate": 7.201993528471009e-06, + "loss": 1.6647, + "step": 75230 + }, + { + "epoch": 2.8, + "learning_rate": 7.201621601517462e-06, + "loss": 1.6387, + "step": 75240 + }, + { + "epoch": 2.8, + "learning_rate": 7.201249674563916e-06, + "loss": 1.659, + "step": 75250 + }, + { + "epoch": 2.8, + "learning_rate": 7.20087774761037e-06, + "loss": 1.6397, + "step": 75260 + }, + { + "epoch": 2.8, + "learning_rate": 7.2005058206568235e-06, + "loss": 1.7105, + "step": 75270 + }, + { + "epoch": 2.8, + "learning_rate": 7.200133893703277e-06, + "loss": 1.6448, + "step": 75280 + }, + { + "epoch": 2.8, + "learning_rate": 7.199761966749731e-06, + "loss": 1.7809, + "step": 75290 + }, + { + "epoch": 2.8, + "learning_rate": 7.199390039796185e-06, + "loss": 1.7578, + "step": 75300 + }, + { + "epoch": 2.8, + "eval_loss": 1.6730787754058838, + "eval_runtime": 16.8384, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 75300 + }, + { + "epoch": 2.8, + "learning_rate": 7.199018112842638e-06, + "loss": 1.6535, + "step": 75310 + }, + { + "epoch": 2.8, + "learning_rate": 7.1986461858890925e-06, + "loss": 1.7491, + "step": 75320 + }, + { + "epoch": 2.8, + "learning_rate": 7.198274258935546e-06, + "loss": 1.7084, + "step": 75330 + }, + { + "epoch": 2.8, + "learning_rate": 7.197902331981999e-06, + "loss": 1.7968, + "step": 75340 + }, + { + "epoch": 2.8, + "learning_rate": 7.197530405028454e-06, + "loss": 1.9089, + "step": 75350 + }, + { + "epoch": 2.8, + "learning_rate": 7.197158478074907e-06, + "loss": 1.7181, + "step": 75360 + }, + { + "epoch": 2.8, + "learning_rate": 7.196786551121361e-06, + "loss": 1.746, + "step": 75370 + }, + { + "epoch": 2.8, + "learning_rate": 7.196414624167815e-06, + "loss": 1.7653, + "step": 75380 + }, + { + "epoch": 2.8, + "learning_rate": 7.1960426972142676e-06, + "loss": 1.6638, + "step": 75390 + }, + { + "epoch": 2.8, + "learning_rate": 7.195670770260721e-06, + "loss": 1.821, + "step": 75400 + }, + { + "epoch": 2.8, + "eval_loss": 1.6743552684783936, + "eval_runtime": 16.8306, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 75400 + }, + { + "epoch": 2.8, + "learning_rate": 7.1952988433071745e-06, + "loss": 1.6854, + "step": 75410 + }, + { + "epoch": 2.81, + "learning_rate": 7.194926916353629e-06, + "loss": 1.633, + "step": 75420 + }, + { + "epoch": 2.81, + "learning_rate": 7.194554989400082e-06, + "loss": 1.5935, + "step": 75430 + }, + { + "epoch": 2.81, + "learning_rate": 7.194183062446536e-06, + "loss": 1.6656, + "step": 75440 + }, + { + "epoch": 2.81, + "learning_rate": 7.19381113549299e-06, + "loss": 1.6711, + "step": 75450 + }, + { + "epoch": 2.81, + "learning_rate": 7.1934392085394435e-06, + "loss": 1.7876, + "step": 75460 + }, + { + "epoch": 2.81, + "learning_rate": 7.193067281585897e-06, + "loss": 1.5513, + "step": 75470 + }, + { + "epoch": 2.81, + "learning_rate": 7.19269535463235e-06, + "loss": 1.9045, + "step": 75480 + }, + { + "epoch": 2.81, + "learning_rate": 7.192323427678805e-06, + "loss": 1.8641, + "step": 75490 + }, + { + "epoch": 2.81, + "learning_rate": 7.191951500725258e-06, + "loss": 1.7009, + "step": 75500 + }, + { + "epoch": 2.81, + "eval_loss": 1.6727824211120605, + "eval_runtime": 16.854, + "eval_samples_per_second": 59.333, + "eval_steps_per_second": 3.738, + "step": 75500 + }, + { + "epoch": 2.81, + "learning_rate": 7.191579573771712e-06, + "loss": 1.623, + "step": 75510 + }, + { + "epoch": 2.81, + "learning_rate": 7.191207646818166e-06, + "loss": 1.8181, + "step": 75520 + }, + { + "epoch": 2.81, + "learning_rate": 7.190835719864619e-06, + "loss": 1.8818, + "step": 75530 + }, + { + "epoch": 2.81, + "learning_rate": 7.190463792911073e-06, + "loss": 1.78, + "step": 75540 + }, + { + "epoch": 2.81, + "learning_rate": 7.190091865957527e-06, + "loss": 1.6814, + "step": 75550 + }, + { + "epoch": 2.81, + "learning_rate": 7.189719939003981e-06, + "loss": 1.5907, + "step": 75560 + }, + { + "epoch": 2.81, + "learning_rate": 7.189348012050434e-06, + "loss": 1.6423, + "step": 75570 + }, + { + "epoch": 2.81, + "learning_rate": 7.188976085096887e-06, + "loss": 1.7494, + "step": 75580 + }, + { + "epoch": 2.81, + "learning_rate": 7.188604158143341e-06, + "loss": 1.6759, + "step": 75590 + }, + { + "epoch": 2.81, + "learning_rate": 7.1882322311897944e-06, + "loss": 1.7995, + "step": 75600 + }, + { + "epoch": 2.81, + "eval_loss": 1.673179268836975, + "eval_runtime": 16.8368, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 75600 + }, + { + "epoch": 2.81, + "learning_rate": 7.187860304236248e-06, + "loss": 1.6563, + "step": 75610 + }, + { + "epoch": 2.81, + "learning_rate": 7.187488377282702e-06, + "loss": 1.7454, + "step": 75620 + }, + { + "epoch": 2.81, + "learning_rate": 7.187116450329156e-06, + "loss": 1.725, + "step": 75630 + }, + { + "epoch": 2.81, + "learning_rate": 7.186744523375609e-06, + "loss": 1.8632, + "step": 75640 + }, + { + "epoch": 2.81, + "learning_rate": 7.1863725964220634e-06, + "loss": 1.8624, + "step": 75650 + }, + { + "epoch": 2.81, + "learning_rate": 7.186000669468517e-06, + "loss": 1.5876, + "step": 75660 + }, + { + "epoch": 2.81, + "learning_rate": 7.18562874251497e-06, + "loss": 1.7303, + "step": 75670 + }, + { + "epoch": 2.81, + "learning_rate": 7.185256815561425e-06, + "loss": 1.7649, + "step": 75680 + }, + { + "epoch": 2.82, + "learning_rate": 7.184884888607878e-06, + "loss": 1.7446, + "step": 75690 + }, + { + "epoch": 2.82, + "learning_rate": 7.1845129616543316e-06, + "loss": 1.7327, + "step": 75700 + }, + { + "epoch": 2.82, + "eval_loss": 1.673406958580017, + "eval_runtime": 16.8502, + "eval_samples_per_second": 59.347, + "eval_steps_per_second": 3.739, + "step": 75700 + }, + { + "epoch": 2.82, + "learning_rate": 7.184141034700786e-06, + "loss": 1.7588, + "step": 75710 + }, + { + "epoch": 2.82, + "learning_rate": 7.183769107747239e-06, + "loss": 1.6303, + "step": 75720 + }, + { + "epoch": 2.82, + "learning_rate": 7.183397180793693e-06, + "loss": 1.6113, + "step": 75730 + }, + { + "epoch": 2.82, + "learning_rate": 7.183025253840147e-06, + "loss": 1.8077, + "step": 75740 + }, + { + "epoch": 2.82, + "learning_rate": 7.1826533268866006e-06, + "loss": 1.738, + "step": 75750 + }, + { + "epoch": 2.82, + "learning_rate": 7.182281399933054e-06, + "loss": 1.6686, + "step": 75760 + }, + { + "epoch": 2.82, + "learning_rate": 7.181909472979507e-06, + "loss": 1.7009, + "step": 75770 + }, + { + "epoch": 2.82, + "learning_rate": 7.181537546025961e-06, + "loss": 1.7029, + "step": 75780 + }, + { + "epoch": 2.82, + "learning_rate": 7.181165619072414e-06, + "loss": 1.7801, + "step": 75790 + }, + { + "epoch": 2.82, + "learning_rate": 7.180793692118868e-06, + "loss": 1.7225, + "step": 75800 + }, + { + "epoch": 2.82, + "eval_loss": 1.6738132238388062, + "eval_runtime": 16.8529, + "eval_samples_per_second": 59.337, + "eval_steps_per_second": 3.738, + "step": 75800 + }, + { + "epoch": 2.82, + "learning_rate": 7.180421765165322e-06, + "loss": 1.7141, + "step": 75810 + }, + { + "epoch": 2.82, + "learning_rate": 7.180049838211776e-06, + "loss": 1.7347, + "step": 75820 + }, + { + "epoch": 2.82, + "learning_rate": 7.179677911258229e-06, + "loss": 1.7822, + "step": 75830 + }, + { + "epoch": 2.82, + "learning_rate": 7.179305984304683e-06, + "loss": 1.6717, + "step": 75840 + }, + { + "epoch": 2.82, + "learning_rate": 7.178934057351137e-06, + "loss": 1.765, + "step": 75850 + }, + { + "epoch": 2.82, + "learning_rate": 7.17856213039759e-06, + "loss": 1.6449, + "step": 75860 + }, + { + "epoch": 2.82, + "learning_rate": 7.178190203444045e-06, + "loss": 1.6126, + "step": 75870 + }, + { + "epoch": 2.82, + "learning_rate": 7.177818276490498e-06, + "loss": 1.6894, + "step": 75880 + }, + { + "epoch": 2.82, + "learning_rate": 7.1774463495369515e-06, + "loss": 1.8004, + "step": 75890 + }, + { + "epoch": 2.82, + "learning_rate": 7.177074422583406e-06, + "loss": 1.6329, + "step": 75900 + }, + { + "epoch": 2.82, + "eval_loss": 1.672284722328186, + "eval_runtime": 16.8284, + "eval_samples_per_second": 59.423, + "eval_steps_per_second": 3.744, + "step": 75900 + }, + { + "epoch": 2.82, + "learning_rate": 7.176702495629859e-06, + "loss": 1.6994, + "step": 75910 + }, + { + "epoch": 2.82, + "learning_rate": 7.176330568676313e-06, + "loss": 1.7538, + "step": 75920 + }, + { + "epoch": 2.82, + "learning_rate": 7.175958641722767e-06, + "loss": 1.4473, + "step": 75930 + }, + { + "epoch": 2.82, + "learning_rate": 7.1755867147692205e-06, + "loss": 1.7744, + "step": 75940 + }, + { + "epoch": 2.82, + "learning_rate": 7.175214787815673e-06, + "loss": 1.8083, + "step": 75950 + }, + { + "epoch": 2.83, + "learning_rate": 7.174842860862127e-06, + "loss": 1.7404, + "step": 75960 + }, + { + "epoch": 2.83, + "learning_rate": 7.174470933908581e-06, + "loss": 1.6978, + "step": 75970 + }, + { + "epoch": 2.83, + "learning_rate": 7.174099006955034e-06, + "loss": 1.6364, + "step": 75980 + }, + { + "epoch": 2.83, + "learning_rate": 7.173727080001488e-06, + "loss": 1.8678, + "step": 75990 + }, + { + "epoch": 2.83, + "learning_rate": 7.173355153047942e-06, + "loss": 1.6154, + "step": 76000 + }, + { + "epoch": 2.83, + "eval_loss": 1.6716760396957397, + "eval_runtime": 16.8698, + "eval_samples_per_second": 59.277, + "eval_steps_per_second": 3.734, + "step": 76000 + }, + { + "epoch": 2.83, + "learning_rate": 7.172983226094396e-06, + "loss": 1.7786, + "step": 76010 + }, + { + "epoch": 2.83, + "learning_rate": 7.172611299140849e-06, + "loss": 1.6599, + "step": 76020 + }, + { + "epoch": 2.83, + "learning_rate": 7.172239372187303e-06, + "loss": 1.766, + "step": 76030 + }, + { + "epoch": 2.83, + "learning_rate": 7.171867445233757e-06, + "loss": 1.6913, + "step": 76040 + }, + { + "epoch": 2.83, + "learning_rate": 7.17149551828021e-06, + "loss": 1.6689, + "step": 76050 + }, + { + "epoch": 2.83, + "learning_rate": 7.171123591326664e-06, + "loss": 1.7685, + "step": 76060 + }, + { + "epoch": 2.83, + "learning_rate": 7.170751664373118e-06, + "loss": 1.6806, + "step": 76070 + }, + { + "epoch": 2.83, + "learning_rate": 7.1703797374195715e-06, + "loss": 1.7654, + "step": 76080 + }, + { + "epoch": 2.83, + "learning_rate": 7.170007810466025e-06, + "loss": 1.6539, + "step": 76090 + }, + { + "epoch": 2.83, + "learning_rate": 7.169635883512479e-06, + "loss": 1.8298, + "step": 76100 + }, + { + "epoch": 2.83, + "eval_loss": 1.6723395586013794, + "eval_runtime": 16.8463, + "eval_samples_per_second": 59.36, + "eval_steps_per_second": 3.74, + "step": 76100 + }, + { + "epoch": 2.83, + "learning_rate": 7.169263956558933e-06, + "loss": 1.874, + "step": 76110 + }, + { + "epoch": 2.83, + "learning_rate": 7.168892029605386e-06, + "loss": 1.6882, + "step": 76120 + }, + { + "epoch": 2.83, + "learning_rate": 7.1685201026518405e-06, + "loss": 1.613, + "step": 76130 + }, + { + "epoch": 2.83, + "learning_rate": 7.168148175698293e-06, + "loss": 1.6587, + "step": 76140 + }, + { + "epoch": 2.83, + "learning_rate": 7.1677762487447466e-06, + "loss": 1.7309, + "step": 76150 + }, + { + "epoch": 2.83, + "learning_rate": 7.1674043217912e-06, + "loss": 1.7023, + "step": 76160 + }, + { + "epoch": 2.83, + "learning_rate": 7.167032394837654e-06, + "loss": 1.6725, + "step": 76170 + }, + { + "epoch": 2.83, + "learning_rate": 7.166660467884108e-06, + "loss": 1.6406, + "step": 76180 + }, + { + "epoch": 2.83, + "learning_rate": 7.166288540930561e-06, + "loss": 1.7865, + "step": 76190 + }, + { + "epoch": 2.83, + "learning_rate": 7.1659166139770155e-06, + "loss": 1.8774, + "step": 76200 + }, + { + "epoch": 2.83, + "eval_loss": 1.6723055839538574, + "eval_runtime": 16.848, + "eval_samples_per_second": 59.354, + "eval_steps_per_second": 3.739, + "step": 76200 + }, + { + "epoch": 2.83, + "learning_rate": 7.165544687023469e-06, + "loss": 1.7238, + "step": 76210 + }, + { + "epoch": 2.83, + "learning_rate": 7.1651727600699225e-06, + "loss": 1.5848, + "step": 76220 + }, + { + "epoch": 2.84, + "learning_rate": 7.164800833116377e-06, + "loss": 1.6776, + "step": 76230 + }, + { + "epoch": 2.84, + "learning_rate": 7.16442890616283e-06, + "loss": 1.7029, + "step": 76240 + }, + { + "epoch": 2.84, + "learning_rate": 7.164056979209284e-06, + "loss": 1.7591, + "step": 76250 + }, + { + "epoch": 2.84, + "learning_rate": 7.163685052255738e-06, + "loss": 1.6038, + "step": 76260 + }, + { + "epoch": 2.84, + "learning_rate": 7.1633131253021915e-06, + "loss": 1.7424, + "step": 76270 + }, + { + "epoch": 2.84, + "learning_rate": 7.162941198348645e-06, + "loss": 1.7325, + "step": 76280 + }, + { + "epoch": 2.84, + "learning_rate": 7.162569271395099e-06, + "loss": 1.7526, + "step": 76290 + }, + { + "epoch": 2.84, + "learning_rate": 7.162197344441553e-06, + "loss": 1.6457, + "step": 76300 + }, + { + "epoch": 2.84, + "eval_loss": 1.6707162857055664, + "eval_runtime": 16.8357, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 76300 + }, + { + "epoch": 2.84, + "learning_rate": 7.161825417488006e-06, + "loss": 1.7178, + "step": 76310 + }, + { + "epoch": 2.84, + "learning_rate": 7.1614534905344604e-06, + "loss": 1.6951, + "step": 76320 + }, + { + "epoch": 2.84, + "learning_rate": 7.161081563580913e-06, + "loss": 1.6185, + "step": 76330 + }, + { + "epoch": 2.84, + "learning_rate": 7.1607096366273665e-06, + "loss": 1.7391, + "step": 76340 + }, + { + "epoch": 2.84, + "learning_rate": 7.16033770967382e-06, + "loss": 1.6227, + "step": 76350 + }, + { + "epoch": 2.84, + "learning_rate": 7.159965782720274e-06, + "loss": 1.6431, + "step": 76360 + }, + { + "epoch": 2.84, + "learning_rate": 7.159593855766728e-06, + "loss": 1.6472, + "step": 76370 + }, + { + "epoch": 2.84, + "learning_rate": 7.159221928813181e-06, + "loss": 1.7329, + "step": 76380 + }, + { + "epoch": 2.84, + "learning_rate": 7.1588500018596355e-06, + "loss": 1.7351, + "step": 76390 + }, + { + "epoch": 2.84, + "learning_rate": 7.158478074906089e-06, + "loss": 1.8515, + "step": 76400 + }, + { + "epoch": 2.84, + "eval_loss": 1.6707446575164795, + "eval_runtime": 16.8247, + "eval_samples_per_second": 59.436, + "eval_steps_per_second": 3.744, + "step": 76400 + }, + { + "epoch": 2.84, + "learning_rate": 7.158106147952542e-06, + "loss": 1.5851, + "step": 76410 + }, + { + "epoch": 2.84, + "learning_rate": 7.157734220998997e-06, + "loss": 1.7235, + "step": 76420 + }, + { + "epoch": 2.84, + "learning_rate": 7.15736229404545e-06, + "loss": 1.7004, + "step": 76430 + }, + { + "epoch": 2.84, + "learning_rate": 7.156990367091904e-06, + "loss": 1.6459, + "step": 76440 + }, + { + "epoch": 2.84, + "learning_rate": 7.156618440138358e-06, + "loss": 1.7187, + "step": 76450 + }, + { + "epoch": 2.84, + "learning_rate": 7.156246513184811e-06, + "loss": 1.9158, + "step": 76460 + }, + { + "epoch": 2.84, + "learning_rate": 7.155874586231265e-06, + "loss": 1.7616, + "step": 76470 + }, + { + "epoch": 2.84, + "learning_rate": 7.155502659277719e-06, + "loss": 1.6938, + "step": 76480 + }, + { + "epoch": 2.84, + "learning_rate": 7.155130732324173e-06, + "loss": 1.6729, + "step": 76490 + }, + { + "epoch": 2.85, + "learning_rate": 7.154758805370626e-06, + "loss": 1.7405, + "step": 76500 + }, + { + "epoch": 2.85, + "eval_loss": 1.6712409257888794, + "eval_runtime": 16.8422, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 76500 + }, + { + "epoch": 2.85, + "learning_rate": 7.15438687841708e-06, + "loss": 1.6932, + "step": 76510 + }, + { + "epoch": 2.85, + "learning_rate": 7.154014951463533e-06, + "loss": 1.8211, + "step": 76520 + }, + { + "epoch": 2.85, + "learning_rate": 7.1536430245099865e-06, + "loss": 1.6342, + "step": 76530 + }, + { + "epoch": 2.85, + "learning_rate": 7.15327109755644e-06, + "loss": 1.72, + "step": 76540 + }, + { + "epoch": 2.85, + "learning_rate": 7.152899170602894e-06, + "loss": 1.7475, + "step": 76550 + }, + { + "epoch": 2.85, + "learning_rate": 7.152527243649348e-06, + "loss": 1.7663, + "step": 76560 + }, + { + "epoch": 2.85, + "learning_rate": 7.152155316695801e-06, + "loss": 1.7114, + "step": 76570 + }, + { + "epoch": 2.85, + "learning_rate": 7.1517833897422555e-06, + "loss": 1.7687, + "step": 76580 + }, + { + "epoch": 2.85, + "learning_rate": 7.151411462788709e-06, + "loss": 1.8154, + "step": 76590 + }, + { + "epoch": 2.85, + "learning_rate": 7.151039535835162e-06, + "loss": 1.7857, + "step": 76600 + }, + { + "epoch": 2.85, + "eval_loss": 1.6705589294433594, + "eval_runtime": 16.8287, + "eval_samples_per_second": 59.422, + "eval_steps_per_second": 3.744, + "step": 76600 + }, + { + "epoch": 2.85, + "learning_rate": 7.150667608881617e-06, + "loss": 1.7373, + "step": 76610 + }, + { + "epoch": 2.85, + "learning_rate": 7.15029568192807e-06, + "loss": 1.7941, + "step": 76620 + }, + { + "epoch": 2.85, + "learning_rate": 7.149923754974524e-06, + "loss": 1.7061, + "step": 76630 + }, + { + "epoch": 2.85, + "learning_rate": 7.149551828020977e-06, + "loss": 1.8166, + "step": 76640 + }, + { + "epoch": 2.85, + "learning_rate": 7.149179901067431e-06, + "loss": 1.9174, + "step": 76650 + }, + { + "epoch": 2.85, + "learning_rate": 7.148807974113885e-06, + "loss": 1.7593, + "step": 76660 + }, + { + "epoch": 2.85, + "learning_rate": 7.148436047160338e-06, + "loss": 1.7359, + "step": 76670 + }, + { + "epoch": 2.85, + "learning_rate": 7.148064120206793e-06, + "loss": 1.678, + "step": 76680 + }, + { + "epoch": 2.85, + "learning_rate": 7.147692193253246e-06, + "loss": 1.7069, + "step": 76690 + }, + { + "epoch": 2.85, + "learning_rate": 7.147320266299699e-06, + "loss": 1.5987, + "step": 76700 + }, + { + "epoch": 2.85, + "eval_loss": 1.670407772064209, + "eval_runtime": 16.8412, + "eval_samples_per_second": 59.378, + "eval_steps_per_second": 3.741, + "step": 76700 + }, + { + "epoch": 2.85, + "learning_rate": 7.146948339346152e-06, + "loss": 1.7741, + "step": 76710 + }, + { + "epoch": 2.85, + "learning_rate": 7.1465764123926064e-06, + "loss": 1.6906, + "step": 76720 + }, + { + "epoch": 2.85, + "learning_rate": 7.14620448543906e-06, + "loss": 1.588, + "step": 76730 + }, + { + "epoch": 2.85, + "learning_rate": 7.145832558485513e-06, + "loss": 1.6639, + "step": 76740 + }, + { + "epoch": 2.85, + "learning_rate": 7.145460631531968e-06, + "loss": 1.7898, + "step": 76750 + }, + { + "epoch": 2.85, + "learning_rate": 7.145088704578421e-06, + "loss": 1.844, + "step": 76760 + }, + { + "epoch": 2.86, + "learning_rate": 7.1447167776248746e-06, + "loss": 1.7998, + "step": 76770 + }, + { + "epoch": 2.86, + "learning_rate": 7.144344850671329e-06, + "loss": 1.6755, + "step": 76780 + }, + { + "epoch": 2.86, + "learning_rate": 7.143972923717782e-06, + "loss": 1.6206, + "step": 76790 + }, + { + "epoch": 2.86, + "learning_rate": 7.143600996764236e-06, + "loss": 1.6911, + "step": 76800 + }, + { + "epoch": 2.86, + "eval_loss": 1.6702669858932495, + "eval_runtime": 16.8351, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 76800 + }, + { + "epoch": 2.86, + "learning_rate": 7.14322906981069e-06, + "loss": 1.7325, + "step": 76810 + }, + { + "epoch": 2.86, + "learning_rate": 7.1428571428571436e-06, + "loss": 1.6663, + "step": 76820 + }, + { + "epoch": 2.86, + "learning_rate": 7.142485215903597e-06, + "loss": 1.8472, + "step": 76830 + }, + { + "epoch": 2.86, + "learning_rate": 7.142113288950051e-06, + "loss": 1.7485, + "step": 76840 + }, + { + "epoch": 2.86, + "learning_rate": 7.141741361996505e-06, + "loss": 1.668, + "step": 76850 + }, + { + "epoch": 2.86, + "learning_rate": 7.141369435042958e-06, + "loss": 1.6647, + "step": 76860 + }, + { + "epoch": 2.86, + "learning_rate": 7.1409975080894126e-06, + "loss": 1.6966, + "step": 76870 + }, + { + "epoch": 2.86, + "learning_rate": 7.140625581135866e-06, + "loss": 1.7933, + "step": 76880 + }, + { + "epoch": 2.86, + "learning_rate": 7.140253654182319e-06, + "loss": 1.6674, + "step": 76890 + }, + { + "epoch": 2.86, + "learning_rate": 7.139881727228772e-06, + "loss": 1.7551, + "step": 76900 + }, + { + "epoch": 2.86, + "eval_loss": 1.6705162525177002, + "eval_runtime": 16.8276, + "eval_samples_per_second": 59.426, + "eval_steps_per_second": 3.744, + "step": 76900 + }, + { + "epoch": 2.86, + "learning_rate": 7.139509800275226e-06, + "loss": 1.6443, + "step": 76910 + }, + { + "epoch": 2.86, + "learning_rate": 7.13913787332168e-06, + "loss": 1.838, + "step": 76920 + }, + { + "epoch": 2.86, + "learning_rate": 7.138765946368133e-06, + "loss": 1.626, + "step": 76930 + }, + { + "epoch": 2.86, + "learning_rate": 7.138394019414588e-06, + "loss": 1.6964, + "step": 76940 + }, + { + "epoch": 2.86, + "learning_rate": 7.138022092461041e-06, + "loss": 1.7114, + "step": 76950 + }, + { + "epoch": 2.86, + "learning_rate": 7.1376501655074945e-06, + "loss": 1.6139, + "step": 76960 + }, + { + "epoch": 2.86, + "learning_rate": 7.137278238553949e-06, + "loss": 1.7076, + "step": 76970 + }, + { + "epoch": 2.86, + "learning_rate": 7.136906311600402e-06, + "loss": 1.7696, + "step": 76980 + }, + { + "epoch": 2.86, + "learning_rate": 7.136534384646856e-06, + "loss": 1.7188, + "step": 76990 + }, + { + "epoch": 2.86, + "learning_rate": 7.13616245769331e-06, + "loss": 1.5839, + "step": 77000 + }, + { + "epoch": 2.86, + "eval_loss": 1.67109215259552, + "eval_runtime": 16.8342, + "eval_samples_per_second": 59.403, + "eval_steps_per_second": 3.742, + "step": 77000 + }, + { + "epoch": 2.86, + "learning_rate": 7.1357905307397635e-06, + "loss": 1.7099, + "step": 77010 + }, + { + "epoch": 2.86, + "learning_rate": 7.135418603786217e-06, + "loss": 1.6085, + "step": 77020 + }, + { + "epoch": 2.86, + "learning_rate": 7.135046676832671e-06, + "loss": 1.7292, + "step": 77030 + }, + { + "epoch": 2.87, + "learning_rate": 7.134674749879125e-06, + "loss": 1.6637, + "step": 77040 + }, + { + "epoch": 2.87, + "learning_rate": 7.134302822925578e-06, + "loss": 1.765, + "step": 77050 + }, + { + "epoch": 2.87, + "learning_rate": 7.1339308959720325e-06, + "loss": 1.6681, + "step": 77060 + }, + { + "epoch": 2.87, + "learning_rate": 7.133558969018486e-06, + "loss": 1.6288, + "step": 77070 + }, + { + "epoch": 2.87, + "learning_rate": 7.133187042064939e-06, + "loss": 1.7263, + "step": 77080 + }, + { + "epoch": 2.87, + "learning_rate": 7.132815115111392e-06, + "loss": 1.7046, + "step": 77090 + }, + { + "epoch": 2.87, + "learning_rate": 7.132443188157846e-06, + "loss": 1.6809, + "step": 77100 + }, + { + "epoch": 2.87, + "eval_loss": 1.670782446861267, + "eval_runtime": 16.8328, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 77100 + }, + { + "epoch": 2.87, + "learning_rate": 7.1320712612043e-06, + "loss": 1.7682, + "step": 77110 + }, + { + "epoch": 2.87, + "learning_rate": 7.131699334250753e-06, + "loss": 1.5732, + "step": 77120 + }, + { + "epoch": 2.87, + "learning_rate": 7.1313274072972076e-06, + "loss": 1.6506, + "step": 77130 + }, + { + "epoch": 2.87, + "learning_rate": 7.130955480343661e-06, + "loss": 1.7781, + "step": 77140 + }, + { + "epoch": 2.87, + "learning_rate": 7.1305835533901145e-06, + "loss": 1.8322, + "step": 77150 + }, + { + "epoch": 2.87, + "learning_rate": 7.130211626436569e-06, + "loss": 1.7102, + "step": 77160 + }, + { + "epoch": 2.87, + "learning_rate": 7.129839699483022e-06, + "loss": 1.6474, + "step": 77170 + }, + { + "epoch": 2.87, + "learning_rate": 7.129467772529476e-06, + "loss": 1.5588, + "step": 77180 + }, + { + "epoch": 2.87, + "learning_rate": 7.129095845575929e-06, + "loss": 1.8452, + "step": 77190 + }, + { + "epoch": 2.87, + "learning_rate": 7.1287239186223835e-06, + "loss": 1.6883, + "step": 77200 + }, + { + "epoch": 2.87, + "eval_loss": 1.6698864698410034, + "eval_runtime": 16.8417, + "eval_samples_per_second": 59.377, + "eval_steps_per_second": 3.741, + "step": 77200 + }, + { + "epoch": 2.87, + "learning_rate": 7.128351991668837e-06, + "loss": 1.7081, + "step": 77210 + }, + { + "epoch": 2.87, + "learning_rate": 7.12798006471529e-06, + "loss": 1.8295, + "step": 77220 + }, + { + "epoch": 2.87, + "learning_rate": 7.127608137761745e-06, + "loss": 1.6728, + "step": 77230 + }, + { + "epoch": 2.87, + "learning_rate": 7.127236210808198e-06, + "loss": 1.6575, + "step": 77240 + }, + { + "epoch": 2.87, + "learning_rate": 7.126864283854652e-06, + "loss": 1.6565, + "step": 77250 + }, + { + "epoch": 2.87, + "learning_rate": 7.126492356901106e-06, + "loss": 1.714, + "step": 77260 + }, + { + "epoch": 2.87, + "learning_rate": 7.1261204299475585e-06, + "loss": 1.8164, + "step": 77270 + }, + { + "epoch": 2.87, + "learning_rate": 7.125748502994012e-06, + "loss": 1.7331, + "step": 77280 + }, + { + "epoch": 2.87, + "learning_rate": 7.1253765760404655e-06, + "loss": 1.8993, + "step": 77290 + }, + { + "epoch": 2.87, + "learning_rate": 7.12500464908692e-06, + "loss": 1.8866, + "step": 77300 + }, + { + "epoch": 2.87, + "eval_loss": 1.6704777479171753, + "eval_runtime": 16.8318, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 77300 + }, + { + "epoch": 2.88, + "learning_rate": 7.124632722133373e-06, + "loss": 1.737, + "step": 77310 + }, + { + "epoch": 2.88, + "learning_rate": 7.124260795179827e-06, + "loss": 1.7633, + "step": 77320 + }, + { + "epoch": 2.88, + "learning_rate": 7.123888868226281e-06, + "loss": 1.7108, + "step": 77330 + }, + { + "epoch": 2.88, + "learning_rate": 7.1235169412727345e-06, + "loss": 1.6426, + "step": 77340 + }, + { + "epoch": 2.88, + "learning_rate": 7.123145014319188e-06, + "loss": 1.6748, + "step": 77350 + }, + { + "epoch": 2.88, + "learning_rate": 7.122773087365642e-06, + "loss": 1.7194, + "step": 77360 + }, + { + "epoch": 2.88, + "learning_rate": 7.122401160412096e-06, + "loss": 1.7306, + "step": 77370 + }, + { + "epoch": 2.88, + "learning_rate": 7.122029233458549e-06, + "loss": 1.9316, + "step": 77380 + }, + { + "epoch": 2.88, + "learning_rate": 7.1216573065050034e-06, + "loss": 1.6591, + "step": 77390 + }, + { + "epoch": 2.88, + "learning_rate": 7.121285379551457e-06, + "loss": 1.8444, + "step": 77400 + }, + { + "epoch": 2.88, + "eval_loss": 1.670935034751892, + "eval_runtime": 16.84, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 77400 + }, + { + "epoch": 2.88, + "learning_rate": 7.12091345259791e-06, + "loss": 1.6795, + "step": 77410 + }, + { + "epoch": 2.88, + "learning_rate": 7.120541525644365e-06, + "loss": 1.897, + "step": 77420 + }, + { + "epoch": 2.88, + "learning_rate": 7.120169598690818e-06, + "loss": 1.7669, + "step": 77430 + }, + { + "epoch": 2.88, + "learning_rate": 7.119797671737272e-06, + "loss": 1.8056, + "step": 77440 + }, + { + "epoch": 2.88, + "learning_rate": 7.119425744783726e-06, + "loss": 1.8049, + "step": 77450 + }, + { + "epoch": 2.88, + "learning_rate": 7.1190538178301785e-06, + "loss": 1.7456, + "step": 77460 + }, + { + "epoch": 2.88, + "learning_rate": 7.118681890876632e-06, + "loss": 1.6101, + "step": 77470 + }, + { + "epoch": 2.88, + "learning_rate": 7.118309963923085e-06, + "loss": 1.8269, + "step": 77480 + }, + { + "epoch": 2.88, + "learning_rate": 7.11793803696954e-06, + "loss": 1.7032, + "step": 77490 + }, + { + "epoch": 2.88, + "learning_rate": 7.117566110015993e-06, + "loss": 1.8839, + "step": 77500 + }, + { + "epoch": 2.88, + "eval_loss": 1.6705342531204224, + "eval_runtime": 16.827, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 77500 + }, + { + "epoch": 2.88, + "learning_rate": 7.117194183062447e-06, + "loss": 1.7424, + "step": 77510 + }, + { + "epoch": 2.88, + "learning_rate": 7.116822256108901e-06, + "loss": 1.719, + "step": 77520 + }, + { + "epoch": 2.88, + "learning_rate": 7.116450329155354e-06, + "loss": 1.7066, + "step": 77530 + }, + { + "epoch": 2.88, + "learning_rate": 7.116078402201808e-06, + "loss": 1.7825, + "step": 77540 + }, + { + "epoch": 2.88, + "learning_rate": 7.115706475248262e-06, + "loss": 1.8518, + "step": 77550 + }, + { + "epoch": 2.88, + "learning_rate": 7.115334548294716e-06, + "loss": 1.8939, + "step": 77560 + }, + { + "epoch": 2.89, + "learning_rate": 7.114962621341169e-06, + "loss": 1.665, + "step": 77570 + }, + { + "epoch": 2.89, + "learning_rate": 7.114590694387623e-06, + "loss": 1.7455, + "step": 77580 + }, + { + "epoch": 2.89, + "learning_rate": 7.114218767434077e-06, + "loss": 1.8329, + "step": 77590 + }, + { + "epoch": 2.89, + "learning_rate": 7.11384684048053e-06, + "loss": 1.9834, + "step": 77600 + }, + { + "epoch": 2.89, + "eval_loss": 1.670000433921814, + "eval_runtime": 16.8359, + "eval_samples_per_second": 59.397, + "eval_steps_per_second": 3.742, + "step": 77600 + }, + { + "epoch": 2.89, + "learning_rate": 7.113474913526985e-06, + "loss": 1.7436, + "step": 77610 + }, + { + "epoch": 2.89, + "learning_rate": 7.113102986573438e-06, + "loss": 1.7429, + "step": 77620 + }, + { + "epoch": 2.89, + "learning_rate": 7.1127310596198915e-06, + "loss": 1.7862, + "step": 77630 + }, + { + "epoch": 2.89, + "learning_rate": 7.112359132666344e-06, + "loss": 1.6444, + "step": 77640 + }, + { + "epoch": 2.89, + "learning_rate": 7.1119872057127985e-06, + "loss": 1.6387, + "step": 77650 + }, + { + "epoch": 2.89, + "learning_rate": 7.111615278759252e-06, + "loss": 1.7181, + "step": 77660 + }, + { + "epoch": 2.89, + "learning_rate": 7.111243351805705e-06, + "loss": 1.763, + "step": 77670 + }, + { + "epoch": 2.89, + "learning_rate": 7.11087142485216e-06, + "loss": 1.7133, + "step": 77680 + }, + { + "epoch": 2.89, + "learning_rate": 7.110499497898613e-06, + "loss": 1.756, + "step": 77690 + }, + { + "epoch": 2.89, + "learning_rate": 7.110127570945067e-06, + "loss": 1.6925, + "step": 77700 + }, + { + "epoch": 2.89, + "eval_loss": 1.6702399253845215, + "eval_runtime": 16.8248, + "eval_samples_per_second": 59.436, + "eval_steps_per_second": 3.744, + "step": 77700 + }, + { + "epoch": 2.89, + "learning_rate": 7.109755643991521e-06, + "loss": 1.7466, + "step": 77710 + }, + { + "epoch": 2.89, + "learning_rate": 7.109383717037974e-06, + "loss": 1.8251, + "step": 77720 + }, + { + "epoch": 2.89, + "learning_rate": 7.109011790084428e-06, + "loss": 1.6415, + "step": 77730 + }, + { + "epoch": 2.89, + "learning_rate": 7.108639863130882e-06, + "loss": 1.7353, + "step": 77740 + }, + { + "epoch": 2.89, + "learning_rate": 7.108267936177336e-06, + "loss": 1.644, + "step": 77750 + }, + { + "epoch": 2.89, + "learning_rate": 7.107896009223789e-06, + "loss": 1.8936, + "step": 77760 + }, + { + "epoch": 2.89, + "learning_rate": 7.1075240822702425e-06, + "loss": 1.7811, + "step": 77770 + }, + { + "epoch": 2.89, + "learning_rate": 7.107152155316697e-06, + "loss": 1.7576, + "step": 77780 + }, + { + "epoch": 2.89, + "learning_rate": 7.10678022836315e-06, + "loss": 1.7545, + "step": 77790 + }, + { + "epoch": 2.89, + "learning_rate": 7.106408301409604e-06, + "loss": 1.7595, + "step": 77800 + }, + { + "epoch": 2.89, + "eval_loss": 1.669376015663147, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 77800 + }, + { + "epoch": 2.89, + "learning_rate": 7.106036374456058e-06, + "loss": 1.6902, + "step": 77810 + }, + { + "epoch": 2.89, + "learning_rate": 7.1056644475025115e-06, + "loss": 1.5912, + "step": 77820 + }, + { + "epoch": 2.89, + "learning_rate": 7.105292520548964e-06, + "loss": 1.7521, + "step": 77830 + }, + { + "epoch": 2.9, + "learning_rate": 7.1049205935954176e-06, + "loss": 1.7205, + "step": 77840 + }, + { + "epoch": 2.9, + "learning_rate": 7.104548666641872e-06, + "loss": 1.6757, + "step": 77850 + }, + { + "epoch": 2.9, + "learning_rate": 7.104176739688325e-06, + "loss": 1.7624, + "step": 77860 + }, + { + "epoch": 2.9, + "learning_rate": 7.103804812734779e-06, + "loss": 1.5997, + "step": 77870 + }, + { + "epoch": 2.9, + "learning_rate": 7.103432885781233e-06, + "loss": 1.6404, + "step": 77880 + }, + { + "epoch": 2.9, + "learning_rate": 7.1030609588276866e-06, + "loss": 1.7302, + "step": 77890 + }, + { + "epoch": 2.9, + "learning_rate": 7.10268903187414e-06, + "loss": 1.8085, + "step": 77900 + }, + { + "epoch": 2.9, + "eval_loss": 1.669871211051941, + "eval_runtime": 16.8343, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 77900 + }, + { + "epoch": 2.9, + "learning_rate": 7.102317104920594e-06, + "loss": 1.7496, + "step": 77910 + }, + { + "epoch": 2.9, + "learning_rate": 7.101945177967048e-06, + "loss": 1.7229, + "step": 77920 + }, + { + "epoch": 2.9, + "learning_rate": 7.101573251013501e-06, + "loss": 1.6614, + "step": 77930 + }, + { + "epoch": 2.9, + "learning_rate": 7.1012013240599556e-06, + "loss": 1.6114, + "step": 77940 + }, + { + "epoch": 2.9, + "learning_rate": 7.100829397106409e-06, + "loss": 1.7127, + "step": 77950 + }, + { + "epoch": 2.9, + "learning_rate": 7.1004574701528625e-06, + "loss": 1.7237, + "step": 77960 + }, + { + "epoch": 2.9, + "learning_rate": 7.100085543199317e-06, + "loss": 1.7693, + "step": 77970 + }, + { + "epoch": 2.9, + "learning_rate": 7.09971361624577e-06, + "loss": 1.778, + "step": 77980 + }, + { + "epoch": 2.9, + "learning_rate": 7.099341689292224e-06, + "loss": 1.8006, + "step": 77990 + }, + { + "epoch": 2.9, + "learning_rate": 7.098969762338678e-06, + "loss": 1.8157, + "step": 78000 + }, + { + "epoch": 2.9, + "eval_loss": 1.670279860496521, + "eval_runtime": 16.8504, + "eval_samples_per_second": 59.346, + "eval_steps_per_second": 3.739, + "step": 78000 + }, + { + "epoch": 2.9, + "learning_rate": 7.0985978353851315e-06, + "loss": 1.772, + "step": 78010 + }, + { + "epoch": 2.9, + "learning_rate": 7.098225908431584e-06, + "loss": 1.759, + "step": 78020 + }, + { + "epoch": 2.9, + "learning_rate": 7.0978539814780375e-06, + "loss": 1.8149, + "step": 78030 + }, + { + "epoch": 2.9, + "learning_rate": 7.097482054524492e-06, + "loss": 1.6893, + "step": 78040 + }, + { + "epoch": 2.9, + "learning_rate": 7.097110127570945e-06, + "loss": 1.676, + "step": 78050 + }, + { + "epoch": 2.9, + "learning_rate": 7.096738200617399e-06, + "loss": 1.6692, + "step": 78060 + }, + { + "epoch": 2.9, + "learning_rate": 7.096366273663853e-06, + "loss": 1.6944, + "step": 78070 + }, + { + "epoch": 2.9, + "learning_rate": 7.0959943467103065e-06, + "loss": 1.7715, + "step": 78080 + }, + { + "epoch": 2.9, + "learning_rate": 7.09562241975676e-06, + "loss": 1.6084, + "step": 78090 + }, + { + "epoch": 2.9, + "learning_rate": 7.095250492803214e-06, + "loss": 1.7023, + "step": 78100 + }, + { + "epoch": 2.9, + "eval_loss": 1.6696645021438599, + "eval_runtime": 16.8507, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 78100 + }, + { + "epoch": 2.91, + "learning_rate": 7.094878565849668e-06, + "loss": 1.7067, + "step": 78110 + }, + { + "epoch": 2.91, + "learning_rate": 7.094506638896121e-06, + "loss": 1.6292, + "step": 78120 + }, + { + "epoch": 2.91, + "learning_rate": 7.0941347119425755e-06, + "loss": 1.7511, + "step": 78130 + }, + { + "epoch": 2.91, + "learning_rate": 7.093762784989029e-06, + "loss": 1.6813, + "step": 78140 + }, + { + "epoch": 2.91, + "learning_rate": 7.0933908580354824e-06, + "loss": 1.666, + "step": 78150 + }, + { + "epoch": 2.91, + "learning_rate": 7.093018931081937e-06, + "loss": 1.7901, + "step": 78160 + }, + { + "epoch": 2.91, + "learning_rate": 7.09264700412839e-06, + "loss": 1.7283, + "step": 78170 + }, + { + "epoch": 2.91, + "learning_rate": 7.092275077174844e-06, + "loss": 1.892, + "step": 78180 + }, + { + "epoch": 2.91, + "learning_rate": 7.091903150221298e-06, + "loss": 1.6777, + "step": 78190 + }, + { + "epoch": 2.91, + "learning_rate": 7.091531223267751e-06, + "loss": 1.6604, + "step": 78200 + }, + { + "epoch": 2.91, + "eval_loss": 1.6689283847808838, + "eval_runtime": 16.8152, + "eval_samples_per_second": 59.47, + "eval_steps_per_second": 3.747, + "step": 78200 + }, + { + "epoch": 2.91, + "learning_rate": 7.091159296314204e-06, + "loss": 1.6201, + "step": 78210 + }, + { + "epoch": 2.91, + "learning_rate": 7.0907873693606575e-06, + "loss": 1.6476, + "step": 78220 + }, + { + "epoch": 2.91, + "learning_rate": 7.090415442407112e-06, + "loss": 1.7399, + "step": 78230 + }, + { + "epoch": 2.91, + "learning_rate": 7.090043515453565e-06, + "loss": 1.7838, + "step": 78240 + }, + { + "epoch": 2.91, + "learning_rate": 7.089671588500019e-06, + "loss": 1.5662, + "step": 78250 + }, + { + "epoch": 2.91, + "learning_rate": 7.089299661546473e-06, + "loss": 1.6994, + "step": 78260 + }, + { + "epoch": 2.91, + "learning_rate": 7.0889277345929265e-06, + "loss": 1.7636, + "step": 78270 + }, + { + "epoch": 2.91, + "learning_rate": 7.08855580763938e-06, + "loss": 1.8242, + "step": 78280 + }, + { + "epoch": 2.91, + "learning_rate": 7.088183880685834e-06, + "loss": 1.7147, + "step": 78290 + }, + { + "epoch": 2.91, + "learning_rate": 7.087811953732288e-06, + "loss": 1.6691, + "step": 78300 + }, + { + "epoch": 2.91, + "eval_loss": 1.6688441038131714, + "eval_runtime": 16.8255, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 78300 + }, + { + "epoch": 2.91, + "learning_rate": 7.087440026778741e-06, + "loss": 1.7201, + "step": 78310 + }, + { + "epoch": 2.91, + "learning_rate": 7.0870680998251955e-06, + "loss": 1.7162, + "step": 78320 + }, + { + "epoch": 2.91, + "learning_rate": 7.086696172871649e-06, + "loss": 1.7652, + "step": 78330 + }, + { + "epoch": 2.91, + "learning_rate": 7.086324245918102e-06, + "loss": 1.7544, + "step": 78340 + }, + { + "epoch": 2.91, + "learning_rate": 7.085952318964556e-06, + "loss": 1.7535, + "step": 78350 + }, + { + "epoch": 2.91, + "learning_rate": 7.08558039201101e-06, + "loss": 1.6601, + "step": 78360 + }, + { + "epoch": 2.91, + "learning_rate": 7.085208465057464e-06, + "loss": 1.5772, + "step": 78370 + }, + { + "epoch": 2.92, + "learning_rate": 7.084836538103917e-06, + "loss": 1.7143, + "step": 78380 + }, + { + "epoch": 2.92, + "learning_rate": 7.08446461115037e-06, + "loss": 1.6448, + "step": 78390 + }, + { + "epoch": 2.92, + "learning_rate": 7.084092684196824e-06, + "loss": 1.789, + "step": 78400 + }, + { + "epoch": 2.92, + "eval_loss": 1.6685364246368408, + "eval_runtime": 16.8338, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 78400 + }, + { + "epoch": 2.92, + "learning_rate": 7.0837207572432774e-06, + "loss": 1.8364, + "step": 78410 + }, + { + "epoch": 2.92, + "learning_rate": 7.083348830289731e-06, + "loss": 1.6962, + "step": 78420 + }, + { + "epoch": 2.92, + "learning_rate": 7.082976903336185e-06, + "loss": 1.6319, + "step": 78430 + }, + { + "epoch": 2.92, + "learning_rate": 7.082604976382639e-06, + "loss": 1.7305, + "step": 78440 + }, + { + "epoch": 2.92, + "learning_rate": 7.082233049429092e-06, + "loss": 1.6837, + "step": 78450 + }, + { + "epoch": 2.92, + "learning_rate": 7.0818611224755464e-06, + "loss": 1.7646, + "step": 78460 + }, + { + "epoch": 2.92, + "learning_rate": 7.081489195522e-06, + "loss": 1.7623, + "step": 78470 + }, + { + "epoch": 2.92, + "learning_rate": 7.081117268568453e-06, + "loss": 1.6136, + "step": 78480 + }, + { + "epoch": 2.92, + "learning_rate": 7.080745341614908e-06, + "loss": 1.8397, + "step": 78490 + }, + { + "epoch": 2.92, + "learning_rate": 7.080373414661361e-06, + "loss": 1.7317, + "step": 78500 + }, + { + "epoch": 2.92, + "eval_loss": 1.6698369979858398, + "eval_runtime": 16.8531, + "eval_samples_per_second": 59.336, + "eval_steps_per_second": 3.738, + "step": 78500 + }, + { + "epoch": 2.92, + "learning_rate": 7.080001487707815e-06, + "loss": 1.6407, + "step": 78510 + }, + { + "epoch": 2.92, + "learning_rate": 7.079629560754269e-06, + "loss": 1.8429, + "step": 78520 + }, + { + "epoch": 2.92, + "learning_rate": 7.079257633800722e-06, + "loss": 1.7783, + "step": 78530 + }, + { + "epoch": 2.92, + "learning_rate": 7.078885706847176e-06, + "loss": 1.6362, + "step": 78540 + }, + { + "epoch": 2.92, + "learning_rate": 7.07851377989363e-06, + "loss": 1.7895, + "step": 78550 + }, + { + "epoch": 2.92, + "learning_rate": 7.0781418529400836e-06, + "loss": 1.7555, + "step": 78560 + }, + { + "epoch": 2.92, + "learning_rate": 7.077769925986537e-06, + "loss": 1.7055, + "step": 78570 + }, + { + "epoch": 2.92, + "learning_rate": 7.07739799903299e-06, + "loss": 1.6615, + "step": 78580 + }, + { + "epoch": 2.92, + "learning_rate": 7.077026072079444e-06, + "loss": 1.8584, + "step": 78590 + }, + { + "epoch": 2.92, + "learning_rate": 7.076654145125897e-06, + "loss": 1.7144, + "step": 78600 + }, + { + "epoch": 2.92, + "eval_loss": 1.6690584421157837, + "eval_runtime": 16.841, + "eval_samples_per_second": 59.379, + "eval_steps_per_second": 3.741, + "step": 78600 + }, + { + "epoch": 2.92, + "learning_rate": 7.076282218172351e-06, + "loss": 1.7451, + "step": 78610 + }, + { + "epoch": 2.92, + "learning_rate": 7.075910291218805e-06, + "loss": 1.6967, + "step": 78620 + }, + { + "epoch": 2.92, + "learning_rate": 7.075538364265259e-06, + "loss": 1.7363, + "step": 78630 + }, + { + "epoch": 2.92, + "learning_rate": 7.075166437311712e-06, + "loss": 1.7132, + "step": 78640 + }, + { + "epoch": 2.93, + "learning_rate": 7.074794510358166e-06, + "loss": 1.7582, + "step": 78650 + }, + { + "epoch": 2.93, + "learning_rate": 7.07442258340462e-06, + "loss": 1.7065, + "step": 78660 + }, + { + "epoch": 2.93, + "learning_rate": 7.074050656451073e-06, + "loss": 1.7668, + "step": 78670 + }, + { + "epoch": 2.93, + "learning_rate": 7.073678729497528e-06, + "loss": 1.7577, + "step": 78680 + }, + { + "epoch": 2.93, + "learning_rate": 7.073306802543981e-06, + "loss": 1.7711, + "step": 78690 + }, + { + "epoch": 2.93, + "learning_rate": 7.0729348755904345e-06, + "loss": 1.6982, + "step": 78700 + }, + { + "epoch": 2.93, + "eval_loss": 1.6692728996276855, + "eval_runtime": 16.8549, + "eval_samples_per_second": 59.33, + "eval_steps_per_second": 3.738, + "step": 78700 + }, + { + "epoch": 2.93, + "learning_rate": 7.072562948636889e-06, + "loss": 1.7701, + "step": 78710 + }, + { + "epoch": 2.93, + "learning_rate": 7.072191021683342e-06, + "loss": 1.6953, + "step": 78720 + }, + { + "epoch": 2.93, + "learning_rate": 7.071819094729796e-06, + "loss": 1.7502, + "step": 78730 + }, + { + "epoch": 2.93, + "learning_rate": 7.07144716777625e-06, + "loss": 1.6188, + "step": 78740 + }, + { + "epoch": 2.93, + "learning_rate": 7.0710752408227035e-06, + "loss": 1.7651, + "step": 78750 + }, + { + "epoch": 2.93, + "learning_rate": 7.070703313869157e-06, + "loss": 1.8133, + "step": 78760 + }, + { + "epoch": 2.93, + "learning_rate": 7.07033138691561e-06, + "loss": 1.5857, + "step": 78770 + }, + { + "epoch": 2.93, + "learning_rate": 7.069959459962064e-06, + "loss": 1.7848, + "step": 78780 + }, + { + "epoch": 2.93, + "learning_rate": 7.069587533008517e-06, + "loss": 1.6733, + "step": 78790 + }, + { + "epoch": 2.93, + "learning_rate": 7.069215606054971e-06, + "loss": 1.6588, + "step": 78800 + }, + { + "epoch": 2.93, + "eval_loss": 1.6682374477386475, + "eval_runtime": 16.8529, + "eval_samples_per_second": 59.337, + "eval_steps_per_second": 3.738, + "step": 78800 + }, + { + "epoch": 2.93, + "learning_rate": 7.068843679101425e-06, + "loss": 1.7614, + "step": 78810 + }, + { + "epoch": 2.93, + "learning_rate": 7.068471752147879e-06, + "loss": 1.6798, + "step": 78820 + }, + { + "epoch": 2.93, + "learning_rate": 7.068099825194332e-06, + "loss": 1.7294, + "step": 78830 + }, + { + "epoch": 2.93, + "learning_rate": 7.067727898240786e-06, + "loss": 1.7376, + "step": 78840 + }, + { + "epoch": 2.93, + "learning_rate": 7.06735597128724e-06, + "loss": 1.7666, + "step": 78850 + }, + { + "epoch": 2.93, + "learning_rate": 7.066984044333693e-06, + "loss": 1.7272, + "step": 78860 + }, + { + "epoch": 2.93, + "learning_rate": 7.066612117380148e-06, + "loss": 1.6453, + "step": 78870 + }, + { + "epoch": 2.93, + "learning_rate": 7.066240190426601e-06, + "loss": 1.63, + "step": 78880 + }, + { + "epoch": 2.93, + "learning_rate": 7.0658682634730545e-06, + "loss": 1.6414, + "step": 78890 + }, + { + "epoch": 2.93, + "learning_rate": 7.065496336519509e-06, + "loss": 1.8466, + "step": 78900 + }, + { + "epoch": 2.93, + "eval_loss": 1.6681941747665405, + "eval_runtime": 16.8159, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.746, + "step": 78900 + }, + { + "epoch": 2.93, + "learning_rate": 7.065124409565962e-06, + "loss": 1.7114, + "step": 78910 + }, + { + "epoch": 2.94, + "learning_rate": 7.064752482612416e-06, + "loss": 1.7113, + "step": 78920 + }, + { + "epoch": 2.94, + "learning_rate": 7.064380555658869e-06, + "loss": 1.6132, + "step": 78930 + }, + { + "epoch": 2.94, + "learning_rate": 7.0640086287053235e-06, + "loss": 1.9045, + "step": 78940 + }, + { + "epoch": 2.94, + "learning_rate": 7.063636701751777e-06, + "loss": 1.6511, + "step": 78950 + }, + { + "epoch": 2.94, + "learning_rate": 7.0632647747982296e-06, + "loss": 1.6966, + "step": 78960 + }, + { + "epoch": 2.94, + "learning_rate": 7.062892847844683e-06, + "loss": 1.6908, + "step": 78970 + }, + { + "epoch": 2.94, + "learning_rate": 7.062520920891137e-06, + "loss": 1.8612, + "step": 78980 + }, + { + "epoch": 2.94, + "learning_rate": 7.062148993937591e-06, + "loss": 1.697, + "step": 78990 + }, + { + "epoch": 2.94, + "learning_rate": 7.061777066984044e-06, + "loss": 1.8963, + "step": 79000 + }, + { + "epoch": 2.94, + "eval_loss": 1.6680270433425903, + "eval_runtime": 16.8486, + "eval_samples_per_second": 59.352, + "eval_steps_per_second": 3.739, + "step": 79000 + }, + { + "epoch": 2.94, + "learning_rate": 7.0614051400304986e-06, + "loss": 1.6959, + "step": 79010 + }, + { + "epoch": 2.94, + "learning_rate": 7.061033213076952e-06, + "loss": 1.6498, + "step": 79020 + }, + { + "epoch": 2.94, + "learning_rate": 7.0606612861234055e-06, + "loss": 1.7281, + "step": 79030 + }, + { + "epoch": 2.94, + "learning_rate": 7.06028935916986e-06, + "loss": 1.6595, + "step": 79040 + }, + { + "epoch": 2.94, + "learning_rate": 7.059917432216313e-06, + "loss": 1.7039, + "step": 79050 + }, + { + "epoch": 2.94, + "learning_rate": 7.059545505262767e-06, + "loss": 1.7423, + "step": 79060 + }, + { + "epoch": 2.94, + "learning_rate": 7.059173578309221e-06, + "loss": 1.5727, + "step": 79070 + }, + { + "epoch": 2.94, + "learning_rate": 7.0588016513556745e-06, + "loss": 1.8088, + "step": 79080 + }, + { + "epoch": 2.94, + "learning_rate": 7.058429724402128e-06, + "loss": 1.7091, + "step": 79090 + }, + { + "epoch": 2.94, + "learning_rate": 7.058057797448582e-06, + "loss": 1.5879, + "step": 79100 + }, + { + "epoch": 2.94, + "eval_loss": 1.6678988933563232, + "eval_runtime": 16.8463, + "eval_samples_per_second": 59.36, + "eval_steps_per_second": 3.74, + "step": 79100 + }, + { + "epoch": 2.94, + "learning_rate": 7.057685870495036e-06, + "loss": 1.6792, + "step": 79110 + }, + { + "epoch": 2.94, + "learning_rate": 7.057313943541489e-06, + "loss": 1.6688, + "step": 79120 + }, + { + "epoch": 2.94, + "learning_rate": 7.0569420165879434e-06, + "loss": 1.8572, + "step": 79130 + }, + { + "epoch": 2.94, + "learning_rate": 7.056570089634397e-06, + "loss": 1.7655, + "step": 79140 + }, + { + "epoch": 2.94, + "learning_rate": 7.0561981626808495e-06, + "loss": 1.8808, + "step": 79150 + }, + { + "epoch": 2.94, + "learning_rate": 7.055826235727303e-06, + "loss": 1.7475, + "step": 79160 + }, + { + "epoch": 2.94, + "learning_rate": 7.055454308773757e-06, + "loss": 1.7131, + "step": 79170 + }, + { + "epoch": 2.94, + "learning_rate": 7.055082381820211e-06, + "loss": 1.7952, + "step": 79180 + }, + { + "epoch": 2.95, + "learning_rate": 7.054710454866664e-06, + "loss": 1.5494, + "step": 79190 + }, + { + "epoch": 2.95, + "learning_rate": 7.0543385279131185e-06, + "loss": 1.7109, + "step": 79200 + }, + { + "epoch": 2.95, + "eval_loss": 1.6668022871017456, + "eval_runtime": 16.8424, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 79200 + }, + { + "epoch": 2.95, + "learning_rate": 7.053966600959572e-06, + "loss": 1.8429, + "step": 79210 + }, + { + "epoch": 2.95, + "learning_rate": 7.0535946740060254e-06, + "loss": 1.722, + "step": 79220 + }, + { + "epoch": 2.95, + "learning_rate": 7.05322274705248e-06, + "loss": 1.711, + "step": 79230 + }, + { + "epoch": 2.95, + "learning_rate": 7.052850820098933e-06, + "loss": 1.6842, + "step": 79240 + }, + { + "epoch": 2.95, + "learning_rate": 7.052478893145387e-06, + "loss": 1.6316, + "step": 79250 + }, + { + "epoch": 2.95, + "learning_rate": 7.052106966191841e-06, + "loss": 1.702, + "step": 79260 + }, + { + "epoch": 2.95, + "learning_rate": 7.051735039238294e-06, + "loss": 1.6328, + "step": 79270 + }, + { + "epoch": 2.95, + "learning_rate": 7.051363112284748e-06, + "loss": 1.629, + "step": 79280 + }, + { + "epoch": 2.95, + "learning_rate": 7.050991185331202e-06, + "loss": 1.7209, + "step": 79290 + }, + { + "epoch": 2.95, + "learning_rate": 7.050619258377656e-06, + "loss": 1.7474, + "step": 79300 + }, + { + "epoch": 2.95, + "eval_loss": 1.6678566932678223, + "eval_runtime": 16.8577, + "eval_samples_per_second": 59.32, + "eval_steps_per_second": 3.737, + "step": 79300 + }, + { + "epoch": 2.95, + "learning_rate": 7.050247331424109e-06, + "loss": 1.8367, + "step": 79310 + }, + { + "epoch": 2.95, + "learning_rate": 7.049875404470563e-06, + "loss": 1.7236, + "step": 79320 + }, + { + "epoch": 2.95, + "learning_rate": 7.049503477517016e-06, + "loss": 1.6804, + "step": 79330 + }, + { + "epoch": 2.95, + "learning_rate": 7.0491315505634695e-06, + "loss": 1.6779, + "step": 79340 + }, + { + "epoch": 2.95, + "learning_rate": 7.048759623609923e-06, + "loss": 1.7374, + "step": 79350 + }, + { + "epoch": 2.95, + "learning_rate": 7.048387696656377e-06, + "loss": 1.7187, + "step": 79360 + }, + { + "epoch": 2.95, + "learning_rate": 7.048015769702831e-06, + "loss": 1.6634, + "step": 79370 + }, + { + "epoch": 2.95, + "learning_rate": 7.047643842749284e-06, + "loss": 1.7922, + "step": 79380 + }, + { + "epoch": 2.95, + "learning_rate": 7.0472719157957385e-06, + "loss": 1.6675, + "step": 79390 + }, + { + "epoch": 2.95, + "learning_rate": 7.046899988842192e-06, + "loss": 1.6889, + "step": 79400 + }, + { + "epoch": 2.95, + "eval_loss": 1.6670145988464355, + "eval_runtime": 16.843, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 79400 + }, + { + "epoch": 2.95, + "learning_rate": 7.046528061888645e-06, + "loss": 1.7559, + "step": 79410 + }, + { + "epoch": 2.95, + "learning_rate": 7.0461561349351e-06, + "loss": 1.9211, + "step": 79420 + }, + { + "epoch": 2.95, + "learning_rate": 7.045784207981553e-06, + "loss": 1.6856, + "step": 79430 + }, + { + "epoch": 2.95, + "learning_rate": 7.045412281028007e-06, + "loss": 1.8115, + "step": 79440 + }, + { + "epoch": 2.95, + "learning_rate": 7.045040354074461e-06, + "loss": 1.725, + "step": 79450 + }, + { + "epoch": 2.96, + "learning_rate": 7.044668427120914e-06, + "loss": 1.765, + "step": 79460 + }, + { + "epoch": 2.96, + "learning_rate": 7.044296500167368e-06, + "loss": 1.7525, + "step": 79470 + }, + { + "epoch": 2.96, + "learning_rate": 7.043924573213822e-06, + "loss": 1.5864, + "step": 79480 + }, + { + "epoch": 2.96, + "learning_rate": 7.043552646260276e-06, + "loss": 1.9121, + "step": 79490 + }, + { + "epoch": 2.96, + "learning_rate": 7.043180719306729e-06, + "loss": 1.6958, + "step": 79500 + }, + { + "epoch": 2.96, + "eval_loss": 1.6670390367507935, + "eval_runtime": 16.8449, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 79500 + }, + { + "epoch": 2.96, + "learning_rate": 7.0428087923531825e-06, + "loss": 1.6803, + "step": 79510 + }, + { + "epoch": 2.96, + "learning_rate": 7.042436865399636e-06, + "loss": 1.6251, + "step": 79520 + }, + { + "epoch": 2.96, + "learning_rate": 7.0420649384460894e-06, + "loss": 1.6883, + "step": 79530 + }, + { + "epoch": 2.96, + "learning_rate": 7.041693011492543e-06, + "loss": 1.62, + "step": 79540 + }, + { + "epoch": 2.96, + "learning_rate": 7.041321084538996e-06, + "loss": 1.6594, + "step": 79550 + }, + { + "epoch": 2.96, + "learning_rate": 7.040949157585451e-06, + "loss": 1.4994, + "step": 79560 + }, + { + "epoch": 2.96, + "learning_rate": 7.040577230631904e-06, + "loss": 1.7126, + "step": 79570 + }, + { + "epoch": 2.96, + "learning_rate": 7.040205303678358e-06, + "loss": 1.8071, + "step": 79580 + }, + { + "epoch": 2.96, + "learning_rate": 7.039833376724812e-06, + "loss": 1.6848, + "step": 79590 + }, + { + "epoch": 2.96, + "learning_rate": 7.039461449771265e-06, + "loss": 1.6717, + "step": 79600 + }, + { + "epoch": 2.96, + "eval_loss": 1.6669631004333496, + "eval_runtime": 16.8458, + "eval_samples_per_second": 59.362, + "eval_steps_per_second": 3.74, + "step": 79600 + }, + { + "epoch": 2.96, + "learning_rate": 7.039089522817719e-06, + "loss": 1.7489, + "step": 79610 + }, + { + "epoch": 2.96, + "learning_rate": 7.038717595864173e-06, + "loss": 1.7116, + "step": 79620 + }, + { + "epoch": 2.96, + "learning_rate": 7.0383456689106266e-06, + "loss": 1.7829, + "step": 79630 + }, + { + "epoch": 2.96, + "learning_rate": 7.03797374195708e-06, + "loss": 1.6674, + "step": 79640 + }, + { + "epoch": 2.96, + "learning_rate": 7.037601815003534e-06, + "loss": 1.6314, + "step": 79650 + }, + { + "epoch": 2.96, + "learning_rate": 7.037229888049988e-06, + "loss": 1.8293, + "step": 79660 + }, + { + "epoch": 2.96, + "learning_rate": 7.036857961096441e-06, + "loss": 1.813, + "step": 79670 + }, + { + "epoch": 2.96, + "learning_rate": 7.0364860341428956e-06, + "loss": 1.6271, + "step": 79680 + }, + { + "epoch": 2.96, + "learning_rate": 7.036114107189349e-06, + "loss": 1.6778, + "step": 79690 + }, + { + "epoch": 2.96, + "learning_rate": 7.0357421802358025e-06, + "loss": 1.7476, + "step": 79700 + }, + { + "epoch": 2.96, + "eval_loss": 1.6663919687271118, + "eval_runtime": 16.8615, + "eval_samples_per_second": 59.307, + "eval_steps_per_second": 3.736, + "step": 79700 + }, + { + "epoch": 2.96, + "learning_rate": 7.035370253282255e-06, + "loss": 1.8539, + "step": 79710 + }, + { + "epoch": 2.97, + "learning_rate": 7.034998326328709e-06, + "loss": 1.8169, + "step": 79720 + }, + { + "epoch": 2.97, + "learning_rate": 7.034626399375163e-06, + "loss": 1.7199, + "step": 79730 + }, + { + "epoch": 2.97, + "learning_rate": 7.034254472421616e-06, + "loss": 1.7687, + "step": 79740 + }, + { + "epoch": 2.97, + "learning_rate": 7.033882545468071e-06, + "loss": 1.6814, + "step": 79750 + }, + { + "epoch": 2.97, + "learning_rate": 7.033510618514524e-06, + "loss": 1.7689, + "step": 79760 + }, + { + "epoch": 2.97, + "learning_rate": 7.0331386915609775e-06, + "loss": 1.6738, + "step": 79770 + }, + { + "epoch": 2.97, + "learning_rate": 7.032766764607432e-06, + "loss": 1.7184, + "step": 79780 + }, + { + "epoch": 2.97, + "learning_rate": 7.032394837653885e-06, + "loss": 1.7081, + "step": 79790 + }, + { + "epoch": 2.97, + "learning_rate": 7.032022910700339e-06, + "loss": 1.7534, + "step": 79800 + }, + { + "epoch": 2.97, + "eval_loss": 1.6664538383483887, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 79800 + }, + { + "epoch": 2.97, + "learning_rate": 7.031650983746793e-06, + "loss": 1.6684, + "step": 79810 + }, + { + "epoch": 2.97, + "learning_rate": 7.0312790567932465e-06, + "loss": 1.667, + "step": 79820 + }, + { + "epoch": 2.97, + "learning_rate": 7.0309071298397e-06, + "loss": 1.7914, + "step": 79830 + }, + { + "epoch": 2.97, + "learning_rate": 7.030535202886154e-06, + "loss": 1.6677, + "step": 79840 + }, + { + "epoch": 2.97, + "learning_rate": 7.030163275932608e-06, + "loss": 1.7083, + "step": 79850 + }, + { + "epoch": 2.97, + "learning_rate": 7.029791348979061e-06, + "loss": 1.7628, + "step": 79860 + }, + { + "epoch": 2.97, + "learning_rate": 7.0294194220255155e-06, + "loss": 1.6888, + "step": 79870 + }, + { + "epoch": 2.97, + "learning_rate": 7.029047495071969e-06, + "loss": 1.8491, + "step": 79880 + }, + { + "epoch": 2.97, + "learning_rate": 7.0286755681184224e-06, + "loss": 1.7044, + "step": 79890 + }, + { + "epoch": 2.97, + "learning_rate": 7.028303641164875e-06, + "loss": 1.7994, + "step": 79900 + }, + { + "epoch": 2.97, + "eval_loss": 1.6664819717407227, + "eval_runtime": 16.8364, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 79900 + }, + { + "epoch": 2.97, + "learning_rate": 7.027931714211329e-06, + "loss": 1.6227, + "step": 79910 + }, + { + "epoch": 2.97, + "learning_rate": 7.027559787257783e-06, + "loss": 1.8101, + "step": 79920 + }, + { + "epoch": 2.97, + "learning_rate": 7.027187860304236e-06, + "loss": 1.7878, + "step": 79930 + }, + { + "epoch": 2.97, + "learning_rate": 7.026815933350691e-06, + "loss": 1.7271, + "step": 79940 + }, + { + "epoch": 2.97, + "learning_rate": 7.026444006397144e-06, + "loss": 1.7394, + "step": 79950 + }, + { + "epoch": 2.97, + "learning_rate": 7.0260720794435975e-06, + "loss": 1.6822, + "step": 79960 + }, + { + "epoch": 2.97, + "learning_rate": 7.025700152490052e-06, + "loss": 1.6722, + "step": 79970 + }, + { + "epoch": 2.97, + "learning_rate": 7.025328225536505e-06, + "loss": 1.6883, + "step": 79980 + }, + { + "epoch": 2.98, + "learning_rate": 7.024956298582959e-06, + "loss": 1.6843, + "step": 79990 + }, + { + "epoch": 2.98, + "learning_rate": 7.024584371629413e-06, + "loss": 1.7083, + "step": 80000 + }, + { + "epoch": 2.98, + "eval_loss": 1.6654412746429443, + "eval_runtime": 16.8352, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 80000 + }, + { + "epoch": 2.98, + "learning_rate": 7.0242124446758665e-06, + "loss": 1.7278, + "step": 80010 + }, + { + "epoch": 2.98, + "learning_rate": 7.02384051772232e-06, + "loss": 1.9016, + "step": 80020 + }, + { + "epoch": 2.98, + "learning_rate": 7.023468590768774e-06, + "loss": 1.7124, + "step": 80030 + }, + { + "epoch": 2.98, + "learning_rate": 7.023096663815228e-06, + "loss": 1.6686, + "step": 80040 + }, + { + "epoch": 2.98, + "learning_rate": 7.022724736861681e-06, + "loss": 1.6699, + "step": 80050 + }, + { + "epoch": 2.98, + "learning_rate": 7.0223528099081355e-06, + "loss": 1.5248, + "step": 80060 + }, + { + "epoch": 2.98, + "learning_rate": 7.021980882954589e-06, + "loss": 1.7213, + "step": 80070 + }, + { + "epoch": 2.98, + "learning_rate": 7.0216089560010416e-06, + "loss": 1.7581, + "step": 80080 + }, + { + "epoch": 2.98, + "learning_rate": 7.021237029047495e-06, + "loss": 1.7847, + "step": 80090 + }, + { + "epoch": 2.98, + "learning_rate": 7.0208651020939485e-06, + "loss": 1.7563, + "step": 80100 + }, + { + "epoch": 2.98, + "eval_loss": 1.6657310724258423, + "eval_runtime": 16.8323, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 80100 + }, + { + "epoch": 2.98, + "learning_rate": 7.020493175140403e-06, + "loss": 1.7463, + "step": 80110 + }, + { + "epoch": 2.98, + "learning_rate": 7.020121248186856e-06, + "loss": 1.7213, + "step": 80120 + }, + { + "epoch": 2.98, + "learning_rate": 7.01974932123331e-06, + "loss": 1.7197, + "step": 80130 + }, + { + "epoch": 2.98, + "learning_rate": 7.019377394279764e-06, + "loss": 1.7822, + "step": 80140 + }, + { + "epoch": 2.98, + "learning_rate": 7.0190054673262175e-06, + "loss": 1.811, + "step": 80150 + }, + { + "epoch": 2.98, + "learning_rate": 7.018633540372671e-06, + "loss": 1.6795, + "step": 80160 + }, + { + "epoch": 2.98, + "learning_rate": 7.018261613419125e-06, + "loss": 1.652, + "step": 80170 + }, + { + "epoch": 2.98, + "learning_rate": 7.017889686465579e-06, + "loss": 1.5775, + "step": 80180 + }, + { + "epoch": 2.98, + "learning_rate": 7.017517759512032e-06, + "loss": 1.7986, + "step": 80190 + }, + { + "epoch": 2.98, + "learning_rate": 7.0171458325584864e-06, + "loss": 1.8214, + "step": 80200 + }, + { + "epoch": 2.98, + "eval_loss": 1.6661924123764038, + "eval_runtime": 16.8592, + "eval_samples_per_second": 59.315, + "eval_steps_per_second": 3.737, + "step": 80200 + }, + { + "epoch": 2.98, + "learning_rate": 7.01677390560494e-06, + "loss": 1.6927, + "step": 80210 + }, + { + "epoch": 2.98, + "learning_rate": 7.016401978651393e-06, + "loss": 1.6972, + "step": 80220 + }, + { + "epoch": 2.98, + "learning_rate": 7.016030051697848e-06, + "loss": 1.6951, + "step": 80230 + }, + { + "epoch": 2.98, + "learning_rate": 7.015658124744301e-06, + "loss": 1.722, + "step": 80240 + }, + { + "epoch": 2.98, + "learning_rate": 7.015286197790755e-06, + "loss": 1.6576, + "step": 80250 + }, + { + "epoch": 2.99, + "learning_rate": 7.014914270837209e-06, + "loss": 1.8578, + "step": 80260 + }, + { + "epoch": 2.99, + "learning_rate": 7.0145423438836615e-06, + "loss": 1.857, + "step": 80270 + }, + { + "epoch": 2.99, + "learning_rate": 7.014170416930115e-06, + "loss": 1.7642, + "step": 80280 + }, + { + "epoch": 2.99, + "learning_rate": 7.0137984899765684e-06, + "loss": 1.8371, + "step": 80290 + }, + { + "epoch": 2.99, + "learning_rate": 7.013426563023023e-06, + "loss": 1.7066, + "step": 80300 + }, + { + "epoch": 2.99, + "eval_loss": 1.6667065620422363, + "eval_runtime": 16.8415, + "eval_samples_per_second": 59.377, + "eval_steps_per_second": 3.741, + "step": 80300 + }, + { + "epoch": 2.99, + "learning_rate": 7.013054636069476e-06, + "loss": 1.5591, + "step": 80310 + }, + { + "epoch": 2.99, + "learning_rate": 7.01268270911593e-06, + "loss": 1.7675, + "step": 80320 + }, + { + "epoch": 2.99, + "learning_rate": 7.012310782162384e-06, + "loss": 1.8422, + "step": 80330 + }, + { + "epoch": 2.99, + "learning_rate": 7.011938855208837e-06, + "loss": 1.7485, + "step": 80340 + }, + { + "epoch": 2.99, + "learning_rate": 7.011566928255291e-06, + "loss": 1.6522, + "step": 80350 + }, + { + "epoch": 2.99, + "learning_rate": 7.011195001301745e-06, + "loss": 1.7261, + "step": 80360 + }, + { + "epoch": 2.99, + "learning_rate": 7.010823074348199e-06, + "loss": 1.6667, + "step": 80370 + }, + { + "epoch": 2.99, + "learning_rate": 7.010451147394652e-06, + "loss": 1.795, + "step": 80380 + }, + { + "epoch": 2.99, + "learning_rate": 7.010079220441106e-06, + "loss": 1.7248, + "step": 80390 + }, + { + "epoch": 2.99, + "learning_rate": 7.00970729348756e-06, + "loss": 1.6598, + "step": 80400 + }, + { + "epoch": 2.99, + "eval_loss": 1.6652661561965942, + "eval_runtime": 16.826, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 80400 + }, + { + "epoch": 2.99, + "learning_rate": 7.009335366534013e-06, + "loss": 1.6595, + "step": 80410 + }, + { + "epoch": 2.99, + "learning_rate": 7.008963439580468e-06, + "loss": 1.7499, + "step": 80420 + }, + { + "epoch": 2.99, + "learning_rate": 7.008591512626921e-06, + "loss": 1.7226, + "step": 80430 + }, + { + "epoch": 2.99, + "learning_rate": 7.0082195856733746e-06, + "loss": 1.7179, + "step": 80440 + }, + { + "epoch": 2.99, + "learning_rate": 7.007847658719829e-06, + "loss": 1.6396, + "step": 80450 + }, + { + "epoch": 2.99, + "learning_rate": 7.0074757317662815e-06, + "loss": 1.6716, + "step": 80460 + }, + { + "epoch": 2.99, + "learning_rate": 7.007103804812735e-06, + "loss": 1.7982, + "step": 80470 + }, + { + "epoch": 2.99, + "learning_rate": 7.006731877859188e-06, + "loss": 1.8281, + "step": 80480 + }, + { + "epoch": 2.99, + "learning_rate": 7.006359950905643e-06, + "loss": 1.5316, + "step": 80490 + }, + { + "epoch": 2.99, + "learning_rate": 7.005988023952096e-06, + "loss": 1.6835, + "step": 80500 + }, + { + "epoch": 2.99, + "eval_loss": 1.6657392978668213, + "eval_runtime": 16.8389, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 80500 + }, + { + "epoch": 2.99, + "learning_rate": 7.00561609699855e-06, + "loss": 1.6822, + "step": 80510 + }, + { + "epoch": 2.99, + "learning_rate": 7.005244170045004e-06, + "loss": 1.903, + "step": 80520 + }, + { + "epoch": 3.0, + "learning_rate": 7.004872243091457e-06, + "loss": 1.7792, + "step": 80530 + }, + { + "epoch": 3.0, + "learning_rate": 7.004500316137911e-06, + "loss": 1.7227, + "step": 80540 + }, + { + "epoch": 3.0, + "learning_rate": 7.004128389184365e-06, + "loss": 1.705, + "step": 80550 + }, + { + "epoch": 3.0, + "learning_rate": 7.003756462230819e-06, + "loss": 1.76, + "step": 80560 + }, + { + "epoch": 3.0, + "learning_rate": 7.003384535277272e-06, + "loss": 1.8003, + "step": 80570 + }, + { + "epoch": 3.0, + "learning_rate": 7.003012608323726e-06, + "loss": 1.7558, + "step": 80580 + }, + { + "epoch": 3.0, + "learning_rate": 7.00264068137018e-06, + "loss": 1.7695, + "step": 80590 + }, + { + "epoch": 3.0, + "learning_rate": 7.002268754416633e-06, + "loss": 1.8566, + "step": 80600 + }, + { + "epoch": 3.0, + "eval_loss": 1.6656384468078613, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 80600 + }, + { + "epoch": 3.0, + "learning_rate": 7.001896827463088e-06, + "loss": 1.7119, + "step": 80610 + }, + { + "epoch": 3.0, + "learning_rate": 7.001524900509541e-06, + "loss": 1.6401, + "step": 80620 + }, + { + "epoch": 3.0, + "learning_rate": 7.0011529735559945e-06, + "loss": 1.6121, + "step": 80630 + }, + { + "epoch": 3.0, + "learning_rate": 7.000781046602449e-06, + "loss": 1.7068, + "step": 80640 + }, + { + "epoch": 3.0, + "learning_rate": 7.0004091196489014e-06, + "loss": 1.728, + "step": 80650 + }, + { + "epoch": 3.0, + "learning_rate": 7.000037192695355e-06, + "loss": 1.7304, + "step": 80660 + }, + { + "epoch": 3.0, + "learning_rate": 6.999665265741808e-06, + "loss": 1.705, + "step": 80670 + }, + { + "epoch": 3.0, + "learning_rate": 6.999293338788262e-06, + "loss": 1.6902, + "step": 80680 + }, + { + "epoch": 3.0, + "learning_rate": 6.998921411834716e-06, + "loss": 1.6527, + "step": 80690 + }, + { + "epoch": 3.0, + "learning_rate": 6.9985494848811696e-06, + "loss": 1.6713, + "step": 80700 + }, + { + "epoch": 3.0, + "eval_loss": 1.665009617805481, + "eval_runtime": 16.8361, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 80700 + }, + { + "epoch": 3.0, + "learning_rate": 6.998177557927623e-06, + "loss": 1.7071, + "step": 80710 + }, + { + "epoch": 3.0, + "learning_rate": 6.997805630974077e-06, + "loss": 1.6189, + "step": 80720 + }, + { + "epoch": 3.0, + "learning_rate": 6.997433704020531e-06, + "loss": 1.6824, + "step": 80730 + }, + { + "epoch": 3.0, + "learning_rate": 6.997061777066984e-06, + "loss": 1.7051, + "step": 80740 + }, + { + "epoch": 3.0, + "learning_rate": 6.9966898501134386e-06, + "loss": 1.8275, + "step": 80750 + }, + { + "epoch": 3.0, + "learning_rate": 6.996317923159892e-06, + "loss": 1.6337, + "step": 80760 + }, + { + "epoch": 3.0, + "learning_rate": 6.9959459962063455e-06, + "loss": 1.6697, + "step": 80770 + }, + { + "epoch": 3.0, + "learning_rate": 6.9955740692528e-06, + "loss": 1.7266, + "step": 80780 + }, + { + "epoch": 3.0, + "learning_rate": 6.995202142299253e-06, + "loss": 1.706, + "step": 80790 + }, + { + "epoch": 3.01, + "learning_rate": 6.994830215345707e-06, + "loss": 1.6728, + "step": 80800 + }, + { + "epoch": 3.01, + "eval_loss": 1.665850043296814, + "eval_runtime": 16.8334, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 80800 + }, + { + "epoch": 3.01, + "learning_rate": 6.994458288392161e-06, + "loss": 1.6345, + "step": 80810 + }, + { + "epoch": 3.01, + "learning_rate": 6.9940863614386145e-06, + "loss": 1.6624, + "step": 80820 + }, + { + "epoch": 3.01, + "learning_rate": 6.993714434485067e-06, + "loss": 1.801, + "step": 80830 + }, + { + "epoch": 3.01, + "learning_rate": 6.9933425075315205e-06, + "loss": 1.706, + "step": 80840 + }, + { + "epoch": 3.01, + "learning_rate": 6.992970580577975e-06, + "loss": 1.7917, + "step": 80850 + }, + { + "epoch": 3.01, + "learning_rate": 6.992598653624428e-06, + "loss": 1.8074, + "step": 80860 + }, + { + "epoch": 3.01, + "learning_rate": 6.992226726670882e-06, + "loss": 1.7632, + "step": 80870 + }, + { + "epoch": 3.01, + "learning_rate": 6.991854799717336e-06, + "loss": 1.6998, + "step": 80880 + }, + { + "epoch": 3.01, + "learning_rate": 6.9914828727637895e-06, + "loss": 1.8752, + "step": 80890 + }, + { + "epoch": 3.01, + "learning_rate": 6.991110945810243e-06, + "loss": 1.7955, + "step": 80900 + }, + { + "epoch": 3.01, + "eval_loss": 1.6661356687545776, + "eval_runtime": 16.8158, + "eval_samples_per_second": 59.468, + "eval_steps_per_second": 3.746, + "step": 80900 + }, + { + "epoch": 3.01, + "learning_rate": 6.990739018856697e-06, + "loss": 1.6748, + "step": 80910 + }, + { + "epoch": 3.01, + "learning_rate": 6.990367091903151e-06, + "loss": 1.5003, + "step": 80920 + }, + { + "epoch": 3.01, + "learning_rate": 6.989995164949604e-06, + "loss": 1.7559, + "step": 80930 + }, + { + "epoch": 3.01, + "learning_rate": 6.9896232379960585e-06, + "loss": 1.7651, + "step": 80940 + }, + { + "epoch": 3.01, + "learning_rate": 6.989251311042512e-06, + "loss": 1.7259, + "step": 80950 + }, + { + "epoch": 3.01, + "learning_rate": 6.9888793840889654e-06, + "loss": 1.6972, + "step": 80960 + }, + { + "epoch": 3.01, + "learning_rate": 6.98850745713542e-06, + "loss": 1.7549, + "step": 80970 + }, + { + "epoch": 3.01, + "learning_rate": 6.988135530181873e-06, + "loss": 1.7879, + "step": 80980 + }, + { + "epoch": 3.01, + "learning_rate": 6.987763603228327e-06, + "loss": 1.9965, + "step": 80990 + }, + { + "epoch": 3.01, + "learning_rate": 6.987391676274781e-06, + "loss": 1.6475, + "step": 81000 + }, + { + "epoch": 3.01, + "eval_loss": 1.665149450302124, + "eval_runtime": 16.8516, + "eval_samples_per_second": 59.341, + "eval_steps_per_second": 3.739, + "step": 81000 + }, + { + "epoch": 3.01, + "learning_rate": 6.9870197493212344e-06, + "loss": 1.7532, + "step": 81010 + }, + { + "epoch": 3.01, + "learning_rate": 6.986647822367687e-06, + "loss": 1.6328, + "step": 81020 + }, + { + "epoch": 3.01, + "learning_rate": 6.9862758954141405e-06, + "loss": 1.633, + "step": 81030 + }, + { + "epoch": 3.01, + "learning_rate": 6.985903968460595e-06, + "loss": 1.6909, + "step": 81040 + }, + { + "epoch": 3.01, + "learning_rate": 6.985532041507048e-06, + "loss": 1.8058, + "step": 81050 + }, + { + "epoch": 3.01, + "learning_rate": 6.985160114553502e-06, + "loss": 1.7241, + "step": 81060 + }, + { + "epoch": 3.02, + "learning_rate": 6.984788187599956e-06, + "loss": 1.681, + "step": 81070 + }, + { + "epoch": 3.02, + "learning_rate": 6.9844162606464095e-06, + "loss": 1.7376, + "step": 81080 + }, + { + "epoch": 3.02, + "learning_rate": 6.984044333692863e-06, + "loss": 1.781, + "step": 81090 + }, + { + "epoch": 3.02, + "learning_rate": 6.983672406739317e-06, + "loss": 1.6341, + "step": 81100 + }, + { + "epoch": 3.02, + "eval_loss": 1.665595531463623, + "eval_runtime": 16.8393, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 81100 + }, + { + "epoch": 3.02, + "learning_rate": 6.983300479785771e-06, + "loss": 1.8953, + "step": 81110 + }, + { + "epoch": 3.02, + "learning_rate": 6.982928552832224e-06, + "loss": 1.7793, + "step": 81120 + }, + { + "epoch": 3.02, + "learning_rate": 6.9825566258786785e-06, + "loss": 1.7383, + "step": 81130 + }, + { + "epoch": 3.02, + "learning_rate": 6.982184698925132e-06, + "loss": 1.7027, + "step": 81140 + }, + { + "epoch": 3.02, + "learning_rate": 6.981812771971585e-06, + "loss": 1.5015, + "step": 81150 + }, + { + "epoch": 3.02, + "learning_rate": 6.98144084501804e-06, + "loss": 1.6523, + "step": 81160 + }, + { + "epoch": 3.02, + "learning_rate": 6.981068918064493e-06, + "loss": 1.6959, + "step": 81170 + }, + { + "epoch": 3.02, + "learning_rate": 6.980696991110947e-06, + "loss": 1.7753, + "step": 81180 + }, + { + "epoch": 3.02, + "learning_rate": 6.980325064157401e-06, + "loss": 1.7694, + "step": 81190 + }, + { + "epoch": 3.02, + "learning_rate": 6.979953137203854e-06, + "loss": 1.7197, + "step": 81200 + }, + { + "epoch": 3.02, + "eval_loss": 1.6648896932601929, + "eval_runtime": 16.8322, + "eval_samples_per_second": 59.41, + "eval_steps_per_second": 3.743, + "step": 81200 + }, + { + "epoch": 3.02, + "learning_rate": 6.979581210250307e-06, + "loss": 1.5995, + "step": 81210 + }, + { + "epoch": 3.02, + "learning_rate": 6.9792092832967605e-06, + "loss": 1.6803, + "step": 81220 + }, + { + "epoch": 3.02, + "learning_rate": 6.978837356343215e-06, + "loss": 1.7312, + "step": 81230 + }, + { + "epoch": 3.02, + "learning_rate": 6.978465429389668e-06, + "loss": 1.65, + "step": 81240 + }, + { + "epoch": 3.02, + "learning_rate": 6.978093502436122e-06, + "loss": 1.5972, + "step": 81250 + }, + { + "epoch": 3.02, + "learning_rate": 6.977721575482575e-06, + "loss": 1.6849, + "step": 81260 + }, + { + "epoch": 3.02, + "learning_rate": 6.9773496485290294e-06, + "loss": 1.6474, + "step": 81270 + }, + { + "epoch": 3.02, + "learning_rate": 6.976977721575483e-06, + "loss": 1.6528, + "step": 81280 + }, + { + "epoch": 3.02, + "learning_rate": 6.976605794621936e-06, + "loss": 1.7508, + "step": 81290 + }, + { + "epoch": 3.02, + "learning_rate": 6.976233867668391e-06, + "loss": 1.6309, + "step": 81300 + }, + { + "epoch": 3.02, + "eval_loss": 1.666131854057312, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 81300 + }, + { + "epoch": 3.02, + "learning_rate": 6.975861940714844e-06, + "loss": 1.698, + "step": 81310 + }, + { + "epoch": 3.02, + "learning_rate": 6.975490013761298e-06, + "loss": 1.6627, + "step": 81320 + }, + { + "epoch": 3.02, + "learning_rate": 6.975118086807752e-06, + "loss": 1.7864, + "step": 81330 + }, + { + "epoch": 3.03, + "learning_rate": 6.974746159854205e-06, + "loss": 1.7467, + "step": 81340 + }, + { + "epoch": 3.03, + "learning_rate": 6.974374232900659e-06, + "loss": 1.7369, + "step": 81350 + }, + { + "epoch": 3.03, + "learning_rate": 6.974002305947113e-06, + "loss": 1.6828, + "step": 81360 + }, + { + "epoch": 3.03, + "learning_rate": 6.973630378993567e-06, + "loss": 1.7579, + "step": 81370 + }, + { + "epoch": 3.03, + "learning_rate": 6.97325845204002e-06, + "loss": 1.7608, + "step": 81380 + }, + { + "epoch": 3.03, + "learning_rate": 6.972886525086474e-06, + "loss": 1.8146, + "step": 81390 + }, + { + "epoch": 3.03, + "learning_rate": 6.972514598132927e-06, + "loss": 1.7398, + "step": 81400 + }, + { + "epoch": 3.03, + "eval_loss": 1.6664727926254272, + "eval_runtime": 16.8526, + "eval_samples_per_second": 59.338, + "eval_steps_per_second": 3.738, + "step": 81400 + }, + { + "epoch": 3.03, + "learning_rate": 6.97214267117938e-06, + "loss": 1.7468, + "step": 81410 + }, + { + "epoch": 3.03, + "learning_rate": 6.971770744225834e-06, + "loss": 1.6828, + "step": 81420 + }, + { + "epoch": 3.03, + "learning_rate": 6.971398817272288e-06, + "loss": 1.6994, + "step": 81430 + }, + { + "epoch": 3.03, + "learning_rate": 6.971026890318742e-06, + "loss": 1.7355, + "step": 81440 + }, + { + "epoch": 3.03, + "learning_rate": 6.970654963365195e-06, + "loss": 1.5587, + "step": 81450 + }, + { + "epoch": 3.03, + "learning_rate": 6.970283036411649e-06, + "loss": 1.6659, + "step": 81460 + }, + { + "epoch": 3.03, + "learning_rate": 6.969911109458103e-06, + "loss": 1.6107, + "step": 81470 + }, + { + "epoch": 3.03, + "learning_rate": 6.969539182504556e-06, + "loss": 1.7018, + "step": 81480 + }, + { + "epoch": 3.03, + "learning_rate": 6.969167255551011e-06, + "loss": 1.7576, + "step": 81490 + }, + { + "epoch": 3.03, + "learning_rate": 6.968795328597464e-06, + "loss": 1.8408, + "step": 81500 + }, + { + "epoch": 3.03, + "eval_loss": 1.6664350032806396, + "eval_runtime": 16.8403, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 81500 + }, + { + "epoch": 3.03, + "learning_rate": 6.9684234016439176e-06, + "loss": 1.692, + "step": 81510 + }, + { + "epoch": 3.03, + "learning_rate": 6.968051474690372e-06, + "loss": 1.6651, + "step": 81520 + }, + { + "epoch": 3.03, + "learning_rate": 6.967679547736825e-06, + "loss": 1.7665, + "step": 81530 + }, + { + "epoch": 3.03, + "learning_rate": 6.967307620783279e-06, + "loss": 1.6388, + "step": 81540 + }, + { + "epoch": 3.03, + "learning_rate": 6.966935693829733e-06, + "loss": 1.7282, + "step": 81550 + }, + { + "epoch": 3.03, + "learning_rate": 6.9665637668761865e-06, + "loss": 1.7362, + "step": 81560 + }, + { + "epoch": 3.03, + "learning_rate": 6.96619183992264e-06, + "loss": 1.6575, + "step": 81570 + }, + { + "epoch": 3.03, + "learning_rate": 6.965819912969094e-06, + "loss": 1.7606, + "step": 81580 + }, + { + "epoch": 3.03, + "learning_rate": 6.965447986015547e-06, + "loss": 1.6834, + "step": 81590 + }, + { + "epoch": 3.03, + "learning_rate": 6.965076059062e-06, + "loss": 1.688, + "step": 81600 + }, + { + "epoch": 3.03, + "eval_loss": 1.6650514602661133, + "eval_runtime": 16.8398, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 81600 + }, + { + "epoch": 3.04, + "learning_rate": 6.964704132108454e-06, + "loss": 1.6339, + "step": 81610 + }, + { + "epoch": 3.04, + "learning_rate": 6.964332205154908e-06, + "loss": 1.6422, + "step": 81620 + }, + { + "epoch": 3.04, + "learning_rate": 6.963960278201362e-06, + "loss": 1.7283, + "step": 81630 + }, + { + "epoch": 3.04, + "learning_rate": 6.963588351247815e-06, + "loss": 1.7843, + "step": 81640 + }, + { + "epoch": 3.04, + "learning_rate": 6.963216424294269e-06, + "loss": 1.6496, + "step": 81650 + }, + { + "epoch": 3.04, + "learning_rate": 6.962844497340723e-06, + "loss": 1.7328, + "step": 81660 + }, + { + "epoch": 3.04, + "learning_rate": 6.962472570387176e-06, + "loss": 1.6176, + "step": 81670 + }, + { + "epoch": 3.04, + "learning_rate": 6.962100643433631e-06, + "loss": 1.6721, + "step": 81680 + }, + { + "epoch": 3.04, + "learning_rate": 6.961728716480084e-06, + "loss": 1.637, + "step": 81690 + }, + { + "epoch": 3.04, + "learning_rate": 6.9613567895265375e-06, + "loss": 1.6218, + "step": 81700 + }, + { + "epoch": 3.04, + "eval_loss": 1.6646699905395508, + "eval_runtime": 16.8466, + "eval_samples_per_second": 59.359, + "eval_steps_per_second": 3.74, + "step": 81700 + }, + { + "epoch": 3.04, + "learning_rate": 6.960984862572992e-06, + "loss": 1.6675, + "step": 81710 + }, + { + "epoch": 3.04, + "learning_rate": 6.960612935619445e-06, + "loss": 1.6565, + "step": 81720 + }, + { + "epoch": 3.04, + "learning_rate": 6.960241008665899e-06, + "loss": 1.7035, + "step": 81730 + }, + { + "epoch": 3.04, + "learning_rate": 6.959869081712353e-06, + "loss": 1.6561, + "step": 81740 + }, + { + "epoch": 3.04, + "learning_rate": 6.9594971547588065e-06, + "loss": 1.756, + "step": 81750 + }, + { + "epoch": 3.04, + "learning_rate": 6.95912522780526e-06, + "loss": 1.8081, + "step": 81760 + }, + { + "epoch": 3.04, + "learning_rate": 6.9587533008517126e-06, + "loss": 1.5326, + "step": 81770 + }, + { + "epoch": 3.04, + "learning_rate": 6.958381373898167e-06, + "loss": 1.6666, + "step": 81780 + }, + { + "epoch": 3.04, + "learning_rate": 6.95800944694462e-06, + "loss": 1.8024, + "step": 81790 + }, + { + "epoch": 3.04, + "learning_rate": 6.957637519991074e-06, + "loss": 1.7133, + "step": 81800 + }, + { + "epoch": 3.04, + "eval_loss": 1.6644536256790161, + "eval_runtime": 16.8315, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 81800 + }, + { + "epoch": 3.04, + "learning_rate": 6.957265593037528e-06, + "loss": 1.6563, + "step": 81810 + }, + { + "epoch": 3.04, + "learning_rate": 6.9568936660839816e-06, + "loss": 1.7039, + "step": 81820 + }, + { + "epoch": 3.04, + "learning_rate": 6.956521739130435e-06, + "loss": 1.6856, + "step": 81830 + }, + { + "epoch": 3.04, + "learning_rate": 6.9561498121768885e-06, + "loss": 1.662, + "step": 81840 + }, + { + "epoch": 3.04, + "learning_rate": 6.955777885223343e-06, + "loss": 1.5483, + "step": 81850 + }, + { + "epoch": 3.04, + "learning_rate": 6.955405958269796e-06, + "loss": 1.7629, + "step": 81860 + }, + { + "epoch": 3.04, + "learning_rate": 6.95503403131625e-06, + "loss": 1.6829, + "step": 81870 + }, + { + "epoch": 3.05, + "learning_rate": 6.954662104362704e-06, + "loss": 1.6719, + "step": 81880 + }, + { + "epoch": 3.05, + "learning_rate": 6.9542901774091575e-06, + "loss": 1.7486, + "step": 81890 + }, + { + "epoch": 3.05, + "learning_rate": 6.953918250455611e-06, + "loss": 1.6028, + "step": 81900 + }, + { + "epoch": 3.05, + "eval_loss": 1.6650512218475342, + "eval_runtime": 16.8452, + "eval_samples_per_second": 59.364, + "eval_steps_per_second": 3.74, + "step": 81900 + }, + { + "epoch": 3.05, + "learning_rate": 6.953546323502065e-06, + "loss": 1.6866, + "step": 81910 + }, + { + "epoch": 3.05, + "learning_rate": 6.953174396548519e-06, + "loss": 1.6094, + "step": 81920 + }, + { + "epoch": 3.05, + "learning_rate": 6.952802469594972e-06, + "loss": 1.7537, + "step": 81930 + }, + { + "epoch": 3.05, + "learning_rate": 6.9524305426414265e-06, + "loss": 1.6576, + "step": 81940 + }, + { + "epoch": 3.05, + "learning_rate": 6.95205861568788e-06, + "loss": 1.6706, + "step": 81950 + }, + { + "epoch": 3.05, + "learning_rate": 6.9516866887343325e-06, + "loss": 1.6255, + "step": 81960 + }, + { + "epoch": 3.05, + "learning_rate": 6.951314761780786e-06, + "loss": 1.8836, + "step": 81970 + }, + { + "epoch": 3.05, + "learning_rate": 6.95094283482724e-06, + "loss": 1.6385, + "step": 81980 + }, + { + "epoch": 3.05, + "learning_rate": 6.950570907873694e-06, + "loss": 1.5554, + "step": 81990 + }, + { + "epoch": 3.05, + "learning_rate": 6.950198980920147e-06, + "loss": 1.7326, + "step": 82000 + }, + { + "epoch": 3.05, + "eval_loss": 1.6637852191925049, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 82000 + }, + { + "epoch": 3.05, + "learning_rate": 6.9498270539666015e-06, + "loss": 1.7524, + "step": 82010 + }, + { + "epoch": 3.05, + "learning_rate": 6.949455127013055e-06, + "loss": 1.7155, + "step": 82020 + }, + { + "epoch": 3.05, + "learning_rate": 6.9490832000595084e-06, + "loss": 1.6054, + "step": 82030 + }, + { + "epoch": 3.05, + "learning_rate": 6.948711273105963e-06, + "loss": 1.6916, + "step": 82040 + }, + { + "epoch": 3.05, + "learning_rate": 6.948339346152416e-06, + "loss": 1.7554, + "step": 82050 + }, + { + "epoch": 3.05, + "learning_rate": 6.94796741919887e-06, + "loss": 1.7534, + "step": 82060 + }, + { + "epoch": 3.05, + "learning_rate": 6.947595492245324e-06, + "loss": 1.6735, + "step": 82070 + }, + { + "epoch": 3.05, + "learning_rate": 6.9472235652917774e-06, + "loss": 1.6911, + "step": 82080 + }, + { + "epoch": 3.05, + "learning_rate": 6.946851638338231e-06, + "loss": 1.616, + "step": 82090 + }, + { + "epoch": 3.05, + "learning_rate": 6.946479711384685e-06, + "loss": 1.7004, + "step": 82100 + }, + { + "epoch": 3.05, + "eval_loss": 1.6640101671218872, + "eval_runtime": 16.8399, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 82100 + }, + { + "epoch": 3.05, + "learning_rate": 6.946107784431139e-06, + "loss": 1.8094, + "step": 82110 + }, + { + "epoch": 3.05, + "learning_rate": 6.945735857477592e-06, + "loss": 1.6904, + "step": 82120 + }, + { + "epoch": 3.05, + "learning_rate": 6.945363930524046e-06, + "loss": 1.6184, + "step": 82130 + }, + { + "epoch": 3.06, + "learning_rate": 6.9449920035705e-06, + "loss": 1.7096, + "step": 82140 + }, + { + "epoch": 3.06, + "learning_rate": 6.9446200766169525e-06, + "loss": 1.5155, + "step": 82150 + }, + { + "epoch": 3.06, + "learning_rate": 6.944248149663406e-06, + "loss": 1.7149, + "step": 82160 + }, + { + "epoch": 3.06, + "learning_rate": 6.94387622270986e-06, + "loss": 1.7108, + "step": 82170 + }, + { + "epoch": 3.06, + "learning_rate": 6.943504295756314e-06, + "loss": 1.7945, + "step": 82180 + }, + { + "epoch": 3.06, + "learning_rate": 6.943132368802767e-06, + "loss": 1.7448, + "step": 82190 + }, + { + "epoch": 3.06, + "learning_rate": 6.9427604418492215e-06, + "loss": 1.6748, + "step": 82200 + }, + { + "epoch": 3.06, + "eval_loss": 1.6642842292785645, + "eval_runtime": 16.8463, + "eval_samples_per_second": 59.36, + "eval_steps_per_second": 3.74, + "step": 82200 + }, + { + "epoch": 3.06, + "learning_rate": 6.942388514895675e-06, + "loss": 1.7064, + "step": 82210 + }, + { + "epoch": 3.06, + "learning_rate": 6.942016587942128e-06, + "loss": 1.698, + "step": 82220 + }, + { + "epoch": 3.06, + "learning_rate": 6.941644660988583e-06, + "loss": 1.692, + "step": 82230 + }, + { + "epoch": 3.06, + "learning_rate": 6.941272734035036e-06, + "loss": 1.598, + "step": 82240 + }, + { + "epoch": 3.06, + "learning_rate": 6.94090080708149e-06, + "loss": 1.7257, + "step": 82250 + }, + { + "epoch": 3.06, + "learning_rate": 6.940528880127944e-06, + "loss": 1.7549, + "step": 82260 + }, + { + "epoch": 3.06, + "learning_rate": 6.940156953174397e-06, + "loss": 1.552, + "step": 82270 + }, + { + "epoch": 3.06, + "learning_rate": 6.939785026220851e-06, + "loss": 1.7313, + "step": 82280 + }, + { + "epoch": 3.06, + "learning_rate": 6.939413099267305e-06, + "loss": 1.6638, + "step": 82290 + }, + { + "epoch": 3.06, + "learning_rate": 6.939041172313759e-06, + "loss": 1.6995, + "step": 82300 + }, + { + "epoch": 3.06, + "eval_loss": 1.6642742156982422, + "eval_runtime": 16.843, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 82300 + }, + { + "epoch": 3.06, + "learning_rate": 6.938669245360212e-06, + "loss": 1.5712, + "step": 82310 + }, + { + "epoch": 3.06, + "learning_rate": 6.938297318406666e-06, + "loss": 1.6188, + "step": 82320 + }, + { + "epoch": 3.06, + "learning_rate": 6.93792539145312e-06, + "loss": 1.7411, + "step": 82330 + }, + { + "epoch": 3.06, + "learning_rate": 6.9375534644995724e-06, + "loss": 1.8465, + "step": 82340 + }, + { + "epoch": 3.06, + "learning_rate": 6.937181537546026e-06, + "loss": 1.6742, + "step": 82350 + }, + { + "epoch": 3.06, + "learning_rate": 6.93680961059248e-06, + "loss": 1.6603, + "step": 82360 + }, + { + "epoch": 3.06, + "learning_rate": 6.936437683638934e-06, + "loss": 1.7225, + "step": 82370 + }, + { + "epoch": 3.06, + "learning_rate": 6.936065756685387e-06, + "loss": 1.7044, + "step": 82380 + }, + { + "epoch": 3.06, + "learning_rate": 6.9356938297318414e-06, + "loss": 1.7715, + "step": 82390 + }, + { + "epoch": 3.06, + "learning_rate": 6.935321902778295e-06, + "loss": 1.5837, + "step": 82400 + }, + { + "epoch": 3.06, + "eval_loss": 1.663391351699829, + "eval_runtime": 16.8204, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.745, + "step": 82400 + }, + { + "epoch": 3.07, + "learning_rate": 6.934949975824748e-06, + "loss": 1.5655, + "step": 82410 + }, + { + "epoch": 3.07, + "learning_rate": 6.934578048871202e-06, + "loss": 1.713, + "step": 82420 + }, + { + "epoch": 3.07, + "learning_rate": 6.934206121917656e-06, + "loss": 1.5848, + "step": 82430 + }, + { + "epoch": 3.07, + "learning_rate": 6.93383419496411e-06, + "loss": 1.7381, + "step": 82440 + }, + { + "epoch": 3.07, + "learning_rate": 6.933462268010563e-06, + "loss": 1.6888, + "step": 82450 + }, + { + "epoch": 3.07, + "learning_rate": 6.933090341057017e-06, + "loss": 1.6276, + "step": 82460 + }, + { + "epoch": 3.07, + "learning_rate": 6.932718414103471e-06, + "loss": 1.5941, + "step": 82470 + }, + { + "epoch": 3.07, + "learning_rate": 6.932346487149924e-06, + "loss": 1.7178, + "step": 82480 + }, + { + "epoch": 3.07, + "learning_rate": 6.9319745601963786e-06, + "loss": 1.7165, + "step": 82490 + }, + { + "epoch": 3.07, + "learning_rate": 6.931602633242832e-06, + "loss": 1.6477, + "step": 82500 + }, + { + "epoch": 3.07, + "eval_loss": 1.663069248199463, + "eval_runtime": 16.8298, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 82500 + }, + { + "epoch": 3.07, + "learning_rate": 6.9312307062892855e-06, + "loss": 1.643, + "step": 82510 + }, + { + "epoch": 3.07, + "learning_rate": 6.930858779335738e-06, + "loss": 1.5868, + "step": 82520 + }, + { + "epoch": 3.07, + "learning_rate": 6.930486852382192e-06, + "loss": 1.6368, + "step": 82530 + }, + { + "epoch": 3.07, + "learning_rate": 6.930114925428646e-06, + "loss": 1.6923, + "step": 82540 + }, + { + "epoch": 3.07, + "learning_rate": 6.929742998475099e-06, + "loss": 1.6751, + "step": 82550 + }, + { + "epoch": 3.07, + "learning_rate": 6.929371071521554e-06, + "loss": 1.676, + "step": 82560 + }, + { + "epoch": 3.07, + "learning_rate": 6.928999144568007e-06, + "loss": 1.6738, + "step": 82570 + }, + { + "epoch": 3.07, + "learning_rate": 6.9286272176144606e-06, + "loss": 1.8323, + "step": 82580 + }, + { + "epoch": 3.07, + "learning_rate": 6.928255290660915e-06, + "loss": 1.8302, + "step": 82590 + }, + { + "epoch": 3.07, + "learning_rate": 6.927883363707368e-06, + "loss": 1.686, + "step": 82600 + }, + { + "epoch": 3.07, + "eval_loss": 1.663964867591858, + "eval_runtime": 16.8331, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 82600 + }, + { + "epoch": 3.07, + "learning_rate": 6.927511436753822e-06, + "loss": 1.7294, + "step": 82610 + }, + { + "epoch": 3.07, + "learning_rate": 6.927139509800276e-06, + "loss": 1.7262, + "step": 82620 + }, + { + "epoch": 3.07, + "learning_rate": 6.9267675828467295e-06, + "loss": 1.7466, + "step": 82630 + }, + { + "epoch": 3.07, + "learning_rate": 6.926395655893183e-06, + "loss": 1.6035, + "step": 82640 + }, + { + "epoch": 3.07, + "learning_rate": 6.926023728939637e-06, + "loss": 1.7042, + "step": 82650 + }, + { + "epoch": 3.07, + "learning_rate": 6.925651801986091e-06, + "loss": 1.6598, + "step": 82660 + }, + { + "epoch": 3.07, + "learning_rate": 6.925279875032544e-06, + "loss": 1.8262, + "step": 82670 + }, + { + "epoch": 3.08, + "learning_rate": 6.9249079480789985e-06, + "loss": 1.7187, + "step": 82680 + }, + { + "epoch": 3.08, + "learning_rate": 6.924536021125452e-06, + "loss": 1.7971, + "step": 82690 + }, + { + "epoch": 3.08, + "learning_rate": 6.9241640941719054e-06, + "loss": 1.6913, + "step": 82700 + }, + { + "epoch": 3.08, + "eval_loss": 1.6636685132980347, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 82700 + }, + { + "epoch": 3.08, + "learning_rate": 6.923792167218358e-06, + "loss": 1.6421, + "step": 82710 + }, + { + "epoch": 3.08, + "learning_rate": 6.923420240264812e-06, + "loss": 1.6124, + "step": 82720 + }, + { + "epoch": 3.08, + "learning_rate": 6.923048313311266e-06, + "loss": 1.8067, + "step": 82730 + }, + { + "epoch": 3.08, + "learning_rate": 6.922676386357719e-06, + "loss": 1.6048, + "step": 82740 + }, + { + "epoch": 3.08, + "learning_rate": 6.922304459404174e-06, + "loss": 1.7223, + "step": 82750 + }, + { + "epoch": 3.08, + "learning_rate": 6.921932532450627e-06, + "loss": 1.8132, + "step": 82760 + }, + { + "epoch": 3.08, + "learning_rate": 6.9215606054970805e-06, + "loss": 1.6495, + "step": 82770 + }, + { + "epoch": 3.08, + "learning_rate": 6.921188678543535e-06, + "loss": 1.6854, + "step": 82780 + }, + { + "epoch": 3.08, + "learning_rate": 6.920816751589988e-06, + "loss": 1.7628, + "step": 82790 + }, + { + "epoch": 3.08, + "learning_rate": 6.920444824636442e-06, + "loss": 1.6275, + "step": 82800 + }, + { + "epoch": 3.08, + "eval_loss": 1.6640658378601074, + "eval_runtime": 16.8372, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 82800 + }, + { + "epoch": 3.08, + "learning_rate": 6.920072897682896e-06, + "loss": 1.6199, + "step": 82810 + }, + { + "epoch": 3.08, + "learning_rate": 6.9197009707293495e-06, + "loss": 1.6865, + "step": 82820 + }, + { + "epoch": 3.08, + "learning_rate": 6.919329043775803e-06, + "loss": 1.7724, + "step": 82830 + }, + { + "epoch": 3.08, + "learning_rate": 6.918957116822257e-06, + "loss": 1.5766, + "step": 82840 + }, + { + "epoch": 3.08, + "learning_rate": 6.918585189868711e-06, + "loss": 1.5915, + "step": 82850 + }, + { + "epoch": 3.08, + "learning_rate": 6.918213262915164e-06, + "loss": 1.7087, + "step": 82860 + }, + { + "epoch": 3.08, + "learning_rate": 6.9178413359616185e-06, + "loss": 1.6095, + "step": 82870 + }, + { + "epoch": 3.08, + "learning_rate": 6.917469409008072e-06, + "loss": 1.671, + "step": 82880 + }, + { + "epoch": 3.08, + "learning_rate": 6.917097482054525e-06, + "loss": 1.5887, + "step": 82890 + }, + { + "epoch": 3.08, + "learning_rate": 6.916725555100978e-06, + "loss": 1.7965, + "step": 82900 + }, + { + "epoch": 3.08, + "eval_loss": 1.6637295484542847, + "eval_runtime": 16.8336, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 82900 + }, + { + "epoch": 3.08, + "learning_rate": 6.916353628147432e-06, + "loss": 1.5714, + "step": 82910 + }, + { + "epoch": 3.08, + "learning_rate": 6.915981701193886e-06, + "loss": 1.7868, + "step": 82920 + }, + { + "epoch": 3.08, + "learning_rate": 6.915609774240339e-06, + "loss": 1.696, + "step": 82930 + }, + { + "epoch": 3.08, + "learning_rate": 6.9152378472867936e-06, + "loss": 1.8051, + "step": 82940 + }, + { + "epoch": 3.09, + "learning_rate": 6.914865920333247e-06, + "loss": 1.858, + "step": 82950 + }, + { + "epoch": 3.09, + "learning_rate": 6.9144939933797005e-06, + "loss": 1.7912, + "step": 82960 + }, + { + "epoch": 3.09, + "learning_rate": 6.914122066426155e-06, + "loss": 1.8021, + "step": 82970 + }, + { + "epoch": 3.09, + "learning_rate": 6.913750139472608e-06, + "loss": 1.6681, + "step": 82980 + }, + { + "epoch": 3.09, + "learning_rate": 6.913378212519062e-06, + "loss": 1.7267, + "step": 82990 + }, + { + "epoch": 3.09, + "learning_rate": 6.913006285565515e-06, + "loss": 1.7494, + "step": 83000 + }, + { + "epoch": 3.09, + "eval_loss": 1.6632076501846313, + "eval_runtime": 16.846, + "eval_samples_per_second": 59.361, + "eval_steps_per_second": 3.74, + "step": 83000 + }, + { + "epoch": 3.09, + "learning_rate": 6.9126343586119695e-06, + "loss": 1.6867, + "step": 83010 + }, + { + "epoch": 3.09, + "learning_rate": 6.912262431658423e-06, + "loss": 1.7975, + "step": 83020 + }, + { + "epoch": 3.09, + "learning_rate": 6.911890504704876e-06, + "loss": 1.7851, + "step": 83030 + }, + { + "epoch": 3.09, + "learning_rate": 6.911518577751331e-06, + "loss": 1.7244, + "step": 83040 + }, + { + "epoch": 3.09, + "learning_rate": 6.911146650797784e-06, + "loss": 1.7235, + "step": 83050 + }, + { + "epoch": 3.09, + "learning_rate": 6.910774723844238e-06, + "loss": 1.6731, + "step": 83060 + }, + { + "epoch": 3.09, + "learning_rate": 6.910402796890692e-06, + "loss": 1.7095, + "step": 83070 + }, + { + "epoch": 3.09, + "learning_rate": 6.910030869937145e-06, + "loss": 1.6643, + "step": 83080 + }, + { + "epoch": 3.09, + "learning_rate": 6.909658942983598e-06, + "loss": 1.7115, + "step": 83090 + }, + { + "epoch": 3.09, + "learning_rate": 6.9092870160300514e-06, + "loss": 1.7863, + "step": 83100 + }, + { + "epoch": 3.09, + "eval_loss": 1.6629973649978638, + "eval_runtime": 16.8535, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 83100 + }, + { + "epoch": 3.09, + "learning_rate": 6.908915089076506e-06, + "loss": 1.7324, + "step": 83110 + }, + { + "epoch": 3.09, + "learning_rate": 6.908543162122959e-06, + "loss": 1.9247, + "step": 83120 + }, + { + "epoch": 3.09, + "learning_rate": 6.908171235169413e-06, + "loss": 1.7417, + "step": 83130 + }, + { + "epoch": 3.09, + "learning_rate": 6.907799308215867e-06, + "loss": 1.672, + "step": 83140 + }, + { + "epoch": 3.09, + "learning_rate": 6.9074273812623204e-06, + "loss": 1.6109, + "step": 83150 + }, + { + "epoch": 3.09, + "learning_rate": 6.907055454308774e-06, + "loss": 1.5588, + "step": 83160 + }, + { + "epoch": 3.09, + "learning_rate": 6.906683527355228e-06, + "loss": 1.6644, + "step": 83170 + }, + { + "epoch": 3.09, + "learning_rate": 6.906311600401682e-06, + "loss": 1.6991, + "step": 83180 + }, + { + "epoch": 3.09, + "learning_rate": 6.905939673448135e-06, + "loss": 1.7632, + "step": 83190 + }, + { + "epoch": 3.09, + "learning_rate": 6.905567746494589e-06, + "loss": 1.6847, + "step": 83200 + }, + { + "epoch": 3.09, + "eval_loss": 1.6636104583740234, + "eval_runtime": 16.8643, + "eval_samples_per_second": 59.297, + "eval_steps_per_second": 3.736, + "step": 83200 + }, + { + "epoch": 3.09, + "learning_rate": 6.905195819541043e-06, + "loss": 1.7311, + "step": 83210 + }, + { + "epoch": 3.1, + "learning_rate": 6.904823892587496e-06, + "loss": 1.6822, + "step": 83220 + }, + { + "epoch": 3.1, + "learning_rate": 6.904451965633951e-06, + "loss": 1.7284, + "step": 83230 + }, + { + "epoch": 3.1, + "learning_rate": 6.904080038680404e-06, + "loss": 1.6924, + "step": 83240 + }, + { + "epoch": 3.1, + "learning_rate": 6.9037081117268576e-06, + "loss": 1.712, + "step": 83250 + }, + { + "epoch": 3.1, + "learning_rate": 6.903336184773312e-06, + "loss": 1.7079, + "step": 83260 + }, + { + "epoch": 3.1, + "learning_rate": 6.902964257819765e-06, + "loss": 1.7929, + "step": 83270 + }, + { + "epoch": 3.1, + "learning_rate": 6.902592330866218e-06, + "loss": 1.7065, + "step": 83280 + }, + { + "epoch": 3.1, + "learning_rate": 6.902220403912671e-06, + "loss": 1.7329, + "step": 83290 + }, + { + "epoch": 3.1, + "learning_rate": 6.901848476959126e-06, + "loss": 1.5655, + "step": 83300 + }, + { + "epoch": 3.1, + "eval_loss": 1.6636875867843628, + "eval_runtime": 16.8273, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 83300 + }, + { + "epoch": 3.1, + "learning_rate": 6.901476550005579e-06, + "loss": 1.6467, + "step": 83310 + }, + { + "epoch": 3.1, + "learning_rate": 6.901104623052033e-06, + "loss": 1.7709, + "step": 83320 + }, + { + "epoch": 3.1, + "learning_rate": 6.900732696098487e-06, + "loss": 1.6418, + "step": 83330 + }, + { + "epoch": 3.1, + "learning_rate": 6.90036076914494e-06, + "loss": 1.6866, + "step": 83340 + }, + { + "epoch": 3.1, + "learning_rate": 6.899988842191394e-06, + "loss": 1.6573, + "step": 83350 + }, + { + "epoch": 3.1, + "learning_rate": 6.899616915237848e-06, + "loss": 1.5545, + "step": 83360 + }, + { + "epoch": 3.1, + "learning_rate": 6.899244988284302e-06, + "loss": 1.7356, + "step": 83370 + }, + { + "epoch": 3.1, + "learning_rate": 6.898873061330755e-06, + "loss": 1.7317, + "step": 83380 + }, + { + "epoch": 3.1, + "learning_rate": 6.898501134377209e-06, + "loss": 1.7471, + "step": 83390 + }, + { + "epoch": 3.1, + "learning_rate": 6.898129207423663e-06, + "loss": 1.7563, + "step": 83400 + }, + { + "epoch": 3.1, + "eval_loss": 1.6617751121520996, + "eval_runtime": 16.8538, + "eval_samples_per_second": 59.334, + "eval_steps_per_second": 3.738, + "step": 83400 + }, + { + "epoch": 3.1, + "learning_rate": 6.897757280470116e-06, + "loss": 1.5967, + "step": 83410 + }, + { + "epoch": 3.1, + "learning_rate": 6.897385353516571e-06, + "loss": 1.9771, + "step": 83420 + }, + { + "epoch": 3.1, + "learning_rate": 6.897013426563024e-06, + "loss": 1.5749, + "step": 83430 + }, + { + "epoch": 3.1, + "learning_rate": 6.8966414996094775e-06, + "loss": 1.7267, + "step": 83440 + }, + { + "epoch": 3.1, + "learning_rate": 6.896269572655932e-06, + "loss": 1.7511, + "step": 83450 + }, + { + "epoch": 3.1, + "learning_rate": 6.8958976457023844e-06, + "loss": 1.7286, + "step": 83460 + }, + { + "epoch": 3.1, + "learning_rate": 6.895525718748838e-06, + "loss": 1.7261, + "step": 83470 + }, + { + "epoch": 3.1, + "learning_rate": 6.895153791795291e-06, + "loss": 1.8744, + "step": 83480 + }, + { + "epoch": 3.11, + "learning_rate": 6.894781864841746e-06, + "loss": 1.5687, + "step": 83490 + }, + { + "epoch": 3.11, + "learning_rate": 6.894409937888199e-06, + "loss": 1.6997, + "step": 83500 + }, + { + "epoch": 3.11, + "eval_loss": 1.6620795726776123, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 83500 + }, + { + "epoch": 3.11, + "learning_rate": 6.894038010934653e-06, + "loss": 1.6546, + "step": 83510 + }, + { + "epoch": 3.11, + "learning_rate": 6.893666083981107e-06, + "loss": 1.6312, + "step": 83520 + }, + { + "epoch": 3.11, + "learning_rate": 6.89329415702756e-06, + "loss": 1.6095, + "step": 83530 + }, + { + "epoch": 3.11, + "learning_rate": 6.892922230074014e-06, + "loss": 1.6679, + "step": 83540 + }, + { + "epoch": 3.11, + "learning_rate": 6.892550303120468e-06, + "loss": 1.6606, + "step": 83550 + }, + { + "epoch": 3.11, + "learning_rate": 6.8921783761669216e-06, + "loss": 1.6102, + "step": 83560 + }, + { + "epoch": 3.11, + "learning_rate": 6.891806449213375e-06, + "loss": 1.7716, + "step": 83570 + }, + { + "epoch": 3.11, + "learning_rate": 6.8914345222598285e-06, + "loss": 1.6409, + "step": 83580 + }, + { + "epoch": 3.11, + "learning_rate": 6.891062595306283e-06, + "loss": 1.669, + "step": 83590 + }, + { + "epoch": 3.11, + "learning_rate": 6.890690668352736e-06, + "loss": 1.6727, + "step": 83600 + }, + { + "epoch": 3.11, + "eval_loss": 1.6617680788040161, + "eval_runtime": 16.8301, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 83600 + }, + { + "epoch": 3.11, + "learning_rate": 6.89031874139919e-06, + "loss": 1.7353, + "step": 83610 + }, + { + "epoch": 3.11, + "learning_rate": 6.889946814445644e-06, + "loss": 1.7501, + "step": 83620 + }, + { + "epoch": 3.11, + "learning_rate": 6.8895748874920975e-06, + "loss": 1.6196, + "step": 83630 + }, + { + "epoch": 3.11, + "learning_rate": 6.889202960538551e-06, + "loss": 1.781, + "step": 83640 + }, + { + "epoch": 3.11, + "learning_rate": 6.8888310335850036e-06, + "loss": 1.6599, + "step": 83650 + }, + { + "epoch": 3.11, + "learning_rate": 6.888459106631458e-06, + "loss": 1.7991, + "step": 83660 + }, + { + "epoch": 3.11, + "learning_rate": 6.888087179677911e-06, + "loss": 1.7217, + "step": 83670 + }, + { + "epoch": 3.11, + "learning_rate": 6.887715252724365e-06, + "loss": 1.8725, + "step": 83680 + }, + { + "epoch": 3.11, + "learning_rate": 6.887343325770819e-06, + "loss": 1.6225, + "step": 83690 + }, + { + "epoch": 3.11, + "learning_rate": 6.8869713988172725e-06, + "loss": 1.6562, + "step": 83700 + }, + { + "epoch": 3.11, + "eval_loss": 1.661368727684021, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 83700 + }, + { + "epoch": 3.11, + "learning_rate": 6.886599471863726e-06, + "loss": 1.6271, + "step": 83710 + }, + { + "epoch": 3.11, + "learning_rate": 6.88622754491018e-06, + "loss": 1.6019, + "step": 83720 + }, + { + "epoch": 3.11, + "learning_rate": 6.885855617956634e-06, + "loss": 1.5703, + "step": 83730 + }, + { + "epoch": 3.11, + "learning_rate": 6.885483691003087e-06, + "loss": 1.6649, + "step": 83740 + }, + { + "epoch": 3.11, + "learning_rate": 6.8851117640495415e-06, + "loss": 1.6854, + "step": 83750 + }, + { + "epoch": 3.12, + "learning_rate": 6.884739837095995e-06, + "loss": 1.7092, + "step": 83760 + }, + { + "epoch": 3.12, + "learning_rate": 6.8843679101424484e-06, + "loss": 1.5808, + "step": 83770 + }, + { + "epoch": 3.12, + "learning_rate": 6.883995983188903e-06, + "loss": 1.7201, + "step": 83780 + }, + { + "epoch": 3.12, + "learning_rate": 6.883624056235356e-06, + "loss": 1.6251, + "step": 83790 + }, + { + "epoch": 3.12, + "learning_rate": 6.88325212928181e-06, + "loss": 1.7048, + "step": 83800 + }, + { + "epoch": 3.12, + "eval_loss": 1.6611318588256836, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.743, + "step": 83800 + }, + { + "epoch": 3.12, + "learning_rate": 6.882880202328264e-06, + "loss": 1.7069, + "step": 83810 + }, + { + "epoch": 3.12, + "learning_rate": 6.8825082753747174e-06, + "loss": 1.7788, + "step": 83820 + }, + { + "epoch": 3.12, + "learning_rate": 6.882136348421171e-06, + "loss": 1.58, + "step": 83830 + }, + { + "epoch": 3.12, + "learning_rate": 6.8817644214676235e-06, + "loss": 1.8258, + "step": 83840 + }, + { + "epoch": 3.12, + "learning_rate": 6.881392494514078e-06, + "loss": 1.6157, + "step": 83850 + }, + { + "epoch": 3.12, + "learning_rate": 6.881020567560531e-06, + "loss": 1.571, + "step": 83860 + }, + { + "epoch": 3.12, + "learning_rate": 6.880648640606985e-06, + "loss": 1.6159, + "step": 83870 + }, + { + "epoch": 3.12, + "learning_rate": 6.880276713653439e-06, + "loss": 1.8048, + "step": 83880 + }, + { + "epoch": 3.12, + "learning_rate": 6.8799047866998925e-06, + "loss": 1.7688, + "step": 83890 + }, + { + "epoch": 3.12, + "learning_rate": 6.879532859746346e-06, + "loss": 1.8327, + "step": 83900 + }, + { + "epoch": 3.12, + "eval_loss": 1.660470962524414, + "eval_runtime": 16.8222, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 83900 + }, + { + "epoch": 3.12, + "learning_rate": 6.8791609327928e-06, + "loss": 1.7963, + "step": 83910 + }, + { + "epoch": 3.12, + "learning_rate": 6.878789005839254e-06, + "loss": 1.6507, + "step": 83920 + }, + { + "epoch": 3.12, + "learning_rate": 6.878417078885707e-06, + "loss": 1.9183, + "step": 83930 + }, + { + "epoch": 3.12, + "learning_rate": 6.8780451519321615e-06, + "loss": 1.7181, + "step": 83940 + }, + { + "epoch": 3.12, + "learning_rate": 6.877673224978615e-06, + "loss": 1.8349, + "step": 83950 + }, + { + "epoch": 3.12, + "learning_rate": 6.877301298025068e-06, + "loss": 1.5668, + "step": 83960 + }, + { + "epoch": 3.12, + "learning_rate": 6.876929371071523e-06, + "loss": 1.6619, + "step": 83970 + }, + { + "epoch": 3.12, + "learning_rate": 6.876557444117976e-06, + "loss": 1.6936, + "step": 83980 + }, + { + "epoch": 3.12, + "learning_rate": 6.87618551716443e-06, + "loss": 1.6692, + "step": 83990 + }, + { + "epoch": 3.12, + "learning_rate": 6.875813590210884e-06, + "loss": 1.7213, + "step": 84000 + }, + { + "epoch": 3.12, + "eval_loss": 1.6606109142303467, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 84000 + }, + { + "epoch": 3.12, + "learning_rate": 6.875441663257337e-06, + "loss": 1.5315, + "step": 84010 + }, + { + "epoch": 3.12, + "learning_rate": 6.875069736303791e-06, + "loss": 1.7165, + "step": 84020 + }, + { + "epoch": 3.13, + "learning_rate": 6.8746978093502435e-06, + "loss": 1.6806, + "step": 84030 + }, + { + "epoch": 3.13, + "learning_rate": 6.874325882396698e-06, + "loss": 1.7468, + "step": 84040 + }, + { + "epoch": 3.13, + "learning_rate": 6.873953955443151e-06, + "loss": 1.7404, + "step": 84050 + }, + { + "epoch": 3.13, + "learning_rate": 6.873582028489605e-06, + "loss": 1.6518, + "step": 84060 + }, + { + "epoch": 3.13, + "learning_rate": 6.873210101536059e-06, + "loss": 1.7626, + "step": 84070 + }, + { + "epoch": 3.13, + "learning_rate": 6.8728381745825125e-06, + "loss": 1.6259, + "step": 84080 + }, + { + "epoch": 3.13, + "learning_rate": 6.872466247628966e-06, + "loss": 1.7486, + "step": 84090 + }, + { + "epoch": 3.13, + "learning_rate": 6.87209432067542e-06, + "loss": 1.7678, + "step": 84100 + }, + { + "epoch": 3.13, + "eval_loss": 1.6613649129867554, + "eval_runtime": 16.8367, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 84100 + }, + { + "epoch": 3.13, + "learning_rate": 6.871722393721874e-06, + "loss": 1.7116, + "step": 84110 + }, + { + "epoch": 3.13, + "learning_rate": 6.871350466768327e-06, + "loss": 1.6313, + "step": 84120 + }, + { + "epoch": 3.13, + "learning_rate": 6.870978539814781e-06, + "loss": 1.7243, + "step": 84130 + }, + { + "epoch": 3.13, + "learning_rate": 6.870606612861235e-06, + "loss": 1.6851, + "step": 84140 + }, + { + "epoch": 3.13, + "learning_rate": 6.870234685907688e-06, + "loss": 1.6952, + "step": 84150 + }, + { + "epoch": 3.13, + "learning_rate": 6.869862758954142e-06, + "loss": 1.6836, + "step": 84160 + }, + { + "epoch": 3.13, + "learning_rate": 6.869490832000596e-06, + "loss": 1.6635, + "step": 84170 + }, + { + "epoch": 3.13, + "learning_rate": 6.86911890504705e-06, + "loss": 1.7992, + "step": 84180 + }, + { + "epoch": 3.13, + "learning_rate": 6.868746978093503e-06, + "loss": 1.7381, + "step": 84190 + }, + { + "epoch": 3.13, + "learning_rate": 6.868375051139957e-06, + "loss": 1.7442, + "step": 84200 + }, + { + "epoch": 3.13, + "eval_loss": 1.6602673530578613, + "eval_runtime": 16.819, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 84200 + }, + { + "epoch": 3.13, + "learning_rate": 6.86800312418641e-06, + "loss": 1.602, + "step": 84210 + }, + { + "epoch": 3.13, + "learning_rate": 6.8676311972328634e-06, + "loss": 1.4783, + "step": 84220 + }, + { + "epoch": 3.13, + "learning_rate": 6.867259270279317e-06, + "loss": 1.6426, + "step": 84230 + }, + { + "epoch": 3.13, + "learning_rate": 6.866887343325771e-06, + "loss": 1.9118, + "step": 84240 + }, + { + "epoch": 3.13, + "learning_rate": 6.866515416372225e-06, + "loss": 1.6677, + "step": 84250 + }, + { + "epoch": 3.13, + "learning_rate": 6.866143489418678e-06, + "loss": 1.7218, + "step": 84260 + }, + { + "epoch": 3.13, + "learning_rate": 6.865771562465132e-06, + "loss": 1.7161, + "step": 84270 + }, + { + "epoch": 3.13, + "learning_rate": 6.865399635511586e-06, + "loss": 1.8118, + "step": 84280 + }, + { + "epoch": 3.13, + "learning_rate": 6.865027708558039e-06, + "loss": 1.7517, + "step": 84290 + }, + { + "epoch": 3.14, + "learning_rate": 6.864655781604494e-06, + "loss": 1.6861, + "step": 84300 + }, + { + "epoch": 3.14, + "eval_loss": 1.6602994203567505, + "eval_runtime": 16.8242, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 84300 + }, + { + "epoch": 3.14, + "learning_rate": 6.864283854650947e-06, + "loss": 1.6752, + "step": 84310 + }, + { + "epoch": 3.14, + "learning_rate": 6.8639119276974006e-06, + "loss": 1.5842, + "step": 84320 + }, + { + "epoch": 3.14, + "learning_rate": 6.863540000743855e-06, + "loss": 1.6704, + "step": 84330 + }, + { + "epoch": 3.14, + "learning_rate": 6.863168073790308e-06, + "loss": 1.7856, + "step": 84340 + }, + { + "epoch": 3.14, + "learning_rate": 6.862796146836762e-06, + "loss": 1.5573, + "step": 84350 + }, + { + "epoch": 3.14, + "learning_rate": 6.862424219883216e-06, + "loss": 1.7534, + "step": 84360 + }, + { + "epoch": 3.14, + "learning_rate": 6.8620522929296696e-06, + "loss": 1.6365, + "step": 84370 + }, + { + "epoch": 3.14, + "learning_rate": 6.861680365976123e-06, + "loss": 1.7059, + "step": 84380 + }, + { + "epoch": 3.14, + "learning_rate": 6.861308439022577e-06, + "loss": 1.6056, + "step": 84390 + }, + { + "epoch": 3.14, + "learning_rate": 6.86093651206903e-06, + "loss": 1.6473, + "step": 84400 + }, + { + "epoch": 3.14, + "eval_loss": 1.6609033346176147, + "eval_runtime": 16.8568, + "eval_samples_per_second": 59.323, + "eval_steps_per_second": 3.737, + "step": 84400 + }, + { + "epoch": 3.14, + "learning_rate": 6.860564585115483e-06, + "loss": 1.6908, + "step": 84410 + }, + { + "epoch": 3.14, + "learning_rate": 6.860192658161937e-06, + "loss": 1.7652, + "step": 84420 + }, + { + "epoch": 3.14, + "learning_rate": 6.859820731208391e-06, + "loss": 1.7524, + "step": 84430 + }, + { + "epoch": 3.14, + "learning_rate": 6.859448804254845e-06, + "loss": 1.693, + "step": 84440 + }, + { + "epoch": 3.14, + "learning_rate": 6.859076877301298e-06, + "loss": 1.5915, + "step": 84450 + }, + { + "epoch": 3.14, + "learning_rate": 6.858704950347752e-06, + "loss": 1.6383, + "step": 84460 + }, + { + "epoch": 3.14, + "learning_rate": 6.858333023394206e-06, + "loss": 1.7978, + "step": 84470 + }, + { + "epoch": 3.14, + "learning_rate": 6.857961096440659e-06, + "loss": 1.8015, + "step": 84480 + }, + { + "epoch": 3.14, + "learning_rate": 6.857589169487114e-06, + "loss": 1.6734, + "step": 84490 + }, + { + "epoch": 3.14, + "learning_rate": 6.857217242533567e-06, + "loss": 1.6413, + "step": 84500 + }, + { + "epoch": 3.14, + "eval_loss": 1.662477731704712, + "eval_runtime": 16.8372, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 84500 + }, + { + "epoch": 3.14, + "learning_rate": 6.8568453155800205e-06, + "loss": 1.6407, + "step": 84510 + }, + { + "epoch": 3.14, + "learning_rate": 6.856473388626475e-06, + "loss": 1.6974, + "step": 84520 + }, + { + "epoch": 3.14, + "learning_rate": 6.856101461672928e-06, + "loss": 1.7205, + "step": 84530 + }, + { + "epoch": 3.14, + "learning_rate": 6.855729534719382e-06, + "loss": 1.6866, + "step": 84540 + }, + { + "epoch": 3.14, + "learning_rate": 6.855357607765836e-06, + "loss": 1.5369, + "step": 84550 + }, + { + "epoch": 3.15, + "learning_rate": 6.8549856808122895e-06, + "loss": 1.8141, + "step": 84560 + }, + { + "epoch": 3.15, + "learning_rate": 6.854613753858743e-06, + "loss": 1.7513, + "step": 84570 + }, + { + "epoch": 3.15, + "learning_rate": 6.854241826905197e-06, + "loss": 1.6465, + "step": 84580 + }, + { + "epoch": 3.15, + "learning_rate": 6.85386989995165e-06, + "loss": 1.6226, + "step": 84590 + }, + { + "epoch": 3.15, + "learning_rate": 6.853497972998103e-06, + "loss": 1.6406, + "step": 84600 + }, + { + "epoch": 3.15, + "eval_loss": 1.6604019403457642, + "eval_runtime": 16.8458, + "eval_samples_per_second": 59.362, + "eval_steps_per_second": 3.74, + "step": 84600 + }, + { + "epoch": 3.15, + "learning_rate": 6.853126046044557e-06, + "loss": 1.6568, + "step": 84610 + }, + { + "epoch": 3.15, + "learning_rate": 6.852754119091011e-06, + "loss": 1.6739, + "step": 84620 + }, + { + "epoch": 3.15, + "learning_rate": 6.8523821921374646e-06, + "loss": 1.5592, + "step": 84630 + }, + { + "epoch": 3.15, + "learning_rate": 6.852010265183918e-06, + "loss": 1.639, + "step": 84640 + }, + { + "epoch": 3.15, + "learning_rate": 6.851638338230372e-06, + "loss": 1.632, + "step": 84650 + }, + { + "epoch": 3.15, + "learning_rate": 6.851266411276826e-06, + "loss": 1.6422, + "step": 84660 + }, + { + "epoch": 3.15, + "learning_rate": 6.850894484323279e-06, + "loss": 1.5943, + "step": 84670 + }, + { + "epoch": 3.15, + "learning_rate": 6.8505225573697336e-06, + "loss": 1.7236, + "step": 84680 + }, + { + "epoch": 3.15, + "learning_rate": 6.850150630416187e-06, + "loss": 1.702, + "step": 84690 + }, + { + "epoch": 3.15, + "learning_rate": 6.8497787034626405e-06, + "loss": 1.7184, + "step": 84700 + }, + { + "epoch": 3.15, + "eval_loss": 1.6608953475952148, + "eval_runtime": 16.8675, + "eval_samples_per_second": 59.286, + "eval_steps_per_second": 3.735, + "step": 84700 + }, + { + "epoch": 3.15, + "learning_rate": 6.849406776509094e-06, + "loss": 1.7265, + "step": 84710 + }, + { + "epoch": 3.15, + "learning_rate": 6.849034849555548e-06, + "loss": 1.7832, + "step": 84720 + }, + { + "epoch": 3.15, + "learning_rate": 6.848662922602002e-06, + "loss": 1.9041, + "step": 84730 + }, + { + "epoch": 3.15, + "learning_rate": 6.848290995648455e-06, + "loss": 1.7525, + "step": 84740 + }, + { + "epoch": 3.15, + "learning_rate": 6.8479190686949095e-06, + "loss": 1.7065, + "step": 84750 + }, + { + "epoch": 3.15, + "learning_rate": 6.847547141741363e-06, + "loss": 1.7373, + "step": 84760 + }, + { + "epoch": 3.15, + "learning_rate": 6.847175214787816e-06, + "loss": 1.6802, + "step": 84770 + }, + { + "epoch": 3.15, + "learning_rate": 6.846803287834269e-06, + "loss": 1.6783, + "step": 84780 + }, + { + "epoch": 3.15, + "learning_rate": 6.846431360880723e-06, + "loss": 1.7109, + "step": 84790 + }, + { + "epoch": 3.15, + "learning_rate": 6.846059433927177e-06, + "loss": 1.8216, + "step": 84800 + }, + { + "epoch": 3.15, + "eval_loss": 1.6602460145950317, + "eval_runtime": 16.8491, + "eval_samples_per_second": 59.351, + "eval_steps_per_second": 3.739, + "step": 84800 + }, + { + "epoch": 3.15, + "learning_rate": 6.84568750697363e-06, + "loss": 1.7214, + "step": 84810 + }, + { + "epoch": 3.15, + "learning_rate": 6.8453155800200845e-06, + "loss": 1.6929, + "step": 84820 + }, + { + "epoch": 3.16, + "learning_rate": 6.844943653066538e-06, + "loss": 1.645, + "step": 84830 + }, + { + "epoch": 3.16, + "learning_rate": 6.8445717261129914e-06, + "loss": 1.6737, + "step": 84840 + }, + { + "epoch": 3.16, + "learning_rate": 6.844199799159446e-06, + "loss": 1.6468, + "step": 84850 + }, + { + "epoch": 3.16, + "learning_rate": 6.843827872205899e-06, + "loss": 1.8, + "step": 84860 + }, + { + "epoch": 3.16, + "learning_rate": 6.843455945252353e-06, + "loss": 1.6405, + "step": 84870 + }, + { + "epoch": 3.16, + "learning_rate": 6.843084018298807e-06, + "loss": 1.664, + "step": 84880 + }, + { + "epoch": 3.16, + "learning_rate": 6.8427120913452604e-06, + "loss": 1.819, + "step": 84890 + }, + { + "epoch": 3.16, + "learning_rate": 6.842340164391714e-06, + "loss": 1.7552, + "step": 84900 + }, + { + "epoch": 3.16, + "eval_loss": 1.6591167449951172, + "eval_runtime": 16.8223, + "eval_samples_per_second": 59.445, + "eval_steps_per_second": 3.745, + "step": 84900 + }, + { + "epoch": 3.16, + "learning_rate": 6.841968237438168e-06, + "loss": 1.8674, + "step": 84910 + }, + { + "epoch": 3.16, + "learning_rate": 6.841596310484622e-06, + "loss": 1.7171, + "step": 84920 + }, + { + "epoch": 3.16, + "learning_rate": 6.841224383531075e-06, + "loss": 1.7088, + "step": 84930 + }, + { + "epoch": 3.16, + "learning_rate": 6.8408524565775294e-06, + "loss": 1.7767, + "step": 84940 + }, + { + "epoch": 3.16, + "learning_rate": 6.840480529623983e-06, + "loss": 1.7809, + "step": 84950 + }, + { + "epoch": 3.16, + "learning_rate": 6.840108602670436e-06, + "loss": 1.7124, + "step": 84960 + }, + { + "epoch": 3.16, + "learning_rate": 6.839736675716889e-06, + "loss": 1.653, + "step": 84970 + }, + { + "epoch": 3.16, + "learning_rate": 6.839364748763343e-06, + "loss": 1.7123, + "step": 84980 + }, + { + "epoch": 3.16, + "learning_rate": 6.838992821809797e-06, + "loss": 1.6584, + "step": 84990 + }, + { + "epoch": 3.16, + "learning_rate": 6.83862089485625e-06, + "loss": 1.7048, + "step": 85000 + }, + { + "epoch": 3.16, + "eval_loss": 1.6592129468917847, + "eval_runtime": 16.8423, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 85000 + }, + { + "epoch": 3.16, + "learning_rate": 6.8382489679027045e-06, + "loss": 1.6416, + "step": 85010 + }, + { + "epoch": 3.16, + "learning_rate": 6.837877040949158e-06, + "loss": 1.7981, + "step": 85020 + }, + { + "epoch": 3.16, + "learning_rate": 6.837505113995611e-06, + "loss": 1.6945, + "step": 85030 + }, + { + "epoch": 3.16, + "learning_rate": 6.837133187042066e-06, + "loss": 1.6437, + "step": 85040 + }, + { + "epoch": 3.16, + "learning_rate": 6.836761260088519e-06, + "loss": 1.5606, + "step": 85050 + }, + { + "epoch": 3.16, + "learning_rate": 6.836389333134973e-06, + "loss": 1.8, + "step": 85060 + }, + { + "epoch": 3.16, + "learning_rate": 6.836017406181427e-06, + "loss": 1.615, + "step": 85070 + }, + { + "epoch": 3.16, + "learning_rate": 6.83564547922788e-06, + "loss": 1.5675, + "step": 85080 + }, + { + "epoch": 3.16, + "learning_rate": 6.835273552274334e-06, + "loss": 1.578, + "step": 85090 + }, + { + "epoch": 3.17, + "learning_rate": 6.834901625320788e-06, + "loss": 1.6397, + "step": 85100 + }, + { + "epoch": 3.17, + "eval_loss": 1.6598014831542969, + "eval_runtime": 16.8307, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 85100 + }, + { + "epoch": 3.17, + "learning_rate": 6.834529698367242e-06, + "loss": 1.66, + "step": 85110 + }, + { + "epoch": 3.17, + "learning_rate": 6.834157771413695e-06, + "loss": 1.8386, + "step": 85120 + }, + { + "epoch": 3.17, + "learning_rate": 6.833785844460149e-06, + "loss": 1.6676, + "step": 85130 + }, + { + "epoch": 3.17, + "learning_rate": 6.833413917506603e-06, + "loss": 1.729, + "step": 85140 + }, + { + "epoch": 3.17, + "learning_rate": 6.8330419905530555e-06, + "loss": 1.8151, + "step": 85150 + }, + { + "epoch": 3.17, + "learning_rate": 6.832670063599509e-06, + "loss": 1.6727, + "step": 85160 + }, + { + "epoch": 3.17, + "learning_rate": 6.832298136645963e-06, + "loss": 1.7214, + "step": 85170 + }, + { + "epoch": 3.17, + "learning_rate": 6.831926209692417e-06, + "loss": 1.7581, + "step": 85180 + }, + { + "epoch": 3.17, + "learning_rate": 6.83155428273887e-06, + "loss": 1.5779, + "step": 85190 + }, + { + "epoch": 3.17, + "learning_rate": 6.8311823557853244e-06, + "loss": 1.7953, + "step": 85200 + }, + { + "epoch": 3.17, + "eval_loss": 1.6597414016723633, + "eval_runtime": 16.8304, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 85200 + }, + { + "epoch": 3.17, + "learning_rate": 6.830810428831778e-06, + "loss": 1.8097, + "step": 85210 + }, + { + "epoch": 3.17, + "learning_rate": 6.830438501878231e-06, + "loss": 1.6218, + "step": 85220 + }, + { + "epoch": 3.17, + "learning_rate": 6.830066574924686e-06, + "loss": 1.6773, + "step": 85230 + }, + { + "epoch": 3.17, + "learning_rate": 6.829694647971139e-06, + "loss": 1.6752, + "step": 85240 + }, + { + "epoch": 3.17, + "learning_rate": 6.829322721017593e-06, + "loss": 1.7047, + "step": 85250 + }, + { + "epoch": 3.17, + "learning_rate": 6.828950794064047e-06, + "loss": 1.7754, + "step": 85260 + }, + { + "epoch": 3.17, + "learning_rate": 6.8285788671105e-06, + "loss": 1.6661, + "step": 85270 + }, + { + "epoch": 3.17, + "learning_rate": 6.828206940156954e-06, + "loss": 1.7389, + "step": 85280 + }, + { + "epoch": 3.17, + "learning_rate": 6.827835013203407e-06, + "loss": 1.5655, + "step": 85290 + }, + { + "epoch": 3.17, + "learning_rate": 6.827463086249862e-06, + "loss": 1.7162, + "step": 85300 + }, + { + "epoch": 3.17, + "eval_loss": 1.6591233015060425, + "eval_runtime": 16.8408, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 85300 + }, + { + "epoch": 3.17, + "learning_rate": 6.827091159296315e-06, + "loss": 1.6697, + "step": 85310 + }, + { + "epoch": 3.17, + "learning_rate": 6.8267192323427685e-06, + "loss": 1.5513, + "step": 85320 + }, + { + "epoch": 3.17, + "learning_rate": 6.826347305389223e-06, + "loss": 1.6026, + "step": 85330 + }, + { + "epoch": 3.17, + "learning_rate": 6.825975378435675e-06, + "loss": 1.6486, + "step": 85340 + }, + { + "epoch": 3.17, + "learning_rate": 6.825603451482129e-06, + "loss": 1.7845, + "step": 85350 + }, + { + "epoch": 3.17, + "learning_rate": 6.825231524528582e-06, + "loss": 1.6476, + "step": 85360 + }, + { + "epoch": 3.18, + "learning_rate": 6.824859597575037e-06, + "loss": 1.7096, + "step": 85370 + }, + { + "epoch": 3.18, + "learning_rate": 6.82448767062149e-06, + "loss": 1.6655, + "step": 85380 + }, + { + "epoch": 3.18, + "learning_rate": 6.8241157436679436e-06, + "loss": 1.7689, + "step": 85390 + }, + { + "epoch": 3.18, + "learning_rate": 6.823743816714398e-06, + "loss": 1.887, + "step": 85400 + }, + { + "epoch": 3.18, + "eval_loss": 1.65925133228302, + "eval_runtime": 16.8332, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 85400 + }, + { + "epoch": 3.18, + "learning_rate": 6.823371889760851e-06, + "loss": 1.7504, + "step": 85410 + }, + { + "epoch": 3.18, + "learning_rate": 6.822999962807305e-06, + "loss": 1.6961, + "step": 85420 + }, + { + "epoch": 3.18, + "learning_rate": 6.822628035853759e-06, + "loss": 1.6614, + "step": 85430 + }, + { + "epoch": 3.18, + "learning_rate": 6.8222561089002125e-06, + "loss": 1.7135, + "step": 85440 + }, + { + "epoch": 3.18, + "learning_rate": 6.821884181946666e-06, + "loss": 1.6587, + "step": 85450 + }, + { + "epoch": 3.18, + "learning_rate": 6.82151225499312e-06, + "loss": 1.7419, + "step": 85460 + }, + { + "epoch": 3.18, + "learning_rate": 6.821140328039574e-06, + "loss": 1.622, + "step": 85470 + }, + { + "epoch": 3.18, + "learning_rate": 6.820768401086027e-06, + "loss": 1.7059, + "step": 85480 + }, + { + "epoch": 3.18, + "learning_rate": 6.8203964741324815e-06, + "loss": 1.7546, + "step": 85490 + }, + { + "epoch": 3.18, + "learning_rate": 6.820024547178935e-06, + "loss": 1.7218, + "step": 85500 + }, + { + "epoch": 3.18, + "eval_loss": 1.659637451171875, + "eval_runtime": 16.8256, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 85500 + }, + { + "epoch": 3.18, + "learning_rate": 6.8196526202253885e-06, + "loss": 1.6651, + "step": 85510 + }, + { + "epoch": 3.18, + "learning_rate": 6.819280693271843e-06, + "loss": 1.5835, + "step": 85520 + }, + { + "epoch": 3.18, + "learning_rate": 6.818908766318295e-06, + "loss": 1.6932, + "step": 85530 + }, + { + "epoch": 3.18, + "learning_rate": 6.818536839364749e-06, + "loss": 1.7815, + "step": 85540 + }, + { + "epoch": 3.18, + "learning_rate": 6.818164912411202e-06, + "loss": 1.5818, + "step": 85550 + }, + { + "epoch": 3.18, + "learning_rate": 6.817792985457657e-06, + "loss": 1.7104, + "step": 85560 + }, + { + "epoch": 3.18, + "learning_rate": 6.81742105850411e-06, + "loss": 1.7605, + "step": 85570 + }, + { + "epoch": 3.18, + "learning_rate": 6.8170491315505635e-06, + "loss": 1.6878, + "step": 85580 + }, + { + "epoch": 3.18, + "learning_rate": 6.816677204597018e-06, + "loss": 1.8598, + "step": 85590 + }, + { + "epoch": 3.18, + "learning_rate": 6.816305277643471e-06, + "loss": 1.7055, + "step": 85600 + }, + { + "epoch": 3.18, + "eval_loss": 1.6582907438278198, + "eval_runtime": 16.8146, + "eval_samples_per_second": 59.472, + "eval_steps_per_second": 3.747, + "step": 85600 + }, + { + "epoch": 3.18, + "learning_rate": 6.815933350689925e-06, + "loss": 1.6163, + "step": 85610 + }, + { + "epoch": 3.18, + "learning_rate": 6.815561423736379e-06, + "loss": 1.6927, + "step": 85620 + }, + { + "epoch": 3.18, + "learning_rate": 6.8151894967828325e-06, + "loss": 1.7391, + "step": 85630 + }, + { + "epoch": 3.19, + "learning_rate": 6.814817569829286e-06, + "loss": 1.8545, + "step": 85640 + }, + { + "epoch": 3.19, + "learning_rate": 6.81444564287574e-06, + "loss": 1.6806, + "step": 85650 + }, + { + "epoch": 3.19, + "learning_rate": 6.814073715922194e-06, + "loss": 1.6831, + "step": 85660 + }, + { + "epoch": 3.19, + "learning_rate": 6.813701788968647e-06, + "loss": 1.7217, + "step": 85670 + }, + { + "epoch": 3.19, + "learning_rate": 6.8133298620151015e-06, + "loss": 1.7545, + "step": 85680 + }, + { + "epoch": 3.19, + "learning_rate": 6.812957935061555e-06, + "loss": 1.6649, + "step": 85690 + }, + { + "epoch": 3.19, + "learning_rate": 6.812586008108008e-06, + "loss": 1.678, + "step": 85700 + }, + { + "epoch": 3.19, + "eval_loss": 1.659928798675537, + "eval_runtime": 16.8348, + "eval_samples_per_second": 59.401, + "eval_steps_per_second": 3.742, + "step": 85700 + }, + { + "epoch": 3.19, + "learning_rate": 6.812214081154463e-06, + "loss": 1.7993, + "step": 85710 + }, + { + "epoch": 3.19, + "learning_rate": 6.811842154200915e-06, + "loss": 1.7024, + "step": 85720 + }, + { + "epoch": 3.19, + "learning_rate": 6.811470227247369e-06, + "loss": 1.562, + "step": 85730 + }, + { + "epoch": 3.19, + "learning_rate": 6.811098300293822e-06, + "loss": 1.7209, + "step": 85740 + }, + { + "epoch": 3.19, + "learning_rate": 6.8107263733402766e-06, + "loss": 1.848, + "step": 85750 + }, + { + "epoch": 3.19, + "learning_rate": 6.81035444638673e-06, + "loss": 1.7674, + "step": 85760 + }, + { + "epoch": 3.19, + "learning_rate": 6.8099825194331835e-06, + "loss": 1.7955, + "step": 85770 + }, + { + "epoch": 3.19, + "learning_rate": 6.809610592479638e-06, + "loss": 1.7588, + "step": 85780 + }, + { + "epoch": 3.19, + "learning_rate": 6.809238665526091e-06, + "loss": 1.6976, + "step": 85790 + }, + { + "epoch": 3.19, + "learning_rate": 6.808866738572545e-06, + "loss": 1.6354, + "step": 85800 + }, + { + "epoch": 3.19, + "eval_loss": 1.6602256298065186, + "eval_runtime": 16.8417, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 85800 + }, + { + "epoch": 3.19, + "learning_rate": 6.808494811618999e-06, + "loss": 1.751, + "step": 85810 + }, + { + "epoch": 3.19, + "learning_rate": 6.8081228846654525e-06, + "loss": 1.7332, + "step": 85820 + }, + { + "epoch": 3.19, + "learning_rate": 6.807750957711906e-06, + "loss": 1.6207, + "step": 85830 + }, + { + "epoch": 3.19, + "learning_rate": 6.80737903075836e-06, + "loss": 1.7001, + "step": 85840 + }, + { + "epoch": 3.19, + "learning_rate": 6.807007103804814e-06, + "loss": 1.6231, + "step": 85850 + }, + { + "epoch": 3.19, + "learning_rate": 6.806635176851267e-06, + "loss": 1.7285, + "step": 85860 + }, + { + "epoch": 3.19, + "learning_rate": 6.806263249897721e-06, + "loss": 1.6887, + "step": 85870 + }, + { + "epoch": 3.19, + "learning_rate": 6.805891322944175e-06, + "loss": 1.5847, + "step": 85880 + }, + { + "epoch": 3.19, + "learning_rate": 6.805519395990628e-06, + "loss": 1.6928, + "step": 85890 + }, + { + "epoch": 3.19, + "learning_rate": 6.805147469037081e-06, + "loss": 1.7818, + "step": 85900 + }, + { + "epoch": 3.19, + "eval_loss": 1.6585074663162231, + "eval_runtime": 16.8427, + "eval_samples_per_second": 59.373, + "eval_steps_per_second": 3.74, + "step": 85900 + }, + { + "epoch": 3.2, + "learning_rate": 6.8047755420835344e-06, + "loss": 1.6951, + "step": 85910 + }, + { + "epoch": 3.2, + "learning_rate": 6.804403615129989e-06, + "loss": 1.7362, + "step": 85920 + }, + { + "epoch": 3.2, + "learning_rate": 6.804031688176442e-06, + "loss": 1.7895, + "step": 85930 + }, + { + "epoch": 3.2, + "learning_rate": 6.803659761222896e-06, + "loss": 1.6043, + "step": 85940 + }, + { + "epoch": 3.2, + "learning_rate": 6.80328783426935e-06, + "loss": 1.6735, + "step": 85950 + }, + { + "epoch": 3.2, + "learning_rate": 6.8029159073158034e-06, + "loss": 1.621, + "step": 85960 + }, + { + "epoch": 3.2, + "learning_rate": 6.802543980362257e-06, + "loss": 1.847, + "step": 85970 + }, + { + "epoch": 3.2, + "learning_rate": 6.802172053408711e-06, + "loss": 1.7151, + "step": 85980 + }, + { + "epoch": 3.2, + "learning_rate": 6.801800126455165e-06, + "loss": 1.6143, + "step": 85990 + }, + { + "epoch": 3.2, + "learning_rate": 6.801428199501618e-06, + "loss": 1.7299, + "step": 86000 + }, + { + "epoch": 3.2, + "eval_loss": 1.6590685844421387, + "eval_runtime": 16.843, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 86000 + }, + { + "epoch": 3.2, + "learning_rate": 6.8010562725480724e-06, + "loss": 1.6651, + "step": 86010 + }, + { + "epoch": 3.2, + "learning_rate": 6.800684345594526e-06, + "loss": 1.7471, + "step": 86020 + }, + { + "epoch": 3.2, + "learning_rate": 6.800312418640979e-06, + "loss": 1.799, + "step": 86030 + }, + { + "epoch": 3.2, + "learning_rate": 6.799940491687434e-06, + "loss": 1.6248, + "step": 86040 + }, + { + "epoch": 3.2, + "learning_rate": 6.799568564733887e-06, + "loss": 1.8435, + "step": 86050 + }, + { + "epoch": 3.2, + "learning_rate": 6.7991966377803406e-06, + "loss": 1.6855, + "step": 86060 + }, + { + "epoch": 3.2, + "learning_rate": 6.798824710826795e-06, + "loss": 1.8459, + "step": 86070 + }, + { + "epoch": 3.2, + "learning_rate": 6.798452783873248e-06, + "loss": 1.8829, + "step": 86080 + }, + { + "epoch": 3.2, + "learning_rate": 6.798080856919701e-06, + "loss": 1.6752, + "step": 86090 + }, + { + "epoch": 3.2, + "learning_rate": 6.797708929966154e-06, + "loss": 1.6765, + "step": 86100 + }, + { + "epoch": 3.2, + "eval_loss": 1.6590315103530884, + "eval_runtime": 16.8449, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 86100 + }, + { + "epoch": 3.2, + "learning_rate": 6.797337003012609e-06, + "loss": 1.7817, + "step": 86110 + }, + { + "epoch": 3.2, + "learning_rate": 6.796965076059062e-06, + "loss": 1.6612, + "step": 86120 + }, + { + "epoch": 3.2, + "learning_rate": 6.796593149105516e-06, + "loss": 1.5831, + "step": 86130 + }, + { + "epoch": 3.2, + "learning_rate": 6.79622122215197e-06, + "loss": 1.7031, + "step": 86140 + }, + { + "epoch": 3.2, + "learning_rate": 6.795849295198423e-06, + "loss": 1.7338, + "step": 86150 + }, + { + "epoch": 3.2, + "learning_rate": 6.795477368244877e-06, + "loss": 1.7622, + "step": 86160 + }, + { + "epoch": 3.2, + "learning_rate": 6.795105441291331e-06, + "loss": 1.7237, + "step": 86170 + }, + { + "epoch": 3.21, + "learning_rate": 6.794733514337785e-06, + "loss": 1.7478, + "step": 86180 + }, + { + "epoch": 3.21, + "learning_rate": 6.794361587384238e-06, + "loss": 1.6905, + "step": 86190 + }, + { + "epoch": 3.21, + "learning_rate": 6.793989660430692e-06, + "loss": 1.7332, + "step": 86200 + }, + { + "epoch": 3.21, + "eval_loss": 1.6594070196151733, + "eval_runtime": 16.8358, + "eval_samples_per_second": 59.397, + "eval_steps_per_second": 3.742, + "step": 86200 + }, + { + "epoch": 3.21, + "learning_rate": 6.793617733477146e-06, + "loss": 1.714, + "step": 86210 + }, + { + "epoch": 3.21, + "learning_rate": 6.793245806523599e-06, + "loss": 1.71, + "step": 86220 + }, + { + "epoch": 3.21, + "learning_rate": 6.792873879570054e-06, + "loss": 1.7777, + "step": 86230 + }, + { + "epoch": 3.21, + "learning_rate": 6.792501952616507e-06, + "loss": 1.7776, + "step": 86240 + }, + { + "epoch": 3.21, + "learning_rate": 6.7921300256629605e-06, + "loss": 1.6854, + "step": 86250 + }, + { + "epoch": 3.21, + "learning_rate": 6.791758098709415e-06, + "loss": 1.9166, + "step": 86260 + }, + { + "epoch": 3.21, + "learning_rate": 6.791386171755868e-06, + "loss": 1.6141, + "step": 86270 + }, + { + "epoch": 3.21, + "learning_rate": 6.791014244802321e-06, + "loss": 1.7689, + "step": 86280 + }, + { + "epoch": 3.21, + "learning_rate": 6.790642317848774e-06, + "loss": 1.6501, + "step": 86290 + }, + { + "epoch": 3.21, + "learning_rate": 6.790270390895229e-06, + "loss": 1.7097, + "step": 86300 + }, + { + "epoch": 3.21, + "eval_loss": 1.6590324640274048, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 86300 + }, + { + "epoch": 3.21, + "learning_rate": 6.789898463941682e-06, + "loss": 1.7098, + "step": 86310 + }, + { + "epoch": 3.21, + "learning_rate": 6.789526536988136e-06, + "loss": 1.6776, + "step": 86320 + }, + { + "epoch": 3.21, + "learning_rate": 6.78915461003459e-06, + "loss": 1.6933, + "step": 86330 + }, + { + "epoch": 3.21, + "learning_rate": 6.788782683081043e-06, + "loss": 1.7896, + "step": 86340 + }, + { + "epoch": 3.21, + "learning_rate": 6.788410756127497e-06, + "loss": 1.8568, + "step": 86350 + }, + { + "epoch": 3.21, + "learning_rate": 6.788038829173951e-06, + "loss": 1.7553, + "step": 86360 + }, + { + "epoch": 3.21, + "learning_rate": 6.787666902220405e-06, + "loss": 1.6945, + "step": 86370 + }, + { + "epoch": 3.21, + "learning_rate": 6.787294975266858e-06, + "loss": 1.6897, + "step": 86380 + }, + { + "epoch": 3.21, + "learning_rate": 6.786923048313312e-06, + "loss": 1.8455, + "step": 86390 + }, + { + "epoch": 3.21, + "learning_rate": 6.786551121359766e-06, + "loss": 1.7654, + "step": 86400 + }, + { + "epoch": 3.21, + "eval_loss": 1.6585907936096191, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.403, + "eval_steps_per_second": 3.742, + "step": 86400 + }, + { + "epoch": 3.21, + "learning_rate": 6.786179194406219e-06, + "loss": 1.6176, + "step": 86410 + }, + { + "epoch": 3.21, + "learning_rate": 6.7858072674526736e-06, + "loss": 1.8268, + "step": 86420 + }, + { + "epoch": 3.21, + "learning_rate": 6.785435340499127e-06, + "loss": 1.7499, + "step": 86430 + }, + { + "epoch": 3.21, + "learning_rate": 6.7850634135455805e-06, + "loss": 1.7578, + "step": 86440 + }, + { + "epoch": 3.22, + "learning_rate": 6.784691486592034e-06, + "loss": 1.7347, + "step": 86450 + }, + { + "epoch": 3.22, + "learning_rate": 6.784319559638488e-06, + "loss": 1.6248, + "step": 86460 + }, + { + "epoch": 3.22, + "learning_rate": 6.783947632684941e-06, + "loss": 1.7535, + "step": 86470 + }, + { + "epoch": 3.22, + "learning_rate": 6.783575705731394e-06, + "loss": 1.7963, + "step": 86480 + }, + { + "epoch": 3.22, + "learning_rate": 6.783203778777848e-06, + "loss": 1.7221, + "step": 86490 + }, + { + "epoch": 3.22, + "learning_rate": 6.782831851824302e-06, + "loss": 1.6512, + "step": 86500 + }, + { + "epoch": 3.22, + "eval_loss": 1.6578327417373657, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 86500 + }, + { + "epoch": 3.22, + "learning_rate": 6.7824599248707555e-06, + "loss": 1.6375, + "step": 86510 + }, + { + "epoch": 3.22, + "learning_rate": 6.782087997917209e-06, + "loss": 1.7112, + "step": 86520 + }, + { + "epoch": 3.22, + "learning_rate": 6.781716070963663e-06, + "loss": 1.7203, + "step": 86530 + }, + { + "epoch": 3.22, + "learning_rate": 6.781344144010117e-06, + "loss": 1.6239, + "step": 86540 + }, + { + "epoch": 3.22, + "learning_rate": 6.78097221705657e-06, + "loss": 1.6581, + "step": 86550 + }, + { + "epoch": 3.22, + "learning_rate": 6.7806002901030245e-06, + "loss": 1.7343, + "step": 86560 + }, + { + "epoch": 3.22, + "learning_rate": 6.780228363149478e-06, + "loss": 1.6615, + "step": 86570 + }, + { + "epoch": 3.22, + "learning_rate": 6.7798564361959315e-06, + "loss": 1.6713, + "step": 86580 + }, + { + "epoch": 3.22, + "learning_rate": 6.779484509242386e-06, + "loss": 1.7497, + "step": 86590 + }, + { + "epoch": 3.22, + "learning_rate": 6.779112582288839e-06, + "loss": 1.733, + "step": 86600 + }, + { + "epoch": 3.22, + "eval_loss": 1.658341884613037, + "eval_runtime": 16.827, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 86600 + }, + { + "epoch": 3.22, + "learning_rate": 6.778740655335293e-06, + "loss": 1.6452, + "step": 86610 + }, + { + "epoch": 3.22, + "learning_rate": 6.778368728381747e-06, + "loss": 1.6912, + "step": 86620 + }, + { + "epoch": 3.22, + "learning_rate": 6.7779968014282004e-06, + "loss": 1.721, + "step": 86630 + }, + { + "epoch": 3.22, + "learning_rate": 6.777624874474654e-06, + "loss": 1.623, + "step": 86640 + }, + { + "epoch": 3.22, + "learning_rate": 6.777252947521108e-06, + "loss": 1.6886, + "step": 86650 + }, + { + "epoch": 3.22, + "learning_rate": 6.776881020567561e-06, + "loss": 1.7636, + "step": 86660 + }, + { + "epoch": 3.22, + "learning_rate": 6.776509093614014e-06, + "loss": 1.6887, + "step": 86670 + }, + { + "epoch": 3.22, + "learning_rate": 6.776137166660468e-06, + "loss": 1.581, + "step": 86680 + }, + { + "epoch": 3.22, + "learning_rate": 6.775765239706922e-06, + "loss": 1.7031, + "step": 86690 + }, + { + "epoch": 3.22, + "learning_rate": 6.7753933127533755e-06, + "loss": 1.6728, + "step": 86700 + }, + { + "epoch": 3.22, + "eval_loss": 1.658492922782898, + "eval_runtime": 16.8497, + "eval_samples_per_second": 59.348, + "eval_steps_per_second": 3.739, + "step": 86700 + }, + { + "epoch": 3.22, + "learning_rate": 6.775021385799829e-06, + "loss": 1.6057, + "step": 86710 + }, + { + "epoch": 3.23, + "learning_rate": 6.774649458846283e-06, + "loss": 1.7756, + "step": 86720 + }, + { + "epoch": 3.23, + "learning_rate": 6.774277531892737e-06, + "loss": 1.713, + "step": 86730 + }, + { + "epoch": 3.23, + "learning_rate": 6.77390560493919e-06, + "loss": 1.7458, + "step": 86740 + }, + { + "epoch": 3.23, + "learning_rate": 6.7735336779856445e-06, + "loss": 1.6827, + "step": 86750 + }, + { + "epoch": 3.23, + "learning_rate": 6.773161751032098e-06, + "loss": 1.6724, + "step": 86760 + }, + { + "epoch": 3.23, + "learning_rate": 6.772789824078551e-06, + "loss": 1.6882, + "step": 86770 + }, + { + "epoch": 3.23, + "learning_rate": 6.772417897125006e-06, + "loss": 1.7643, + "step": 86780 + }, + { + "epoch": 3.23, + "learning_rate": 6.772045970171459e-06, + "loss": 1.77, + "step": 86790 + }, + { + "epoch": 3.23, + "learning_rate": 6.771674043217913e-06, + "loss": 1.6585, + "step": 86800 + }, + { + "epoch": 3.23, + "eval_loss": 1.6579554080963135, + "eval_runtime": 16.8425, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 86800 + }, + { + "epoch": 3.23, + "learning_rate": 6.771302116264367e-06, + "loss": 1.7417, + "step": 86810 + }, + { + "epoch": 3.23, + "learning_rate": 6.77093018931082e-06, + "loss": 1.8063, + "step": 86820 + }, + { + "epoch": 3.23, + "learning_rate": 6.770558262357274e-06, + "loss": 1.6583, + "step": 86830 + }, + { + "epoch": 3.23, + "learning_rate": 6.7701863354037265e-06, + "loss": 1.7323, + "step": 86840 + }, + { + "epoch": 3.23, + "learning_rate": 6.769814408450181e-06, + "loss": 1.6229, + "step": 86850 + }, + { + "epoch": 3.23, + "learning_rate": 6.769442481496634e-06, + "loss": 1.6959, + "step": 86860 + }, + { + "epoch": 3.23, + "learning_rate": 6.769070554543088e-06, + "loss": 1.8381, + "step": 86870 + }, + { + "epoch": 3.23, + "learning_rate": 6.768698627589542e-06, + "loss": 1.6731, + "step": 86880 + }, + { + "epoch": 3.23, + "learning_rate": 6.7683267006359955e-06, + "loss": 1.6728, + "step": 86890 + }, + { + "epoch": 3.23, + "learning_rate": 6.767954773682449e-06, + "loss": 1.6597, + "step": 86900 + }, + { + "epoch": 3.23, + "eval_loss": 1.6579291820526123, + "eval_runtime": 16.8398, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 86900 + }, + { + "epoch": 3.23, + "learning_rate": 6.767582846728903e-06, + "loss": 1.6059, + "step": 86910 + }, + { + "epoch": 3.23, + "learning_rate": 6.767210919775357e-06, + "loss": 1.6658, + "step": 86920 + }, + { + "epoch": 3.23, + "learning_rate": 6.76683899282181e-06, + "loss": 1.8005, + "step": 86930 + }, + { + "epoch": 3.23, + "learning_rate": 6.7664670658682645e-06, + "loss": 1.7086, + "step": 86940 + }, + { + "epoch": 3.23, + "learning_rate": 6.766095138914718e-06, + "loss": 1.7113, + "step": 86950 + }, + { + "epoch": 3.23, + "learning_rate": 6.765723211961171e-06, + "loss": 1.7295, + "step": 86960 + }, + { + "epoch": 3.23, + "learning_rate": 6.765351285007626e-06, + "loss": 1.7328, + "step": 86970 + }, + { + "epoch": 3.24, + "learning_rate": 6.764979358054079e-06, + "loss": 1.7578, + "step": 86980 + }, + { + "epoch": 3.24, + "learning_rate": 6.764607431100533e-06, + "loss": 1.7655, + "step": 86990 + }, + { + "epoch": 3.24, + "learning_rate": 6.764235504146987e-06, + "loss": 1.7001, + "step": 87000 + }, + { + "epoch": 3.24, + "eval_loss": 1.6576167345046997, + "eval_runtime": 16.8341, + "eval_samples_per_second": 59.403, + "eval_steps_per_second": 3.742, + "step": 87000 + }, + { + "epoch": 3.24, + "learning_rate": 6.76386357719344e-06, + "loss": 1.882, + "step": 87010 + }, + { + "epoch": 3.24, + "learning_rate": 6.763491650239894e-06, + "loss": 1.7034, + "step": 87020 + }, + { + "epoch": 3.24, + "learning_rate": 6.7631197232863464e-06, + "loss": 1.7767, + "step": 87030 + }, + { + "epoch": 3.24, + "learning_rate": 6.7627477963328e-06, + "loss": 1.5626, + "step": 87040 + }, + { + "epoch": 3.24, + "learning_rate": 6.762375869379254e-06, + "loss": 1.658, + "step": 87050 + }, + { + "epoch": 3.24, + "learning_rate": 6.762003942425708e-06, + "loss": 1.7426, + "step": 87060 + }, + { + "epoch": 3.24, + "learning_rate": 6.761632015472161e-06, + "loss": 1.6193, + "step": 87070 + }, + { + "epoch": 3.24, + "learning_rate": 6.7612600885186154e-06, + "loss": 1.8441, + "step": 87080 + }, + { + "epoch": 3.24, + "learning_rate": 6.760888161565069e-06, + "loss": 1.6579, + "step": 87090 + }, + { + "epoch": 3.24, + "learning_rate": 6.760516234611522e-06, + "loss": 1.7037, + "step": 87100 + }, + { + "epoch": 3.24, + "eval_loss": 1.6581270694732666, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 87100 + }, + { + "epoch": 3.24, + "learning_rate": 6.760144307657977e-06, + "loss": 1.6865, + "step": 87110 + }, + { + "epoch": 3.24, + "learning_rate": 6.75977238070443e-06, + "loss": 1.7297, + "step": 87120 + }, + { + "epoch": 3.24, + "learning_rate": 6.7594004537508836e-06, + "loss": 1.797, + "step": 87130 + }, + { + "epoch": 3.24, + "learning_rate": 6.759028526797338e-06, + "loss": 1.7327, + "step": 87140 + }, + { + "epoch": 3.24, + "learning_rate": 6.758656599843791e-06, + "loss": 1.7264, + "step": 87150 + }, + { + "epoch": 3.24, + "learning_rate": 6.758284672890245e-06, + "loss": 1.6251, + "step": 87160 + }, + { + "epoch": 3.24, + "learning_rate": 6.757912745936699e-06, + "loss": 1.5902, + "step": 87170 + }, + { + "epoch": 3.24, + "learning_rate": 6.7575408189831526e-06, + "loss": 1.5778, + "step": 87180 + }, + { + "epoch": 3.24, + "learning_rate": 6.757168892029606e-06, + "loss": 1.6129, + "step": 87190 + }, + { + "epoch": 3.24, + "learning_rate": 6.75679696507606e-06, + "loss": 1.6681, + "step": 87200 + }, + { + "epoch": 3.24, + "eval_loss": 1.6584856510162354, + "eval_runtime": 16.8421, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 87200 + }, + { + "epoch": 3.24, + "learning_rate": 6.756425038122514e-06, + "loss": 1.5922, + "step": 87210 + }, + { + "epoch": 3.24, + "learning_rate": 6.756053111168966e-06, + "loss": 1.6013, + "step": 87220 + }, + { + "epoch": 3.24, + "learning_rate": 6.75568118421542e-06, + "loss": 1.7035, + "step": 87230 + }, + { + "epoch": 3.24, + "learning_rate": 6.755309257261874e-06, + "loss": 1.6739, + "step": 87240 + }, + { + "epoch": 3.25, + "learning_rate": 6.754937330308328e-06, + "loss": 1.5819, + "step": 87250 + }, + { + "epoch": 3.25, + "learning_rate": 6.754565403354781e-06, + "loss": 1.6363, + "step": 87260 + }, + { + "epoch": 3.25, + "learning_rate": 6.754193476401235e-06, + "loss": 1.85, + "step": 87270 + }, + { + "epoch": 3.25, + "learning_rate": 6.753821549447689e-06, + "loss": 1.7135, + "step": 87280 + }, + { + "epoch": 3.25, + "learning_rate": 6.753449622494142e-06, + "loss": 1.7088, + "step": 87290 + }, + { + "epoch": 3.25, + "learning_rate": 6.753077695540597e-06, + "loss": 1.734, + "step": 87300 + }, + { + "epoch": 3.25, + "eval_loss": 1.6578391790390015, + "eval_runtime": 16.8296, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 87300 + }, + { + "epoch": 3.25, + "learning_rate": 6.75270576858705e-06, + "loss": 1.6594, + "step": 87310 + }, + { + "epoch": 3.25, + "learning_rate": 6.7523338416335035e-06, + "loss": 1.7069, + "step": 87320 + }, + { + "epoch": 3.25, + "learning_rate": 6.751961914679958e-06, + "loss": 1.7604, + "step": 87330 + }, + { + "epoch": 3.25, + "learning_rate": 6.751589987726411e-06, + "loss": 1.7917, + "step": 87340 + }, + { + "epoch": 3.25, + "learning_rate": 6.751218060772865e-06, + "loss": 1.8317, + "step": 87350 + }, + { + "epoch": 3.25, + "learning_rate": 6.750846133819319e-06, + "loss": 1.7069, + "step": 87360 + }, + { + "epoch": 3.25, + "learning_rate": 6.7504742068657725e-06, + "loss": 1.8123, + "step": 87370 + }, + { + "epoch": 3.25, + "learning_rate": 6.750102279912226e-06, + "loss": 1.6407, + "step": 87380 + }, + { + "epoch": 3.25, + "learning_rate": 6.74973035295868e-06, + "loss": 1.6148, + "step": 87390 + }, + { + "epoch": 3.25, + "learning_rate": 6.749358426005134e-06, + "loss": 1.644, + "step": 87400 + }, + { + "epoch": 3.25, + "eval_loss": 1.6585286855697632, + "eval_runtime": 16.8314, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 87400 + }, + { + "epoch": 3.25, + "learning_rate": 6.748986499051586e-06, + "loss": 1.6436, + "step": 87410 + }, + { + "epoch": 3.25, + "learning_rate": 6.74861457209804e-06, + "loss": 1.6829, + "step": 87420 + }, + { + "epoch": 3.25, + "learning_rate": 6.748242645144494e-06, + "loss": 1.6671, + "step": 87430 + }, + { + "epoch": 3.25, + "learning_rate": 6.747870718190948e-06, + "loss": 1.7043, + "step": 87440 + }, + { + "epoch": 3.25, + "learning_rate": 6.747498791237401e-06, + "loss": 1.7065, + "step": 87450 + }, + { + "epoch": 3.25, + "learning_rate": 6.747126864283855e-06, + "loss": 1.7504, + "step": 87460 + }, + { + "epoch": 3.25, + "learning_rate": 6.746754937330309e-06, + "loss": 1.8652, + "step": 87470 + }, + { + "epoch": 3.25, + "learning_rate": 6.746383010376762e-06, + "loss": 1.6367, + "step": 87480 + }, + { + "epoch": 3.25, + "learning_rate": 6.7460110834232166e-06, + "loss": 1.7329, + "step": 87490 + }, + { + "epoch": 3.25, + "learning_rate": 6.74563915646967e-06, + "loss": 1.777, + "step": 87500 + }, + { + "epoch": 3.25, + "eval_loss": 1.6580673456192017, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 87500 + }, + { + "epoch": 3.25, + "learning_rate": 6.7452672295161235e-06, + "loss": 1.6389, + "step": 87510 + }, + { + "epoch": 3.26, + "learning_rate": 6.744895302562578e-06, + "loss": 1.8608, + "step": 87520 + }, + { + "epoch": 3.26, + "learning_rate": 6.744523375609031e-06, + "loss": 1.6771, + "step": 87530 + }, + { + "epoch": 3.26, + "learning_rate": 6.744151448655485e-06, + "loss": 1.7898, + "step": 87540 + }, + { + "epoch": 3.26, + "learning_rate": 6.743779521701939e-06, + "loss": 1.6496, + "step": 87550 + }, + { + "epoch": 3.26, + "learning_rate": 6.7434075947483925e-06, + "loss": 1.7245, + "step": 87560 + }, + { + "epoch": 3.26, + "learning_rate": 6.743035667794846e-06, + "loss": 1.7587, + "step": 87570 + }, + { + "epoch": 3.26, + "learning_rate": 6.7426637408413e-06, + "loss": 1.6962, + "step": 87580 + }, + { + "epoch": 3.26, + "learning_rate": 6.742291813887753e-06, + "loss": 1.7584, + "step": 87590 + }, + { + "epoch": 3.26, + "learning_rate": 6.741919886934206e-06, + "loss": 1.6428, + "step": 87600 + }, + { + "epoch": 3.26, + "eval_loss": 1.6571474075317383, + "eval_runtime": 16.8348, + "eval_samples_per_second": 59.401, + "eval_steps_per_second": 3.742, + "step": 87600 + }, + { + "epoch": 3.26, + "learning_rate": 6.74154795998066e-06, + "loss": 1.7399, + "step": 87610 + }, + { + "epoch": 3.26, + "learning_rate": 6.741176033027113e-06, + "loss": 1.6364, + "step": 87620 + }, + { + "epoch": 3.26, + "learning_rate": 6.7408041060735675e-06, + "loss": 1.8275, + "step": 87630 + }, + { + "epoch": 3.26, + "learning_rate": 6.740432179120021e-06, + "loss": 1.7488, + "step": 87640 + }, + { + "epoch": 3.26, + "learning_rate": 6.7400602521664745e-06, + "loss": 1.8443, + "step": 87650 + }, + { + "epoch": 3.26, + "learning_rate": 6.739688325212929e-06, + "loss": 1.7639, + "step": 87660 + }, + { + "epoch": 3.26, + "learning_rate": 6.739316398259382e-06, + "loss": 1.8353, + "step": 87670 + }, + { + "epoch": 3.26, + "learning_rate": 6.738944471305836e-06, + "loss": 1.676, + "step": 87680 + }, + { + "epoch": 3.26, + "learning_rate": 6.73857254435229e-06, + "loss": 1.7165, + "step": 87690 + }, + { + "epoch": 3.26, + "learning_rate": 6.7382006173987434e-06, + "loss": 1.6631, + "step": 87700 + }, + { + "epoch": 3.26, + "eval_loss": 1.65672767162323, + "eval_runtime": 16.8202, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.746, + "step": 87700 + }, + { + "epoch": 3.26, + "learning_rate": 6.737828690445197e-06, + "loss": 1.7187, + "step": 87710 + }, + { + "epoch": 3.26, + "learning_rate": 6.737456763491651e-06, + "loss": 1.6523, + "step": 87720 + }, + { + "epoch": 3.26, + "learning_rate": 6.737084836538105e-06, + "loss": 1.6258, + "step": 87730 + }, + { + "epoch": 3.26, + "learning_rate": 6.736712909584558e-06, + "loss": 1.7227, + "step": 87740 + }, + { + "epoch": 3.26, + "learning_rate": 6.7363409826310124e-06, + "loss": 1.7271, + "step": 87750 + }, + { + "epoch": 3.26, + "learning_rate": 6.735969055677466e-06, + "loss": 1.6495, + "step": 87760 + }, + { + "epoch": 3.26, + "learning_rate": 6.735597128723919e-06, + "loss": 1.6741, + "step": 87770 + }, + { + "epoch": 3.26, + "learning_rate": 6.735225201770372e-06, + "loss": 1.7356, + "step": 87780 + }, + { + "epoch": 3.27, + "learning_rate": 6.734853274816826e-06, + "loss": 1.7228, + "step": 87790 + }, + { + "epoch": 3.27, + "learning_rate": 6.73448134786328e-06, + "loss": 1.6698, + "step": 87800 + }, + { + "epoch": 3.27, + "eval_loss": 1.656923532485962, + "eval_runtime": 16.8297, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 87800 + }, + { + "epoch": 3.27, + "learning_rate": 6.734109420909733e-06, + "loss": 1.6496, + "step": 87810 + }, + { + "epoch": 3.27, + "learning_rate": 6.7337374939561875e-06, + "loss": 1.6922, + "step": 87820 + }, + { + "epoch": 3.27, + "learning_rate": 6.733365567002641e-06, + "loss": 1.696, + "step": 87830 + }, + { + "epoch": 3.27, + "learning_rate": 6.732993640049094e-06, + "loss": 1.7349, + "step": 87840 + }, + { + "epoch": 3.27, + "learning_rate": 6.732621713095549e-06, + "loss": 1.8145, + "step": 87850 + }, + { + "epoch": 3.27, + "learning_rate": 6.732249786142002e-06, + "loss": 1.6635, + "step": 87860 + }, + { + "epoch": 3.27, + "learning_rate": 6.731877859188456e-06, + "loss": 1.8237, + "step": 87870 + }, + { + "epoch": 3.27, + "learning_rate": 6.73150593223491e-06, + "loss": 1.6542, + "step": 87880 + }, + { + "epoch": 3.27, + "learning_rate": 6.731134005281363e-06, + "loss": 1.673, + "step": 87890 + }, + { + "epoch": 3.27, + "learning_rate": 6.730762078327817e-06, + "loss": 1.7422, + "step": 87900 + }, + { + "epoch": 3.27, + "eval_loss": 1.6566306352615356, + "eval_runtime": 16.8279, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 87900 + }, + { + "epoch": 3.27, + "learning_rate": 6.730390151374271e-06, + "loss": 1.6927, + "step": 87910 + }, + { + "epoch": 3.27, + "learning_rate": 6.730018224420725e-06, + "loss": 1.6028, + "step": 87920 + }, + { + "epoch": 3.27, + "learning_rate": 6.729646297467178e-06, + "loss": 1.7067, + "step": 87930 + }, + { + "epoch": 3.27, + "learning_rate": 6.729274370513632e-06, + "loss": 1.8332, + "step": 87940 + }, + { + "epoch": 3.27, + "learning_rate": 6.728902443560086e-06, + "loss": 1.7005, + "step": 87950 + }, + { + "epoch": 3.27, + "learning_rate": 6.728530516606539e-06, + "loss": 1.7067, + "step": 87960 + }, + { + "epoch": 3.27, + "learning_rate": 6.728158589652992e-06, + "loss": 1.6794, + "step": 87970 + }, + { + "epoch": 3.27, + "learning_rate": 6.727786662699446e-06, + "loss": 1.8057, + "step": 87980 + }, + { + "epoch": 3.27, + "learning_rate": 6.7274147357459e-06, + "loss": 1.6631, + "step": 87990 + }, + { + "epoch": 3.27, + "learning_rate": 6.727042808792353e-06, + "loss": 1.6746, + "step": 88000 + }, + { + "epoch": 3.27, + "eval_loss": 1.6565269231796265, + "eval_runtime": 16.8149, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 88000 + }, + { + "epoch": 3.27, + "learning_rate": 6.7266708818388075e-06, + "loss": 1.6577, + "step": 88010 + }, + { + "epoch": 3.27, + "learning_rate": 6.726298954885261e-06, + "loss": 1.6909, + "step": 88020 + }, + { + "epoch": 3.27, + "learning_rate": 6.725927027931714e-06, + "loss": 1.6093, + "step": 88030 + }, + { + "epoch": 3.27, + "learning_rate": 6.725555100978169e-06, + "loss": 1.7521, + "step": 88040 + }, + { + "epoch": 3.27, + "learning_rate": 6.725183174024622e-06, + "loss": 1.6215, + "step": 88050 + }, + { + "epoch": 3.28, + "learning_rate": 6.724811247071076e-06, + "loss": 1.6439, + "step": 88060 + }, + { + "epoch": 3.28, + "learning_rate": 6.72443932011753e-06, + "loss": 1.7317, + "step": 88070 + }, + { + "epoch": 3.28, + "learning_rate": 6.724067393163983e-06, + "loss": 1.647, + "step": 88080 + }, + { + "epoch": 3.28, + "learning_rate": 6.723695466210437e-06, + "loss": 1.674, + "step": 88090 + }, + { + "epoch": 3.28, + "learning_rate": 6.723323539256891e-06, + "loss": 1.6765, + "step": 88100 + }, + { + "epoch": 3.28, + "eval_loss": 1.6563303470611572, + "eval_runtime": 16.8271, + "eval_samples_per_second": 59.428, + "eval_steps_per_second": 3.744, + "step": 88100 + }, + { + "epoch": 3.28, + "learning_rate": 6.722951612303345e-06, + "loss": 1.7491, + "step": 88110 + }, + { + "epoch": 3.28, + "learning_rate": 6.722579685349798e-06, + "loss": 1.6945, + "step": 88120 + }, + { + "epoch": 3.28, + "learning_rate": 6.722207758396252e-06, + "loss": 1.7109, + "step": 88130 + }, + { + "epoch": 3.28, + "learning_rate": 6.721835831442706e-06, + "loss": 1.6824, + "step": 88140 + }, + { + "epoch": 3.28, + "learning_rate": 6.721463904489159e-06, + "loss": 1.8684, + "step": 88150 + }, + { + "epoch": 3.28, + "learning_rate": 6.721091977535612e-06, + "loss": 1.7185, + "step": 88160 + }, + { + "epoch": 3.28, + "learning_rate": 6.720720050582066e-06, + "loss": 1.7417, + "step": 88170 + }, + { + "epoch": 3.28, + "learning_rate": 6.72034812362852e-06, + "loss": 1.7582, + "step": 88180 + }, + { + "epoch": 3.28, + "learning_rate": 6.719976196674973e-06, + "loss": 1.6537, + "step": 88190 + }, + { + "epoch": 3.28, + "learning_rate": 6.7196042697214266e-06, + "loss": 1.7133, + "step": 88200 + }, + { + "epoch": 3.28, + "eval_loss": 1.6566437482833862, + "eval_runtime": 16.828, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 88200 + }, + { + "epoch": 3.28, + "learning_rate": 6.719232342767881e-06, + "loss": 1.6593, + "step": 88210 + }, + { + "epoch": 3.28, + "learning_rate": 6.718860415814334e-06, + "loss": 1.6716, + "step": 88220 + }, + { + "epoch": 3.28, + "learning_rate": 6.718488488860788e-06, + "loss": 1.6146, + "step": 88230 + }, + { + "epoch": 3.28, + "learning_rate": 6.718116561907242e-06, + "loss": 1.5702, + "step": 88240 + }, + { + "epoch": 3.28, + "learning_rate": 6.7177446349536956e-06, + "loss": 1.6392, + "step": 88250 + }, + { + "epoch": 3.28, + "learning_rate": 6.717372708000149e-06, + "loss": 1.7358, + "step": 88260 + }, + { + "epoch": 3.28, + "learning_rate": 6.717000781046603e-06, + "loss": 1.7554, + "step": 88270 + }, + { + "epoch": 3.28, + "learning_rate": 6.716628854093057e-06, + "loss": 1.6028, + "step": 88280 + }, + { + "epoch": 3.28, + "learning_rate": 6.71625692713951e-06, + "loss": 1.6851, + "step": 88290 + }, + { + "epoch": 3.28, + "learning_rate": 6.7158850001859645e-06, + "loss": 1.5963, + "step": 88300 + }, + { + "epoch": 3.28, + "eval_loss": 1.6569340229034424, + "eval_runtime": 16.8292, + "eval_samples_per_second": 59.421, + "eval_steps_per_second": 3.743, + "step": 88300 + }, + { + "epoch": 3.28, + "learning_rate": 6.715513073232418e-06, + "loss": 1.6489, + "step": 88310 + }, + { + "epoch": 3.28, + "learning_rate": 6.7151411462788715e-06, + "loss": 1.7931, + "step": 88320 + }, + { + "epoch": 3.29, + "learning_rate": 6.714769219325326e-06, + "loss": 1.8248, + "step": 88330 + }, + { + "epoch": 3.29, + "learning_rate": 6.714397292371779e-06, + "loss": 1.6601, + "step": 88340 + }, + { + "epoch": 3.29, + "learning_rate": 6.714025365418232e-06, + "loss": 1.6559, + "step": 88350 + }, + { + "epoch": 3.29, + "learning_rate": 6.713653438464685e-06, + "loss": 1.6564, + "step": 88360 + }, + { + "epoch": 3.29, + "learning_rate": 6.71328151151114e-06, + "loss": 1.6468, + "step": 88370 + }, + { + "epoch": 3.29, + "learning_rate": 6.712909584557593e-06, + "loss": 1.6447, + "step": 88380 + }, + { + "epoch": 3.29, + "learning_rate": 6.7125376576040465e-06, + "loss": 1.7207, + "step": 88390 + }, + { + "epoch": 3.29, + "learning_rate": 6.712165730650501e-06, + "loss": 1.8106, + "step": 88400 + }, + { + "epoch": 3.29, + "eval_loss": 1.6576621532440186, + "eval_runtime": 16.8444, + "eval_samples_per_second": 59.367, + "eval_steps_per_second": 3.74, + "step": 88400 + }, + { + "epoch": 3.29, + "learning_rate": 6.711793803696954e-06, + "loss": 1.6775, + "step": 88410 + }, + { + "epoch": 3.29, + "learning_rate": 6.711421876743408e-06, + "loss": 1.738, + "step": 88420 + }, + { + "epoch": 3.29, + "learning_rate": 6.711049949789862e-06, + "loss": 1.7127, + "step": 88430 + }, + { + "epoch": 3.29, + "learning_rate": 6.7106780228363155e-06, + "loss": 1.6357, + "step": 88440 + }, + { + "epoch": 3.29, + "learning_rate": 6.710306095882769e-06, + "loss": 1.6362, + "step": 88450 + }, + { + "epoch": 3.29, + "learning_rate": 6.709934168929223e-06, + "loss": 1.7831, + "step": 88460 + }, + { + "epoch": 3.29, + "learning_rate": 6.709562241975677e-06, + "loss": 1.6487, + "step": 88470 + }, + { + "epoch": 3.29, + "learning_rate": 6.70919031502213e-06, + "loss": 1.713, + "step": 88480 + }, + { + "epoch": 3.29, + "learning_rate": 6.7088183880685845e-06, + "loss": 1.652, + "step": 88490 + }, + { + "epoch": 3.29, + "learning_rate": 6.708446461115038e-06, + "loss": 1.6604, + "step": 88500 + }, + { + "epoch": 3.29, + "eval_loss": 1.657071590423584, + "eval_runtime": 16.8402, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 88500 + }, + { + "epoch": 3.29, + "learning_rate": 6.7080745341614914e-06, + "loss": 1.6243, + "step": 88510 + }, + { + "epoch": 3.29, + "learning_rate": 6.707702607207946e-06, + "loss": 1.7566, + "step": 88520 + }, + { + "epoch": 3.29, + "learning_rate": 6.707330680254398e-06, + "loss": 1.764, + "step": 88530 + }, + { + "epoch": 3.29, + "learning_rate": 6.706958753300852e-06, + "loss": 1.7575, + "step": 88540 + }, + { + "epoch": 3.29, + "learning_rate": 6.706586826347305e-06, + "loss": 1.7176, + "step": 88550 + }, + { + "epoch": 3.29, + "learning_rate": 6.7062148993937596e-06, + "loss": 1.725, + "step": 88560 + }, + { + "epoch": 3.29, + "learning_rate": 6.705842972440213e-06, + "loss": 1.7216, + "step": 88570 + }, + { + "epoch": 3.29, + "learning_rate": 6.7054710454866665e-06, + "loss": 1.7086, + "step": 88580 + }, + { + "epoch": 3.29, + "learning_rate": 6.705099118533121e-06, + "loss": 1.6772, + "step": 88590 + }, + { + "epoch": 3.3, + "learning_rate": 6.704727191579574e-06, + "loss": 1.7533, + "step": 88600 + }, + { + "epoch": 3.3, + "eval_loss": 1.6563544273376465, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 88600 + }, + { + "epoch": 3.3, + "learning_rate": 6.704355264626028e-06, + "loss": 1.7134, + "step": 88610 + }, + { + "epoch": 3.3, + "learning_rate": 6.703983337672482e-06, + "loss": 1.72, + "step": 88620 + }, + { + "epoch": 3.3, + "learning_rate": 6.7036114107189355e-06, + "loss": 1.7215, + "step": 88630 + }, + { + "epoch": 3.3, + "learning_rate": 6.703239483765389e-06, + "loss": 1.6613, + "step": 88640 + }, + { + "epoch": 3.3, + "learning_rate": 6.702867556811843e-06, + "loss": 1.733, + "step": 88650 + }, + { + "epoch": 3.3, + "learning_rate": 6.702495629858297e-06, + "loss": 1.6187, + "step": 88660 + }, + { + "epoch": 3.3, + "learning_rate": 6.70212370290475e-06, + "loss": 1.6286, + "step": 88670 + }, + { + "epoch": 3.3, + "learning_rate": 6.7017517759512045e-06, + "loss": 1.6333, + "step": 88680 + }, + { + "epoch": 3.3, + "learning_rate": 6.701379848997658e-06, + "loss": 1.5929, + "step": 88690 + }, + { + "epoch": 3.3, + "learning_rate": 6.701007922044111e-06, + "loss": 1.5928, + "step": 88700 + }, + { + "epoch": 3.3, + "eval_loss": 1.6573066711425781, + "eval_runtime": 16.8315, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 88700 + }, + { + "epoch": 3.3, + "learning_rate": 6.700635995090566e-06, + "loss": 1.6053, + "step": 88710 + }, + { + "epoch": 3.3, + "learning_rate": 6.700264068137018e-06, + "loss": 1.5795, + "step": 88720 + }, + { + "epoch": 3.3, + "learning_rate": 6.699892141183472e-06, + "loss": 1.6452, + "step": 88730 + }, + { + "epoch": 3.3, + "learning_rate": 6.699520214229925e-06, + "loss": 1.6497, + "step": 88740 + }, + { + "epoch": 3.3, + "learning_rate": 6.6991482872763795e-06, + "loss": 1.7271, + "step": 88750 + }, + { + "epoch": 3.3, + "learning_rate": 6.698776360322833e-06, + "loss": 1.7094, + "step": 88760 + }, + { + "epoch": 3.3, + "learning_rate": 6.6984044333692864e-06, + "loss": 1.7192, + "step": 88770 + }, + { + "epoch": 3.3, + "learning_rate": 6.69803250641574e-06, + "loss": 1.7355, + "step": 88780 + }, + { + "epoch": 3.3, + "learning_rate": 6.697660579462194e-06, + "loss": 1.6837, + "step": 88790 + }, + { + "epoch": 3.3, + "learning_rate": 6.697288652508648e-06, + "loss": 1.7824, + "step": 88800 + }, + { + "epoch": 3.3, + "eval_loss": 1.6569721698760986, + "eval_runtime": 16.8203, + "eval_samples_per_second": 59.452, + "eval_steps_per_second": 3.745, + "step": 88800 + }, + { + "epoch": 3.3, + "learning_rate": 6.696916725555101e-06, + "loss": 1.8309, + "step": 88810 + }, + { + "epoch": 3.3, + "learning_rate": 6.6965447986015554e-06, + "loss": 1.7481, + "step": 88820 + }, + { + "epoch": 3.3, + "learning_rate": 6.696172871648009e-06, + "loss": 1.7709, + "step": 88830 + }, + { + "epoch": 3.3, + "learning_rate": 6.695800944694462e-06, + "loss": 1.7917, + "step": 88840 + }, + { + "epoch": 3.3, + "learning_rate": 6.695429017740917e-06, + "loss": 1.6098, + "step": 88850 + }, + { + "epoch": 3.3, + "learning_rate": 6.69505709078737e-06, + "loss": 1.6362, + "step": 88860 + }, + { + "epoch": 3.31, + "learning_rate": 6.694685163833824e-06, + "loss": 1.6102, + "step": 88870 + }, + { + "epoch": 3.31, + "learning_rate": 6.694313236880278e-06, + "loss": 1.63, + "step": 88880 + }, + { + "epoch": 3.31, + "learning_rate": 6.693941309926731e-06, + "loss": 1.6974, + "step": 88890 + }, + { + "epoch": 3.31, + "learning_rate": 6.693569382973185e-06, + "loss": 1.7091, + "step": 88900 + }, + { + "epoch": 3.31, + "eval_loss": 1.6571907997131348, + "eval_runtime": 16.8372, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 88900 + }, + { + "epoch": 3.31, + "learning_rate": 6.693197456019637e-06, + "loss": 1.7706, + "step": 88910 + }, + { + "epoch": 3.31, + "learning_rate": 6.692825529066092e-06, + "loss": 1.766, + "step": 88920 + }, + { + "epoch": 3.31, + "learning_rate": 6.692453602112545e-06, + "loss": 1.8743, + "step": 88930 + }, + { + "epoch": 3.31, + "learning_rate": 6.692081675158999e-06, + "loss": 1.809, + "step": 88940 + }, + { + "epoch": 3.31, + "learning_rate": 6.691709748205453e-06, + "loss": 1.6151, + "step": 88950 + }, + { + "epoch": 3.31, + "learning_rate": 6.691337821251906e-06, + "loss": 1.6231, + "step": 88960 + }, + { + "epoch": 3.31, + "learning_rate": 6.69096589429836e-06, + "loss": 1.725, + "step": 88970 + }, + { + "epoch": 3.31, + "learning_rate": 6.690593967344814e-06, + "loss": 1.6347, + "step": 88980 + }, + { + "epoch": 3.31, + "learning_rate": 6.690222040391268e-06, + "loss": 1.6562, + "step": 88990 + }, + { + "epoch": 3.31, + "learning_rate": 6.689850113437721e-06, + "loss": 1.6179, + "step": 89000 + }, + { + "epoch": 3.31, + "eval_loss": 1.6565991640090942, + "eval_runtime": 16.8305, + "eval_samples_per_second": 59.416, + "eval_steps_per_second": 3.743, + "step": 89000 + }, + { + "epoch": 3.31, + "learning_rate": 6.689478186484175e-06, + "loss": 1.7659, + "step": 89010 + }, + { + "epoch": 3.31, + "learning_rate": 6.689106259530629e-06, + "loss": 1.6384, + "step": 89020 + }, + { + "epoch": 3.31, + "learning_rate": 6.688734332577082e-06, + "loss": 1.7563, + "step": 89030 + }, + { + "epoch": 3.31, + "learning_rate": 6.688362405623537e-06, + "loss": 1.6334, + "step": 89040 + }, + { + "epoch": 3.31, + "learning_rate": 6.68799047866999e-06, + "loss": 1.7022, + "step": 89050 + }, + { + "epoch": 3.31, + "learning_rate": 6.6876185517164435e-06, + "loss": 1.6985, + "step": 89060 + }, + { + "epoch": 3.31, + "learning_rate": 6.687246624762898e-06, + "loss": 1.5496, + "step": 89070 + }, + { + "epoch": 3.31, + "learning_rate": 6.686874697809351e-06, + "loss": 1.6757, + "step": 89080 + }, + { + "epoch": 3.31, + "learning_rate": 6.686502770855805e-06, + "loss": 1.6596, + "step": 89090 + }, + { + "epoch": 3.31, + "learning_rate": 6.686130843902257e-06, + "loss": 1.5972, + "step": 89100 + }, + { + "epoch": 3.31, + "eval_loss": 1.6561055183410645, + "eval_runtime": 16.8518, + "eval_samples_per_second": 59.341, + "eval_steps_per_second": 3.738, + "step": 89100 + }, + { + "epoch": 3.31, + "learning_rate": 6.685758916948712e-06, + "loss": 1.6561, + "step": 89110 + }, + { + "epoch": 3.31, + "learning_rate": 6.685386989995165e-06, + "loss": 1.7302, + "step": 89120 + }, + { + "epoch": 3.31, + "learning_rate": 6.685015063041619e-06, + "loss": 1.7135, + "step": 89130 + }, + { + "epoch": 3.32, + "learning_rate": 6.684643136088073e-06, + "loss": 1.873, + "step": 89140 + }, + { + "epoch": 3.32, + "learning_rate": 6.684271209134526e-06, + "loss": 1.6438, + "step": 89150 + }, + { + "epoch": 3.32, + "learning_rate": 6.68389928218098e-06, + "loss": 1.7875, + "step": 89160 + }, + { + "epoch": 3.32, + "learning_rate": 6.683527355227434e-06, + "loss": 1.6739, + "step": 89170 + }, + { + "epoch": 3.32, + "learning_rate": 6.683155428273888e-06, + "loss": 1.7222, + "step": 89180 + }, + { + "epoch": 3.32, + "learning_rate": 6.682783501320341e-06, + "loss": 1.6763, + "step": 89190 + }, + { + "epoch": 3.32, + "learning_rate": 6.682411574366795e-06, + "loss": 1.6326, + "step": 89200 + }, + { + "epoch": 3.32, + "eval_loss": 1.6558713912963867, + "eval_runtime": 16.8509, + "eval_samples_per_second": 59.344, + "eval_steps_per_second": 3.739, + "step": 89200 + }, + { + "epoch": 3.32, + "learning_rate": 6.682039647413249e-06, + "loss": 1.7487, + "step": 89210 + }, + { + "epoch": 3.32, + "learning_rate": 6.681667720459702e-06, + "loss": 1.7579, + "step": 89220 + }, + { + "epoch": 3.32, + "learning_rate": 6.681295793506157e-06, + "loss": 1.678, + "step": 89230 + }, + { + "epoch": 3.32, + "learning_rate": 6.68092386655261e-06, + "loss": 1.6445, + "step": 89240 + }, + { + "epoch": 3.32, + "learning_rate": 6.6805519395990635e-06, + "loss": 1.8297, + "step": 89250 + }, + { + "epoch": 3.32, + "learning_rate": 6.680180012645518e-06, + "loss": 1.8782, + "step": 89260 + }, + { + "epoch": 3.32, + "learning_rate": 6.679808085691971e-06, + "loss": 1.7838, + "step": 89270 + }, + { + "epoch": 3.32, + "learning_rate": 6.679436158738424e-06, + "loss": 1.7745, + "step": 89280 + }, + { + "epoch": 3.32, + "learning_rate": 6.679064231784877e-06, + "loss": 1.7203, + "step": 89290 + }, + { + "epoch": 3.32, + "learning_rate": 6.678692304831332e-06, + "loss": 1.7284, + "step": 89300 + }, + { + "epoch": 3.32, + "eval_loss": 1.6554601192474365, + "eval_runtime": 16.8434, + "eval_samples_per_second": 59.37, + "eval_steps_per_second": 3.74, + "step": 89300 + }, + { + "epoch": 3.32, + "learning_rate": 6.678320377877785e-06, + "loss": 1.7313, + "step": 89310 + }, + { + "epoch": 3.32, + "learning_rate": 6.6779484509242386e-06, + "loss": 1.6044, + "step": 89320 + }, + { + "epoch": 3.32, + "learning_rate": 6.677576523970693e-06, + "loss": 1.649, + "step": 89330 + }, + { + "epoch": 3.32, + "learning_rate": 6.677204597017146e-06, + "loss": 1.5752, + "step": 89340 + }, + { + "epoch": 3.32, + "learning_rate": 6.6768326700636e-06, + "loss": 1.6593, + "step": 89350 + }, + { + "epoch": 3.32, + "learning_rate": 6.676460743110053e-06, + "loss": 1.5402, + "step": 89360 + }, + { + "epoch": 3.32, + "learning_rate": 6.6760888161565075e-06, + "loss": 1.8082, + "step": 89370 + }, + { + "epoch": 3.32, + "learning_rate": 6.675716889202961e-06, + "loss": 1.6006, + "step": 89380 + }, + { + "epoch": 3.32, + "learning_rate": 6.6753449622494145e-06, + "loss": 1.7701, + "step": 89390 + }, + { + "epoch": 3.33, + "learning_rate": 6.674973035295869e-06, + "loss": 1.6978, + "step": 89400 + }, + { + "epoch": 3.33, + "eval_loss": 1.6564069986343384, + "eval_runtime": 16.8406, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 89400 + }, + { + "epoch": 3.33, + "learning_rate": 6.674601108342322e-06, + "loss": 1.6282, + "step": 89410 + }, + { + "epoch": 3.33, + "learning_rate": 6.674229181388776e-06, + "loss": 1.691, + "step": 89420 + }, + { + "epoch": 3.33, + "learning_rate": 6.67385725443523e-06, + "loss": 1.5513, + "step": 89430 + }, + { + "epoch": 3.33, + "learning_rate": 6.6734853274816835e-06, + "loss": 1.7249, + "step": 89440 + }, + { + "epoch": 3.33, + "learning_rate": 6.673113400528137e-06, + "loss": 1.7601, + "step": 89450 + }, + { + "epoch": 3.33, + "learning_rate": 6.672741473574591e-06, + "loss": 1.743, + "step": 89460 + }, + { + "epoch": 3.33, + "learning_rate": 6.672369546621044e-06, + "loss": 1.6862, + "step": 89470 + }, + { + "epoch": 3.33, + "learning_rate": 6.671997619667497e-06, + "loss": 1.6407, + "step": 89480 + }, + { + "epoch": 3.33, + "learning_rate": 6.671625692713951e-06, + "loss": 1.6528, + "step": 89490 + }, + { + "epoch": 3.33, + "learning_rate": 6.671253765760405e-06, + "loss": 1.6563, + "step": 89500 + }, + { + "epoch": 3.33, + "eval_loss": 1.6550071239471436, + "eval_runtime": 16.837, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 89500 + }, + { + "epoch": 3.33, + "learning_rate": 6.6708818388068585e-06, + "loss": 1.6041, + "step": 89510 + }, + { + "epoch": 3.33, + "learning_rate": 6.670509911853312e-06, + "loss": 1.6384, + "step": 89520 + }, + { + "epoch": 3.33, + "learning_rate": 6.670137984899766e-06, + "loss": 1.7085, + "step": 89530 + }, + { + "epoch": 3.33, + "learning_rate": 6.66976605794622e-06, + "loss": 1.7286, + "step": 89540 + }, + { + "epoch": 3.33, + "learning_rate": 6.669394130992673e-06, + "loss": 1.6699, + "step": 89550 + }, + { + "epoch": 3.33, + "learning_rate": 6.6690222040391275e-06, + "loss": 1.6158, + "step": 89560 + }, + { + "epoch": 3.33, + "learning_rate": 6.668650277085581e-06, + "loss": 1.7482, + "step": 89570 + }, + { + "epoch": 3.33, + "learning_rate": 6.6682783501320344e-06, + "loss": 1.6923, + "step": 89580 + }, + { + "epoch": 3.33, + "learning_rate": 6.667906423178489e-06, + "loss": 1.6967, + "step": 89590 + }, + { + "epoch": 3.33, + "learning_rate": 6.667534496224942e-06, + "loss": 1.7974, + "step": 89600 + }, + { + "epoch": 3.33, + "eval_loss": 1.6556710004806519, + "eval_runtime": 16.83, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 89600 + }, + { + "epoch": 3.33, + "learning_rate": 6.667162569271396e-06, + "loss": 1.7947, + "step": 89610 + }, + { + "epoch": 3.33, + "learning_rate": 6.66679064231785e-06, + "loss": 1.6245, + "step": 89620 + }, + { + "epoch": 3.33, + "learning_rate": 6.666418715364303e-06, + "loss": 1.7845, + "step": 89630 + }, + { + "epoch": 3.33, + "learning_rate": 6.666046788410757e-06, + "loss": 1.5844, + "step": 89640 + }, + { + "epoch": 3.33, + "learning_rate": 6.665674861457211e-06, + "loss": 1.667, + "step": 89650 + }, + { + "epoch": 3.33, + "learning_rate": 6.665302934503664e-06, + "loss": 1.7841, + "step": 89660 + }, + { + "epoch": 3.34, + "learning_rate": 6.664931007550117e-06, + "loss": 1.7955, + "step": 89670 + }, + { + "epoch": 3.34, + "learning_rate": 6.664559080596571e-06, + "loss": 1.7448, + "step": 89680 + }, + { + "epoch": 3.34, + "learning_rate": 6.664187153643025e-06, + "loss": 1.6366, + "step": 89690 + }, + { + "epoch": 3.34, + "learning_rate": 6.6638152266894785e-06, + "loss": 1.7948, + "step": 89700 + }, + { + "epoch": 3.34, + "eval_loss": 1.6547966003417969, + "eval_runtime": 16.8325, + "eval_samples_per_second": 59.409, + "eval_steps_per_second": 3.743, + "step": 89700 + }, + { + "epoch": 3.34, + "learning_rate": 6.663443299735932e-06, + "loss": 1.6669, + "step": 89710 + }, + { + "epoch": 3.34, + "learning_rate": 6.663071372782386e-06, + "loss": 1.6744, + "step": 89720 + }, + { + "epoch": 3.34, + "learning_rate": 6.66269944582884e-06, + "loss": 1.7024, + "step": 89730 + }, + { + "epoch": 3.34, + "learning_rate": 6.662327518875293e-06, + "loss": 1.6915, + "step": 89740 + }, + { + "epoch": 3.34, + "learning_rate": 6.6619555919217475e-06, + "loss": 1.8117, + "step": 89750 + }, + { + "epoch": 3.34, + "learning_rate": 6.661583664968201e-06, + "loss": 1.8082, + "step": 89760 + }, + { + "epoch": 3.34, + "learning_rate": 6.661211738014654e-06, + "loss": 1.7792, + "step": 89770 + }, + { + "epoch": 3.34, + "learning_rate": 6.660839811061109e-06, + "loss": 1.7522, + "step": 89780 + }, + { + "epoch": 3.34, + "learning_rate": 6.660467884107562e-06, + "loss": 1.8104, + "step": 89790 + }, + { + "epoch": 3.34, + "learning_rate": 6.660095957154016e-06, + "loss": 1.5438, + "step": 89800 + }, + { + "epoch": 3.34, + "eval_loss": 1.655604362487793, + "eval_runtime": 16.835, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 89800 + }, + { + "epoch": 3.34, + "learning_rate": 6.65972403020047e-06, + "loss": 1.6438, + "step": 89810 + }, + { + "epoch": 3.34, + "learning_rate": 6.659352103246923e-06, + "loss": 1.5585, + "step": 89820 + }, + { + "epoch": 3.34, + "learning_rate": 6.658980176293377e-06, + "loss": 1.7244, + "step": 89830 + }, + { + "epoch": 3.34, + "learning_rate": 6.658608249339831e-06, + "loss": 1.7522, + "step": 89840 + }, + { + "epoch": 3.34, + "learning_rate": 6.658236322386284e-06, + "loss": 1.5764, + "step": 89850 + }, + { + "epoch": 3.34, + "learning_rate": 6.657864395432737e-06, + "loss": 1.7497, + "step": 89860 + }, + { + "epoch": 3.34, + "learning_rate": 6.657492468479191e-06, + "loss": 1.6169, + "step": 89870 + }, + { + "epoch": 3.34, + "learning_rate": 6.657120541525645e-06, + "loss": 1.5598, + "step": 89880 + }, + { + "epoch": 3.34, + "learning_rate": 6.6567486145720984e-06, + "loss": 1.6369, + "step": 89890 + }, + { + "epoch": 3.34, + "learning_rate": 6.656376687618552e-06, + "loss": 1.7962, + "step": 89900 + }, + { + "epoch": 3.34, + "eval_loss": 1.6549382209777832, + "eval_runtime": 16.8394, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 89900 + }, + { + "epoch": 3.34, + "learning_rate": 6.656004760665006e-06, + "loss": 1.5968, + "step": 89910 + }, + { + "epoch": 3.34, + "learning_rate": 6.65563283371146e-06, + "loss": 1.6655, + "step": 89920 + }, + { + "epoch": 3.34, + "learning_rate": 6.655260906757913e-06, + "loss": 1.5651, + "step": 89930 + }, + { + "epoch": 3.35, + "learning_rate": 6.654888979804367e-06, + "loss": 1.8234, + "step": 89940 + }, + { + "epoch": 3.35, + "learning_rate": 6.654517052850821e-06, + "loss": 1.6945, + "step": 89950 + }, + { + "epoch": 3.35, + "learning_rate": 6.654145125897274e-06, + "loss": 1.6229, + "step": 89960 + }, + { + "epoch": 3.35, + "learning_rate": 6.653773198943728e-06, + "loss": 1.6215, + "step": 89970 + }, + { + "epoch": 3.35, + "learning_rate": 6.653401271990182e-06, + "loss": 1.5591, + "step": 89980 + }, + { + "epoch": 3.35, + "learning_rate": 6.6530293450366356e-06, + "loss": 1.7139, + "step": 89990 + }, + { + "epoch": 3.35, + "learning_rate": 6.652657418083089e-06, + "loss": 1.6622, + "step": 90000 + }, + { + "epoch": 3.35, + "eval_loss": 1.6554028987884521, + "eval_runtime": 16.8275, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 90000 + }, + { + "epoch": 3.35, + "learning_rate": 6.652285491129543e-06, + "loss": 1.6639, + "step": 90010 + }, + { + "epoch": 3.35, + "learning_rate": 6.651913564175997e-06, + "loss": 1.7011, + "step": 90020 + }, + { + "epoch": 3.35, + "learning_rate": 6.65154163722245e-06, + "loss": 1.7735, + "step": 90030 + }, + { + "epoch": 3.35, + "learning_rate": 6.651169710268903e-06, + "loss": 1.7917, + "step": 90040 + }, + { + "epoch": 3.35, + "learning_rate": 6.650797783315357e-06, + "loss": 1.8286, + "step": 90050 + }, + { + "epoch": 3.35, + "learning_rate": 6.650425856361811e-06, + "loss": 1.5653, + "step": 90060 + }, + { + "epoch": 3.35, + "learning_rate": 6.650053929408264e-06, + "loss": 1.7644, + "step": 90070 + }, + { + "epoch": 3.35, + "learning_rate": 6.649682002454718e-06, + "loss": 1.8156, + "step": 90080 + }, + { + "epoch": 3.35, + "learning_rate": 6.649310075501172e-06, + "loss": 1.7855, + "step": 90090 + }, + { + "epoch": 3.35, + "learning_rate": 6.648938148547625e-06, + "loss": 1.7991, + "step": 90100 + }, + { + "epoch": 3.35, + "eval_loss": 1.6550134420394897, + "eval_runtime": 16.8242, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 90100 + }, + { + "epoch": 3.35, + "learning_rate": 6.64856622159408e-06, + "loss": 1.6131, + "step": 90110 + }, + { + "epoch": 3.35, + "learning_rate": 6.648194294640533e-06, + "loss": 1.6913, + "step": 90120 + }, + { + "epoch": 3.35, + "learning_rate": 6.6478223676869865e-06, + "loss": 1.6504, + "step": 90130 + }, + { + "epoch": 3.35, + "learning_rate": 6.647450440733441e-06, + "loss": 1.6526, + "step": 90140 + }, + { + "epoch": 3.35, + "learning_rate": 6.647078513779894e-06, + "loss": 1.7108, + "step": 90150 + }, + { + "epoch": 3.35, + "learning_rate": 6.646706586826348e-06, + "loss": 1.7033, + "step": 90160 + }, + { + "epoch": 3.35, + "learning_rate": 6.646334659872802e-06, + "loss": 1.5848, + "step": 90170 + }, + { + "epoch": 3.35, + "learning_rate": 6.6459627329192555e-06, + "loss": 1.7144, + "step": 90180 + }, + { + "epoch": 3.35, + "learning_rate": 6.645590805965709e-06, + "loss": 1.793, + "step": 90190 + }, + { + "epoch": 3.35, + "learning_rate": 6.645218879012163e-06, + "loss": 1.6528, + "step": 90200 + }, + { + "epoch": 3.35, + "eval_loss": 1.654852271080017, + "eval_runtime": 16.8314, + "eval_samples_per_second": 59.413, + "eval_steps_per_second": 3.743, + "step": 90200 + }, + { + "epoch": 3.36, + "learning_rate": 6.644846952058617e-06, + "loss": 1.7528, + "step": 90210 + }, + { + "epoch": 3.36, + "learning_rate": 6.644475025105069e-06, + "loss": 1.7319, + "step": 90220 + }, + { + "epoch": 3.36, + "learning_rate": 6.644103098151523e-06, + "loss": 1.5551, + "step": 90230 + }, + { + "epoch": 3.36, + "learning_rate": 6.643731171197977e-06, + "loss": 1.7007, + "step": 90240 + }, + { + "epoch": 3.36, + "learning_rate": 6.643359244244431e-06, + "loss": 1.625, + "step": 90250 + }, + { + "epoch": 3.36, + "learning_rate": 6.642987317290884e-06, + "loss": 1.6513, + "step": 90260 + }, + { + "epoch": 3.36, + "learning_rate": 6.642615390337338e-06, + "loss": 1.6616, + "step": 90270 + }, + { + "epoch": 3.36, + "learning_rate": 6.642243463383792e-06, + "loss": 1.5775, + "step": 90280 + }, + { + "epoch": 3.36, + "learning_rate": 6.641871536430245e-06, + "loss": 1.7891, + "step": 90290 + }, + { + "epoch": 3.36, + "learning_rate": 6.6414996094767e-06, + "loss": 1.6008, + "step": 90300 + }, + { + "epoch": 3.36, + "eval_loss": 1.6551555395126343, + "eval_runtime": 16.8517, + "eval_samples_per_second": 59.341, + "eval_steps_per_second": 3.738, + "step": 90300 + }, + { + "epoch": 3.36, + "learning_rate": 6.641127682523153e-06, + "loss": 1.7235, + "step": 90310 + }, + { + "epoch": 3.36, + "learning_rate": 6.6407557555696065e-06, + "loss": 1.8066, + "step": 90320 + }, + { + "epoch": 3.36, + "learning_rate": 6.640383828616061e-06, + "loss": 1.7894, + "step": 90330 + }, + { + "epoch": 3.36, + "learning_rate": 6.640011901662514e-06, + "loss": 1.6753, + "step": 90340 + }, + { + "epoch": 3.36, + "learning_rate": 6.639639974708968e-06, + "loss": 1.6463, + "step": 90350 + }, + { + "epoch": 3.36, + "learning_rate": 6.639268047755422e-06, + "loss": 1.7795, + "step": 90360 + }, + { + "epoch": 3.36, + "learning_rate": 6.6388961208018755e-06, + "loss": 1.7204, + "step": 90370 + }, + { + "epoch": 3.36, + "learning_rate": 6.638524193848329e-06, + "loss": 1.5891, + "step": 90380 + }, + { + "epoch": 3.36, + "learning_rate": 6.638152266894783e-06, + "loss": 1.6029, + "step": 90390 + }, + { + "epoch": 3.36, + "learning_rate": 6.637780339941237e-06, + "loss": 1.6561, + "step": 90400 + }, + { + "epoch": 3.36, + "eval_loss": 1.655495047569275, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 90400 + }, + { + "epoch": 3.36, + "learning_rate": 6.637408412987689e-06, + "loss": 1.6654, + "step": 90410 + }, + { + "epoch": 3.36, + "learning_rate": 6.637036486034143e-06, + "loss": 1.621, + "step": 90420 + }, + { + "epoch": 3.36, + "learning_rate": 6.636664559080597e-06, + "loss": 1.8071, + "step": 90430 + }, + { + "epoch": 3.36, + "learning_rate": 6.6362926321270505e-06, + "loss": 1.5876, + "step": 90440 + }, + { + "epoch": 3.36, + "learning_rate": 6.635920705173504e-06, + "loss": 1.848, + "step": 90450 + }, + { + "epoch": 3.36, + "learning_rate": 6.635548778219958e-06, + "loss": 1.7242, + "step": 90460 + }, + { + "epoch": 3.36, + "learning_rate": 6.635176851266412e-06, + "loss": 1.7082, + "step": 90470 + }, + { + "epoch": 3.37, + "learning_rate": 6.634804924312865e-06, + "loss": 1.6351, + "step": 90480 + }, + { + "epoch": 3.37, + "learning_rate": 6.6344329973593195e-06, + "loss": 1.6889, + "step": 90490 + }, + { + "epoch": 3.37, + "learning_rate": 6.634061070405773e-06, + "loss": 1.6855, + "step": 90500 + }, + { + "epoch": 3.37, + "eval_loss": 1.6551867723464966, + "eval_runtime": 16.8505, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 90500 + }, + { + "epoch": 3.37, + "learning_rate": 6.6336891434522265e-06, + "loss": 1.5874, + "step": 90510 + }, + { + "epoch": 3.37, + "learning_rate": 6.63331721649868e-06, + "loss": 1.6359, + "step": 90520 + }, + { + "epoch": 3.37, + "learning_rate": 6.632945289545134e-06, + "loss": 1.763, + "step": 90530 + }, + { + "epoch": 3.37, + "learning_rate": 6.632573362591588e-06, + "loss": 1.8315, + "step": 90540 + }, + { + "epoch": 3.37, + "learning_rate": 6.632201435638041e-06, + "loss": 1.7565, + "step": 90550 + }, + { + "epoch": 3.37, + "learning_rate": 6.6318295086844954e-06, + "loss": 1.6771, + "step": 90560 + }, + { + "epoch": 3.37, + "learning_rate": 6.631457581730949e-06, + "loss": 1.7112, + "step": 90570 + }, + { + "epoch": 3.37, + "learning_rate": 6.631085654777402e-06, + "loss": 1.5535, + "step": 90580 + }, + { + "epoch": 3.37, + "learning_rate": 6.630713727823857e-06, + "loss": 1.7249, + "step": 90590 + }, + { + "epoch": 3.37, + "learning_rate": 6.630341800870309e-06, + "loss": 1.5957, + "step": 90600 + }, + { + "epoch": 3.37, + "eval_loss": 1.654153823852539, + "eval_runtime": 16.8273, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 90600 + }, + { + "epoch": 3.37, + "learning_rate": 6.629969873916763e-06, + "loss": 1.7366, + "step": 90610 + }, + { + "epoch": 3.37, + "learning_rate": 6.629597946963216e-06, + "loss": 1.7659, + "step": 90620 + }, + { + "epoch": 3.37, + "learning_rate": 6.6292260200096705e-06, + "loss": 1.7112, + "step": 90630 + }, + { + "epoch": 3.37, + "learning_rate": 6.628854093056124e-06, + "loss": 1.7071, + "step": 90640 + }, + { + "epoch": 3.37, + "learning_rate": 6.6284821661025774e-06, + "loss": 1.6656, + "step": 90650 + }, + { + "epoch": 3.37, + "learning_rate": 6.628110239149032e-06, + "loss": 1.6194, + "step": 90660 + }, + { + "epoch": 3.37, + "learning_rate": 6.627738312195485e-06, + "loss": 1.6598, + "step": 90670 + }, + { + "epoch": 3.37, + "learning_rate": 6.627366385241939e-06, + "loss": 1.6788, + "step": 90680 + }, + { + "epoch": 3.37, + "learning_rate": 6.626994458288393e-06, + "loss": 1.8092, + "step": 90690 + }, + { + "epoch": 3.37, + "learning_rate": 6.626622531334846e-06, + "loss": 1.8595, + "step": 90700 + }, + { + "epoch": 3.37, + "eval_loss": 1.6550025939941406, + "eval_runtime": 16.8319, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 90700 + }, + { + "epoch": 3.37, + "learning_rate": 6.6262506043813e-06, + "loss": 1.7865, + "step": 90710 + }, + { + "epoch": 3.37, + "learning_rate": 6.625878677427754e-06, + "loss": 1.7022, + "step": 90720 + }, + { + "epoch": 3.37, + "learning_rate": 6.625506750474208e-06, + "loss": 1.6299, + "step": 90730 + }, + { + "epoch": 3.37, + "learning_rate": 6.625134823520661e-06, + "loss": 1.7352, + "step": 90740 + }, + { + "epoch": 3.38, + "learning_rate": 6.624762896567115e-06, + "loss": 1.5795, + "step": 90750 + }, + { + "epoch": 3.38, + "learning_rate": 6.624390969613569e-06, + "loss": 1.7824, + "step": 90760 + }, + { + "epoch": 3.38, + "learning_rate": 6.624019042660022e-06, + "loss": 1.6434, + "step": 90770 + }, + { + "epoch": 3.38, + "learning_rate": 6.623647115706477e-06, + "loss": 1.6903, + "step": 90780 + }, + { + "epoch": 3.38, + "learning_rate": 6.623275188752929e-06, + "loss": 1.6501, + "step": 90790 + }, + { + "epoch": 3.38, + "learning_rate": 6.622903261799383e-06, + "loss": 1.7146, + "step": 90800 + }, + { + "epoch": 3.38, + "eval_loss": 1.654367208480835, + "eval_runtime": 16.842, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 90800 + }, + { + "epoch": 3.38, + "learning_rate": 6.622531334845836e-06, + "loss": 1.7219, + "step": 90810 + }, + { + "epoch": 3.38, + "learning_rate": 6.6221594078922905e-06, + "loss": 1.7919, + "step": 90820 + }, + { + "epoch": 3.38, + "learning_rate": 6.621787480938744e-06, + "loss": 1.6705, + "step": 90830 + }, + { + "epoch": 3.38, + "learning_rate": 6.621415553985197e-06, + "loss": 1.6231, + "step": 90840 + }, + { + "epoch": 3.38, + "learning_rate": 6.621043627031652e-06, + "loss": 1.6134, + "step": 90850 + }, + { + "epoch": 3.38, + "learning_rate": 6.620671700078105e-06, + "loss": 1.6495, + "step": 90860 + }, + { + "epoch": 3.38, + "learning_rate": 6.620299773124559e-06, + "loss": 1.7226, + "step": 90870 + }, + { + "epoch": 3.38, + "learning_rate": 6.619927846171013e-06, + "loss": 1.6782, + "step": 90880 + }, + { + "epoch": 3.38, + "learning_rate": 6.619555919217466e-06, + "loss": 1.605, + "step": 90890 + }, + { + "epoch": 3.38, + "learning_rate": 6.61918399226392e-06, + "loss": 1.6588, + "step": 90900 + }, + { + "epoch": 3.38, + "eval_loss": 1.6551775932312012, + "eval_runtime": 16.8367, + "eval_samples_per_second": 59.394, + "eval_steps_per_second": 3.742, + "step": 90900 + }, + { + "epoch": 3.38, + "learning_rate": 6.618812065310374e-06, + "loss": 1.6778, + "step": 90910 + }, + { + "epoch": 3.38, + "learning_rate": 6.618440138356828e-06, + "loss": 1.6134, + "step": 90920 + }, + { + "epoch": 3.38, + "learning_rate": 6.618068211403281e-06, + "loss": 1.6216, + "step": 90930 + }, + { + "epoch": 3.38, + "learning_rate": 6.617696284449735e-06, + "loss": 1.667, + "step": 90940 + }, + { + "epoch": 3.38, + "learning_rate": 6.617324357496189e-06, + "loss": 1.7389, + "step": 90950 + }, + { + "epoch": 3.38, + "learning_rate": 6.616952430542642e-06, + "loss": 1.7005, + "step": 90960 + }, + { + "epoch": 3.38, + "learning_rate": 6.616580503589095e-06, + "loss": 1.8229, + "step": 90970 + }, + { + "epoch": 3.38, + "learning_rate": 6.616208576635549e-06, + "loss": 1.5106, + "step": 90980 + }, + { + "epoch": 3.38, + "learning_rate": 6.615836649682003e-06, + "loss": 1.6799, + "step": 90990 + }, + { + "epoch": 3.38, + "learning_rate": 6.615464722728456e-06, + "loss": 1.7253, + "step": 91000 + }, + { + "epoch": 3.38, + "eval_loss": 1.6549677848815918, + "eval_runtime": 16.8422, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 91000 + }, + { + "epoch": 3.38, + "learning_rate": 6.6150927957749104e-06, + "loss": 1.7169, + "step": 91010 + }, + { + "epoch": 3.39, + "learning_rate": 6.614720868821364e-06, + "loss": 1.6721, + "step": 91020 + }, + { + "epoch": 3.39, + "learning_rate": 6.614348941867817e-06, + "loss": 1.6831, + "step": 91030 + }, + { + "epoch": 3.39, + "learning_rate": 6.613977014914272e-06, + "loss": 1.7258, + "step": 91040 + }, + { + "epoch": 3.39, + "learning_rate": 6.613605087960725e-06, + "loss": 1.647, + "step": 91050 + }, + { + "epoch": 3.39, + "learning_rate": 6.6132331610071786e-06, + "loss": 1.6725, + "step": 91060 + }, + { + "epoch": 3.39, + "learning_rate": 6.612861234053632e-06, + "loss": 1.6106, + "step": 91070 + }, + { + "epoch": 3.39, + "learning_rate": 6.612489307100086e-06, + "loss": 1.5612, + "step": 91080 + }, + { + "epoch": 3.39, + "learning_rate": 6.61211738014654e-06, + "loss": 1.7389, + "step": 91090 + }, + { + "epoch": 3.39, + "learning_rate": 6.611745453192993e-06, + "loss": 1.7466, + "step": 91100 + }, + { + "epoch": 3.39, + "eval_loss": 1.6554664373397827, + "eval_runtime": 16.8378, + "eval_samples_per_second": 59.39, + "eval_steps_per_second": 3.742, + "step": 91100 + }, + { + "epoch": 3.39, + "learning_rate": 6.6113735262394476e-06, + "loss": 1.6276, + "step": 91110 + }, + { + "epoch": 3.39, + "learning_rate": 6.611001599285901e-06, + "loss": 1.7435, + "step": 91120 + }, + { + "epoch": 3.39, + "learning_rate": 6.6106296723323545e-06, + "loss": 1.7055, + "step": 91130 + }, + { + "epoch": 3.39, + "learning_rate": 6.610257745378809e-06, + "loss": 1.4969, + "step": 91140 + }, + { + "epoch": 3.39, + "learning_rate": 6.609885818425262e-06, + "loss": 1.786, + "step": 91150 + }, + { + "epoch": 3.39, + "learning_rate": 6.609513891471715e-06, + "loss": 1.7569, + "step": 91160 + }, + { + "epoch": 3.39, + "learning_rate": 6.609141964518168e-06, + "loss": 1.6789, + "step": 91170 + }, + { + "epoch": 3.39, + "learning_rate": 6.608770037564623e-06, + "loss": 1.8025, + "step": 91180 + }, + { + "epoch": 3.39, + "learning_rate": 6.608398110611076e-06, + "loss": 1.7715, + "step": 91190 + }, + { + "epoch": 3.39, + "learning_rate": 6.6080261836575295e-06, + "loss": 1.7068, + "step": 91200 + }, + { + "epoch": 3.39, + "eval_loss": 1.6540846824645996, + "eval_runtime": 16.8614, + "eval_samples_per_second": 59.307, + "eval_steps_per_second": 3.736, + "step": 91200 + }, + { + "epoch": 3.39, + "learning_rate": 6.607654256703984e-06, + "loss": 1.6478, + "step": 91210 + }, + { + "epoch": 3.39, + "learning_rate": 6.607282329750437e-06, + "loss": 1.7415, + "step": 91220 + }, + { + "epoch": 3.39, + "learning_rate": 6.606910402796891e-06, + "loss": 1.8341, + "step": 91230 + }, + { + "epoch": 3.39, + "learning_rate": 6.606538475843345e-06, + "loss": 1.8067, + "step": 91240 + }, + { + "epoch": 3.39, + "learning_rate": 6.6061665488897985e-06, + "loss": 1.6409, + "step": 91250 + }, + { + "epoch": 3.39, + "learning_rate": 6.605794621936252e-06, + "loss": 1.6285, + "step": 91260 + }, + { + "epoch": 3.39, + "learning_rate": 6.605422694982706e-06, + "loss": 1.6885, + "step": 91270 + }, + { + "epoch": 3.39, + "learning_rate": 6.60505076802916e-06, + "loss": 1.7267, + "step": 91280 + }, + { + "epoch": 3.4, + "learning_rate": 6.604678841075613e-06, + "loss": 1.7539, + "step": 91290 + }, + { + "epoch": 3.4, + "learning_rate": 6.6043069141220675e-06, + "loss": 1.6513, + "step": 91300 + }, + { + "epoch": 3.4, + "eval_loss": 1.6540874242782593, + "eval_runtime": 16.8526, + "eval_samples_per_second": 59.338, + "eval_steps_per_second": 3.738, + "step": 91300 + }, + { + "epoch": 3.4, + "learning_rate": 6.603934987168521e-06, + "loss": 1.8151, + "step": 91310 + }, + { + "epoch": 3.4, + "learning_rate": 6.6035630602149744e-06, + "loss": 1.7027, + "step": 91320 + }, + { + "epoch": 3.4, + "learning_rate": 6.603191133261429e-06, + "loss": 1.5873, + "step": 91330 + }, + { + "epoch": 3.4, + "learning_rate": 6.602819206307882e-06, + "loss": 1.7517, + "step": 91340 + }, + { + "epoch": 3.4, + "learning_rate": 6.602447279354335e-06, + "loss": 1.8144, + "step": 91350 + }, + { + "epoch": 3.4, + "learning_rate": 6.602075352400788e-06, + "loss": 1.7729, + "step": 91360 + }, + { + "epoch": 3.4, + "learning_rate": 6.601703425447243e-06, + "loss": 1.6932, + "step": 91370 + }, + { + "epoch": 3.4, + "learning_rate": 6.601331498493696e-06, + "loss": 1.6655, + "step": 91380 + }, + { + "epoch": 3.4, + "learning_rate": 6.6009595715401495e-06, + "loss": 1.7056, + "step": 91390 + }, + { + "epoch": 3.4, + "learning_rate": 6.600587644586604e-06, + "loss": 1.7063, + "step": 91400 + }, + { + "epoch": 3.4, + "eval_loss": 1.6545311212539673, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 91400 + }, + { + "epoch": 3.4, + "learning_rate": 6.600215717633057e-06, + "loss": 1.6012, + "step": 91410 + }, + { + "epoch": 3.4, + "learning_rate": 6.599843790679511e-06, + "loss": 1.6863, + "step": 91420 + }, + { + "epoch": 3.4, + "learning_rate": 6.599471863725965e-06, + "loss": 1.8684, + "step": 91430 + }, + { + "epoch": 3.4, + "learning_rate": 6.5990999367724185e-06, + "loss": 1.6227, + "step": 91440 + }, + { + "epoch": 3.4, + "learning_rate": 6.598728009818872e-06, + "loss": 1.6423, + "step": 91450 + }, + { + "epoch": 3.4, + "learning_rate": 6.598356082865326e-06, + "loss": 1.7345, + "step": 91460 + }, + { + "epoch": 3.4, + "learning_rate": 6.59798415591178e-06, + "loss": 1.7064, + "step": 91470 + }, + { + "epoch": 3.4, + "learning_rate": 6.597612228958233e-06, + "loss": 1.7646, + "step": 91480 + }, + { + "epoch": 3.4, + "learning_rate": 6.5972403020046875e-06, + "loss": 1.6395, + "step": 91490 + }, + { + "epoch": 3.4, + "learning_rate": 6.596868375051141e-06, + "loss": 1.7336, + "step": 91500 + }, + { + "epoch": 3.4, + "eval_loss": 1.6544525623321533, + "eval_runtime": 16.8183, + "eval_samples_per_second": 59.459, + "eval_steps_per_second": 3.746, + "step": 91500 + }, + { + "epoch": 3.4, + "learning_rate": 6.596496448097594e-06, + "loss": 1.6091, + "step": 91510 + }, + { + "epoch": 3.4, + "learning_rate": 6.596124521144049e-06, + "loss": 1.6686, + "step": 91520 + }, + { + "epoch": 3.4, + "learning_rate": 6.595752594190502e-06, + "loss": 1.6088, + "step": 91530 + }, + { + "epoch": 3.4, + "learning_rate": 6.595380667236955e-06, + "loss": 1.8401, + "step": 91540 + }, + { + "epoch": 3.4, + "learning_rate": 6.595008740283408e-06, + "loss": 1.6742, + "step": 91550 + }, + { + "epoch": 3.41, + "learning_rate": 6.5946368133298625e-06, + "loss": 1.7455, + "step": 91560 + }, + { + "epoch": 3.41, + "learning_rate": 6.594264886376316e-06, + "loss": 1.5512, + "step": 91570 + }, + { + "epoch": 3.41, + "learning_rate": 6.5938929594227695e-06, + "loss": 1.7624, + "step": 91580 + }, + { + "epoch": 3.41, + "learning_rate": 6.593521032469224e-06, + "loss": 1.6436, + "step": 91590 + }, + { + "epoch": 3.41, + "learning_rate": 6.593149105515677e-06, + "loss": 1.6632, + "step": 91600 + }, + { + "epoch": 3.41, + "eval_loss": 1.6537292003631592, + "eval_runtime": 16.8345, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 91600 + }, + { + "epoch": 3.41, + "learning_rate": 6.592777178562131e-06, + "loss": 1.725, + "step": 91610 + }, + { + "epoch": 3.41, + "learning_rate": 6.592405251608585e-06, + "loss": 1.7339, + "step": 91620 + }, + { + "epoch": 3.41, + "learning_rate": 6.5920333246550384e-06, + "loss": 1.6478, + "step": 91630 + }, + { + "epoch": 3.41, + "learning_rate": 6.591661397701492e-06, + "loss": 1.6596, + "step": 91640 + }, + { + "epoch": 3.41, + "learning_rate": 6.591289470747945e-06, + "loss": 1.7546, + "step": 91650 + }, + { + "epoch": 3.41, + "learning_rate": 6.5909175437944e-06, + "loss": 1.6206, + "step": 91660 + }, + { + "epoch": 3.41, + "learning_rate": 6.590545616840853e-06, + "loss": 1.7893, + "step": 91670 + }, + { + "epoch": 3.41, + "learning_rate": 6.590173689887307e-06, + "loss": 1.7638, + "step": 91680 + }, + { + "epoch": 3.41, + "learning_rate": 6.589801762933761e-06, + "loss": 1.7244, + "step": 91690 + }, + { + "epoch": 3.41, + "learning_rate": 6.589429835980214e-06, + "loss": 1.7526, + "step": 91700 + }, + { + "epoch": 3.41, + "eval_loss": 1.654150128364563, + "eval_runtime": 16.8259, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 91700 + }, + { + "epoch": 3.41, + "learning_rate": 6.589057909026668e-06, + "loss": 1.6227, + "step": 91710 + }, + { + "epoch": 3.41, + "learning_rate": 6.5886859820731204e-06, + "loss": 1.8555, + "step": 91720 + }, + { + "epoch": 3.41, + "learning_rate": 6.588314055119575e-06, + "loss": 1.7353, + "step": 91730 + }, + { + "epoch": 3.41, + "learning_rate": 6.587942128166028e-06, + "loss": 1.5628, + "step": 91740 + }, + { + "epoch": 3.41, + "learning_rate": 6.587570201212482e-06, + "loss": 1.7007, + "step": 91750 + }, + { + "epoch": 3.41, + "learning_rate": 6.587198274258936e-06, + "loss": 1.5396, + "step": 91760 + }, + { + "epoch": 3.41, + "learning_rate": 6.586826347305389e-06, + "loss": 1.6639, + "step": 91770 + }, + { + "epoch": 3.41, + "learning_rate": 6.586454420351843e-06, + "loss": 1.7151, + "step": 91780 + }, + { + "epoch": 3.41, + "learning_rate": 6.586082493398297e-06, + "loss": 1.6097, + "step": 91790 + }, + { + "epoch": 3.41, + "learning_rate": 6.585710566444751e-06, + "loss": 1.488, + "step": 91800 + }, + { + "epoch": 3.41, + "eval_loss": 1.65444016456604, + "eval_runtime": 16.824, + "eval_samples_per_second": 59.439, + "eval_steps_per_second": 3.745, + "step": 91800 + }, + { + "epoch": 3.41, + "learning_rate": 6.585338639491204e-06, + "loss": 1.6974, + "step": 91810 + }, + { + "epoch": 3.42, + "learning_rate": 6.584966712537658e-06, + "loss": 1.5625, + "step": 91820 + }, + { + "epoch": 3.42, + "learning_rate": 6.584594785584112e-06, + "loss": 1.6647, + "step": 91830 + }, + { + "epoch": 3.42, + "learning_rate": 6.584222858630565e-06, + "loss": 1.7086, + "step": 91840 + }, + { + "epoch": 3.42, + "learning_rate": 6.58385093167702e-06, + "loss": 1.5903, + "step": 91850 + }, + { + "epoch": 3.42, + "learning_rate": 6.583479004723473e-06, + "loss": 1.622, + "step": 91860 + }, + { + "epoch": 3.42, + "learning_rate": 6.5831070777699265e-06, + "loss": 1.8367, + "step": 91870 + }, + { + "epoch": 3.42, + "learning_rate": 6.582735150816381e-06, + "loss": 1.7028, + "step": 91880 + }, + { + "epoch": 3.42, + "learning_rate": 6.582363223862834e-06, + "loss": 1.799, + "step": 91890 + }, + { + "epoch": 3.42, + "learning_rate": 6.581991296909288e-06, + "loss": 1.7506, + "step": 91900 + }, + { + "epoch": 3.42, + "eval_loss": 1.6530619859695435, + "eval_runtime": 16.8429, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 91900 + }, + { + "epoch": 3.42, + "learning_rate": 6.58161936995574e-06, + "loss": 1.7196, + "step": 91910 + }, + { + "epoch": 3.42, + "learning_rate": 6.581247443002195e-06, + "loss": 1.8051, + "step": 91920 + }, + { + "epoch": 3.42, + "learning_rate": 6.580875516048648e-06, + "loss": 1.6131, + "step": 91930 + }, + { + "epoch": 3.42, + "learning_rate": 6.580503589095102e-06, + "loss": 1.641, + "step": 91940 + }, + { + "epoch": 3.42, + "learning_rate": 6.580131662141556e-06, + "loss": 1.5755, + "step": 91950 + }, + { + "epoch": 3.42, + "learning_rate": 6.579759735188009e-06, + "loss": 1.703, + "step": 91960 + }, + { + "epoch": 3.42, + "learning_rate": 6.579387808234463e-06, + "loss": 1.6353, + "step": 91970 + }, + { + "epoch": 3.42, + "learning_rate": 6.579015881280917e-06, + "loss": 1.7731, + "step": 91980 + }, + { + "epoch": 3.42, + "learning_rate": 6.578643954327371e-06, + "loss": 1.6088, + "step": 91990 + }, + { + "epoch": 3.42, + "learning_rate": 6.578272027373824e-06, + "loss": 1.6997, + "step": 92000 + }, + { + "epoch": 3.42, + "eval_loss": 1.652938961982727, + "eval_runtime": 16.8375, + "eval_samples_per_second": 59.391, + "eval_steps_per_second": 3.742, + "step": 92000 + }, + { + "epoch": 3.42, + "learning_rate": 6.577900100420278e-06, + "loss": 1.619, + "step": 92010 + }, + { + "epoch": 3.42, + "learning_rate": 6.577528173466732e-06, + "loss": 1.7256, + "step": 92020 + }, + { + "epoch": 3.42, + "learning_rate": 6.577156246513185e-06, + "loss": 1.7259, + "step": 92030 + }, + { + "epoch": 3.42, + "learning_rate": 6.57678431955964e-06, + "loss": 1.9894, + "step": 92040 + }, + { + "epoch": 3.42, + "learning_rate": 6.576412392606093e-06, + "loss": 1.6447, + "step": 92050 + }, + { + "epoch": 3.42, + "learning_rate": 6.5760404656525465e-06, + "loss": 1.7579, + "step": 92060 + }, + { + "epoch": 3.42, + "learning_rate": 6.575668538699001e-06, + "loss": 1.7648, + "step": 92070 + }, + { + "epoch": 3.42, + "learning_rate": 6.575296611745454e-06, + "loss": 1.6926, + "step": 92080 + }, + { + "epoch": 3.43, + "learning_rate": 6.574924684791908e-06, + "loss": 1.6169, + "step": 92090 + }, + { + "epoch": 3.43, + "learning_rate": 6.57455275783836e-06, + "loss": 1.7174, + "step": 92100 + }, + { + "epoch": 3.43, + "eval_loss": 1.6528751850128174, + "eval_runtime": 16.8391, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 92100 + }, + { + "epoch": 3.43, + "learning_rate": 6.574180830884815e-06, + "loss": 1.7527, + "step": 92110 + }, + { + "epoch": 3.43, + "learning_rate": 6.573808903931268e-06, + "loss": 1.6604, + "step": 92120 + }, + { + "epoch": 3.43, + "learning_rate": 6.5734369769777216e-06, + "loss": 1.7233, + "step": 92130 + }, + { + "epoch": 3.43, + "learning_rate": 6.573065050024176e-06, + "loss": 1.6246, + "step": 92140 + }, + { + "epoch": 3.43, + "learning_rate": 6.572693123070629e-06, + "loss": 1.7368, + "step": 92150 + }, + { + "epoch": 3.43, + "learning_rate": 6.572321196117083e-06, + "loss": 1.6586, + "step": 92160 + }, + { + "epoch": 3.43, + "learning_rate": 6.571949269163537e-06, + "loss": 1.6716, + "step": 92170 + }, + { + "epoch": 3.43, + "learning_rate": 6.5715773422099906e-06, + "loss": 1.7034, + "step": 92180 + }, + { + "epoch": 3.43, + "learning_rate": 6.571205415256444e-06, + "loss": 1.7317, + "step": 92190 + }, + { + "epoch": 3.43, + "learning_rate": 6.570833488302898e-06, + "loss": 1.7361, + "step": 92200 + }, + { + "epoch": 3.43, + "eval_loss": 1.6534653902053833, + "eval_runtime": 16.8441, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 92200 + }, + { + "epoch": 3.43, + "learning_rate": 6.570461561349352e-06, + "loss": 1.589, + "step": 92210 + }, + { + "epoch": 3.43, + "learning_rate": 6.570089634395805e-06, + "loss": 1.635, + "step": 92220 + }, + { + "epoch": 3.43, + "learning_rate": 6.569717707442259e-06, + "loss": 1.7393, + "step": 92230 + }, + { + "epoch": 3.43, + "learning_rate": 6.569345780488713e-06, + "loss": 1.7486, + "step": 92240 + }, + { + "epoch": 3.43, + "learning_rate": 6.5689738535351665e-06, + "loss": 1.7294, + "step": 92250 + }, + { + "epoch": 3.43, + "learning_rate": 6.56860192658162e-06, + "loss": 1.5794, + "step": 92260 + }, + { + "epoch": 3.43, + "learning_rate": 6.568229999628074e-06, + "loss": 1.7594, + "step": 92270 + }, + { + "epoch": 3.43, + "learning_rate": 6.567858072674528e-06, + "loss": 1.6339, + "step": 92280 + }, + { + "epoch": 3.43, + "learning_rate": 6.56748614572098e-06, + "loss": 1.6087, + "step": 92290 + }, + { + "epoch": 3.43, + "learning_rate": 6.567114218767434e-06, + "loss": 1.6966, + "step": 92300 + }, + { + "epoch": 3.43, + "eval_loss": 1.6530312299728394, + "eval_runtime": 16.8328, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 92300 + }, + { + "epoch": 3.43, + "learning_rate": 6.566742291813888e-06, + "loss": 1.6549, + "step": 92310 + }, + { + "epoch": 3.43, + "learning_rate": 6.5663703648603415e-06, + "loss": 1.6222, + "step": 92320 + }, + { + "epoch": 3.43, + "learning_rate": 6.565998437906795e-06, + "loss": 1.6627, + "step": 92330 + }, + { + "epoch": 3.43, + "learning_rate": 6.565626510953249e-06, + "loss": 1.6506, + "step": 92340 + }, + { + "epoch": 3.43, + "learning_rate": 6.565254583999703e-06, + "loss": 1.8613, + "step": 92350 + }, + { + "epoch": 3.44, + "learning_rate": 6.564882657046156e-06, + "loss": 1.7426, + "step": 92360 + }, + { + "epoch": 3.44, + "learning_rate": 6.5645107300926105e-06, + "loss": 1.6843, + "step": 92370 + }, + { + "epoch": 3.44, + "learning_rate": 6.564138803139064e-06, + "loss": 1.7868, + "step": 92380 + }, + { + "epoch": 3.44, + "learning_rate": 6.5637668761855174e-06, + "loss": 1.695, + "step": 92390 + }, + { + "epoch": 3.44, + "learning_rate": 6.563394949231972e-06, + "loss": 1.5893, + "step": 92400 + }, + { + "epoch": 3.44, + "eval_loss": 1.6523021459579468, + "eval_runtime": 16.8469, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 92400 + }, + { + "epoch": 3.44, + "learning_rate": 6.563023022278425e-06, + "loss": 1.5749, + "step": 92410 + }, + { + "epoch": 3.44, + "learning_rate": 6.562651095324879e-06, + "loss": 1.6835, + "step": 92420 + }, + { + "epoch": 3.44, + "learning_rate": 6.562279168371333e-06, + "loss": 1.7035, + "step": 92430 + }, + { + "epoch": 3.44, + "learning_rate": 6.5619072414177864e-06, + "loss": 1.545, + "step": 92440 + }, + { + "epoch": 3.44, + "learning_rate": 6.56153531446424e-06, + "loss": 1.6375, + "step": 92450 + }, + { + "epoch": 3.44, + "learning_rate": 6.561163387510694e-06, + "loss": 1.7228, + "step": 92460 + }, + { + "epoch": 3.44, + "learning_rate": 6.560791460557148e-06, + "loss": 1.6715, + "step": 92470 + }, + { + "epoch": 3.44, + "learning_rate": 6.5604195336036e-06, + "loss": 1.7454, + "step": 92480 + }, + { + "epoch": 3.44, + "learning_rate": 6.560047606650054e-06, + "loss": 1.8307, + "step": 92490 + }, + { + "epoch": 3.44, + "learning_rate": 6.559675679696508e-06, + "loss": 1.786, + "step": 92500 + }, + { + "epoch": 3.44, + "eval_loss": 1.6531330347061157, + "eval_runtime": 16.8279, + "eval_samples_per_second": 59.425, + "eval_steps_per_second": 3.744, + "step": 92500 + }, + { + "epoch": 3.44, + "learning_rate": 6.5593037527429615e-06, + "loss": 1.5686, + "step": 92510 + }, + { + "epoch": 3.44, + "learning_rate": 6.558931825789415e-06, + "loss": 1.5145, + "step": 92520 + }, + { + "epoch": 3.44, + "learning_rate": 6.558559898835869e-06, + "loss": 1.6463, + "step": 92530 + }, + { + "epoch": 3.44, + "learning_rate": 6.558187971882323e-06, + "loss": 1.7134, + "step": 92540 + }, + { + "epoch": 3.44, + "learning_rate": 6.557816044928776e-06, + "loss": 1.6867, + "step": 92550 + }, + { + "epoch": 3.44, + "learning_rate": 6.5574441179752305e-06, + "loss": 1.6239, + "step": 92560 + }, + { + "epoch": 3.44, + "learning_rate": 6.557072191021684e-06, + "loss": 1.9833, + "step": 92570 + }, + { + "epoch": 3.44, + "learning_rate": 6.556700264068137e-06, + "loss": 1.6137, + "step": 92580 + }, + { + "epoch": 3.44, + "learning_rate": 6.556328337114592e-06, + "loss": 1.7327, + "step": 92590 + }, + { + "epoch": 3.44, + "learning_rate": 6.555956410161045e-06, + "loss": 1.7302, + "step": 92600 + }, + { + "epoch": 3.44, + "eval_loss": 1.6526292562484741, + "eval_runtime": 16.8193, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 92600 + }, + { + "epoch": 3.44, + "learning_rate": 6.555584483207499e-06, + "loss": 1.6553, + "step": 92610 + }, + { + "epoch": 3.44, + "learning_rate": 6.555212556253953e-06, + "loss": 1.7115, + "step": 92620 + }, + { + "epoch": 3.45, + "learning_rate": 6.554840629300406e-06, + "loss": 1.6243, + "step": 92630 + }, + { + "epoch": 3.45, + "learning_rate": 6.55446870234686e-06, + "loss": 1.7538, + "step": 92640 + }, + { + "epoch": 3.45, + "learning_rate": 6.554096775393314e-06, + "loss": 1.7076, + "step": 92650 + }, + { + "epoch": 3.45, + "learning_rate": 6.553724848439767e-06, + "loss": 1.8299, + "step": 92660 + }, + { + "epoch": 3.45, + "learning_rate": 6.55335292148622e-06, + "loss": 1.6824, + "step": 92670 + }, + { + "epoch": 3.45, + "learning_rate": 6.552980994532674e-06, + "loss": 1.7949, + "step": 92680 + }, + { + "epoch": 3.45, + "learning_rate": 6.552609067579128e-06, + "loss": 1.6959, + "step": 92690 + }, + { + "epoch": 3.45, + "learning_rate": 6.5522371406255814e-06, + "loss": 1.5628, + "step": 92700 + }, + { + "epoch": 3.45, + "eval_loss": 1.6531561613082886, + "eval_runtime": 16.8403, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 92700 + }, + { + "epoch": 3.45, + "learning_rate": 6.551865213672035e-06, + "loss": 1.7181, + "step": 92710 + }, + { + "epoch": 3.45, + "learning_rate": 6.551493286718489e-06, + "loss": 1.6885, + "step": 92720 + }, + { + "epoch": 3.45, + "learning_rate": 6.551121359764943e-06, + "loss": 1.6573, + "step": 92730 + }, + { + "epoch": 3.45, + "learning_rate": 6.550749432811396e-06, + "loss": 1.8344, + "step": 92740 + }, + { + "epoch": 3.45, + "learning_rate": 6.5503775058578504e-06, + "loss": 1.8606, + "step": 92750 + }, + { + "epoch": 3.45, + "learning_rate": 6.550005578904304e-06, + "loss": 1.7318, + "step": 92760 + }, + { + "epoch": 3.45, + "learning_rate": 6.549633651950757e-06, + "loss": 1.6927, + "step": 92770 + }, + { + "epoch": 3.45, + "learning_rate": 6.549261724997212e-06, + "loss": 1.6765, + "step": 92780 + }, + { + "epoch": 3.45, + "learning_rate": 6.548889798043665e-06, + "loss": 1.705, + "step": 92790 + }, + { + "epoch": 3.45, + "learning_rate": 6.548517871090119e-06, + "loss": 1.6822, + "step": 92800 + }, + { + "epoch": 3.45, + "eval_loss": 1.65276300907135, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 92800 + }, + { + "epoch": 3.45, + "learning_rate": 6.548145944136572e-06, + "loss": 1.6883, + "step": 92810 + }, + { + "epoch": 3.45, + "learning_rate": 6.547774017183026e-06, + "loss": 1.8827, + "step": 92820 + }, + { + "epoch": 3.45, + "learning_rate": 6.54740209022948e-06, + "loss": 1.6335, + "step": 92830 + }, + { + "epoch": 3.45, + "learning_rate": 6.547030163275933e-06, + "loss": 1.7025, + "step": 92840 + }, + { + "epoch": 3.45, + "learning_rate": 6.546658236322386e-06, + "loss": 1.7142, + "step": 92850 + }, + { + "epoch": 3.45, + "learning_rate": 6.54628630936884e-06, + "loss": 1.7205, + "step": 92860 + }, + { + "epoch": 3.45, + "learning_rate": 6.545914382415294e-06, + "loss": 1.8544, + "step": 92870 + }, + { + "epoch": 3.45, + "learning_rate": 6.545542455461747e-06, + "loss": 1.6482, + "step": 92880 + }, + { + "epoch": 3.45, + "learning_rate": 6.545170528508201e-06, + "loss": 1.6022, + "step": 92890 + }, + { + "epoch": 3.46, + "learning_rate": 6.544798601554655e-06, + "loss": 1.7056, + "step": 92900 + }, + { + "epoch": 3.46, + "eval_loss": 1.6531232595443726, + "eval_runtime": 16.8265, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 92900 + }, + { + "epoch": 3.46, + "learning_rate": 6.544426674601108e-06, + "loss": 1.777, + "step": 92910 + }, + { + "epoch": 3.46, + "learning_rate": 6.544054747647563e-06, + "loss": 1.4659, + "step": 92920 + }, + { + "epoch": 3.46, + "learning_rate": 6.543682820694016e-06, + "loss": 1.7637, + "step": 92930 + }, + { + "epoch": 3.46, + "learning_rate": 6.5433108937404695e-06, + "loss": 1.8108, + "step": 92940 + }, + { + "epoch": 3.46, + "learning_rate": 6.542938966786924e-06, + "loss": 1.7671, + "step": 92950 + }, + { + "epoch": 3.46, + "learning_rate": 6.542567039833377e-06, + "loss": 1.6911, + "step": 92960 + }, + { + "epoch": 3.46, + "learning_rate": 6.542195112879831e-06, + "loss": 1.6503, + "step": 92970 + }, + { + "epoch": 3.46, + "learning_rate": 6.541823185926285e-06, + "loss": 1.6102, + "step": 92980 + }, + { + "epoch": 3.46, + "learning_rate": 6.5414512589727385e-06, + "loss": 1.8269, + "step": 92990 + }, + { + "epoch": 3.46, + "learning_rate": 6.541079332019192e-06, + "loss": 1.5634, + "step": 93000 + }, + { + "epoch": 3.46, + "eval_loss": 1.6520626544952393, + "eval_runtime": 16.8275, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 93000 + }, + { + "epoch": 3.46, + "learning_rate": 6.540707405065646e-06, + "loss": 1.5497, + "step": 93010 + }, + { + "epoch": 3.46, + "learning_rate": 6.5403354781121e-06, + "loss": 1.6804, + "step": 93020 + }, + { + "epoch": 3.46, + "learning_rate": 6.539963551158553e-06, + "loss": 1.6322, + "step": 93030 + }, + { + "epoch": 3.46, + "learning_rate": 6.539591624205006e-06, + "loss": 1.7863, + "step": 93040 + }, + { + "epoch": 3.46, + "learning_rate": 6.53921969725146e-06, + "loss": 1.6204, + "step": 93050 + }, + { + "epoch": 3.46, + "learning_rate": 6.538847770297914e-06, + "loss": 1.6797, + "step": 93060 + }, + { + "epoch": 3.46, + "learning_rate": 6.538475843344367e-06, + "loss": 1.6241, + "step": 93070 + }, + { + "epoch": 3.46, + "learning_rate": 6.538103916390821e-06, + "loss": 1.7897, + "step": 93080 + }, + { + "epoch": 3.46, + "learning_rate": 6.537731989437275e-06, + "loss": 1.6704, + "step": 93090 + }, + { + "epoch": 3.46, + "learning_rate": 6.537360062483728e-06, + "loss": 1.7373, + "step": 93100 + }, + { + "epoch": 3.46, + "eval_loss": 1.6519262790679932, + "eval_runtime": 16.8693, + "eval_samples_per_second": 59.279, + "eval_steps_per_second": 3.735, + "step": 93100 + }, + { + "epoch": 3.46, + "learning_rate": 6.536988135530183e-06, + "loss": 1.6954, + "step": 93110 + }, + { + "epoch": 3.46, + "learning_rate": 6.536616208576636e-06, + "loss": 1.6417, + "step": 93120 + }, + { + "epoch": 3.46, + "learning_rate": 6.5362442816230895e-06, + "loss": 1.7155, + "step": 93130 + }, + { + "epoch": 3.46, + "learning_rate": 6.535872354669544e-06, + "loss": 1.6308, + "step": 93140 + }, + { + "epoch": 3.46, + "learning_rate": 6.535500427715997e-06, + "loss": 1.6713, + "step": 93150 + }, + { + "epoch": 3.46, + "learning_rate": 6.535128500762451e-06, + "loss": 1.6721, + "step": 93160 + }, + { + "epoch": 3.47, + "learning_rate": 6.534756573808905e-06, + "loss": 1.5905, + "step": 93170 + }, + { + "epoch": 3.47, + "learning_rate": 6.5343846468553585e-06, + "loss": 1.6919, + "step": 93180 + }, + { + "epoch": 3.47, + "learning_rate": 6.534012719901812e-06, + "loss": 1.8847, + "step": 93190 + }, + { + "epoch": 3.47, + "learning_rate": 6.533640792948266e-06, + "loss": 1.6552, + "step": 93200 + }, + { + "epoch": 3.47, + "eval_loss": 1.6516501903533936, + "eval_runtime": 16.8461, + "eval_samples_per_second": 59.361, + "eval_steps_per_second": 3.74, + "step": 93200 + }, + { + "epoch": 3.47, + "learning_rate": 6.53326886599472e-06, + "loss": 1.687, + "step": 93210 + }, + { + "epoch": 3.47, + "learning_rate": 6.532896939041173e-06, + "loss": 1.6837, + "step": 93220 + }, + { + "epoch": 3.47, + "learning_rate": 6.532525012087626e-06, + "loss": 1.7244, + "step": 93230 + }, + { + "epoch": 3.47, + "learning_rate": 6.53215308513408e-06, + "loss": 1.6127, + "step": 93240 + }, + { + "epoch": 3.47, + "learning_rate": 6.5317811581805336e-06, + "loss": 1.5522, + "step": 93250 + }, + { + "epoch": 3.47, + "learning_rate": 6.531409231226987e-06, + "loss": 1.7064, + "step": 93260 + }, + { + "epoch": 3.47, + "learning_rate": 6.531037304273441e-06, + "loss": 1.7624, + "step": 93270 + }, + { + "epoch": 3.47, + "learning_rate": 6.530665377319895e-06, + "loss": 1.6813, + "step": 93280 + }, + { + "epoch": 3.47, + "learning_rate": 6.530293450366348e-06, + "loss": 1.6332, + "step": 93290 + }, + { + "epoch": 3.47, + "learning_rate": 6.5299215234128025e-06, + "loss": 1.6081, + "step": 93300 + }, + { + "epoch": 3.47, + "eval_loss": 1.6519677639007568, + "eval_runtime": 16.8296, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 93300 + }, + { + "epoch": 3.47, + "learning_rate": 6.529549596459256e-06, + "loss": 1.7088, + "step": 93310 + }, + { + "epoch": 3.47, + "learning_rate": 6.5291776695057095e-06, + "loss": 1.7651, + "step": 93320 + }, + { + "epoch": 3.47, + "learning_rate": 6.528805742552164e-06, + "loss": 1.6882, + "step": 93330 + }, + { + "epoch": 3.47, + "learning_rate": 6.528433815598617e-06, + "loss": 1.7396, + "step": 93340 + }, + { + "epoch": 3.47, + "learning_rate": 6.528061888645071e-06, + "loss": 1.6756, + "step": 93350 + }, + { + "epoch": 3.47, + "learning_rate": 6.527689961691525e-06, + "loss": 1.6018, + "step": 93360 + }, + { + "epoch": 3.47, + "learning_rate": 6.5273180347379785e-06, + "loss": 1.6221, + "step": 93370 + }, + { + "epoch": 3.47, + "learning_rate": 6.526946107784432e-06, + "loss": 1.6913, + "step": 93380 + }, + { + "epoch": 3.47, + "learning_rate": 6.526574180830885e-06, + "loss": 1.7328, + "step": 93390 + }, + { + "epoch": 3.47, + "learning_rate": 6.52620225387734e-06, + "loss": 1.7086, + "step": 93400 + }, + { + "epoch": 3.47, + "eval_loss": 1.652590274810791, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 93400 + }, + { + "epoch": 3.47, + "learning_rate": 6.525830326923792e-06, + "loss": 1.8416, + "step": 93410 + }, + { + "epoch": 3.47, + "learning_rate": 6.525458399970246e-06, + "loss": 1.7282, + "step": 93420 + }, + { + "epoch": 3.47, + "learning_rate": 6.525086473016699e-06, + "loss": 1.6129, + "step": 93430 + }, + { + "epoch": 3.48, + "learning_rate": 6.5247145460631535e-06, + "loss": 1.7552, + "step": 93440 + }, + { + "epoch": 3.48, + "learning_rate": 6.524342619109607e-06, + "loss": 1.7169, + "step": 93450 + }, + { + "epoch": 3.48, + "learning_rate": 6.5239706921560604e-06, + "loss": 1.8072, + "step": 93460 + }, + { + "epoch": 3.48, + "learning_rate": 6.523598765202515e-06, + "loss": 1.6743, + "step": 93470 + }, + { + "epoch": 3.48, + "learning_rate": 6.523226838248968e-06, + "loss": 1.6728, + "step": 93480 + }, + { + "epoch": 3.48, + "learning_rate": 6.522854911295422e-06, + "loss": 1.7154, + "step": 93490 + }, + { + "epoch": 3.48, + "learning_rate": 6.522482984341876e-06, + "loss": 1.6646, + "step": 93500 + }, + { + "epoch": 3.48, + "eval_loss": 1.6516062021255493, + "eval_runtime": 16.8226, + "eval_samples_per_second": 59.444, + "eval_steps_per_second": 3.745, + "step": 93500 + }, + { + "epoch": 3.48, + "learning_rate": 6.5221110573883294e-06, + "loss": 1.8064, + "step": 93510 + }, + { + "epoch": 3.48, + "learning_rate": 6.521739130434783e-06, + "loss": 1.7316, + "step": 93520 + }, + { + "epoch": 3.48, + "learning_rate": 6.521367203481237e-06, + "loss": 1.7224, + "step": 93530 + }, + { + "epoch": 3.48, + "learning_rate": 6.520995276527691e-06, + "loss": 1.8187, + "step": 93540 + }, + { + "epoch": 3.48, + "learning_rate": 6.520623349574144e-06, + "loss": 1.6686, + "step": 93550 + }, + { + "epoch": 3.48, + "learning_rate": 6.520251422620598e-06, + "loss": 1.7414, + "step": 93560 + }, + { + "epoch": 3.48, + "learning_rate": 6.519879495667052e-06, + "loss": 1.6093, + "step": 93570 + }, + { + "epoch": 3.48, + "learning_rate": 6.519507568713505e-06, + "loss": 1.6862, + "step": 93580 + }, + { + "epoch": 3.48, + "learning_rate": 6.51913564175996e-06, + "loss": 1.6767, + "step": 93590 + }, + { + "epoch": 3.48, + "learning_rate": 6.518763714806412e-06, + "loss": 1.7535, + "step": 93600 + }, + { + "epoch": 3.48, + "eval_loss": 1.6513029336929321, + "eval_runtime": 16.8096, + "eval_samples_per_second": 59.49, + "eval_steps_per_second": 3.748, + "step": 93600 + }, + { + "epoch": 3.48, + "learning_rate": 6.518391787852866e-06, + "loss": 1.7399, + "step": 93610 + }, + { + "epoch": 3.48, + "learning_rate": 6.518019860899319e-06, + "loss": 1.6941, + "step": 93620 + }, + { + "epoch": 3.48, + "learning_rate": 6.5176479339457735e-06, + "loss": 1.7967, + "step": 93630 + }, + { + "epoch": 3.48, + "learning_rate": 6.517276006992227e-06, + "loss": 1.6842, + "step": 93640 + }, + { + "epoch": 3.48, + "learning_rate": 6.51690408003868e-06, + "loss": 1.7149, + "step": 93650 + }, + { + "epoch": 3.48, + "learning_rate": 6.516532153085135e-06, + "loss": 1.5865, + "step": 93660 + }, + { + "epoch": 3.48, + "learning_rate": 6.516160226131588e-06, + "loss": 1.7048, + "step": 93670 + }, + { + "epoch": 3.48, + "learning_rate": 6.515788299178042e-06, + "loss": 1.7307, + "step": 93680 + }, + { + "epoch": 3.48, + "learning_rate": 6.515416372224496e-06, + "loss": 1.7218, + "step": 93690 + }, + { + "epoch": 3.48, + "learning_rate": 6.515044445270949e-06, + "loss": 1.4824, + "step": 93700 + }, + { + "epoch": 3.48, + "eval_loss": 1.6516284942626953, + "eval_runtime": 16.851, + "eval_samples_per_second": 59.344, + "eval_steps_per_second": 3.739, + "step": 93700 + }, + { + "epoch": 3.49, + "learning_rate": 6.514672518317403e-06, + "loss": 1.6671, + "step": 93710 + }, + { + "epoch": 3.49, + "learning_rate": 6.514300591363857e-06, + "loss": 1.7515, + "step": 93720 + }, + { + "epoch": 3.49, + "learning_rate": 6.513928664410311e-06, + "loss": 1.6305, + "step": 93730 + }, + { + "epoch": 3.49, + "learning_rate": 6.513556737456764e-06, + "loss": 1.7752, + "step": 93740 + }, + { + "epoch": 3.49, + "learning_rate": 6.513184810503218e-06, + "loss": 1.6608, + "step": 93750 + }, + { + "epoch": 3.49, + "learning_rate": 6.512812883549672e-06, + "loss": 1.8553, + "step": 93760 + }, + { + "epoch": 3.49, + "learning_rate": 6.512440956596125e-06, + "loss": 1.7747, + "step": 93770 + }, + { + "epoch": 3.49, + "learning_rate": 6.51206902964258e-06, + "loss": 1.7081, + "step": 93780 + }, + { + "epoch": 3.49, + "learning_rate": 6.511697102689032e-06, + "loss": 1.7847, + "step": 93790 + }, + { + "epoch": 3.49, + "learning_rate": 6.511325175735486e-06, + "loss": 1.6047, + "step": 93800 + }, + { + "epoch": 3.49, + "eval_loss": 1.6514555215835571, + "eval_runtime": 16.8502, + "eval_samples_per_second": 59.346, + "eval_steps_per_second": 3.739, + "step": 93800 + }, + { + "epoch": 3.49, + "learning_rate": 6.510953248781939e-06, + "loss": 1.6934, + "step": 93810 + }, + { + "epoch": 3.49, + "learning_rate": 6.5105813218283934e-06, + "loss": 1.6511, + "step": 93820 + }, + { + "epoch": 3.49, + "learning_rate": 6.510209394874847e-06, + "loss": 1.6002, + "step": 93830 + }, + { + "epoch": 3.49, + "learning_rate": 6.5098374679213e-06, + "loss": 1.5893, + "step": 93840 + }, + { + "epoch": 3.49, + "learning_rate": 6.509465540967755e-06, + "loss": 1.5202, + "step": 93850 + }, + { + "epoch": 3.49, + "learning_rate": 6.509093614014208e-06, + "loss": 1.7615, + "step": 93860 + }, + { + "epoch": 3.49, + "learning_rate": 6.508721687060662e-06, + "loss": 1.6607, + "step": 93870 + }, + { + "epoch": 3.49, + "learning_rate": 6.508349760107116e-06, + "loss": 1.6365, + "step": 93880 + }, + { + "epoch": 3.49, + "learning_rate": 6.507977833153569e-06, + "loss": 1.6656, + "step": 93890 + }, + { + "epoch": 3.49, + "learning_rate": 6.507605906200023e-06, + "loss": 1.6756, + "step": 93900 + }, + { + "epoch": 3.49, + "eval_loss": 1.6518813371658325, + "eval_runtime": 16.845, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 93900 + }, + { + "epoch": 3.49, + "learning_rate": 6.507233979246477e-06, + "loss": 1.6897, + "step": 93910 + }, + { + "epoch": 3.49, + "learning_rate": 6.5068620522929306e-06, + "loss": 1.815, + "step": 93920 + }, + { + "epoch": 3.49, + "learning_rate": 6.506490125339384e-06, + "loss": 1.7197, + "step": 93930 + }, + { + "epoch": 3.49, + "learning_rate": 6.506118198385838e-06, + "loss": 1.8704, + "step": 93940 + }, + { + "epoch": 3.49, + "learning_rate": 6.505746271432292e-06, + "loss": 1.7518, + "step": 93950 + }, + { + "epoch": 3.49, + "learning_rate": 6.505374344478745e-06, + "loss": 1.6754, + "step": 93960 + }, + { + "epoch": 3.49, + "learning_rate": 6.505002417525199e-06, + "loss": 1.6524, + "step": 93970 + }, + { + "epoch": 3.5, + "learning_rate": 6.504630490571651e-06, + "loss": 1.7606, + "step": 93980 + }, + { + "epoch": 3.5, + "learning_rate": 6.504258563618106e-06, + "loss": 1.6977, + "step": 93990 + }, + { + "epoch": 3.5, + "learning_rate": 6.503886636664559e-06, + "loss": 1.5548, + "step": 94000 + }, + { + "epoch": 3.5, + "eval_loss": 1.6517184972763062, + "eval_runtime": 16.8473, + "eval_samples_per_second": 59.357, + "eval_steps_per_second": 3.739, + "step": 94000 + }, + { + "epoch": 3.5, + "learning_rate": 6.5035147097110125e-06, + "loss": 1.8639, + "step": 94010 + }, + { + "epoch": 3.5, + "learning_rate": 6.503142782757467e-06, + "loss": 1.6787, + "step": 94020 + }, + { + "epoch": 3.5, + "learning_rate": 6.50277085580392e-06, + "loss": 1.7001, + "step": 94030 + }, + { + "epoch": 3.5, + "learning_rate": 6.502398928850374e-06, + "loss": 1.7128, + "step": 94040 + }, + { + "epoch": 3.5, + "learning_rate": 6.502027001896828e-06, + "loss": 1.7266, + "step": 94050 + }, + { + "epoch": 3.5, + "learning_rate": 6.5016550749432815e-06, + "loss": 1.83, + "step": 94060 + }, + { + "epoch": 3.5, + "learning_rate": 6.501283147989735e-06, + "loss": 1.7263, + "step": 94070 + }, + { + "epoch": 3.5, + "learning_rate": 6.500911221036189e-06, + "loss": 1.7615, + "step": 94080 + }, + { + "epoch": 3.5, + "learning_rate": 6.500539294082643e-06, + "loss": 1.6639, + "step": 94090 + }, + { + "epoch": 3.5, + "learning_rate": 6.500167367129096e-06, + "loss": 1.6798, + "step": 94100 + }, + { + "epoch": 3.5, + "eval_loss": 1.6513136625289917, + "eval_runtime": 16.8525, + "eval_samples_per_second": 59.338, + "eval_steps_per_second": 3.738, + "step": 94100 + }, + { + "epoch": 3.5, + "learning_rate": 6.4997954401755505e-06, + "loss": 1.6843, + "step": 94110 + }, + { + "epoch": 3.5, + "learning_rate": 6.499423513222004e-06, + "loss": 1.8127, + "step": 94120 + }, + { + "epoch": 3.5, + "learning_rate": 6.4990515862684574e-06, + "loss": 1.712, + "step": 94130 + }, + { + "epoch": 3.5, + "learning_rate": 6.498679659314912e-06, + "loss": 1.5522, + "step": 94140 + }, + { + "epoch": 3.5, + "learning_rate": 6.498307732361365e-06, + "loss": 1.6055, + "step": 94150 + }, + { + "epoch": 3.5, + "learning_rate": 6.497935805407819e-06, + "loss": 1.5179, + "step": 94160 + }, + { + "epoch": 3.5, + "learning_rate": 6.497563878454271e-06, + "loss": 1.6356, + "step": 94170 + }, + { + "epoch": 3.5, + "learning_rate": 6.497191951500726e-06, + "loss": 1.8129, + "step": 94180 + }, + { + "epoch": 3.5, + "learning_rate": 6.496820024547179e-06, + "loss": 1.5701, + "step": 94190 + }, + { + "epoch": 3.5, + "learning_rate": 6.4964480975936325e-06, + "loss": 1.5897, + "step": 94200 + }, + { + "epoch": 3.5, + "eval_loss": 1.6506760120391846, + "eval_runtime": 16.8441, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 94200 + }, + { + "epoch": 3.5, + "learning_rate": 6.496076170640087e-06, + "loss": 1.6081, + "step": 94210 + }, + { + "epoch": 3.5, + "learning_rate": 6.49570424368654e-06, + "loss": 1.7228, + "step": 94220 + }, + { + "epoch": 3.5, + "learning_rate": 6.495332316732994e-06, + "loss": 1.6777, + "step": 94230 + }, + { + "epoch": 3.51, + "learning_rate": 6.494960389779448e-06, + "loss": 1.585, + "step": 94240 + }, + { + "epoch": 3.51, + "learning_rate": 6.4945884628259015e-06, + "loss": 1.8027, + "step": 94250 + }, + { + "epoch": 3.51, + "learning_rate": 6.494216535872355e-06, + "loss": 1.776, + "step": 94260 + }, + { + "epoch": 3.51, + "learning_rate": 6.493844608918809e-06, + "loss": 1.7463, + "step": 94270 + }, + { + "epoch": 3.51, + "learning_rate": 6.493472681965263e-06, + "loss": 1.7603, + "step": 94280 + }, + { + "epoch": 3.51, + "learning_rate": 6.493100755011716e-06, + "loss": 1.6657, + "step": 94290 + }, + { + "epoch": 3.51, + "learning_rate": 6.4927288280581705e-06, + "loss": 1.6924, + "step": 94300 + }, + { + "epoch": 3.51, + "eval_loss": 1.6508605480194092, + "eval_runtime": 16.8344, + "eval_samples_per_second": 59.402, + "eval_steps_per_second": 3.742, + "step": 94300 + }, + { + "epoch": 3.51, + "learning_rate": 6.492356901104624e-06, + "loss": 1.6775, + "step": 94310 + }, + { + "epoch": 3.51, + "learning_rate": 6.491984974151077e-06, + "loss": 1.8485, + "step": 94320 + }, + { + "epoch": 3.51, + "learning_rate": 6.491613047197532e-06, + "loss": 1.6279, + "step": 94330 + }, + { + "epoch": 3.51, + "learning_rate": 6.491241120243985e-06, + "loss": 1.7022, + "step": 94340 + }, + { + "epoch": 3.51, + "learning_rate": 6.490869193290438e-06, + "loss": 1.5481, + "step": 94350 + }, + { + "epoch": 3.51, + "learning_rate": 6.490497266336891e-06, + "loss": 1.6429, + "step": 94360 + }, + { + "epoch": 3.51, + "learning_rate": 6.4901253393833455e-06, + "loss": 1.5982, + "step": 94370 + }, + { + "epoch": 3.51, + "learning_rate": 6.489753412429799e-06, + "loss": 1.642, + "step": 94380 + }, + { + "epoch": 3.51, + "learning_rate": 6.4893814854762525e-06, + "loss": 1.7269, + "step": 94390 + }, + { + "epoch": 3.51, + "learning_rate": 6.489009558522707e-06, + "loss": 1.682, + "step": 94400 + }, + { + "epoch": 3.51, + "eval_loss": 1.650627851486206, + "eval_runtime": 16.8434, + "eval_samples_per_second": 59.371, + "eval_steps_per_second": 3.74, + "step": 94400 + }, + { + "epoch": 3.51, + "learning_rate": 6.48863763156916e-06, + "loss": 1.7892, + "step": 94410 + }, + { + "epoch": 3.51, + "learning_rate": 6.488265704615614e-06, + "loss": 1.6625, + "step": 94420 + }, + { + "epoch": 3.51, + "learning_rate": 6.487893777662068e-06, + "loss": 1.5924, + "step": 94430 + }, + { + "epoch": 3.51, + "learning_rate": 6.4875218507085215e-06, + "loss": 1.7011, + "step": 94440 + }, + { + "epoch": 3.51, + "learning_rate": 6.487149923754975e-06, + "loss": 1.6453, + "step": 94450 + }, + { + "epoch": 3.51, + "learning_rate": 6.486777996801429e-06, + "loss": 1.484, + "step": 94460 + }, + { + "epoch": 3.51, + "learning_rate": 6.486406069847883e-06, + "loss": 1.6195, + "step": 94470 + }, + { + "epoch": 3.51, + "learning_rate": 6.486034142894336e-06, + "loss": 1.6187, + "step": 94480 + }, + { + "epoch": 3.51, + "learning_rate": 6.4856622159407904e-06, + "loss": 1.7043, + "step": 94490 + }, + { + "epoch": 3.51, + "learning_rate": 6.485290288987244e-06, + "loss": 1.8201, + "step": 94500 + }, + { + "epoch": 3.51, + "eval_loss": 1.6508678197860718, + "eval_runtime": 16.841, + "eval_samples_per_second": 59.379, + "eval_steps_per_second": 3.741, + "step": 94500 + }, + { + "epoch": 3.52, + "learning_rate": 6.484918362033697e-06, + "loss": 1.733, + "step": 94510 + }, + { + "epoch": 3.52, + "learning_rate": 6.484546435080152e-06, + "loss": 1.6832, + "step": 94520 + }, + { + "epoch": 3.52, + "learning_rate": 6.484174508126605e-06, + "loss": 1.6596, + "step": 94530 + }, + { + "epoch": 3.52, + "learning_rate": 6.483802581173058e-06, + "loss": 1.6969, + "step": 94540 + }, + { + "epoch": 3.52, + "learning_rate": 6.483430654219511e-06, + "loss": 1.6324, + "step": 94550 + }, + { + "epoch": 3.52, + "learning_rate": 6.483058727265965e-06, + "loss": 1.6348, + "step": 94560 + }, + { + "epoch": 3.52, + "learning_rate": 6.482686800312419e-06, + "loss": 1.6936, + "step": 94570 + }, + { + "epoch": 3.52, + "learning_rate": 6.4823148733588724e-06, + "loss": 1.8769, + "step": 94580 + }, + { + "epoch": 3.52, + "learning_rate": 6.481942946405326e-06, + "loss": 1.5879, + "step": 94590 + }, + { + "epoch": 3.52, + "learning_rate": 6.48157101945178e-06, + "loss": 1.6926, + "step": 94600 + }, + { + "epoch": 3.52, + "eval_loss": 1.6506903171539307, + "eval_runtime": 16.8389, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 94600 + }, + { + "epoch": 3.52, + "learning_rate": 6.481199092498234e-06, + "loss": 1.6659, + "step": 94610 + }, + { + "epoch": 3.52, + "learning_rate": 6.480827165544687e-06, + "loss": 1.6384, + "step": 94620 + }, + { + "epoch": 3.52, + "learning_rate": 6.480455238591141e-06, + "loss": 1.6724, + "step": 94630 + }, + { + "epoch": 3.52, + "learning_rate": 6.480083311637595e-06, + "loss": 1.7726, + "step": 94640 + }, + { + "epoch": 3.52, + "learning_rate": 6.479711384684048e-06, + "loss": 1.7788, + "step": 94650 + }, + { + "epoch": 3.52, + "learning_rate": 6.479339457730503e-06, + "loss": 1.8514, + "step": 94660 + }, + { + "epoch": 3.52, + "learning_rate": 6.478967530776956e-06, + "loss": 1.6586, + "step": 94670 + }, + { + "epoch": 3.52, + "learning_rate": 6.4785956038234096e-06, + "loss": 1.6338, + "step": 94680 + }, + { + "epoch": 3.52, + "learning_rate": 6.478223676869864e-06, + "loss": 1.7244, + "step": 94690 + }, + { + "epoch": 3.52, + "learning_rate": 6.477851749916317e-06, + "loss": 1.6316, + "step": 94700 + }, + { + "epoch": 3.52, + "eval_loss": 1.650602102279663, + "eval_runtime": 16.8441, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 94700 + }, + { + "epoch": 3.52, + "learning_rate": 6.477479822962771e-06, + "loss": 1.7612, + "step": 94710 + }, + { + "epoch": 3.52, + "learning_rate": 6.477107896009225e-06, + "loss": 1.7278, + "step": 94720 + }, + { + "epoch": 3.52, + "learning_rate": 6.476735969055678e-06, + "loss": 1.7066, + "step": 94730 + }, + { + "epoch": 3.52, + "learning_rate": 6.476364042102131e-06, + "loss": 1.6194, + "step": 94740 + }, + { + "epoch": 3.52, + "learning_rate": 6.475992115148585e-06, + "loss": 1.6858, + "step": 94750 + }, + { + "epoch": 3.52, + "learning_rate": 6.475620188195039e-06, + "loss": 1.6027, + "step": 94760 + }, + { + "epoch": 3.52, + "learning_rate": 6.475248261241492e-06, + "loss": 1.6268, + "step": 94770 + }, + { + "epoch": 3.53, + "learning_rate": 6.474876334287946e-06, + "loss": 1.7234, + "step": 94780 + }, + { + "epoch": 3.53, + "learning_rate": 6.4745044073344e-06, + "loss": 1.731, + "step": 94790 + }, + { + "epoch": 3.53, + "learning_rate": 6.474132480380854e-06, + "loss": 1.6115, + "step": 94800 + }, + { + "epoch": 3.53, + "eval_loss": 1.6500935554504395, + "eval_runtime": 16.8493, + "eval_samples_per_second": 59.35, + "eval_steps_per_second": 3.739, + "step": 94800 + }, + { + "epoch": 3.53, + "learning_rate": 6.473760553427307e-06, + "loss": 1.6212, + "step": 94810 + }, + { + "epoch": 3.53, + "learning_rate": 6.473388626473761e-06, + "loss": 1.5895, + "step": 94820 + }, + { + "epoch": 3.53, + "learning_rate": 6.473016699520215e-06, + "loss": 1.6438, + "step": 94830 + }, + { + "epoch": 3.53, + "learning_rate": 6.472644772566668e-06, + "loss": 1.7632, + "step": 94840 + }, + { + "epoch": 3.53, + "learning_rate": 6.472272845613123e-06, + "loss": 1.5815, + "step": 94850 + }, + { + "epoch": 3.53, + "learning_rate": 6.471900918659576e-06, + "loss": 1.7074, + "step": 94860 + }, + { + "epoch": 3.53, + "learning_rate": 6.4715289917060295e-06, + "loss": 1.7395, + "step": 94870 + }, + { + "epoch": 3.53, + "learning_rate": 6.471157064752484e-06, + "loss": 1.6611, + "step": 94880 + }, + { + "epoch": 3.53, + "learning_rate": 6.470785137798937e-06, + "loss": 1.5575, + "step": 94890 + }, + { + "epoch": 3.53, + "learning_rate": 6.470413210845391e-06, + "loss": 1.662, + "step": 94900 + }, + { + "epoch": 3.53, + "eval_loss": 1.6498134136199951, + "eval_runtime": 16.8364, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 94900 + }, + { + "epoch": 3.53, + "learning_rate": 6.470041283891845e-06, + "loss": 1.5471, + "step": 94910 + }, + { + "epoch": 3.53, + "learning_rate": 6.469669356938298e-06, + "loss": 1.6339, + "step": 94920 + }, + { + "epoch": 3.53, + "learning_rate": 6.469297429984751e-06, + "loss": 1.6594, + "step": 94930 + }, + { + "epoch": 3.53, + "learning_rate": 6.468925503031205e-06, + "loss": 1.5762, + "step": 94940 + }, + { + "epoch": 3.53, + "learning_rate": 6.468553576077659e-06, + "loss": 1.6856, + "step": 94950 + }, + { + "epoch": 3.53, + "learning_rate": 6.468181649124112e-06, + "loss": 1.7974, + "step": 94960 + }, + { + "epoch": 3.53, + "learning_rate": 6.467809722170566e-06, + "loss": 1.6673, + "step": 94970 + }, + { + "epoch": 3.53, + "learning_rate": 6.46743779521702e-06, + "loss": 1.6209, + "step": 94980 + }, + { + "epoch": 3.53, + "learning_rate": 6.4670658682634736e-06, + "loss": 1.6878, + "step": 94990 + }, + { + "epoch": 3.53, + "learning_rate": 6.466693941309927e-06, + "loss": 1.7923, + "step": 95000 + }, + { + "epoch": 3.53, + "eval_loss": 1.6502783298492432, + "eval_runtime": 16.8544, + "eval_samples_per_second": 59.332, + "eval_steps_per_second": 3.738, + "step": 95000 + }, + { + "epoch": 3.53, + "learning_rate": 6.466322014356381e-06, + "loss": 1.7275, + "step": 95010 + }, + { + "epoch": 3.53, + "learning_rate": 6.465950087402835e-06, + "loss": 1.7283, + "step": 95020 + }, + { + "epoch": 3.53, + "learning_rate": 6.465578160449288e-06, + "loss": 1.7003, + "step": 95030 + }, + { + "epoch": 3.53, + "learning_rate": 6.4652062334957426e-06, + "loss": 1.7831, + "step": 95040 + }, + { + "epoch": 3.54, + "learning_rate": 6.464834306542196e-06, + "loss": 1.6207, + "step": 95050 + }, + { + "epoch": 3.54, + "learning_rate": 6.4644623795886495e-06, + "loss": 1.7705, + "step": 95060 + }, + { + "epoch": 3.54, + "learning_rate": 6.464090452635104e-06, + "loss": 1.6165, + "step": 95070 + }, + { + "epoch": 3.54, + "learning_rate": 6.463718525681557e-06, + "loss": 1.769, + "step": 95080 + }, + { + "epoch": 3.54, + "learning_rate": 6.463346598728011e-06, + "loss": 1.5476, + "step": 95090 + }, + { + "epoch": 3.54, + "learning_rate": 6.462974671774463e-06, + "loss": 1.68, + "step": 95100 + }, + { + "epoch": 3.54, + "eval_loss": 1.6500827074050903, + "eval_runtime": 16.8253, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 95100 + }, + { + "epoch": 3.54, + "learning_rate": 6.462602744820918e-06, + "loss": 1.6285, + "step": 95110 + }, + { + "epoch": 3.54, + "learning_rate": 6.462230817867371e-06, + "loss": 1.7597, + "step": 95120 + }, + { + "epoch": 3.54, + "learning_rate": 6.4618588909138245e-06, + "loss": 1.6857, + "step": 95130 + }, + { + "epoch": 3.54, + "learning_rate": 6.461486963960278e-06, + "loss": 1.7287, + "step": 95140 + }, + { + "epoch": 3.54, + "learning_rate": 6.461115037006732e-06, + "loss": 1.7132, + "step": 95150 + }, + { + "epoch": 3.54, + "learning_rate": 6.460743110053186e-06, + "loss": 1.6868, + "step": 95160 + }, + { + "epoch": 3.54, + "learning_rate": 6.460371183099639e-06, + "loss": 1.6361, + "step": 95170 + }, + { + "epoch": 3.54, + "learning_rate": 6.4599992561460935e-06, + "loss": 1.6494, + "step": 95180 + }, + { + "epoch": 3.54, + "learning_rate": 6.459627329192547e-06, + "loss": 1.7565, + "step": 95190 + }, + { + "epoch": 3.54, + "learning_rate": 6.4592554022390004e-06, + "loss": 1.5957, + "step": 95200 + }, + { + "epoch": 3.54, + "eval_loss": 1.6503883600234985, + "eval_runtime": 16.8393, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 95200 + }, + { + "epoch": 3.54, + "learning_rate": 6.458883475285455e-06, + "loss": 1.7144, + "step": 95210 + }, + { + "epoch": 3.54, + "learning_rate": 6.458511548331908e-06, + "loss": 1.6804, + "step": 95220 + }, + { + "epoch": 3.54, + "learning_rate": 6.458139621378362e-06, + "loss": 1.8778, + "step": 95230 + }, + { + "epoch": 3.54, + "learning_rate": 6.457767694424816e-06, + "loss": 1.6461, + "step": 95240 + }, + { + "epoch": 3.54, + "learning_rate": 6.4573957674712694e-06, + "loss": 1.6884, + "step": 95250 + }, + { + "epoch": 3.54, + "learning_rate": 6.457023840517723e-06, + "loss": 1.6858, + "step": 95260 + }, + { + "epoch": 3.54, + "learning_rate": 6.456651913564177e-06, + "loss": 1.643, + "step": 95270 + }, + { + "epoch": 3.54, + "learning_rate": 6.456279986610631e-06, + "loss": 1.6072, + "step": 95280 + }, + { + "epoch": 3.54, + "learning_rate": 6.455908059657083e-06, + "loss": 1.937, + "step": 95290 + }, + { + "epoch": 3.54, + "learning_rate": 6.455536132703537e-06, + "loss": 1.7022, + "step": 95300 + }, + { + "epoch": 3.54, + "eval_loss": 1.6506612300872803, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 95300 + }, + { + "epoch": 3.54, + "learning_rate": 6.455164205749991e-06, + "loss": 1.7386, + "step": 95310 + }, + { + "epoch": 3.55, + "learning_rate": 6.4547922787964445e-06, + "loss": 1.5515, + "step": 95320 + }, + { + "epoch": 3.55, + "learning_rate": 6.454420351842898e-06, + "loss": 1.6993, + "step": 95330 + }, + { + "epoch": 3.55, + "learning_rate": 6.454048424889352e-06, + "loss": 1.5839, + "step": 95340 + }, + { + "epoch": 3.55, + "learning_rate": 6.453676497935806e-06, + "loss": 1.6786, + "step": 95350 + }, + { + "epoch": 3.55, + "learning_rate": 6.453304570982259e-06, + "loss": 1.6383, + "step": 95360 + }, + { + "epoch": 3.55, + "learning_rate": 6.4529326440287135e-06, + "loss": 1.7369, + "step": 95370 + }, + { + "epoch": 3.55, + "learning_rate": 6.452560717075167e-06, + "loss": 1.8977, + "step": 95380 + }, + { + "epoch": 3.55, + "learning_rate": 6.45218879012162e-06, + "loss": 1.7314, + "step": 95390 + }, + { + "epoch": 3.55, + "learning_rate": 6.451816863168075e-06, + "loss": 1.6456, + "step": 95400 + }, + { + "epoch": 3.55, + "eval_loss": 1.6505842208862305, + "eval_runtime": 16.8283, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 95400 + }, + { + "epoch": 3.55, + "learning_rate": 6.451444936214528e-06, + "loss": 1.8304, + "step": 95410 + }, + { + "epoch": 3.55, + "learning_rate": 6.451073009260982e-06, + "loss": 1.6372, + "step": 95420 + }, + { + "epoch": 3.55, + "learning_rate": 6.450701082307436e-06, + "loss": 1.6227, + "step": 95430 + }, + { + "epoch": 3.55, + "learning_rate": 6.450329155353889e-06, + "loss": 1.6459, + "step": 95440 + }, + { + "epoch": 3.55, + "learning_rate": 6.449957228400343e-06, + "loss": 1.6723, + "step": 95450 + }, + { + "epoch": 3.55, + "learning_rate": 6.449585301446797e-06, + "loss": 1.6327, + "step": 95460 + }, + { + "epoch": 3.55, + "learning_rate": 6.449213374493251e-06, + "loss": 1.6078, + "step": 95470 + }, + { + "epoch": 3.55, + "learning_rate": 6.448841447539703e-06, + "loss": 1.658, + "step": 95480 + }, + { + "epoch": 3.55, + "learning_rate": 6.448469520586157e-06, + "loss": 1.8542, + "step": 95490 + }, + { + "epoch": 3.55, + "learning_rate": 6.448097593632611e-06, + "loss": 1.6477, + "step": 95500 + }, + { + "epoch": 3.55, + "eval_loss": 1.6497611999511719, + "eval_runtime": 16.8274, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 95500 + }, + { + "epoch": 3.55, + "learning_rate": 6.4477256666790645e-06, + "loss": 1.6276, + "step": 95510 + }, + { + "epoch": 3.55, + "learning_rate": 6.447353739725518e-06, + "loss": 1.7168, + "step": 95520 + }, + { + "epoch": 3.55, + "learning_rate": 6.446981812771972e-06, + "loss": 1.6516, + "step": 95530 + }, + { + "epoch": 3.55, + "learning_rate": 6.446609885818426e-06, + "loss": 1.6365, + "step": 95540 + }, + { + "epoch": 3.55, + "learning_rate": 6.446237958864879e-06, + "loss": 1.6422, + "step": 95550 + }, + { + "epoch": 3.55, + "learning_rate": 6.4458660319113334e-06, + "loss": 1.6694, + "step": 95560 + }, + { + "epoch": 3.55, + "learning_rate": 6.445494104957787e-06, + "loss": 1.6075, + "step": 95570 + }, + { + "epoch": 3.55, + "learning_rate": 6.44512217800424e-06, + "loss": 1.5825, + "step": 95580 + }, + { + "epoch": 3.56, + "learning_rate": 6.444750251050695e-06, + "loss": 1.7325, + "step": 95590 + }, + { + "epoch": 3.56, + "learning_rate": 6.444378324097148e-06, + "loss": 1.7575, + "step": 95600 + }, + { + "epoch": 3.56, + "eval_loss": 1.6495459079742432, + "eval_runtime": 16.8427, + "eval_samples_per_second": 59.373, + "eval_steps_per_second": 3.741, + "step": 95600 + }, + { + "epoch": 3.56, + "learning_rate": 6.444006397143602e-06, + "loss": 1.7848, + "step": 95610 + }, + { + "epoch": 3.56, + "learning_rate": 6.443634470190056e-06, + "loss": 1.6516, + "step": 95620 + }, + { + "epoch": 3.56, + "learning_rate": 6.443262543236509e-06, + "loss": 1.928, + "step": 95630 + }, + { + "epoch": 3.56, + "learning_rate": 6.442890616282963e-06, + "loss": 1.7749, + "step": 95640 + }, + { + "epoch": 3.56, + "learning_rate": 6.442518689329417e-06, + "loss": 1.8024, + "step": 95650 + }, + { + "epoch": 3.56, + "learning_rate": 6.442146762375871e-06, + "loss": 1.7849, + "step": 95660 + }, + { + "epoch": 3.56, + "learning_rate": 6.441774835422323e-06, + "loss": 1.732, + "step": 95670 + }, + { + "epoch": 3.56, + "learning_rate": 6.441402908468777e-06, + "loss": 1.652, + "step": 95680 + }, + { + "epoch": 3.56, + "learning_rate": 6.441030981515231e-06, + "loss": 1.6538, + "step": 95690 + }, + { + "epoch": 3.56, + "learning_rate": 6.440659054561684e-06, + "loss": 1.725, + "step": 95700 + }, + { + "epoch": 3.56, + "eval_loss": 1.64918053150177, + "eval_runtime": 16.8426, + "eval_samples_per_second": 59.373, + "eval_steps_per_second": 3.741, + "step": 95700 + }, + { + "epoch": 3.56, + "learning_rate": 6.440287127608138e-06, + "loss": 1.7788, + "step": 95710 + }, + { + "epoch": 3.56, + "learning_rate": 6.439915200654591e-06, + "loss": 1.62, + "step": 95720 + }, + { + "epoch": 3.56, + "learning_rate": 6.439543273701046e-06, + "loss": 1.7386, + "step": 95730 + }, + { + "epoch": 3.56, + "learning_rate": 6.439171346747499e-06, + "loss": 1.5659, + "step": 95740 + }, + { + "epoch": 3.56, + "learning_rate": 6.4387994197939526e-06, + "loss": 1.6074, + "step": 95750 + }, + { + "epoch": 3.56, + "learning_rate": 6.438427492840407e-06, + "loss": 1.7589, + "step": 95760 + }, + { + "epoch": 3.56, + "learning_rate": 6.43805556588686e-06, + "loss": 1.6932, + "step": 95770 + }, + { + "epoch": 3.56, + "learning_rate": 6.437683638933314e-06, + "loss": 1.7329, + "step": 95780 + }, + { + "epoch": 3.56, + "learning_rate": 6.437311711979768e-06, + "loss": 1.7953, + "step": 95790 + }, + { + "epoch": 3.56, + "learning_rate": 6.4369397850262215e-06, + "loss": 1.6631, + "step": 95800 + }, + { + "epoch": 3.56, + "eval_loss": 1.6496633291244507, + "eval_runtime": 16.8206, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 95800 + }, + { + "epoch": 3.56, + "learning_rate": 6.436567858072675e-06, + "loss": 1.7932, + "step": 95810 + }, + { + "epoch": 3.56, + "learning_rate": 6.436195931119129e-06, + "loss": 1.5456, + "step": 95820 + }, + { + "epoch": 3.56, + "learning_rate": 6.435824004165583e-06, + "loss": 1.6866, + "step": 95830 + }, + { + "epoch": 3.56, + "learning_rate": 6.435452077212036e-06, + "loss": 1.6326, + "step": 95840 + }, + { + "epoch": 3.56, + "learning_rate": 6.4350801502584905e-06, + "loss": 1.5572, + "step": 95850 + }, + { + "epoch": 3.57, + "learning_rate": 6.434708223304943e-06, + "loss": 1.6759, + "step": 95860 + }, + { + "epoch": 3.57, + "learning_rate": 6.434336296351397e-06, + "loss": 1.7937, + "step": 95870 + }, + { + "epoch": 3.57, + "learning_rate": 6.43396436939785e-06, + "loss": 1.6947, + "step": 95880 + }, + { + "epoch": 3.57, + "learning_rate": 6.433592442444304e-06, + "loss": 1.6688, + "step": 95890 + }, + { + "epoch": 3.57, + "learning_rate": 6.433220515490758e-06, + "loss": 1.6197, + "step": 95900 + }, + { + "epoch": 3.57, + "eval_loss": 1.649789810180664, + "eval_runtime": 16.8311, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 95900 + }, + { + "epoch": 3.57, + "learning_rate": 6.432848588537211e-06, + "loss": 1.9043, + "step": 95910 + }, + { + "epoch": 3.57, + "learning_rate": 6.432476661583666e-06, + "loss": 1.7097, + "step": 95920 + }, + { + "epoch": 3.57, + "learning_rate": 6.432104734630119e-06, + "loss": 1.6638, + "step": 95930 + }, + { + "epoch": 3.57, + "learning_rate": 6.4317328076765725e-06, + "loss": 1.8367, + "step": 95940 + }, + { + "epoch": 3.57, + "learning_rate": 6.431360880723027e-06, + "loss": 1.9514, + "step": 95950 + }, + { + "epoch": 3.57, + "learning_rate": 6.43098895376948e-06, + "loss": 1.6659, + "step": 95960 + }, + { + "epoch": 3.57, + "learning_rate": 6.430617026815934e-06, + "loss": 1.5903, + "step": 95970 + }, + { + "epoch": 3.57, + "learning_rate": 6.430245099862388e-06, + "loss": 1.7719, + "step": 95980 + }, + { + "epoch": 3.57, + "learning_rate": 6.4298731729088415e-06, + "loss": 1.7051, + "step": 95990 + }, + { + "epoch": 3.57, + "learning_rate": 6.429501245955295e-06, + "loss": 1.6568, + "step": 96000 + }, + { + "epoch": 3.57, + "eval_loss": 1.649571418762207, + "eval_runtime": 16.834, + "eval_samples_per_second": 59.404, + "eval_steps_per_second": 3.742, + "step": 96000 + }, + { + "epoch": 3.57, + "learning_rate": 6.429129319001749e-06, + "loss": 1.7155, + "step": 96010 + }, + { + "epoch": 3.57, + "learning_rate": 6.428757392048203e-06, + "loss": 1.8078, + "step": 96020 + }, + { + "epoch": 3.57, + "learning_rate": 6.428385465094656e-06, + "loss": 1.653, + "step": 96030 + }, + { + "epoch": 3.57, + "learning_rate": 6.428013538141109e-06, + "loss": 1.6622, + "step": 96040 + }, + { + "epoch": 3.57, + "learning_rate": 6.427641611187563e-06, + "loss": 1.6375, + "step": 96050 + }, + { + "epoch": 3.57, + "learning_rate": 6.4272696842340166e-06, + "loss": 1.7438, + "step": 96060 + }, + { + "epoch": 3.57, + "learning_rate": 6.42689775728047e-06, + "loss": 1.6967, + "step": 96070 + }, + { + "epoch": 3.57, + "learning_rate": 6.426525830326924e-06, + "loss": 1.6657, + "step": 96080 + }, + { + "epoch": 3.57, + "learning_rate": 6.426153903373378e-06, + "loss": 1.9023, + "step": 96090 + }, + { + "epoch": 3.57, + "learning_rate": 6.425781976419831e-06, + "loss": 1.6329, + "step": 96100 + }, + { + "epoch": 3.57, + "eval_loss": 1.651089072227478, + "eval_runtime": 16.8268, + "eval_samples_per_second": 59.429, + "eval_steps_per_second": 3.744, + "step": 96100 + }, + { + "epoch": 3.57, + "learning_rate": 6.4254100494662856e-06, + "loss": 1.7243, + "step": 96110 + }, + { + "epoch": 3.57, + "learning_rate": 6.425038122512739e-06, + "loss": 1.636, + "step": 96120 + }, + { + "epoch": 3.58, + "learning_rate": 6.4246661955591925e-06, + "loss": 1.6889, + "step": 96130 + }, + { + "epoch": 3.58, + "learning_rate": 6.424294268605647e-06, + "loss": 1.6441, + "step": 96140 + }, + { + "epoch": 3.58, + "learning_rate": 6.4239223416521e-06, + "loss": 1.7416, + "step": 96150 + }, + { + "epoch": 3.58, + "learning_rate": 6.423550414698554e-06, + "loss": 1.8141, + "step": 96160 + }, + { + "epoch": 3.58, + "learning_rate": 6.423178487745008e-06, + "loss": 1.7578, + "step": 96170 + }, + { + "epoch": 3.58, + "learning_rate": 6.4228065607914615e-06, + "loss": 1.5758, + "step": 96180 + }, + { + "epoch": 3.58, + "learning_rate": 6.422434633837915e-06, + "loss": 1.6907, + "step": 96190 + }, + { + "epoch": 3.58, + "learning_rate": 6.422062706884369e-06, + "loss": 1.6809, + "step": 96200 + }, + { + "epoch": 3.58, + "eval_loss": 1.6485947370529175, + "eval_runtime": 16.8443, + "eval_samples_per_second": 59.367, + "eval_steps_per_second": 3.74, + "step": 96200 + }, + { + "epoch": 3.58, + "learning_rate": 6.421690779930823e-06, + "loss": 1.6881, + "step": 96210 + }, + { + "epoch": 3.58, + "learning_rate": 6.421318852977276e-06, + "loss": 1.6301, + "step": 96220 + }, + { + "epoch": 3.58, + "learning_rate": 6.420946926023729e-06, + "loss": 1.6654, + "step": 96230 + }, + { + "epoch": 3.58, + "learning_rate": 6.420574999070183e-06, + "loss": 1.7858, + "step": 96240 + }, + { + "epoch": 3.58, + "learning_rate": 6.4202030721166365e-06, + "loss": 1.6677, + "step": 96250 + }, + { + "epoch": 3.58, + "learning_rate": 6.41983114516309e-06, + "loss": 1.583, + "step": 96260 + }, + { + "epoch": 3.58, + "learning_rate": 6.419459218209544e-06, + "loss": 1.8635, + "step": 96270 + }, + { + "epoch": 3.58, + "learning_rate": 6.419087291255998e-06, + "loss": 1.5906, + "step": 96280 + }, + { + "epoch": 3.58, + "learning_rate": 6.418715364302451e-06, + "loss": 1.6391, + "step": 96290 + }, + { + "epoch": 3.58, + "learning_rate": 6.418343437348905e-06, + "loss": 1.6454, + "step": 96300 + }, + { + "epoch": 3.58, + "eval_loss": 1.6497995853424072, + "eval_runtime": 16.8335, + "eval_samples_per_second": 59.405, + "eval_steps_per_second": 3.743, + "step": 96300 + }, + { + "epoch": 3.58, + "learning_rate": 6.417971510395359e-06, + "loss": 1.575, + "step": 96310 + }, + { + "epoch": 3.58, + "learning_rate": 6.4175995834418124e-06, + "loss": 1.7187, + "step": 96320 + }, + { + "epoch": 3.58, + "learning_rate": 6.417227656488266e-06, + "loss": 1.6966, + "step": 96330 + }, + { + "epoch": 3.58, + "learning_rate": 6.41685572953472e-06, + "loss": 1.6843, + "step": 96340 + }, + { + "epoch": 3.58, + "learning_rate": 6.416483802581174e-06, + "loss": 1.6481, + "step": 96350 + }, + { + "epoch": 3.58, + "learning_rate": 6.416111875627627e-06, + "loss": 1.7383, + "step": 96360 + }, + { + "epoch": 3.58, + "learning_rate": 6.4157399486740814e-06, + "loss": 1.6837, + "step": 96370 + }, + { + "epoch": 3.58, + "learning_rate": 6.415368021720535e-06, + "loss": 1.6484, + "step": 96380 + }, + { + "epoch": 3.59, + "learning_rate": 6.414996094766988e-06, + "loss": 1.8635, + "step": 96390 + }, + { + "epoch": 3.59, + "learning_rate": 6.414624167813443e-06, + "loss": 1.71, + "step": 96400 + }, + { + "epoch": 3.59, + "eval_loss": 1.6494977474212646, + "eval_runtime": 16.8316, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 96400 + }, + { + "epoch": 3.59, + "learning_rate": 6.414252240859896e-06, + "loss": 1.6332, + "step": 96410 + }, + { + "epoch": 3.59, + "learning_rate": 6.413880313906349e-06, + "loss": 1.7326, + "step": 96420 + }, + { + "epoch": 3.59, + "learning_rate": 6.413508386952802e-06, + "loss": 1.7046, + "step": 96430 + }, + { + "epoch": 3.59, + "learning_rate": 6.4131364599992565e-06, + "loss": 1.6187, + "step": 96440 + }, + { + "epoch": 3.59, + "learning_rate": 6.41276453304571e-06, + "loss": 1.6253, + "step": 96450 + }, + { + "epoch": 3.59, + "learning_rate": 6.412392606092163e-06, + "loss": 1.7689, + "step": 96460 + }, + { + "epoch": 3.59, + "learning_rate": 6.412020679138618e-06, + "loss": 1.6556, + "step": 96470 + }, + { + "epoch": 3.59, + "learning_rate": 6.411648752185071e-06, + "loss": 1.6478, + "step": 96480 + }, + { + "epoch": 3.59, + "learning_rate": 6.411276825231525e-06, + "loss": 1.5869, + "step": 96490 + }, + { + "epoch": 3.59, + "learning_rate": 6.410904898277979e-06, + "loss": 1.5941, + "step": 96500 + }, + { + "epoch": 3.59, + "eval_loss": 1.6489163637161255, + "eval_runtime": 16.8198, + "eval_samples_per_second": 59.454, + "eval_steps_per_second": 3.746, + "step": 96500 + }, + { + "epoch": 3.59, + "learning_rate": 6.410532971324432e-06, + "loss": 1.6207, + "step": 96510 + }, + { + "epoch": 3.59, + "learning_rate": 6.410161044370886e-06, + "loss": 1.7482, + "step": 96520 + }, + { + "epoch": 3.59, + "learning_rate": 6.40978911741734e-06, + "loss": 1.5638, + "step": 96530 + }, + { + "epoch": 3.59, + "learning_rate": 6.409417190463794e-06, + "loss": 1.7815, + "step": 96540 + }, + { + "epoch": 3.59, + "learning_rate": 6.409045263510247e-06, + "loss": 1.6339, + "step": 96550 + }, + { + "epoch": 3.59, + "learning_rate": 6.408673336556701e-06, + "loss": 1.7096, + "step": 96560 + }, + { + "epoch": 3.59, + "learning_rate": 6.408301409603155e-06, + "loss": 1.6837, + "step": 96570 + }, + { + "epoch": 3.59, + "learning_rate": 6.407929482649608e-06, + "loss": 1.6384, + "step": 96580 + }, + { + "epoch": 3.59, + "learning_rate": 6.407557555696063e-06, + "loss": 1.6984, + "step": 96590 + }, + { + "epoch": 3.59, + "learning_rate": 6.407185628742516e-06, + "loss": 1.6727, + "step": 96600 + }, + { + "epoch": 3.59, + "eval_loss": 1.6497702598571777, + "eval_runtime": 16.8437, + "eval_samples_per_second": 59.37, + "eval_steps_per_second": 3.74, + "step": 96600 + }, + { + "epoch": 3.59, + "learning_rate": 6.406813701788969e-06, + "loss": 1.7033, + "step": 96610 + }, + { + "epoch": 3.59, + "learning_rate": 6.406441774835422e-06, + "loss": 1.5662, + "step": 96620 + }, + { + "epoch": 3.59, + "learning_rate": 6.4060698478818764e-06, + "loss": 1.6627, + "step": 96630 + }, + { + "epoch": 3.59, + "learning_rate": 6.40569792092833e-06, + "loss": 1.6889, + "step": 96640 + }, + { + "epoch": 3.59, + "learning_rate": 6.405325993974783e-06, + "loss": 1.6604, + "step": 96650 + }, + { + "epoch": 3.6, + "learning_rate": 6.404954067021238e-06, + "loss": 1.7367, + "step": 96660 + }, + { + "epoch": 3.6, + "learning_rate": 6.404582140067691e-06, + "loss": 1.5188, + "step": 96670 + }, + { + "epoch": 3.6, + "learning_rate": 6.404210213114145e-06, + "loss": 1.6022, + "step": 96680 + }, + { + "epoch": 3.6, + "learning_rate": 6.403838286160599e-06, + "loss": 1.6356, + "step": 96690 + }, + { + "epoch": 3.6, + "learning_rate": 6.403466359207052e-06, + "loss": 1.6938, + "step": 96700 + }, + { + "epoch": 3.6, + "eval_loss": 1.649322271347046, + "eval_runtime": 16.8669, + "eval_samples_per_second": 59.288, + "eval_steps_per_second": 3.735, + "step": 96700 + }, + { + "epoch": 3.6, + "learning_rate": 6.403094432253506e-06, + "loss": 1.7206, + "step": 96710 + }, + { + "epoch": 3.6, + "learning_rate": 6.40272250529996e-06, + "loss": 1.8155, + "step": 96720 + }, + { + "epoch": 3.6, + "learning_rate": 6.402350578346414e-06, + "loss": 1.672, + "step": 96730 + }, + { + "epoch": 3.6, + "learning_rate": 6.401978651392867e-06, + "loss": 1.6528, + "step": 96740 + }, + { + "epoch": 3.6, + "learning_rate": 6.401606724439321e-06, + "loss": 1.7175, + "step": 96750 + }, + { + "epoch": 3.6, + "learning_rate": 6.401234797485775e-06, + "loss": 1.7054, + "step": 96760 + }, + { + "epoch": 3.6, + "learning_rate": 6.400862870532228e-06, + "loss": 1.7233, + "step": 96770 + }, + { + "epoch": 3.6, + "learning_rate": 6.4004909435786826e-06, + "loss": 1.8667, + "step": 96780 + }, + { + "epoch": 3.6, + "learning_rate": 6.400119016625135e-06, + "loss": 1.6443, + "step": 96790 + }, + { + "epoch": 3.6, + "learning_rate": 6.399747089671589e-06, + "loss": 1.6993, + "step": 96800 + }, + { + "epoch": 3.6, + "eval_loss": 1.6485830545425415, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 96800 + }, + { + "epoch": 3.6, + "learning_rate": 6.399375162718042e-06, + "loss": 1.8272, + "step": 96810 + }, + { + "epoch": 3.6, + "learning_rate": 6.399003235764496e-06, + "loss": 1.624, + "step": 96820 + }, + { + "epoch": 3.6, + "learning_rate": 6.39863130881095e-06, + "loss": 1.6892, + "step": 96830 + }, + { + "epoch": 3.6, + "learning_rate": 6.398259381857403e-06, + "loss": 1.5768, + "step": 96840 + }, + { + "epoch": 3.6, + "learning_rate": 6.397887454903858e-06, + "loss": 1.6745, + "step": 96850 + }, + { + "epoch": 3.6, + "learning_rate": 6.397515527950311e-06, + "loss": 1.7482, + "step": 96860 + }, + { + "epoch": 3.6, + "learning_rate": 6.3971436009967645e-06, + "loss": 1.648, + "step": 96870 + }, + { + "epoch": 3.6, + "learning_rate": 6.396771674043218e-06, + "loss": 1.6894, + "step": 96880 + }, + { + "epoch": 3.6, + "learning_rate": 6.396399747089672e-06, + "loss": 1.6327, + "step": 96890 + }, + { + "epoch": 3.6, + "learning_rate": 6.396027820136126e-06, + "loss": 1.7098, + "step": 96900 + }, + { + "epoch": 3.6, + "eval_loss": 1.6491634845733643, + "eval_runtime": 16.8232, + "eval_samples_per_second": 59.442, + "eval_steps_per_second": 3.745, + "step": 96900 + }, + { + "epoch": 3.6, + "learning_rate": 6.395655893182579e-06, + "loss": 1.7012, + "step": 96910 + }, + { + "epoch": 3.6, + "learning_rate": 6.3952839662290335e-06, + "loss": 1.7008, + "step": 96920 + }, + { + "epoch": 3.61, + "learning_rate": 6.394912039275487e-06, + "loss": 1.6803, + "step": 96930 + }, + { + "epoch": 3.61, + "learning_rate": 6.3945401123219405e-06, + "loss": 1.9405, + "step": 96940 + }, + { + "epoch": 3.61, + "learning_rate": 6.394168185368395e-06, + "loss": 1.7223, + "step": 96950 + }, + { + "epoch": 3.61, + "learning_rate": 6.393796258414848e-06, + "loss": 1.6844, + "step": 96960 + }, + { + "epoch": 3.61, + "learning_rate": 6.393424331461302e-06, + "loss": 1.6033, + "step": 96970 + }, + { + "epoch": 3.61, + "learning_rate": 6.393052404507754e-06, + "loss": 1.6868, + "step": 96980 + }, + { + "epoch": 3.61, + "learning_rate": 6.392680477554209e-06, + "loss": 1.7076, + "step": 96990 + }, + { + "epoch": 3.61, + "learning_rate": 6.392308550600662e-06, + "loss": 1.6938, + "step": 97000 + }, + { + "epoch": 3.61, + "eval_loss": 1.6480200290679932, + "eval_runtime": 16.8312, + "eval_samples_per_second": 59.414, + "eval_steps_per_second": 3.743, + "step": 97000 + }, + { + "epoch": 3.61, + "learning_rate": 6.3919366236471155e-06, + "loss": 1.7826, + "step": 97010 + }, + { + "epoch": 3.61, + "learning_rate": 6.39156469669357e-06, + "loss": 1.6109, + "step": 97020 + }, + { + "epoch": 3.61, + "learning_rate": 6.391192769740023e-06, + "loss": 1.7262, + "step": 97030 + }, + { + "epoch": 3.61, + "learning_rate": 6.390820842786477e-06, + "loss": 1.7142, + "step": 97040 + }, + { + "epoch": 3.61, + "learning_rate": 6.390448915832931e-06, + "loss": 1.7041, + "step": 97050 + }, + { + "epoch": 3.61, + "learning_rate": 6.3900769888793845e-06, + "loss": 1.7928, + "step": 97060 + }, + { + "epoch": 3.61, + "learning_rate": 6.389705061925838e-06, + "loss": 1.7516, + "step": 97070 + }, + { + "epoch": 3.61, + "learning_rate": 6.389333134972292e-06, + "loss": 1.5965, + "step": 97080 + }, + { + "epoch": 3.61, + "learning_rate": 6.388961208018746e-06, + "loss": 1.6704, + "step": 97090 + }, + { + "epoch": 3.61, + "learning_rate": 6.388589281065199e-06, + "loss": 1.6949, + "step": 97100 + }, + { + "epoch": 3.61, + "eval_loss": 1.6495859622955322, + "eval_runtime": 16.8211, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 97100 + }, + { + "epoch": 3.61, + "learning_rate": 6.3882173541116535e-06, + "loss": 1.6046, + "step": 97110 + }, + { + "epoch": 3.61, + "learning_rate": 6.387845427158107e-06, + "loss": 1.6393, + "step": 97120 + }, + { + "epoch": 3.61, + "learning_rate": 6.38747350020456e-06, + "loss": 1.5987, + "step": 97130 + }, + { + "epoch": 3.61, + "learning_rate": 6.387101573251015e-06, + "loss": 1.6896, + "step": 97140 + }, + { + "epoch": 3.61, + "learning_rate": 6.386729646297468e-06, + "loss": 1.5949, + "step": 97150 + }, + { + "epoch": 3.61, + "learning_rate": 6.386357719343922e-06, + "loss": 1.764, + "step": 97160 + }, + { + "epoch": 3.61, + "learning_rate": 6.385985792390374e-06, + "loss": 1.5754, + "step": 97170 + }, + { + "epoch": 3.61, + "learning_rate": 6.3856138654368286e-06, + "loss": 1.6435, + "step": 97180 + }, + { + "epoch": 3.61, + "learning_rate": 6.385241938483282e-06, + "loss": 1.7061, + "step": 97190 + }, + { + "epoch": 3.62, + "learning_rate": 6.3848700115297355e-06, + "loss": 1.7559, + "step": 97200 + }, + { + "epoch": 3.62, + "eval_loss": 1.6479284763336182, + "eval_runtime": 16.8241, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 97200 + }, + { + "epoch": 3.62, + "learning_rate": 6.38449808457619e-06, + "loss": 1.7132, + "step": 97210 + }, + { + "epoch": 3.62, + "learning_rate": 6.384126157622643e-06, + "loss": 1.6405, + "step": 97220 + }, + { + "epoch": 3.62, + "learning_rate": 6.383754230669097e-06, + "loss": 1.7298, + "step": 97230 + }, + { + "epoch": 3.62, + "learning_rate": 6.383382303715551e-06, + "loss": 1.755, + "step": 97240 + }, + { + "epoch": 3.62, + "learning_rate": 6.3830103767620045e-06, + "loss": 1.6656, + "step": 97250 + }, + { + "epoch": 3.62, + "learning_rate": 6.382638449808458e-06, + "loss": 1.7219, + "step": 97260 + }, + { + "epoch": 3.62, + "learning_rate": 6.382266522854912e-06, + "loss": 1.5953, + "step": 97270 + }, + { + "epoch": 3.62, + "learning_rate": 6.381894595901366e-06, + "loss": 1.6746, + "step": 97280 + }, + { + "epoch": 3.62, + "learning_rate": 6.381522668947819e-06, + "loss": 1.686, + "step": 97290 + }, + { + "epoch": 3.62, + "learning_rate": 6.3811507419942735e-06, + "loss": 1.7849, + "step": 97300 + }, + { + "epoch": 3.62, + "eval_loss": 1.6481504440307617, + "eval_runtime": 16.8356, + "eval_samples_per_second": 59.398, + "eval_steps_per_second": 3.742, + "step": 97300 + }, + { + "epoch": 3.62, + "learning_rate": 6.380778815040727e-06, + "loss": 1.666, + "step": 97310 + }, + { + "epoch": 3.62, + "learning_rate": 6.38040688808718e-06, + "loss": 1.7049, + "step": 97320 + }, + { + "epoch": 3.62, + "learning_rate": 6.380034961133635e-06, + "loss": 1.7447, + "step": 97330 + }, + { + "epoch": 3.62, + "learning_rate": 6.379663034180088e-06, + "loss": 1.5861, + "step": 97340 + }, + { + "epoch": 3.62, + "learning_rate": 6.379291107226542e-06, + "loss": 1.6839, + "step": 97350 + }, + { + "epoch": 3.62, + "learning_rate": 6.378919180272994e-06, + "loss": 1.5934, + "step": 97360 + }, + { + "epoch": 3.62, + "learning_rate": 6.3785472533194485e-06, + "loss": 1.7627, + "step": 97370 + }, + { + "epoch": 3.62, + "learning_rate": 6.378175326365902e-06, + "loss": 1.5986, + "step": 97380 + }, + { + "epoch": 3.62, + "learning_rate": 6.3778033994123554e-06, + "loss": 1.6683, + "step": 97390 + }, + { + "epoch": 3.62, + "learning_rate": 6.37743147245881e-06, + "loss": 1.6224, + "step": 97400 + }, + { + "epoch": 3.62, + "eval_loss": 1.6489670276641846, + "eval_runtime": 16.8293, + "eval_samples_per_second": 59.42, + "eval_steps_per_second": 3.743, + "step": 97400 + }, + { + "epoch": 3.62, + "learning_rate": 6.377059545505263e-06, + "loss": 1.7032, + "step": 97410 + }, + { + "epoch": 3.62, + "learning_rate": 6.376687618551717e-06, + "loss": 1.7891, + "step": 97420 + }, + { + "epoch": 3.62, + "learning_rate": 6.376315691598171e-06, + "loss": 1.7647, + "step": 97430 + }, + { + "epoch": 3.62, + "learning_rate": 6.3759437646446244e-06, + "loss": 1.7485, + "step": 97440 + }, + { + "epoch": 3.62, + "learning_rate": 6.375571837691078e-06, + "loss": 1.643, + "step": 97450 + }, + { + "epoch": 3.62, + "learning_rate": 6.375199910737531e-06, + "loss": 1.6611, + "step": 97460 + }, + { + "epoch": 3.63, + "learning_rate": 6.374827983783986e-06, + "loss": 1.613, + "step": 97470 + }, + { + "epoch": 3.63, + "learning_rate": 6.374456056830439e-06, + "loss": 1.6876, + "step": 97480 + }, + { + "epoch": 3.63, + "learning_rate": 6.3740841298768926e-06, + "loss": 1.6976, + "step": 97490 + }, + { + "epoch": 3.63, + "learning_rate": 6.373712202923347e-06, + "loss": 1.6516, + "step": 97500 + }, + { + "epoch": 3.63, + "eval_loss": 1.6483980417251587, + "eval_runtime": 16.8421, + "eval_samples_per_second": 59.375, + "eval_steps_per_second": 3.741, + "step": 97500 + }, + { + "epoch": 3.63, + "learning_rate": 6.3733402759698e-06, + "loss": 1.619, + "step": 97510 + }, + { + "epoch": 3.63, + "learning_rate": 6.372968349016254e-06, + "loss": 1.6501, + "step": 97520 + }, + { + "epoch": 3.63, + "learning_rate": 6.372596422062708e-06, + "loss": 1.6286, + "step": 97530 + }, + { + "epoch": 3.63, + "learning_rate": 6.3722244951091616e-06, + "loss": 1.6314, + "step": 97540 + }, + { + "epoch": 3.63, + "learning_rate": 6.371852568155614e-06, + "loss": 1.6218, + "step": 97550 + }, + { + "epoch": 3.63, + "learning_rate": 6.371480641202068e-06, + "loss": 1.7694, + "step": 97560 + }, + { + "epoch": 3.63, + "learning_rate": 6.371108714248522e-06, + "loss": 1.7395, + "step": 97570 + }, + { + "epoch": 3.63, + "learning_rate": 6.370736787294975e-06, + "loss": 1.5636, + "step": 97580 + }, + { + "epoch": 3.63, + "learning_rate": 6.370364860341429e-06, + "loss": 1.6406, + "step": 97590 + }, + { + "epoch": 3.63, + "learning_rate": 6.369992933387883e-06, + "loss": 1.6292, + "step": 97600 + }, + { + "epoch": 3.63, + "eval_loss": 1.6474928855895996, + "eval_runtime": 16.8361, + "eval_samples_per_second": 59.396, + "eval_steps_per_second": 3.742, + "step": 97600 + }, + { + "epoch": 3.63, + "learning_rate": 6.369621006434337e-06, + "loss": 1.6415, + "step": 97610 + }, + { + "epoch": 3.63, + "learning_rate": 6.36924907948079e-06, + "loss": 1.7919, + "step": 97620 + }, + { + "epoch": 3.63, + "learning_rate": 6.368877152527244e-06, + "loss": 1.6645, + "step": 97630 + }, + { + "epoch": 3.63, + "learning_rate": 6.368505225573698e-06, + "loss": 1.6554, + "step": 97640 + }, + { + "epoch": 3.63, + "learning_rate": 6.368133298620151e-06, + "loss": 1.6112, + "step": 97650 + }, + { + "epoch": 3.63, + "learning_rate": 6.367761371666606e-06, + "loss": 1.6192, + "step": 97660 + }, + { + "epoch": 3.63, + "learning_rate": 6.367389444713059e-06, + "loss": 1.7758, + "step": 97670 + }, + { + "epoch": 3.63, + "learning_rate": 6.3670175177595125e-06, + "loss": 1.7671, + "step": 97680 + }, + { + "epoch": 3.63, + "learning_rate": 6.366645590805967e-06, + "loss": 1.8463, + "step": 97690 + }, + { + "epoch": 3.63, + "learning_rate": 6.36627366385242e-06, + "loss": 1.6622, + "step": 97700 + }, + { + "epoch": 3.63, + "eval_loss": 1.6479600667953491, + "eval_runtime": 16.8184, + "eval_samples_per_second": 59.459, + "eval_steps_per_second": 3.746, + "step": 97700 + }, + { + "epoch": 3.63, + "learning_rate": 6.365901736898874e-06, + "loss": 1.8044, + "step": 97710 + }, + { + "epoch": 3.63, + "learning_rate": 6.365529809945328e-06, + "loss": 1.6453, + "step": 97720 + }, + { + "epoch": 3.63, + "learning_rate": 6.365157882991781e-06, + "loss": 1.6979, + "step": 97730 + }, + { + "epoch": 3.64, + "learning_rate": 6.364785956038234e-06, + "loss": 1.8414, + "step": 97740 + }, + { + "epoch": 3.64, + "learning_rate": 6.364414029084688e-06, + "loss": 1.7872, + "step": 97750 + }, + { + "epoch": 3.64, + "learning_rate": 6.364042102131142e-06, + "loss": 1.6569, + "step": 97760 + }, + { + "epoch": 3.64, + "learning_rate": 6.363670175177595e-06, + "loss": 1.7124, + "step": 97770 + }, + { + "epoch": 3.64, + "learning_rate": 6.363298248224049e-06, + "loss": 1.6796, + "step": 97780 + }, + { + "epoch": 3.64, + "learning_rate": 6.362926321270503e-06, + "loss": 1.6359, + "step": 97790 + }, + { + "epoch": 3.64, + "learning_rate": 6.362554394316957e-06, + "loss": 1.5572, + "step": 97800 + }, + { + "epoch": 3.64, + "eval_loss": 1.6485614776611328, + "eval_runtime": 16.8388, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 97800 + }, + { + "epoch": 3.64, + "learning_rate": 6.36218246736341e-06, + "loss": 1.7064, + "step": 97810 + }, + { + "epoch": 3.64, + "learning_rate": 6.361810540409864e-06, + "loss": 1.6798, + "step": 97820 + }, + { + "epoch": 3.64, + "learning_rate": 6.361438613456318e-06, + "loss": 1.5828, + "step": 97830 + }, + { + "epoch": 3.64, + "learning_rate": 6.361066686502771e-06, + "loss": 1.6851, + "step": 97840 + }, + { + "epoch": 3.64, + "learning_rate": 6.3606947595492256e-06, + "loss": 1.6088, + "step": 97850 + }, + { + "epoch": 3.64, + "learning_rate": 6.360322832595679e-06, + "loss": 1.6874, + "step": 97860 + }, + { + "epoch": 3.64, + "learning_rate": 6.3599509056421325e-06, + "loss": 1.6327, + "step": 97870 + }, + { + "epoch": 3.64, + "learning_rate": 6.359578978688587e-06, + "loss": 1.7396, + "step": 97880 + }, + { + "epoch": 3.64, + "learning_rate": 6.35920705173504e-06, + "loss": 1.7508, + "step": 97890 + }, + { + "epoch": 3.64, + "learning_rate": 6.358835124781494e-06, + "loss": 1.7536, + "step": 97900 + }, + { + "epoch": 3.64, + "eval_loss": 1.647265911102295, + "eval_runtime": 16.83, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 97900 + }, + { + "epoch": 3.64, + "learning_rate": 6.358463197827948e-06, + "loss": 1.6782, + "step": 97910 + }, + { + "epoch": 3.64, + "learning_rate": 6.358091270874401e-06, + "loss": 1.7215, + "step": 97920 + }, + { + "epoch": 3.64, + "learning_rate": 6.357719343920854e-06, + "loss": 1.6704, + "step": 97930 + }, + { + "epoch": 3.64, + "learning_rate": 6.3573474169673075e-06, + "loss": 1.6558, + "step": 97940 + }, + { + "epoch": 3.64, + "learning_rate": 6.356975490013762e-06, + "loss": 1.6822, + "step": 97950 + }, + { + "epoch": 3.64, + "learning_rate": 6.356603563060215e-06, + "loss": 1.6343, + "step": 97960 + }, + { + "epoch": 3.64, + "learning_rate": 6.356231636106669e-06, + "loss": 1.5972, + "step": 97970 + }, + { + "epoch": 3.64, + "learning_rate": 6.355859709153123e-06, + "loss": 1.7048, + "step": 97980 + }, + { + "epoch": 3.64, + "learning_rate": 6.3554877821995765e-06, + "loss": 1.7317, + "step": 97990 + }, + { + "epoch": 3.64, + "learning_rate": 6.35511585524603e-06, + "loss": 1.5562, + "step": 98000 + }, + { + "epoch": 3.64, + "eval_loss": 1.6474804878234863, + "eval_runtime": 16.8462, + "eval_samples_per_second": 59.361, + "eval_steps_per_second": 3.74, + "step": 98000 + }, + { + "epoch": 3.65, + "learning_rate": 6.3547439282924835e-06, + "loss": 1.7429, + "step": 98010 + }, + { + "epoch": 3.65, + "learning_rate": 6.354372001338938e-06, + "loss": 1.7667, + "step": 98020 + }, + { + "epoch": 3.65, + "learning_rate": 6.354000074385391e-06, + "loss": 1.6908, + "step": 98030 + }, + { + "epoch": 3.65, + "learning_rate": 6.353628147431845e-06, + "loss": 1.6758, + "step": 98040 + }, + { + "epoch": 3.65, + "learning_rate": 6.353256220478299e-06, + "loss": 1.6786, + "step": 98050 + }, + { + "epoch": 3.65, + "learning_rate": 6.3528842935247524e-06, + "loss": 1.6233, + "step": 98060 + }, + { + "epoch": 3.65, + "learning_rate": 6.352512366571206e-06, + "loss": 1.7804, + "step": 98070 + }, + { + "epoch": 3.65, + "learning_rate": 6.35214043961766e-06, + "loss": 1.5875, + "step": 98080 + }, + { + "epoch": 3.65, + "learning_rate": 6.351768512664114e-06, + "loss": 1.6854, + "step": 98090 + }, + { + "epoch": 3.65, + "learning_rate": 6.351396585710567e-06, + "loss": 1.6439, + "step": 98100 + }, + { + "epoch": 3.65, + "eval_loss": 1.648114800453186, + "eval_runtime": 16.8468, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 98100 + }, + { + "epoch": 3.65, + "learning_rate": 6.35102465875702e-06, + "loss": 1.8851, + "step": 98110 + }, + { + "epoch": 3.65, + "learning_rate": 6.350652731803474e-06, + "loss": 1.5101, + "step": 98120 + }, + { + "epoch": 3.65, + "learning_rate": 6.3502808048499275e-06, + "loss": 1.667, + "step": 98130 + }, + { + "epoch": 3.65, + "learning_rate": 6.349908877896381e-06, + "loss": 1.5913, + "step": 98140 + }, + { + "epoch": 3.65, + "learning_rate": 6.349536950942835e-06, + "loss": 1.656, + "step": 98150 + }, + { + "epoch": 3.65, + "learning_rate": 6.349165023989289e-06, + "loss": 1.641, + "step": 98160 + }, + { + "epoch": 3.65, + "learning_rate": 6.348793097035742e-06, + "loss": 1.7728, + "step": 98170 + }, + { + "epoch": 3.65, + "learning_rate": 6.3484211700821965e-06, + "loss": 1.5824, + "step": 98180 + }, + { + "epoch": 3.65, + "learning_rate": 6.34804924312865e-06, + "loss": 1.7584, + "step": 98190 + }, + { + "epoch": 3.65, + "learning_rate": 6.347677316175103e-06, + "loss": 1.658, + "step": 98200 + }, + { + "epoch": 3.65, + "eval_loss": 1.6469799280166626, + "eval_runtime": 16.8353, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 98200 + }, + { + "epoch": 3.65, + "learning_rate": 6.347305389221558e-06, + "loss": 1.7094, + "step": 98210 + }, + { + "epoch": 3.65, + "learning_rate": 6.346933462268011e-06, + "loss": 1.7184, + "step": 98220 + }, + { + "epoch": 3.65, + "learning_rate": 6.346561535314465e-06, + "loss": 1.7029, + "step": 98230 + }, + { + "epoch": 3.65, + "learning_rate": 6.346189608360919e-06, + "loss": 1.5446, + "step": 98240 + }, + { + "epoch": 3.65, + "learning_rate": 6.345817681407372e-06, + "loss": 1.7027, + "step": 98250 + }, + { + "epoch": 3.65, + "learning_rate": 6.345445754453826e-06, + "loss": 1.6922, + "step": 98260 + }, + { + "epoch": 3.65, + "learning_rate": 6.34507382750028e-06, + "loss": 1.6074, + "step": 98270 + }, + { + "epoch": 3.66, + "learning_rate": 6.344701900546734e-06, + "loss": 1.7712, + "step": 98280 + }, + { + "epoch": 3.66, + "learning_rate": 6.344329973593187e-06, + "loss": 1.645, + "step": 98290 + }, + { + "epoch": 3.66, + "learning_rate": 6.34395804663964e-06, + "loss": 1.7038, + "step": 98300 + }, + { + "epoch": 3.66, + "eval_loss": 1.6479252576828003, + "eval_runtime": 16.821, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 98300 + }, + { + "epoch": 3.66, + "learning_rate": 6.343586119686094e-06, + "loss": 1.6578, + "step": 98310 + }, + { + "epoch": 3.66, + "learning_rate": 6.3432141927325475e-06, + "loss": 1.7742, + "step": 98320 + }, + { + "epoch": 3.66, + "learning_rate": 6.342842265779001e-06, + "loss": 1.6911, + "step": 98330 + }, + { + "epoch": 3.66, + "learning_rate": 6.342470338825455e-06, + "loss": 1.748, + "step": 98340 + }, + { + "epoch": 3.66, + "learning_rate": 6.342098411871909e-06, + "loss": 1.7721, + "step": 98350 + }, + { + "epoch": 3.66, + "learning_rate": 6.341726484918362e-06, + "loss": 1.736, + "step": 98360 + }, + { + "epoch": 3.66, + "learning_rate": 6.3413545579648165e-06, + "loss": 1.5431, + "step": 98370 + }, + { + "epoch": 3.66, + "learning_rate": 6.34098263101127e-06, + "loss": 1.7157, + "step": 98380 + }, + { + "epoch": 3.66, + "learning_rate": 6.340610704057723e-06, + "loss": 1.6623, + "step": 98390 + }, + { + "epoch": 3.66, + "learning_rate": 6.340238777104178e-06, + "loss": 1.6335, + "step": 98400 + }, + { + "epoch": 3.66, + "eval_loss": 1.6473932266235352, + "eval_runtime": 16.8253, + "eval_samples_per_second": 59.434, + "eval_steps_per_second": 3.744, + "step": 98400 + }, + { + "epoch": 3.66, + "learning_rate": 6.339866850150631e-06, + "loss": 1.6813, + "step": 98410 + }, + { + "epoch": 3.66, + "learning_rate": 6.339494923197085e-06, + "loss": 1.787, + "step": 98420 + }, + { + "epoch": 3.66, + "learning_rate": 6.339122996243539e-06, + "loss": 1.6074, + "step": 98430 + }, + { + "epoch": 3.66, + "learning_rate": 6.338751069289992e-06, + "loss": 1.7286, + "step": 98440 + }, + { + "epoch": 3.66, + "learning_rate": 6.338379142336446e-06, + "loss": 1.7909, + "step": 98450 + }, + { + "epoch": 3.66, + "learning_rate": 6.3380072153829e-06, + "loss": 1.7912, + "step": 98460 + }, + { + "epoch": 3.66, + "learning_rate": 6.337635288429354e-06, + "loss": 1.77, + "step": 98470 + }, + { + "epoch": 3.66, + "learning_rate": 6.337263361475806e-06, + "loss": 1.633, + "step": 98480 + }, + { + "epoch": 3.66, + "learning_rate": 6.33689143452226e-06, + "loss": 1.7366, + "step": 98490 + }, + { + "epoch": 3.66, + "learning_rate": 6.336519507568714e-06, + "loss": 1.5336, + "step": 98500 + }, + { + "epoch": 3.66, + "eval_loss": 1.6472610235214233, + "eval_runtime": 16.8332, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 98500 + }, + { + "epoch": 3.66, + "learning_rate": 6.3361475806151674e-06, + "loss": 1.5608, + "step": 98510 + }, + { + "epoch": 3.66, + "learning_rate": 6.335775653661621e-06, + "loss": 1.6589, + "step": 98520 + }, + { + "epoch": 3.66, + "learning_rate": 6.335403726708075e-06, + "loss": 1.6623, + "step": 98530 + }, + { + "epoch": 3.66, + "learning_rate": 6.335031799754529e-06, + "loss": 1.6039, + "step": 98540 + }, + { + "epoch": 3.67, + "learning_rate": 6.334659872800982e-06, + "loss": 1.6795, + "step": 98550 + }, + { + "epoch": 3.67, + "learning_rate": 6.334287945847436e-06, + "loss": 1.7372, + "step": 98560 + }, + { + "epoch": 3.67, + "learning_rate": 6.33391601889389e-06, + "loss": 1.6002, + "step": 98570 + }, + { + "epoch": 3.67, + "learning_rate": 6.333544091940343e-06, + "loss": 1.588, + "step": 98580 + }, + { + "epoch": 3.67, + "learning_rate": 6.333172164986797e-06, + "loss": 1.6276, + "step": 98590 + }, + { + "epoch": 3.67, + "learning_rate": 6.332800238033251e-06, + "loss": 1.6775, + "step": 98600 + }, + { + "epoch": 3.67, + "eval_loss": 1.6475211381912231, + "eval_runtime": 16.8374, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 98600 + }, + { + "epoch": 3.67, + "learning_rate": 6.3324283110797046e-06, + "loss": 1.6934, + "step": 98610 + }, + { + "epoch": 3.67, + "learning_rate": 6.332056384126158e-06, + "loss": 1.5084, + "step": 98620 + }, + { + "epoch": 3.67, + "learning_rate": 6.331684457172612e-06, + "loss": 1.6265, + "step": 98630 + }, + { + "epoch": 3.67, + "learning_rate": 6.331312530219066e-06, + "loss": 1.623, + "step": 98640 + }, + { + "epoch": 3.67, + "learning_rate": 6.330940603265519e-06, + "loss": 1.7225, + "step": 98650 + }, + { + "epoch": 3.67, + "learning_rate": 6.3305686763119735e-06, + "loss": 1.7133, + "step": 98660 + }, + { + "epoch": 3.67, + "learning_rate": 6.330196749358426e-06, + "loss": 1.6345, + "step": 98670 + }, + { + "epoch": 3.67, + "learning_rate": 6.32982482240488e-06, + "loss": 1.7794, + "step": 98680 + }, + { + "epoch": 3.67, + "learning_rate": 6.329452895451333e-06, + "loss": 1.7346, + "step": 98690 + }, + { + "epoch": 3.67, + "learning_rate": 6.329080968497787e-06, + "loss": 1.6958, + "step": 98700 + }, + { + "epoch": 3.67, + "eval_loss": 1.647171974182129, + "eval_runtime": 16.8266, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 98700 + }, + { + "epoch": 3.67, + "learning_rate": 6.328709041544241e-06, + "loss": 1.6679, + "step": 98710 + }, + { + "epoch": 3.67, + "learning_rate": 6.328337114590694e-06, + "loss": 1.7661, + "step": 98720 + }, + { + "epoch": 3.67, + "learning_rate": 6.327965187637149e-06, + "loss": 1.8136, + "step": 98730 + }, + { + "epoch": 3.67, + "learning_rate": 6.327593260683602e-06, + "loss": 1.6529, + "step": 98740 + }, + { + "epoch": 3.67, + "learning_rate": 6.3272213337300555e-06, + "loss": 1.7603, + "step": 98750 + }, + { + "epoch": 3.67, + "learning_rate": 6.32684940677651e-06, + "loss": 1.8313, + "step": 98760 + }, + { + "epoch": 3.67, + "learning_rate": 6.326477479822963e-06, + "loss": 1.6684, + "step": 98770 + }, + { + "epoch": 3.67, + "learning_rate": 6.326105552869417e-06, + "loss": 1.6548, + "step": 98780 + }, + { + "epoch": 3.67, + "learning_rate": 6.325733625915871e-06, + "loss": 1.8125, + "step": 98790 + }, + { + "epoch": 3.67, + "learning_rate": 6.3253616989623245e-06, + "loss": 1.4869, + "step": 98800 + }, + { + "epoch": 3.67, + "eval_loss": 1.6475225687026978, + "eval_runtime": 16.8333, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 98800 + }, + { + "epoch": 3.68, + "learning_rate": 6.324989772008778e-06, + "loss": 1.7104, + "step": 98810 + }, + { + "epoch": 3.68, + "learning_rate": 6.324617845055232e-06, + "loss": 1.725, + "step": 98820 + }, + { + "epoch": 3.68, + "learning_rate": 6.324245918101686e-06, + "loss": 1.7481, + "step": 98830 + }, + { + "epoch": 3.68, + "learning_rate": 6.323873991148139e-06, + "loss": 1.7661, + "step": 98840 + }, + { + "epoch": 3.68, + "learning_rate": 6.3235020641945935e-06, + "loss": 1.7419, + "step": 98850 + }, + { + "epoch": 3.68, + "learning_rate": 6.323130137241046e-06, + "loss": 1.7378, + "step": 98860 + }, + { + "epoch": 3.68, + "learning_rate": 6.3227582102875e-06, + "loss": 1.6176, + "step": 98870 + }, + { + "epoch": 3.68, + "learning_rate": 6.322386283333953e-06, + "loss": 1.722, + "step": 98880 + }, + { + "epoch": 3.68, + "learning_rate": 6.322014356380407e-06, + "loss": 1.6881, + "step": 98890 + }, + { + "epoch": 3.68, + "learning_rate": 6.321642429426861e-06, + "loss": 1.5805, + "step": 98900 + }, + { + "epoch": 3.68, + "eval_loss": 1.6458537578582764, + "eval_runtime": 16.839, + "eval_samples_per_second": 59.386, + "eval_steps_per_second": 3.741, + "step": 98900 + }, + { + "epoch": 3.68, + "learning_rate": 6.321270502473314e-06, + "loss": 1.6287, + "step": 98910 + }, + { + "epoch": 3.68, + "learning_rate": 6.3208985755197686e-06, + "loss": 1.7408, + "step": 98920 + }, + { + "epoch": 3.68, + "learning_rate": 6.320526648566222e-06, + "loss": 1.807, + "step": 98930 + }, + { + "epoch": 3.68, + "learning_rate": 6.3201547216126755e-06, + "loss": 1.6689, + "step": 98940 + }, + { + "epoch": 3.68, + "learning_rate": 6.31978279465913e-06, + "loss": 1.7209, + "step": 98950 + }, + { + "epoch": 3.68, + "learning_rate": 6.319410867705583e-06, + "loss": 1.7209, + "step": 98960 + }, + { + "epoch": 3.68, + "learning_rate": 6.319038940752037e-06, + "loss": 1.6756, + "step": 98970 + }, + { + "epoch": 3.68, + "learning_rate": 6.318667013798491e-06, + "loss": 1.7645, + "step": 98980 + }, + { + "epoch": 3.68, + "learning_rate": 6.3182950868449445e-06, + "loss": 1.839, + "step": 98990 + }, + { + "epoch": 3.68, + "learning_rate": 6.317923159891398e-06, + "loss": 1.7283, + "step": 99000 + }, + { + "epoch": 3.68, + "eval_loss": 1.6475114822387695, + "eval_runtime": 16.8418, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 99000 + }, + { + "epoch": 3.68, + "learning_rate": 6.317551232937852e-06, + "loss": 1.617, + "step": 99010 + }, + { + "epoch": 3.68, + "learning_rate": 6.317179305984306e-06, + "loss": 1.8333, + "step": 99020 + }, + { + "epoch": 3.68, + "learning_rate": 6.316807379030759e-06, + "loss": 1.7412, + "step": 99030 + }, + { + "epoch": 3.68, + "learning_rate": 6.3164354520772135e-06, + "loss": 1.7063, + "step": 99040 + }, + { + "epoch": 3.68, + "learning_rate": 6.316063525123666e-06, + "loss": 1.6578, + "step": 99050 + }, + { + "epoch": 3.68, + "learning_rate": 6.3156915981701195e-06, + "loss": 1.726, + "step": 99060 + }, + { + "epoch": 3.68, + "learning_rate": 6.315319671216573e-06, + "loss": 1.6075, + "step": 99070 + }, + { + "epoch": 3.69, + "learning_rate": 6.314947744263027e-06, + "loss": 1.5265, + "step": 99080 + }, + { + "epoch": 3.69, + "learning_rate": 6.314575817309481e-06, + "loss": 1.771, + "step": 99090 + }, + { + "epoch": 3.69, + "learning_rate": 6.314203890355934e-06, + "loss": 1.7497, + "step": 99100 + }, + { + "epoch": 3.69, + "eval_loss": 1.6465473175048828, + "eval_runtime": 16.8515, + "eval_samples_per_second": 59.342, + "eval_steps_per_second": 3.739, + "step": 99100 + }, + { + "epoch": 3.69, + "learning_rate": 6.3138319634023885e-06, + "loss": 1.7472, + "step": 99110 + }, + { + "epoch": 3.69, + "learning_rate": 6.313460036448842e-06, + "loss": 1.729, + "step": 99120 + }, + { + "epoch": 3.69, + "learning_rate": 6.3130881094952954e-06, + "loss": 1.6703, + "step": 99130 + }, + { + "epoch": 3.69, + "learning_rate": 6.31271618254175e-06, + "loss": 1.7664, + "step": 99140 + }, + { + "epoch": 3.69, + "learning_rate": 6.312344255588203e-06, + "loss": 1.6961, + "step": 99150 + }, + { + "epoch": 3.69, + "learning_rate": 6.311972328634657e-06, + "loss": 1.6616, + "step": 99160 + }, + { + "epoch": 3.69, + "learning_rate": 6.31160040168111e-06, + "loss": 1.5724, + "step": 99170 + }, + { + "epoch": 3.69, + "learning_rate": 6.3112284747275644e-06, + "loss": 1.7729, + "step": 99180 + }, + { + "epoch": 3.69, + "learning_rate": 6.310856547774018e-06, + "loss": 1.7104, + "step": 99190 + }, + { + "epoch": 3.69, + "learning_rate": 6.310484620820471e-06, + "loss": 1.6587, + "step": 99200 + }, + { + "epoch": 3.69, + "eval_loss": 1.6469897031784058, + "eval_runtime": 16.8282, + "eval_samples_per_second": 59.424, + "eval_steps_per_second": 3.744, + "step": 99200 + }, + { + "epoch": 3.69, + "learning_rate": 6.310112693866926e-06, + "loss": 1.7408, + "step": 99210 + }, + { + "epoch": 3.69, + "learning_rate": 6.309740766913379e-06, + "loss": 1.7255, + "step": 99220 + }, + { + "epoch": 3.69, + "learning_rate": 6.309368839959833e-06, + "loss": 1.7199, + "step": 99230 + }, + { + "epoch": 3.69, + "learning_rate": 6.308996913006285e-06, + "loss": 1.6168, + "step": 99240 + }, + { + "epoch": 3.69, + "learning_rate": 6.3086249860527395e-06, + "loss": 1.7812, + "step": 99250 + }, + { + "epoch": 3.69, + "learning_rate": 6.308253059099193e-06, + "loss": 1.5863, + "step": 99260 + }, + { + "epoch": 3.69, + "learning_rate": 6.307881132145646e-06, + "loss": 1.7282, + "step": 99270 + }, + { + "epoch": 3.69, + "learning_rate": 6.307509205192101e-06, + "loss": 1.6125, + "step": 99280 + }, + { + "epoch": 3.69, + "learning_rate": 6.307137278238554e-06, + "loss": 1.6401, + "step": 99290 + }, + { + "epoch": 3.69, + "learning_rate": 6.306765351285008e-06, + "loss": 1.6284, + "step": 99300 + }, + { + "epoch": 3.69, + "eval_loss": 1.6462552547454834, + "eval_runtime": 16.8226, + "eval_samples_per_second": 59.444, + "eval_steps_per_second": 3.745, + "step": 99300 + }, + { + "epoch": 3.69, + "learning_rate": 6.306393424331462e-06, + "loss": 1.5169, + "step": 99310 + }, + { + "epoch": 3.69, + "learning_rate": 6.306021497377915e-06, + "loss": 1.7471, + "step": 99320 + }, + { + "epoch": 3.69, + "learning_rate": 6.305649570424369e-06, + "loss": 1.688, + "step": 99330 + }, + { + "epoch": 3.69, + "learning_rate": 6.305277643470823e-06, + "loss": 1.7768, + "step": 99340 + }, + { + "epoch": 3.7, + "learning_rate": 6.304905716517277e-06, + "loss": 1.679, + "step": 99350 + }, + { + "epoch": 3.7, + "learning_rate": 6.30453378956373e-06, + "loss": 1.6187, + "step": 99360 + }, + { + "epoch": 3.7, + "learning_rate": 6.304161862610184e-06, + "loss": 1.7475, + "step": 99370 + }, + { + "epoch": 3.7, + "learning_rate": 6.303789935656638e-06, + "loss": 1.7753, + "step": 99380 + }, + { + "epoch": 3.7, + "learning_rate": 6.303418008703091e-06, + "loss": 1.7339, + "step": 99390 + }, + { + "epoch": 3.7, + "learning_rate": 6.303046081749546e-06, + "loss": 1.5898, + "step": 99400 + }, + { + "epoch": 3.7, + "eval_loss": 1.6459406614303589, + "eval_runtime": 16.838, + "eval_samples_per_second": 59.39, + "eval_steps_per_second": 3.742, + "step": 99400 + }, + { + "epoch": 3.7, + "learning_rate": 6.302674154795999e-06, + "loss": 1.7193, + "step": 99410 + }, + { + "epoch": 3.7, + "learning_rate": 6.302302227842452e-06, + "loss": 1.7957, + "step": 99420 + }, + { + "epoch": 3.7, + "learning_rate": 6.301930300888905e-06, + "loss": 1.6356, + "step": 99430 + }, + { + "epoch": 3.7, + "learning_rate": 6.3015583739353595e-06, + "loss": 1.6807, + "step": 99440 + }, + { + "epoch": 3.7, + "learning_rate": 6.301186446981813e-06, + "loss": 1.6397, + "step": 99450 + }, + { + "epoch": 3.7, + "learning_rate": 6.300814520028266e-06, + "loss": 1.73, + "step": 99460 + }, + { + "epoch": 3.7, + "learning_rate": 6.300442593074721e-06, + "loss": 1.5821, + "step": 99470 + }, + { + "epoch": 3.7, + "learning_rate": 6.300070666121174e-06, + "loss": 1.6958, + "step": 99480 + }, + { + "epoch": 3.7, + "learning_rate": 6.299698739167628e-06, + "loss": 1.7131, + "step": 99490 + }, + { + "epoch": 3.7, + "learning_rate": 6.299326812214082e-06, + "loss": 1.6432, + "step": 99500 + }, + { + "epoch": 3.7, + "eval_loss": 1.6460448503494263, + "eval_runtime": 16.8426, + "eval_samples_per_second": 59.373, + "eval_steps_per_second": 3.741, + "step": 99500 + }, + { + "epoch": 3.7, + "learning_rate": 6.298954885260535e-06, + "loss": 1.8027, + "step": 99510 + }, + { + "epoch": 3.7, + "learning_rate": 6.298582958306989e-06, + "loss": 1.6516, + "step": 99520 + }, + { + "epoch": 3.7, + "learning_rate": 6.298211031353443e-06, + "loss": 1.8279, + "step": 99530 + }, + { + "epoch": 3.7, + "learning_rate": 6.297839104399897e-06, + "loss": 1.6556, + "step": 99540 + }, + { + "epoch": 3.7, + "learning_rate": 6.29746717744635e-06, + "loss": 1.7168, + "step": 99550 + }, + { + "epoch": 3.7, + "learning_rate": 6.297095250492804e-06, + "loss": 1.7743, + "step": 99560 + }, + { + "epoch": 3.7, + "learning_rate": 6.296723323539258e-06, + "loss": 1.712, + "step": 99570 + }, + { + "epoch": 3.7, + "learning_rate": 6.296351396585711e-06, + "loss": 1.7412, + "step": 99580 + }, + { + "epoch": 3.7, + "learning_rate": 6.295979469632166e-06, + "loss": 1.6847, + "step": 99590 + }, + { + "epoch": 3.7, + "learning_rate": 6.295607542678619e-06, + "loss": 1.7282, + "step": 99600 + }, + { + "epoch": 3.7, + "eval_loss": 1.6456305980682373, + "eval_runtime": 16.8442, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 99600 + }, + { + "epoch": 3.7, + "learning_rate": 6.295235615725072e-06, + "loss": 1.6738, + "step": 99610 + }, + { + "epoch": 3.71, + "learning_rate": 6.294863688771525e-06, + "loss": 1.7098, + "step": 99620 + }, + { + "epoch": 3.71, + "learning_rate": 6.294491761817979e-06, + "loss": 1.9201, + "step": 99630 + }, + { + "epoch": 3.71, + "learning_rate": 6.294119834864433e-06, + "loss": 1.5983, + "step": 99640 + }, + { + "epoch": 3.71, + "learning_rate": 6.293747907910886e-06, + "loss": 1.5831, + "step": 99650 + }, + { + "epoch": 3.71, + "learning_rate": 6.293375980957341e-06, + "loss": 1.5483, + "step": 99660 + }, + { + "epoch": 3.71, + "learning_rate": 6.293004054003794e-06, + "loss": 1.718, + "step": 99670 + }, + { + "epoch": 3.71, + "learning_rate": 6.2926321270502476e-06, + "loss": 1.5521, + "step": 99680 + }, + { + "epoch": 3.71, + "learning_rate": 6.292260200096702e-06, + "loss": 1.6791, + "step": 99690 + }, + { + "epoch": 3.71, + "learning_rate": 6.291888273143155e-06, + "loss": 1.622, + "step": 99700 + }, + { + "epoch": 3.71, + "eval_loss": 1.6461379528045654, + "eval_runtime": 16.8328, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 99700 + }, + { + "epoch": 3.71, + "learning_rate": 6.291516346189609e-06, + "loss": 1.6175, + "step": 99710 + }, + { + "epoch": 3.71, + "learning_rate": 6.291144419236063e-06, + "loss": 1.7111, + "step": 99720 + }, + { + "epoch": 3.71, + "learning_rate": 6.2907724922825165e-06, + "loss": 1.7377, + "step": 99730 + }, + { + "epoch": 3.71, + "learning_rate": 6.29040056532897e-06, + "loss": 1.6209, + "step": 99740 + }, + { + "epoch": 3.71, + "learning_rate": 6.2900286383754235e-06, + "loss": 1.6583, + "step": 99750 + }, + { + "epoch": 3.71, + "learning_rate": 6.289656711421878e-06, + "loss": 1.6083, + "step": 99760 + }, + { + "epoch": 3.71, + "learning_rate": 6.289284784468331e-06, + "loss": 1.6694, + "step": 99770 + }, + { + "epoch": 3.71, + "learning_rate": 6.288912857514785e-06, + "loss": 1.6363, + "step": 99780 + }, + { + "epoch": 3.71, + "learning_rate": 6.288540930561239e-06, + "loss": 1.8816, + "step": 99790 + }, + { + "epoch": 3.71, + "learning_rate": 6.288169003607692e-06, + "loss": 1.6401, + "step": 99800 + }, + { + "epoch": 3.71, + "eval_loss": 1.6460577249526978, + "eval_runtime": 16.8498, + "eval_samples_per_second": 59.348, + "eval_steps_per_second": 3.739, + "step": 99800 + }, + { + "epoch": 3.71, + "learning_rate": 6.287797076654145e-06, + "loss": 1.6268, + "step": 99810 + }, + { + "epoch": 3.71, + "learning_rate": 6.2874251497005985e-06, + "loss": 1.7017, + "step": 99820 + }, + { + "epoch": 3.71, + "learning_rate": 6.287053222747053e-06, + "loss": 1.6538, + "step": 99830 + }, + { + "epoch": 3.71, + "learning_rate": 6.286681295793506e-06, + "loss": 1.5593, + "step": 99840 + }, + { + "epoch": 3.71, + "learning_rate": 6.28630936883996e-06, + "loss": 1.7829, + "step": 99850 + }, + { + "epoch": 3.71, + "learning_rate": 6.285937441886414e-06, + "loss": 1.7034, + "step": 99860 + }, + { + "epoch": 3.71, + "learning_rate": 6.2855655149328675e-06, + "loss": 1.7411, + "step": 99870 + }, + { + "epoch": 3.71, + "learning_rate": 6.285193587979321e-06, + "loss": 1.7406, + "step": 99880 + }, + { + "epoch": 3.72, + "learning_rate": 6.284821661025775e-06, + "loss": 1.6695, + "step": 99890 + }, + { + "epoch": 3.72, + "learning_rate": 6.284449734072229e-06, + "loss": 1.7867, + "step": 99900 + }, + { + "epoch": 3.72, + "eval_loss": 1.6461026668548584, + "eval_runtime": 16.832, + "eval_samples_per_second": 59.411, + "eval_steps_per_second": 3.743, + "step": 99900 + }, + { + "epoch": 3.72, + "learning_rate": 6.284077807118682e-06, + "loss": 1.765, + "step": 99910 + }, + { + "epoch": 3.72, + "learning_rate": 6.2837058801651365e-06, + "loss": 1.8232, + "step": 99920 + }, + { + "epoch": 3.72, + "learning_rate": 6.28333395321159e-06, + "loss": 1.6584, + "step": 99930 + }, + { + "epoch": 3.72, + "learning_rate": 6.282962026258043e-06, + "loss": 1.8272, + "step": 99940 + }, + { + "epoch": 3.72, + "learning_rate": 6.282590099304498e-06, + "loss": 1.6189, + "step": 99950 + }, + { + "epoch": 3.72, + "learning_rate": 6.282218172350951e-06, + "loss": 1.6699, + "step": 99960 + }, + { + "epoch": 3.72, + "learning_rate": 6.281846245397405e-06, + "loss": 1.7645, + "step": 99970 + }, + { + "epoch": 3.72, + "learning_rate": 6.281474318443859e-06, + "loss": 1.6793, + "step": 99980 + }, + { + "epoch": 3.72, + "learning_rate": 6.2811023914903116e-06, + "loss": 1.6924, + "step": 99990 + }, + { + "epoch": 3.72, + "learning_rate": 6.280730464536765e-06, + "loss": 1.629, + "step": 100000 + }, + { + "epoch": 3.72, + "eval_loss": 1.6462661027908325, + "eval_runtime": 16.8397, + "eval_samples_per_second": 59.383, + "eval_steps_per_second": 3.741, + "step": 100000 + }, + { + "epoch": 3.72, + "learning_rate": 6.2803585375832185e-06, + "loss": 1.8362, + "step": 100010 + }, + { + "epoch": 3.72, + "learning_rate": 6.279986610629673e-06, + "loss": 1.6399, + "step": 100020 + }, + { + "epoch": 3.72, + "learning_rate": 6.279614683676126e-06, + "loss": 1.5743, + "step": 100030 + }, + { + "epoch": 3.72, + "learning_rate": 6.27924275672258e-06, + "loss": 1.7168, + "step": 100040 + }, + { + "epoch": 3.72, + "learning_rate": 6.278870829769034e-06, + "loss": 1.6461, + "step": 100050 + }, + { + "epoch": 3.72, + "learning_rate": 6.2784989028154875e-06, + "loss": 1.6378, + "step": 100060 + }, + { + "epoch": 3.72, + "learning_rate": 6.278126975861941e-06, + "loss": 1.5899, + "step": 100070 + }, + { + "epoch": 3.72, + "learning_rate": 6.277755048908395e-06, + "loss": 1.6352, + "step": 100080 + }, + { + "epoch": 3.72, + "learning_rate": 6.277383121954849e-06, + "loss": 1.8243, + "step": 100090 + }, + { + "epoch": 3.72, + "learning_rate": 6.277011195001302e-06, + "loss": 1.528, + "step": 100100 + }, + { + "epoch": 3.72, + "eval_loss": 1.645893931388855, + "eval_runtime": 16.837, + "eval_samples_per_second": 59.393, + "eval_steps_per_second": 3.742, + "step": 100100 + }, + { + "epoch": 3.72, + "learning_rate": 6.2766392680477565e-06, + "loss": 1.6398, + "step": 100110 + }, + { + "epoch": 3.72, + "learning_rate": 6.27626734109421e-06, + "loss": 1.6543, + "step": 100120 + }, + { + "epoch": 3.72, + "learning_rate": 6.275895414140663e-06, + "loss": 1.7113, + "step": 100130 + }, + { + "epoch": 3.72, + "learning_rate": 6.275523487187118e-06, + "loss": 1.6558, + "step": 100140 + }, + { + "epoch": 3.72, + "learning_rate": 6.275151560233571e-06, + "loss": 1.7456, + "step": 100150 + }, + { + "epoch": 3.73, + "learning_rate": 6.274779633280025e-06, + "loss": 1.7111, + "step": 100160 + }, + { + "epoch": 3.73, + "learning_rate": 6.274407706326477e-06, + "loss": 1.6944, + "step": 100170 + }, + { + "epoch": 3.73, + "learning_rate": 6.2740357793729315e-06, + "loss": 1.6365, + "step": 100180 + }, + { + "epoch": 3.73, + "learning_rate": 6.273663852419385e-06, + "loss": 1.6117, + "step": 100190 + }, + { + "epoch": 3.73, + "learning_rate": 6.2732919254658384e-06, + "loss": 1.6523, + "step": 100200 + }, + { + "epoch": 3.73, + "eval_loss": 1.645009994506836, + "eval_runtime": 16.8464, + "eval_samples_per_second": 59.36, + "eval_steps_per_second": 3.74, + "step": 100200 + }, + { + "epoch": 3.73, + "learning_rate": 6.272919998512293e-06, + "loss": 1.6079, + "step": 100210 + }, + { + "epoch": 3.73, + "learning_rate": 6.272548071558746e-06, + "loss": 1.8329, + "step": 100220 + }, + { + "epoch": 3.73, + "learning_rate": 6.2721761446052e-06, + "loss": 1.7842, + "step": 100230 + }, + { + "epoch": 3.73, + "learning_rate": 6.271804217651654e-06, + "loss": 1.8539, + "step": 100240 + }, + { + "epoch": 3.73, + "learning_rate": 6.2714322906981074e-06, + "loss": 1.644, + "step": 100250 + }, + { + "epoch": 3.73, + "learning_rate": 6.271060363744561e-06, + "loss": 1.5777, + "step": 100260 + }, + { + "epoch": 3.73, + "learning_rate": 6.270688436791015e-06, + "loss": 1.6366, + "step": 100270 + }, + { + "epoch": 3.73, + "learning_rate": 6.270316509837469e-06, + "loss": 1.6868, + "step": 100280 + }, + { + "epoch": 3.73, + "learning_rate": 6.269944582883922e-06, + "loss": 1.569, + "step": 100290 + }, + { + "epoch": 3.73, + "learning_rate": 6.269572655930376e-06, + "loss": 1.6954, + "step": 100300 + }, + { + "epoch": 3.73, + "eval_loss": 1.6450681686401367, + "eval_runtime": 16.8388, + "eval_samples_per_second": 59.387, + "eval_steps_per_second": 3.741, + "step": 100300 + }, + { + "epoch": 3.73, + "learning_rate": 6.26920072897683e-06, + "loss": 1.7195, + "step": 100310 + }, + { + "epoch": 3.73, + "learning_rate": 6.268828802023283e-06, + "loss": 1.7435, + "step": 100320 + }, + { + "epoch": 3.73, + "learning_rate": 6.268456875069737e-06, + "loss": 1.6916, + "step": 100330 + }, + { + "epoch": 3.73, + "learning_rate": 6.268084948116191e-06, + "loss": 1.6785, + "step": 100340 + }, + { + "epoch": 3.73, + "learning_rate": 6.2677130211626446e-06, + "loss": 1.7152, + "step": 100350 + }, + { + "epoch": 3.73, + "learning_rate": 6.267341094209097e-06, + "loss": 1.5696, + "step": 100360 + }, + { + "epoch": 3.73, + "learning_rate": 6.266969167255551e-06, + "loss": 1.639, + "step": 100370 + }, + { + "epoch": 3.73, + "learning_rate": 6.266597240302005e-06, + "loss": 1.7823, + "step": 100380 + }, + { + "epoch": 3.73, + "learning_rate": 6.266225313348458e-06, + "loss": 1.6349, + "step": 100390 + }, + { + "epoch": 3.73, + "learning_rate": 6.265853386394912e-06, + "loss": 1.6807, + "step": 100400 + }, + { + "epoch": 3.73, + "eval_loss": 1.6452670097351074, + "eval_runtime": 16.825, + "eval_samples_per_second": 59.435, + "eval_steps_per_second": 3.744, + "step": 100400 + }, + { + "epoch": 3.73, + "learning_rate": 6.265481459441366e-06, + "loss": 1.6407, + "step": 100410 + }, + { + "epoch": 3.73, + "learning_rate": 6.26510953248782e-06, + "loss": 1.6929, + "step": 100420 + }, + { + "epoch": 3.74, + "learning_rate": 6.264737605534273e-06, + "loss": 1.6677, + "step": 100430 + }, + { + "epoch": 3.74, + "learning_rate": 6.264365678580727e-06, + "loss": 1.7124, + "step": 100440 + }, + { + "epoch": 3.74, + "learning_rate": 6.263993751627181e-06, + "loss": 1.7199, + "step": 100450 + }, + { + "epoch": 3.74, + "learning_rate": 6.263621824673634e-06, + "loss": 1.6596, + "step": 100460 + }, + { + "epoch": 3.74, + "learning_rate": 6.263249897720089e-06, + "loss": 1.7645, + "step": 100470 + }, + { + "epoch": 3.74, + "learning_rate": 6.262877970766542e-06, + "loss": 1.6193, + "step": 100480 + }, + { + "epoch": 3.74, + "learning_rate": 6.2625060438129955e-06, + "loss": 1.6217, + "step": 100490 + }, + { + "epoch": 3.74, + "learning_rate": 6.26213411685945e-06, + "loss": 1.6794, + "step": 100500 + }, + { + "epoch": 3.74, + "eval_loss": 1.6446884870529175, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 100500 + }, + { + "epoch": 3.74, + "learning_rate": 6.261762189905903e-06, + "loss": 1.6849, + "step": 100510 + }, + { + "epoch": 3.74, + "learning_rate": 6.261390262952357e-06, + "loss": 1.7223, + "step": 100520 + }, + { + "epoch": 3.74, + "learning_rate": 6.261018335998811e-06, + "loss": 1.6737, + "step": 100530 + }, + { + "epoch": 3.74, + "learning_rate": 6.2606464090452645e-06, + "loss": 1.8344, + "step": 100540 + }, + { + "epoch": 3.74, + "learning_rate": 6.260274482091717e-06, + "loss": 1.5442, + "step": 100550 + }, + { + "epoch": 3.74, + "learning_rate": 6.259902555138171e-06, + "loss": 1.6764, + "step": 100560 + }, + { + "epoch": 3.74, + "learning_rate": 6.259530628184625e-06, + "loss": 1.7051, + "step": 100570 + }, + { + "epoch": 3.74, + "learning_rate": 6.259158701231078e-06, + "loss": 1.645, + "step": 100580 + }, + { + "epoch": 3.74, + "learning_rate": 6.258786774277532e-06, + "loss": 1.7099, + "step": 100590 + }, + { + "epoch": 3.74, + "learning_rate": 6.258414847323986e-06, + "loss": 1.7004, + "step": 100600 + }, + { + "epoch": 3.74, + "eval_loss": 1.644309401512146, + "eval_runtime": 16.8334, + "eval_samples_per_second": 59.406, + "eval_steps_per_second": 3.743, + "step": 100600 + }, + { + "epoch": 3.74, + "learning_rate": 6.25804292037044e-06, + "loss": 1.7181, + "step": 100610 + }, + { + "epoch": 3.74, + "learning_rate": 6.257670993416893e-06, + "loss": 1.8045, + "step": 100620 + }, + { + "epoch": 3.74, + "learning_rate": 6.257299066463347e-06, + "loss": 1.6168, + "step": 100630 + }, + { + "epoch": 3.74, + "learning_rate": 6.256927139509801e-06, + "loss": 1.6545, + "step": 100640 + }, + { + "epoch": 3.74, + "learning_rate": 6.256555212556254e-06, + "loss": 1.7306, + "step": 100650 + }, + { + "epoch": 3.74, + "learning_rate": 6.2561832856027086e-06, + "loss": 1.6514, + "step": 100660 + }, + { + "epoch": 3.74, + "learning_rate": 6.255811358649162e-06, + "loss": 1.5931, + "step": 100670 + }, + { + "epoch": 3.74, + "learning_rate": 6.2554394316956155e-06, + "loss": 1.5874, + "step": 100680 + }, + { + "epoch": 3.74, + "learning_rate": 6.25506750474207e-06, + "loss": 1.546, + "step": 100690 + }, + { + "epoch": 3.75, + "learning_rate": 6.254695577788523e-06, + "loss": 1.8519, + "step": 100700 + }, + { + "epoch": 3.75, + "eval_loss": 1.644180417060852, + "eval_runtime": 16.8329, + "eval_samples_per_second": 59.408, + "eval_steps_per_second": 3.743, + "step": 100700 + }, + { + "epoch": 3.75, + "learning_rate": 6.254323650834977e-06, + "loss": 1.7403, + "step": 100710 + }, + { + "epoch": 3.75, + "learning_rate": 6.253951723881431e-06, + "loss": 1.7108, + "step": 100720 + }, + { + "epoch": 3.75, + "learning_rate": 6.2535797969278845e-06, + "loss": 1.7579, + "step": 100730 + }, + { + "epoch": 3.75, + "learning_rate": 6.253207869974337e-06, + "loss": 1.5964, + "step": 100740 + }, + { + "epoch": 3.75, + "learning_rate": 6.2528359430207906e-06, + "loss": 1.7981, + "step": 100750 + }, + { + "epoch": 3.75, + "learning_rate": 6.252464016067245e-06, + "loss": 1.6993, + "step": 100760 + }, + { + "epoch": 3.75, + "learning_rate": 6.252092089113698e-06, + "loss": 1.7244, + "step": 100770 + }, + { + "epoch": 3.75, + "learning_rate": 6.251720162160152e-06, + "loss": 1.7143, + "step": 100780 + }, + { + "epoch": 3.75, + "learning_rate": 6.251348235206606e-06, + "loss": 1.7192, + "step": 100790 + }, + { + "epoch": 3.75, + "learning_rate": 6.2509763082530595e-06, + "loss": 1.7054, + "step": 100800 + }, + { + "epoch": 3.75, + "eval_loss": 1.6439785957336426, + "eval_runtime": 16.8358, + "eval_samples_per_second": 59.397, + "eval_steps_per_second": 3.742, + "step": 100800 + }, + { + "epoch": 3.75, + "learning_rate": 6.250604381299513e-06, + "loss": 1.7075, + "step": 100810 + }, + { + "epoch": 3.75, + "learning_rate": 6.250232454345967e-06, + "loss": 1.7551, + "step": 100820 + }, + { + "epoch": 3.75, + "learning_rate": 6.249860527392421e-06, + "loss": 1.7475, + "step": 100830 + }, + { + "epoch": 3.75, + "learning_rate": 6.249488600438874e-06, + "loss": 1.791, + "step": 100840 + }, + { + "epoch": 3.75, + "learning_rate": 6.2491166734853285e-06, + "loss": 1.6515, + "step": 100850 + }, + { + "epoch": 3.75, + "learning_rate": 6.248744746531782e-06, + "loss": 1.7016, + "step": 100860 + }, + { + "epoch": 3.75, + "learning_rate": 6.2483728195782355e-06, + "loss": 1.6958, + "step": 100870 + }, + { + "epoch": 3.75, + "learning_rate": 6.24800089262469e-06, + "loss": 1.5473, + "step": 100880 + }, + { + "epoch": 3.75, + "learning_rate": 6.247628965671143e-06, + "loss": 1.6133, + "step": 100890 + }, + { + "epoch": 3.75, + "learning_rate": 6.247257038717597e-06, + "loss": 1.7718, + "step": 100900 + }, + { + "epoch": 3.75, + "eval_loss": 1.6445484161376953, + "eval_runtime": 16.8211, + "eval_samples_per_second": 59.449, + "eval_steps_per_second": 3.745, + "step": 100900 + }, + { + "epoch": 3.75, + "learning_rate": 6.24688511176405e-06, + "loss": 1.773, + "step": 100910 + }, + { + "epoch": 3.75, + "learning_rate": 6.2465131848105044e-06, + "loss": 1.5234, + "step": 100920 + }, + { + "epoch": 3.75, + "learning_rate": 6.246141257856957e-06, + "loss": 1.7856, + "step": 100930 + }, + { + "epoch": 3.75, + "learning_rate": 6.2457693309034105e-06, + "loss": 1.7397, + "step": 100940 + }, + { + "epoch": 3.75, + "learning_rate": 6.245397403949864e-06, + "loss": 1.6973, + "step": 100950 + }, + { + "epoch": 3.75, + "learning_rate": 6.245025476996318e-06, + "loss": 1.618, + "step": 100960 + }, + { + "epoch": 3.76, + "learning_rate": 6.244653550042772e-06, + "loss": 1.8472, + "step": 100970 + }, + { + "epoch": 3.76, + "learning_rate": 6.244281623089225e-06, + "loss": 1.7, + "step": 100980 + }, + { + "epoch": 3.76, + "learning_rate": 6.2439096961356795e-06, + "loss": 1.7895, + "step": 100990 + }, + { + "epoch": 3.76, + "learning_rate": 6.243537769182133e-06, + "loss": 1.8471, + "step": 101000 + }, + { + "epoch": 3.76, + "eval_loss": 1.6440532207489014, + "eval_runtime": 16.8188, + "eval_samples_per_second": 59.457, + "eval_steps_per_second": 3.746, + "step": 101000 + }, + { + "epoch": 3.76, + "learning_rate": 6.243165842228586e-06, + "loss": 1.8131, + "step": 101010 + }, + { + "epoch": 3.76, + "learning_rate": 6.242793915275041e-06, + "loss": 1.6026, + "step": 101020 + }, + { + "epoch": 3.76, + "learning_rate": 6.242421988321494e-06, + "loss": 1.7801, + "step": 101030 + }, + { + "epoch": 3.76, + "learning_rate": 6.242050061367948e-06, + "loss": 1.8068, + "step": 101040 + }, + { + "epoch": 3.76, + "learning_rate": 6.241678134414402e-06, + "loss": 1.7848, + "step": 101050 + }, + { + "epoch": 3.76, + "learning_rate": 6.241306207460855e-06, + "loss": 1.8469, + "step": 101060 + }, + { + "epoch": 3.76, + "learning_rate": 6.240934280507309e-06, + "loss": 1.5541, + "step": 101070 + }, + { + "epoch": 3.76, + "learning_rate": 6.240562353553763e-06, + "loss": 1.6248, + "step": 101080 + }, + { + "epoch": 3.76, + "learning_rate": 6.240190426600217e-06, + "loss": 1.6774, + "step": 101090 + }, + { + "epoch": 3.76, + "learning_rate": 6.23981849964667e-06, + "loss": 1.7251, + "step": 101100 + }, + { + "epoch": 3.76, + "eval_loss": 1.6428180932998657, + "eval_runtime": 16.8386, + "eval_samples_per_second": 59.388, + "eval_steps_per_second": 3.741, + "step": 101100 + }, + { + "epoch": 3.76, + "learning_rate": 6.239446572693123e-06, + "loss": 1.7866, + "step": 101110 + }, + { + "epoch": 3.76, + "learning_rate": 6.239074645739577e-06, + "loss": 1.6438, + "step": 101120 + }, + { + "epoch": 3.76, + "learning_rate": 6.2387027187860305e-06, + "loss": 1.6893, + "step": 101130 + }, + { + "epoch": 3.76, + "learning_rate": 6.238330791832484e-06, + "loss": 1.6075, + "step": 101140 + }, + { + "epoch": 3.76, + "learning_rate": 6.237958864878938e-06, + "loss": 1.7416, + "step": 101150 + }, + { + "epoch": 3.76, + "learning_rate": 6.237586937925392e-06, + "loss": 1.6553, + "step": 101160 + }, + { + "epoch": 3.76, + "learning_rate": 6.237215010971845e-06, + "loss": 1.7495, + "step": 101170 + }, + { + "epoch": 3.76, + "learning_rate": 6.2368430840182995e-06, + "loss": 1.6541, + "step": 101180 + }, + { + "epoch": 3.76, + "learning_rate": 6.236471157064753e-06, + "loss": 1.5532, + "step": 101190 + }, + { + "epoch": 3.76, + "learning_rate": 6.236099230111206e-06, + "loss": 1.6588, + "step": 101200 + }, + { + "epoch": 3.76, + "eval_loss": 1.6442584991455078, + "eval_runtime": 16.8468, + "eval_samples_per_second": 59.358, + "eval_steps_per_second": 3.74, + "step": 101200 + }, + { + "epoch": 3.76, + "learning_rate": 6.235727303157661e-06, + "loss": 1.6474, + "step": 101210 + }, + { + "epoch": 3.76, + "learning_rate": 6.235355376204114e-06, + "loss": 1.6193, + "step": 101220 + }, + { + "epoch": 3.77, + "learning_rate": 6.234983449250568e-06, + "loss": 1.6131, + "step": 101230 + }, + { + "epoch": 3.77, + "learning_rate": 6.234611522297022e-06, + "loss": 1.6029, + "step": 101240 + }, + { + "epoch": 3.77, + "learning_rate": 6.234239595343475e-06, + "loss": 1.6166, + "step": 101250 + }, + { + "epoch": 3.77, + "learning_rate": 6.233867668389929e-06, + "loss": 1.6512, + "step": 101260 + }, + { + "epoch": 3.77, + "learning_rate": 6.233495741436383e-06, + "loss": 1.6747, + "step": 101270 + }, + { + "epoch": 3.77, + "learning_rate": 6.233123814482837e-06, + "loss": 1.645, + "step": 101280 + }, + { + "epoch": 3.77, + "learning_rate": 6.23275188752929e-06, + "loss": 1.6092, + "step": 101290 + }, + { + "epoch": 3.77, + "learning_rate": 6.232379960575743e-06, + "loss": 1.7526, + "step": 101300 + }, + { + "epoch": 3.77, + "eval_loss": 1.6432197093963623, + "eval_runtime": 16.8404, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 101300 + }, + { + "epoch": 3.77, + "learning_rate": 6.232008033622197e-06, + "loss": 1.6894, + "step": 101310 + }, + { + "epoch": 3.77, + "learning_rate": 6.2316361066686504e-06, + "loss": 1.5586, + "step": 101320 + }, + { + "epoch": 3.77, + "learning_rate": 6.231264179715104e-06, + "loss": 1.5708, + "step": 101330 + }, + { + "epoch": 3.77, + "learning_rate": 6.230892252761558e-06, + "loss": 1.6635, + "step": 101340 + }, + { + "epoch": 3.77, + "learning_rate": 6.230520325808012e-06, + "loss": 1.6825, + "step": 101350 + }, + { + "epoch": 3.77, + "learning_rate": 6.230148398854465e-06, + "loss": 1.723, + "step": 101360 + }, + { + "epoch": 3.77, + "learning_rate": 6.229776471900919e-06, + "loss": 1.5917, + "step": 101370 + }, + { + "epoch": 3.77, + "learning_rate": 6.229404544947373e-06, + "loss": 1.6142, + "step": 101380 + }, + { + "epoch": 3.77, + "learning_rate": 6.229032617993826e-06, + "loss": 1.69, + "step": 101390 + }, + { + "epoch": 3.77, + "learning_rate": 6.228660691040281e-06, + "loss": 1.5971, + "step": 101400 + }, + { + "epoch": 3.77, + "eval_loss": 1.6442973613739014, + "eval_runtime": 16.8365, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 101400 + }, + { + "epoch": 3.77, + "learning_rate": 6.228288764086734e-06, + "loss": 1.6241, + "step": 101410 + }, + { + "epoch": 3.77, + "learning_rate": 6.2279168371331876e-06, + "loss": 1.6392, + "step": 101420 + }, + { + "epoch": 3.77, + "learning_rate": 6.227544910179642e-06, + "loss": 1.7666, + "step": 101430 + }, + { + "epoch": 3.77, + "learning_rate": 6.227172983226095e-06, + "loss": 1.6364, + "step": 101440 + }, + { + "epoch": 3.77, + "learning_rate": 6.226801056272549e-06, + "loss": 1.7, + "step": 101450 + }, + { + "epoch": 3.77, + "learning_rate": 6.226429129319003e-06, + "loss": 1.6734, + "step": 101460 + }, + { + "epoch": 3.77, + "learning_rate": 6.2260572023654566e-06, + "loss": 1.667, + "step": 101470 + }, + { + "epoch": 3.77, + "learning_rate": 6.22568527541191e-06, + "loss": 1.5576, + "step": 101480 + }, + { + "epoch": 3.77, + "learning_rate": 6.225313348458363e-06, + "loss": 1.7593, + "step": 101490 + }, + { + "epoch": 3.78, + "learning_rate": 6.224941421504816e-06, + "loss": 1.5688, + "step": 101500 + }, + { + "epoch": 3.78, + "eval_loss": 1.6438339948654175, + "eval_runtime": 16.8429, + "eval_samples_per_second": 59.372, + "eval_steps_per_second": 3.74, + "step": 101500 + }, + { + "epoch": 3.78, + "learning_rate": 6.22456949455127e-06, + "loss": 1.7208, + "step": 101510 + }, + { + "epoch": 3.78, + "learning_rate": 6.224197567597724e-06, + "loss": 1.583, + "step": 101520 + }, + { + "epoch": 3.78, + "learning_rate": 6.223825640644177e-06, + "loss": 1.7073, + "step": 101530 + }, + { + "epoch": 3.78, + "learning_rate": 6.223453713690632e-06, + "loss": 1.6406, + "step": 101540 + }, + { + "epoch": 3.78, + "learning_rate": 6.223081786737085e-06, + "loss": 1.6346, + "step": 101550 + }, + { + "epoch": 3.78, + "learning_rate": 6.2227098597835385e-06, + "loss": 1.6392, + "step": 101560 + }, + { + "epoch": 3.78, + "learning_rate": 6.222337932829993e-06, + "loss": 1.7842, + "step": 101570 + }, + { + "epoch": 3.78, + "learning_rate": 6.221966005876446e-06, + "loss": 1.7364, + "step": 101580 + }, + { + "epoch": 3.78, + "learning_rate": 6.2215940789229e-06, + "loss": 1.7129, + "step": 101590 + }, + { + "epoch": 3.78, + "learning_rate": 6.221222151969354e-06, + "loss": 1.7267, + "step": 101600 + }, + { + "epoch": 3.78, + "eval_loss": 1.643408179283142, + "eval_runtime": 16.8437, + "eval_samples_per_second": 59.369, + "eval_steps_per_second": 3.74, + "step": 101600 + }, + { + "epoch": 3.78, + "learning_rate": 6.2208502250158075e-06, + "loss": 1.7429, + "step": 101610 + }, + { + "epoch": 3.78, + "learning_rate": 6.220478298062261e-06, + "loss": 1.697, + "step": 101620 + }, + { + "epoch": 3.78, + "learning_rate": 6.220106371108715e-06, + "loss": 1.5085, + "step": 101630 + }, + { + "epoch": 3.78, + "learning_rate": 6.219734444155169e-06, + "loss": 1.6483, + "step": 101640 + }, + { + "epoch": 3.78, + "learning_rate": 6.219362517201622e-06, + "loss": 1.726, + "step": 101650 + }, + { + "epoch": 3.78, + "learning_rate": 6.2189905902480765e-06, + "loss": 1.7377, + "step": 101660 + }, + { + "epoch": 3.78, + "learning_rate": 6.21861866329453e-06, + "loss": 1.5992, + "step": 101670 + }, + { + "epoch": 3.78, + "learning_rate": 6.218246736340983e-06, + "loss": 1.6783, + "step": 101680 + }, + { + "epoch": 3.78, + "learning_rate": 6.217874809387436e-06, + "loss": 1.5995, + "step": 101690 + }, + { + "epoch": 3.78, + "learning_rate": 6.21750288243389e-06, + "loss": 1.6842, + "step": 101700 + }, + { + "epoch": 3.78, + "eval_loss": 1.64341139793396, + "eval_runtime": 16.8258, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 101700 + }, + { + "epoch": 3.78, + "learning_rate": 6.217130955480344e-06, + "loss": 1.6685, + "step": 101710 + }, + { + "epoch": 3.78, + "learning_rate": 6.216759028526797e-06, + "loss": 1.6909, + "step": 101720 + }, + { + "epoch": 3.78, + "learning_rate": 6.2163871015732516e-06, + "loss": 1.7133, + "step": 101730 + }, + { + "epoch": 3.78, + "learning_rate": 6.216015174619705e-06, + "loss": 1.7403, + "step": 101740 + }, + { + "epoch": 3.78, + "learning_rate": 6.2156432476661585e-06, + "loss": 1.7355, + "step": 101750 + }, + { + "epoch": 3.78, + "learning_rate": 6.215271320712613e-06, + "loss": 1.6167, + "step": 101760 + }, + { + "epoch": 3.79, + "learning_rate": 6.214899393759066e-06, + "loss": 1.7233, + "step": 101770 + }, + { + "epoch": 3.79, + "learning_rate": 6.21452746680552e-06, + "loss": 1.6604, + "step": 101780 + }, + { + "epoch": 3.79, + "learning_rate": 6.214155539851974e-06, + "loss": 1.6, + "step": 101790 + }, + { + "epoch": 3.79, + "learning_rate": 6.2137836128984275e-06, + "loss": 1.5932, + "step": 101800 + }, + { + "epoch": 3.79, + "eval_loss": 1.6436290740966797, + "eval_runtime": 16.8172, + "eval_samples_per_second": 59.463, + "eval_steps_per_second": 3.746, + "step": 101800 + }, + { + "epoch": 3.79, + "learning_rate": 6.213411685944881e-06, + "loss": 1.6371, + "step": 101810 + }, + { + "epoch": 3.79, + "learning_rate": 6.213039758991335e-06, + "loss": 1.7574, + "step": 101820 + }, + { + "epoch": 3.79, + "learning_rate": 6.212667832037789e-06, + "loss": 1.6931, + "step": 101830 + }, + { + "epoch": 3.79, + "learning_rate": 6.212295905084242e-06, + "loss": 1.6978, + "step": 101840 + }, + { + "epoch": 3.79, + "learning_rate": 6.2119239781306965e-06, + "loss": 1.6663, + "step": 101850 + }, + { + "epoch": 3.79, + "learning_rate": 6.211552051177149e-06, + "loss": 1.6781, + "step": 101860 + }, + { + "epoch": 3.79, + "learning_rate": 6.2111801242236025e-06, + "loss": 1.7081, + "step": 101870 + }, + { + "epoch": 3.79, + "learning_rate": 6.210808197270056e-06, + "loss": 1.6979, + "step": 101880 + }, + { + "epoch": 3.79, + "learning_rate": 6.21043627031651e-06, + "loss": 1.7189, + "step": 101890 + }, + { + "epoch": 3.79, + "learning_rate": 6.210064343362964e-06, + "loss": 1.6986, + "step": 101900 + }, + { + "epoch": 3.79, + "eval_loss": 1.6439504623413086, + "eval_runtime": 16.8207, + "eval_samples_per_second": 59.45, + "eval_steps_per_second": 3.745, + "step": 101900 + }, + { + "epoch": 3.79, + "learning_rate": 6.209692416409417e-06, + "loss": 1.6291, + "step": 101910 + }, + { + "epoch": 3.79, + "learning_rate": 6.2093204894558715e-06, + "loss": 1.6883, + "step": 101920 + }, + { + "epoch": 3.79, + "learning_rate": 6.208948562502325e-06, + "loss": 1.7278, + "step": 101930 + }, + { + "epoch": 3.79, + "learning_rate": 6.2085766355487785e-06, + "loss": 1.6437, + "step": 101940 + }, + { + "epoch": 3.79, + "learning_rate": 6.208204708595233e-06, + "loss": 1.7042, + "step": 101950 + }, + { + "epoch": 3.79, + "learning_rate": 6.207832781641686e-06, + "loss": 1.6406, + "step": 101960 + }, + { + "epoch": 3.79, + "learning_rate": 6.20746085468814e-06, + "loss": 1.7182, + "step": 101970 + }, + { + "epoch": 3.79, + "learning_rate": 6.207088927734594e-06, + "loss": 1.8242, + "step": 101980 + }, + { + "epoch": 3.79, + "learning_rate": 6.2067170007810474e-06, + "loss": 1.7804, + "step": 101990 + }, + { + "epoch": 3.79, + "learning_rate": 6.206345073827501e-06, + "loss": 1.8528, + "step": 102000 + }, + { + "epoch": 3.79, + "eval_loss": 1.644042730331421, + "eval_runtime": 16.8343, + "eval_samples_per_second": 59.403, + "eval_steps_per_second": 3.742, + "step": 102000 + }, + { + "epoch": 3.79, + "learning_rate": 6.205973146873955e-06, + "loss": 1.7406, + "step": 102010 + }, + { + "epoch": 3.79, + "learning_rate": 6.205601219920409e-06, + "loss": 1.6628, + "step": 102020 + }, + { + "epoch": 3.79, + "learning_rate": 6.205229292966862e-06, + "loss": 1.7811, + "step": 102030 + }, + { + "epoch": 3.8, + "learning_rate": 6.204857366013316e-06, + "loss": 1.6057, + "step": 102040 + }, + { + "epoch": 3.8, + "learning_rate": 6.204485439059769e-06, + "loss": 1.5977, + "step": 102050 + }, + { + "epoch": 3.8, + "learning_rate": 6.2041135121062225e-06, + "loss": 1.6457, + "step": 102060 + }, + { + "epoch": 3.8, + "learning_rate": 6.203741585152676e-06, + "loss": 1.6819, + "step": 102070 + }, + { + "epoch": 3.8, + "learning_rate": 6.203369658199129e-06, + "loss": 1.5957, + "step": 102080 + }, + { + "epoch": 3.8, + "learning_rate": 6.202997731245584e-06, + "loss": 1.7147, + "step": 102090 + }, + { + "epoch": 3.8, + "learning_rate": 6.202625804292037e-06, + "loss": 1.7175, + "step": 102100 + }, + { + "epoch": 3.8, + "eval_loss": 1.6429659128189087, + "eval_runtime": 16.8181, + "eval_samples_per_second": 59.46, + "eval_steps_per_second": 3.746, + "step": 102100 + }, + { + "epoch": 3.8, + "learning_rate": 6.202253877338491e-06, + "loss": 1.7342, + "step": 102110 + }, + { + "epoch": 3.8, + "learning_rate": 6.201881950384945e-06, + "loss": 1.7923, + "step": 102120 + }, + { + "epoch": 3.8, + "learning_rate": 6.201510023431398e-06, + "loss": 1.7295, + "step": 102130 + }, + { + "epoch": 3.8, + "learning_rate": 6.201138096477852e-06, + "loss": 1.6531, + "step": 102140 + }, + { + "epoch": 3.8, + "learning_rate": 6.200766169524306e-06, + "loss": 1.8028, + "step": 102150 + }, + { + "epoch": 3.8, + "learning_rate": 6.20039424257076e-06, + "loss": 1.5806, + "step": 102160 + }, + { + "epoch": 3.8, + "learning_rate": 6.200022315617213e-06, + "loss": 1.7479, + "step": 102170 + }, + { + "epoch": 3.8, + "learning_rate": 6.199650388663667e-06, + "loss": 1.7018, + "step": 102180 + }, + { + "epoch": 3.8, + "learning_rate": 6.199278461710121e-06, + "loss": 1.7641, + "step": 102190 + }, + { + "epoch": 3.8, + "learning_rate": 6.198906534756574e-06, + "loss": 1.8135, + "step": 102200 + }, + { + "epoch": 3.8, + "eval_loss": 1.6426599025726318, + "eval_runtime": 16.8354, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 102200 + }, + { + "epoch": 3.8, + "learning_rate": 6.198534607803029e-06, + "loss": 1.6574, + "step": 102210 + }, + { + "epoch": 3.8, + "learning_rate": 6.198162680849482e-06, + "loss": 1.7196, + "step": 102220 + }, + { + "epoch": 3.8, + "learning_rate": 6.1977907538959355e-06, + "loss": 1.6566, + "step": 102230 + }, + { + "epoch": 3.8, + "learning_rate": 6.197418826942388e-06, + "loss": 1.6948, + "step": 102240 + }, + { + "epoch": 3.8, + "learning_rate": 6.1970468999888425e-06, + "loss": 1.7456, + "step": 102250 + }, + { + "epoch": 3.8, + "learning_rate": 6.196674973035296e-06, + "loss": 1.8551, + "step": 102260 + }, + { + "epoch": 3.8, + "learning_rate": 6.196303046081749e-06, + "loss": 1.6117, + "step": 102270 + }, + { + "epoch": 3.8, + "learning_rate": 6.195931119128204e-06, + "loss": 1.7952, + "step": 102280 + }, + { + "epoch": 3.8, + "learning_rate": 6.195559192174657e-06, + "loss": 1.6078, + "step": 102290 + }, + { + "epoch": 3.8, + "learning_rate": 6.195187265221111e-06, + "loss": 1.6766, + "step": 102300 + }, + { + "epoch": 3.8, + "eval_loss": 1.642967700958252, + "eval_runtime": 16.8382, + "eval_samples_per_second": 59.389, + "eval_steps_per_second": 3.741, + "step": 102300 + }, + { + "epoch": 3.81, + "learning_rate": 6.194815338267565e-06, + "loss": 1.5688, + "step": 102310 + }, + { + "epoch": 3.81, + "learning_rate": 6.194443411314018e-06, + "loss": 1.7138, + "step": 102320 + }, + { + "epoch": 3.81, + "learning_rate": 6.194071484360472e-06, + "loss": 1.6931, + "step": 102330 + }, + { + "epoch": 3.81, + "learning_rate": 6.193699557406926e-06, + "loss": 1.568, + "step": 102340 + }, + { + "epoch": 3.81, + "learning_rate": 6.19332763045338e-06, + "loss": 1.6607, + "step": 102350 + }, + { + "epoch": 3.81, + "learning_rate": 6.192955703499833e-06, + "loss": 1.5486, + "step": 102360 + }, + { + "epoch": 3.81, + "learning_rate": 6.192583776546287e-06, + "loss": 1.6339, + "step": 102370 + }, + { + "epoch": 3.81, + "learning_rate": 6.192211849592741e-06, + "loss": 1.8239, + "step": 102380 + }, + { + "epoch": 3.81, + "learning_rate": 6.191839922639194e-06, + "loss": 1.7255, + "step": 102390 + }, + { + "epoch": 3.81, + "learning_rate": 6.191467995685649e-06, + "loss": 1.5504, + "step": 102400 + }, + { + "epoch": 3.81, + "eval_loss": 1.6435651779174805, + "eval_runtime": 16.833, + "eval_samples_per_second": 59.407, + "eval_steps_per_second": 3.743, + "step": 102400 + }, + { + "epoch": 3.81, + "learning_rate": 6.191096068732102e-06, + "loss": 1.553, + "step": 102410 + }, + { + "epoch": 3.81, + "learning_rate": 6.1907241417785555e-06, + "loss": 1.5744, + "step": 102420 + }, + { + "epoch": 3.81, + "learning_rate": 6.190352214825008e-06, + "loss": 1.6106, + "step": 102430 + }, + { + "epoch": 3.81, + "learning_rate": 6.189980287871462e-06, + "loss": 1.7286, + "step": 102440 + }, + { + "epoch": 3.81, + "learning_rate": 6.189608360917916e-06, + "loss": 1.6347, + "step": 102450 + }, + { + "epoch": 3.81, + "learning_rate": 6.189236433964369e-06, + "loss": 1.7394, + "step": 102460 + }, + { + "epoch": 3.81, + "learning_rate": 6.188864507010824e-06, + "loss": 1.7679, + "step": 102470 + }, + { + "epoch": 3.81, + "learning_rate": 6.188492580057277e-06, + "loss": 1.7231, + "step": 102480 + }, + { + "epoch": 3.81, + "learning_rate": 6.1881206531037306e-06, + "loss": 1.7008, + "step": 102490 + }, + { + "epoch": 3.81, + "learning_rate": 6.187748726150185e-06, + "loss": 1.6245, + "step": 102500 + }, + { + "epoch": 3.81, + "eval_loss": 1.6436357498168945, + "eval_runtime": 16.8418, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 102500 + }, + { + "epoch": 3.81, + "learning_rate": 6.187376799196638e-06, + "loss": 1.8287, + "step": 102510 + }, + { + "epoch": 3.81, + "learning_rate": 6.187004872243092e-06, + "loss": 1.6589, + "step": 102520 + }, + { + "epoch": 3.81, + "learning_rate": 6.186632945289546e-06, + "loss": 1.6388, + "step": 102530 + }, + { + "epoch": 3.81, + "learning_rate": 6.1862610183359996e-06, + "loss": 1.6437, + "step": 102540 + }, + { + "epoch": 3.81, + "learning_rate": 6.185889091382453e-06, + "loss": 1.664, + "step": 102550 + }, + { + "epoch": 3.81, + "learning_rate": 6.185517164428907e-06, + "loss": 1.6528, + "step": 102560 + }, + { + "epoch": 3.81, + "learning_rate": 6.185145237475361e-06, + "loss": 1.6567, + "step": 102570 + }, + { + "epoch": 3.82, + "learning_rate": 6.184773310521814e-06, + "loss": 1.6956, + "step": 102580 + }, + { + "epoch": 3.82, + "learning_rate": 6.1844013835682685e-06, + "loss": 1.6547, + "step": 102590 + }, + { + "epoch": 3.82, + "learning_rate": 6.184029456614722e-06, + "loss": 1.6168, + "step": 102600 + }, + { + "epoch": 3.82, + "eval_loss": 1.6430468559265137, + "eval_runtime": 16.8245, + "eval_samples_per_second": 59.437, + "eval_steps_per_second": 3.745, + "step": 102600 + }, + { + "epoch": 3.82, + "learning_rate": 6.183657529661175e-06, + "loss": 1.7195, + "step": 102610 + }, + { + "epoch": 3.82, + "learning_rate": 6.183285602707628e-06, + "loss": 1.6222, + "step": 102620 + }, + { + "epoch": 3.82, + "learning_rate": 6.182913675754082e-06, + "loss": 1.5865, + "step": 102630 + }, + { + "epoch": 3.82, + "learning_rate": 6.182541748800536e-06, + "loss": 1.7243, + "step": 102640 + }, + { + "epoch": 3.82, + "learning_rate": 6.182169821846989e-06, + "loss": 1.651, + "step": 102650 + }, + { + "epoch": 3.82, + "learning_rate": 6.181797894893443e-06, + "loss": 1.7313, + "step": 102660 + }, + { + "epoch": 3.82, + "learning_rate": 6.181425967939897e-06, + "loss": 1.6501, + "step": 102670 + }, + { + "epoch": 3.82, + "learning_rate": 6.1810540409863505e-06, + "loss": 1.6454, + "step": 102680 + }, + { + "epoch": 3.82, + "learning_rate": 6.180682114032804e-06, + "loss": 1.9136, + "step": 102690 + }, + { + "epoch": 3.82, + "learning_rate": 6.180310187079258e-06, + "loss": 1.6166, + "step": 102700 + }, + { + "epoch": 3.82, + "eval_loss": 1.6424314975738525, + "eval_runtime": 16.8448, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 102700 + }, + { + "epoch": 3.82, + "learning_rate": 6.179938260125712e-06, + "loss": 1.8535, + "step": 102710 + }, + { + "epoch": 3.82, + "learning_rate": 6.179566333172165e-06, + "loss": 1.8251, + "step": 102720 + }, + { + "epoch": 3.82, + "learning_rate": 6.1791944062186195e-06, + "loss": 1.5906, + "step": 102730 + }, + { + "epoch": 3.82, + "learning_rate": 6.178822479265073e-06, + "loss": 1.6695, + "step": 102740 + }, + { + "epoch": 3.82, + "learning_rate": 6.1784505523115264e-06, + "loss": 1.5729, + "step": 102750 + }, + { + "epoch": 3.82, + "learning_rate": 6.178078625357981e-06, + "loss": 1.7516, + "step": 102760 + }, + { + "epoch": 3.82, + "learning_rate": 6.177706698404434e-06, + "loss": 1.6074, + "step": 102770 + }, + { + "epoch": 3.82, + "learning_rate": 6.177334771450888e-06, + "loss": 1.6162, + "step": 102780 + }, + { + "epoch": 3.82, + "learning_rate": 6.176962844497342e-06, + "loss": 1.7427, + "step": 102790 + }, + { + "epoch": 3.82, + "learning_rate": 6.1765909175437946e-06, + "loss": 1.6879, + "step": 102800 + }, + { + "epoch": 3.82, + "eval_loss": 1.6431798934936523, + "eval_runtime": 16.8244, + "eval_samples_per_second": 59.438, + "eval_steps_per_second": 3.745, + "step": 102800 + }, + { + "epoch": 3.82, + "learning_rate": 6.176218990590248e-06, + "loss": 1.7132, + "step": 102810 + }, + { + "epoch": 3.82, + "learning_rate": 6.1758470636367015e-06, + "loss": 1.6822, + "step": 102820 + }, + { + "epoch": 3.82, + "learning_rate": 6.175475136683156e-06, + "loss": 1.774, + "step": 102830 + }, + { + "epoch": 3.82, + "learning_rate": 6.175103209729609e-06, + "loss": 1.7409, + "step": 102840 + }, + { + "epoch": 3.83, + "learning_rate": 6.174731282776063e-06, + "loss": 1.6374, + "step": 102850 + }, + { + "epoch": 3.83, + "learning_rate": 6.174359355822517e-06, + "loss": 1.8213, + "step": 102860 + }, + { + "epoch": 3.83, + "learning_rate": 6.1739874288689705e-06, + "loss": 1.6352, + "step": 102870 + }, + { + "epoch": 3.83, + "learning_rate": 6.173615501915424e-06, + "loss": 1.6523, + "step": 102880 + }, + { + "epoch": 3.83, + "learning_rate": 6.173243574961878e-06, + "loss": 1.6298, + "step": 102890 + }, + { + "epoch": 3.83, + "learning_rate": 6.172871648008332e-06, + "loss": 1.713, + "step": 102900 + }, + { + "epoch": 3.83, + "eval_loss": 1.6421171426773071, + "eval_runtime": 16.8351, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 102900 + }, + { + "epoch": 3.83, + "learning_rate": 6.172499721054785e-06, + "loss": 1.5812, + "step": 102910 + }, + { + "epoch": 3.83, + "learning_rate": 6.1721277941012395e-06, + "loss": 1.7789, + "step": 102920 + }, + { + "epoch": 3.83, + "learning_rate": 6.171755867147693e-06, + "loss": 1.7709, + "step": 102930 + }, + { + "epoch": 3.83, + "learning_rate": 6.171383940194146e-06, + "loss": 1.8406, + "step": 102940 + }, + { + "epoch": 3.83, + "learning_rate": 6.171012013240601e-06, + "loss": 1.6936, + "step": 102950 + }, + { + "epoch": 3.83, + "learning_rate": 6.170640086287054e-06, + "loss": 1.6827, + "step": 102960 + }, + { + "epoch": 3.83, + "learning_rate": 6.170268159333508e-06, + "loss": 1.5497, + "step": 102970 + }, + { + "epoch": 3.83, + "learning_rate": 6.169896232379962e-06, + "loss": 1.7439, + "step": 102980 + }, + { + "epoch": 3.83, + "learning_rate": 6.1695243054264145e-06, + "loss": 1.6991, + "step": 102990 + }, + { + "epoch": 3.83, + "learning_rate": 6.169152378472868e-06, + "loss": 1.532, + "step": 103000 + }, + { + "epoch": 3.83, + "eval_loss": 1.642380714416504, + "eval_runtime": 16.8353, + "eval_samples_per_second": 59.399, + "eval_steps_per_second": 3.742, + "step": 103000 + }, + { + "epoch": 3.83, + "learning_rate": 6.1687804515193215e-06, + "loss": 1.6008, + "step": 103010 + }, + { + "epoch": 3.83, + "learning_rate": 6.168408524565776e-06, + "loss": 1.641, + "step": 103020 + }, + { + "epoch": 3.83, + "learning_rate": 6.168036597612229e-06, + "loss": 1.7629, + "step": 103030 + }, + { + "epoch": 3.83, + "learning_rate": 6.167664670658683e-06, + "loss": 1.6188, + "step": 103040 + }, + { + "epoch": 3.83, + "learning_rate": 6.167292743705137e-06, + "loss": 1.5798, + "step": 103050 + }, + { + "epoch": 3.83, + "learning_rate": 6.1669208167515904e-06, + "loss": 1.7232, + "step": 103060 + }, + { + "epoch": 3.83, + "learning_rate": 6.166548889798044e-06, + "loss": 1.7866, + "step": 103070 + }, + { + "epoch": 3.83, + "learning_rate": 6.166176962844498e-06, + "loss": 1.7471, + "step": 103080 + }, + { + "epoch": 3.83, + "learning_rate": 6.165805035890952e-06, + "loss": 1.6548, + "step": 103090 + }, + { + "epoch": 3.83, + "learning_rate": 6.165433108937405e-06, + "loss": 1.654, + "step": 103100 + }, + { + "epoch": 3.83, + "eval_loss": 1.642633080482483, + "eval_runtime": 16.8495, + "eval_samples_per_second": 59.349, + "eval_steps_per_second": 3.739, + "step": 103100 + }, + { + "epoch": 3.83, + "learning_rate": 6.1650611819838594e-06, + "loss": 1.7551, + "step": 103110 + }, + { + "epoch": 3.84, + "learning_rate": 6.164689255030313e-06, + "loss": 1.7597, + "step": 103120 + }, + { + "epoch": 3.84, + "learning_rate": 6.164317328076766e-06, + "loss": 1.6822, + "step": 103130 + }, + { + "epoch": 3.84, + "learning_rate": 6.163945401123221e-06, + "loss": 1.5781, + "step": 103140 + }, + { + "epoch": 3.84, + "learning_rate": 6.163573474169674e-06, + "loss": 1.7082, + "step": 103150 + }, + { + "epoch": 3.84, + "learning_rate": 6.1632015472161276e-06, + "loss": 1.6226, + "step": 103160 + }, + { + "epoch": 3.84, + "learning_rate": 6.162829620262582e-06, + "loss": 1.8604, + "step": 103170 + }, + { + "epoch": 3.84, + "learning_rate": 6.1624576933090345e-06, + "loss": 1.6592, + "step": 103180 + }, + { + "epoch": 3.84, + "learning_rate": 6.162085766355488e-06, + "loss": 1.6546, + "step": 103190 + }, + { + "epoch": 3.84, + "learning_rate": 6.161713839401941e-06, + "loss": 1.6303, + "step": 103200 + }, + { + "epoch": 3.84, + "eval_loss": 1.641606330871582, + "eval_runtime": 16.8264, + "eval_samples_per_second": 59.43, + "eval_steps_per_second": 3.744, + "step": 103200 + }, + { + "epoch": 3.84, + "learning_rate": 6.161341912448396e-06, + "loss": 1.7129, + "step": 103210 + }, + { + "epoch": 3.84, + "learning_rate": 6.160969985494849e-06, + "loss": 1.6184, + "step": 103220 + }, + { + "epoch": 3.84, + "learning_rate": 6.160598058541303e-06, + "loss": 1.6682, + "step": 103230 + }, + { + "epoch": 3.84, + "learning_rate": 6.160226131587756e-06, + "loss": 1.7033, + "step": 103240 + }, + { + "epoch": 3.84, + "learning_rate": 6.15985420463421e-06, + "loss": 1.6667, + "step": 103250 + }, + { + "epoch": 3.84, + "learning_rate": 6.159482277680664e-06, + "loss": 1.5916, + "step": 103260 + }, + { + "epoch": 3.84, + "learning_rate": 6.159110350727117e-06, + "loss": 1.6778, + "step": 103270 + }, + { + "epoch": 3.84, + "learning_rate": 6.158738423773572e-06, + "loss": 1.6804, + "step": 103280 + }, + { + "epoch": 3.84, + "learning_rate": 6.158366496820025e-06, + "loss": 1.5741, + "step": 103290 + }, + { + "epoch": 3.84, + "learning_rate": 6.1579945698664785e-06, + "loss": 1.6876, + "step": 103300 + }, + { + "epoch": 3.84, + "eval_loss": 1.6418945789337158, + "eval_runtime": 16.8507, + "eval_samples_per_second": 59.345, + "eval_steps_per_second": 3.739, + "step": 103300 + }, + { + "epoch": 3.84, + "learning_rate": 6.157622642912933e-06, + "loss": 1.7587, + "step": 103310 + }, + { + "epoch": 3.84, + "learning_rate": 6.157250715959386e-06, + "loss": 1.7557, + "step": 103320 + }, + { + "epoch": 3.84, + "learning_rate": 6.15687878900584e-06, + "loss": 1.7598, + "step": 103330 + }, + { + "epoch": 3.84, + "learning_rate": 6.156506862052294e-06, + "loss": 1.6069, + "step": 103340 + }, + { + "epoch": 3.84, + "learning_rate": 6.1561349350987475e-06, + "loss": 1.7141, + "step": 103350 + }, + { + "epoch": 3.84, + "learning_rate": 6.155763008145201e-06, + "loss": 1.5661, + "step": 103360 + }, + { + "epoch": 3.84, + "learning_rate": 6.155391081191654e-06, + "loss": 1.681, + "step": 103370 + }, + { + "epoch": 3.84, + "learning_rate": 6.155019154238108e-06, + "loss": 1.6672, + "step": 103380 + }, + { + "epoch": 3.85, + "learning_rate": 6.154647227284561e-06, + "loss": 1.5519, + "step": 103390 + }, + { + "epoch": 3.85, + "learning_rate": 6.154275300331015e-06, + "loss": 1.8273, + "step": 103400 + }, + { + "epoch": 3.85, + "eval_loss": 1.6419271230697632, + "eval_runtime": 16.8408, + "eval_samples_per_second": 59.38, + "eval_steps_per_second": 3.741, + "step": 103400 + }, + { + "epoch": 3.85, + "learning_rate": 6.153903373377469e-06, + "loss": 1.7014, + "step": 103410 + }, + { + "epoch": 3.85, + "learning_rate": 6.153531446423923e-06, + "loss": 1.7889, + "step": 103420 + }, + { + "epoch": 3.85, + "learning_rate": 6.153159519470376e-06, + "loss": 1.743, + "step": 103430 + }, + { + "epoch": 3.85, + "learning_rate": 6.15278759251683e-06, + "loss": 1.7542, + "step": 103440 + }, + { + "epoch": 3.85, + "learning_rate": 6.152415665563284e-06, + "loss": 1.7067, + "step": 103450 + }, + { + "epoch": 3.85, + "learning_rate": 6.152043738609737e-06, + "loss": 1.6028, + "step": 103460 + }, + { + "epoch": 3.85, + "learning_rate": 6.151671811656192e-06, + "loss": 1.6312, + "step": 103470 + }, + { + "epoch": 3.85, + "learning_rate": 6.151299884702645e-06, + "loss": 1.8344, + "step": 103480 + }, + { + "epoch": 3.85, + "learning_rate": 6.1509279577490985e-06, + "loss": 1.5826, + "step": 103490 + }, + { + "epoch": 3.85, + "learning_rate": 6.150556030795553e-06, + "loss": 1.6873, + "step": 103500 + }, + { + "epoch": 3.85, + "eval_loss": 1.6415752172470093, + "eval_runtime": 16.8317, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 103500 + }, + { + "epoch": 3.85, + "learning_rate": 6.150184103842006e-06, + "loss": 1.6484, + "step": 103510 + }, + { + "epoch": 3.85, + "learning_rate": 6.14981217688846e-06, + "loss": 1.5783, + "step": 103520 + }, + { + "epoch": 3.85, + "learning_rate": 6.149440249934914e-06, + "loss": 1.8912, + "step": 103530 + }, + { + "epoch": 3.85, + "learning_rate": 6.1490683229813675e-06, + "loss": 1.6328, + "step": 103540 + }, + { + "epoch": 3.85, + "learning_rate": 6.14869639602782e-06, + "loss": 1.76, + "step": 103550 + }, + { + "epoch": 3.85, + "learning_rate": 6.1483244690742736e-06, + "loss": 1.7876, + "step": 103560 + }, + { + "epoch": 3.85, + "learning_rate": 6.147952542120728e-06, + "loss": 1.553, + "step": 103570 + }, + { + "epoch": 3.85, + "learning_rate": 6.147580615167181e-06, + "loss": 1.5881, + "step": 103580 + }, + { + "epoch": 3.85, + "learning_rate": 6.147208688213635e-06, + "loss": 1.6607, + "step": 103590 + }, + { + "epoch": 3.85, + "learning_rate": 6.146836761260089e-06, + "loss": 1.8097, + "step": 103600 + }, + { + "epoch": 3.85, + "eval_loss": 1.6417863368988037, + "eval_runtime": 16.8534, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 103600 + }, + { + "epoch": 3.85, + "learning_rate": 6.1464648343065426e-06, + "loss": 1.7666, + "step": 103610 + }, + { + "epoch": 3.85, + "learning_rate": 6.146092907352996e-06, + "loss": 1.6494, + "step": 103620 + }, + { + "epoch": 3.85, + "learning_rate": 6.14572098039945e-06, + "loss": 1.6505, + "step": 103630 + }, + { + "epoch": 3.85, + "learning_rate": 6.145349053445904e-06, + "loss": 1.7085, + "step": 103640 + }, + { + "epoch": 3.86, + "learning_rate": 6.144977126492357e-06, + "loss": 1.712, + "step": 103650 + }, + { + "epoch": 3.86, + "learning_rate": 6.1446051995388115e-06, + "loss": 1.6393, + "step": 103660 + }, + { + "epoch": 3.86, + "learning_rate": 6.144233272585265e-06, + "loss": 1.704, + "step": 103670 + }, + { + "epoch": 3.86, + "learning_rate": 6.1438613456317185e-06, + "loss": 1.7084, + "step": 103680 + }, + { + "epoch": 3.86, + "learning_rate": 6.143489418678173e-06, + "loss": 1.6483, + "step": 103690 + }, + { + "epoch": 3.86, + "learning_rate": 6.143117491724626e-06, + "loss": 1.7911, + "step": 103700 + }, + { + "epoch": 3.86, + "eval_loss": 1.6414134502410889, + "eval_runtime": 16.8194, + "eval_samples_per_second": 59.455, + "eval_steps_per_second": 3.746, + "step": 103700 + }, + { + "epoch": 3.86, + "learning_rate": 6.14274556477108e-06, + "loss": 1.7094, + "step": 103710 + }, + { + "epoch": 3.86, + "learning_rate": 6.142373637817534e-06, + "loss": 1.7748, + "step": 103720 + }, + { + "epoch": 3.86, + "learning_rate": 6.1420017108639875e-06, + "loss": 1.732, + "step": 103730 + }, + { + "epoch": 3.86, + "learning_rate": 6.14162978391044e-06, + "loss": 1.7855, + "step": 103740 + }, + { + "epoch": 3.86, + "learning_rate": 6.1412578569568935e-06, + "loss": 1.5379, + "step": 103750 + }, + { + "epoch": 3.86, + "learning_rate": 6.140885930003348e-06, + "loss": 1.6996, + "step": 103760 + }, + { + "epoch": 3.86, + "learning_rate": 6.140514003049801e-06, + "loss": 1.7098, + "step": 103770 + }, + { + "epoch": 3.86, + "learning_rate": 6.140142076096255e-06, + "loss": 1.7447, + "step": 103780 + }, + { + "epoch": 3.86, + "learning_rate": 6.139770149142709e-06, + "loss": 1.7883, + "step": 103790 + }, + { + "epoch": 3.86, + "learning_rate": 6.1393982221891625e-06, + "loss": 1.7695, + "step": 103800 + }, + { + "epoch": 3.86, + "eval_loss": 1.6416032314300537, + "eval_runtime": 16.8263, + "eval_samples_per_second": 59.431, + "eval_steps_per_second": 3.744, + "step": 103800 + }, + { + "epoch": 3.86, + "learning_rate": 6.139026295235616e-06, + "loss": 1.6396, + "step": 103810 + }, + { + "epoch": 3.86, + "learning_rate": 6.1386543682820694e-06, + "loss": 1.774, + "step": 103820 + }, + { + "epoch": 3.86, + "learning_rate": 6.138282441328524e-06, + "loss": 1.6521, + "step": 103830 + }, + { + "epoch": 3.86, + "learning_rate": 6.137910514374977e-06, + "loss": 1.6234, + "step": 103840 + }, + { + "epoch": 3.86, + "learning_rate": 6.137538587421431e-06, + "loss": 1.5658, + "step": 103850 + }, + { + "epoch": 3.86, + "learning_rate": 6.137166660467885e-06, + "loss": 1.6485, + "step": 103860 + }, + { + "epoch": 3.86, + "learning_rate": 6.136794733514338e-06, + "loss": 1.6388, + "step": 103870 + }, + { + "epoch": 3.86, + "learning_rate": 6.136422806560792e-06, + "loss": 1.6735, + "step": 103880 + }, + { + "epoch": 3.86, + "learning_rate": 6.136050879607246e-06, + "loss": 1.6241, + "step": 103890 + }, + { + "epoch": 3.86, + "learning_rate": 6.1356789526537e-06, + "loss": 1.7704, + "step": 103900 + }, + { + "epoch": 3.86, + "eval_loss": 1.6417880058288574, + "eval_runtime": 16.8423, + "eval_samples_per_second": 59.374, + "eval_steps_per_second": 3.741, + "step": 103900 + }, + { + "epoch": 3.86, + "learning_rate": 6.135307025700153e-06, + "loss": 1.6959, + "step": 103910 + }, + { + "epoch": 3.87, + "learning_rate": 6.134935098746607e-06, + "loss": 1.7106, + "step": 103920 + }, + { + "epoch": 3.87, + "learning_rate": 6.13456317179306e-06, + "loss": 1.6765, + "step": 103930 + }, + { + "epoch": 3.87, + "learning_rate": 6.1341912448395135e-06, + "loss": 1.6433, + "step": 103940 + }, + { + "epoch": 3.87, + "learning_rate": 6.133819317885967e-06, + "loss": 1.7469, + "step": 103950 + }, + { + "epoch": 3.87, + "learning_rate": 6.133447390932421e-06, + "loss": 1.6138, + "step": 103960 + }, + { + "epoch": 3.87, + "learning_rate": 6.133075463978875e-06, + "loss": 1.5678, + "step": 103970 + }, + { + "epoch": 3.87, + "learning_rate": 6.132703537025328e-06, + "loss": 1.7166, + "step": 103980 + }, + { + "epoch": 3.87, + "learning_rate": 6.1323316100717825e-06, + "loss": 1.6814, + "step": 103990 + }, + { + "epoch": 3.87, + "learning_rate": 6.131959683118236e-06, + "loss": 1.7221, + "step": 104000 + }, + { + "epoch": 3.87, + "eval_loss": 1.6406201124191284, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 104000 + }, + { + "epoch": 3.87, + "learning_rate": 6.131587756164689e-06, + "loss": 1.7054, + "step": 104010 + }, + { + "epoch": 3.87, + "learning_rate": 6.131215829211144e-06, + "loss": 1.702, + "step": 104020 + }, + { + "epoch": 3.87, + "learning_rate": 6.130843902257597e-06, + "loss": 1.8589, + "step": 104030 + }, + { + "epoch": 3.87, + "learning_rate": 6.130471975304051e-06, + "loss": 1.6879, + "step": 104040 + }, + { + "epoch": 3.87, + "learning_rate": 6.130100048350505e-06, + "loss": 1.7021, + "step": 104050 + }, + { + "epoch": 3.87, + "learning_rate": 6.129728121396958e-06, + "loss": 1.9403, + "step": 104060 + }, + { + "epoch": 3.87, + "learning_rate": 6.129356194443412e-06, + "loss": 1.6862, + "step": 104070 + }, + { + "epoch": 3.87, + "learning_rate": 6.128984267489866e-06, + "loss": 1.6019, + "step": 104080 + }, + { + "epoch": 3.87, + "learning_rate": 6.12861234053632e-06, + "loss": 1.6722, + "step": 104090 + }, + { + "epoch": 3.87, + "learning_rate": 6.128240413582773e-06, + "loss": 1.7065, + "step": 104100 + }, + { + "epoch": 3.87, + "eval_loss": 1.640802264213562, + "eval_runtime": 16.8393, + "eval_samples_per_second": 59.385, + "eval_steps_per_second": 3.741, + "step": 104100 + }, + { + "epoch": 3.87, + "learning_rate": 6.127868486629227e-06, + "loss": 1.6678, + "step": 104110 + }, + { + "epoch": 3.87, + "learning_rate": 6.12749655967568e-06, + "loss": 1.7333, + "step": 104120 + }, + { + "epoch": 3.87, + "learning_rate": 6.1271246327221334e-06, + "loss": 1.6879, + "step": 104130 + }, + { + "epoch": 3.87, + "learning_rate": 6.126752705768587e-06, + "loss": 1.7558, + "step": 104140 + }, + { + "epoch": 3.87, + "learning_rate": 6.126380778815041e-06, + "loss": 1.6513, + "step": 104150 + }, + { + "epoch": 3.87, + "learning_rate": 6.126008851861495e-06, + "loss": 1.6662, + "step": 104160 + }, + { + "epoch": 3.87, + "learning_rate": 6.125636924907948e-06, + "loss": 1.6149, + "step": 104170 + }, + { + "epoch": 3.87, + "learning_rate": 6.1252649979544024e-06, + "loss": 1.5705, + "step": 104180 + }, + { + "epoch": 3.88, + "learning_rate": 6.124893071000856e-06, + "loss": 1.7591, + "step": 104190 + }, + { + "epoch": 3.88, + "learning_rate": 6.124521144047309e-06, + "loss": 1.7298, + "step": 104200 + }, + { + "epoch": 3.88, + "eval_loss": 1.6423680782318115, + "eval_runtime": 16.8456, + "eval_samples_per_second": 59.363, + "eval_steps_per_second": 3.74, + "step": 104200 + }, + { + "epoch": 3.88, + "learning_rate": 6.124149217093764e-06, + "loss": 1.8633, + "step": 104210 + }, + { + "epoch": 3.88, + "learning_rate": 6.123777290140217e-06, + "loss": 1.6804, + "step": 104220 + }, + { + "epoch": 3.88, + "learning_rate": 6.1234053631866706e-06, + "loss": 1.4958, + "step": 104230 + }, + { + "epoch": 3.88, + "learning_rate": 6.123033436233125e-06, + "loss": 1.6108, + "step": 104240 + }, + { + "epoch": 3.88, + "learning_rate": 6.122661509279578e-06, + "loss": 1.6553, + "step": 104250 + }, + { + "epoch": 3.88, + "learning_rate": 6.122289582326032e-06, + "loss": 1.6646, + "step": 104260 + }, + { + "epoch": 3.88, + "learning_rate": 6.121917655372486e-06, + "loss": 1.6561, + "step": 104270 + }, + { + "epoch": 3.88, + "learning_rate": 6.1215457284189396e-06, + "loss": 1.8122, + "step": 104280 + }, + { + "epoch": 3.88, + "learning_rate": 6.121173801465393e-06, + "loss": 1.6701, + "step": 104290 + }, + { + "epoch": 3.88, + "learning_rate": 6.120801874511846e-06, + "loss": 1.9576, + "step": 104300 + }, + { + "epoch": 3.88, + "eval_loss": 1.6413301229476929, + "eval_runtime": 16.8417, + "eval_samples_per_second": 59.376, + "eval_steps_per_second": 3.741, + "step": 104300 + }, + { + "epoch": 3.88, + "learning_rate": 6.1204299475583e-06, + "loss": 1.5796, + "step": 104310 + }, + { + "epoch": 3.88, + "learning_rate": 6.120058020604753e-06, + "loss": 1.6942, + "step": 104320 + }, + { + "epoch": 3.88, + "learning_rate": 6.119686093651207e-06, + "loss": 1.733, + "step": 104330 + }, + { + "epoch": 3.88, + "learning_rate": 6.119314166697661e-06, + "loss": 1.7669, + "step": 104340 + }, + { + "epoch": 3.88, + "learning_rate": 6.118942239744115e-06, + "loss": 1.8272, + "step": 104350 + }, + { + "epoch": 3.88, + "learning_rate": 6.118570312790568e-06, + "loss": 1.792, + "step": 104360 + }, + { + "epoch": 3.88, + "learning_rate": 6.118198385837022e-06, + "loss": 1.7825, + "step": 104370 + }, + { + "epoch": 3.88, + "learning_rate": 6.117826458883476e-06, + "loss": 1.5505, + "step": 104380 + }, + { + "epoch": 3.88, + "learning_rate": 6.117454531929929e-06, + "loss": 1.6627, + "step": 104390 + }, + { + "epoch": 3.88, + "learning_rate": 6.117082604976383e-06, + "loss": 1.7338, + "step": 104400 + }, + { + "epoch": 3.88, + "eval_loss": 1.642022728919983, + "eval_runtime": 16.8517, + "eval_samples_per_second": 59.341, + "eval_steps_per_second": 3.739, + "step": 104400 + }, + { + "epoch": 3.88, + "learning_rate": 6.116710678022837e-06, + "loss": 1.8615, + "step": 104410 + }, + { + "epoch": 3.88, + "learning_rate": 6.1163387510692905e-06, + "loss": 1.8031, + "step": 104420 + }, + { + "epoch": 3.88, + "learning_rate": 6.115966824115744e-06, + "loss": 1.6052, + "step": 104430 + }, + { + "epoch": 3.88, + "learning_rate": 6.115594897162198e-06, + "loss": 1.8104, + "step": 104440 + }, + { + "epoch": 3.88, + "learning_rate": 6.115222970208652e-06, + "loss": 1.6578, + "step": 104450 + }, + { + "epoch": 3.89, + "learning_rate": 6.114851043255105e-06, + "loss": 1.5466, + "step": 104460 + }, + { + "epoch": 3.89, + "learning_rate": 6.1144791163015595e-06, + "loss": 1.6356, + "step": 104470 + }, + { + "epoch": 3.89, + "learning_rate": 6.114107189348013e-06, + "loss": 1.6554, + "step": 104480 + }, + { + "epoch": 3.89, + "learning_rate": 6.113735262394466e-06, + "loss": 1.6546, + "step": 104490 + }, + { + "epoch": 3.89, + "learning_rate": 6.113363335440919e-06, + "loss": 1.7333, + "step": 104500 + }, + { + "epoch": 3.89, + "eval_loss": 1.6419963836669922, + "eval_runtime": 16.8295, + "eval_samples_per_second": 59.419, + "eval_steps_per_second": 3.743, + "step": 104500 + }, + { + "epoch": 3.89, + "learning_rate": 6.112991408487373e-06, + "loss": 1.7486, + "step": 104510 + }, + { + "epoch": 3.89, + "learning_rate": 6.112619481533827e-06, + "loss": 1.7295, + "step": 104520 + }, + { + "epoch": 3.89, + "learning_rate": 6.11224755458028e-06, + "loss": 1.5248, + "step": 104530 + }, + { + "epoch": 3.89, + "learning_rate": 6.111875627626735e-06, + "loss": 1.6841, + "step": 104540 + }, + { + "epoch": 3.89, + "learning_rate": 6.111503700673188e-06, + "loss": 1.6195, + "step": 104550 + }, + { + "epoch": 3.89, + "learning_rate": 6.1111317737196415e-06, + "loss": 1.694, + "step": 104560 + }, + { + "epoch": 3.89, + "learning_rate": 6.110759846766096e-06, + "loss": 1.6827, + "step": 104570 + }, + { + "epoch": 3.89, + "learning_rate": 6.110387919812549e-06, + "loss": 1.6257, + "step": 104580 + }, + { + "epoch": 3.89, + "learning_rate": 6.110015992859003e-06, + "loss": 1.753, + "step": 104590 + }, + { + "epoch": 3.89, + "learning_rate": 6.109644065905457e-06, + "loss": 1.653, + "step": 104600 + }, + { + "epoch": 3.89, + "eval_loss": 1.6417138576507568, + "eval_runtime": 16.8257, + "eval_samples_per_second": 59.433, + "eval_steps_per_second": 3.744, + "step": 104600 + }, + { + "epoch": 3.89, + "learning_rate": 6.1092721389519105e-06, + "loss": 1.736, + "step": 104610 + }, + { + "epoch": 3.89, + "learning_rate": 6.108900211998364e-06, + "loss": 1.5488, + "step": 104620 + }, + { + "epoch": 3.89, + "learning_rate": 6.108528285044818e-06, + "loss": 1.7262, + "step": 104630 + }, + { + "epoch": 3.89, + "learning_rate": 6.108156358091272e-06, + "loss": 1.6058, + "step": 104640 + }, + { + "epoch": 3.89, + "learning_rate": 6.107784431137725e-06, + "loss": 1.802, + "step": 104650 + }, + { + "epoch": 3.89, + "learning_rate": 6.1074125041841795e-06, + "loss": 1.7772, + "step": 104660 + }, + { + "epoch": 3.89, + "learning_rate": 6.107040577230633e-06, + "loss": 1.873, + "step": 104670 + }, + { + "epoch": 3.89, + "learning_rate": 6.1066686502770856e-06, + "loss": 1.6767, + "step": 104680 + }, + { + "epoch": 3.89, + "learning_rate": 6.106296723323539e-06, + "loss": 1.8797, + "step": 104690 + }, + { + "epoch": 3.89, + "learning_rate": 6.105924796369993e-06, + "loss": 1.6808, + "step": 104700 + }, + { + "epoch": 3.89, + "eval_loss": 1.6413166522979736, + "eval_runtime": 16.8207, + "eval_samples_per_second": 59.451, + "eval_steps_per_second": 3.745, + "step": 104700 + }, + { + "epoch": 3.89, + "learning_rate": 6.105552869416447e-06, + "loss": 1.5588, + "step": 104710 + }, + { + "epoch": 3.89, + "learning_rate": 6.1051809424629e-06, + "loss": 1.8072, + "step": 104720 + }, + { + "epoch": 3.9, + "learning_rate": 6.1048090155093545e-06, + "loss": 1.5959, + "step": 104730 + }, + { + "epoch": 3.9, + "learning_rate": 6.104437088555808e-06, + "loss": 1.6704, + "step": 104740 + }, + { + "epoch": 3.9, + "learning_rate": 6.1040651616022615e-06, + "loss": 1.6303, + "step": 104750 + }, + { + "epoch": 3.9, + "learning_rate": 6.103693234648716e-06, + "loss": 1.6709, + "step": 104760 + }, + { + "epoch": 3.9, + "learning_rate": 6.103321307695169e-06, + "loss": 1.7609, + "step": 104770 + }, + { + "epoch": 3.9, + "learning_rate": 6.102949380741623e-06, + "loss": 1.7266, + "step": 104780 + }, + { + "epoch": 3.9, + "learning_rate": 6.102577453788077e-06, + "loss": 1.6878, + "step": 104790 + }, + { + "epoch": 3.9, + "learning_rate": 6.1022055268345305e-06, + "loss": 1.7131, + "step": 104800 + }, + { + "epoch": 3.9, + "eval_loss": 1.6416419744491577, + "eval_runtime": 16.8273, + "eval_samples_per_second": 59.427, + "eval_steps_per_second": 3.744, + "step": 104800 + }, + { + "epoch": 3.9, + "learning_rate": 6.101833599880984e-06, + "loss": 1.6196, + "step": 104810 + }, + { + "epoch": 3.9, + "learning_rate": 6.101461672927438e-06, + "loss": 1.8264, + "step": 104820 + }, + { + "epoch": 3.9, + "learning_rate": 6.101089745973892e-06, + "loss": 1.6617, + "step": 104830 + }, + { + "epoch": 3.9, + "learning_rate": 6.100717819020345e-06, + "loss": 1.6784, + "step": 104840 + }, + { + "epoch": 3.9, + "learning_rate": 6.1003458920667994e-06, + "loss": 1.6838, + "step": 104850 + }, + { + "epoch": 3.9, + "learning_rate": 6.099973965113253e-06, + "loss": 1.6514, + "step": 104860 + }, + { + "epoch": 3.9, + "learning_rate": 6.0996020381597055e-06, + "loss": 1.6295, + "step": 104870 + }, + { + "epoch": 3.9, + "learning_rate": 6.099230111206159e-06, + "loss": 1.6893, + "step": 104880 + }, + { + "epoch": 3.9, + "learning_rate": 6.098858184252613e-06, + "loss": 1.7127, + "step": 104890 + }, + { + "epoch": 3.9, + "learning_rate": 6.098486257299067e-06, + "loss": 1.6948, + "step": 104900 + }, + { + "epoch": 3.9, + "eval_loss": 1.6413425207138062, + "eval_runtime": 16.85, + "eval_samples_per_second": 59.347, + "eval_steps_per_second": 3.739, + "step": 104900 + }, + { + "epoch": 3.9, + "learning_rate": 6.09811433034552e-06, + "loss": 1.6633, + "step": 104910 + }, + { + "epoch": 3.9, + "learning_rate": 6.0977424033919745e-06, + "loss": 1.6507, + "step": 104920 + }, + { + "epoch": 3.9, + "learning_rate": 6.097370476438428e-06, + "loss": 1.6455, + "step": 104930 + }, + { + "epoch": 3.9, + "learning_rate": 6.096998549484881e-06, + "loss": 1.7022, + "step": 104940 + }, + { + "epoch": 3.9, + "learning_rate": 6.096626622531335e-06, + "loss": 1.698, + "step": 104950 + }, + { + "epoch": 3.9, + "learning_rate": 6.096254695577789e-06, + "loss": 1.7756, + "step": 104960 + }, + { + "epoch": 3.9, + "learning_rate": 6.095882768624243e-06, + "loss": 1.6995, + "step": 104970 + }, + { + "epoch": 3.9, + "learning_rate": 6.095510841670696e-06, + "loss": 1.725, + "step": 104980 + }, + { + "epoch": 3.9, + "learning_rate": 6.09513891471715e-06, + "loss": 1.7803, + "step": 104990 + }, + { + "epoch": 3.91, + "learning_rate": 6.094766987763604e-06, + "loss": 1.6791, + "step": 105000 + }, + { + "epoch": 3.91, + "eval_loss": 1.6403273344039917, + "eval_runtime": 16.8609, + "eval_samples_per_second": 59.309, + "eval_steps_per_second": 3.736, + "step": 105000 + }, + { + "epoch": 3.91, + "learning_rate": 6.094395060810057e-06, + "loss": 1.6565, + "step": 105010 + }, + { + "epoch": 3.91, + "learning_rate": 6.094023133856512e-06, + "loss": 1.7404, + "step": 105020 + }, + { + "epoch": 3.91, + "learning_rate": 6.093651206902965e-06, + "loss": 1.7157, + "step": 105030 + }, + { + "epoch": 3.91, + "learning_rate": 6.0932792799494186e-06, + "loss": 1.6056, + "step": 105040 + }, + { + "epoch": 3.91, + "learning_rate": 6.092907352995873e-06, + "loss": 1.7562, + "step": 105050 + }, + { + "epoch": 3.91, + "learning_rate": 6.0925354260423255e-06, + "loss": 1.7188, + "step": 105060 + }, + { + "epoch": 3.91, + "learning_rate": 6.092163499088779e-06, + "loss": 1.6236, + "step": 105070 + }, + { + "epoch": 3.91, + "learning_rate": 6.091791572135232e-06, + "loss": 1.6091, + "step": 105080 + }, + { + "epoch": 3.91, + "learning_rate": 6.091419645181687e-06, + "loss": 1.6251, + "step": 105090 + }, + { + "epoch": 3.91, + "learning_rate": 6.09104771822814e-06, + "loss": 1.6404, + "step": 105100 + }, + { + "epoch": 3.91, + "eval_loss": 1.6405863761901855, + "eval_runtime": 16.8401, + "eval_samples_per_second": 59.382, + "eval_steps_per_second": 3.741, + "step": 105100 + }, + { + "epoch": 3.91, + "learning_rate": 6.090675791274594e-06, + "loss": 1.7266, + "step": 105110 + }, + { + "epoch": 3.91, + "learning_rate": 6.090303864321048e-06, + "loss": 1.6736, + "step": 105120 + }, + { + "epoch": 3.91, + "learning_rate": 6.089931937367501e-06, + "loss": 1.5964, + "step": 105130 + }, + { + "epoch": 3.91, + "learning_rate": 6.089560010413955e-06, + "loss": 1.7235, + "step": 105140 + }, + { + "epoch": 3.91, + "learning_rate": 6.089188083460409e-06, + "loss": 1.7789, + "step": 105150 + }, + { + "epoch": 3.91, + "learning_rate": 6.088816156506863e-06, + "loss": 1.6205, + "step": 105160 + }, + { + "epoch": 3.91, + "learning_rate": 6.088444229553316e-06, + "loss": 1.7222, + "step": 105170 + }, + { + "epoch": 3.91, + "learning_rate": 6.08807230259977e-06, + "loss": 1.6568, + "step": 105180 + }, + { + "epoch": 3.91, + "learning_rate": 6.087700375646224e-06, + "loss": 1.7004, + "step": 105190 + }, + { + "epoch": 3.91, + "learning_rate": 6.087328448692677e-06, + "loss": 1.8234, + "step": 105200 + }, + { + "epoch": 3.91, + "eval_loss": 1.6399279832839966, + "eval_runtime": 16.8561, + "eval_samples_per_second": 59.326, + "eval_steps_per_second": 3.738, + "step": 105200 + }, + { + "epoch": 3.91, + "learning_rate": 6.086956521739132e-06, + "loss": 1.5493, + "step": 105210 + }, + { + "epoch": 3.91, + "learning_rate": 6.086584594785585e-06, + "loss": 1.8498, + "step": 105220 + }, + { + "epoch": 3.91, + "learning_rate": 6.0862126678320385e-06, + "loss": 1.5376, + "step": 105230 + }, + { + "epoch": 3.91, + "learning_rate": 6.085840740878491e-06, + "loss": 1.5576, + "step": 105240 + }, + { + "epoch": 3.91, + "learning_rate": 6.0854688139249454e-06, + "loss": 1.7524, + "step": 105250 + }, + { + "epoch": 3.91, + "learning_rate": 6.085096886971399e-06, + "loss": 1.7054, + "step": 105260 + }, + { + "epoch": 3.92, + "learning_rate": 6.084724960017852e-06, + "loss": 1.6225, + "step": 105270 + }, + { + "epoch": 3.92, + "learning_rate": 6.084353033064307e-06, + "loss": 1.7406, + "step": 105280 + }, + { + "epoch": 3.92, + "learning_rate": 6.08398110611076e-06, + "loss": 1.711, + "step": 105290 + }, + { + "epoch": 3.92, + "learning_rate": 6.0836091791572136e-06, + "loss": 1.7873, + "step": 105300 + }, + { + "epoch": 3.92, + "eval_loss": 1.6408263444900513, + "eval_runtime": 16.8536, + "eval_samples_per_second": 59.335, + "eval_steps_per_second": 3.738, + "step": 105300 + }, + { + "epoch": 3.92, + "learning_rate": 6.083237252203668e-06, + "loss": 1.8541, + "step": 105310 + }, + { + "epoch": 3.92, + "learning_rate": 6.082865325250121e-06, + "loss": 1.6484, + "step": 105320 + }, + { + "epoch": 3.92, + "learning_rate": 6.082493398296575e-06, + "loss": 1.7141, + "step": 105330 + }, + { + "epoch": 3.92, + "learning_rate": 6.082121471343029e-06, + "loss": 1.6248, + "step": 105340 + }, + { + "epoch": 3.92, + "learning_rate": 6.0817495443894826e-06, + "loss": 1.7076, + "step": 105350 + }, + { + "epoch": 3.92, + "learning_rate": 6.081377617435936e-06, + "loss": 1.6989, + "step": 105360 + }, + { + "epoch": 3.92, + "learning_rate": 6.08100569048239e-06, + "loss": 1.9234, + "step": 105370 + }, + { + "epoch": 3.92, + "learning_rate": 6.080633763528844e-06, + "loss": 1.7466, + "step": 105380 + }, + { + "epoch": 3.92, + "learning_rate": 6.080261836575297e-06, + "loss": 1.7875, + "step": 105390 + }, + { + "epoch": 3.92, + "learning_rate": 6.0798899096217516e-06, + "loss": 1.5861, + "step": 105400 + }, + { + "epoch": 3.92, + "eval_loss": 1.6405261754989624, + "eval_runtime": 16.845, + "eval_samples_per_second": 59.365, + "eval_steps_per_second": 3.74, + "step": 105400 + }, + { + "epoch": 3.92, + "learning_rate": 6.079517982668205e-06, + "loss": 1.6781, + "step": 105410 + }, + { + "epoch": 3.92, + "learning_rate": 6.0791460557146585e-06, + "loss": 1.6814, + "step": 105420 + }, + { + "epoch": 3.92, + "learning_rate": 6.078774128761111e-06, + "loss": 1.7056, + "step": 105430 + }, + { + "epoch": 3.92, + "learning_rate": 6.078402201807565e-06, + "loss": 1.6887, + "step": 105440 + }, + { + "epoch": 3.92, + "learning_rate": 6.078030274854019e-06, + "loss": 1.6326, + "step": 105450 + }, + { + "epoch": 3.92, + "learning_rate": 6.077658347900472e-06, + "loss": 1.6533, + "step": 105460 + }, + { + "epoch": 3.92, + "learning_rate": 6.077286420946927e-06, + "loss": 1.7365, + "step": 105470 + }, + { + "epoch": 3.92, + "learning_rate": 6.07691449399338e-06, + "loss": 1.6233, + "step": 105480 + }, + { + "epoch": 3.92, + "learning_rate": 6.0765425670398335e-06, + "loss": 1.6533, + "step": 105490 + }, + { + "epoch": 3.92, + "learning_rate": 6.076170640086288e-06, + "loss": 1.7089, + "step": 105500 + }, + { + "epoch": 3.92, + "eval_loss": 1.6398106813430786, + "eval_runtime": 16.8373, + "eval_samples_per_second": 59.392, + "eval_steps_per_second": 3.742, + "step": 105500 + }, + { + "epoch": 3.92, + "learning_rate": 6.075798713132741e-06, + "loss": 1.5949, + "step": 105510 + }, + { + "epoch": 3.92, + "learning_rate": 6.075426786179195e-06, + "loss": 1.6719, + "step": 105520 + }, + { + "epoch": 3.92, + "learning_rate": 6.075054859225648e-06, + "loss": 1.7746, + "step": 105530 + }, + { + "epoch": 3.93, + "learning_rate": 6.0746829322721025e-06, + "loss": 1.7556, + "step": 105540 + }, + { + "epoch": 3.93, + "learning_rate": 6.074311005318556e-06, + "loss": 1.6141, + "step": 105550 + }, + { + "epoch": 3.93, + "learning_rate": 6.0739390783650094e-06, + "loss": 1.5886, + "step": 105560 + }, + { + "epoch": 3.93, + "learning_rate": 6.073567151411464e-06, + "loss": 1.6293, + "step": 105570 + }, + { + "epoch": 3.93, + "learning_rate": 6.073195224457917e-06, + "loss": 1.7195, + "step": 105580 + }, + { + "epoch": 3.93, + "learning_rate": 6.072823297504371e-06, + "loss": 1.6896, + "step": 105590 + }, + { + "epoch": 3.93, + "learning_rate": 6.072451370550825e-06, + "loss": 1.6595, + "step": 105600 + }, + { + "epoch": 3.93, + "eval_loss": 1.6392316818237305, + "eval_runtime": 16.8301, + "eval_samples_per_second": 59.418, + "eval_steps_per_second": 3.743, + "step": 105600 + }, + { + "epoch": 3.93, + "learning_rate": 6.0720794435972784e-06, + "loss": 1.7332, + "step": 105610 + }, + { + "epoch": 3.93, + "learning_rate": 6.071707516643731e-06, + "loss": 1.7761, + "step": 105620 + }, + { + "epoch": 3.93, + "learning_rate": 6.0713355896901845e-06, + "loss": 1.5566, + "step": 105630 + }, + { + "epoch": 3.93, + "learning_rate": 6.070963662736639e-06, + "loss": 1.6305, + "step": 105640 + }, + { + "epoch": 3.93, + "learning_rate": 6.070591735783092e-06, + "loss": 1.673, + "step": 105650 + }, + { + "epoch": 3.93, + "learning_rate": 6.070219808829546e-06, + "loss": 1.5539, + "step": 105660 + }, + { + "epoch": 3.93, + "learning_rate": 6.069847881876e-06, + "loss": 1.6798, + "step": 105670 + }, + { + "epoch": 3.93, + "learning_rate": 6.0694759549224535e-06, + "loss": 1.8198, + "step": 105680 + }, + { + "epoch": 3.93, + "learning_rate": 6.069104027968907e-06, + "loss": 1.7519, + "step": 105690 + }, + { + "epoch": 3.93, + "learning_rate": 6.068732101015361e-06, + "loss": 1.6866, + "step": 105700 + }, + { + "epoch": 3.93, + "eval_loss": 1.639522671699524, + "eval_runtime": 16.8261, + "eval_samples_per_second": 59.432, + "eval_steps_per_second": 3.744, + "step": 105700 + }, + { + "epoch": 3.93, + "learning_rate": 6.068360174061815e-06, + "loss": 1.6058, + "step": 105710 + }, + { + "epoch": 3.93, + "learning_rate": 6.067988247108268e-06, + "loss": 1.6735, + "step": 105720 + }, + { + "epoch": 3.93, + "learning_rate": 6.0676163201547225e-06, + "loss": 1.8028, + "step": 105730 + }, + { + "epoch": 3.93, + "learning_rate": 6.067244393201176e-06, + "loss": 1.7068, + "step": 105740 + }, + { + "epoch": 3.93, + "learning_rate": 6.066872466247629e-06, + "loss": 1.5363, + "step": 105750 + }, + { + "epoch": 3.93, + "learning_rate": 6.066500539294084e-06, + "loss": 1.7509, + "step": 105760 + }, + { + "epoch": 3.93, + "learning_rate": 6.066128612340537e-06, + "loss": 1.6448, + "step": 105770 + }, + { + "epoch": 3.93, + "learning_rate": 6.065756685386991e-06, + "loss": 1.7232, + "step": 105780 + }, + { + "epoch": 3.93, + "learning_rate": 6.065384758433445e-06, + "loss": 1.6004, + "step": 105790 + }, + { + "epoch": 3.93, + "learning_rate": 6.065012831479898e-06, + "loss": 1.6979, + "step": 105800 + }, + { + "epoch": 3.93, + "eval_loss": 1.6392605304718018, + "eval_runtime": 16.8228, + "eval_samples_per_second": 59.443, + "eval_steps_per_second": 3.745, + "step": 105800 + }, + { + "epoch": 3.94, + "learning_rate": 6.064640904526351e-06, + "loss": 1.7133, + "step": 105810 + }, + { + "epoch": 3.94, + "learning_rate": 6.0642689775728045e-06, + "loss": 1.6163, + "step": 105820 + }, + { + "epoch": 3.94, + "learning_rate": 6.063897050619259e-06, + "loss": 1.7241, + "step": 105830 + }, + { + "epoch": 3.94, + "learning_rate": 6.063525123665712e-06, + "loss": 1.6509, + "step": 105840 + }, + { + "epoch": 3.94, + "learning_rate": 6.063153196712166e-06, + "loss": 1.6968, + "step": 105850 + }, + { + "epoch": 3.94, + "learning_rate": 6.06278126975862e-06, + "loss": 1.8454, + "step": 105860 + }, + { + "epoch": 3.94, + "learning_rate": 6.0624093428050735e-06, + "loss": 1.6716, + "step": 105870 + }, + { + "epoch": 3.94, + "learning_rate": 6.062037415851527e-06, + "loss": 1.6872, + "step": 105880 + }, + { + "epoch": 3.94, + "learning_rate": 6.061665488897981e-06, + "loss": 1.7254, + "step": 105890 + }, + { + "epoch": 3.94, + "learning_rate": 6.061293561944435e-06, + "loss": 1.7246, + "step": 105900 + }, + { + "epoch": 3.94, + "eval_loss": 1.6397886276245117, + "eval_runtime": 16.8349, + "eval_samples_per_second": 59.4, + "eval_steps_per_second": 3.742, + "step": 105900 + }, + { + "epoch": 3.94, + "learning_rate": 6.060921634990888e-06, + "loss": 1.6669, + "step": 105910 + }, + { + "epoch": 3.94, + "learning_rate": 6.0605497080373424e-06, + "loss": 1.7033, + "step": 105920 + }, + { + "epoch": 3.94, + "learning_rate": 6.060177781083796e-06, + "loss": 1.6089, + "step": 105930 + }, + { + "epoch": 3.94, + "learning_rate": 6.059805854130249e-06, + "loss": 1.7716, + "step": 105940 + }, + { + "epoch": 3.94, + "learning_rate": 6.059433927176704e-06, + "loss": 1.7572, + "step": 105950 + }, + { + "epoch": 3.94, + "learning_rate": 6.059062000223157e-06, + "loss": 1.6572, + "step": 105960 + }, + { + "epoch": 3.94, + "learning_rate": 6.058690073269611e-06, + "loss": 1.6011, + "step": 105970 + }, + { + "epoch": 3.94, + "learning_rate": 6.058318146316065e-06, + "loss": 1.6052, + "step": 105980 + }, + { + "epoch": 3.94, + "learning_rate": 6.0579462193625175e-06, + "loss": 1.8102, + "step": 105990 + }, + { + "epoch": 3.94, + "learning_rate": 6.057574292408971e-06, + "loss": 1.6908, + "step": 106000 + }, + { + "epoch": 3.94, + "eval_loss": 1.6391018629074097, + "eval_runtime": 16.8303, + "eval_samples_per_second": 59.417, + "eval_steps_per_second": 3.743, + "step": 106000 + }, + { + "epoch": 3.94, + "learning_rate": 6.057202365455424e-06, + "loss": 1.7222, + "step": 106010 + }, + { + "epoch": 3.94, + "learning_rate": 6.056830438501879e-06, + "loss": 1.843, + "step": 106020 + }, + { + "epoch": 3.94, + "learning_rate": 6.056458511548332e-06, + "loss": 1.6003, + "step": 106030 + }, + { + "epoch": 3.94, + "learning_rate": 6.056086584594786e-06, + "loss": 1.8874, + "step": 106040 + }, + { + "epoch": 3.94, + "learning_rate": 6.05571465764124e-06, + "loss": 1.8324, + "step": 106050 + }, + { + "epoch": 3.94, + "learning_rate": 6.055342730687693e-06, + "loss": 1.5821, + "step": 106060 + }, + { + "epoch": 3.95, + "learning_rate": 6.054970803734147e-06, + "loss": 1.7269, + "step": 106070 + }, + { + "epoch": 3.95, + "learning_rate": 6.054598876780601e-06, + "loss": 1.574, + "step": 106080 + }, + { + "epoch": 3.95, + "learning_rate": 6.054226949827055e-06, + "loss": 1.8124, + "step": 106090 + }, + { + "epoch": 3.95, + "learning_rate": 6.053855022873508e-06, + "loss": 1.6289, + "step": 106100 + }, + { + "epoch": 3.95, + "eval_loss": 1.6397311687469482, + "eval_runtime": 16.8442, + "eval_samples_per_second": 59.368, + "eval_steps_per_second": 3.74, + "step": 106100 + }, + { + "epoch": 3.95, + "learning_rate": 6.0534830959199616e-06, + "loss": 1.6672, + "step": 106110 + }, + { + "epoch": 3.95, + "learning_rate": 6.053111168966416e-06, + "loss": 1.8223, + "step": 106120 + }, + { + "epoch": 3.95, + "learning_rate": 6.052739242012869e-06, + "loss": 1.7243, + "step": 106130 + }, + { + "epoch": 3.95, + "learning_rate": 6.052367315059323e-06, + "loss": 1.6716, + "step": 106140 + }, + { + "epoch": 3.95, + "learning_rate": 6.051995388105777e-06, + "loss": 1.593, + "step": 106150 + }, + { + "epoch": 3.95, + "learning_rate": 6.0516234611522305e-06, + "loss": 1.6555, + "step": 106160 + }, + { + "epoch": 3.95, + "learning_rate": 6.051251534198684e-06, + "loss": 1.6487, + "step": 106170 + }, + { + "epoch": 3.95, + "learning_rate": 6.050879607245137e-06, + "loss": 1.7429, + "step": 106180 + }, + { + "epoch": 3.95, + "learning_rate": 6.050507680291591e-06, + "loss": 1.6568, + "step": 106190 + }, + { + "epoch": 3.95, + "learning_rate": 6.050135753338044e-06, + "loss": 1.7211, + "step": 106200 + }, + { + "epoch": 3.95, + "eval_loss": 1.6396987438201904, + "eval_runtime": 16.8307, + "eval_samples_per_second": 59.415, + "eval_steps_per_second": 3.743, + "step": 106200 + }, + { + "epoch": 3.95, + "learning_rate": 6.049763826384498e-06, + "loss": 1.5993, + "step": 106210 + }, + { + "epoch": 3.95, + "learning_rate": 6.049391899430952e-06, + "loss": 1.7737, + "step": 106220 + }, + { + "epoch": 3.95, + "learning_rate": 6.049019972477406e-06, + "loss": 1.6747, + "step": 106230 + }, + { + "epoch": 3.95, + "learning_rate": 6.048648045523859e-06, + "loss": 1.9282, + "step": 106240 + }, + { + "epoch": 3.95, + "learning_rate": 6.048276118570313e-06, + "loss": 1.6016, + "step": 106250 + }, + { + "epoch": 3.95, + "learning_rate": 6.047904191616767e-06, + "loss": 1.7486, + "step": 106260 + }, + { + "epoch": 3.95, + "learning_rate": 6.04753226466322e-06, + "loss": 1.5326, + "step": 106270 + }, + { + "epoch": 3.95, + "learning_rate": 6.047160337709675e-06, + "loss": 1.6817, + "step": 106280 + }, + { + "epoch": 3.95, + "learning_rate": 6.046788410756128e-06, + "loss": 1.791, + "step": 106290 + }, + { + "epoch": 3.95, + "learning_rate": 6.0464164838025815e-06, + "loss": 1.6552, + "step": 106300 + }, + { + "epoch": 3.95, + "eval_loss": 1.638910174369812, + "eval_runtime": 16.8364, + "eval_samples_per_second": 59.395, + "eval_steps_per_second": 3.742, + "step": 106300 + }, + { + "epoch": 3.95, + "learning_rate": 6.046044556849036e-06, + "loss": 1.6587, + "step": 106310 + }, + { + "epoch": 3.95, + "learning_rate": 6.045672629895489e-06, + "loss": 1.6553, + "step": 106320 + }, + { + "epoch": 3.95, + "learning_rate": 6.045300702941943e-06, + "loss": 1.636, + "step": 106330 + }, + { + "epoch": 3.96, + "learning_rate": 6.044928775988397e-06, + "loss": 1.7735, + "step": 106340 + }, + { + "epoch": 3.96, + "learning_rate": 6.0445568490348505e-06, + "loss": 1.8153, + "step": 106350 + }, + { + "epoch": 3.96, + "learning_rate": 6.044184922081304e-06, + "loss": 1.6015, + "step": 106360 + }, + { + "epoch": 3.96, + "learning_rate": 6.0438129951277566e-06, + "loss": 1.6264, + "step": 106370 + }, + { + "epoch": 3.96, + "learning_rate": 6.043441068174211e-06, + "loss": 1.724, + "step": 106380 + }, + { + "epoch": 3.96, + "learning_rate": 6.043069141220664e-06, + "loss": 1.7151, + "step": 106390 + }, + { + "epoch": 3.96, + "learning_rate": 6.042697214267118e-06, + "loss": 1.6608, + "step": 106400 + }, + { + "epoch": 3.96, + "eval_loss": 1.6388415098190308, + "eval_runtime": 16.8149, + "eval_samples_per_second": 59.471, + "eval_steps_per_second": 3.747, + "step": 106400 + }, + { + "epoch": 3.96, + "learning_rate": 6.042325287313572e-06, + "loss": 1.7147, + "step": 106410 + }, + { + "epoch": 3.96, + "learning_rate": 6.0419533603600256e-06, + "loss": 1.7768, + "step": 106420 + }, + { + "epoch": 3.96, + "learning_rate": 6.041581433406479e-06, + "loss": 1.5205, + "step": 106430 + }, + { + "epoch": 3.96, + "learning_rate": 6.041209506452933e-06, + "loss": 1.698, + "step": 106440 + }, + { + "epoch": 3.96, + "learning_rate": 6.040837579499387e-06, + "loss": 1.7447, + "step": 106450 + }, + { + "epoch": 3.96, + "learning_rate": 6.04046565254584e-06, + "loss": 1.659, + "step": 106460 + }, + { + "epoch": 3.96, + "learning_rate": 6.0400937255922946e-06, + "loss": 1.6734, + "step": 106470 + }, + { + "epoch": 3.96, + "learning_rate": 6.039721798638748e-06, + "loss": 1.6882, + "step": 106480 + }, + { + "epoch": 3.96, + "learning_rate": 6.0393498716852015e-06, + "loss": 1.5314, + "step": 106490 + }, + { + "epoch": 3.96, + "learning_rate": 6.038977944731656e-06, + "loss": 1.6504, + "step": 106500 + }, + { + "epoch": 3.96, + "eval_loss": 1.6388953924179077, + "eval_runtime": 16.8316, + "eval_samples_per_second": 59.412, + "eval_steps_per_second": 3.743, + "step": 106500 + }, + { + "epoch": 3.96, + "learning_rate": 6.038606017778109e-06, + "loss": 1.6621, + "step": 106510 + }, + { + "epoch": 3.96, + "learning_rate": 6.038234090824563e-06, + "loss": 1.6582, + "step": 106520 + }, + { + "epoch": 3.96, + "learning_rate": 6.037862163871017e-06, + "loss": 1.6701, + "step": 106530 + }, + { + "epoch": 3.96, + "learning_rate": 6.0374902369174705e-06, + "loss": 1.6762, + "step": 106540 + }, + { + "epoch": 3.96, + "learning_rate": 6.037118309963924e-06, + "loss": 1.6312, + "step": 106550 + }, + { + "epoch": 3.96, + "learning_rate": 6.0367463830103765e-06, + "loss": 1.7328, + "step": 106560 + }, + { + "epoch": 3.96, + "learning_rate": 6.036374456056831e-06, + "loss": 1.7032, + "step": 106570 + }, + { + "epoch": 3.96, + "learning_rate": 6.036002529103284e-06, + "loss": 1.6352, + "step": 106580 + }, + { + "epoch": 3.96, + "learning_rate": 6.035630602149738e-06, + "loss": 1.6577, + "step": 106590 + }, + { + "epoch": 3.96, + "learning_rate": 6.035258675196192e-06, + "loss": 1.7057, + "step": 106600 + }, + { + "epoch": 3.96, + "eval_loss": 1.6387135982513428, + "eval_runtime": 16.8405, + "eval_samples_per_second": 59.381, + "eval_steps_per_second": 3.741, + "step": 106600 + } + ], + "max_steps": 268870, + "num_train_epochs": 10, + "total_flos": 4.82028964457472e+17, + "trial_name": null, + "trial_params": null +}