{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.7624309392265194, "eval_steps": 500, "global_step": 4000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 4.9884898710865566e-05, "loss": 1.803, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.976979742173112e-05, "loss": 1.781, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.965469613259669e-05, "loss": 1.721, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.953959484346225e-05, "loss": 1.6942, "step": 40 }, { "epoch": 0.03, "learning_rate": 4.942449355432781e-05, "loss": 1.7153, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.930939226519337e-05, "loss": 1.6549, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.919429097605893e-05, "loss": 1.6161, "step": 70 }, { "epoch": 0.06, "learning_rate": 4.9079189686924495e-05, "loss": 1.6448, "step": 80 }, { "epoch": 0.06, "learning_rate": 4.896408839779006e-05, "loss": 1.602, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.884898710865562e-05, "loss": 1.6401, "step": 100 }, { "epoch": 0.08, "learning_rate": 4.873388581952118e-05, "loss": 1.5939, "step": 110 }, { "epoch": 0.08, "learning_rate": 4.861878453038674e-05, "loss": 1.6273, "step": 120 }, { "epoch": 0.09, "learning_rate": 4.8503683241252305e-05, "loss": 1.5847, "step": 130 }, { "epoch": 0.1, "learning_rate": 4.838858195211787e-05, "loss": 1.6303, "step": 140 }, { "epoch": 0.1, "learning_rate": 4.8273480662983425e-05, "loss": 1.5958, "step": 150 }, { "epoch": 0.11, "learning_rate": 4.815837937384899e-05, "loss": 1.628, "step": 160 }, { "epoch": 0.12, "learning_rate": 4.804327808471455e-05, "loss": 1.6073, "step": 170 }, { "epoch": 0.12, "learning_rate": 4.7928176795580114e-05, "loss": 1.6069, "step": 180 }, { "epoch": 0.13, "learning_rate": 4.781307550644568e-05, "loss": 1.5774, "step": 190 }, { "epoch": 0.14, "learning_rate": 4.7697974217311234e-05, "loss": 1.5908, "step": 200 }, { "epoch": 0.15, "learning_rate": 4.75828729281768e-05, "loss": 1.6272, "step": 210 }, { "epoch": 0.15, "learning_rate": 4.746777163904236e-05, "loss": 1.5789, "step": 220 }, { "epoch": 0.16, "learning_rate": 4.7352670349907924e-05, "loss": 1.6184, "step": 230 }, { "epoch": 0.17, "learning_rate": 4.723756906077349e-05, "loss": 1.5601, "step": 240 }, { "epoch": 0.17, "learning_rate": 4.7122467771639044e-05, "loss": 1.6025, "step": 250 }, { "epoch": 0.18, "learning_rate": 4.700736648250461e-05, "loss": 1.5405, "step": 260 }, { "epoch": 0.19, "learning_rate": 4.6892265193370164e-05, "loss": 1.5928, "step": 270 }, { "epoch": 0.19, "learning_rate": 4.6777163904235734e-05, "loss": 1.5753, "step": 280 }, { "epoch": 0.2, "learning_rate": 4.666206261510129e-05, "loss": 1.6019, "step": 290 }, { "epoch": 0.21, "learning_rate": 4.6546961325966854e-05, "loss": 1.6118, "step": 300 }, { "epoch": 0.21, "learning_rate": 4.643186003683242e-05, "loss": 1.6183, "step": 310 }, { "epoch": 0.22, "learning_rate": 4.6316758747697973e-05, "loss": 1.5882, "step": 320 }, { "epoch": 0.23, "learning_rate": 4.6201657458563544e-05, "loss": 1.5797, "step": 330 }, { "epoch": 0.23, "learning_rate": 4.60865561694291e-05, "loss": 1.6227, "step": 340 }, { "epoch": 0.24, "learning_rate": 4.597145488029466e-05, "loss": 1.5912, "step": 350 }, { "epoch": 0.25, "learning_rate": 4.585635359116022e-05, "loss": 1.5672, "step": 360 }, { "epoch": 0.26, "learning_rate": 4.574125230202578e-05, "loss": 1.612, "step": 370 }, { "epoch": 0.26, "learning_rate": 4.5626151012891346e-05, "loss": 1.6161, "step": 380 }, { "epoch": 0.27, "learning_rate": 4.551104972375691e-05, "loss": 1.6061, "step": 390 }, { "epoch": 0.28, "learning_rate": 4.539594843462247e-05, "loss": 1.5733, "step": 400 }, { "epoch": 0.28, "learning_rate": 4.528084714548803e-05, "loss": 1.5949, "step": 410 }, { "epoch": 0.29, "learning_rate": 4.516574585635359e-05, "loss": 1.6355, "step": 420 }, { "epoch": 0.3, "learning_rate": 4.505064456721915e-05, "loss": 1.6296, "step": 430 }, { "epoch": 0.3, "learning_rate": 4.493554327808472e-05, "loss": 1.592, "step": 440 }, { "epoch": 0.31, "learning_rate": 4.4820441988950276e-05, "loss": 1.5712, "step": 450 }, { "epoch": 0.32, "learning_rate": 4.470534069981584e-05, "loss": 1.6086, "step": 460 }, { "epoch": 0.32, "learning_rate": 4.45902394106814e-05, "loss": 1.5757, "step": 470 }, { "epoch": 0.33, "learning_rate": 4.447513812154696e-05, "loss": 1.5885, "step": 480 }, { "epoch": 0.34, "learning_rate": 4.436003683241253e-05, "loss": 1.5828, "step": 490 }, { "epoch": 0.35, "learning_rate": 4.4244935543278086e-05, "loss": 1.5782, "step": 500 }, { "epoch": 0.35, "learning_rate": 4.412983425414365e-05, "loss": 1.6, "step": 510 }, { "epoch": 0.36, "learning_rate": 4.401473296500921e-05, "loss": 1.5992, "step": 520 }, { "epoch": 0.37, "learning_rate": 4.389963167587477e-05, "loss": 1.5709, "step": 530 }, { "epoch": 0.37, "learning_rate": 4.378453038674034e-05, "loss": 1.5642, "step": 540 }, { "epoch": 0.38, "learning_rate": 4.3669429097605895e-05, "loss": 1.6253, "step": 550 }, { "epoch": 0.39, "learning_rate": 4.355432780847146e-05, "loss": 1.5742, "step": 560 }, { "epoch": 0.39, "learning_rate": 4.3439226519337015e-05, "loss": 1.5912, "step": 570 }, { "epoch": 0.4, "learning_rate": 4.332412523020258e-05, "loss": 1.587, "step": 580 }, { "epoch": 0.41, "learning_rate": 4.320902394106814e-05, "loss": 1.5834, "step": 590 }, { "epoch": 0.41, "learning_rate": 4.3093922651933705e-05, "loss": 1.6063, "step": 600 }, { "epoch": 0.42, "learning_rate": 4.297882136279927e-05, "loss": 1.5801, "step": 610 }, { "epoch": 0.43, "learning_rate": 4.2863720073664825e-05, "loss": 1.5947, "step": 620 }, { "epoch": 0.44, "learning_rate": 4.274861878453039e-05, "loss": 1.6001, "step": 630 }, { "epoch": 0.44, "learning_rate": 4.263351749539595e-05, "loss": 1.6476, "step": 640 }, { "epoch": 0.45, "learning_rate": 4.2518416206261515e-05, "loss": 1.6008, "step": 650 }, { "epoch": 0.46, "learning_rate": 4.240331491712707e-05, "loss": 1.6011, "step": 660 }, { "epoch": 0.46, "learning_rate": 4.2288213627992634e-05, "loss": 1.603, "step": 670 }, { "epoch": 0.47, "learning_rate": 4.21731123388582e-05, "loss": 1.5862, "step": 680 }, { "epoch": 0.48, "learning_rate": 4.205801104972376e-05, "loss": 1.6024, "step": 690 }, { "epoch": 0.48, "learning_rate": 4.1942909760589324e-05, "loss": 1.6072, "step": 700 }, { "epoch": 0.49, "learning_rate": 4.182780847145488e-05, "loss": 1.5769, "step": 710 }, { "epoch": 0.5, "learning_rate": 4.1712707182320444e-05, "loss": 1.5869, "step": 720 }, { "epoch": 0.5, "learning_rate": 4.1597605893186e-05, "loss": 1.5877, "step": 730 }, { "epoch": 0.51, "learning_rate": 4.148250460405157e-05, "loss": 1.6401, "step": 740 }, { "epoch": 0.52, "learning_rate": 4.136740331491713e-05, "loss": 1.6012, "step": 750 }, { "epoch": 0.52, "learning_rate": 4.125230202578269e-05, "loss": 1.5881, "step": 760 }, { "epoch": 0.53, "learning_rate": 4.1137200736648254e-05, "loss": 1.6215, "step": 770 }, { "epoch": 0.54, "learning_rate": 4.102209944751381e-05, "loss": 1.6339, "step": 780 }, { "epoch": 0.55, "learning_rate": 4.090699815837938e-05, "loss": 1.627, "step": 790 }, { "epoch": 0.55, "learning_rate": 4.079189686924494e-05, "loss": 1.595, "step": 800 }, { "epoch": 0.56, "learning_rate": 4.06767955801105e-05, "loss": 1.5975, "step": 810 }, { "epoch": 0.57, "learning_rate": 4.056169429097606e-05, "loss": 1.581, "step": 820 }, { "epoch": 0.57, "learning_rate": 4.044659300184162e-05, "loss": 1.6179, "step": 830 }, { "epoch": 0.58, "learning_rate": 4.033149171270719e-05, "loss": 1.5888, "step": 840 }, { "epoch": 0.59, "learning_rate": 4.0216390423572746e-05, "loss": 1.5645, "step": 850 }, { "epoch": 0.59, "learning_rate": 4.010128913443831e-05, "loss": 1.6079, "step": 860 }, { "epoch": 0.6, "learning_rate": 3.9986187845303866e-05, "loss": 1.5738, "step": 870 }, { "epoch": 0.61, "learning_rate": 3.987108655616943e-05, "loss": 1.5887, "step": 880 }, { "epoch": 0.61, "learning_rate": 3.975598526703499e-05, "loss": 1.6049, "step": 890 }, { "epoch": 0.62, "learning_rate": 3.9640883977900556e-05, "loss": 1.6021, "step": 900 }, { "epoch": 0.63, "learning_rate": 3.952578268876612e-05, "loss": 1.5762, "step": 910 }, { "epoch": 0.64, "learning_rate": 3.9410681399631676e-05, "loss": 1.5568, "step": 920 }, { "epoch": 0.64, "learning_rate": 3.929558011049724e-05, "loss": 1.5439, "step": 930 }, { "epoch": 0.65, "learning_rate": 3.91804788213628e-05, "loss": 1.5901, "step": 940 }, { "epoch": 0.66, "learning_rate": 3.9065377532228366e-05, "loss": 1.6208, "step": 950 }, { "epoch": 0.66, "learning_rate": 3.895027624309392e-05, "loss": 1.6169, "step": 960 }, { "epoch": 0.67, "learning_rate": 3.8835174953959486e-05, "loss": 1.6367, "step": 970 }, { "epoch": 0.68, "learning_rate": 3.872007366482505e-05, "loss": 1.6195, "step": 980 }, { "epoch": 0.68, "learning_rate": 3.860497237569061e-05, "loss": 1.6107, "step": 990 }, { "epoch": 0.69, "learning_rate": 3.8489871086556175e-05, "loss": 1.607, "step": 1000 }, { "epoch": 0.7, "learning_rate": 3.837476979742173e-05, "loss": 1.572, "step": 1010 }, { "epoch": 0.7, "learning_rate": 3.8259668508287295e-05, "loss": 1.5877, "step": 1020 }, { "epoch": 0.71, "learning_rate": 3.814456721915285e-05, "loss": 1.5893, "step": 1030 }, { "epoch": 0.72, "learning_rate": 3.8029465930018415e-05, "loss": 1.5979, "step": 1040 }, { "epoch": 0.73, "learning_rate": 3.791436464088398e-05, "loss": 1.62, "step": 1050 }, { "epoch": 0.73, "learning_rate": 3.779926335174954e-05, "loss": 1.5397, "step": 1060 }, { "epoch": 0.74, "learning_rate": 3.7684162062615105e-05, "loss": 1.6262, "step": 1070 }, { "epoch": 0.75, "learning_rate": 3.756906077348066e-05, "loss": 1.5745, "step": 1080 }, { "epoch": 0.75, "learning_rate": 3.7453959484346225e-05, "loss": 1.6107, "step": 1090 }, { "epoch": 0.76, "learning_rate": 3.733885819521179e-05, "loss": 1.6006, "step": 1100 }, { "epoch": 0.77, "learning_rate": 3.722375690607735e-05, "loss": 1.6287, "step": 1110 }, { "epoch": 0.77, "learning_rate": 3.710865561694291e-05, "loss": 1.5726, "step": 1120 }, { "epoch": 0.78, "learning_rate": 3.699355432780847e-05, "loss": 1.5706, "step": 1130 }, { "epoch": 0.79, "learning_rate": 3.6878453038674034e-05, "loss": 1.542, "step": 1140 }, { "epoch": 0.79, "learning_rate": 3.67633517495396e-05, "loss": 1.5889, "step": 1150 }, { "epoch": 0.8, "learning_rate": 3.664825046040516e-05, "loss": 1.594, "step": 1160 }, { "epoch": 0.81, "learning_rate": 3.653314917127072e-05, "loss": 1.584, "step": 1170 }, { "epoch": 0.81, "learning_rate": 3.641804788213628e-05, "loss": 1.5925, "step": 1180 }, { "epoch": 0.82, "learning_rate": 3.6302946593001844e-05, "loss": 1.6085, "step": 1190 }, { "epoch": 0.83, "learning_rate": 3.618784530386741e-05, "loss": 1.5677, "step": 1200 }, { "epoch": 0.84, "learning_rate": 3.607274401473297e-05, "loss": 1.6185, "step": 1210 }, { "epoch": 0.84, "learning_rate": 3.595764272559853e-05, "loss": 1.584, "step": 1220 }, { "epoch": 0.85, "learning_rate": 3.584254143646409e-05, "loss": 1.6028, "step": 1230 }, { "epoch": 0.86, "learning_rate": 3.572744014732965e-05, "loss": 1.5581, "step": 1240 }, { "epoch": 0.86, "learning_rate": 3.561233885819522e-05, "loss": 1.5907, "step": 1250 }, { "epoch": 0.87, "learning_rate": 3.5497237569060774e-05, "loss": 1.5602, "step": 1260 }, { "epoch": 0.88, "learning_rate": 3.538213627992634e-05, "loss": 1.5887, "step": 1270 }, { "epoch": 0.88, "learning_rate": 3.52670349907919e-05, "loss": 1.5724, "step": 1280 }, { "epoch": 0.89, "learning_rate": 3.515193370165746e-05, "loss": 1.58, "step": 1290 }, { "epoch": 0.9, "learning_rate": 3.503683241252303e-05, "loss": 1.6222, "step": 1300 }, { "epoch": 0.9, "learning_rate": 3.492173112338858e-05, "loss": 1.5889, "step": 1310 }, { "epoch": 0.91, "learning_rate": 3.4806629834254147e-05, "loss": 1.5776, "step": 1320 }, { "epoch": 0.92, "learning_rate": 3.46915285451197e-05, "loss": 1.5561, "step": 1330 }, { "epoch": 0.93, "learning_rate": 3.4576427255985266e-05, "loss": 1.6076, "step": 1340 }, { "epoch": 0.93, "learning_rate": 3.446132596685083e-05, "loss": 1.586, "step": 1350 }, { "epoch": 0.94, "learning_rate": 3.434622467771639e-05, "loss": 1.5443, "step": 1360 }, { "epoch": 0.95, "learning_rate": 3.4231123388581956e-05, "loss": 1.6226, "step": 1370 }, { "epoch": 0.95, "learning_rate": 3.411602209944751e-05, "loss": 1.5835, "step": 1380 }, { "epoch": 0.96, "learning_rate": 3.4000920810313076e-05, "loss": 1.5367, "step": 1390 }, { "epoch": 0.97, "learning_rate": 3.388581952117864e-05, "loss": 1.5967, "step": 1400 }, { "epoch": 0.97, "learning_rate": 3.37707182320442e-05, "loss": 1.559, "step": 1410 }, { "epoch": 0.98, "learning_rate": 3.365561694290976e-05, "loss": 1.6235, "step": 1420 }, { "epoch": 0.99, "learning_rate": 3.354051565377532e-05, "loss": 1.5517, "step": 1430 }, { "epoch": 0.99, "learning_rate": 3.3425414364640886e-05, "loss": 1.5651, "step": 1440 }, { "epoch": 1.0, "learning_rate": 3.331031307550645e-05, "loss": 1.5994, "step": 1450 }, { "epoch": 1.01, "learning_rate": 3.319521178637201e-05, "loss": 1.6072, "step": 1460 }, { "epoch": 1.02, "learning_rate": 3.308011049723757e-05, "loss": 1.5715, "step": 1470 }, { "epoch": 1.02, "learning_rate": 3.296500920810313e-05, "loss": 1.5736, "step": 1480 }, { "epoch": 1.03, "learning_rate": 3.2849907918968695e-05, "loss": 1.5581, "step": 1490 }, { "epoch": 1.04, "learning_rate": 3.273480662983426e-05, "loss": 1.5204, "step": 1500 }, { "epoch": 1.04, "learning_rate": 3.261970534069982e-05, "loss": 1.5835, "step": 1510 }, { "epoch": 1.05, "learning_rate": 3.250460405156538e-05, "loss": 1.5892, "step": 1520 }, { "epoch": 1.06, "learning_rate": 3.238950276243094e-05, "loss": 1.5769, "step": 1530 }, { "epoch": 1.06, "learning_rate": 3.22744014732965e-05, "loss": 1.5565, "step": 1540 }, { "epoch": 1.07, "learning_rate": 3.215930018416207e-05, "loss": 1.585, "step": 1550 }, { "epoch": 1.08, "learning_rate": 3.2044198895027625e-05, "loss": 1.5896, "step": 1560 }, { "epoch": 1.08, "learning_rate": 3.192909760589319e-05, "loss": 1.5741, "step": 1570 }, { "epoch": 1.09, "learning_rate": 3.181399631675875e-05, "loss": 1.5669, "step": 1580 }, { "epoch": 1.1, "learning_rate": 3.169889502762431e-05, "loss": 1.6052, "step": 1590 }, { "epoch": 1.1, "learning_rate": 3.158379373848988e-05, "loss": 1.6087, "step": 1600 }, { "epoch": 1.11, "learning_rate": 3.1468692449355434e-05, "loss": 1.6186, "step": 1610 }, { "epoch": 1.12, "learning_rate": 3.1353591160221e-05, "loss": 1.5654, "step": 1620 }, { "epoch": 1.13, "learning_rate": 3.1238489871086554e-05, "loss": 1.5747, "step": 1630 }, { "epoch": 1.13, "learning_rate": 3.112338858195212e-05, "loss": 1.6006, "step": 1640 }, { "epoch": 1.14, "learning_rate": 3.100828729281768e-05, "loss": 1.5931, "step": 1650 }, { "epoch": 1.15, "learning_rate": 3.0893186003683244e-05, "loss": 1.5518, "step": 1660 }, { "epoch": 1.15, "learning_rate": 3.077808471454881e-05, "loss": 1.5872, "step": 1670 }, { "epoch": 1.16, "learning_rate": 3.0662983425414364e-05, "loss": 1.6109, "step": 1680 }, { "epoch": 1.17, "learning_rate": 3.054788213627993e-05, "loss": 1.5978, "step": 1690 }, { "epoch": 1.17, "learning_rate": 3.0432780847145487e-05, "loss": 1.6005, "step": 1700 }, { "epoch": 1.18, "learning_rate": 3.0317679558011054e-05, "loss": 1.5629, "step": 1710 }, { "epoch": 1.19, "learning_rate": 3.0202578268876614e-05, "loss": 1.5958, "step": 1720 }, { "epoch": 1.19, "learning_rate": 3.0087476979742174e-05, "loss": 1.5918, "step": 1730 }, { "epoch": 1.2, "learning_rate": 2.9972375690607734e-05, "loss": 1.6137, "step": 1740 }, { "epoch": 1.21, "learning_rate": 2.9857274401473297e-05, "loss": 1.5628, "step": 1750 }, { "epoch": 1.22, "learning_rate": 2.974217311233886e-05, "loss": 1.5806, "step": 1760 }, { "epoch": 1.22, "learning_rate": 2.9627071823204423e-05, "loss": 1.5868, "step": 1770 }, { "epoch": 1.23, "learning_rate": 2.9511970534069983e-05, "loss": 1.5842, "step": 1780 }, { "epoch": 1.24, "learning_rate": 2.9396869244935543e-05, "loss": 1.5898, "step": 1790 }, { "epoch": 1.24, "learning_rate": 2.9281767955801103e-05, "loss": 1.5812, "step": 1800 }, { "epoch": 1.25, "learning_rate": 2.916666666666667e-05, "loss": 1.5812, "step": 1810 }, { "epoch": 1.26, "learning_rate": 2.905156537753223e-05, "loss": 1.6343, "step": 1820 }, { "epoch": 1.26, "learning_rate": 2.893646408839779e-05, "loss": 1.5993, "step": 1830 }, { "epoch": 1.27, "learning_rate": 2.8821362799263353e-05, "loss": 1.5398, "step": 1840 }, { "epoch": 1.28, "learning_rate": 2.8706261510128913e-05, "loss": 1.585, "step": 1850 }, { "epoch": 1.28, "learning_rate": 2.859116022099448e-05, "loss": 1.5969, "step": 1860 }, { "epoch": 1.29, "learning_rate": 2.847605893186004e-05, "loss": 1.582, "step": 1870 }, { "epoch": 1.3, "learning_rate": 2.83609576427256e-05, "loss": 1.5646, "step": 1880 }, { "epoch": 1.31, "learning_rate": 2.824585635359116e-05, "loss": 1.5525, "step": 1890 }, { "epoch": 1.31, "learning_rate": 2.8130755064456722e-05, "loss": 1.5957, "step": 1900 }, { "epoch": 1.32, "learning_rate": 2.8015653775322286e-05, "loss": 1.5797, "step": 1910 }, { "epoch": 1.33, "learning_rate": 2.790055248618785e-05, "loss": 1.5693, "step": 1920 }, { "epoch": 1.33, "learning_rate": 2.778545119705341e-05, "loss": 1.5788, "step": 1930 }, { "epoch": 1.34, "learning_rate": 2.767034990791897e-05, "loss": 1.5635, "step": 1940 }, { "epoch": 1.35, "learning_rate": 2.755524861878453e-05, "loss": 1.5764, "step": 1950 }, { "epoch": 1.35, "learning_rate": 2.7440147329650095e-05, "loss": 1.5704, "step": 1960 }, { "epoch": 1.36, "learning_rate": 2.7325046040515655e-05, "loss": 1.5623, "step": 1970 }, { "epoch": 1.37, "learning_rate": 2.7209944751381215e-05, "loss": 1.6165, "step": 1980 }, { "epoch": 1.37, "learning_rate": 2.709484346224678e-05, "loss": 1.5834, "step": 1990 }, { "epoch": 1.38, "learning_rate": 2.697974217311234e-05, "loss": 1.5569, "step": 2000 }, { "epoch": 1.39, "learning_rate": 2.6864640883977905e-05, "loss": 1.5973, "step": 2010 }, { "epoch": 1.4, "learning_rate": 2.6749539594843465e-05, "loss": 1.611, "step": 2020 }, { "epoch": 1.4, "learning_rate": 2.6634438305709025e-05, "loss": 1.5728, "step": 2030 }, { "epoch": 1.41, "learning_rate": 2.6519337016574585e-05, "loss": 1.5953, "step": 2040 }, { "epoch": 1.42, "learning_rate": 2.6404235727440148e-05, "loss": 1.5468, "step": 2050 }, { "epoch": 1.42, "learning_rate": 2.628913443830571e-05, "loss": 1.5737, "step": 2060 }, { "epoch": 1.43, "learning_rate": 2.6174033149171275e-05, "loss": 1.559, "step": 2070 }, { "epoch": 1.44, "learning_rate": 2.6058931860036835e-05, "loss": 1.595, "step": 2080 }, { "epoch": 1.44, "learning_rate": 2.5943830570902394e-05, "loss": 1.5688, "step": 2090 }, { "epoch": 1.45, "learning_rate": 2.5828729281767954e-05, "loss": 1.5566, "step": 2100 }, { "epoch": 1.46, "learning_rate": 2.571362799263352e-05, "loss": 1.6499, "step": 2110 }, { "epoch": 1.46, "learning_rate": 2.559852670349908e-05, "loss": 1.6233, "step": 2120 }, { "epoch": 1.47, "learning_rate": 2.548342541436464e-05, "loss": 1.5406, "step": 2130 }, { "epoch": 1.48, "learning_rate": 2.5368324125230204e-05, "loss": 1.5989, "step": 2140 }, { "epoch": 1.48, "learning_rate": 2.5253222836095764e-05, "loss": 1.5964, "step": 2150 }, { "epoch": 1.49, "learning_rate": 2.513812154696133e-05, "loss": 1.5715, "step": 2160 }, { "epoch": 1.5, "learning_rate": 2.502302025782689e-05, "loss": 1.5662, "step": 2170 }, { "epoch": 1.51, "learning_rate": 2.490791896869245e-05, "loss": 1.6269, "step": 2180 }, { "epoch": 1.51, "learning_rate": 2.479281767955801e-05, "loss": 1.5549, "step": 2190 }, { "epoch": 1.52, "learning_rate": 2.4677716390423574e-05, "loss": 1.6521, "step": 2200 }, { "epoch": 1.53, "learning_rate": 2.4562615101289137e-05, "loss": 1.6164, "step": 2210 }, { "epoch": 1.53, "learning_rate": 2.4447513812154697e-05, "loss": 1.5851, "step": 2220 }, { "epoch": 1.54, "learning_rate": 2.433241252302026e-05, "loss": 1.6146, "step": 2230 }, { "epoch": 1.55, "learning_rate": 2.421731123388582e-05, "loss": 1.5704, "step": 2240 }, { "epoch": 1.55, "learning_rate": 2.4102209944751383e-05, "loss": 1.6094, "step": 2250 }, { "epoch": 1.56, "learning_rate": 2.3987108655616943e-05, "loss": 1.5886, "step": 2260 }, { "epoch": 1.57, "learning_rate": 2.3872007366482503e-05, "loss": 1.5399, "step": 2270 }, { "epoch": 1.57, "learning_rate": 2.3756906077348066e-05, "loss": 1.5285, "step": 2280 }, { "epoch": 1.58, "learning_rate": 2.364180478821363e-05, "loss": 1.6065, "step": 2290 }, { "epoch": 1.59, "learning_rate": 2.3526703499079193e-05, "loss": 1.5909, "step": 2300 }, { "epoch": 1.6, "learning_rate": 2.3411602209944753e-05, "loss": 1.5671, "step": 2310 }, { "epoch": 1.6, "learning_rate": 2.3296500920810313e-05, "loss": 1.6306, "step": 2320 }, { "epoch": 1.61, "learning_rate": 2.3181399631675876e-05, "loss": 1.5684, "step": 2330 }, { "epoch": 1.62, "learning_rate": 2.3066298342541436e-05, "loss": 1.5746, "step": 2340 }, { "epoch": 1.62, "learning_rate": 2.2951197053407e-05, "loss": 1.5796, "step": 2350 }, { "epoch": 1.63, "learning_rate": 2.2836095764272563e-05, "loss": 1.5653, "step": 2360 }, { "epoch": 1.64, "learning_rate": 2.2720994475138122e-05, "loss": 1.6186, "step": 2370 }, { "epoch": 1.64, "learning_rate": 2.2605893186003686e-05, "loss": 1.5848, "step": 2380 }, { "epoch": 1.65, "learning_rate": 2.2490791896869246e-05, "loss": 1.5488, "step": 2390 }, { "epoch": 1.66, "learning_rate": 2.237569060773481e-05, "loss": 1.5522, "step": 2400 }, { "epoch": 1.66, "learning_rate": 2.226058931860037e-05, "loss": 1.5386, "step": 2410 }, { "epoch": 1.67, "learning_rate": 2.214548802946593e-05, "loss": 1.5603, "step": 2420 }, { "epoch": 1.68, "learning_rate": 2.2030386740331492e-05, "loss": 1.5723, "step": 2430 }, { "epoch": 1.69, "learning_rate": 2.1915285451197055e-05, "loss": 1.5712, "step": 2440 }, { "epoch": 1.69, "learning_rate": 2.180018416206262e-05, "loss": 1.5656, "step": 2450 }, { "epoch": 1.7, "learning_rate": 2.168508287292818e-05, "loss": 1.6042, "step": 2460 }, { "epoch": 1.71, "learning_rate": 2.156998158379374e-05, "loss": 1.619, "step": 2470 }, { "epoch": 1.71, "learning_rate": 2.1454880294659302e-05, "loss": 1.6388, "step": 2480 }, { "epoch": 1.72, "learning_rate": 2.133977900552486e-05, "loss": 1.5726, "step": 2490 }, { "epoch": 1.73, "learning_rate": 2.1224677716390425e-05, "loss": 1.5748, "step": 2500 }, { "epoch": 1.73, "learning_rate": 2.1109576427255985e-05, "loss": 1.5391, "step": 2510 }, { "epoch": 1.74, "learning_rate": 2.0994475138121548e-05, "loss": 1.5533, "step": 2520 }, { "epoch": 1.75, "learning_rate": 2.087937384898711e-05, "loss": 1.6024, "step": 2530 }, { "epoch": 1.75, "learning_rate": 2.076427255985267e-05, "loss": 1.6164, "step": 2540 }, { "epoch": 1.76, "learning_rate": 2.064917127071823e-05, "loss": 1.6015, "step": 2550 }, { "epoch": 1.77, "learning_rate": 2.0534069981583794e-05, "loss": 1.5342, "step": 2560 }, { "epoch": 1.77, "learning_rate": 2.0418968692449354e-05, "loss": 1.5803, "step": 2570 }, { "epoch": 1.78, "learning_rate": 2.0303867403314918e-05, "loss": 1.5785, "step": 2580 }, { "epoch": 1.79, "learning_rate": 2.018876611418048e-05, "loss": 1.6065, "step": 2590 }, { "epoch": 1.8, "learning_rate": 2.007366482504604e-05, "loss": 1.5749, "step": 2600 }, { "epoch": 1.8, "learning_rate": 1.9958563535911604e-05, "loss": 1.6449, "step": 2610 }, { "epoch": 1.81, "learning_rate": 1.9843462246777164e-05, "loss": 1.5728, "step": 2620 }, { "epoch": 1.82, "learning_rate": 1.9728360957642727e-05, "loss": 1.5928, "step": 2630 }, { "epoch": 1.82, "learning_rate": 1.9613259668508287e-05, "loss": 1.574, "step": 2640 }, { "epoch": 1.83, "learning_rate": 1.9498158379373847e-05, "loss": 1.6048, "step": 2650 }, { "epoch": 1.84, "learning_rate": 1.938305709023941e-05, "loss": 1.6058, "step": 2660 }, { "epoch": 1.84, "learning_rate": 1.9267955801104974e-05, "loss": 1.5239, "step": 2670 }, { "epoch": 1.85, "learning_rate": 1.9152854511970537e-05, "loss": 1.6128, "step": 2680 }, { "epoch": 1.86, "learning_rate": 1.9037753222836097e-05, "loss": 1.5784, "step": 2690 }, { "epoch": 1.86, "learning_rate": 1.8922651933701657e-05, "loss": 1.5574, "step": 2700 }, { "epoch": 1.87, "learning_rate": 1.880755064456722e-05, "loss": 1.5636, "step": 2710 }, { "epoch": 1.88, "learning_rate": 1.869244935543278e-05, "loss": 1.5488, "step": 2720 }, { "epoch": 1.89, "learning_rate": 1.8577348066298343e-05, "loss": 1.5796, "step": 2730 }, { "epoch": 1.89, "learning_rate": 1.8462246777163907e-05, "loss": 1.5908, "step": 2740 }, { "epoch": 1.9, "learning_rate": 1.8347145488029466e-05, "loss": 1.5796, "step": 2750 }, { "epoch": 1.91, "learning_rate": 1.823204419889503e-05, "loss": 1.5791, "step": 2760 }, { "epoch": 1.91, "learning_rate": 1.811694290976059e-05, "loss": 1.5562, "step": 2770 }, { "epoch": 1.92, "learning_rate": 1.8001841620626153e-05, "loss": 1.5847, "step": 2780 }, { "epoch": 1.93, "learning_rate": 1.7886740331491713e-05, "loss": 1.5811, "step": 2790 }, { "epoch": 1.93, "learning_rate": 1.7771639042357273e-05, "loss": 1.5668, "step": 2800 }, { "epoch": 1.94, "learning_rate": 1.7656537753222836e-05, "loss": 1.5274, "step": 2810 }, { "epoch": 1.95, "learning_rate": 1.75414364640884e-05, "loss": 1.6038, "step": 2820 }, { "epoch": 1.95, "learning_rate": 1.7426335174953963e-05, "loss": 1.5604, "step": 2830 }, { "epoch": 1.96, "learning_rate": 1.7311233885819523e-05, "loss": 1.5769, "step": 2840 }, { "epoch": 1.97, "learning_rate": 1.7196132596685082e-05, "loss": 1.5398, "step": 2850 }, { "epoch": 1.98, "learning_rate": 1.7081031307550646e-05, "loss": 1.5883, "step": 2860 }, { "epoch": 1.98, "learning_rate": 1.6965930018416206e-05, "loss": 1.5578, "step": 2870 }, { "epoch": 1.99, "learning_rate": 1.685082872928177e-05, "loss": 1.6156, "step": 2880 }, { "epoch": 2.0, "learning_rate": 1.6735727440147332e-05, "loss": 1.5839, "step": 2890 }, { "epoch": 2.0, "learning_rate": 1.6620626151012892e-05, "loss": 1.5896, "step": 2900 }, { "epoch": 2.01, "learning_rate": 1.6505524861878455e-05, "loss": 1.5763, "step": 2910 }, { "epoch": 2.02, "learning_rate": 1.6390423572744015e-05, "loss": 1.6019, "step": 2920 }, { "epoch": 2.02, "learning_rate": 1.6275322283609575e-05, "loss": 1.5952, "step": 2930 }, { "epoch": 2.03, "learning_rate": 1.616022099447514e-05, "loss": 1.5675, "step": 2940 }, { "epoch": 2.04, "learning_rate": 1.60451197053407e-05, "loss": 1.5652, "step": 2950 }, { "epoch": 2.04, "learning_rate": 1.593001841620626e-05, "loss": 1.5941, "step": 2960 }, { "epoch": 2.05, "learning_rate": 1.5814917127071825e-05, "loss": 1.6385, "step": 2970 }, { "epoch": 2.06, "learning_rate": 1.5699815837937385e-05, "loss": 1.5991, "step": 2980 }, { "epoch": 2.06, "learning_rate": 1.5584714548802948e-05, "loss": 1.6065, "step": 2990 }, { "epoch": 2.07, "learning_rate": 1.5469613259668508e-05, "loss": 1.5563, "step": 3000 }, { "epoch": 2.08, "learning_rate": 1.535451197053407e-05, "loss": 1.6216, "step": 3010 }, { "epoch": 2.09, "learning_rate": 1.5239410681399633e-05, "loss": 1.5723, "step": 3020 }, { "epoch": 2.09, "learning_rate": 1.5124309392265193e-05, "loss": 1.5637, "step": 3030 }, { "epoch": 2.1, "learning_rate": 1.5009208103130756e-05, "loss": 1.5871, "step": 3040 }, { "epoch": 2.11, "learning_rate": 1.4894106813996318e-05, "loss": 1.5696, "step": 3050 }, { "epoch": 2.11, "learning_rate": 1.4779005524861881e-05, "loss": 1.5912, "step": 3060 }, { "epoch": 2.12, "learning_rate": 1.4663904235727441e-05, "loss": 1.5855, "step": 3070 }, { "epoch": 2.13, "learning_rate": 1.4548802946593e-05, "loss": 1.5646, "step": 3080 }, { "epoch": 2.13, "learning_rate": 1.4433701657458564e-05, "loss": 1.5838, "step": 3090 }, { "epoch": 2.14, "learning_rate": 1.4318600368324126e-05, "loss": 1.5627, "step": 3100 }, { "epoch": 2.15, "learning_rate": 1.4203499079189689e-05, "loss": 1.5359, "step": 3110 }, { "epoch": 2.15, "learning_rate": 1.4088397790055249e-05, "loss": 1.5563, "step": 3120 }, { "epoch": 2.16, "learning_rate": 1.397329650092081e-05, "loss": 1.5612, "step": 3130 }, { "epoch": 2.17, "learning_rate": 1.3858195211786374e-05, "loss": 1.5943, "step": 3140 }, { "epoch": 2.18, "learning_rate": 1.3743093922651934e-05, "loss": 1.5607, "step": 3150 }, { "epoch": 2.18, "learning_rate": 1.3627992633517497e-05, "loss": 1.601, "step": 3160 }, { "epoch": 2.19, "learning_rate": 1.3512891344383059e-05, "loss": 1.6082, "step": 3170 }, { "epoch": 2.2, "learning_rate": 1.3397790055248618e-05, "loss": 1.5749, "step": 3180 }, { "epoch": 2.2, "learning_rate": 1.3282688766114182e-05, "loss": 1.545, "step": 3190 }, { "epoch": 2.21, "learning_rate": 1.3167587476979742e-05, "loss": 1.5448, "step": 3200 }, { "epoch": 2.22, "learning_rate": 1.3052486187845307e-05, "loss": 1.574, "step": 3210 }, { "epoch": 2.22, "learning_rate": 1.2937384898710867e-05, "loss": 1.5566, "step": 3220 }, { "epoch": 2.23, "learning_rate": 1.2822283609576426e-05, "loss": 1.5462, "step": 3230 }, { "epoch": 2.24, "learning_rate": 1.270718232044199e-05, "loss": 1.5684, "step": 3240 }, { "epoch": 2.24, "learning_rate": 1.2592081031307551e-05, "loss": 1.553, "step": 3250 }, { "epoch": 2.25, "learning_rate": 1.2476979742173113e-05, "loss": 1.5781, "step": 3260 }, { "epoch": 2.26, "learning_rate": 1.2361878453038675e-05, "loss": 1.5651, "step": 3270 }, { "epoch": 2.27, "learning_rate": 1.2246777163904238e-05, "loss": 1.6042, "step": 3280 }, { "epoch": 2.27, "learning_rate": 1.2131675874769798e-05, "loss": 1.5505, "step": 3290 }, { "epoch": 2.28, "learning_rate": 1.201657458563536e-05, "loss": 1.5766, "step": 3300 }, { "epoch": 2.29, "learning_rate": 1.1901473296500921e-05, "loss": 1.5531, "step": 3310 }, { "epoch": 2.29, "learning_rate": 1.1786372007366484e-05, "loss": 1.5837, "step": 3320 }, { "epoch": 2.3, "learning_rate": 1.1671270718232044e-05, "loss": 1.573, "step": 3330 }, { "epoch": 2.31, "learning_rate": 1.1556169429097606e-05, "loss": 1.5422, "step": 3340 }, { "epoch": 2.31, "learning_rate": 1.1441068139963167e-05, "loss": 1.5768, "step": 3350 }, { "epoch": 2.32, "learning_rate": 1.132596685082873e-05, "loss": 1.5988, "step": 3360 }, { "epoch": 2.33, "learning_rate": 1.1210865561694292e-05, "loss": 1.5839, "step": 3370 }, { "epoch": 2.33, "learning_rate": 1.1095764272559852e-05, "loss": 1.5619, "step": 3380 }, { "epoch": 2.34, "learning_rate": 1.0980662983425415e-05, "loss": 1.6055, "step": 3390 }, { "epoch": 2.35, "learning_rate": 1.0865561694290977e-05, "loss": 1.5814, "step": 3400 }, { "epoch": 2.35, "learning_rate": 1.0750460405156539e-05, "loss": 1.5522, "step": 3410 }, { "epoch": 2.36, "learning_rate": 1.06353591160221e-05, "loss": 1.6209, "step": 3420 }, { "epoch": 2.37, "learning_rate": 1.0520257826887662e-05, "loss": 1.539, "step": 3430 }, { "epoch": 2.38, "learning_rate": 1.0405156537753223e-05, "loss": 1.5939, "step": 3440 }, { "epoch": 2.38, "learning_rate": 1.0290055248618785e-05, "loss": 1.5985, "step": 3450 }, { "epoch": 2.39, "learning_rate": 1.0174953959484347e-05, "loss": 1.5489, "step": 3460 }, { "epoch": 2.4, "learning_rate": 1.005985267034991e-05, "loss": 1.5676, "step": 3470 }, { "epoch": 2.4, "learning_rate": 9.94475138121547e-06, "loss": 1.5781, "step": 3480 }, { "epoch": 2.41, "learning_rate": 9.829650092081031e-06, "loss": 1.5754, "step": 3490 }, { "epoch": 2.42, "learning_rate": 9.714548802946593e-06, "loss": 1.5654, "step": 3500 }, { "epoch": 2.42, "learning_rate": 9.599447513812156e-06, "loss": 1.5657, "step": 3510 }, { "epoch": 2.43, "learning_rate": 9.484346224677716e-06, "loss": 1.5615, "step": 3520 }, { "epoch": 2.44, "learning_rate": 9.369244935543278e-06, "loss": 1.5707, "step": 3530 }, { "epoch": 2.44, "learning_rate": 9.254143646408841e-06, "loss": 1.5984, "step": 3540 }, { "epoch": 2.45, "learning_rate": 9.139042357274403e-06, "loss": 1.5645, "step": 3550 }, { "epoch": 2.46, "learning_rate": 9.023941068139964e-06, "loss": 1.5785, "step": 3560 }, { "epoch": 2.47, "learning_rate": 8.908839779005524e-06, "loss": 1.5553, "step": 3570 }, { "epoch": 2.47, "learning_rate": 8.793738489871087e-06, "loss": 1.6238, "step": 3580 }, { "epoch": 2.48, "learning_rate": 8.678637200736649e-06, "loss": 1.6065, "step": 3590 }, { "epoch": 2.49, "learning_rate": 8.56353591160221e-06, "loss": 1.6151, "step": 3600 }, { "epoch": 2.49, "learning_rate": 8.448434622467772e-06, "loss": 1.5465, "step": 3610 }, { "epoch": 2.5, "learning_rate": 8.333333333333334e-06, "loss": 1.5963, "step": 3620 }, { "epoch": 2.51, "learning_rate": 8.218232044198895e-06, "loss": 1.622, "step": 3630 }, { "epoch": 2.51, "learning_rate": 8.103130755064457e-06, "loss": 1.5567, "step": 3640 }, { "epoch": 2.52, "learning_rate": 7.988029465930019e-06, "loss": 1.6297, "step": 3650 }, { "epoch": 2.53, "learning_rate": 7.87292817679558e-06, "loss": 1.604, "step": 3660 }, { "epoch": 2.53, "learning_rate": 7.757826887661142e-06, "loss": 1.5723, "step": 3670 }, { "epoch": 2.54, "learning_rate": 7.642725598526703e-06, "loss": 1.5547, "step": 3680 }, { "epoch": 2.55, "learning_rate": 7.527624309392266e-06, "loss": 1.5715, "step": 3690 }, { "epoch": 2.56, "learning_rate": 7.412523020257827e-06, "loss": 1.5572, "step": 3700 }, { "epoch": 2.56, "learning_rate": 7.297421731123388e-06, "loss": 1.5453, "step": 3710 }, { "epoch": 2.57, "learning_rate": 7.1823204419889505e-06, "loss": 1.5311, "step": 3720 }, { "epoch": 2.58, "learning_rate": 7.067219152854512e-06, "loss": 1.5624, "step": 3730 }, { "epoch": 2.58, "learning_rate": 6.9521178637200746e-06, "loss": 1.5522, "step": 3740 }, { "epoch": 2.59, "learning_rate": 6.837016574585636e-06, "loss": 1.5861, "step": 3750 }, { "epoch": 2.6, "learning_rate": 6.721915285451197e-06, "loss": 1.5685, "step": 3760 }, { "epoch": 2.6, "learning_rate": 6.6068139963167585e-06, "loss": 1.5779, "step": 3770 }, { "epoch": 2.61, "learning_rate": 6.491712707182321e-06, "loss": 1.5882, "step": 3780 }, { "epoch": 2.62, "learning_rate": 6.3766114180478825e-06, "loss": 1.5875, "step": 3790 }, { "epoch": 2.62, "learning_rate": 6.261510128913445e-06, "loss": 1.6015, "step": 3800 }, { "epoch": 2.63, "learning_rate": 6.146408839779006e-06, "loss": 1.5859, "step": 3810 }, { "epoch": 2.64, "learning_rate": 6.031307550644567e-06, "loss": 1.5485, "step": 3820 }, { "epoch": 2.65, "learning_rate": 5.91620626151013e-06, "loss": 1.5688, "step": 3830 }, { "epoch": 2.65, "learning_rate": 5.8011049723756905e-06, "loss": 1.5561, "step": 3840 }, { "epoch": 2.66, "learning_rate": 5.686003683241253e-06, "loss": 1.5852, "step": 3850 }, { "epoch": 2.67, "learning_rate": 5.5709023941068146e-06, "loss": 1.6032, "step": 3860 }, { "epoch": 2.67, "learning_rate": 5.455801104972376e-06, "loss": 1.5734, "step": 3870 }, { "epoch": 2.68, "learning_rate": 5.340699815837938e-06, "loss": 1.6035, "step": 3880 }, { "epoch": 2.69, "learning_rate": 5.225598526703499e-06, "loss": 1.5613, "step": 3890 }, { "epoch": 2.69, "learning_rate": 5.110497237569061e-06, "loss": 1.5639, "step": 3900 }, { "epoch": 2.7, "learning_rate": 4.9953959484346225e-06, "loss": 1.6206, "step": 3910 }, { "epoch": 2.71, "learning_rate": 4.880294659300184e-06, "loss": 1.5319, "step": 3920 }, { "epoch": 2.71, "learning_rate": 4.7651933701657466e-06, "loss": 1.5747, "step": 3930 }, { "epoch": 2.72, "learning_rate": 4.650092081031307e-06, "loss": 1.5648, "step": 3940 }, { "epoch": 2.73, "learning_rate": 4.53499079189687e-06, "loss": 1.5794, "step": 3950 }, { "epoch": 2.73, "learning_rate": 4.419889502762431e-06, "loss": 1.6074, "step": 3960 }, { "epoch": 2.74, "learning_rate": 4.304788213627993e-06, "loss": 1.5554, "step": 3970 }, { "epoch": 2.75, "learning_rate": 4.1896869244935545e-06, "loss": 1.5737, "step": 3980 }, { "epoch": 2.76, "learning_rate": 4.074585635359116e-06, "loss": 1.6078, "step": 3990 }, { "epoch": 2.76, "learning_rate": 3.959484346224679e-06, "loss": 1.562, "step": 4000 } ], "logging_steps": 10, "max_steps": 4344, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.527151250462474e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }