{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9873039581777445, "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": 4.98755290017426e-05, "loss": 1.789, "step": 10 }, { "epoch": 0.01, "learning_rate": 4.975105800348519e-05, "loss": 1.7868, "step": 20 }, { "epoch": 0.02, "learning_rate": 4.962658700522779e-05, "loss": 1.7871, "step": 30 }, { "epoch": 0.03, "learning_rate": 4.9502116006970375e-05, "loss": 1.7554, "step": 40 }, { "epoch": 0.04, "learning_rate": 4.937764500871298e-05, "loss": 1.6774, "step": 50 }, { "epoch": 0.04, "learning_rate": 4.9253174010455565e-05, "loss": 1.7076, "step": 60 }, { "epoch": 0.05, "learning_rate": 4.912870301219816e-05, "loss": 1.6946, "step": 70 }, { "epoch": 0.06, "learning_rate": 4.9004232013940755e-05, "loss": 1.7129, "step": 80 }, { "epoch": 0.07, "learning_rate": 4.887976101568335e-05, "loss": 1.7002, "step": 90 }, { "epoch": 0.07, "learning_rate": 4.8755290017425944e-05, "loss": 1.7244, "step": 100 }, { "epoch": 0.08, "learning_rate": 4.863081901916854e-05, "loss": 1.7187, "step": 110 }, { "epoch": 0.09, "learning_rate": 4.850634802091113e-05, "loss": 1.7207, "step": 120 }, { "epoch": 0.1, "learning_rate": 4.838187702265373e-05, "loss": 1.7349, "step": 130 }, { "epoch": 0.1, "learning_rate": 4.825740602439632e-05, "loss": 1.7021, "step": 140 }, { "epoch": 0.11, "learning_rate": 4.813293502613891e-05, "loss": 1.6658, "step": 150 }, { "epoch": 0.12, "learning_rate": 4.800846402788151e-05, "loss": 1.6851, "step": 160 }, { "epoch": 0.13, "learning_rate": 4.78839930296241e-05, "loss": 1.6748, "step": 170 }, { "epoch": 0.13, "learning_rate": 4.7759522031366697e-05, "loss": 1.6882, "step": 180 }, { "epoch": 0.14, "learning_rate": 4.763505103310929e-05, "loss": 1.6568, "step": 190 }, { "epoch": 0.15, "learning_rate": 4.751058003485188e-05, "loss": 1.7129, "step": 200 }, { "epoch": 0.16, "learning_rate": 4.738610903659448e-05, "loss": 1.71, "step": 210 }, { "epoch": 0.16, "learning_rate": 4.726163803833707e-05, "loss": 1.728, "step": 220 }, { "epoch": 0.17, "learning_rate": 4.7137167040079664e-05, "loss": 1.7038, "step": 230 }, { "epoch": 0.18, "learning_rate": 4.701269604182226e-05, "loss": 1.6916, "step": 240 }, { "epoch": 0.19, "learning_rate": 4.6888225043564854e-05, "loss": 1.6826, "step": 250 }, { "epoch": 0.19, "learning_rate": 4.676375404530744e-05, "loss": 1.7249, "step": 260 }, { "epoch": 0.2, "learning_rate": 4.6639283047050044e-05, "loss": 1.6766, "step": 270 }, { "epoch": 0.21, "learning_rate": 4.651481204879263e-05, "loss": 1.6795, "step": 280 }, { "epoch": 0.22, "learning_rate": 4.6390341050535227e-05, "loss": 1.7304, "step": 290 }, { "epoch": 0.22, "learning_rate": 4.626587005227782e-05, "loss": 1.747, "step": 300 }, { "epoch": 0.23, "learning_rate": 4.6141399054020416e-05, "loss": 1.6345, "step": 310 }, { "epoch": 0.24, "learning_rate": 4.601692805576301e-05, "loss": 1.6762, "step": 320 }, { "epoch": 0.25, "learning_rate": 4.5892457057505606e-05, "loss": 1.6601, "step": 330 }, { "epoch": 0.25, "learning_rate": 4.5767986059248194e-05, "loss": 1.6635, "step": 340 }, { "epoch": 0.26, "learning_rate": 4.5643515060990796e-05, "loss": 1.6952, "step": 350 }, { "epoch": 0.27, "learning_rate": 4.5519044062733384e-05, "loss": 1.683, "step": 360 }, { "epoch": 0.28, "learning_rate": 4.539457306447598e-05, "loss": 1.657, "step": 370 }, { "epoch": 0.28, "learning_rate": 4.5270102066218574e-05, "loss": 1.6471, "step": 380 }, { "epoch": 0.29, "learning_rate": 4.514563106796117e-05, "loss": 1.6852, "step": 390 }, { "epoch": 0.3, "learning_rate": 4.502116006970376e-05, "loss": 1.6737, "step": 400 }, { "epoch": 0.31, "learning_rate": 4.489668907144636e-05, "loss": 1.6938, "step": 410 }, { "epoch": 0.31, "learning_rate": 4.4772218073188946e-05, "loss": 1.6716, "step": 420 }, { "epoch": 0.32, "learning_rate": 4.464774707493155e-05, "loss": 1.6678, "step": 430 }, { "epoch": 0.33, "learning_rate": 4.4523276076674136e-05, "loss": 1.6229, "step": 440 }, { "epoch": 0.34, "learning_rate": 4.439880507841673e-05, "loss": 1.659, "step": 450 }, { "epoch": 0.34, "learning_rate": 4.4274334080159326e-05, "loss": 1.6842, "step": 460 }, { "epoch": 0.35, "learning_rate": 4.414986308190192e-05, "loss": 1.6751, "step": 470 }, { "epoch": 0.36, "learning_rate": 4.4025392083644516e-05, "loss": 1.6745, "step": 480 }, { "epoch": 0.37, "learning_rate": 4.390092108538711e-05, "loss": 1.6791, "step": 490 }, { "epoch": 0.37, "learning_rate": 4.37764500871297e-05, "loss": 1.6958, "step": 500 }, { "epoch": 0.38, "learning_rate": 4.36519790888723e-05, "loss": 1.6891, "step": 510 }, { "epoch": 0.39, "learning_rate": 4.352750809061489e-05, "loss": 1.6732, "step": 520 }, { "epoch": 0.4, "learning_rate": 4.340303709235748e-05, "loss": 1.6965, "step": 530 }, { "epoch": 0.4, "learning_rate": 4.327856609410008e-05, "loss": 1.6567, "step": 540 }, { "epoch": 0.41, "learning_rate": 4.315409509584267e-05, "loss": 1.6773, "step": 550 }, { "epoch": 0.42, "learning_rate": 4.302962409758526e-05, "loss": 1.7101, "step": 560 }, { "epoch": 0.43, "learning_rate": 4.290515309932786e-05, "loss": 1.6942, "step": 570 }, { "epoch": 0.43, "learning_rate": 4.278068210107045e-05, "loss": 1.6925, "step": 580 }, { "epoch": 0.44, "learning_rate": 4.2656211102813046e-05, "loss": 1.6626, "step": 590 }, { "epoch": 0.45, "learning_rate": 4.253174010455564e-05, "loss": 1.7122, "step": 600 }, { "epoch": 0.46, "learning_rate": 4.2407269106298235e-05, "loss": 1.6773, "step": 610 }, { "epoch": 0.46, "learning_rate": 4.228279810804083e-05, "loss": 1.6429, "step": 620 }, { "epoch": 0.47, "learning_rate": 4.2158327109783425e-05, "loss": 1.6471, "step": 630 }, { "epoch": 0.48, "learning_rate": 4.203385611152601e-05, "loss": 1.6818, "step": 640 }, { "epoch": 0.49, "learning_rate": 4.1909385113268615e-05, "loss": 1.6826, "step": 650 }, { "epoch": 0.49, "learning_rate": 4.17849141150112e-05, "loss": 1.6817, "step": 660 }, { "epoch": 0.5, "learning_rate": 4.16604431167538e-05, "loss": 1.7324, "step": 670 }, { "epoch": 0.51, "learning_rate": 4.153597211849639e-05, "loss": 1.7007, "step": 680 }, { "epoch": 0.52, "learning_rate": 4.141150112023899e-05, "loss": 1.6553, "step": 690 }, { "epoch": 0.52, "learning_rate": 4.128703012198158e-05, "loss": 1.6715, "step": 700 }, { "epoch": 0.53, "learning_rate": 4.116255912372418e-05, "loss": 1.6409, "step": 710 }, { "epoch": 0.54, "learning_rate": 4.1038088125466765e-05, "loss": 1.7091, "step": 720 }, { "epoch": 0.55, "learning_rate": 4.091361712720937e-05, "loss": 1.7258, "step": 730 }, { "epoch": 0.55, "learning_rate": 4.0789146128951955e-05, "loss": 1.6653, "step": 740 }, { "epoch": 0.56, "learning_rate": 4.066467513069455e-05, "loss": 1.7244, "step": 750 }, { "epoch": 0.57, "learning_rate": 4.0540204132437145e-05, "loss": 1.6709, "step": 760 }, { "epoch": 0.58, "learning_rate": 4.041573313417974e-05, "loss": 1.6641, "step": 770 }, { "epoch": 0.58, "learning_rate": 4.029126213592233e-05, "loss": 1.6804, "step": 780 }, { "epoch": 0.59, "learning_rate": 4.016679113766493e-05, "loss": 1.6868, "step": 790 }, { "epoch": 0.6, "learning_rate": 4.004232013940752e-05, "loss": 1.6939, "step": 800 }, { "epoch": 0.6, "learning_rate": 3.991784914115011e-05, "loss": 1.6804, "step": 810 }, { "epoch": 0.61, "learning_rate": 3.979337814289271e-05, "loss": 1.6861, "step": 820 }, { "epoch": 0.62, "learning_rate": 3.96689071446353e-05, "loss": 1.6643, "step": 830 }, { "epoch": 0.63, "learning_rate": 3.95444361463779e-05, "loss": 1.6765, "step": 840 }, { "epoch": 0.63, "learning_rate": 3.941996514812049e-05, "loss": 1.6819, "step": 850 }, { "epoch": 0.64, "learning_rate": 3.929549414986308e-05, "loss": 1.6677, "step": 860 }, { "epoch": 0.65, "learning_rate": 3.917102315160568e-05, "loss": 1.6847, "step": 870 }, { "epoch": 0.66, "learning_rate": 3.904655215334827e-05, "loss": 1.608, "step": 880 }, { "epoch": 0.66, "learning_rate": 3.8922081155090865e-05, "loss": 1.6625, "step": 890 }, { "epoch": 0.67, "learning_rate": 3.879761015683346e-05, "loss": 1.6619, "step": 900 }, { "epoch": 0.68, "learning_rate": 3.8673139158576054e-05, "loss": 1.7024, "step": 910 }, { "epoch": 0.69, "learning_rate": 3.854866816031865e-05, "loss": 1.73, "step": 920 }, { "epoch": 0.69, "learning_rate": 3.8424197162061244e-05, "loss": 1.6909, "step": 930 }, { "epoch": 0.7, "learning_rate": 3.829972616380383e-05, "loss": 1.7046, "step": 940 }, { "epoch": 0.71, "learning_rate": 3.8175255165546434e-05, "loss": 1.666, "step": 950 }, { "epoch": 0.72, "learning_rate": 3.805078416728902e-05, "loss": 1.6979, "step": 960 }, { "epoch": 0.72, "learning_rate": 3.792631316903162e-05, "loss": 1.6619, "step": 970 }, { "epoch": 0.73, "learning_rate": 3.780184217077421e-05, "loss": 1.7073, "step": 980 }, { "epoch": 0.74, "learning_rate": 3.7677371172516806e-05, "loss": 1.6487, "step": 990 }, { "epoch": 0.75, "learning_rate": 3.7552900174259395e-05, "loss": 1.6706, "step": 1000 }, { "epoch": 0.75, "learning_rate": 3.7428429176001996e-05, "loss": 1.7042, "step": 1010 }, { "epoch": 0.76, "learning_rate": 3.7303958177744584e-05, "loss": 1.6835, "step": 1020 }, { "epoch": 0.77, "learning_rate": 3.717948717948718e-05, "loss": 1.668, "step": 1030 }, { "epoch": 0.78, "learning_rate": 3.7055016181229774e-05, "loss": 1.6358, "step": 1040 }, { "epoch": 0.78, "learning_rate": 3.693054518297237e-05, "loss": 1.6796, "step": 1050 }, { "epoch": 0.79, "learning_rate": 3.6806074184714964e-05, "loss": 1.6369, "step": 1060 }, { "epoch": 0.8, "learning_rate": 3.668160318645756e-05, "loss": 1.6751, "step": 1070 }, { "epoch": 0.81, "learning_rate": 3.655713218820015e-05, "loss": 1.7043, "step": 1080 }, { "epoch": 0.81, "learning_rate": 3.643266118994275e-05, "loss": 1.7065, "step": 1090 }, { "epoch": 0.82, "learning_rate": 3.6308190191685337e-05, "loss": 1.6562, "step": 1100 }, { "epoch": 0.83, "learning_rate": 3.618371919342793e-05, "loss": 1.6445, "step": 1110 }, { "epoch": 0.84, "learning_rate": 3.6059248195170526e-05, "loss": 1.6906, "step": 1120 }, { "epoch": 0.84, "learning_rate": 3.593477719691312e-05, "loss": 1.6744, "step": 1130 }, { "epoch": 0.85, "learning_rate": 3.5810306198655716e-05, "loss": 1.6557, "step": 1140 }, { "epoch": 0.86, "learning_rate": 3.568583520039831e-05, "loss": 1.6482, "step": 1150 }, { "epoch": 0.87, "learning_rate": 3.55613642021409e-05, "loss": 1.6418, "step": 1160 }, { "epoch": 0.87, "learning_rate": 3.54368932038835e-05, "loss": 1.6888, "step": 1170 }, { "epoch": 0.88, "learning_rate": 3.531242220562609e-05, "loss": 1.7157, "step": 1180 }, { "epoch": 0.89, "learning_rate": 3.5187951207368684e-05, "loss": 1.6781, "step": 1190 }, { "epoch": 0.9, "learning_rate": 3.506348020911128e-05, "loss": 1.705, "step": 1200 }, { "epoch": 0.9, "learning_rate": 3.493900921085387e-05, "loss": 1.6837, "step": 1210 }, { "epoch": 0.91, "learning_rate": 3.481453821259646e-05, "loss": 1.7337, "step": 1220 }, { "epoch": 0.92, "learning_rate": 3.469006721433906e-05, "loss": 1.6492, "step": 1230 }, { "epoch": 0.93, "learning_rate": 3.456559621608165e-05, "loss": 1.7011, "step": 1240 }, { "epoch": 0.93, "learning_rate": 3.4441125217824246e-05, "loss": 1.6501, "step": 1250 }, { "epoch": 0.94, "learning_rate": 3.431665421956684e-05, "loss": 1.6614, "step": 1260 }, { "epoch": 0.95, "learning_rate": 3.4192183221309436e-05, "loss": 1.7155, "step": 1270 }, { "epoch": 0.96, "learning_rate": 3.406771222305203e-05, "loss": 1.6906, "step": 1280 }, { "epoch": 0.96, "learning_rate": 3.3943241224794625e-05, "loss": 1.6602, "step": 1290 }, { "epoch": 0.97, "learning_rate": 3.3818770226537214e-05, "loss": 1.66, "step": 1300 }, { "epoch": 0.98, "learning_rate": 3.3694299228279815e-05, "loss": 1.7053, "step": 1310 }, { "epoch": 0.99, "learning_rate": 3.35698282300224e-05, "loss": 1.6676, "step": 1320 }, { "epoch": 0.99, "learning_rate": 3.3445357231765e-05, "loss": 1.6714, "step": 1330 }, { "epoch": 1.0, "learning_rate": 3.332088623350759e-05, "loss": 1.6601, "step": 1340 }, { "epoch": 1.01, "learning_rate": 3.319641523525019e-05, "loss": 1.6518, "step": 1350 }, { "epoch": 1.02, "learning_rate": 3.307194423699278e-05, "loss": 1.6621, "step": 1360 }, { "epoch": 1.02, "learning_rate": 3.294747323873538e-05, "loss": 1.6654, "step": 1370 }, { "epoch": 1.03, "learning_rate": 3.2823002240477966e-05, "loss": 1.6664, "step": 1380 }, { "epoch": 1.04, "learning_rate": 3.269853124222057e-05, "loss": 1.6809, "step": 1390 }, { "epoch": 1.05, "learning_rate": 3.2574060243963156e-05, "loss": 1.6632, "step": 1400 }, { "epoch": 1.05, "learning_rate": 3.244958924570575e-05, "loss": 1.6527, "step": 1410 }, { "epoch": 1.06, "learning_rate": 3.2325118247448345e-05, "loss": 1.6937, "step": 1420 }, { "epoch": 1.07, "learning_rate": 3.220064724919094e-05, "loss": 1.6931, "step": 1430 }, { "epoch": 1.08, "learning_rate": 3.2076176250933535e-05, "loss": 1.6712, "step": 1440 }, { "epoch": 1.08, "learning_rate": 3.195170525267613e-05, "loss": 1.6707, "step": 1450 }, { "epoch": 1.09, "learning_rate": 3.182723425441872e-05, "loss": 1.6674, "step": 1460 }, { "epoch": 1.1, "learning_rate": 3.170276325616132e-05, "loss": 1.7057, "step": 1470 }, { "epoch": 1.11, "learning_rate": 3.157829225790391e-05, "loss": 1.7014, "step": 1480 }, { "epoch": 1.11, "learning_rate": 3.14538212596465e-05, "loss": 1.6852, "step": 1490 }, { "epoch": 1.12, "learning_rate": 3.13293502613891e-05, "loss": 1.6425, "step": 1500 }, { "epoch": 1.13, "learning_rate": 3.120487926313169e-05, "loss": 1.6973, "step": 1510 }, { "epoch": 1.14, "learning_rate": 3.108040826487428e-05, "loss": 1.6973, "step": 1520 }, { "epoch": 1.14, "learning_rate": 3.095593726661688e-05, "loss": 1.6713, "step": 1530 }, { "epoch": 1.15, "learning_rate": 3.083146626835947e-05, "loss": 1.7021, "step": 1540 }, { "epoch": 1.16, "learning_rate": 3.0706995270102065e-05, "loss": 1.6646, "step": 1550 }, { "epoch": 1.17, "learning_rate": 3.058252427184466e-05, "loss": 1.7032, "step": 1560 }, { "epoch": 1.17, "learning_rate": 3.0458053273587255e-05, "loss": 1.6848, "step": 1570 }, { "epoch": 1.18, "learning_rate": 3.0333582275329846e-05, "loss": 1.6337, "step": 1580 }, { "epoch": 1.19, "learning_rate": 3.0209111277072444e-05, "loss": 1.6587, "step": 1590 }, { "epoch": 1.19, "learning_rate": 3.0084640278815036e-05, "loss": 1.6244, "step": 1600 }, { "epoch": 1.2, "learning_rate": 2.996016928055763e-05, "loss": 1.6825, "step": 1610 }, { "epoch": 1.21, "learning_rate": 2.9835698282300222e-05, "loss": 1.7051, "step": 1620 }, { "epoch": 1.22, "learning_rate": 2.971122728404282e-05, "loss": 1.6515, "step": 1630 }, { "epoch": 1.22, "learning_rate": 2.9586756285785412e-05, "loss": 1.6795, "step": 1640 }, { "epoch": 1.23, "learning_rate": 2.9462285287528007e-05, "loss": 1.6282, "step": 1650 }, { "epoch": 1.24, "learning_rate": 2.93378142892706e-05, "loss": 1.6598, "step": 1660 }, { "epoch": 1.25, "learning_rate": 2.9213343291013197e-05, "loss": 1.6899, "step": 1670 }, { "epoch": 1.25, "learning_rate": 2.9088872292755788e-05, "loss": 1.6548, "step": 1680 }, { "epoch": 1.26, "learning_rate": 2.8964401294498383e-05, "loss": 1.6493, "step": 1690 }, { "epoch": 1.27, "learning_rate": 2.8839930296240975e-05, "loss": 1.7092, "step": 1700 }, { "epoch": 1.28, "learning_rate": 2.8715459297983573e-05, "loss": 1.6715, "step": 1710 }, { "epoch": 1.28, "learning_rate": 2.859098829972616e-05, "loss": 1.6296, "step": 1720 }, { "epoch": 1.29, "learning_rate": 2.846651730146876e-05, "loss": 1.6878, "step": 1730 }, { "epoch": 1.3, "learning_rate": 2.834204630321135e-05, "loss": 1.6497, "step": 1740 }, { "epoch": 1.31, "learning_rate": 2.8217575304953945e-05, "loss": 1.6484, "step": 1750 }, { "epoch": 1.31, "learning_rate": 2.8093104306696544e-05, "loss": 1.6681, "step": 1760 }, { "epoch": 1.32, "learning_rate": 2.7968633308439135e-05, "loss": 1.6982, "step": 1770 }, { "epoch": 1.33, "learning_rate": 2.784416231018173e-05, "loss": 1.6472, "step": 1780 }, { "epoch": 1.34, "learning_rate": 2.771969131192432e-05, "loss": 1.6652, "step": 1790 }, { "epoch": 1.34, "learning_rate": 2.759522031366692e-05, "loss": 1.6703, "step": 1800 }, { "epoch": 1.35, "learning_rate": 2.747074931540951e-05, "loss": 1.665, "step": 1810 }, { "epoch": 1.36, "learning_rate": 2.7346278317152106e-05, "loss": 1.6412, "step": 1820 }, { "epoch": 1.37, "learning_rate": 2.7221807318894698e-05, "loss": 1.691, "step": 1830 }, { "epoch": 1.37, "learning_rate": 2.7097336320637296e-05, "loss": 1.6903, "step": 1840 }, { "epoch": 1.38, "learning_rate": 2.6972865322379887e-05, "loss": 1.6342, "step": 1850 }, { "epoch": 1.39, "learning_rate": 2.6848394324122482e-05, "loss": 1.6901, "step": 1860 }, { "epoch": 1.4, "learning_rate": 2.6723923325865074e-05, "loss": 1.6818, "step": 1870 }, { "epoch": 1.4, "learning_rate": 2.6599452327607672e-05, "loss": 1.6394, "step": 1880 }, { "epoch": 1.41, "learning_rate": 2.6474981329350264e-05, "loss": 1.672, "step": 1890 }, { "epoch": 1.42, "learning_rate": 2.635051033109286e-05, "loss": 1.6732, "step": 1900 }, { "epoch": 1.43, "learning_rate": 2.622603933283545e-05, "loss": 1.6735, "step": 1910 }, { "epoch": 1.43, "learning_rate": 2.6101568334578048e-05, "loss": 1.6763, "step": 1920 }, { "epoch": 1.44, "learning_rate": 2.597709733632064e-05, "loss": 1.6835, "step": 1930 }, { "epoch": 1.45, "learning_rate": 2.5852626338063234e-05, "loss": 1.7059, "step": 1940 }, { "epoch": 1.46, "learning_rate": 2.5728155339805826e-05, "loss": 1.7034, "step": 1950 }, { "epoch": 1.46, "learning_rate": 2.5603684341548424e-05, "loss": 1.656, "step": 1960 }, { "epoch": 1.47, "learning_rate": 2.5479213343291016e-05, "loss": 1.6794, "step": 1970 }, { "epoch": 1.48, "learning_rate": 2.535474234503361e-05, "loss": 1.6465, "step": 1980 }, { "epoch": 1.49, "learning_rate": 2.5230271346776202e-05, "loss": 1.6674, "step": 1990 }, { "epoch": 1.49, "learning_rate": 2.51058003485188e-05, "loss": 1.6629, "step": 2000 }, { "epoch": 1.5, "learning_rate": 2.498132935026139e-05, "loss": 1.6795, "step": 2010 }, { "epoch": 1.51, "learning_rate": 2.4856858352003983e-05, "loss": 1.6806, "step": 2020 }, { "epoch": 1.52, "learning_rate": 2.4732387353746578e-05, "loss": 1.6361, "step": 2030 }, { "epoch": 1.52, "learning_rate": 2.4607916355489173e-05, "loss": 1.6767, "step": 2040 }, { "epoch": 1.53, "learning_rate": 2.4483445357231764e-05, "loss": 1.6192, "step": 2050 }, { "epoch": 1.54, "learning_rate": 2.435897435897436e-05, "loss": 1.6863, "step": 2060 }, { "epoch": 1.55, "learning_rate": 2.4234503360716954e-05, "loss": 1.6547, "step": 2070 }, { "epoch": 1.55, "learning_rate": 2.411003236245955e-05, "loss": 1.6817, "step": 2080 }, { "epoch": 1.56, "learning_rate": 2.398556136420214e-05, "loss": 1.6606, "step": 2090 }, { "epoch": 1.57, "learning_rate": 2.3861090365944735e-05, "loss": 1.6661, "step": 2100 }, { "epoch": 1.58, "learning_rate": 2.373661936768733e-05, "loss": 1.6896, "step": 2110 }, { "epoch": 1.58, "learning_rate": 2.3612148369429922e-05, "loss": 1.6468, "step": 2120 }, { "epoch": 1.59, "learning_rate": 2.3487677371172517e-05, "loss": 1.6631, "step": 2130 }, { "epoch": 1.6, "learning_rate": 2.336320637291511e-05, "loss": 1.6272, "step": 2140 }, { "epoch": 1.61, "learning_rate": 2.3238735374657706e-05, "loss": 1.6793, "step": 2150 }, { "epoch": 1.61, "learning_rate": 2.3114264376400298e-05, "loss": 1.641, "step": 2160 }, { "epoch": 1.62, "learning_rate": 2.2989793378142893e-05, "loss": 1.6789, "step": 2170 }, { "epoch": 1.63, "learning_rate": 2.2865322379885488e-05, "loss": 1.6769, "step": 2180 }, { "epoch": 1.64, "learning_rate": 2.2740851381628083e-05, "loss": 1.6422, "step": 2190 }, { "epoch": 1.64, "learning_rate": 2.2616380383370674e-05, "loss": 1.661, "step": 2200 }, { "epoch": 1.65, "learning_rate": 2.249190938511327e-05, "loss": 1.6496, "step": 2210 }, { "epoch": 1.66, "learning_rate": 2.2367438386855864e-05, "loss": 1.6844, "step": 2220 }, { "epoch": 1.67, "learning_rate": 2.2242967388598455e-05, "loss": 1.6807, "step": 2230 }, { "epoch": 1.67, "learning_rate": 2.211849639034105e-05, "loss": 1.6609, "step": 2240 }, { "epoch": 1.68, "learning_rate": 2.1994025392083645e-05, "loss": 1.6628, "step": 2250 }, { "epoch": 1.69, "learning_rate": 2.186955439382624e-05, "loss": 1.6671, "step": 2260 }, { "epoch": 1.7, "learning_rate": 2.174508339556883e-05, "loss": 1.6524, "step": 2270 }, { "epoch": 1.7, "learning_rate": 2.1620612397311426e-05, "loss": 1.7217, "step": 2280 }, { "epoch": 1.71, "learning_rate": 2.149614139905402e-05, "loss": 1.6693, "step": 2290 }, { "epoch": 1.72, "learning_rate": 2.1371670400796616e-05, "loss": 1.634, "step": 2300 }, { "epoch": 1.73, "learning_rate": 2.1247199402539207e-05, "loss": 1.6965, "step": 2310 }, { "epoch": 1.73, "learning_rate": 2.1122728404281802e-05, "loss": 1.6922, "step": 2320 }, { "epoch": 1.74, "learning_rate": 2.0998257406024397e-05, "loss": 1.6451, "step": 2330 }, { "epoch": 1.75, "learning_rate": 2.0873786407766992e-05, "loss": 1.6364, "step": 2340 }, { "epoch": 1.76, "learning_rate": 2.0749315409509583e-05, "loss": 1.6811, "step": 2350 }, { "epoch": 1.76, "learning_rate": 2.062484441125218e-05, "loss": 1.6723, "step": 2360 }, { "epoch": 1.77, "learning_rate": 2.0500373412994773e-05, "loss": 1.6712, "step": 2370 }, { "epoch": 1.78, "learning_rate": 2.0375902414737365e-05, "loss": 1.6953, "step": 2380 }, { "epoch": 1.78, "learning_rate": 2.025143141647996e-05, "loss": 1.6718, "step": 2390 }, { "epoch": 1.79, "learning_rate": 2.0126960418222554e-05, "loss": 1.655, "step": 2400 }, { "epoch": 1.8, "learning_rate": 2.000248941996515e-05, "loss": 1.6761, "step": 2410 }, { "epoch": 1.81, "learning_rate": 1.987801842170774e-05, "loss": 1.658, "step": 2420 }, { "epoch": 1.81, "learning_rate": 1.9753547423450336e-05, "loss": 1.6194, "step": 2430 }, { "epoch": 1.82, "learning_rate": 1.962907642519293e-05, "loss": 1.6643, "step": 2440 }, { "epoch": 1.83, "learning_rate": 1.9504605426935525e-05, "loss": 1.6555, "step": 2450 }, { "epoch": 1.84, "learning_rate": 1.9380134428678117e-05, "loss": 1.6388, "step": 2460 }, { "epoch": 1.84, "learning_rate": 1.9255663430420712e-05, "loss": 1.6469, "step": 2470 }, { "epoch": 1.85, "learning_rate": 1.9131192432163307e-05, "loss": 1.6517, "step": 2480 }, { "epoch": 1.86, "learning_rate": 1.9006721433905898e-05, "loss": 1.6792, "step": 2490 }, { "epoch": 1.87, "learning_rate": 1.8882250435648493e-05, "loss": 1.6577, "step": 2500 }, { "epoch": 1.87, "learning_rate": 1.8757779437391088e-05, "loss": 1.673, "step": 2510 }, { "epoch": 1.88, "learning_rate": 1.8633308439133683e-05, "loss": 1.6155, "step": 2520 }, { "epoch": 1.89, "learning_rate": 1.8508837440876274e-05, "loss": 1.709, "step": 2530 }, { "epoch": 1.9, "learning_rate": 1.838436644261887e-05, "loss": 1.6798, "step": 2540 }, { "epoch": 1.9, "learning_rate": 1.8259895444361464e-05, "loss": 1.7004, "step": 2550 }, { "epoch": 1.91, "learning_rate": 1.813542444610406e-05, "loss": 1.6927, "step": 2560 }, { "epoch": 1.92, "learning_rate": 1.801095344784665e-05, "loss": 1.6998, "step": 2570 }, { "epoch": 1.93, "learning_rate": 1.7886482449589245e-05, "loss": 1.6848, "step": 2580 }, { "epoch": 1.93, "learning_rate": 1.776201145133184e-05, "loss": 1.6526, "step": 2590 }, { "epoch": 1.94, "learning_rate": 1.763754045307443e-05, "loss": 1.6384, "step": 2600 }, { "epoch": 1.95, "learning_rate": 1.7513069454817026e-05, "loss": 1.6833, "step": 2610 }, { "epoch": 1.96, "learning_rate": 1.7388598456559625e-05, "loss": 1.6854, "step": 2620 }, { "epoch": 1.96, "learning_rate": 1.7264127458302216e-05, "loss": 1.6871, "step": 2630 }, { "epoch": 1.97, "learning_rate": 1.713965646004481e-05, "loss": 1.688, "step": 2640 }, { "epoch": 1.98, "learning_rate": 1.7015185461787406e-05, "loss": 1.7067, "step": 2650 }, { "epoch": 1.99, "learning_rate": 1.689071446353e-05, "loss": 1.6734, "step": 2660 }, { "epoch": 1.99, "learning_rate": 1.6766243465272592e-05, "loss": 1.6537, "step": 2670 }, { "epoch": 2.0, "learning_rate": 1.6641772467015187e-05, "loss": 1.6809, "step": 2680 }, { "epoch": 2.01, "learning_rate": 1.6517301468757782e-05, "loss": 1.6702, "step": 2690 }, { "epoch": 2.02, "learning_rate": 1.6392830470500377e-05, "loss": 1.6719, "step": 2700 }, { "epoch": 2.02, "learning_rate": 1.626835947224297e-05, "loss": 1.6825, "step": 2710 }, { "epoch": 2.03, "learning_rate": 1.6143888473985563e-05, "loss": 1.7066, "step": 2720 }, { "epoch": 2.04, "learning_rate": 1.6019417475728158e-05, "loss": 1.6579, "step": 2730 }, { "epoch": 2.05, "learning_rate": 1.5894946477470753e-05, "loss": 1.6634, "step": 2740 }, { "epoch": 2.05, "learning_rate": 1.5770475479213344e-05, "loss": 1.6612, "step": 2750 }, { "epoch": 2.06, "learning_rate": 1.564600448095594e-05, "loss": 1.6682, "step": 2760 }, { "epoch": 2.07, "learning_rate": 1.5521533482698534e-05, "loss": 1.6575, "step": 2770 }, { "epoch": 2.08, "learning_rate": 1.5397062484441126e-05, "loss": 1.6786, "step": 2780 }, { "epoch": 2.08, "learning_rate": 1.527259148618372e-05, "loss": 1.6397, "step": 2790 }, { "epoch": 2.09, "learning_rate": 1.5148120487926315e-05, "loss": 1.6569, "step": 2800 }, { "epoch": 2.1, "learning_rate": 1.5023649489668909e-05, "loss": 1.6597, "step": 2810 }, { "epoch": 2.11, "learning_rate": 1.4899178491411503e-05, "loss": 1.6825, "step": 2820 }, { "epoch": 2.11, "learning_rate": 1.4774707493154097e-05, "loss": 1.6471, "step": 2830 }, { "epoch": 2.12, "learning_rate": 1.4650236494896691e-05, "loss": 1.6394, "step": 2840 }, { "epoch": 2.13, "learning_rate": 1.4525765496639285e-05, "loss": 1.6551, "step": 2850 }, { "epoch": 2.14, "learning_rate": 1.440129449838188e-05, "loss": 1.6614, "step": 2860 }, { "epoch": 2.14, "learning_rate": 1.4276823500124473e-05, "loss": 1.6617, "step": 2870 }, { "epoch": 2.15, "learning_rate": 1.4152352501867066e-05, "loss": 1.6885, "step": 2880 }, { "epoch": 2.16, "learning_rate": 1.402788150360966e-05, "loss": 1.6814, "step": 2890 }, { "epoch": 2.17, "learning_rate": 1.3903410505352254e-05, "loss": 1.6264, "step": 2900 }, { "epoch": 2.17, "learning_rate": 1.3778939507094849e-05, "loss": 1.6935, "step": 2910 }, { "epoch": 2.18, "learning_rate": 1.3654468508837442e-05, "loss": 1.6797, "step": 2920 }, { "epoch": 2.19, "learning_rate": 1.3529997510580037e-05, "loss": 1.6546, "step": 2930 }, { "epoch": 2.2, "learning_rate": 1.340552651232263e-05, "loss": 1.6493, "step": 2940 }, { "epoch": 2.2, "learning_rate": 1.3281055514065225e-05, "loss": 1.6395, "step": 2950 }, { "epoch": 2.21, "learning_rate": 1.3156584515807818e-05, "loss": 1.6785, "step": 2960 }, { "epoch": 2.22, "learning_rate": 1.3032113517550413e-05, "loss": 1.6671, "step": 2970 }, { "epoch": 2.23, "learning_rate": 1.2907642519293006e-05, "loss": 1.6423, "step": 2980 }, { "epoch": 2.23, "learning_rate": 1.27831715210356e-05, "loss": 1.6864, "step": 2990 }, { "epoch": 2.24, "learning_rate": 1.2658700522778194e-05, "loss": 1.6775, "step": 3000 }, { "epoch": 2.25, "learning_rate": 1.2534229524520787e-05, "loss": 1.677, "step": 3010 }, { "epoch": 2.26, "learning_rate": 1.240975852626338e-05, "loss": 1.6594, "step": 3020 }, { "epoch": 2.26, "learning_rate": 1.2285287528005974e-05, "loss": 1.6899, "step": 3030 }, { "epoch": 2.27, "learning_rate": 1.2160816529748569e-05, "loss": 1.641, "step": 3040 }, { "epoch": 2.28, "learning_rate": 1.2036345531491162e-05, "loss": 1.6345, "step": 3050 }, { "epoch": 2.29, "learning_rate": 1.1911874533233758e-05, "loss": 1.6668, "step": 3060 }, { "epoch": 2.29, "learning_rate": 1.1787403534976351e-05, "loss": 1.6614, "step": 3070 }, { "epoch": 2.3, "learning_rate": 1.1662932536718946e-05, "loss": 1.7066, "step": 3080 }, { "epoch": 2.31, "learning_rate": 1.153846153846154e-05, "loss": 1.6707, "step": 3090 }, { "epoch": 2.32, "learning_rate": 1.1413990540204134e-05, "loss": 1.6684, "step": 3100 }, { "epoch": 2.32, "learning_rate": 1.1289519541946728e-05, "loss": 1.6838, "step": 3110 }, { "epoch": 2.33, "learning_rate": 1.116504854368932e-05, "loss": 1.663, "step": 3120 }, { "epoch": 2.34, "learning_rate": 1.1040577545431916e-05, "loss": 1.6635, "step": 3130 }, { "epoch": 2.35, "learning_rate": 1.0916106547174509e-05, "loss": 1.6491, "step": 3140 }, { "epoch": 2.35, "learning_rate": 1.0791635548917104e-05, "loss": 1.6566, "step": 3150 }, { "epoch": 2.36, "learning_rate": 1.0667164550659697e-05, "loss": 1.6981, "step": 3160 }, { "epoch": 2.37, "learning_rate": 1.0542693552402292e-05, "loss": 1.6573, "step": 3170 }, { "epoch": 2.37, "learning_rate": 1.0418222554144885e-05, "loss": 1.6907, "step": 3180 }, { "epoch": 2.38, "learning_rate": 1.029375155588748e-05, "loss": 1.6762, "step": 3190 }, { "epoch": 2.39, "learning_rate": 1.0169280557630073e-05, "loss": 1.649, "step": 3200 }, { "epoch": 2.4, "learning_rate": 1.0044809559372668e-05, "loss": 1.678, "step": 3210 }, { "epoch": 2.4, "learning_rate": 9.920338561115261e-06, "loss": 1.6419, "step": 3220 }, { "epoch": 2.41, "learning_rate": 9.795867562857854e-06, "loss": 1.6539, "step": 3230 }, { "epoch": 2.42, "learning_rate": 9.671396564600449e-06, "loss": 1.6939, "step": 3240 }, { "epoch": 2.43, "learning_rate": 9.546925566343042e-06, "loss": 1.6699, "step": 3250 }, { "epoch": 2.43, "learning_rate": 9.422454568085637e-06, "loss": 1.6442, "step": 3260 }, { "epoch": 2.44, "learning_rate": 9.29798356982823e-06, "loss": 1.6746, "step": 3270 }, { "epoch": 2.45, "learning_rate": 9.173512571570825e-06, "loss": 1.6676, "step": 3280 }, { "epoch": 2.46, "learning_rate": 9.049041573313418e-06, "loss": 1.6911, "step": 3290 }, { "epoch": 2.46, "learning_rate": 8.924570575056013e-06, "loss": 1.7072, "step": 3300 }, { "epoch": 2.47, "learning_rate": 8.800099576798606e-06, "loss": 1.6721, "step": 3310 }, { "epoch": 2.48, "learning_rate": 8.675628578541201e-06, "loss": 1.6278, "step": 3320 }, { "epoch": 2.49, "learning_rate": 8.551157580283794e-06, "loss": 1.6314, "step": 3330 }, { "epoch": 2.49, "learning_rate": 8.42668658202639e-06, "loss": 1.6696, "step": 3340 }, { "epoch": 2.5, "learning_rate": 8.302215583768982e-06, "loss": 1.6121, "step": 3350 }, { "epoch": 2.51, "learning_rate": 8.177744585511576e-06, "loss": 1.6726, "step": 3360 }, { "epoch": 2.52, "learning_rate": 8.05327358725417e-06, "loss": 1.6661, "step": 3370 }, { "epoch": 2.52, "learning_rate": 7.928802588996764e-06, "loss": 1.6523, "step": 3380 }, { "epoch": 2.53, "learning_rate": 7.804331590739359e-06, "loss": 1.6714, "step": 3390 }, { "epoch": 2.54, "learning_rate": 7.679860592481952e-06, "loss": 1.6351, "step": 3400 }, { "epoch": 2.55, "learning_rate": 7.555389594224547e-06, "loss": 1.6881, "step": 3410 }, { "epoch": 2.55, "learning_rate": 7.43091859596714e-06, "loss": 1.6949, "step": 3420 }, { "epoch": 2.56, "learning_rate": 7.306447597709734e-06, "loss": 1.6454, "step": 3430 }, { "epoch": 2.57, "learning_rate": 7.181976599452328e-06, "loss": 1.6394, "step": 3440 }, { "epoch": 2.58, "learning_rate": 7.057505601194922e-06, "loss": 1.6367, "step": 3450 }, { "epoch": 2.58, "learning_rate": 6.933034602937516e-06, "loss": 1.6482, "step": 3460 }, { "epoch": 2.59, "learning_rate": 6.80856360468011e-06, "loss": 1.6331, "step": 3470 }, { "epoch": 2.6, "learning_rate": 6.684092606422704e-06, "loss": 1.6791, "step": 3480 }, { "epoch": 2.61, "learning_rate": 6.559621608165298e-06, "loss": 1.6691, "step": 3490 }, { "epoch": 2.61, "learning_rate": 6.435150609907892e-06, "loss": 1.6751, "step": 3500 }, { "epoch": 2.62, "learning_rate": 6.310679611650486e-06, "loss": 1.6517, "step": 3510 }, { "epoch": 2.63, "learning_rate": 6.18620861339308e-06, "loss": 1.6628, "step": 3520 }, { "epoch": 2.64, "learning_rate": 6.061737615135674e-06, "loss": 1.6565, "step": 3530 }, { "epoch": 2.64, "learning_rate": 5.937266616878267e-06, "loss": 1.6631, "step": 3540 }, { "epoch": 2.65, "learning_rate": 5.812795618620861e-06, "loss": 1.6575, "step": 3550 }, { "epoch": 2.66, "learning_rate": 5.688324620363455e-06, "loss": 1.6385, "step": 3560 }, { "epoch": 2.67, "learning_rate": 5.563853622106049e-06, "loss": 1.6281, "step": 3570 }, { "epoch": 2.67, "learning_rate": 5.439382623848643e-06, "loss": 1.6831, "step": 3580 }, { "epoch": 2.68, "learning_rate": 5.314911625591237e-06, "loss": 1.6922, "step": 3590 }, { "epoch": 2.69, "learning_rate": 5.190440627333831e-06, "loss": 1.6478, "step": 3600 }, { "epoch": 2.7, "learning_rate": 5.065969629076425e-06, "loss": 1.6458, "step": 3610 }, { "epoch": 2.7, "learning_rate": 4.941498630819019e-06, "loss": 1.6797, "step": 3620 }, { "epoch": 2.71, "learning_rate": 4.817027632561613e-06, "loss": 1.6636, "step": 3630 }, { "epoch": 2.72, "learning_rate": 4.6925566343042074e-06, "loss": 1.6216, "step": 3640 }, { "epoch": 2.73, "learning_rate": 4.5680856360468015e-06, "loss": 1.6484, "step": 3650 }, { "epoch": 2.73, "learning_rate": 4.443614637789395e-06, "loss": 1.6447, "step": 3660 }, { "epoch": 2.74, "learning_rate": 4.319143639531989e-06, "loss": 1.5841, "step": 3670 }, { "epoch": 2.75, "learning_rate": 4.194672641274583e-06, "loss": 1.6766, "step": 3680 }, { "epoch": 2.76, "learning_rate": 4.070201643017177e-06, "loss": 1.646, "step": 3690 }, { "epoch": 2.76, "learning_rate": 3.945730644759771e-06, "loss": 1.676, "step": 3700 }, { "epoch": 2.77, "learning_rate": 3.821259646502365e-06, "loss": 1.6297, "step": 3710 }, { "epoch": 2.78, "learning_rate": 3.6967886482449596e-06, "loss": 1.6641, "step": 3720 }, { "epoch": 2.79, "learning_rate": 3.5723176499875532e-06, "loss": 1.675, "step": 3730 }, { "epoch": 2.79, "learning_rate": 3.4478466517301472e-06, "loss": 1.6388, "step": 3740 }, { "epoch": 2.8, "learning_rate": 3.3233756534727413e-06, "loss": 1.6747, "step": 3750 }, { "epoch": 2.81, "learning_rate": 3.1989046552153353e-06, "loss": 1.6584, "step": 3760 }, { "epoch": 2.82, "learning_rate": 3.074433656957929e-06, "loss": 1.6621, "step": 3770 }, { "epoch": 2.82, "learning_rate": 2.949962658700523e-06, "loss": 1.7047, "step": 3780 }, { "epoch": 2.83, "learning_rate": 2.825491660443117e-06, "loss": 1.6595, "step": 3790 }, { "epoch": 2.84, "learning_rate": 2.7010206621857105e-06, "loss": 1.629, "step": 3800 }, { "epoch": 2.85, "learning_rate": 2.5765496639283046e-06, "loss": 1.687, "step": 3810 }, { "epoch": 2.85, "learning_rate": 2.4520786656708986e-06, "loss": 1.6321, "step": 3820 }, { "epoch": 2.86, "learning_rate": 2.327607667413493e-06, "loss": 1.6649, "step": 3830 }, { "epoch": 2.87, "learning_rate": 2.203136669156087e-06, "loss": 1.6685, "step": 3840 }, { "epoch": 2.88, "learning_rate": 2.0786656708986807e-06, "loss": 1.6639, "step": 3850 }, { "epoch": 2.88, "learning_rate": 1.9541946726412747e-06, "loss": 1.6427, "step": 3860 }, { "epoch": 2.89, "learning_rate": 1.8297236743838687e-06, "loss": 1.6682, "step": 3870 }, { "epoch": 2.9, "learning_rate": 1.7052526761264627e-06, "loss": 1.6765, "step": 3880 }, { "epoch": 2.91, "learning_rate": 1.5807816778690567e-06, "loss": 1.6803, "step": 3890 }, { "epoch": 2.91, "learning_rate": 1.4563106796116506e-06, "loss": 1.6578, "step": 3900 }, { "epoch": 2.92, "learning_rate": 1.3318396813542446e-06, "loss": 1.6806, "step": 3910 }, { "epoch": 2.93, "learning_rate": 1.2073686830968386e-06, "loss": 1.6621, "step": 3920 }, { "epoch": 2.94, "learning_rate": 1.0828976848394324e-06, "loss": 1.6427, "step": 3930 }, { "epoch": 2.94, "learning_rate": 9.584266865820264e-07, "loss": 1.6748, "step": 3940 }, { "epoch": 2.95, "learning_rate": 8.339556883246204e-07, "loss": 1.6731, "step": 3950 }, { "epoch": 2.96, "learning_rate": 7.094846900672144e-07, "loss": 1.6514, "step": 3960 }, { "epoch": 2.96, "learning_rate": 5.850136918098084e-07, "loss": 1.6385, "step": 3970 }, { "epoch": 2.97, "learning_rate": 4.605426935524023e-07, "loss": 1.6492, "step": 3980 }, { "epoch": 2.98, "learning_rate": 3.360716952949963e-07, "loss": 1.6556, "step": 3990 }, { "epoch": 2.99, "learning_rate": 2.1160069703759027e-07, "loss": 1.6593, "step": 4000 } ], "logging_steps": 10, "max_steps": 4017, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 500, "total_flos": 2.52809928769536e+18, "train_batch_size": 4, "trial_name": null, "trial_params": null }