{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "eval_steps": 500, "global_step": 2205, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.022701475595913734, "grad_norm": 151.42454528808594, "learning_rate": 4.072398190045249e-07, "loss": 2.7892, "step": 10 }, { "epoch": 0.04540295119182747, "grad_norm": 123.80890655517578, "learning_rate": 8.597285067873304e-07, "loss": 2.7931, "step": 20 }, { "epoch": 0.0681044267877412, "grad_norm": 52.09438705444336, "learning_rate": 1.312217194570136e-06, "loss": 1.8545, "step": 30 }, { "epoch": 0.09080590238365494, "grad_norm": 28.316225051879883, "learning_rate": 1.7647058823529414e-06, "loss": 0.952, "step": 40 }, { "epoch": 0.11350737797956867, "grad_norm": 30.68117904663086, "learning_rate": 2.2171945701357465e-06, "loss": 0.5236, "step": 50 }, { "epoch": 0.1362088535754824, "grad_norm": 27.550668716430664, "learning_rate": 2.6696832579185524e-06, "loss": 0.4524, "step": 60 }, { "epoch": 0.15891032917139614, "grad_norm": 26.233320236206055, "learning_rate": 3.122171945701358e-06, "loss": 0.4041, "step": 70 }, { "epoch": 0.18161180476730987, "grad_norm": 33.194515228271484, "learning_rate": 3.5746606334841633e-06, "loss": 0.561, "step": 80 }, { "epoch": 0.2043132803632236, "grad_norm": 25.627391815185547, "learning_rate": 4.027149321266969e-06, "loss": 0.4058, "step": 90 }, { "epoch": 0.22701475595913734, "grad_norm": 30.34755516052246, "learning_rate": 4.479638009049775e-06, "loss": 0.4308, "step": 100 }, { "epoch": 0.24971623155505107, "grad_norm": 17.873517990112305, "learning_rate": 4.93212669683258e-06, "loss": 0.3573, "step": 110 }, { "epoch": 0.2724177071509648, "grad_norm": 21.3922119140625, "learning_rate": 5.384615384615385e-06, "loss": 0.4073, "step": 120 }, { "epoch": 0.29511918274687854, "grad_norm": 18.313337326049805, "learning_rate": 5.837104072398191e-06, "loss": 0.4094, "step": 130 }, { "epoch": 0.3178206583427923, "grad_norm": 17.395597457885742, "learning_rate": 6.2895927601809956e-06, "loss": 0.4447, "step": 140 }, { "epoch": 0.340522133938706, "grad_norm": 14.854466438293457, "learning_rate": 6.742081447963802e-06, "loss": 0.3943, "step": 150 }, { "epoch": 0.36322360953461974, "grad_norm": 15.115214347839355, "learning_rate": 7.1945701357466065e-06, "loss": 0.3596, "step": 160 }, { "epoch": 0.3859250851305335, "grad_norm": 15.582769393920898, "learning_rate": 7.647058823529411e-06, "loss": 0.3457, "step": 170 }, { "epoch": 0.4086265607264472, "grad_norm": 15.982388496398926, "learning_rate": 8.099547511312217e-06, "loss": 0.4043, "step": 180 }, { "epoch": 0.43132803632236094, "grad_norm": 18.891918182373047, "learning_rate": 8.552036199095024e-06, "loss": 0.4481, "step": 190 }, { "epoch": 0.4540295119182747, "grad_norm": 23.0708065032959, "learning_rate": 9.004524886877828e-06, "loss": 0.4184, "step": 200 }, { "epoch": 0.4767309875141884, "grad_norm": 19.941478729248047, "learning_rate": 9.457013574660635e-06, "loss": 0.4063, "step": 210 }, { "epoch": 0.49943246311010214, "grad_norm": 12.360922813415527, "learning_rate": 9.90950226244344e-06, "loss": 0.442, "step": 220 }, { "epoch": 0.5221339387060159, "grad_norm": 17.297880172729492, "learning_rate": 9.999598828026644e-06, "loss": 0.3473, "step": 230 }, { "epoch": 0.5448354143019296, "grad_norm": 9.550736427307129, "learning_rate": 9.997969177215449e-06, "loss": 0.371, "step": 240 }, { "epoch": 0.5675368898978433, "grad_norm": 12.789599418640137, "learning_rate": 9.995086382607064e-06, "loss": 0.2994, "step": 250 }, { "epoch": 0.5902383654937571, "grad_norm": 25.442951202392578, "learning_rate": 9.9909511670063e-06, "loss": 0.432, "step": 260 }, { "epoch": 0.6129398410896708, "grad_norm": 13.32232666015625, "learning_rate": 9.985564567238237e-06, "loss": 0.2707, "step": 270 }, { "epoch": 0.6356413166855845, "grad_norm": 10.177874565124512, "learning_rate": 9.978927933888254e-06, "loss": 0.4047, "step": 280 }, { "epoch": 0.6583427922814983, "grad_norm": 13.890095710754395, "learning_rate": 9.97104293096339e-06, "loss": 0.3528, "step": 290 }, { "epoch": 0.681044267877412, "grad_norm": 13.592388153076172, "learning_rate": 9.961911535475141e-06, "loss": 0.3083, "step": 300 }, { "epoch": 0.7037457434733257, "grad_norm": 12.367026329040527, "learning_rate": 9.951536036943753e-06, "loss": 0.2783, "step": 310 }, { "epoch": 0.7264472190692395, "grad_norm": 16.529279708862305, "learning_rate": 9.939919036824171e-06, "loss": 0.3797, "step": 320 }, { "epoch": 0.7491486946651532, "grad_norm": 10.961788177490234, "learning_rate": 9.92706344785377e-06, "loss": 0.4323, "step": 330 }, { "epoch": 0.771850170261067, "grad_norm": 6.987422943115234, "learning_rate": 9.912972493322058e-06, "loss": 0.3892, "step": 340 }, { "epoch": 0.7945516458569807, "grad_norm": 12.691405296325684, "learning_rate": 9.897649706262474e-06, "loss": 0.2924, "step": 350 }, { "epoch": 0.8172531214528944, "grad_norm": 12.293281555175781, "learning_rate": 9.881098928566574e-06, "loss": 0.3671, "step": 360 }, { "epoch": 0.8399545970488081, "grad_norm": 8.666092872619629, "learning_rate": 9.863324310020735e-06, "loss": 0.3381, "step": 370 }, { "epoch": 0.8626560726447219, "grad_norm": 18.942655563354492, "learning_rate": 9.844330307265684e-06, "loss": 0.3318, "step": 380 }, { "epoch": 0.8853575482406356, "grad_norm": 12.078003883361816, "learning_rate": 9.824121682679072e-06, "loss": 0.3401, "step": 390 }, { "epoch": 0.9080590238365494, "grad_norm": 13.534192085266113, "learning_rate": 9.802703503181422e-06, "loss": 0.3932, "step": 400 }, { "epoch": 0.9307604994324631, "grad_norm": 10.377079010009766, "learning_rate": 9.780081138965663e-06, "loss": 0.3122, "step": 410 }, { "epoch": 0.9534619750283768, "grad_norm": 10.819889068603516, "learning_rate": 9.756260262150694e-06, "loss": 0.4402, "step": 420 }, { "epoch": 0.9761634506242906, "grad_norm": 6.329880237579346, "learning_rate": 9.731246845359187e-06, "loss": 0.3601, "step": 430 }, { "epoch": 0.9988649262202043, "grad_norm": 16.57404136657715, "learning_rate": 9.70504716022007e-06, "loss": 0.3667, "step": 440 }, { "epoch": 1.0204313280363224, "grad_norm": 3.712496757507324, "learning_rate": 9.677667775796052e-06, "loss": 0.1515, "step": 450 }, { "epoch": 1.043132803632236, "grad_norm": 16.97614097595215, "learning_rate": 9.649115556936543e-06, "loss": 0.1758, "step": 460 }, { "epoch": 1.0658342792281499, "grad_norm": 5.374657154083252, "learning_rate": 9.619397662556434e-06, "loss": 0.1449, "step": 470 }, { "epoch": 1.0885357548240635, "grad_norm": 15.91373062133789, "learning_rate": 9.588521543841133e-06, "loss": 0.1962, "step": 480 }, { "epoch": 1.1112372304199774, "grad_norm": 9.699517250061035, "learning_rate": 9.556494942378328e-06, "loss": 0.1813, "step": 490 }, { "epoch": 1.133938706015891, "grad_norm": 10.416573524475098, "learning_rate": 9.523325888216932e-06, "loss": 0.2731, "step": 500 }, { "epoch": 1.1566401816118048, "grad_norm": 11.052528381347656, "learning_rate": 9.48902269785371e-06, "loss": 0.2051, "step": 510 }, { "epoch": 1.1793416572077184, "grad_norm": 12.394085884094238, "learning_rate": 9.45359397214807e-06, "loss": 0.1438, "step": 520 }, { "epoch": 1.2020431328036323, "grad_norm": 10.093958854675293, "learning_rate": 9.417048594165572e-06, "loss": 0.149, "step": 530 }, { "epoch": 1.224744608399546, "grad_norm": 0.7013342380523682, "learning_rate": 9.379395726950669e-06, "loss": 0.1611, "step": 540 }, { "epoch": 1.2474460839954598, "grad_norm": 8.697464942932129, "learning_rate": 9.340644811229243e-06, "loss": 0.0884, "step": 550 }, { "epoch": 1.2701475595913734, "grad_norm": 15.312997817993164, "learning_rate": 9.300805563041544e-06, "loss": 0.2006, "step": 560 }, { "epoch": 1.2928490351872872, "grad_norm": 19.4388484954834, "learning_rate": 9.259887971306064e-06, "loss": 0.2624, "step": 570 }, { "epoch": 1.3155505107832008, "grad_norm": 13.549400329589844, "learning_rate": 9.217902295315022e-06, "loss": 0.1479, "step": 580 }, { "epoch": 1.3382519863791147, "grad_norm": 3.1928927898406982, "learning_rate": 9.174859062162037e-06, "loss": 0.2136, "step": 590 }, { "epoch": 1.3609534619750283, "grad_norm": 18.86738395690918, "learning_rate": 9.130769064102668e-06, "loss": 0.1709, "step": 600 }, { "epoch": 1.3836549375709422, "grad_norm": 4.533754825592041, "learning_rate": 9.085643355848468e-06, "loss": 0.2012, "step": 610 }, { "epoch": 1.4063564131668558, "grad_norm": 3.2722301483154297, "learning_rate": 9.039493251795215e-06, "loss": 0.1408, "step": 620 }, { "epoch": 1.4290578887627696, "grad_norm": 10.776287078857422, "learning_rate": 8.992330323186069e-06, "loss": 0.1568, "step": 630 }, { "epoch": 1.4517593643586832, "grad_norm": 9.144874572753906, "learning_rate": 8.944166395210291e-06, "loss": 0.186, "step": 640 }, { "epoch": 1.474460839954597, "grad_norm": 18.156970977783203, "learning_rate": 8.89501354403831e-06, "loss": 0.1889, "step": 650 }, { "epoch": 1.4971623155505107, "grad_norm": 13.364849090576172, "learning_rate": 8.844884093793866e-06, "loss": 0.1807, "step": 660 }, { "epoch": 1.5198637911464246, "grad_norm": 10.344949722290039, "learning_rate": 8.793790613463956e-06, "loss": 0.2176, "step": 670 }, { "epoch": 1.5425652667423382, "grad_norm": 8.828970909118652, "learning_rate": 8.741745913747423e-06, "loss": 0.1564, "step": 680 }, { "epoch": 1.565266742338252, "grad_norm": 8.841721534729004, "learning_rate": 8.688763043842916e-06, "loss": 0.2232, "step": 690 }, { "epoch": 1.5879682179341659, "grad_norm": 11.328946113586426, "learning_rate": 8.634855288177056e-06, "loss": 0.1999, "step": 700 }, { "epoch": 1.6106696935300795, "grad_norm": 9.481406211853027, "learning_rate": 8.580036163073615e-06, "loss": 0.1817, "step": 710 }, { "epoch": 1.6333711691259931, "grad_norm": 17.757545471191406, "learning_rate": 8.524319413364581e-06, "loss": 0.1914, "step": 720 }, { "epoch": 1.656072644721907, "grad_norm": 8.789188385009766, "learning_rate": 8.467719008943886e-06, "loss": 0.2162, "step": 730 }, { "epoch": 1.6787741203178208, "grad_norm": 18.05352783203125, "learning_rate": 8.41024914126474e-06, "loss": 0.2626, "step": 740 }, { "epoch": 1.7014755959137344, "grad_norm": 12.42115306854248, "learning_rate": 8.351924219781393e-06, "loss": 0.2043, "step": 750 }, { "epoch": 1.724177071509648, "grad_norm": 9.867905616760254, "learning_rate": 8.292758868336249e-06, "loss": 0.1833, "step": 760 }, { "epoch": 1.746878547105562, "grad_norm": 6.408987998962402, "learning_rate": 8.232767921493216e-06, "loss": 0.1587, "step": 770 }, { "epoch": 1.7695800227014757, "grad_norm": 12.573471069335938, "learning_rate": 8.171966420818227e-06, "loss": 0.1164, "step": 780 }, { "epoch": 1.7922814982973894, "grad_norm": 11.657837867736816, "learning_rate": 8.110369611107869e-06, "loss": 0.1301, "step": 790 }, { "epoch": 1.814982973893303, "grad_norm": 12.20677375793457, "learning_rate": 8.047992936567031e-06, "loss": 0.2248, "step": 800 }, { "epoch": 1.8376844494892168, "grad_norm": 7.982995986938477, "learning_rate": 7.984852036936578e-06, "loss": 0.2195, "step": 810 }, { "epoch": 1.8603859250851307, "grad_norm": 12.152588844299316, "learning_rate": 7.920962743571993e-06, "loss": 0.1891, "step": 820 }, { "epoch": 1.8830874006810443, "grad_norm": 17.834014892578125, "learning_rate": 7.856341075473963e-06, "loss": 0.2178, "step": 830 }, { "epoch": 1.905788876276958, "grad_norm": 10.333915710449219, "learning_rate": 7.791003235271928e-06, "loss": 0.1267, "step": 840 }, { "epoch": 1.9284903518728718, "grad_norm": 7.806848526000977, "learning_rate": 7.72496560516159e-06, "loss": 0.1374, "step": 850 }, { "epoch": 1.9511918274687856, "grad_norm": 7.341245174407959, "learning_rate": 7.658244742797392e-06, "loss": 0.1314, "step": 860 }, { "epoch": 1.9738933030646992, "grad_norm": 11.020069122314453, "learning_rate": 7.59085737714101e-06, "loss": 0.1508, "step": 870 }, { "epoch": 1.9965947786606129, "grad_norm": 14.469411849975586, "learning_rate": 7.522820404266886e-06, "loss": 0.15, "step": 880 }, { "epoch": 2.018161180476731, "grad_norm": 14.892839431762695, "learning_rate": 7.4541508831258695e-06, "loss": 0.0928, "step": 890 }, { "epoch": 2.040862656072645, "grad_norm": 5.067284107208252, "learning_rate": 7.384866031268011e-06, "loss": 0.0592, "step": 900 }, { "epoch": 2.0635641316685582, "grad_norm": 4.749638557434082, "learning_rate": 7.314983220525604e-06, "loss": 0.0401, "step": 910 }, { "epoch": 2.086265607264472, "grad_norm": 13.793910026550293, "learning_rate": 7.2445199726575295e-06, "loss": 0.0403, "step": 920 }, { "epoch": 2.108967082860386, "grad_norm": 0.4042888879776001, "learning_rate": 7.173493954956012e-06, "loss": 0.0842, "step": 930 }, { "epoch": 2.1316685584562998, "grad_norm": 11.68775749206543, "learning_rate": 7.1019229758168995e-06, "loss": 0.0687, "step": 940 }, { "epoch": 2.1543700340522136, "grad_norm": 7.229358673095703, "learning_rate": 7.029824980274536e-06, "loss": 0.0572, "step": 950 }, { "epoch": 2.177071509648127, "grad_norm": 9.067594528198242, "learning_rate": 6.957218045502414e-06, "loss": 0.0605, "step": 960 }, { "epoch": 2.199772985244041, "grad_norm": 15.782684326171875, "learning_rate": 6.884120376280658e-06, "loss": 0.0586, "step": 970 }, { "epoch": 2.2224744608399547, "grad_norm": 8.513503074645996, "learning_rate": 6.810550300431533e-06, "loss": 0.052, "step": 980 }, { "epoch": 2.245175936435868, "grad_norm": 13.284876823425293, "learning_rate": 6.736526264224101e-06, "loss": 0.1237, "step": 990 }, { "epoch": 2.267877412031782, "grad_norm": 12.934537887573242, "learning_rate": 6.6620668277491805e-06, "loss": 0.0787, "step": 1000 }, { "epoch": 2.290578887627696, "grad_norm": 5.002994060516357, "learning_rate": 6.587190660265752e-06, "loss": 0.0342, "step": 1010 }, { "epoch": 2.3132803632236096, "grad_norm": 9.043930053710938, "learning_rate": 6.511916535520013e-06, "loss": 0.0598, "step": 1020 }, { "epoch": 2.3359818388195235, "grad_norm": 8.2041015625, "learning_rate": 6.436263327038225e-06, "loss": 0.0951, "step": 1030 }, { "epoch": 2.358683314415437, "grad_norm": 5.8873796463012695, "learning_rate": 6.360250003394539e-06, "loss": 0.0405, "step": 1040 }, { "epoch": 2.3813847900113507, "grad_norm": 7.40029239654541, "learning_rate": 6.283895623454997e-06, "loss": 0.0896, "step": 1050 }, { "epoch": 2.4040862656072646, "grad_norm": 6.101646900177002, "learning_rate": 6.207219331598891e-06, "loss": 0.0657, "step": 1060 }, { "epoch": 2.426787741203178, "grad_norm": 0.6795443296432495, "learning_rate": 6.130240352918675e-06, "loss": 0.0473, "step": 1070 }, { "epoch": 2.449489216799092, "grad_norm": 20.0849666595459, "learning_rate": 6.052977988399658e-06, "loss": 0.0445, "step": 1080 }, { "epoch": 2.4721906923950057, "grad_norm": 7.945412635803223, "learning_rate": 5.975451610080643e-06, "loss": 0.0341, "step": 1090 }, { "epoch": 2.4948921679909195, "grad_norm": 7.104022979736328, "learning_rate": 5.897680656196775e-06, "loss": 0.0909, "step": 1100 }, { "epoch": 2.5175936435868334, "grad_norm": 2.1615724563598633, "learning_rate": 5.819684626305776e-06, "loss": 0.0527, "step": 1110 }, { "epoch": 2.5402951191827468, "grad_norm": 3.8635029792785645, "learning_rate": 5.74148307639881e-06, "loss": 0.0631, "step": 1120 }, { "epoch": 2.5629965947786606, "grad_norm": 3.274219036102295, "learning_rate": 5.663095613997196e-06, "loss": 0.076, "step": 1130 }, { "epoch": 2.5856980703745744, "grad_norm": 5.097989082336426, "learning_rate": 5.5845418932362035e-06, "loss": 0.0846, "step": 1140 }, { "epoch": 2.608399545970488, "grad_norm": 6.223990440368652, "learning_rate": 5.505841609937162e-06, "loss": 0.0614, "step": 1150 }, { "epoch": 2.6311010215664017, "grad_norm": 18.470592498779297, "learning_rate": 5.427014496669111e-06, "loss": 0.0578, "step": 1160 }, { "epoch": 2.6538024971623155, "grad_norm": 9.530206680297852, "learning_rate": 5.348080317801244e-06, "loss": 0.0863, "step": 1170 }, { "epoch": 2.6765039727582294, "grad_norm": 12.68597412109375, "learning_rate": 5.269058864547383e-06, "loss": 0.0567, "step": 1180 }, { "epoch": 2.699205448354143, "grad_norm": 8.416796684265137, "learning_rate": 5.189969950003697e-06, "loss": 0.056, "step": 1190 }, { "epoch": 2.7219069239500566, "grad_norm": 10.224136352539062, "learning_rate": 5.1108334041809736e-06, "loss": 0.0651, "step": 1200 }, { "epoch": 2.7446083995459705, "grad_norm": 7.490987777709961, "learning_rate": 5.0316690690326175e-06, "loss": 0.0523, "step": 1210 }, { "epoch": 2.7673098751418843, "grad_norm": 3.6634716987609863, "learning_rate": 4.9524967934796664e-06, "loss": 0.0833, "step": 1220 }, { "epoch": 2.7900113507377977, "grad_norm": 5.3087286949157715, "learning_rate": 4.873336428434062e-06, "loss": 0.068, "step": 1230 }, { "epoch": 2.8127128263337116, "grad_norm": 5.159224033355713, "learning_rate": 4.794207821821414e-06, "loss": 0.0654, "step": 1240 }, { "epoch": 2.8354143019296254, "grad_norm": 6.141483783721924, "learning_rate": 4.715130813604522e-06, "loss": 0.1134, "step": 1250 }, { "epoch": 2.8581157775255392, "grad_norm": 9.958399772644043, "learning_rate": 4.636125230808897e-06, "loss": 0.0303, "step": 1260 }, { "epoch": 2.880817253121453, "grad_norm": 5.475862503051758, "learning_rate": 4.5572108825515e-06, "loss": 0.0543, "step": 1270 }, { "epoch": 2.9035187287173665, "grad_norm": 4.167320728302002, "learning_rate": 4.478407555074006e-06, "loss": 0.0536, "step": 1280 }, { "epoch": 2.9262202043132803, "grad_norm": 4.539482116699219, "learning_rate": 4.3997350067817866e-06, "loss": 0.0729, "step": 1290 }, { "epoch": 2.948921679909194, "grad_norm": 5.991142749786377, "learning_rate": 4.321212963289869e-06, "loss": 0.0344, "step": 1300 }, { "epoch": 2.9716231555051076, "grad_norm": 0.05109904706478119, "learning_rate": 4.2428611124771184e-06, "loss": 0.0824, "step": 1310 }, { "epoch": 2.9943246311010214, "grad_norm": 14.385650634765625, "learning_rate": 4.164699099549889e-06, "loss": 0.0643, "step": 1320 }, { "epoch": 3.0158910329171396, "grad_norm": 2.193084478378296, "learning_rate": 4.086746522116372e-06, "loss": 0.0268, "step": 1330 }, { "epoch": 3.0385925085130534, "grad_norm": 1.7137833833694458, "learning_rate": 4.009022925272872e-06, "loss": 0.0088, "step": 1340 }, { "epoch": 3.0612939841089672, "grad_norm": 0.09790412336587906, "learning_rate": 3.931547796703245e-06, "loss": 0.0102, "step": 1350 }, { "epoch": 3.0839954597048806, "grad_norm": 1.6275984048843384, "learning_rate": 3.8543405617927624e-06, "loss": 0.0121, "step": 1360 }, { "epoch": 3.1066969353007945, "grad_norm": 0.12331096082925797, "learning_rate": 3.7774205787575455e-06, "loss": 0.0084, "step": 1370 }, { "epoch": 3.1293984108967083, "grad_norm": 2.3316988945007324, "learning_rate": 3.7008071337908896e-06, "loss": 0.0274, "step": 1380 }, { "epoch": 3.152099886492622, "grad_norm": 14.122298240661621, "learning_rate": 3.62451943622761e-06, "loss": 0.0286, "step": 1390 }, { "epoch": 3.1748013620885356, "grad_norm": 0.49344602227211, "learning_rate": 3.5485766137276894e-06, "loss": 0.0057, "step": 1400 }, { "epoch": 3.1975028376844494, "grad_norm": 8.099455833435059, "learning_rate": 3.472997707480372e-06, "loss": 0.0192, "step": 1410 }, { "epoch": 3.2202043132803633, "grad_norm": 7.685230255126953, "learning_rate": 3.3978016674299676e-06, "loss": 0.0212, "step": 1420 }, { "epoch": 3.242905788876277, "grad_norm": 9.709684371948242, "learning_rate": 3.323007347524515e-06, "loss": 0.035, "step": 1430 }, { "epoch": 3.2656072644721905, "grad_norm": 2.777675151824951, "learning_rate": 3.2486335009885185e-06, "loss": 0.0266, "step": 1440 }, { "epoch": 3.2883087400681044, "grad_norm": 2.5289320945739746, "learning_rate": 3.174698775620947e-06, "loss": 0.0217, "step": 1450 }, { "epoch": 3.311010215664018, "grad_norm": 0.3003811836242676, "learning_rate": 3.1012217091196505e-06, "loss": 0.0109, "step": 1460 }, { "epoch": 3.333711691259932, "grad_norm": 0.5938064455986023, "learning_rate": 3.0282207244334084e-06, "loss": 0.0108, "step": 1470 }, { "epoch": 3.3564131668558455, "grad_norm": 0.06921522319316864, "learning_rate": 2.955714125142711e-06, "loss": 0.0135, "step": 1480 }, { "epoch": 3.3791146424517593, "grad_norm": 0.024770274758338928, "learning_rate": 2.88372009087051e-06, "loss": 0.0093, "step": 1490 }, { "epoch": 3.401816118047673, "grad_norm": 3.0060906410217285, "learning_rate": 2.8122566727240223e-06, "loss": 0.0069, "step": 1500 }, { "epoch": 3.424517593643587, "grad_norm": 0.09452546387910843, "learning_rate": 2.7413417887687644e-06, "loss": 0.0035, "step": 1510 }, { "epoch": 3.4472190692395004, "grad_norm": 1.457892656326294, "learning_rate": 2.6709932195359533e-06, "loss": 0.0165, "step": 1520 }, { "epoch": 3.4699205448354142, "grad_norm": 0.2586440145969391, "learning_rate": 2.601228603564368e-06, "loss": 0.0115, "step": 1530 }, { "epoch": 3.492622020431328, "grad_norm": 0.07195116579532623, "learning_rate": 2.532065432977848e-06, "loss": 0.0279, "step": 1540 }, { "epoch": 3.515323496027242, "grad_norm": 15.794938087463379, "learning_rate": 2.4635210490994648e-06, "loss": 0.0191, "step": 1550 }, { "epoch": 3.5380249716231553, "grad_norm": 3.96319317817688, "learning_rate": 2.395612638103529e-06, "loss": 0.028, "step": 1560 }, { "epoch": 3.560726447219069, "grad_norm": 1.5859898328781128, "learning_rate": 2.3283572267064963e-06, "loss": 0.0169, "step": 1570 }, { "epoch": 3.583427922814983, "grad_norm": 2.4183928966522217, "learning_rate": 2.261771677897838e-06, "loss": 0.0109, "step": 1580 }, { "epoch": 3.606129398410897, "grad_norm": 6.201639652252197, "learning_rate": 2.1958726867119785e-06, "loss": 0.0166, "step": 1590 }, { "epoch": 3.6288308740068107, "grad_norm": 6.767637252807617, "learning_rate": 2.130676776042341e-06, "loss": 0.023, "step": 1600 }, { "epoch": 3.651532349602724, "grad_norm": 0.3271225094795227, "learning_rate": 2.066200292498553e-06, "loss": 0.0249, "step": 1610 }, { "epoch": 3.674233825198638, "grad_norm": 0.7651416063308716, "learning_rate": 2.0024594023078446e-06, "loss": 0.0194, "step": 1620 }, { "epoch": 3.696935300794552, "grad_norm": 3.0265684127807617, "learning_rate": 1.9394700872616856e-06, "loss": 0.0276, "step": 1630 }, { "epoch": 3.719636776390465, "grad_norm": 0.30172616243362427, "learning_rate": 1.8772481407086656e-06, "loss": 0.0177, "step": 1640 }, { "epoch": 3.742338251986379, "grad_norm": 1.2350537776947021, "learning_rate": 1.815809163594609e-06, "loss": 0.0272, "step": 1650 }, { "epoch": 3.765039727582293, "grad_norm": 6.861649036407471, "learning_rate": 1.755168560550944e-06, "loss": 0.0201, "step": 1660 }, { "epoch": 3.7877412031782067, "grad_norm": 5.084821701049805, "learning_rate": 1.6953415360322972e-06, "loss": 0.0097, "step": 1670 }, { "epoch": 3.8104426787741206, "grad_norm": 13.576436042785645, "learning_rate": 1.6363430905042581e-06, "loss": 0.0151, "step": 1680 }, { "epoch": 3.833144154370034, "grad_norm": 0.686917245388031, "learning_rate": 1.57818801668232e-06, "loss": 0.0323, "step": 1690 }, { "epoch": 3.855845629965948, "grad_norm": 9.852540969848633, "learning_rate": 1.5208908958228741e-06, "loss": 0.0322, "step": 1700 }, { "epoch": 3.8785471055618617, "grad_norm": 1.0231153964996338, "learning_rate": 1.4644660940672628e-06, "loss": 0.014, "step": 1710 }, { "epoch": 3.901248581157775, "grad_norm": 9.582091331481934, "learning_rate": 1.408927758839732e-06, "loss": 0.0187, "step": 1720 }, { "epoch": 3.923950056753689, "grad_norm": 0.96387779712677, "learning_rate": 1.3542898153002453e-06, "loss": 0.0286, "step": 1730 }, { "epoch": 3.9466515323496028, "grad_norm": 0.033427830785512924, "learning_rate": 1.300565962853027e-06, "loss": 0.0041, "step": 1740 }, { "epoch": 3.9693530079455166, "grad_norm": 1.130692720413208, "learning_rate": 1.2477696717116878e-06, "loss": 0.0027, "step": 1750 }, { "epoch": 3.9920544835414304, "grad_norm": 0.39794811606407166, "learning_rate": 1.1959141795218449e-06, "loss": 0.0117, "step": 1760 }, { "epoch": 4.013620885357549, "grad_norm": 0.021422021090984344, "learning_rate": 1.145012488042026e-06, "loss": 0.0013, "step": 1770 }, { "epoch": 4.036322360953462, "grad_norm": 0.11807658523321152, "learning_rate": 1.0950773598837445e-06, "loss": 0.0043, "step": 1780 }, { "epoch": 4.059023836549375, "grad_norm": 0.26249679923057556, "learning_rate": 1.046121315311508e-06, "loss": 0.0079, "step": 1790 }, { "epoch": 4.08172531214529, "grad_norm": 1.9791966676712036, "learning_rate": 9.981566291036139e-07, "loss": 0.0032, "step": 1800 }, { "epoch": 4.104426787741203, "grad_norm": 0.11679504066705704, "learning_rate": 9.511953274744884e-07, "loss": 0.0009, "step": 1810 }, { "epoch": 4.1271282633371165, "grad_norm": 0.19793881475925446, "learning_rate": 9.052491850593376e-07, "loss": 0.0025, "step": 1820 }, { "epoch": 4.149829738933031, "grad_norm": 0.16998326778411865, "learning_rate": 8.603297219618933e-07, "loss": 0.0029, "step": 1830 }, { "epoch": 4.172531214528944, "grad_norm": 0.16812190413475037, "learning_rate": 8.164482008659708e-07, "loss": 0.0034, "step": 1840 }, { "epoch": 4.195232690124858, "grad_norm": 0.06632530689239502, "learning_rate": 7.736156242115661e-07, "loss": 0.0006, "step": 1850 }, { "epoch": 4.217934165720772, "grad_norm": 0.6872692704200745, "learning_rate": 7.318427314362076e-07, "loss": 0.0031, "step": 1860 }, { "epoch": 4.240635641316685, "grad_norm": 0.04997648298740387, "learning_rate": 6.911399962822518e-07, "loss": 0.0005, "step": 1870 }, { "epoch": 4.2633371169125995, "grad_norm": 0.078142449259758, "learning_rate": 6.515176241707983e-07, "loss": 0.0022, "step": 1880 }, { "epoch": 4.286038592508513, "grad_norm": 0.015545888803899288, "learning_rate": 6.129855496428732e-07, "loss": 0.0002, "step": 1890 }, { "epoch": 4.308740068104427, "grad_norm": 6.2386040687561035, "learning_rate": 5.755534338685375e-07, "loss": 0.0043, "step": 1900 }, { "epoch": 4.331441543700341, "grad_norm": 0.03828069195151329, "learning_rate": 5.392306622245408e-07, "loss": 0.0033, "step": 1910 }, { "epoch": 4.354143019296254, "grad_norm": 0.075731560587883, "learning_rate": 5.040263419411107e-07, "loss": 0.0046, "step": 1920 }, { "epoch": 4.376844494892168, "grad_norm": 3.0917651653289795, "learning_rate": 4.699492998185029e-07, "loss": 0.008, "step": 1930 }, { "epoch": 4.399545970488082, "grad_norm": 0.007497379556298256, "learning_rate": 4.370080800138415e-07, "loss": 0.0013, "step": 1940 }, { "epoch": 4.422247446083995, "grad_norm": 7.69155740737915, "learning_rate": 4.05210941898847e-07, "loss": 0.0057, "step": 1950 }, { "epoch": 4.444948921679909, "grad_norm": 0.11394481360912323, "learning_rate": 3.745658579889505e-07, "loss": 0.0012, "step": 1960 }, { "epoch": 4.467650397275823, "grad_norm": 2.758218288421631, "learning_rate": 3.4508051194434456e-07, "loss": 0.0018, "step": 1970 }, { "epoch": 4.490351872871736, "grad_norm": 0.1146424412727356, "learning_rate": 3.167622966434575e-07, "loss": 0.0018, "step": 1980 }, { "epoch": 4.5130533484676505, "grad_norm": 0.010834336280822754, "learning_rate": 2.896183123293256e-07, "loss": 0.0068, "step": 1990 }, { "epoch": 4.535754824063564, "grad_norm": 0.8865907788276672, "learning_rate": 2.6365536482934937e-07, "loss": 0.0047, "step": 2000 }, { "epoch": 4.558456299659478, "grad_norm": 0.2468201071023941, "learning_rate": 2.388799638488631e-07, "loss": 0.0012, "step": 2010 }, { "epoch": 4.581157775255392, "grad_norm": 0.026508383452892303, "learning_rate": 2.152983213389559e-07, "loss": 0.0034, "step": 2020 }, { "epoch": 4.603859250851305, "grad_norm": 0.7979089617729187, "learning_rate": 1.9291634993893803e-07, "loss": 0.0011, "step": 2030 }, { "epoch": 4.626560726447219, "grad_norm": 0.09112267941236496, "learning_rate": 1.7173966149386766e-07, "loss": 0.0012, "step": 2040 }, { "epoch": 4.649262202043133, "grad_norm": 0.0434434674680233, "learning_rate": 1.517735656474889e-07, "loss": 0.0012, "step": 2050 }, { "epoch": 4.671963677639047, "grad_norm": 0.5990062355995178, "learning_rate": 1.330230685109396e-07, "loss": 0.0048, "step": 2060 }, { "epoch": 4.69466515323496, "grad_norm": 0.014222468249499798, "learning_rate": 1.1549287140756593e-07, "loss": 0.0033, "step": 2070 }, { "epoch": 4.717366628830874, "grad_norm": 0.07564973086118698, "learning_rate": 9.918736969415866e-08, "loss": 0.0016, "step": 2080 }, { "epoch": 4.740068104426788, "grad_norm": 0.5025691390037537, "learning_rate": 8.411065165890243e-08, "loss": 0.0099, "step": 2090 }, { "epoch": 4.7627695800227015, "grad_norm": 0.5759874582290649, "learning_rate": 7.026649749631687e-08, "loss": 0.0071, "step": 2100 }, { "epoch": 4.785471055618615, "grad_norm": 0.27006009221076965, "learning_rate": 5.7658378359443104e-08, "loss": 0.0024, "step": 2110 }, { "epoch": 4.808172531214529, "grad_norm": 0.08679729700088501, "learning_rate": 4.6289455489523794e-08, "loss": 0.0032, "step": 2120 }, { "epoch": 4.8308740068104425, "grad_norm": 0.3090740144252777, "learning_rate": 3.6162579423381636e-08, "loss": 0.0039, "step": 2130 }, { "epoch": 4.853575482406356, "grad_norm": 0.03656087815761566, "learning_rate": 2.7280289278701077e-08, "loss": 0.0022, "step": 2140 }, { "epoch": 4.87627695800227, "grad_norm": 1.7539772987365723, "learning_rate": 1.964481211739533e-08, "loss": 0.0011, "step": 2150 }, { "epoch": 4.898978433598184, "grad_norm": 0.5640947818756104, "learning_rate": 1.3258062387214165e-08, "loss": 0.0013, "step": 2160 }, { "epoch": 4.921679909194098, "grad_norm": 0.11486465483903885, "learning_rate": 8.121641441732886e-09, "loss": 0.0071, "step": 2170 }, { "epoch": 4.944381384790011, "grad_norm": 0.13496723771095276, "learning_rate": 4.236837138842931e-09, "loss": 0.003, "step": 2180 }, { "epoch": 4.967082860385925, "grad_norm": 0.016427382826805115, "learning_rate": 1.6046235178474034e-09, "loss": 0.0075, "step": 2190 }, { "epoch": 4.989784335981839, "grad_norm": 0.4205330014228821, "learning_rate": 2.256605552397595e-10, "loss": 0.0015, "step": 2200 } ], "logging_steps": 10, "max_steps": 2205, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.256960217317376e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }