{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.999947295374291, "eval_steps": 500, "global_step": 42690, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007027283427908856, "grad_norm": 0.5592142939567566, "learning_rate": 0.0001995548787630315, "loss": 1.0457, "step": 100 }, { "epoch": 0.014054566855817713, "grad_norm": 0.6605722308158875, "learning_rate": 0.00019908633009253836, "loss": 0.8075, "step": 200 }, { "epoch": 0.02108185028372657, "grad_norm": 0.5018069744110107, "learning_rate": 0.00019861778142204523, "loss": 0.7927, "step": 300 }, { "epoch": 0.028109133711635426, "grad_norm": 0.5429800152778625, "learning_rate": 0.00019814923275155208, "loss": 0.7648, "step": 400 }, { "epoch": 0.03513641713954428, "grad_norm": 0.5747570395469666, "learning_rate": 0.00019768068408105893, "loss": 0.7732, "step": 500 }, { "epoch": 0.03513641713954428, "eval_loss": 0.7362164855003357, "eval_runtime": 118.3556, "eval_samples_per_second": 106.873, "eval_steps_per_second": 13.367, "step": 500 }, { "epoch": 0.04216370056745314, "grad_norm": 0.6291443109512329, "learning_rate": 0.00019721213541056578, "loss": 0.7614, "step": 600 }, { "epoch": 0.049190983995361995, "grad_norm": 0.6160371899604797, "learning_rate": 0.00019674358674007263, "loss": 0.7489, "step": 700 }, { "epoch": 0.05621826742327085, "grad_norm": 0.5804228782653809, "learning_rate": 0.00019627503806957949, "loss": 0.7399, "step": 800 }, { "epoch": 0.06324555085117971, "grad_norm": 0.6000151634216309, "learning_rate": 0.00019580648939908634, "loss": 0.7349, "step": 900 }, { "epoch": 0.07027283427908856, "grad_norm": 0.5746223330497742, "learning_rate": 0.00019533794072859319, "loss": 0.7282, "step": 1000 }, { "epoch": 0.07027283427908856, "eval_loss": 0.7145671248435974, "eval_runtime": 118.2812, "eval_samples_per_second": 106.94, "eval_steps_per_second": 13.375, "step": 1000 }, { "epoch": 0.07730011770699742, "grad_norm": 0.6321994066238403, "learning_rate": 0.00019486939205810004, "loss": 0.7241, "step": 1100 }, { "epoch": 0.08432740113490628, "grad_norm": 0.7580232620239258, "learning_rate": 0.00019440084338760689, "loss": 0.7254, "step": 1200 }, { "epoch": 0.09135468456281513, "grad_norm": 0.6181788444519043, "learning_rate": 0.00019393229471711376, "loss": 0.7349, "step": 1300 }, { "epoch": 0.09838196799072399, "grad_norm": 0.6435703635215759, "learning_rate": 0.00019346374604662061, "loss": 0.7082, "step": 1400 }, { "epoch": 0.10540925141863285, "grad_norm": 0.5934786200523376, "learning_rate": 0.00019299519737612746, "loss": 0.7145, "step": 1500 }, { "epoch": 0.10540925141863285, "eval_loss": 0.6975060701370239, "eval_runtime": 118.4288, "eval_samples_per_second": 106.807, "eval_steps_per_second": 13.358, "step": 1500 }, { "epoch": 0.1124365348465417, "grad_norm": 0.4486166536808014, "learning_rate": 0.00019252664870563431, "loss": 0.7226, "step": 1600 }, { "epoch": 0.11946381827445056, "grad_norm": 0.4868922531604767, "learning_rate": 0.00019205810003514116, "loss": 0.6951, "step": 1700 }, { "epoch": 0.12649110170235942, "grad_norm": 0.5752139687538147, "learning_rate": 0.00019158955136464801, "loss": 0.7117, "step": 1800 }, { "epoch": 0.13351838513026826, "grad_norm": 0.5520344972610474, "learning_rate": 0.00019112100269415486, "loss": 0.7111, "step": 1900 }, { "epoch": 0.14054566855817713, "grad_norm": 0.5359894633293152, "learning_rate": 0.00019065245402366172, "loss": 0.7093, "step": 2000 }, { "epoch": 0.14054566855817713, "eval_loss": 0.687991201877594, "eval_runtime": 118.7631, "eval_samples_per_second": 106.506, "eval_steps_per_second": 13.321, "step": 2000 }, { "epoch": 0.14757295198608597, "grad_norm": 0.5415408611297607, "learning_rate": 0.00019018390535316857, "loss": 0.7117, "step": 2100 }, { "epoch": 0.15460023541399484, "grad_norm": 0.6338439583778381, "learning_rate": 0.00018971535668267542, "loss": 0.7253, "step": 2200 }, { "epoch": 0.16162751884190368, "grad_norm": 0.6666418313980103, "learning_rate": 0.00018924680801218227, "loss": 0.7058, "step": 2300 }, { "epoch": 0.16865480226981255, "grad_norm": 0.5344674587249756, "learning_rate": 0.00018877825934168914, "loss": 0.7036, "step": 2400 }, { "epoch": 0.1756820856977214, "grad_norm": 0.5522785186767578, "learning_rate": 0.000188309710671196, "loss": 0.6809, "step": 2500 }, { "epoch": 0.1756820856977214, "eval_loss": 0.679720938205719, "eval_runtime": 118.6143, "eval_samples_per_second": 106.64, "eval_steps_per_second": 13.337, "step": 2500 }, { "epoch": 0.18270936912563027, "grad_norm": 0.7211841344833374, "learning_rate": 0.00018784116200070284, "loss": 0.6972, "step": 2600 }, { "epoch": 0.1897366525535391, "grad_norm": 0.5469601154327393, "learning_rate": 0.00018737261333020967, "loss": 0.6996, "step": 2700 }, { "epoch": 0.19676393598144798, "grad_norm": 0.5906969904899597, "learning_rate": 0.00018690406465971652, "loss": 0.6828, "step": 2800 }, { "epoch": 0.20379121940935682, "grad_norm": 0.703484833240509, "learning_rate": 0.0001864355159892234, "loss": 0.6906, "step": 2900 }, { "epoch": 0.2108185028372657, "grad_norm": 0.5544711947441101, "learning_rate": 0.00018596696731873024, "loss": 0.6891, "step": 3000 }, { "epoch": 0.2108185028372657, "eval_loss": 0.6728695034980774, "eval_runtime": 118.909, "eval_samples_per_second": 106.375, "eval_steps_per_second": 13.304, "step": 3000 }, { "epoch": 0.21784578626517453, "grad_norm": 0.5521793365478516, "learning_rate": 0.0001854984186482371, "loss": 0.6777, "step": 3100 }, { "epoch": 0.2248730696930834, "grad_norm": 0.4634329080581665, "learning_rate": 0.00018502986997774394, "loss": 0.6744, "step": 3200 }, { "epoch": 0.23190035312099225, "grad_norm": 0.7366927266120911, "learning_rate": 0.0001845613213072508, "loss": 0.6642, "step": 3300 }, { "epoch": 0.23892763654890112, "grad_norm": 0.5567039251327515, "learning_rate": 0.00018409277263675767, "loss": 0.6895, "step": 3400 }, { "epoch": 0.24595491997680996, "grad_norm": 0.6940245628356934, "learning_rate": 0.0001836242239662645, "loss": 0.6708, "step": 3500 }, { "epoch": 0.24595491997680996, "eval_loss": 0.6706892848014832, "eval_runtime": 118.4648, "eval_samples_per_second": 106.774, "eval_steps_per_second": 13.354, "step": 3500 }, { "epoch": 0.25298220340471883, "grad_norm": 0.5577242970466614, "learning_rate": 0.00018315567529577135, "loss": 0.679, "step": 3600 }, { "epoch": 0.2600094868326277, "grad_norm": 0.6587842702865601, "learning_rate": 0.0001826871266252782, "loss": 0.6918, "step": 3700 }, { "epoch": 0.2670367702605365, "grad_norm": 0.6200099587440491, "learning_rate": 0.00018221857795478505, "loss": 0.7002, "step": 3800 }, { "epoch": 0.2740640536884454, "grad_norm": 0.5648295879364014, "learning_rate": 0.00018175002928429192, "loss": 0.6791, "step": 3900 }, { "epoch": 0.28109133711635426, "grad_norm": 0.5908897519111633, "learning_rate": 0.00018128148061379877, "loss": 0.6839, "step": 4000 }, { "epoch": 0.28109133711635426, "eval_loss": 0.664506196975708, "eval_runtime": 119.1229, "eval_samples_per_second": 106.184, "eval_steps_per_second": 13.28, "step": 4000 }, { "epoch": 0.2881186205442631, "grad_norm": 0.5778653621673584, "learning_rate": 0.00018081293194330562, "loss": 0.6654, "step": 4100 }, { "epoch": 0.29514590397217194, "grad_norm": 0.700835645198822, "learning_rate": 0.00018034438327281247, "loss": 0.6897, "step": 4200 }, { "epoch": 0.3021731874000808, "grad_norm": 0.5250533819198608, "learning_rate": 0.00017987583460231932, "loss": 0.6934, "step": 4300 }, { "epoch": 0.3092004708279897, "grad_norm": 0.725397527217865, "learning_rate": 0.00017940728593182617, "loss": 0.6781, "step": 4400 }, { "epoch": 0.31622775425589855, "grad_norm": 0.5805392265319824, "learning_rate": 0.00017893873726133302, "loss": 0.6866, "step": 4500 }, { "epoch": 0.31622775425589855, "eval_loss": 0.65822434425354, "eval_runtime": 118.7959, "eval_samples_per_second": 106.477, "eval_steps_per_second": 13.317, "step": 4500 }, { "epoch": 0.32325503768380737, "grad_norm": 0.6944029331207275, "learning_rate": 0.00017847018859083988, "loss": 0.6683, "step": 4600 }, { "epoch": 0.33028232111171624, "grad_norm": 0.5891593098640442, "learning_rate": 0.00017800163992034673, "loss": 0.6817, "step": 4700 }, { "epoch": 0.3373096045396251, "grad_norm": 0.6220216751098633, "learning_rate": 0.00017753309124985358, "loss": 0.6845, "step": 4800 }, { "epoch": 0.344336887967534, "grad_norm": 0.7002474665641785, "learning_rate": 0.00017706454257936045, "loss": 0.6551, "step": 4900 }, { "epoch": 0.3513641713954428, "grad_norm": 0.5766635537147522, "learning_rate": 0.0001765959939088673, "loss": 0.6741, "step": 5000 }, { "epoch": 0.3513641713954428, "eval_loss": 0.6550154685974121, "eval_runtime": 118.5512, "eval_samples_per_second": 106.697, "eval_steps_per_second": 13.344, "step": 5000 }, { "epoch": 0.35839145482335166, "grad_norm": 0.5734873414039612, "learning_rate": 0.00017612744523837415, "loss": 0.6583, "step": 5100 }, { "epoch": 0.36541873825126053, "grad_norm": 0.4953276515007019, "learning_rate": 0.000175658896567881, "loss": 0.6621, "step": 5200 }, { "epoch": 0.37244602167916935, "grad_norm": 0.7837636470794678, "learning_rate": 0.00017519034789738785, "loss": 0.6846, "step": 5300 }, { "epoch": 0.3794733051070782, "grad_norm": 0.718715488910675, "learning_rate": 0.0001747217992268947, "loss": 0.6776, "step": 5400 }, { "epoch": 0.3865005885349871, "grad_norm": 0.5844186544418335, "learning_rate": 0.00017425325055640155, "loss": 0.6627, "step": 5500 }, { "epoch": 0.3865005885349871, "eval_loss": 0.6532958149909973, "eval_runtime": 118.7133, "eval_samples_per_second": 106.551, "eval_steps_per_second": 13.326, "step": 5500 }, { "epoch": 0.39352787196289596, "grad_norm": 0.4426696300506592, "learning_rate": 0.0001737847018859084, "loss": 0.6546, "step": 5600 }, { "epoch": 0.4005551553908048, "grad_norm": 0.5954882502555847, "learning_rate": 0.00017331615321541525, "loss": 0.6448, "step": 5700 }, { "epoch": 0.40758243881871364, "grad_norm": 0.601349413394928, "learning_rate": 0.0001728476045449221, "loss": 0.6637, "step": 5800 }, { "epoch": 0.4146097222466225, "grad_norm": 0.6108406782150269, "learning_rate": 0.00017237905587442898, "loss": 0.6709, "step": 5900 }, { "epoch": 0.4216370056745314, "grad_norm": 0.6442033052444458, "learning_rate": 0.00017191050720393583, "loss": 0.6588, "step": 6000 }, { "epoch": 0.4216370056745314, "eval_loss": 0.6498988270759583, "eval_runtime": 118.8665, "eval_samples_per_second": 106.413, "eval_steps_per_second": 13.309, "step": 6000 }, { "epoch": 0.4286642891024402, "grad_norm": 0.4642776846885681, "learning_rate": 0.00017144195853344268, "loss": 0.6706, "step": 6100 }, { "epoch": 0.43569157253034907, "grad_norm": 0.6703388690948486, "learning_rate": 0.0001709734098629495, "loss": 0.6675, "step": 6200 }, { "epoch": 0.44271885595825794, "grad_norm": 0.6001936793327332, "learning_rate": 0.00017050486119245636, "loss": 0.6545, "step": 6300 }, { "epoch": 0.4497461393861668, "grad_norm": 0.7159720063209534, "learning_rate": 0.00017003631252196323, "loss": 0.6684, "step": 6400 }, { "epoch": 0.4567734228140756, "grad_norm": 0.5892972350120544, "learning_rate": 0.00016956776385147008, "loss": 0.6509, "step": 6500 }, { "epoch": 0.4567734228140756, "eval_loss": 0.6456841230392456, "eval_runtime": 118.8557, "eval_samples_per_second": 106.423, "eval_steps_per_second": 13.31, "step": 6500 }, { "epoch": 0.4638007062419845, "grad_norm": 0.6351083517074585, "learning_rate": 0.00016909921518097693, "loss": 0.634, "step": 6600 }, { "epoch": 0.47082798966989337, "grad_norm": 0.7939039468765259, "learning_rate": 0.00016863066651048378, "loss": 0.6595, "step": 6700 }, { "epoch": 0.47785527309780224, "grad_norm": 0.5831073522567749, "learning_rate": 0.00016816211783999063, "loss": 0.6444, "step": 6800 }, { "epoch": 0.48488255652571105, "grad_norm": 0.6314815282821655, "learning_rate": 0.0001676935691694975, "loss": 0.6622, "step": 6900 }, { "epoch": 0.4919098399536199, "grad_norm": 0.5781182646751404, "learning_rate": 0.00016722502049900433, "loss": 0.6448, "step": 7000 }, { "epoch": 0.4919098399536199, "eval_loss": 0.6440666317939758, "eval_runtime": 118.5556, "eval_samples_per_second": 106.693, "eval_steps_per_second": 13.344, "step": 7000 }, { "epoch": 0.4989371233815288, "grad_norm": 0.7241762280464172, "learning_rate": 0.00016675647182851119, "loss": 0.6727, "step": 7100 }, { "epoch": 0.5059644068094377, "grad_norm": 0.7668181657791138, "learning_rate": 0.00016628792315801804, "loss": 0.6564, "step": 7200 }, { "epoch": 0.5129916902373465, "grad_norm": 0.5727465152740479, "learning_rate": 0.00016581937448752489, "loss": 0.6348, "step": 7300 }, { "epoch": 0.5200189736652554, "grad_norm": 0.6217190027236938, "learning_rate": 0.00016535082581703176, "loss": 0.6434, "step": 7400 }, { "epoch": 0.5270462570931642, "grad_norm": 0.6559625864028931, "learning_rate": 0.0001648822771465386, "loss": 0.6551, "step": 7500 }, { "epoch": 0.5270462570931642, "eval_loss": 0.6428527235984802, "eval_runtime": 118.6739, "eval_samples_per_second": 106.586, "eval_steps_per_second": 13.331, "step": 7500 }, { "epoch": 0.534073540521073, "grad_norm": 0.6792352795600891, "learning_rate": 0.00016441372847604546, "loss": 0.6622, "step": 7600 }, { "epoch": 0.541100823948982, "grad_norm": 0.6426942944526672, "learning_rate": 0.00016394517980555231, "loss": 0.6529, "step": 7700 }, { "epoch": 0.5481281073768908, "grad_norm": 0.8337587118148804, "learning_rate": 0.00016347663113505916, "loss": 0.6506, "step": 7800 }, { "epoch": 0.5551553908047996, "grad_norm": 0.5555398464202881, "learning_rate": 0.00016300808246456601, "loss": 0.6572, "step": 7900 }, { "epoch": 0.5621826742327085, "grad_norm": 0.6205873489379883, "learning_rate": 0.00016253953379407286, "loss": 0.6545, "step": 8000 }, { "epoch": 0.5621826742327085, "eval_loss": 0.639687716960907, "eval_runtime": 118.9175, "eval_samples_per_second": 106.368, "eval_steps_per_second": 13.303, "step": 8000 }, { "epoch": 0.5692099576606173, "grad_norm": 0.7055862545967102, "learning_rate": 0.00016207098512357971, "loss": 0.6428, "step": 8100 }, { "epoch": 0.5762372410885263, "grad_norm": 0.5852298140525818, "learning_rate": 0.00016160243645308656, "loss": 0.6404, "step": 8200 }, { "epoch": 0.5832645245164351, "grad_norm": 0.551387369632721, "learning_rate": 0.00016113388778259341, "loss": 0.6618, "step": 8300 }, { "epoch": 0.5902918079443439, "grad_norm": 0.7349231839179993, "learning_rate": 0.0001606653391121003, "loss": 0.6592, "step": 8400 }, { "epoch": 0.5973190913722528, "grad_norm": 0.502613365650177, "learning_rate": 0.00016019679044160714, "loss": 0.6467, "step": 8500 }, { "epoch": 0.5973190913722528, "eval_loss": 0.6377580165863037, "eval_runtime": 118.7487, "eval_samples_per_second": 106.519, "eval_steps_per_second": 13.322, "step": 8500 }, { "epoch": 0.6043463748001616, "grad_norm": 0.7003266215324402, "learning_rate": 0.000159728241771114, "loss": 0.6531, "step": 8600 }, { "epoch": 0.6113736582280704, "grad_norm": 0.42152824997901917, "learning_rate": 0.00015925969310062084, "loss": 0.647, "step": 8700 }, { "epoch": 0.6184009416559794, "grad_norm": 0.7964949607849121, "learning_rate": 0.0001587911444301277, "loss": 0.6623, "step": 8800 }, { "epoch": 0.6254282250838882, "grad_norm": 0.6723759770393372, "learning_rate": 0.00015832259575963452, "loss": 0.6528, "step": 8900 }, { "epoch": 0.6324555085117971, "grad_norm": 0.6479921936988831, "learning_rate": 0.0001578540470891414, "loss": 0.6615, "step": 9000 }, { "epoch": 0.6324555085117971, "eval_loss": 0.634124755859375, "eval_runtime": 118.6171, "eval_samples_per_second": 106.637, "eval_steps_per_second": 13.337, "step": 9000 }, { "epoch": 0.6394827919397059, "grad_norm": 0.6251150965690613, "learning_rate": 0.00015738549841864824, "loss": 0.6575, "step": 9100 }, { "epoch": 0.6465100753676147, "grad_norm": 0.6354021430015564, "learning_rate": 0.0001569169497481551, "loss": 0.6371, "step": 9200 }, { "epoch": 0.6535373587955237, "grad_norm": 0.6997053027153015, "learning_rate": 0.00015644840107766194, "loss": 0.6724, "step": 9300 }, { "epoch": 0.6605646422234325, "grad_norm": 0.6767123341560364, "learning_rate": 0.0001559798524071688, "loss": 0.6382, "step": 9400 }, { "epoch": 0.6675919256513413, "grad_norm": 0.5579701662063599, "learning_rate": 0.00015551130373667567, "loss": 0.6362, "step": 9500 }, { "epoch": 0.6675919256513413, "eval_loss": 0.6337981224060059, "eval_runtime": 118.7227, "eval_samples_per_second": 106.542, "eval_steps_per_second": 13.325, "step": 9500 }, { "epoch": 0.6746192090792502, "grad_norm": 0.6185320019721985, "learning_rate": 0.00015504275506618252, "loss": 0.638, "step": 9600 }, { "epoch": 0.681646492507159, "grad_norm": 0.5869000554084778, "learning_rate": 0.00015457420639568935, "loss": 0.6557, "step": 9700 }, { "epoch": 0.688673775935068, "grad_norm": 0.6124538779258728, "learning_rate": 0.0001541056577251962, "loss": 0.6394, "step": 9800 }, { "epoch": 0.6957010593629768, "grad_norm": 1.008245587348938, "learning_rate": 0.00015363710905470305, "loss": 0.6516, "step": 9900 }, { "epoch": 0.7027283427908856, "grad_norm": 0.5377674698829651, "learning_rate": 0.00015316856038420992, "loss": 0.6089, "step": 10000 }, { "epoch": 0.7027283427908856, "eval_loss": 0.6323862671852112, "eval_runtime": 118.7128, "eval_samples_per_second": 106.551, "eval_steps_per_second": 13.326, "step": 10000 }, { "epoch": 0.7097556262187945, "grad_norm": 0.6718229651451111, "learning_rate": 0.00015270001171371677, "loss": 0.6463, "step": 10100 }, { "epoch": 0.7167829096467033, "grad_norm": 0.613488495349884, "learning_rate": 0.00015223146304322362, "loss": 0.6513, "step": 10200 }, { "epoch": 0.7238101930746121, "grad_norm": 0.6889612674713135, "learning_rate": 0.00015176291437273047, "loss": 0.644, "step": 10300 }, { "epoch": 0.7308374765025211, "grad_norm": 0.845743715763092, "learning_rate": 0.00015129436570223732, "loss": 0.6299, "step": 10400 }, { "epoch": 0.7378647599304299, "grad_norm": 0.8277881145477295, "learning_rate": 0.00015082581703174417, "loss": 0.6592, "step": 10500 }, { "epoch": 0.7378647599304299, "eval_loss": 0.629069983959198, "eval_runtime": 118.7997, "eval_samples_per_second": 106.473, "eval_steps_per_second": 13.317, "step": 10500 }, { "epoch": 0.7448920433583387, "grad_norm": 0.5254293084144592, "learning_rate": 0.00015035726836125102, "loss": 0.6634, "step": 10600 }, { "epoch": 0.7519193267862476, "grad_norm": 0.7291231155395508, "learning_rate": 0.00014988871969075787, "loss": 0.653, "step": 10700 }, { "epoch": 0.7589466102141564, "grad_norm": 0.5473717451095581, "learning_rate": 0.00014942017102026472, "loss": 0.6477, "step": 10800 }, { "epoch": 0.7659738936420654, "grad_norm": 0.717761218547821, "learning_rate": 0.00014895162234977158, "loss": 0.6481, "step": 10900 }, { "epoch": 0.7730011770699742, "grad_norm": 0.5327322483062744, "learning_rate": 0.00014848307367927845, "loss": 0.6581, "step": 11000 }, { "epoch": 0.7730011770699742, "eval_loss": 0.6284623146057129, "eval_runtime": 119.1069, "eval_samples_per_second": 106.199, "eval_steps_per_second": 13.282, "step": 11000 }, { "epoch": 0.780028460497883, "grad_norm": 0.5596719980239868, "learning_rate": 0.0001480145250087853, "loss": 0.6372, "step": 11100 }, { "epoch": 0.7870557439257919, "grad_norm": 0.56830894947052, "learning_rate": 0.00014754597633829215, "loss": 0.6353, "step": 11200 }, { "epoch": 0.7940830273537007, "grad_norm": 0.6329615712165833, "learning_rate": 0.000147077427667799, "loss": 0.6365, "step": 11300 }, { "epoch": 0.8011103107816095, "grad_norm": 0.8399169445037842, "learning_rate": 0.00014660887899730585, "loss": 0.6212, "step": 11400 }, { "epoch": 0.8081375942095185, "grad_norm": 0.7220659255981445, "learning_rate": 0.0001461403303268127, "loss": 0.6438, "step": 11500 }, { "epoch": 0.8081375942095185, "eval_loss": 0.6267364621162415, "eval_runtime": 118.3852, "eval_samples_per_second": 106.846, "eval_steps_per_second": 13.363, "step": 11500 }, { "epoch": 0.8151648776374273, "grad_norm": 0.5614886283874512, "learning_rate": 0.00014567178165631955, "loss": 0.6262, "step": 11600 }, { "epoch": 0.8221921610653362, "grad_norm": 0.7679696679115295, "learning_rate": 0.0001452032329858264, "loss": 0.6473, "step": 11700 }, { "epoch": 0.829219444493245, "grad_norm": 0.6253560185432434, "learning_rate": 0.00014473468431533325, "loss": 0.6483, "step": 11800 }, { "epoch": 0.8362467279211538, "grad_norm": 0.5834682583808899, "learning_rate": 0.0001442661356448401, "loss": 0.6411, "step": 11900 }, { "epoch": 0.8432740113490628, "grad_norm": 0.4512103497982025, "learning_rate": 0.00014379758697434698, "loss": 0.6321, "step": 12000 }, { "epoch": 0.8432740113490628, "eval_loss": 0.6246777772903442, "eval_runtime": 118.7689, "eval_samples_per_second": 106.501, "eval_steps_per_second": 13.32, "step": 12000 }, { "epoch": 0.8503012947769716, "grad_norm": 0.6617989540100098, "learning_rate": 0.00014332903830385383, "loss": 0.6485, "step": 12100 }, { "epoch": 0.8573285782048804, "grad_norm": 0.6235445737838745, "learning_rate": 0.00014286048963336068, "loss": 0.6254, "step": 12200 }, { "epoch": 0.8643558616327893, "grad_norm": 0.612450122833252, "learning_rate": 0.00014239194096286753, "loss": 0.649, "step": 12300 }, { "epoch": 0.8713831450606981, "grad_norm": 0.7379807829856873, "learning_rate": 0.00014192339229237436, "loss": 0.6284, "step": 12400 }, { "epoch": 0.8784104284886071, "grad_norm": 0.8035106658935547, "learning_rate": 0.00014145484362188123, "loss": 0.6466, "step": 12500 }, { "epoch": 0.8784104284886071, "eval_loss": 0.6244432330131531, "eval_runtime": 118.6995, "eval_samples_per_second": 106.563, "eval_steps_per_second": 13.328, "step": 12500 }, { "epoch": 0.8854377119165159, "grad_norm": 0.6433550715446472, "learning_rate": 0.00014098629495138808, "loss": 0.6324, "step": 12600 }, { "epoch": 0.8924649953444247, "grad_norm": 0.7102698087692261, "learning_rate": 0.00014051774628089493, "loss": 0.6536, "step": 12700 }, { "epoch": 0.8994922787723336, "grad_norm": 0.7628334164619446, "learning_rate": 0.00014004919761040178, "loss": 0.6434, "step": 12800 }, { "epoch": 0.9065195622002424, "grad_norm": 0.5142523050308228, "learning_rate": 0.00013958064893990863, "loss": 0.6406, "step": 12900 }, { "epoch": 0.9135468456281512, "grad_norm": 0.8540221452713013, "learning_rate": 0.0001391121002694155, "loss": 0.6317, "step": 13000 }, { "epoch": 0.9135468456281512, "eval_loss": 0.6225576996803284, "eval_runtime": 118.6623, "eval_samples_per_second": 106.597, "eval_steps_per_second": 13.332, "step": 13000 }, { "epoch": 0.9205741290560602, "grad_norm": 0.6770111918449402, "learning_rate": 0.00013864355159892236, "loss": 0.6381, "step": 13100 }, { "epoch": 0.927601412483969, "grad_norm": 0.7313960194587708, "learning_rate": 0.00013817500292842918, "loss": 0.643, "step": 13200 }, { "epoch": 0.9346286959118779, "grad_norm": 0.8158569931983948, "learning_rate": 0.00013770645425793603, "loss": 0.6381, "step": 13300 }, { "epoch": 0.9416559793397867, "grad_norm": 0.6563596725463867, "learning_rate": 0.00013723790558744289, "loss": 0.6445, "step": 13400 }, { "epoch": 0.9486832627676955, "grad_norm": 0.6007642149925232, "learning_rate": 0.00013676935691694976, "loss": 0.6165, "step": 13500 }, { "epoch": 0.9486832627676955, "eval_loss": 0.6213079690933228, "eval_runtime": 118.8856, "eval_samples_per_second": 106.396, "eval_steps_per_second": 13.307, "step": 13500 }, { "epoch": 0.9557105461956045, "grad_norm": 0.7704166173934937, "learning_rate": 0.0001363008082464566, "loss": 0.6475, "step": 13600 }, { "epoch": 0.9627378296235133, "grad_norm": 0.6467058658599854, "learning_rate": 0.00013583225957596346, "loss": 0.626, "step": 13700 }, { "epoch": 0.9697651130514221, "grad_norm": 0.5320102572441101, "learning_rate": 0.0001353637109054703, "loss": 0.6283, "step": 13800 }, { "epoch": 0.976792396479331, "grad_norm": 0.6444761157035828, "learning_rate": 0.00013489516223497716, "loss": 0.6381, "step": 13900 }, { "epoch": 0.9838196799072398, "grad_norm": 0.7598044872283936, "learning_rate": 0.00013442661356448404, "loss": 0.6305, "step": 14000 }, { "epoch": 0.9838196799072398, "eval_loss": 0.6203290820121765, "eval_runtime": 118.8928, "eval_samples_per_second": 106.39, "eval_steps_per_second": 13.306, "step": 14000 }, { "epoch": 0.9908469633351488, "grad_norm": 0.735137403011322, "learning_rate": 0.00013395806489399086, "loss": 0.6378, "step": 14100 }, { "epoch": 0.9978742467630576, "grad_norm": 0.758840799331665, "learning_rate": 0.00013348951622349771, "loss": 0.6469, "step": 14200 }, { "epoch": 1.0049015301909665, "grad_norm": 0.5422857403755188, "learning_rate": 0.00013302096755300456, "loss": 0.586, "step": 14300 }, { "epoch": 1.0119288136188753, "grad_norm": 0.5595451593399048, "learning_rate": 0.00013255241888251141, "loss": 0.5967, "step": 14400 }, { "epoch": 1.0189560970467841, "grad_norm": 0.6194477081298828, "learning_rate": 0.0001320838702120183, "loss": 0.602, "step": 14500 }, { "epoch": 1.0189560970467841, "eval_loss": 0.6205016374588013, "eval_runtime": 118.9575, "eval_samples_per_second": 106.332, "eval_steps_per_second": 13.299, "step": 14500 }, { "epoch": 1.025983380474693, "grad_norm": 0.710670530796051, "learning_rate": 0.00013161532154152514, "loss": 0.5954, "step": 14600 }, { "epoch": 1.0330106639026018, "grad_norm": 0.613923192024231, "learning_rate": 0.000131146772871032, "loss": 0.5855, "step": 14700 }, { "epoch": 1.0400379473305108, "grad_norm": 0.7411431670188904, "learning_rate": 0.00013067822420053884, "loss": 0.5881, "step": 14800 }, { "epoch": 1.0470652307584196, "grad_norm": 0.7143989205360413, "learning_rate": 0.0001302096755300457, "loss": 0.5891, "step": 14900 }, { "epoch": 1.0540925141863284, "grad_norm": 0.6597478985786438, "learning_rate": 0.00012974112685955254, "loss": 0.5915, "step": 15000 }, { "epoch": 1.0540925141863284, "eval_loss": 0.6205988526344299, "eval_runtime": 118.9337, "eval_samples_per_second": 106.353, "eval_steps_per_second": 13.302, "step": 15000 }, { "epoch": 1.0611197976142372, "grad_norm": 0.5813501477241516, "learning_rate": 0.0001292725781890594, "loss": 0.5877, "step": 15100 }, { "epoch": 1.068147081042146, "grad_norm": 0.5610823631286621, "learning_rate": 0.00012880402951856624, "loss": 0.5911, "step": 15200 }, { "epoch": 1.075174364470055, "grad_norm": 0.5839988589286804, "learning_rate": 0.0001283354808480731, "loss": 0.5903, "step": 15300 }, { "epoch": 1.082201647897964, "grad_norm": 0.6421522498130798, "learning_rate": 0.00012786693217757994, "loss": 0.591, "step": 15400 }, { "epoch": 1.0892289313258727, "grad_norm": 0.6854695081710815, "learning_rate": 0.0001273983835070868, "loss": 0.5998, "step": 15500 }, { "epoch": 1.0892289313258727, "eval_loss": 0.6208451986312866, "eval_runtime": 118.6829, "eval_samples_per_second": 106.578, "eval_steps_per_second": 13.33, "step": 15500 }, { "epoch": 1.0962562147537815, "grad_norm": 0.7333750128746033, "learning_rate": 0.00012692983483659367, "loss": 0.5916, "step": 15600 }, { "epoch": 1.1032834981816904, "grad_norm": 0.5983602404594421, "learning_rate": 0.00012646128616610052, "loss": 0.581, "step": 15700 }, { "epoch": 1.1103107816095992, "grad_norm": 0.5112642645835876, "learning_rate": 0.00012599273749560737, "loss": 0.5984, "step": 15800 }, { "epoch": 1.1173380650375082, "grad_norm": 0.5569522976875305, "learning_rate": 0.0001255241888251142, "loss": 0.5983, "step": 15900 }, { "epoch": 1.124365348465417, "grad_norm": 0.6089062690734863, "learning_rate": 0.00012505564015462105, "loss": 0.6019, "step": 16000 }, { "epoch": 1.124365348465417, "eval_loss": 0.6191478967666626, "eval_runtime": 118.6608, "eval_samples_per_second": 106.598, "eval_steps_per_second": 13.332, "step": 16000 }, { "epoch": 1.1313926318933258, "grad_norm": 0.5710394978523254, "learning_rate": 0.00012458709148412792, "loss": 0.5907, "step": 16100 }, { "epoch": 1.1384199153212347, "grad_norm": 0.7836496233940125, "learning_rate": 0.00012411854281363477, "loss": 0.5818, "step": 16200 }, { "epoch": 1.1454471987491435, "grad_norm": 0.600236177444458, "learning_rate": 0.00012364999414314162, "loss": 0.5834, "step": 16300 }, { "epoch": 1.1524744821770523, "grad_norm": 0.7090241312980652, "learning_rate": 0.00012318144547264847, "loss": 0.5963, "step": 16400 }, { "epoch": 1.1595017656049613, "grad_norm": 0.5439143180847168, "learning_rate": 0.00012271289680215532, "loss": 0.5939, "step": 16500 }, { "epoch": 1.1595017656049613, "eval_loss": 0.6187065243721008, "eval_runtime": 118.7823, "eval_samples_per_second": 106.489, "eval_steps_per_second": 13.318, "step": 16500 }, { "epoch": 1.1665290490328701, "grad_norm": 0.6133089661598206, "learning_rate": 0.0001222443481316622, "loss": 0.583, "step": 16600 }, { "epoch": 1.173556332460779, "grad_norm": 0.6947652101516724, "learning_rate": 0.00012177579946116904, "loss": 0.5851, "step": 16700 }, { "epoch": 1.1805836158886878, "grad_norm": 0.799213707447052, "learning_rate": 0.00012130725079067589, "loss": 0.5815, "step": 16800 }, { "epoch": 1.1876108993165966, "grad_norm": 0.6443912982940674, "learning_rate": 0.00012083870212018274, "loss": 0.5794, "step": 16900 }, { "epoch": 1.1946381827445056, "grad_norm": 0.8435219526290894, "learning_rate": 0.00012037015344968959, "loss": 0.5747, "step": 17000 }, { "epoch": 1.1946381827445056, "eval_loss": 0.6187562942504883, "eval_runtime": 118.6879, "eval_samples_per_second": 106.574, "eval_steps_per_second": 13.329, "step": 17000 }, { "epoch": 1.2016654661724144, "grad_norm": 0.7162328958511353, "learning_rate": 0.00011990160477919645, "loss": 0.596, "step": 17100 }, { "epoch": 1.2086927496003232, "grad_norm": 0.6594322919845581, "learning_rate": 0.0001194330561087033, "loss": 0.6054, "step": 17200 }, { "epoch": 1.215720033028232, "grad_norm": 0.5395209193229675, "learning_rate": 0.00011896450743821015, "loss": 0.5835, "step": 17300 }, { "epoch": 1.2227473164561409, "grad_norm": 0.7208767533302307, "learning_rate": 0.000118495958767717, "loss": 0.595, "step": 17400 }, { "epoch": 1.22977459988405, "grad_norm": 0.6752803921699524, "learning_rate": 0.00011802741009722384, "loss": 0.5937, "step": 17500 }, { "epoch": 1.22977459988405, "eval_loss": 0.6167559623718262, "eval_runtime": 118.8202, "eval_samples_per_second": 106.455, "eval_steps_per_second": 13.314, "step": 17500 }, { "epoch": 1.2368018833119587, "grad_norm": 0.7853017449378967, "learning_rate": 0.00011755886142673072, "loss": 0.6035, "step": 17600 }, { "epoch": 1.2438291667398675, "grad_norm": 0.6420643329620361, "learning_rate": 0.00011709031275623757, "loss": 0.5834, "step": 17700 }, { "epoch": 1.2508564501677764, "grad_norm": 0.8449912667274475, "learning_rate": 0.00011662176408574442, "loss": 0.5964, "step": 17800 }, { "epoch": 1.2578837335956852, "grad_norm": 0.6199436783790588, "learning_rate": 0.00011615321541525125, "loss": 0.5771, "step": 17900 }, { "epoch": 1.2649110170235942, "grad_norm": 1.0329114198684692, "learning_rate": 0.0001156846667447581, "loss": 0.5678, "step": 18000 }, { "epoch": 1.2649110170235942, "eval_loss": 0.6171479821205139, "eval_runtime": 118.9379, "eval_samples_per_second": 106.35, "eval_steps_per_second": 13.301, "step": 18000 }, { "epoch": 1.271938300451503, "grad_norm": 0.7668006420135498, "learning_rate": 0.00011521611807426498, "loss": 0.5895, "step": 18100 }, { "epoch": 1.2789655838794118, "grad_norm": 0.661259651184082, "learning_rate": 0.00011474756940377183, "loss": 0.5951, "step": 18200 }, { "epoch": 1.2859928673073207, "grad_norm": 0.5448057055473328, "learning_rate": 0.00011427902073327867, "loss": 0.5958, "step": 18300 }, { "epoch": 1.2930201507352295, "grad_norm": 0.5419151782989502, "learning_rate": 0.00011381047206278552, "loss": 0.5788, "step": 18400 }, { "epoch": 1.3000474341631385, "grad_norm": 0.595245361328125, "learning_rate": 0.00011334192339229237, "loss": 0.5849, "step": 18500 }, { "epoch": 1.3000474341631385, "eval_loss": 0.6158913969993591, "eval_runtime": 118.7534, "eval_samples_per_second": 106.515, "eval_steps_per_second": 13.322, "step": 18500 }, { "epoch": 1.3070747175910473, "grad_norm": 0.6495450139045715, "learning_rate": 0.00011287337472179925, "loss": 0.5849, "step": 18600 }, { "epoch": 1.3141020010189561, "grad_norm": 0.686590313911438, "learning_rate": 0.00011240482605130608, "loss": 0.5679, "step": 18700 }, { "epoch": 1.321129284446865, "grad_norm": 0.60063636302948, "learning_rate": 0.00011193627738081293, "loss": 0.5805, "step": 18800 }, { "epoch": 1.3281565678747738, "grad_norm": 0.6396400332450867, "learning_rate": 0.00011146772871031978, "loss": 0.5996, "step": 18900 }, { "epoch": 1.3351838513026828, "grad_norm": 0.6631867289543152, "learning_rate": 0.00011099918003982663, "loss": 0.5926, "step": 19000 }, { "epoch": 1.3351838513026828, "eval_loss": 0.6149775981903076, "eval_runtime": 118.2284, "eval_samples_per_second": 106.988, "eval_steps_per_second": 13.381, "step": 19000 }, { "epoch": 1.3422111347305914, "grad_norm": 0.6868234276771545, "learning_rate": 0.0001105306313693335, "loss": 0.5826, "step": 19100 }, { "epoch": 1.3492384181585004, "grad_norm": 0.6282151937484741, "learning_rate": 0.00011006208269884035, "loss": 0.5927, "step": 19200 }, { "epoch": 1.3562657015864092, "grad_norm": 0.6498789191246033, "learning_rate": 0.0001095935340283472, "loss": 0.598, "step": 19300 }, { "epoch": 1.363292985014318, "grad_norm": 0.7654560804367065, "learning_rate": 0.00010912498535785405, "loss": 0.5819, "step": 19400 }, { "epoch": 1.3703202684422269, "grad_norm": 0.6079320907592773, "learning_rate": 0.0001086564366873609, "loss": 0.5941, "step": 19500 }, { "epoch": 1.3703202684422269, "eval_loss": 0.6134491562843323, "eval_runtime": 118.1186, "eval_samples_per_second": 107.087, "eval_steps_per_second": 13.393, "step": 19500 }, { "epoch": 1.3773475518701357, "grad_norm": 0.7858242392539978, "learning_rate": 0.00010818788801686776, "loss": 0.6035, "step": 19600 }, { "epoch": 1.3843748352980447, "grad_norm": 0.46175357699394226, "learning_rate": 0.00010771933934637461, "loss": 0.6054, "step": 19700 }, { "epoch": 1.3914021187259535, "grad_norm": 0.817308783531189, "learning_rate": 0.00010725079067588146, "loss": 0.5844, "step": 19800 }, { "epoch": 1.3984294021538624, "grad_norm": 0.7891727685928345, "learning_rate": 0.00010678224200538831, "loss": 0.5885, "step": 19900 }, { "epoch": 1.4054566855817712, "grad_norm": 0.7089536786079407, "learning_rate": 0.00010631369333489516, "loss": 0.6108, "step": 20000 }, { "epoch": 1.4054566855817712, "eval_loss": 0.6131945252418518, "eval_runtime": 119.3154, "eval_samples_per_second": 106.013, "eval_steps_per_second": 13.259, "step": 20000 }, { "epoch": 1.41248396900968, "grad_norm": 0.6867943406105042, "learning_rate": 0.00010584514466440203, "loss": 0.5863, "step": 20100 }, { "epoch": 1.419511252437589, "grad_norm": 0.9261388182640076, "learning_rate": 0.00010537659599390888, "loss": 0.6027, "step": 20200 }, { "epoch": 1.4265385358654978, "grad_norm": 0.7854331135749817, "learning_rate": 0.00010490804732341573, "loss": 0.5637, "step": 20300 }, { "epoch": 1.4335658192934067, "grad_norm": 0.4610428214073181, "learning_rate": 0.00010443949865292258, "loss": 0.5961, "step": 20400 }, { "epoch": 1.4405931027213155, "grad_norm": 0.651196300983429, "learning_rate": 0.00010397094998242943, "loss": 0.5829, "step": 20500 }, { "epoch": 1.4405931027213155, "eval_loss": 0.6108871698379517, "eval_runtime": 119.1208, "eval_samples_per_second": 106.186, "eval_steps_per_second": 13.281, "step": 20500 }, { "epoch": 1.4476203861492243, "grad_norm": 0.7416488528251648, "learning_rate": 0.00010350240131193629, "loss": 0.5869, "step": 20600 }, { "epoch": 1.4546476695771333, "grad_norm": 0.6142196655273438, "learning_rate": 0.00010303385264144314, "loss": 0.5858, "step": 20700 }, { "epoch": 1.4616749530050421, "grad_norm": 0.644241213798523, "learning_rate": 0.00010256530397094999, "loss": 0.5861, "step": 20800 }, { "epoch": 1.468702236432951, "grad_norm": 0.8656560182571411, "learning_rate": 0.00010209675530045684, "loss": 0.6099, "step": 20900 }, { "epoch": 1.4757295198608598, "grad_norm": 0.5667104721069336, "learning_rate": 0.00010162820662996368, "loss": 0.601, "step": 21000 }, { "epoch": 1.4757295198608598, "eval_loss": 0.6112544536590576, "eval_runtime": 119.0171, "eval_samples_per_second": 106.279, "eval_steps_per_second": 13.292, "step": 21000 }, { "epoch": 1.4827568032887686, "grad_norm": 0.6884378790855408, "learning_rate": 0.00010115965795947056, "loss": 0.5882, "step": 21100 }, { "epoch": 1.4897840867166776, "grad_norm": 0.7136459946632385, "learning_rate": 0.0001006911092889774, "loss": 0.5905, "step": 21200 }, { "epoch": 1.4968113701445864, "grad_norm": 0.8048639297485352, "learning_rate": 0.00010022256061848426, "loss": 0.5875, "step": 21300 }, { "epoch": 1.5038386535724952, "grad_norm": 0.7300230860710144, "learning_rate": 9.975401194799109e-05, "loss": 0.5916, "step": 21400 }, { "epoch": 1.510865937000404, "grad_norm": 0.7058496475219727, "learning_rate": 9.928546327749796e-05, "loss": 0.5768, "step": 21500 }, { "epoch": 1.510865937000404, "eval_loss": 0.6108001470565796, "eval_runtime": 118.8504, "eval_samples_per_second": 106.428, "eval_steps_per_second": 13.311, "step": 21500 }, { "epoch": 1.5178932204283129, "grad_norm": 0.8157733678817749, "learning_rate": 9.881691460700481e-05, "loss": 0.5872, "step": 21600 }, { "epoch": 1.524920503856222, "grad_norm": 0.8618035316467285, "learning_rate": 9.834836593651166e-05, "loss": 0.5861, "step": 21700 }, { "epoch": 1.5319477872841305, "grad_norm": 0.7457069158554077, "learning_rate": 9.787981726601851e-05, "loss": 0.5948, "step": 21800 }, { "epoch": 1.5389750707120395, "grad_norm": 0.7307142615318298, "learning_rate": 9.741126859552536e-05, "loss": 0.6068, "step": 21900 }, { "epoch": 1.5460023541399484, "grad_norm": 0.7692698836326599, "learning_rate": 9.694271992503222e-05, "loss": 0.5732, "step": 22000 }, { "epoch": 1.5460023541399484, "eval_loss": 0.6103039979934692, "eval_runtime": 118.5221, "eval_samples_per_second": 106.723, "eval_steps_per_second": 13.348, "step": 22000 }, { "epoch": 1.5530296375678572, "grad_norm": 0.7781071662902832, "learning_rate": 9.647417125453907e-05, "loss": 0.5915, "step": 22100 }, { "epoch": 1.5600569209957662, "grad_norm": 0.7720737457275391, "learning_rate": 9.600562258404592e-05, "loss": 0.6007, "step": 22200 }, { "epoch": 1.5670842044236748, "grad_norm": 0.632757306098938, "learning_rate": 9.553707391355277e-05, "loss": 0.5838, "step": 22300 }, { "epoch": 1.5741114878515838, "grad_norm": 0.7514855265617371, "learning_rate": 9.506852524305962e-05, "loss": 0.5894, "step": 22400 }, { "epoch": 1.5811387712794926, "grad_norm": 0.5634511113166809, "learning_rate": 9.459997657256649e-05, "loss": 0.5774, "step": 22500 }, { "epoch": 1.5811387712794926, "eval_loss": 0.6085862517356873, "eval_runtime": 119.1435, "eval_samples_per_second": 106.166, "eval_steps_per_second": 13.278, "step": 22500 }, { "epoch": 1.5881660547074015, "grad_norm": 0.8155964612960815, "learning_rate": 9.413142790207334e-05, "loss": 0.582, "step": 22600 }, { "epoch": 1.5951933381353105, "grad_norm": 0.7442721128463745, "learning_rate": 9.366287923158019e-05, "loss": 0.595, "step": 22700 }, { "epoch": 1.602220621563219, "grad_norm": 0.6977400183677673, "learning_rate": 9.319433056108704e-05, "loss": 0.5906, "step": 22800 }, { "epoch": 1.6092479049911281, "grad_norm": 0.7066090703010559, "learning_rate": 9.272578189059389e-05, "loss": 0.5917, "step": 22900 }, { "epoch": 1.616275188419037, "grad_norm": 0.9004433751106262, "learning_rate": 9.225723322010075e-05, "loss": 0.5821, "step": 23000 }, { "epoch": 1.616275188419037, "eval_loss": 0.608232319355011, "eval_runtime": 118.5994, "eval_samples_per_second": 106.653, "eval_steps_per_second": 13.339, "step": 23000 }, { "epoch": 1.6233024718469458, "grad_norm": 0.6980244517326355, "learning_rate": 9.17886845496076e-05, "loss": 0.5986, "step": 23100 }, { "epoch": 1.6303297552748546, "grad_norm": 0.6959982514381409, "learning_rate": 9.132013587911444e-05, "loss": 0.5751, "step": 23200 }, { "epoch": 1.6373570387027634, "grad_norm": 0.6452066898345947, "learning_rate": 9.08515872086213e-05, "loss": 0.5834, "step": 23300 }, { "epoch": 1.6443843221306724, "grad_norm": 0.563113272190094, "learning_rate": 9.038303853812815e-05, "loss": 0.5943, "step": 23400 }, { "epoch": 1.6514116055585812, "grad_norm": 0.6849614977836609, "learning_rate": 8.991448986763502e-05, "loss": 0.581, "step": 23500 }, { "epoch": 1.6514116055585812, "eval_loss": 0.607568621635437, "eval_runtime": 119.0065, "eval_samples_per_second": 106.288, "eval_steps_per_second": 13.293, "step": 23500 }, { "epoch": 1.65843888898649, "grad_norm": 0.8570700287818909, "learning_rate": 8.944594119714185e-05, "loss": 0.592, "step": 23600 }, { "epoch": 1.6654661724143989, "grad_norm": 0.4864564538002014, "learning_rate": 8.89773925266487e-05, "loss": 0.5722, "step": 23700 }, { "epoch": 1.6724934558423077, "grad_norm": 0.6979348063468933, "learning_rate": 8.850884385615557e-05, "loss": 0.578, "step": 23800 }, { "epoch": 1.6795207392702167, "grad_norm": 0.7699964046478271, "learning_rate": 8.804029518566242e-05, "loss": 0.5897, "step": 23900 }, { "epoch": 1.6865480226981253, "grad_norm": 0.8256754875183105, "learning_rate": 8.757174651516927e-05, "loss": 0.5845, "step": 24000 }, { "epoch": 1.6865480226981253, "eval_loss": 0.6071833372116089, "eval_runtime": 119.1197, "eval_samples_per_second": 106.187, "eval_steps_per_second": 13.281, "step": 24000 }, { "epoch": 1.6935753061260344, "grad_norm": 0.6591055393218994, "learning_rate": 8.710319784467612e-05, "loss": 0.5867, "step": 24100 }, { "epoch": 1.7006025895539432, "grad_norm": 0.7720032334327698, "learning_rate": 8.663464917418297e-05, "loss": 0.5905, "step": 24200 }, { "epoch": 1.707629872981852, "grad_norm": 0.5807234048843384, "learning_rate": 8.616610050368983e-05, "loss": 0.5849, "step": 24300 }, { "epoch": 1.714657156409761, "grad_norm": 0.6583465337753296, "learning_rate": 8.569755183319668e-05, "loss": 0.5706, "step": 24400 }, { "epoch": 1.7216844398376696, "grad_norm": 0.7280032634735107, "learning_rate": 8.522900316270352e-05, "loss": 0.5843, "step": 24500 }, { "epoch": 1.7216844398376696, "eval_loss": 0.6051200032234192, "eval_runtime": 119.1844, "eval_samples_per_second": 106.13, "eval_steps_per_second": 13.274, "step": 24500 }, { "epoch": 1.7287117232655786, "grad_norm": 0.7264565825462341, "learning_rate": 8.476045449221038e-05, "loss": 0.5866, "step": 24600 }, { "epoch": 1.7357390066934875, "grad_norm": 0.7795102596282959, "learning_rate": 8.429190582171723e-05, "loss": 0.5807, "step": 24700 }, { "epoch": 1.7427662901213963, "grad_norm": 0.702314019203186, "learning_rate": 8.38233571512241e-05, "loss": 0.5856, "step": 24800 }, { "epoch": 1.7497935735493053, "grad_norm": 0.7014954090118408, "learning_rate": 8.335480848073095e-05, "loss": 0.5812, "step": 24900 }, { "epoch": 1.756820856977214, "grad_norm": 0.6724287867546082, "learning_rate": 8.288625981023778e-05, "loss": 0.5803, "step": 25000 }, { "epoch": 1.756820856977214, "eval_loss": 0.6055319309234619, "eval_runtime": 119.2213, "eval_samples_per_second": 106.097, "eval_steps_per_second": 13.269, "step": 25000 }, { "epoch": 1.763848140405123, "grad_norm": 0.9690128564834595, "learning_rate": 8.241771113974465e-05, "loss": 0.5674, "step": 25100 }, { "epoch": 1.7708754238330318, "grad_norm": 1.0121440887451172, "learning_rate": 8.19491624692515e-05, "loss": 0.5913, "step": 25200 }, { "epoch": 1.7779027072609406, "grad_norm": 0.7207921743392944, "learning_rate": 8.148061379875836e-05, "loss": 0.592, "step": 25300 }, { "epoch": 1.7849299906888496, "grad_norm": 0.6326346397399902, "learning_rate": 8.10120651282652e-05, "loss": 0.592, "step": 25400 }, { "epoch": 1.7919572741167582, "grad_norm": 0.7215606570243835, "learning_rate": 8.054351645777205e-05, "loss": 0.578, "step": 25500 }, { "epoch": 1.7919572741167582, "eval_loss": 0.6045902371406555, "eval_runtime": 118.5573, "eval_samples_per_second": 106.691, "eval_steps_per_second": 13.344, "step": 25500 }, { "epoch": 1.7989845575446672, "grad_norm": 0.6932191848754883, "learning_rate": 8.007496778727891e-05, "loss": 0.5881, "step": 25600 }, { "epoch": 1.806011840972576, "grad_norm": 0.7887512445449829, "learning_rate": 7.960641911678576e-05, "loss": 0.5875, "step": 25700 }, { "epoch": 1.8130391244004849, "grad_norm": 0.5214329957962036, "learning_rate": 7.913787044629261e-05, "loss": 0.5757, "step": 25800 }, { "epoch": 1.8200664078283937, "grad_norm": 0.6298120021820068, "learning_rate": 7.866932177579946e-05, "loss": 0.5634, "step": 25900 }, { "epoch": 1.8270936912563025, "grad_norm": 0.6642977595329285, "learning_rate": 7.820077310530631e-05, "loss": 0.5708, "step": 26000 }, { "epoch": 1.8270936912563025, "eval_loss": 0.6030368804931641, "eval_runtime": 118.8611, "eval_samples_per_second": 106.418, "eval_steps_per_second": 13.31, "step": 26000 }, { "epoch": 1.8341209746842115, "grad_norm": 0.5501639246940613, "learning_rate": 7.773222443481318e-05, "loss": 0.5692, "step": 26100 }, { "epoch": 1.8411482581121204, "grad_norm": 0.6441388726234436, "learning_rate": 7.726367576432003e-05, "loss": 0.5881, "step": 26200 }, { "epoch": 1.8481755415400292, "grad_norm": 0.6169604063034058, "learning_rate": 7.679512709382688e-05, "loss": 0.5762, "step": 26300 }, { "epoch": 1.855202824967938, "grad_norm": 0.6980007290840149, "learning_rate": 7.632657842333373e-05, "loss": 0.5739, "step": 26400 }, { "epoch": 1.8622301083958468, "grad_norm": 0.7939792275428772, "learning_rate": 7.585802975284058e-05, "loss": 0.5746, "step": 26500 }, { "epoch": 1.8622301083958468, "eval_loss": 0.6025614142417908, "eval_runtime": 118.9608, "eval_samples_per_second": 106.329, "eval_steps_per_second": 13.298, "step": 26500 }, { "epoch": 1.8692573918237558, "grad_norm": 0.6231071352958679, "learning_rate": 7.538948108234744e-05, "loss": 0.5634, "step": 26600 }, { "epoch": 1.8762846752516644, "grad_norm": 0.6939712762832642, "learning_rate": 7.492093241185428e-05, "loss": 0.5792, "step": 26700 }, { "epoch": 1.8833119586795735, "grad_norm": 0.6055401563644409, "learning_rate": 7.445238374136114e-05, "loss": 0.5929, "step": 26800 }, { "epoch": 1.8903392421074823, "grad_norm": 0.7465933561325073, "learning_rate": 7.398383507086799e-05, "loss": 0.5817, "step": 26900 }, { "epoch": 1.897366525535391, "grad_norm": 0.6460291743278503, "learning_rate": 7.351528640037484e-05, "loss": 0.5831, "step": 27000 }, { "epoch": 1.897366525535391, "eval_loss": 0.6021212935447693, "eval_runtime": 118.8793, "eval_samples_per_second": 106.402, "eval_steps_per_second": 13.308, "step": 27000 }, { "epoch": 1.9043938089633001, "grad_norm": 0.5837533473968506, "learning_rate": 7.304673772988169e-05, "loss": 0.5807, "step": 27100 }, { "epoch": 1.9114210923912087, "grad_norm": 0.7371869087219238, "learning_rate": 7.257818905938854e-05, "loss": 0.5967, "step": 27200 }, { "epoch": 1.9184483758191178, "grad_norm": 0.8853654861450195, "learning_rate": 7.21096403888954e-05, "loss": 0.5967, "step": 27300 }, { "epoch": 1.9254756592470266, "grad_norm": 0.7515887022018433, "learning_rate": 7.164109171840226e-05, "loss": 0.5708, "step": 27400 }, { "epoch": 1.9325029426749354, "grad_norm": 0.6723042130470276, "learning_rate": 7.11725430479091e-05, "loss": 0.5687, "step": 27500 }, { "epoch": 1.9325029426749354, "eval_loss": 0.6017782092094421, "eval_runtime": 118.9577, "eval_samples_per_second": 106.332, "eval_steps_per_second": 13.299, "step": 27500 }, { "epoch": 1.9395302261028444, "grad_norm": 0.5766080617904663, "learning_rate": 7.070399437741596e-05, "loss": 0.5876, "step": 27600 }, { "epoch": 1.946557509530753, "grad_norm": 0.6501230597496033, "learning_rate": 7.02354457069228e-05, "loss": 0.5726, "step": 27700 }, { "epoch": 1.953584792958662, "grad_norm": 0.7194878458976746, "learning_rate": 6.976689703642966e-05, "loss": 0.5741, "step": 27800 }, { "epoch": 1.9606120763865709, "grad_norm": 0.8090994954109192, "learning_rate": 6.929834836593652e-05, "loss": 0.5764, "step": 27900 }, { "epoch": 1.9676393598144797, "grad_norm": 0.6500638127326965, "learning_rate": 6.882979969544337e-05, "loss": 0.5752, "step": 28000 }, { "epoch": 1.9676393598144797, "eval_loss": 0.6010117530822754, "eval_runtime": 119.0388, "eval_samples_per_second": 106.259, "eval_steps_per_second": 13.29, "step": 28000 }, { "epoch": 1.9746666432423887, "grad_norm": 0.7954403162002563, "learning_rate": 6.836125102495022e-05, "loss": 0.5698, "step": 28100 }, { "epoch": 1.9816939266702973, "grad_norm": 0.4845888316631317, "learning_rate": 6.789270235445707e-05, "loss": 0.5677, "step": 28200 }, { "epoch": 1.9887212100982063, "grad_norm": 0.7075939774513245, "learning_rate": 6.742415368396392e-05, "loss": 0.5736, "step": 28300 }, { "epoch": 1.9957484935261152, "grad_norm": 0.6423342823982239, "learning_rate": 6.695560501347079e-05, "loss": 0.5824, "step": 28400 }, { "epoch": 2.002775776954024, "grad_norm": 0.49882400035858154, "learning_rate": 6.648705634297762e-05, "loss": 0.5598, "step": 28500 }, { "epoch": 2.002775776954024, "eval_loss": 0.6018995642662048, "eval_runtime": 118.7564, "eval_samples_per_second": 106.512, "eval_steps_per_second": 13.321, "step": 28500 }, { "epoch": 2.009803060381933, "grad_norm": 0.6685127019882202, "learning_rate": 6.601850767248449e-05, "loss": 0.5498, "step": 28600 }, { "epoch": 2.0168303438098416, "grad_norm": 0.7776573896408081, "learning_rate": 6.554995900199134e-05, "loss": 0.541, "step": 28700 }, { "epoch": 2.0238576272377506, "grad_norm": 0.9224827885627747, "learning_rate": 6.508141033149819e-05, "loss": 0.5404, "step": 28800 }, { "epoch": 2.0308849106656592, "grad_norm": 0.6114927530288696, "learning_rate": 6.461286166100504e-05, "loss": 0.541, "step": 28900 }, { "epoch": 2.0379121940935683, "grad_norm": 0.6814767718315125, "learning_rate": 6.414431299051189e-05, "loss": 0.5397, "step": 29000 }, { "epoch": 2.0379121940935683, "eval_loss": 0.6046204566955566, "eval_runtime": 118.9324, "eval_samples_per_second": 106.355, "eval_steps_per_second": 13.302, "step": 29000 }, { "epoch": 2.0449394775214773, "grad_norm": 0.8734195232391357, "learning_rate": 6.367576432001875e-05, "loss": 0.5347, "step": 29100 }, { "epoch": 2.051966760949386, "grad_norm": 0.7100592255592346, "learning_rate": 6.32072156495256e-05, "loss": 0.5349, "step": 29200 }, { "epoch": 2.058994044377295, "grad_norm": 0.5094404816627502, "learning_rate": 6.273866697903245e-05, "loss": 0.5438, "step": 29300 }, { "epoch": 2.0660213278052035, "grad_norm": 0.5938568711280823, "learning_rate": 6.22701183085393e-05, "loss": 0.5367, "step": 29400 }, { "epoch": 2.0730486112331126, "grad_norm": 0.6052954196929932, "learning_rate": 6.180156963804615e-05, "loss": 0.533, "step": 29500 }, { "epoch": 2.0730486112331126, "eval_loss": 0.6042247414588928, "eval_runtime": 119.3016, "eval_samples_per_second": 106.025, "eval_steps_per_second": 13.261, "step": 29500 }, { "epoch": 2.0800758946610216, "grad_norm": 0.8204342126846313, "learning_rate": 6.133302096755302e-05, "loss": 0.5525, "step": 29600 }, { "epoch": 2.08710317808893, "grad_norm": 0.8169859647750854, "learning_rate": 6.086447229705986e-05, "loss": 0.5412, "step": 29700 }, { "epoch": 2.0941304615168392, "grad_norm": 0.6919510960578918, "learning_rate": 6.039592362656671e-05, "loss": 0.5395, "step": 29800 }, { "epoch": 2.101157744944748, "grad_norm": 0.6376796364784241, "learning_rate": 5.9927374956073566e-05, "loss": 0.5296, "step": 29900 }, { "epoch": 2.108185028372657, "grad_norm": 0.6056246161460876, "learning_rate": 5.9458826285580416e-05, "loss": 0.5257, "step": 30000 }, { "epoch": 2.108185028372657, "eval_loss": 0.6040454506874084, "eval_runtime": 119.4721, "eval_samples_per_second": 105.874, "eval_steps_per_second": 13.242, "step": 30000 }, { "epoch": 2.115212311800566, "grad_norm": 0.7951282858848572, "learning_rate": 5.899027761508727e-05, "loss": 0.5231, "step": 30100 }, { "epoch": 2.1222395952284745, "grad_norm": 0.7288519144058228, "learning_rate": 5.852172894459412e-05, "loss": 0.533, "step": 30200 }, { "epoch": 2.1292668786563835, "grad_norm": 0.62901371717453, "learning_rate": 5.8053180274100973e-05, "loss": 0.5475, "step": 30300 }, { "epoch": 2.136294162084292, "grad_norm": 0.7269171476364136, "learning_rate": 5.758463160360783e-05, "loss": 0.5469, "step": 30400 }, { "epoch": 2.143321445512201, "grad_norm": 0.8678474426269531, "learning_rate": 5.711608293311468e-05, "loss": 0.5396, "step": 30500 }, { "epoch": 2.143321445512201, "eval_loss": 0.6033341884613037, "eval_runtime": 119.4525, "eval_samples_per_second": 105.891, "eval_steps_per_second": 13.244, "step": 30500 }, { "epoch": 2.15034872894011, "grad_norm": 0.5461506843566895, "learning_rate": 5.664753426262154e-05, "loss": 0.5543, "step": 30600 }, { "epoch": 2.157376012368019, "grad_norm": 0.6282551884651184, "learning_rate": 5.617898559212839e-05, "loss": 0.519, "step": 30700 }, { "epoch": 2.164403295795928, "grad_norm": 0.5805559158325195, "learning_rate": 5.571043692163523e-05, "loss": 0.5359, "step": 30800 }, { "epoch": 2.1714305792238364, "grad_norm": 0.7047603726387024, "learning_rate": 5.5241888251142095e-05, "loss": 0.5244, "step": 30900 }, { "epoch": 2.1784578626517455, "grad_norm": 1.0538957118988037, "learning_rate": 5.477333958064894e-05, "loss": 0.5284, "step": 31000 }, { "epoch": 2.1784578626517455, "eval_loss": 0.6041498780250549, "eval_runtime": 119.3834, "eval_samples_per_second": 105.953, "eval_steps_per_second": 13.251, "step": 31000 }, { "epoch": 2.185485146079654, "grad_norm": 0.7913850545883179, "learning_rate": 5.43047909101558e-05, "loss": 0.5267, "step": 31100 }, { "epoch": 2.192512429507563, "grad_norm": 0.5944955348968506, "learning_rate": 5.3836242239662646e-05, "loss": 0.5359, "step": 31200 }, { "epoch": 2.199539712935472, "grad_norm": 0.8068099617958069, "learning_rate": 5.3367693569169496e-05, "loss": 0.5449, "step": 31300 }, { "epoch": 2.2065669963633807, "grad_norm": 0.5993140935897827, "learning_rate": 5.289914489867635e-05, "loss": 0.5384, "step": 31400 }, { "epoch": 2.2135942797912898, "grad_norm": 0.6852918267250061, "learning_rate": 5.24305962281832e-05, "loss": 0.5448, "step": 31500 }, { "epoch": 2.2135942797912898, "eval_loss": 0.6034653782844543, "eval_runtime": 119.4509, "eval_samples_per_second": 105.893, "eval_steps_per_second": 13.244, "step": 31500 }, { "epoch": 2.2206215632191983, "grad_norm": 0.9072486758232117, "learning_rate": 5.1962047557690054e-05, "loss": 0.5392, "step": 31600 }, { "epoch": 2.2276488466471074, "grad_norm": 0.5671890377998352, "learning_rate": 5.149349888719691e-05, "loss": 0.5366, "step": 31700 }, { "epoch": 2.2346761300750164, "grad_norm": 0.9552319049835205, "learning_rate": 5.102495021670376e-05, "loss": 0.555, "step": 31800 }, { "epoch": 2.241703413502925, "grad_norm": 0.9220768809318542, "learning_rate": 5.055640154621062e-05, "loss": 0.5323, "step": 31900 }, { "epoch": 2.248730696930834, "grad_norm": 0.7823670506477356, "learning_rate": 5.008785287571747e-05, "loss": 0.5484, "step": 32000 }, { "epoch": 2.248730696930834, "eval_loss": 0.602741539478302, "eval_runtime": 119.5139, "eval_samples_per_second": 105.837, "eval_steps_per_second": 13.237, "step": 32000 }, { "epoch": 2.2557579803587426, "grad_norm": 0.8530369400978088, "learning_rate": 4.961930420522432e-05, "loss": 0.5443, "step": 32100 }, { "epoch": 2.2627852637866517, "grad_norm": 0.8256222605705261, "learning_rate": 4.9150755534731175e-05, "loss": 0.5371, "step": 32200 }, { "epoch": 2.2698125472145607, "grad_norm": 0.8003319501876831, "learning_rate": 4.8682206864238025e-05, "loss": 0.5472, "step": 32300 }, { "epoch": 2.2768398306424693, "grad_norm": 0.6615211367607117, "learning_rate": 4.8213658193744876e-05, "loss": 0.5349, "step": 32400 }, { "epoch": 2.2838671140703783, "grad_norm": 0.7718948125839233, "learning_rate": 4.774510952325173e-05, "loss": 0.5253, "step": 32500 }, { "epoch": 2.2838671140703783, "eval_loss": 0.6034336090087891, "eval_runtime": 119.3326, "eval_samples_per_second": 105.998, "eval_steps_per_second": 13.257, "step": 32500 }, { "epoch": 2.290894397498287, "grad_norm": 0.6703356504440308, "learning_rate": 4.727656085275858e-05, "loss": 0.5356, "step": 32600 }, { "epoch": 2.297921680926196, "grad_norm": 0.6417832970619202, "learning_rate": 4.680801218226544e-05, "loss": 0.5456, "step": 32700 }, { "epoch": 2.3049489643541046, "grad_norm": 0.6749237775802612, "learning_rate": 4.633946351177228e-05, "loss": 0.5374, "step": 32800 }, { "epoch": 2.3119762477820136, "grad_norm": 0.6223445534706116, "learning_rate": 4.587091484127914e-05, "loss": 0.5254, "step": 32900 }, { "epoch": 2.3190035312099226, "grad_norm": 0.6455600261688232, "learning_rate": 4.540236617078599e-05, "loss": 0.5322, "step": 33000 }, { "epoch": 2.3190035312099226, "eval_loss": 0.602424144744873, "eval_runtime": 119.6802, "eval_samples_per_second": 105.69, "eval_steps_per_second": 13.219, "step": 33000 }, { "epoch": 2.3260308146378312, "grad_norm": 0.6882891058921814, "learning_rate": 4.493381750029285e-05, "loss": 0.5406, "step": 33100 }, { "epoch": 2.3330580980657403, "grad_norm": 0.7169196605682373, "learning_rate": 4.44652688297997e-05, "loss": 0.5367, "step": 33200 }, { "epoch": 2.3400853814936493, "grad_norm": 0.6603942513465881, "learning_rate": 4.399672015930655e-05, "loss": 0.5315, "step": 33300 }, { "epoch": 2.347112664921558, "grad_norm": 0.7974775433540344, "learning_rate": 4.3528171488813405e-05, "loss": 0.5438, "step": 33400 }, { "epoch": 2.354139948349467, "grad_norm": 0.7672884464263916, "learning_rate": 4.3059622818320255e-05, "loss": 0.5583, "step": 33500 }, { "epoch": 2.354139948349467, "eval_loss": 0.6008437871932983, "eval_runtime": 119.0367, "eval_samples_per_second": 106.261, "eval_steps_per_second": 13.29, "step": 33500 }, { "epoch": 2.3611672317773755, "grad_norm": 0.7062329649925232, "learning_rate": 4.259107414782711e-05, "loss": 0.5548, "step": 33600 }, { "epoch": 2.3681945152052846, "grad_norm": 0.754173219203949, "learning_rate": 4.212252547733396e-05, "loss": 0.5276, "step": 33700 }, { "epoch": 2.375221798633193, "grad_norm": 0.7143212556838989, "learning_rate": 4.165397680684081e-05, "loss": 0.5413, "step": 33800 }, { "epoch": 2.382249082061102, "grad_norm": 0.8082584142684937, "learning_rate": 4.118542813634766e-05, "loss": 0.534, "step": 33900 }, { "epoch": 2.3892763654890112, "grad_norm": 0.7493578791618347, "learning_rate": 4.071687946585452e-05, "loss": 0.5373, "step": 34000 }, { "epoch": 2.3892763654890112, "eval_loss": 0.6015102863311768, "eval_runtime": 119.2005, "eval_samples_per_second": 106.115, "eval_steps_per_second": 13.272, "step": 34000 }, { "epoch": 2.39630364891692, "grad_norm": 0.9309408068656921, "learning_rate": 4.024833079536137e-05, "loss": 0.5464, "step": 34100 }, { "epoch": 2.403330932344829, "grad_norm": 0.6309605240821838, "learning_rate": 3.977978212486822e-05, "loss": 0.5439, "step": 34200 }, { "epoch": 2.410358215772738, "grad_norm": 0.6428382992744446, "learning_rate": 3.931123345437507e-05, "loss": 0.5412, "step": 34300 }, { "epoch": 2.4173854992006465, "grad_norm": 0.9063606262207031, "learning_rate": 3.884268478388193e-05, "loss": 0.5477, "step": 34400 }, { "epoch": 2.4244127826285555, "grad_norm": 0.7051374316215515, "learning_rate": 3.837413611338878e-05, "loss": 0.5351, "step": 34500 }, { "epoch": 2.4244127826285555, "eval_loss": 0.6011614203453064, "eval_runtime": 119.6428, "eval_samples_per_second": 105.723, "eval_steps_per_second": 13.223, "step": 34500 }, { "epoch": 2.431440066056464, "grad_norm": 0.7466573119163513, "learning_rate": 3.7905587442895635e-05, "loss": 0.5525, "step": 34600 }, { "epoch": 2.438467349484373, "grad_norm": 0.8113718628883362, "learning_rate": 3.7437038772402485e-05, "loss": 0.553, "step": 34700 }, { "epoch": 2.4454946329122818, "grad_norm": 0.5469939112663269, "learning_rate": 3.6968490101909335e-05, "loss": 0.5438, "step": 34800 }, { "epoch": 2.452521916340191, "grad_norm": 0.6911020278930664, "learning_rate": 3.649994143141619e-05, "loss": 0.5349, "step": 34900 }, { "epoch": 2.4595491997681, "grad_norm": 0.7164533734321594, "learning_rate": 3.603139276092304e-05, "loss": 0.5237, "step": 35000 }, { "epoch": 2.4595491997681, "eval_loss": 0.6016719937324524, "eval_runtime": 119.4046, "eval_samples_per_second": 105.934, "eval_steps_per_second": 13.249, "step": 35000 }, { "epoch": 2.4665764831960084, "grad_norm": 0.8674111366271973, "learning_rate": 3.55628440904299e-05, "loss": 0.5469, "step": 35100 }, { "epoch": 2.4736037666239175, "grad_norm": 0.9044885039329529, "learning_rate": 3.509429541993674e-05, "loss": 0.5445, "step": 35200 }, { "epoch": 2.480631050051826, "grad_norm": 0.7213521599769592, "learning_rate": 3.46257467494436e-05, "loss": 0.5136, "step": 35300 }, { "epoch": 2.487658333479735, "grad_norm": 0.6873759627342224, "learning_rate": 3.415719807895045e-05, "loss": 0.5362, "step": 35400 }, { "epoch": 2.494685616907644, "grad_norm": 0.6950516104698181, "learning_rate": 3.368864940845731e-05, "loss": 0.535, "step": 35500 }, { "epoch": 2.494685616907644, "eval_loss": 0.6001349091529846, "eval_runtime": 119.0417, "eval_samples_per_second": 106.257, "eval_steps_per_second": 13.289, "step": 35500 }, { "epoch": 2.5017129003355527, "grad_norm": 0.6840397715568542, "learning_rate": 3.322010073796416e-05, "loss": 0.5385, "step": 35600 }, { "epoch": 2.5087401837634618, "grad_norm": 0.5907210111618042, "learning_rate": 3.275155206747101e-05, "loss": 0.5429, "step": 35700 }, { "epoch": 2.5157674671913703, "grad_norm": 0.801002025604248, "learning_rate": 3.2283003396977865e-05, "loss": 0.5224, "step": 35800 }, { "epoch": 2.5227947506192794, "grad_norm": 0.7259572148323059, "learning_rate": 3.1814454726484715e-05, "loss": 0.5297, "step": 35900 }, { "epoch": 2.5298220340471884, "grad_norm": 0.6602583527565002, "learning_rate": 3.134590605599157e-05, "loss": 0.5496, "step": 36000 }, { "epoch": 2.5298220340471884, "eval_loss": 0.5990512371063232, "eval_runtime": 118.9771, "eval_samples_per_second": 106.315, "eval_steps_per_second": 13.297, "step": 36000 }, { "epoch": 2.536849317475097, "grad_norm": 0.6192248463630676, "learning_rate": 3.0877357385498415e-05, "loss": 0.5432, "step": 36100 }, { "epoch": 2.543876600903006, "grad_norm": 1.0253371000289917, "learning_rate": 3.0408808715005272e-05, "loss": 0.5254, "step": 36200 }, { "epoch": 2.5509038843309146, "grad_norm": 0.8612440228462219, "learning_rate": 2.9940260044512126e-05, "loss": 0.56, "step": 36300 }, { "epoch": 2.5579311677588237, "grad_norm": 0.5663143992424011, "learning_rate": 2.947171137401898e-05, "loss": 0.5329, "step": 36400 }, { "epoch": 2.5649584511867323, "grad_norm": 0.9142153263092041, "learning_rate": 2.9003162703525833e-05, "loss": 0.5384, "step": 36500 }, { "epoch": 2.5649584511867323, "eval_loss": 0.5994681715965271, "eval_runtime": 119.2506, "eval_samples_per_second": 106.071, "eval_steps_per_second": 13.266, "step": 36500 }, { "epoch": 2.5719857346146413, "grad_norm": 0.6240784525871277, "learning_rate": 2.853461403303268e-05, "loss": 0.5332, "step": 36600 }, { "epoch": 2.5790130180425503, "grad_norm": 0.7204896211624146, "learning_rate": 2.8066065362539534e-05, "loss": 0.534, "step": 36700 }, { "epoch": 2.586040301470459, "grad_norm": 0.8071198463439941, "learning_rate": 2.7597516692046387e-05, "loss": 0.533, "step": 36800 }, { "epoch": 2.593067584898368, "grad_norm": 0.5369657278060913, "learning_rate": 2.712896802155324e-05, "loss": 0.5325, "step": 36900 }, { "epoch": 2.600094868326277, "grad_norm": 0.8969751000404358, "learning_rate": 2.6660419351060095e-05, "loss": 0.5349, "step": 37000 }, { "epoch": 2.600094868326277, "eval_loss": 0.5992428064346313, "eval_runtime": 119.3558, "eval_samples_per_second": 105.977, "eval_steps_per_second": 13.254, "step": 37000 }, { "epoch": 2.6071221517541856, "grad_norm": 0.8350916504859924, "learning_rate": 2.6191870680566945e-05, "loss": 0.5388, "step": 37100 }, { "epoch": 2.6141494351820946, "grad_norm": 0.5793244242668152, "learning_rate": 2.57233220100738e-05, "loss": 0.5211, "step": 37200 }, { "epoch": 2.6211767186100032, "grad_norm": 0.6331949830055237, "learning_rate": 2.5254773339580652e-05, "loss": 0.5335, "step": 37300 }, { "epoch": 2.6282040020379123, "grad_norm": 0.799247145652771, "learning_rate": 2.4786224669087502e-05, "loss": 0.5474, "step": 37400 }, { "epoch": 2.635231285465821, "grad_norm": 0.7149389386177063, "learning_rate": 2.4317675998594356e-05, "loss": 0.5316, "step": 37500 }, { "epoch": 2.635231285465821, "eval_loss": 0.5990239977836609, "eval_runtime": 119.2093, "eval_samples_per_second": 106.107, "eval_steps_per_second": 13.271, "step": 37500 }, { "epoch": 2.64225856889373, "grad_norm": 0.6996687650680542, "learning_rate": 2.384912732810121e-05, "loss": 0.5244, "step": 37600 }, { "epoch": 2.649285852321639, "grad_norm": 0.6374346017837524, "learning_rate": 2.338057865760806e-05, "loss": 0.5221, "step": 37700 }, { "epoch": 2.6563131357495475, "grad_norm": 0.7678332328796387, "learning_rate": 2.2912029987114913e-05, "loss": 0.5251, "step": 37800 }, { "epoch": 2.6633404191774566, "grad_norm": 0.6463155150413513, "learning_rate": 2.2443481316621764e-05, "loss": 0.5343, "step": 37900 }, { "epoch": 2.6703677026053656, "grad_norm": 0.6788434386253357, "learning_rate": 2.1974932646128617e-05, "loss": 0.5276, "step": 38000 }, { "epoch": 2.6703677026053656, "eval_loss": 0.5986095070838928, "eval_runtime": 119.1797, "eval_samples_per_second": 106.134, "eval_steps_per_second": 13.274, "step": 38000 }, { "epoch": 2.677394986033274, "grad_norm": 0.7115055322647095, "learning_rate": 2.1506383975635467e-05, "loss": 0.5583, "step": 38100 }, { "epoch": 2.684422269461183, "grad_norm": 0.7007845044136047, "learning_rate": 2.103783530514232e-05, "loss": 0.5294, "step": 38200 }, { "epoch": 2.691449552889092, "grad_norm": 1.0714610815048218, "learning_rate": 2.0569286634649178e-05, "loss": 0.54, "step": 38300 }, { "epoch": 2.698476836317001, "grad_norm": 0.6736337542533875, "learning_rate": 2.0100737964156028e-05, "loss": 0.5343, "step": 38400 }, { "epoch": 2.7055041197449095, "grad_norm": 0.6769545078277588, "learning_rate": 1.9632189293662882e-05, "loss": 0.5406, "step": 38500 }, { "epoch": 2.7055041197449095, "eval_loss": 0.5980576276779175, "eval_runtime": 119.2056, "eval_samples_per_second": 106.111, "eval_steps_per_second": 13.271, "step": 38500 }, { "epoch": 2.7125314031728185, "grad_norm": 0.714820384979248, "learning_rate": 1.9163640623169732e-05, "loss": 0.5408, "step": 38600 }, { "epoch": 2.7195586866007275, "grad_norm": 0.5211949944496155, "learning_rate": 1.8695091952676586e-05, "loss": 0.5257, "step": 38700 }, { "epoch": 2.726585970028636, "grad_norm": 0.7966856360435486, "learning_rate": 1.8226543282183436e-05, "loss": 0.5381, "step": 38800 }, { "epoch": 2.733613253456545, "grad_norm": 0.7282027006149292, "learning_rate": 1.775799461169029e-05, "loss": 0.5415, "step": 38900 }, { "epoch": 2.7406405368844537, "grad_norm": 0.7190561890602112, "learning_rate": 1.7289445941197143e-05, "loss": 0.5436, "step": 39000 }, { "epoch": 2.7406405368844537, "eval_loss": 0.5981852412223816, "eval_runtime": 119.2717, "eval_samples_per_second": 106.052, "eval_steps_per_second": 13.264, "step": 39000 }, { "epoch": 2.747667820312363, "grad_norm": 0.6859644651412964, "learning_rate": 1.6820897270703993e-05, "loss": 0.5371, "step": 39100 }, { "epoch": 2.7546951037402714, "grad_norm": 0.6917553544044495, "learning_rate": 1.6352348600210847e-05, "loss": 0.5411, "step": 39200 }, { "epoch": 2.7617223871681804, "grad_norm": 0.5737515687942505, "learning_rate": 1.58837999297177e-05, "loss": 0.5244, "step": 39300 }, { "epoch": 2.7687496705960895, "grad_norm": 0.7747429013252258, "learning_rate": 1.5415251259224554e-05, "loss": 0.5452, "step": 39400 }, { "epoch": 2.775776954023998, "grad_norm": 0.6782782673835754, "learning_rate": 1.4946702588731405e-05, "loss": 0.5392, "step": 39500 }, { "epoch": 2.775776954023998, "eval_loss": 0.597685694694519, "eval_runtime": 119.3501, "eval_samples_per_second": 105.982, "eval_steps_per_second": 13.255, "step": 39500 }, { "epoch": 2.782804237451907, "grad_norm": 0.6675652265548706, "learning_rate": 1.4478153918238258e-05, "loss": 0.534, "step": 39600 }, { "epoch": 2.789831520879816, "grad_norm": 0.822902262210846, "learning_rate": 1.4009605247745112e-05, "loss": 0.5582, "step": 39700 }, { "epoch": 2.7968588043077247, "grad_norm": 0.6393033266067505, "learning_rate": 1.3541056577251962e-05, "loss": 0.5442, "step": 39800 }, { "epoch": 2.8038860877356337, "grad_norm": 0.744646430015564, "learning_rate": 1.3072507906758816e-05, "loss": 0.537, "step": 39900 }, { "epoch": 2.8109133711635423, "grad_norm": 0.5728178024291992, "learning_rate": 1.2603959236265666e-05, "loss": 0.5316, "step": 40000 }, { "epoch": 2.8109133711635423, "eval_loss": 0.5975730419158936, "eval_runtime": 119.1706, "eval_samples_per_second": 106.142, "eval_steps_per_second": 13.275, "step": 40000 }, { "epoch": 2.8179406545914514, "grad_norm": 0.6350817680358887, "learning_rate": 1.2135410565772521e-05, "loss": 0.5345, "step": 40100 }, { "epoch": 2.82496793801936, "grad_norm": 0.5875131487846375, "learning_rate": 1.1666861895279373e-05, "loss": 0.5336, "step": 40200 }, { "epoch": 2.831995221447269, "grad_norm": 0.7108073234558105, "learning_rate": 1.1198313224786225e-05, "loss": 0.5364, "step": 40300 }, { "epoch": 2.839022504875178, "grad_norm": 0.5973334312438965, "learning_rate": 1.0729764554293077e-05, "loss": 0.5468, "step": 40400 }, { "epoch": 2.8460497883030866, "grad_norm": 0.7775806784629822, "learning_rate": 1.026121588379993e-05, "loss": 0.5349, "step": 40500 }, { "epoch": 2.8460497883030866, "eval_loss": 0.5973463654518127, "eval_runtime": 119.0857, "eval_samples_per_second": 106.218, "eval_steps_per_second": 13.285, "step": 40500 }, { "epoch": 2.8530770717309957, "grad_norm": 0.6160515546798706, "learning_rate": 9.792667213306782e-06, "loss": 0.5317, "step": 40600 }, { "epoch": 2.8601043551589047, "grad_norm": 0.715397834777832, "learning_rate": 9.324118542813636e-06, "loss": 0.5119, "step": 40700 }, { "epoch": 2.8671316385868133, "grad_norm": 0.7450791001319885, "learning_rate": 8.855569872320488e-06, "loss": 0.5302, "step": 40800 }, { "epoch": 2.874158922014722, "grad_norm": 0.5536558628082275, "learning_rate": 8.38702120182734e-06, "loss": 0.5239, "step": 40900 }, { "epoch": 2.881186205442631, "grad_norm": 0.5844016075134277, "learning_rate": 7.918472531334192e-06, "loss": 0.5341, "step": 41000 }, { "epoch": 2.881186205442631, "eval_loss": 0.5972412824630737, "eval_runtime": 119.0402, "eval_samples_per_second": 106.258, "eval_steps_per_second": 13.29, "step": 41000 }, { "epoch": 2.88821348887054, "grad_norm": 0.566956639289856, "learning_rate": 7.449923860841045e-06, "loss": 0.5387, "step": 41100 }, { "epoch": 2.8952407722984486, "grad_norm": 0.6934293508529663, "learning_rate": 6.981375190347898e-06, "loss": 0.5185, "step": 41200 }, { "epoch": 2.9022680557263576, "grad_norm": 0.6890417337417603, "learning_rate": 6.51282651985475e-06, "loss": 0.5419, "step": 41300 }, { "epoch": 2.9092953391542666, "grad_norm": 0.8735133409500122, "learning_rate": 6.044277849361603e-06, "loss": 0.5314, "step": 41400 }, { "epoch": 2.9163226225821752, "grad_norm": 0.746161162853241, "learning_rate": 5.575729178868455e-06, "loss": 0.5208, "step": 41500 }, { "epoch": 2.9163226225821752, "eval_loss": 0.5972864031791687, "eval_runtime": 118.9512, "eval_samples_per_second": 106.338, "eval_steps_per_second": 13.3, "step": 41500 }, { "epoch": 2.9233499060100843, "grad_norm": 0.9560967683792114, "learning_rate": 5.107180508375308e-06, "loss": 0.5505, "step": 41600 }, { "epoch": 2.930377189437993, "grad_norm": 0.7499198317527771, "learning_rate": 4.63863183788216e-06, "loss": 0.5378, "step": 41700 }, { "epoch": 2.937404472865902, "grad_norm": 0.6939593553543091, "learning_rate": 4.170083167389012e-06, "loss": 0.5351, "step": 41800 }, { "epoch": 2.9444317562938105, "grad_norm": 0.6184145212173462, "learning_rate": 3.701534496895865e-06, "loss": 0.5171, "step": 41900 }, { "epoch": 2.9514590397217195, "grad_norm": 0.6636520624160767, "learning_rate": 3.232985826402718e-06, "loss": 0.53, "step": 42000 }, { "epoch": 2.9514590397217195, "eval_loss": 0.5971269607543945, "eval_runtime": 118.9184, "eval_samples_per_second": 106.367, "eval_steps_per_second": 13.303, "step": 42000 }, { "epoch": 2.9584863231496286, "grad_norm": 0.8458754420280457, "learning_rate": 2.76443715590957e-06, "loss": 0.5447, "step": 42100 }, { "epoch": 2.965513606577537, "grad_norm": 0.6426025032997131, "learning_rate": 2.295888485416423e-06, "loss": 0.5287, "step": 42200 }, { "epoch": 2.972540890005446, "grad_norm": 0.7159422039985657, "learning_rate": 1.827339814923275e-06, "loss": 0.5288, "step": 42300 }, { "epoch": 2.9795681734333552, "grad_norm": 0.6702597141265869, "learning_rate": 1.3587911444301279e-06, "loss": 0.5419, "step": 42400 }, { "epoch": 2.986595456861264, "grad_norm": 0.7953273057937622, "learning_rate": 8.902424739369803e-07, "loss": 0.5445, "step": 42500 }, { "epoch": 2.986595456861264, "eval_loss": 0.5969375371932983, "eval_runtime": 119.2187, "eval_samples_per_second": 106.099, "eval_steps_per_second": 13.27, "step": 42500 }, { "epoch": 2.993622740289173, "grad_norm": 0.5247675180435181, "learning_rate": 4.216938034438327e-07, "loss": 0.5485, "step": 42600 } ], "logging_steps": 100, "max_steps": 42690, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 1.4552903446892544e+17, "train_batch_size": 2, "trial_name": null, "trial_params": null }