| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.9931630082763583, |
| "eval_steps": 500, |
| "global_step": 1041, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01439366678661389, |
| "grad_norm": 0.2171054631471634, |
| "learning_rate": 1.5625e-06, |
| "loss": 0.7856, |
| "num_input_tokens_seen": 1344864, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.02878733357322778, |
| "grad_norm": 0.14643871784210205, |
| "learning_rate": 3.125e-06, |
| "loss": 0.7815, |
| "num_input_tokens_seen": 2610336, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.04318100035984167, |
| "grad_norm": 0.08721674233675003, |
| "learning_rate": 4.6875000000000004e-06, |
| "loss": 0.7299, |
| "num_input_tokens_seen": 3942464, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.05757466714645556, |
| "grad_norm": 0.057898711413145065, |
| "learning_rate": 6.25e-06, |
| "loss": 0.6649, |
| "num_input_tokens_seen": 5290176, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.07196833393306945, |
| "grad_norm": 0.06339031457901001, |
| "learning_rate": 7.8125e-06, |
| "loss": 0.6129, |
| "num_input_tokens_seen": 6599904, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.08636200071968334, |
| "grad_norm": 0.04165177047252655, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 0.5695, |
| "num_input_tokens_seen": 7953088, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.10075566750629723, |
| "grad_norm": 0.032423749566078186, |
| "learning_rate": 9.99978187935494e-06, |
| "loss": 0.5424, |
| "num_input_tokens_seen": 9272512, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.11514933429291112, |
| "grad_norm": 0.03219545632600784, |
| "learning_rate": 9.998448988774289e-06, |
| "loss": 0.5248, |
| "num_input_tokens_seen": 10609728, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.12954300107952502, |
| "grad_norm": 0.022432563826441765, |
| "learning_rate": 9.99590470838777e-06, |
| "loss": 0.5156, |
| "num_input_tokens_seen": 11942432, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.1439366678661389, |
| "grad_norm": 0.024161117151379585, |
| "learning_rate": 9.99214965480972e-06, |
| "loss": 0.511, |
| "num_input_tokens_seen": 13244192, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.15833033465275279, |
| "grad_norm": 0.020490078255534172, |
| "learning_rate": 9.987184738089166e-06, |
| "loss": 0.5043, |
| "num_input_tokens_seen": 14608992, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.17272400143936667, |
| "grad_norm": 0.020698031410574913, |
| "learning_rate": 9.981011161489262e-06, |
| "loss": 0.4918, |
| "num_input_tokens_seen": 15935040, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.18711766822598058, |
| "grad_norm": 0.022265350446105003, |
| "learning_rate": 9.973630421195679e-06, |
| "loss": 0.4842, |
| "num_input_tokens_seen": 17230080, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.20151133501259447, |
| "grad_norm": 0.021687887609004974, |
| "learning_rate": 9.965044305954002e-06, |
| "loss": 0.4874, |
| "num_input_tokens_seen": 18514400, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.21590500179920835, |
| "grad_norm": 0.020277954638004303, |
| "learning_rate": 9.955254896636217e-06, |
| "loss": 0.4777, |
| "num_input_tokens_seen": 19896928, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.23029866858582224, |
| "grad_norm": 0.019190184772014618, |
| "learning_rate": 9.944264565736406e-06, |
| "loss": 0.4779, |
| "num_input_tokens_seen": 21225632, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.24469233537243612, |
| "grad_norm": 0.022239679470658302, |
| "learning_rate": 9.93207597679577e-06, |
| "loss": 0.4758, |
| "num_input_tokens_seen": 22554912, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.25908600215905003, |
| "grad_norm": 0.020835548639297485, |
| "learning_rate": 9.918692083757105e-06, |
| "loss": 0.4724, |
| "num_input_tokens_seen": 23877056, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2734796689456639, |
| "grad_norm": 0.02221113070845604, |
| "learning_rate": 9.904116130248913e-06, |
| "loss": 0.4671, |
| "num_input_tokens_seen": 25170944, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.2878733357322778, |
| "grad_norm": 0.02158268541097641, |
| "learning_rate": 9.888351648799288e-06, |
| "loss": 0.4667, |
| "num_input_tokens_seen": 26483136, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3022670025188917, |
| "grad_norm": 0.022542718797922134, |
| "learning_rate": 9.871402459979804e-06, |
| "loss": 0.4724, |
| "num_input_tokens_seen": 27788864, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.31666066930550557, |
| "grad_norm": 0.023939669132232666, |
| "learning_rate": 9.853272671479588e-06, |
| "loss": 0.4612, |
| "num_input_tokens_seen": 29122624, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3310543360921195, |
| "grad_norm": 0.0231157299131155, |
| "learning_rate": 9.833966677109805e-06, |
| "loss": 0.4628, |
| "num_input_tokens_seen": 30425088, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.34544800287873334, |
| "grad_norm": 0.023111021146178246, |
| "learning_rate": 9.813489155738801e-06, |
| "loss": 0.4565, |
| "num_input_tokens_seen": 31758464, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.35984166966534725, |
| "grad_norm": 0.027539370581507683, |
| "learning_rate": 9.791845070158175e-06, |
| "loss": 0.4634, |
| "num_input_tokens_seen": 33056384, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.37423533645196116, |
| "grad_norm": 0.02168864756822586, |
| "learning_rate": 9.769039665880024e-06, |
| "loss": 0.4519, |
| "num_input_tokens_seen": 34398336, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.388629003238575, |
| "grad_norm": 0.02182694338262081, |
| "learning_rate": 9.745078469865673e-06, |
| "loss": 0.4498, |
| "num_input_tokens_seen": 35751168, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.40302267002518893, |
| "grad_norm": 0.02402554452419281, |
| "learning_rate": 9.719967289186211e-06, |
| "loss": 0.4495, |
| "num_input_tokens_seen": 37065920, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4174163368118028, |
| "grad_norm": 0.023280750960111618, |
| "learning_rate": 9.69371220961511e-06, |
| "loss": 0.4485, |
| "num_input_tokens_seen": 38387392, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.4318100035984167, |
| "grad_norm": 0.023174723610281944, |
| "learning_rate": 9.666319594153342e-06, |
| "loss": 0.4512, |
| "num_input_tokens_seen": 39642272, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.44620367038503056, |
| "grad_norm": 0.02440543845295906, |
| "learning_rate": 9.637796081487263e-06, |
| "loss": 0.4452, |
| "num_input_tokens_seen": 40974912, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.46059733717164447, |
| "grad_norm": 0.022896092385053635, |
| "learning_rate": 9.608148584379724e-06, |
| "loss": 0.447, |
| "num_input_tokens_seen": 42268032, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.4749910039582584, |
| "grad_norm": 0.022509625181555748, |
| "learning_rate": 9.577384287994733e-06, |
| "loss": 0.4451, |
| "num_input_tokens_seen": 43600032, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.48938467074487224, |
| "grad_norm": 0.023523326963186264, |
| "learning_rate": 9.545510648156106e-06, |
| "loss": 0.4425, |
| "num_input_tokens_seen": 44907424, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5037783375314862, |
| "grad_norm": 0.021728025749325752, |
| "learning_rate": 9.512535389540532e-06, |
| "loss": 0.4463, |
| "num_input_tokens_seen": 46205760, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.5181720043181001, |
| "grad_norm": 0.024059342220425606, |
| "learning_rate": 9.478466503805467e-06, |
| "loss": 0.4453, |
| "num_input_tokens_seen": 47539584, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.532565671104714, |
| "grad_norm": 0.02262093313038349, |
| "learning_rate": 9.443312247652335e-06, |
| "loss": 0.4434, |
| "num_input_tokens_seen": 48862784, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.5469593378913278, |
| "grad_norm": 0.022450478747487068, |
| "learning_rate": 9.407081140825485e-06, |
| "loss": 0.4478, |
| "num_input_tokens_seen": 50147328, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5613530046779417, |
| "grad_norm": 0.024132946506142616, |
| "learning_rate": 9.36978196404741e-06, |
| "loss": 0.4365, |
| "num_input_tokens_seen": 51466592, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.5757466714645556, |
| "grad_norm": 0.023225655779242516, |
| "learning_rate": 9.331423756890715e-06, |
| "loss": 0.4373, |
| "num_input_tokens_seen": 52771040, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.5901403382511695, |
| "grad_norm": 0.022450394928455353, |
| "learning_rate": 9.292015815587326e-06, |
| "loss": 0.4371, |
| "num_input_tokens_seen": 54068448, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.6045340050377834, |
| "grad_norm": 0.023069795221090317, |
| "learning_rate": 9.251567690775554e-06, |
| "loss": 0.4455, |
| "num_input_tokens_seen": 55357024, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.6189276718243972, |
| "grad_norm": 0.022140709683299065, |
| "learning_rate": 9.210089185185436e-06, |
| "loss": 0.4374, |
| "num_input_tokens_seen": 56672224, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.6333213386110111, |
| "grad_norm": 0.024554293602705002, |
| "learning_rate": 9.167590351263031e-06, |
| "loss": 0.4376, |
| "num_input_tokens_seen": 58019776, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.647715005397625, |
| "grad_norm": 0.023237934336066246, |
| "learning_rate": 9.124081488734173e-06, |
| "loss": 0.4445, |
| "num_input_tokens_seen": 59296576, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.662108672184239, |
| "grad_norm": 0.022342730313539505, |
| "learning_rate": 9.0795731421083e-06, |
| "loss": 0.4328, |
| "num_input_tokens_seen": 60602464, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.6765023389708529, |
| "grad_norm": 0.02406766451895237, |
| "learning_rate": 9.034076098122954e-06, |
| "loss": 0.4324, |
| "num_input_tokens_seen": 61909408, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.6908960057574667, |
| "grad_norm": 0.024235686287283897, |
| "learning_rate": 8.987601383129597e-06, |
| "loss": 0.439, |
| "num_input_tokens_seen": 63190624, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7052896725440806, |
| "grad_norm": 0.02430051937699318, |
| "learning_rate": 8.940160260421315e-06, |
| "loss": 0.4368, |
| "num_input_tokens_seen": 64515360, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.7196833393306945, |
| "grad_norm": 0.0284462608397007, |
| "learning_rate": 8.891764227503148e-06, |
| "loss": 0.4353, |
| "num_input_tokens_seen": 65839808, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7340770061173084, |
| "grad_norm": 0.02868458814918995, |
| "learning_rate": 8.842425013305624e-06, |
| "loss": 0.438, |
| "num_input_tokens_seen": 67134624, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.7484706729039223, |
| "grad_norm": 0.023997368291020393, |
| "learning_rate": 8.79215457534221e-06, |
| "loss": 0.4329, |
| "num_input_tokens_seen": 68459808, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.7628643396905361, |
| "grad_norm": 0.02359464205801487, |
| "learning_rate": 8.740965096811376e-06, |
| "loss": 0.4303, |
| "num_input_tokens_seen": 69771232, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.77725800647715, |
| "grad_norm": 0.02255072444677353, |
| "learning_rate": 8.688868983643966e-06, |
| "loss": 0.4347, |
| "num_input_tokens_seen": 71097184, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.791651673263764, |
| "grad_norm": 0.02909056842327118, |
| "learning_rate": 8.635878861496566e-06, |
| "loss": 0.4295, |
| "num_input_tokens_seen": 72420160, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.8060453400503779, |
| "grad_norm": 0.02871478721499443, |
| "learning_rate": 8.582007572691655e-06, |
| "loss": 0.4357, |
| "num_input_tokens_seen": 73747168, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8204390068369917, |
| "grad_norm": 0.024725815281271935, |
| "learning_rate": 8.52726817310521e-06, |
| "loss": 0.434, |
| "num_input_tokens_seen": 75051072, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.8348326736236056, |
| "grad_norm": 0.02208642102777958, |
| "learning_rate": 8.47167392900258e-06, |
| "loss": 0.4292, |
| "num_input_tokens_seen": 76366528, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.8492263404102195, |
| "grad_norm": 0.021869095042347908, |
| "learning_rate": 8.415238313823375e-06, |
| "loss": 0.4316, |
| "num_input_tokens_seen": 77698080, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.8636200071968334, |
| "grad_norm": 0.02422597073018551, |
| "learning_rate": 8.357975004916122e-06, |
| "loss": 0.4358, |
| "num_input_tokens_seen": 79019904, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.8780136739834473, |
| "grad_norm": 0.02404642663896084, |
| "learning_rate": 8.29989788022352e-06, |
| "loss": 0.4257, |
| "num_input_tokens_seen": 80331968, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.8924073407700611, |
| "grad_norm": 0.02266016975045204, |
| "learning_rate": 8.241021014919085e-06, |
| "loss": 0.4327, |
| "num_input_tokens_seen": 81645536, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.906801007556675, |
| "grad_norm": 0.02396400086581707, |
| "learning_rate": 8.18135867799597e-06, |
| "loss": 0.4221, |
| "num_input_tokens_seen": 82977024, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.9211946743432889, |
| "grad_norm": 0.023356642574071884, |
| "learning_rate": 8.120925328808855e-06, |
| "loss": 0.4208, |
| "num_input_tokens_seen": 84297760, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9355883411299029, |
| "grad_norm": 0.022813964635133743, |
| "learning_rate": 8.059735613569651e-06, |
| "loss": 0.4274, |
| "num_input_tokens_seen": 85651136, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.9499820079165168, |
| "grad_norm": 0.024049192667007446, |
| "learning_rate": 7.997804361797964e-06, |
| "loss": 0.4244, |
| "num_input_tokens_seen": 86960544, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.9643756747031306, |
| "grad_norm": 0.026242297142744064, |
| "learning_rate": 7.935146582727103e-06, |
| "loss": 0.4209, |
| "num_input_tokens_seen": 88266560, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.9787693414897445, |
| "grad_norm": 0.02622361294925213, |
| "learning_rate": 7.87177746166655e-06, |
| "loss": 0.4284, |
| "num_input_tokens_seen": 89625792, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.9931630082763584, |
| "grad_norm": 0.024003153666853905, |
| "learning_rate": 7.80771235632175e-06, |
| "loss": 0.4215, |
| "num_input_tokens_seen": 90982112, |
| "step": 345 |
| }, |
| { |
| "epoch": 1.0057574667146456, |
| "grad_norm": 0.023372355848550797, |
| "learning_rate": 7.742966793072131e-06, |
| "loss": 0.4126, |
| "num_input_tokens_seen": 92150080, |
| "step": 350 |
| }, |
| { |
| "epoch": 1.0201511335012594, |
| "grad_norm": 0.027405107393860817, |
| "learning_rate": 7.677556463208221e-06, |
| "loss": 0.4132, |
| "num_input_tokens_seen": 93492992, |
| "step": 355 |
| }, |
| { |
| "epoch": 1.0345448002878734, |
| "grad_norm": 0.024137645959854126, |
| "learning_rate": 7.61149721912883e-06, |
| "loss": 0.4077, |
| "num_input_tokens_seen": 94826144, |
| "step": 360 |
| }, |
| { |
| "epoch": 1.0489384670744872, |
| "grad_norm": 0.02278914861381054, |
| "learning_rate": 7.544805070499166e-06, |
| "loss": 0.41, |
| "num_input_tokens_seen": 96118176, |
| "step": 365 |
| }, |
| { |
| "epoch": 1.063332133861101, |
| "grad_norm": 0.025209598243236542, |
| "learning_rate": 7.477496180370838e-06, |
| "loss": 0.4096, |
| "num_input_tokens_seen": 97416544, |
| "step": 370 |
| }, |
| { |
| "epoch": 1.077725800647715, |
| "grad_norm": 0.02380400151014328, |
| "learning_rate": 7.409586861264696e-06, |
| "loss": 0.4032, |
| "num_input_tokens_seen": 98709184, |
| "step": 375 |
| }, |
| { |
| "epoch": 1.0921194674343289, |
| "grad_norm": 0.023542974144220352, |
| "learning_rate": 7.3410935712174405e-06, |
| "loss": 0.4085, |
| "num_input_tokens_seen": 100030944, |
| "step": 380 |
| }, |
| { |
| "epoch": 1.1065131342209429, |
| "grad_norm": 0.022723505273461342, |
| "learning_rate": 7.272032909792956e-06, |
| "loss": 0.4068, |
| "num_input_tokens_seen": 101338976, |
| "step": 385 |
| }, |
| { |
| "epoch": 1.1209068010075567, |
| "grad_norm": 0.02252861298620701, |
| "learning_rate": 7.202421614059369e-06, |
| "loss": 0.4138, |
| "num_input_tokens_seen": 102671264, |
| "step": 390 |
| }, |
| { |
| "epoch": 1.1353004677941705, |
| "grad_norm": 0.022021252661943436, |
| "learning_rate": 7.1322765545327555e-06, |
| "loss": 0.4138, |
| "num_input_tokens_seen": 103992480, |
| "step": 395 |
| }, |
| { |
| "epoch": 1.1496941345807845, |
| "grad_norm": 0.02324511669576168, |
| "learning_rate": 7.061614731088523e-06, |
| "loss": 0.4042, |
| "num_input_tokens_seen": 105268512, |
| "step": 400 |
| }, |
| { |
| "epoch": 1.1640878013673983, |
| "grad_norm": 0.02369946427643299, |
| "learning_rate": 6.990453268841438e-06, |
| "loss": 0.4053, |
| "num_input_tokens_seen": 106601248, |
| "step": 405 |
| }, |
| { |
| "epoch": 1.1784814681540121, |
| "grad_norm": 0.024191929027438164, |
| "learning_rate": 6.918809413995299e-06, |
| "loss": 0.407, |
| "num_input_tokens_seen": 107951040, |
| "step": 410 |
| }, |
| { |
| "epoch": 1.1928751349406261, |
| "grad_norm": 0.022732459008693695, |
| "learning_rate": 6.846700529663265e-06, |
| "loss": 0.4042, |
| "num_input_tokens_seen": 109235744, |
| "step": 415 |
| }, |
| { |
| "epoch": 1.20726880172724, |
| "grad_norm": 0.02548997662961483, |
| "learning_rate": 6.774144091659853e-06, |
| "loss": 0.4047, |
| "num_input_tokens_seen": 110547552, |
| "step": 420 |
| }, |
| { |
| "epoch": 1.221662468513854, |
| "grad_norm": 0.022845694795250893, |
| "learning_rate": 6.701157684265613e-06, |
| "loss": 0.404, |
| "num_input_tokens_seen": 111895104, |
| "step": 425 |
| }, |
| { |
| "epoch": 1.2360561353004678, |
| "grad_norm": 0.023235999047756195, |
| "learning_rate": 6.627758995965533e-06, |
| "loss": 0.4091, |
| "num_input_tokens_seen": 113164800, |
| "step": 430 |
| }, |
| { |
| "epoch": 1.2504498020870818, |
| "grad_norm": 0.02374238334596157, |
| "learning_rate": 6.553965815162167e-06, |
| "loss": 0.3971, |
| "num_input_tokens_seen": 114495584, |
| "step": 435 |
| }, |
| { |
| "epoch": 1.2648434688736956, |
| "grad_norm": 0.02480175346136093, |
| "learning_rate": 6.479796025864569e-06, |
| "loss": 0.408, |
| "num_input_tokens_seen": 115789632, |
| "step": 440 |
| }, |
| { |
| "epoch": 1.2792371356603094, |
| "grad_norm": 0.022774415090680122, |
| "learning_rate": 6.405267603354044e-06, |
| "loss": 0.4018, |
| "num_input_tokens_seen": 117138208, |
| "step": 445 |
| }, |
| { |
| "epoch": 1.2936308024469234, |
| "grad_norm": 0.0250807274132967, |
| "learning_rate": 6.330398609827779e-06, |
| "loss": 0.4039, |
| "num_input_tokens_seen": 118444480, |
| "step": 450 |
| }, |
| { |
| "epoch": 1.3080244692335372, |
| "grad_norm": 0.023115675896406174, |
| "learning_rate": 6.255207190021421e-06, |
| "loss": 0.4123, |
| "num_input_tokens_seen": 119739520, |
| "step": 455 |
| }, |
| { |
| "epoch": 1.322418136020151, |
| "grad_norm": 0.024381371214985847, |
| "learning_rate": 6.179711566811637e-06, |
| "loss": 0.4102, |
| "num_input_tokens_seen": 121046112, |
| "step": 460 |
| }, |
| { |
| "epoch": 1.336811802806765, |
| "grad_norm": 0.022843407467007637, |
| "learning_rate": 6.103930036799739e-06, |
| "loss": 0.4099, |
| "num_input_tokens_seen": 122359872, |
| "step": 465 |
| }, |
| { |
| "epoch": 1.3512054695933788, |
| "grad_norm": 0.024828806519508362, |
| "learning_rate": 6.027880965877457e-06, |
| "loss": 0.4109, |
| "num_input_tokens_seen": 123711808, |
| "step": 470 |
| }, |
| { |
| "epoch": 1.3655991363799929, |
| "grad_norm": 0.023335138335824013, |
| "learning_rate": 5.951582784775896e-06, |
| "loss": 0.4071, |
| "num_input_tokens_seen": 125011520, |
| "step": 475 |
| }, |
| { |
| "epoch": 1.3799928031666067, |
| "grad_norm": 0.02501983381807804, |
| "learning_rate": 5.8750539845987945e-06, |
| "loss": 0.3966, |
| "num_input_tokens_seen": 126367392, |
| "step": 480 |
| }, |
| { |
| "epoch": 1.3943864699532207, |
| "grad_norm": 0.025398626923561096, |
| "learning_rate": 5.798313112341153e-06, |
| "loss": 0.404, |
| "num_input_tokens_seen": 127709088, |
| "step": 485 |
| }, |
| { |
| "epoch": 1.4087801367398345, |
| "grad_norm": 0.02458963729441166, |
| "learning_rate": 5.721378766394301e-06, |
| "loss": 0.4067, |
| "num_input_tokens_seen": 129039552, |
| "step": 490 |
| }, |
| { |
| "epoch": 1.4231738035264483, |
| "grad_norm": 0.024260446429252625, |
| "learning_rate": 5.644269592038528e-06, |
| "loss": 0.4076, |
| "num_input_tokens_seen": 130363232, |
| "step": 495 |
| }, |
| { |
| "epoch": 1.4375674703130623, |
| "grad_norm": 0.024336043745279312, |
| "learning_rate": 5.5670042769243375e-06, |
| "loss": 0.4005, |
| "num_input_tokens_seen": 131699264, |
| "step": 500 |
| }, |
| { |
| "epoch": 1.4519611370996761, |
| "grad_norm": 0.023921623826026917, |
| "learning_rate": 5.48960154654343e-06, |
| "loss": 0.3988, |
| "num_input_tokens_seen": 133018144, |
| "step": 505 |
| }, |
| { |
| "epoch": 1.46635480388629, |
| "grad_norm": 0.022856013849377632, |
| "learning_rate": 5.412080159690537e-06, |
| "loss": 0.4037, |
| "num_input_tokens_seen": 134316896, |
| "step": 510 |
| }, |
| { |
| "epoch": 1.480748470672904, |
| "grad_norm": 0.025158999487757683, |
| "learning_rate": 5.33445890391715e-06, |
| "loss": 0.4049, |
| "num_input_tokens_seen": 135591968, |
| "step": 515 |
| }, |
| { |
| "epoch": 1.4951421374595177, |
| "grad_norm": 0.026123400777578354, |
| "learning_rate": 5.25675659097831e-06, |
| "loss": 0.3969, |
| "num_input_tokens_seen": 136903264, |
| "step": 520 |
| }, |
| { |
| "epoch": 1.5095358042461315, |
| "grad_norm": 0.02351614274084568, |
| "learning_rate": 5.178992052273519e-06, |
| "loss": 0.4091, |
| "num_input_tokens_seen": 138205280, |
| "step": 525 |
| }, |
| { |
| "epoch": 1.5239294710327456, |
| "grad_norm": 0.020864520221948624, |
| "learning_rate": 5.101184134282884e-06, |
| "loss": 0.3982, |
| "num_input_tokens_seen": 139582816, |
| "step": 530 |
| }, |
| { |
| "epoch": 1.5383231378193596, |
| "grad_norm": 0.021669739857316017, |
| "learning_rate": 5.023351693999621e-06, |
| "loss": 0.4013, |
| "num_input_tokens_seen": 140928864, |
| "step": 535 |
| }, |
| { |
| "epoch": 1.5527168046059734, |
| "grad_norm": 0.023181382566690445, |
| "learning_rate": 4.945513594360001e-06, |
| "loss": 0.4067, |
| "num_input_tokens_seen": 142234624, |
| "step": 540 |
| }, |
| { |
| "epoch": 1.5671104713925872, |
| "grad_norm": 0.02232653833925724, |
| "learning_rate": 4.867688699671857e-06, |
| "loss": 0.4046, |
| "num_input_tokens_seen": 143542944, |
| "step": 545 |
| }, |
| { |
| "epoch": 1.5815041381792012, |
| "grad_norm": 0.024279937148094177, |
| "learning_rate": 4.78989587104276e-06, |
| "loss": 0.4062, |
| "num_input_tokens_seen": 144867168, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.595897804965815, |
| "grad_norm": 0.02459154650568962, |
| "learning_rate": 4.712153961808974e-06, |
| "loss": 0.4, |
| "num_input_tokens_seen": 146167296, |
| "step": 555 |
| }, |
| { |
| "epoch": 1.6102914717524288, |
| "grad_norm": 0.02406412921845913, |
| "learning_rate": 4.63448181296628e-06, |
| "loss": 0.4059, |
| "num_input_tokens_seen": 147549760, |
| "step": 560 |
| }, |
| { |
| "epoch": 1.6246851385390428, |
| "grad_norm": 0.024887846782803535, |
| "learning_rate": 4.556898248603818e-06, |
| "loss": 0.4065, |
| "num_input_tokens_seen": 148877888, |
| "step": 565 |
| }, |
| { |
| "epoch": 1.6390788053256569, |
| "grad_norm": 0.024574384093284607, |
| "learning_rate": 4.479422071341996e-06, |
| "loss": 0.4059, |
| "num_input_tokens_seen": 150175264, |
| "step": 570 |
| }, |
| { |
| "epoch": 1.6534724721122704, |
| "grad_norm": 0.02655833028256893, |
| "learning_rate": 4.402072057775625e-06, |
| "loss": 0.4024, |
| "num_input_tokens_seen": 151492896, |
| "step": 575 |
| }, |
| { |
| "epoch": 1.6678661388988845, |
| "grad_norm": 0.025273198261857033, |
| "learning_rate": 4.324866953923343e-06, |
| "loss": 0.403, |
| "num_input_tokens_seen": 152796480, |
| "step": 580 |
| }, |
| { |
| "epoch": 1.6822598056854985, |
| "grad_norm": 0.021906346082687378, |
| "learning_rate": 4.247825470684465e-06, |
| "loss": 0.403, |
| "num_input_tokens_seen": 154123680, |
| "step": 585 |
| }, |
| { |
| "epoch": 1.6966534724721123, |
| "grad_norm": 0.024103475734591484, |
| "learning_rate": 4.170966279304343e-06, |
| "loss": 0.4009, |
| "num_input_tokens_seen": 155415008, |
| "step": 590 |
| }, |
| { |
| "epoch": 1.711047139258726, |
| "grad_norm": 0.025105420500040054, |
| "learning_rate": 4.094308006849314e-06, |
| "loss": 0.408, |
| "num_input_tokens_seen": 156700384, |
| "step": 595 |
| }, |
| { |
| "epoch": 1.7254408060453401, |
| "grad_norm": 0.021644530817866325, |
| "learning_rate": 4.017869231692393e-06, |
| "loss": 0.4069, |
| "num_input_tokens_seen": 158013984, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.739834472831954, |
| "grad_norm": 0.023105325177311897, |
| "learning_rate": 3.9416684790107315e-06, |
| "loss": 0.3992, |
| "num_input_tokens_seen": 159346592, |
| "step": 605 |
| }, |
| { |
| "epoch": 1.7542281396185677, |
| "grad_norm": 0.022883733734488487, |
| "learning_rate": 3.8657242162959845e-06, |
| "loss": 0.4027, |
| "num_input_tokens_seen": 160641984, |
| "step": 610 |
| }, |
| { |
| "epoch": 1.7686218064051817, |
| "grad_norm": 0.024626722559332848, |
| "learning_rate": 3.79005484887866e-06, |
| "loss": 0.4021, |
| "num_input_tokens_seen": 161957600, |
| "step": 615 |
| }, |
| { |
| "epoch": 1.7830154731917958, |
| "grad_norm": 0.023260436952114105, |
| "learning_rate": 3.714678715467529e-06, |
| "loss": 0.3975, |
| "num_input_tokens_seen": 163285344, |
| "step": 620 |
| }, |
| { |
| "epoch": 1.7974091399784093, |
| "grad_norm": 0.024760698899626732, |
| "learning_rate": 3.639614083705178e-06, |
| "loss": 0.3955, |
| "num_input_tokens_seen": 164588128, |
| "step": 625 |
| }, |
| { |
| "epoch": 1.8118028067650234, |
| "grad_norm": 0.02492666058242321, |
| "learning_rate": 3.564879145740794e-06, |
| "loss": 0.3975, |
| "num_input_tokens_seen": 165879776, |
| "step": 630 |
| }, |
| { |
| "epoch": 1.8261964735516374, |
| "grad_norm": 0.02142232283949852, |
| "learning_rate": 3.490492013821234e-06, |
| "loss": 0.4005, |
| "num_input_tokens_seen": 167185216, |
| "step": 635 |
| }, |
| { |
| "epoch": 1.8405901403382512, |
| "grad_norm": 0.02252054214477539, |
| "learning_rate": 3.4164707159014675e-06, |
| "loss": 0.3958, |
| "num_input_tokens_seen": 168526560, |
| "step": 640 |
| }, |
| { |
| "epoch": 1.854983807124865, |
| "grad_norm": 0.022308630868792534, |
| "learning_rate": 3.3428331912754507e-06, |
| "loss": 0.4019, |
| "num_input_tokens_seen": 169859840, |
| "step": 645 |
| }, |
| { |
| "epoch": 1.869377473911479, |
| "grad_norm": 0.024216335266828537, |
| "learning_rate": 3.2695972862284707e-06, |
| "loss": 0.402, |
| "num_input_tokens_seen": 171171200, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.8837711406980928, |
| "grad_norm": 0.022730115801095963, |
| "learning_rate": 3.196780749712054e-06, |
| "loss": 0.4038, |
| "num_input_tokens_seen": 172496352, |
| "step": 655 |
| }, |
| { |
| "epoch": 1.8981648074847066, |
| "grad_norm": 0.02168315462768078, |
| "learning_rate": 3.124401229042443e-06, |
| "loss": 0.4011, |
| "num_input_tokens_seen": 173819584, |
| "step": 660 |
| }, |
| { |
| "epoch": 1.9125584742713206, |
| "grad_norm": 0.022848892956972122, |
| "learning_rate": 3.0524762656237184e-06, |
| "loss": 0.3986, |
| "num_input_tokens_seen": 175124000, |
| "step": 665 |
| }, |
| { |
| "epoch": 1.9269521410579347, |
| "grad_norm": 0.0229133740067482, |
| "learning_rate": 2.9810232906965875e-06, |
| "loss": 0.4003, |
| "num_input_tokens_seen": 176404544, |
| "step": 670 |
| }, |
| { |
| "epoch": 1.9413458078445482, |
| "grad_norm": 0.02141651324927807, |
| "learning_rate": 2.9100596211138576e-06, |
| "loss": 0.3969, |
| "num_input_tokens_seen": 177685600, |
| "step": 675 |
| }, |
| { |
| "epoch": 1.9557394746311623, |
| "grad_norm": 0.022065116092562675, |
| "learning_rate": 2.83960245514366e-06, |
| "loss": 0.3999, |
| "num_input_tokens_seen": 179014656, |
| "step": 680 |
| }, |
| { |
| "epoch": 1.9701331414177763, |
| "grad_norm": 0.02093074843287468, |
| "learning_rate": 2.769668868301374e-06, |
| "loss": 0.3954, |
| "num_input_tokens_seen": 180367968, |
| "step": 685 |
| }, |
| { |
| "epoch": 1.98452680820439, |
| "grad_norm": 0.022384867072105408, |
| "learning_rate": 2.700275809211343e-06, |
| "loss": 0.3929, |
| "num_input_tokens_seen": 181711616, |
| "step": 690 |
| }, |
| { |
| "epoch": 1.998920474991004, |
| "grad_norm": 0.022776221856474876, |
| "learning_rate": 2.631440095499306e-06, |
| "loss": 0.3939, |
| "num_input_tokens_seen": 183020704, |
| "step": 695 |
| }, |
| { |
| "epoch": 2.011514933429291, |
| "grad_norm": 0.022738846018910408, |
| "learning_rate": 2.5631784097166024e-06, |
| "loss": 0.386, |
| "num_input_tokens_seen": 184150656, |
| "step": 700 |
| }, |
| { |
| "epoch": 2.025908600215905, |
| "grad_norm": 0.022992299869656563, |
| "learning_rate": 2.4955072952970993e-06, |
| "loss": 0.3836, |
| "num_input_tokens_seen": 185492128, |
| "step": 705 |
| }, |
| { |
| "epoch": 2.040302267002519, |
| "grad_norm": 0.022360729053616524, |
| "learning_rate": 2.42844315254784e-06, |
| "loss": 0.3827, |
| "num_input_tokens_seen": 186797280, |
| "step": 710 |
| }, |
| { |
| "epoch": 2.054695933789133, |
| "grad_norm": 0.02626909501850605, |
| "learning_rate": 2.3620022346743816e-06, |
| "loss": 0.3839, |
| "num_input_tokens_seen": 188086176, |
| "step": 715 |
| }, |
| { |
| "epoch": 2.069089600575747, |
| "grad_norm": 0.02516692690551281, |
| "learning_rate": 2.2962006438417704e-06, |
| "loss": 0.3898, |
| "num_input_tokens_seen": 189416160, |
| "step": 720 |
| }, |
| { |
| "epoch": 2.0834832673623604, |
| "grad_norm": 0.022893643006682396, |
| "learning_rate": 2.231054327272141e-06, |
| "loss": 0.3891, |
| "num_input_tokens_seen": 190743328, |
| "step": 725 |
| }, |
| { |
| "epoch": 2.0978769341489745, |
| "grad_norm": 0.02225966565310955, |
| "learning_rate": 2.1665790733798497e-06, |
| "loss": 0.3868, |
| "num_input_tokens_seen": 192065504, |
| "step": 730 |
| }, |
| { |
| "epoch": 2.1122706009355885, |
| "grad_norm": 0.021935859695076942, |
| "learning_rate": 2.102790507945107e-06, |
| "loss": 0.38, |
| "num_input_tokens_seen": 193379392, |
| "step": 735 |
| }, |
| { |
| "epoch": 2.126664267722202, |
| "grad_norm": 0.02270529605448246, |
| "learning_rate": 2.039704090327024e-06, |
| "loss": 0.3818, |
| "num_input_tokens_seen": 194720576, |
| "step": 740 |
| }, |
| { |
| "epoch": 2.141057934508816, |
| "grad_norm": 0.021578673273324966, |
| "learning_rate": 1.9773351097169785e-06, |
| "loss": 0.3856, |
| "num_input_tokens_seen": 196051456, |
| "step": 745 |
| }, |
| { |
| "epoch": 2.15545160129543, |
| "grad_norm": 0.0224690530449152, |
| "learning_rate": 1.9156986814332374e-06, |
| "loss": 0.3904, |
| "num_input_tokens_seen": 197369120, |
| "step": 750 |
| }, |
| { |
| "epoch": 2.1698452680820437, |
| "grad_norm": 0.02468658983707428, |
| "learning_rate": 1.8548097432577162e-06, |
| "loss": 0.3877, |
| "num_input_tokens_seen": 198667648, |
| "step": 755 |
| }, |
| { |
| "epoch": 2.1842389348686577, |
| "grad_norm": 0.022155508399009705, |
| "learning_rate": 1.7946830518157505e-06, |
| "loss": 0.3857, |
| "num_input_tokens_seen": 200011808, |
| "step": 760 |
| }, |
| { |
| "epoch": 2.1986326016552717, |
| "grad_norm": 0.023383986204862595, |
| "learning_rate": 1.7353331789997869e-06, |
| "loss": 0.3825, |
| "num_input_tokens_seen": 201308992, |
| "step": 765 |
| }, |
| { |
| "epoch": 2.2130262684418858, |
| "grad_norm": 0.022762874141335487, |
| "learning_rate": 1.6767745084378445e-06, |
| "loss": 0.3912, |
| "num_input_tokens_seen": 202606848, |
| "step": 770 |
| }, |
| { |
| "epoch": 2.2274199352284993, |
| "grad_norm": 0.02270393818616867, |
| "learning_rate": 1.6190212320075871e-06, |
| "loss": 0.3827, |
| "num_input_tokens_seen": 203913536, |
| "step": 775 |
| }, |
| { |
| "epoch": 2.2418136020151134, |
| "grad_norm": 0.02072157897055149, |
| "learning_rate": 1.5620873463968827e-06, |
| "loss": 0.3797, |
| "num_input_tokens_seen": 205247360, |
| "step": 780 |
| }, |
| { |
| "epoch": 2.2562072688017274, |
| "grad_norm": 0.023383304476737976, |
| "learning_rate": 1.5059866497116627e-06, |
| "loss": 0.3851, |
| "num_input_tokens_seen": 206580224, |
| "step": 785 |
| }, |
| { |
| "epoch": 2.270600935588341, |
| "grad_norm": 0.024877682328224182, |
| "learning_rate": 1.450732738131904e-06, |
| "loss": 0.386, |
| "num_input_tokens_seen": 207907776, |
| "step": 790 |
| }, |
| { |
| "epoch": 2.284994602374955, |
| "grad_norm": 0.025071872398257256, |
| "learning_rate": 1.3963390026165596e-06, |
| "loss": 0.3829, |
| "num_input_tokens_seen": 209219040, |
| "step": 795 |
| }, |
| { |
| "epoch": 2.299388269161569, |
| "grad_norm": 0.022932719439268112, |
| "learning_rate": 1.3428186256582088e-06, |
| "loss": 0.3847, |
| "num_input_tokens_seen": 210560096, |
| "step": 800 |
| }, |
| { |
| "epoch": 2.3137819359481826, |
| "grad_norm": 0.02210652269423008, |
| "learning_rate": 1.2901845780882427e-06, |
| "loss": 0.3885, |
| "num_input_tokens_seen": 211866176, |
| "step": 805 |
| }, |
| { |
| "epoch": 2.3281756027347966, |
| "grad_norm": 0.02213803492486477, |
| "learning_rate": 1.238449615933343e-06, |
| "loss": 0.3822, |
| "num_input_tokens_seen": 213155808, |
| "step": 810 |
| }, |
| { |
| "epoch": 2.3425692695214106, |
| "grad_norm": 0.021066095679998398, |
| "learning_rate": 1.1876262773240172e-06, |
| "loss": 0.3848, |
| "num_input_tokens_seen": 214440704, |
| "step": 815 |
| }, |
| { |
| "epoch": 2.3569629363080242, |
| "grad_norm": 0.02134723588824272, |
| "learning_rate": 1.1377268794559476e-06, |
| "loss": 0.3856, |
| "num_input_tokens_seen": 215759424, |
| "step": 820 |
| }, |
| { |
| "epoch": 2.3713566030946382, |
| "grad_norm": 0.021346207708120346, |
| "learning_rate": 1.0887635156048736e-06, |
| "loss": 0.3879, |
| "num_input_tokens_seen": 217098240, |
| "step": 825 |
| }, |
| { |
| "epoch": 2.3857502698812523, |
| "grad_norm": 0.021947264671325684, |
| "learning_rate": 1.040748052195752e-06, |
| "loss": 0.3906, |
| "num_input_tokens_seen": 218389984, |
| "step": 830 |
| }, |
| { |
| "epoch": 2.4001439366678663, |
| "grad_norm": 0.023333607241511345, |
| "learning_rate": 9.936921259268944e-07, |
| "loss": 0.3903, |
| "num_input_tokens_seen": 219692384, |
| "step": 835 |
| }, |
| { |
| "epoch": 2.41453760345448, |
| "grad_norm": 0.020792281255126, |
| "learning_rate": 9.476071409497712e-07, |
| "loss": 0.3871, |
| "num_input_tokens_seen": 221013216, |
| "step": 840 |
| }, |
| { |
| "epoch": 2.428931270241094, |
| "grad_norm": 0.022382711991667747, |
| "learning_rate": 9.025042661051808e-07, |
| "loss": 0.3861, |
| "num_input_tokens_seen": 222396512, |
| "step": 845 |
| }, |
| { |
| "epoch": 2.443324937027708, |
| "grad_norm": 0.02197764627635479, |
| "learning_rate": 8.583944322164528e-07, |
| "loss": 0.3842, |
| "num_input_tokens_seen": 223696512, |
| "step": 850 |
| }, |
| { |
| "epoch": 2.457718603814322, |
| "grad_norm": 0.023145312443375587, |
| "learning_rate": 8.15288329440318e-07, |
| "loss": 0.3875, |
| "num_input_tokens_seen": 225019840, |
| "step": 855 |
| }, |
| { |
| "epoch": 2.4721122706009355, |
| "grad_norm": 0.02280507981777191, |
| "learning_rate": 7.731964046761231e-07, |
| "loss": 0.3896, |
| "num_input_tokens_seen": 226347936, |
| "step": 860 |
| }, |
| { |
| "epoch": 2.4865059373875495, |
| "grad_norm": 0.021663593128323555, |
| "learning_rate": 7.321288590339898e-07, |
| "loss": 0.3883, |
| "num_input_tokens_seen": 227650912, |
| "step": 865 |
| }, |
| { |
| "epoch": 2.5008996041741636, |
| "grad_norm": 0.022594928741455078, |
| "learning_rate": 6.920956453625405e-07, |
| "loss": 0.3908, |
| "num_input_tokens_seen": 228960704, |
| "step": 870 |
| }, |
| { |
| "epoch": 2.515293270960777, |
| "grad_norm": 0.022745080292224884, |
| "learning_rate": 6.531064658368019e-07, |
| "loss": 0.3805, |
| "num_input_tokens_seen": 230283136, |
| "step": 875 |
| }, |
| { |
| "epoch": 2.529686937747391, |
| "grad_norm": 0.02337946556508541, |
| "learning_rate": 6.151707696068443e-07, |
| "loss": 0.3892, |
| "num_input_tokens_seen": 231587968, |
| "step": 880 |
| }, |
| { |
| "epoch": 2.544080604534005, |
| "grad_norm": 0.023571399971842766, |
| "learning_rate": 5.782977505077536e-07, |
| "loss": 0.3846, |
| "num_input_tokens_seen": 232939360, |
| "step": 885 |
| }, |
| { |
| "epoch": 2.5584742713206188, |
| "grad_norm": 0.022394301369786263, |
| "learning_rate": 5.42496344831478e-07, |
| "loss": 0.3877, |
| "num_input_tokens_seen": 234292896, |
| "step": 890 |
| }, |
| { |
| "epoch": 2.572867938107233, |
| "grad_norm": 0.020835287868976593, |
| "learning_rate": 5.077752291610854e-07, |
| "loss": 0.3872, |
| "num_input_tokens_seen": 235640864, |
| "step": 895 |
| }, |
| { |
| "epoch": 2.587261604893847, |
| "grad_norm": 0.021807711571455002, |
| "learning_rate": 4.741428182679736e-07, |
| "loss": 0.377, |
| "num_input_tokens_seen": 237012928, |
| "step": 900 |
| }, |
| { |
| "epoch": 2.6016552716804604, |
| "grad_norm": 0.020575975999236107, |
| "learning_rate": 4.416072630725166e-07, |
| "loss": 0.3794, |
| "num_input_tokens_seen": 238318656, |
| "step": 905 |
| }, |
| { |
| "epoch": 2.6160489384670744, |
| "grad_norm": 0.02090187929570675, |
| "learning_rate": 4.101764486686649e-07, |
| "loss": 0.3875, |
| "num_input_tokens_seen": 239625440, |
| "step": 910 |
| }, |
| { |
| "epoch": 2.6304426052536884, |
| "grad_norm": 0.021241318434476852, |
| "learning_rate": 3.798579924129736e-07, |
| "loss": 0.3855, |
| "num_input_tokens_seen": 240930400, |
| "step": 915 |
| }, |
| { |
| "epoch": 2.644836272040302, |
| "grad_norm": 0.022065874189138412, |
| "learning_rate": 3.5065924207850486e-07, |
| "loss": 0.3896, |
| "num_input_tokens_seen": 242234048, |
| "step": 920 |
| }, |
| { |
| "epoch": 2.659229938826916, |
| "grad_norm": 0.02141835354268551, |
| "learning_rate": 3.225872740740754e-07, |
| "loss": 0.3804, |
| "num_input_tokens_seen": 243557280, |
| "step": 925 |
| }, |
| { |
| "epoch": 2.67362360561353, |
| "grad_norm": 0.021051181480288506, |
| "learning_rate": 2.9564889172926993e-07, |
| "loss": 0.3912, |
| "num_input_tokens_seen": 244847776, |
| "step": 930 |
| }, |
| { |
| "epoch": 2.688017272400144, |
| "grad_norm": 0.0236518532037735, |
| "learning_rate": 2.6985062364562607e-07, |
| "loss": 0.3857, |
| "num_input_tokens_seen": 246166048, |
| "step": 935 |
| }, |
| { |
| "epoch": 2.7024109391867577, |
| "grad_norm": 0.021910812705755234, |
| "learning_rate": 2.451987221144109e-07, |
| "loss": 0.3771, |
| "num_input_tokens_seen": 247482240, |
| "step": 940 |
| }, |
| { |
| "epoch": 2.7168046059733717, |
| "grad_norm": 0.022103767842054367, |
| "learning_rate": 2.2169916160136029e-07, |
| "loss": 0.3895, |
| "num_input_tokens_seen": 248809152, |
| "step": 945 |
| }, |
| { |
| "epoch": 2.7311982727599857, |
| "grad_norm": 0.021742546930909157, |
| "learning_rate": 1.9935763729874435e-07, |
| "loss": 0.3884, |
| "num_input_tokens_seen": 250120896, |
| "step": 950 |
| }, |
| { |
| "epoch": 2.7455919395465997, |
| "grad_norm": 0.02116556093096733, |
| "learning_rate": 1.7817956374512334e-07, |
| "loss": 0.3859, |
| "num_input_tokens_seen": 251476704, |
| "step": 955 |
| }, |
| { |
| "epoch": 2.7599856063332133, |
| "grad_norm": 0.021673424169421196, |
| "learning_rate": 1.5817007351311476e-07, |
| "loss": 0.3904, |
| "num_input_tokens_seen": 252782176, |
| "step": 960 |
| }, |
| { |
| "epoch": 2.7743792731198273, |
| "grad_norm": 0.02117246761918068, |
| "learning_rate": 1.393340159654999e-07, |
| "loss": 0.3873, |
| "num_input_tokens_seen": 254045792, |
| "step": 965 |
| }, |
| { |
| "epoch": 2.7887729399064414, |
| "grad_norm": 0.0224041398614645, |
| "learning_rate": 1.2167595607996296e-07, |
| "loss": 0.3852, |
| "num_input_tokens_seen": 255355648, |
| "step": 970 |
| }, |
| { |
| "epoch": 2.803166606693055, |
| "grad_norm": 0.0252470001578331, |
| "learning_rate": 1.0520017334275823e-07, |
| "loss": 0.3793, |
| "num_input_tokens_seen": 256681600, |
| "step": 975 |
| }, |
| { |
| "epoch": 2.817560273479669, |
| "grad_norm": 0.02181648090481758, |
| "learning_rate": 8.991066071156074e-08, |
| "loss": 0.3807, |
| "num_input_tokens_seen": 258015936, |
| "step": 980 |
| }, |
| { |
| "epoch": 2.831953940266283, |
| "grad_norm": 0.022744813933968544, |
| "learning_rate": 7.581112364776044e-08, |
| "loss": 0.3773, |
| "num_input_tokens_seen": 259346816, |
| "step": 985 |
| }, |
| { |
| "epoch": 2.8463476070528966, |
| "grad_norm": 0.02034585550427437, |
| "learning_rate": 6.290497921843219e-08, |
| "loss": 0.3845, |
| "num_input_tokens_seen": 260673024, |
| "step": 990 |
| }, |
| { |
| "epoch": 2.8607412738395106, |
| "grad_norm": 0.021828465163707733, |
| "learning_rate": 5.1195355268199854e-08, |
| "loss": 0.3876, |
| "num_input_tokens_seen": 262019872, |
| "step": 995 |
| }, |
| { |
| "epoch": 2.8751349406261246, |
| "grad_norm": 0.02159695513546467, |
| "learning_rate": 4.0685089661192114e-08, |
| "loss": 0.3851, |
| "num_input_tokens_seen": 263341824, |
| "step": 1000 |
| }, |
| { |
| "epoch": 2.889528607412738, |
| "grad_norm": 0.020134858787059784, |
| "learning_rate": 3.1376729593276534e-08, |
| "loss": 0.3864, |
| "num_input_tokens_seen": 264677152, |
| "step": 1005 |
| }, |
| { |
| "epoch": 2.9039222741993522, |
| "grad_norm": 0.022702520713210106, |
| "learning_rate": 2.327253097474169e-08, |
| "loss": 0.3858, |
| "num_input_tokens_seen": 265961984, |
| "step": 1010 |
| }, |
| { |
| "epoch": 2.9183159409859663, |
| "grad_norm": 0.022232618182897568, |
| "learning_rate": 1.637445788356673e-08, |
| "loss": 0.3828, |
| "num_input_tokens_seen": 267219008, |
| "step": 1015 |
| }, |
| { |
| "epoch": 2.93270960777258, |
| "grad_norm": 0.02198317088186741, |
| "learning_rate": 1.0684182089423234e-08, |
| "loss": 0.3857, |
| "num_input_tokens_seen": 268533920, |
| "step": 1020 |
| }, |
| { |
| "epoch": 2.947103274559194, |
| "grad_norm": 0.021084170788526535, |
| "learning_rate": 6.20308264851488e-09, |
| "loss": 0.3855, |
| "num_input_tokens_seen": 269851232, |
| "step": 1025 |
| }, |
| { |
| "epoch": 2.961496941345808, |
| "grad_norm": 0.02216101624071598, |
| "learning_rate": 2.932245569360892e-09, |
| "loss": 0.3884, |
| "num_input_tokens_seen": 271148416, |
| "step": 1030 |
| }, |
| { |
| "epoch": 2.975890608132422, |
| "grad_norm": 0.020568687468767166, |
| "learning_rate": 8.724635495965805e-10, |
| "loss": 0.3831, |
| "num_input_tokens_seen": 272442080, |
| "step": 1035 |
| }, |
| { |
| "epoch": 2.9902842749190355, |
| "grad_norm": 0.02233074977993965, |
| "learning_rate": 2.4235783861459304e-11, |
| "loss": 0.3872, |
| "num_input_tokens_seen": 273768608, |
| "step": 1040 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 1041, |
| "num_input_tokens_seen": 274036096, |
| "num_train_epochs": 3, |
| "save_steps": -1041, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.0672503407966683e+19, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
