| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 819, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001221001221001221, | |
| "grad_norm": 1.629501933145264, | |
| "learning_rate": 1.2195121951219513e-05, | |
| "loss": 1.3788, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006105006105006105, | |
| "grad_norm": 1.5408249987691998, | |
| "learning_rate": 6.097560975609756e-05, | |
| "loss": 1.3922, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01221001221001221, | |
| "grad_norm": 1.6964330573646578, | |
| "learning_rate": 0.00012195121951219512, | |
| "loss": 1.3357, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018315018315018316, | |
| "grad_norm": 0.5877948098047541, | |
| "learning_rate": 0.00018292682926829268, | |
| "loss": 1.2292, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 0.41277023465903623, | |
| "learning_rate": 0.00024390243902439024, | |
| "loss": 1.1569, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030525030525030524, | |
| "grad_norm": 0.28894210212831173, | |
| "learning_rate": 0.0003048780487804878, | |
| "loss": 1.1017, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03663003663003663, | |
| "grad_norm": 0.15704693527032987, | |
| "learning_rate": 0.00036585365853658537, | |
| "loss": 1.0689, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042735042735042736, | |
| "grad_norm": 0.149497877408929, | |
| "learning_rate": 0.0004268292682926829, | |
| "loss": 1.0597, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04884004884004884, | |
| "grad_norm": 0.17229438336995273, | |
| "learning_rate": 0.0004878048780487805, | |
| "loss": 1.0497, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.054945054945054944, | |
| "grad_norm": 0.1350927997659262, | |
| "learning_rate": 0.0005487804878048781, | |
| "loss": 1.0345, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06105006105006105, | |
| "grad_norm": 0.1316879612941552, | |
| "learning_rate": 0.0006097560975609756, | |
| "loss": 1.03, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06715506715506715, | |
| "grad_norm": 0.12294647268470198, | |
| "learning_rate": 0.0006707317073170732, | |
| "loss": 1.0182, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.07326007326007326, | |
| "grad_norm": 0.13768875749553208, | |
| "learning_rate": 0.0007317073170731707, | |
| "loss": 1.018, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07936507936507936, | |
| "grad_norm": 0.1301026880176555, | |
| "learning_rate": 0.0007926829268292683, | |
| "loss": 1.0148, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 0.15052001326359865, | |
| "learning_rate": 0.0008536585365853659, | |
| "loss": 1.0074, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.09157509157509157, | |
| "grad_norm": 0.15206771365197816, | |
| "learning_rate": 0.0009146341463414635, | |
| "loss": 1.0115, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.09768009768009768, | |
| "grad_norm": 0.12918729689877004, | |
| "learning_rate": 0.000975609756097561, | |
| "loss": 1.0034, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.10378510378510379, | |
| "grad_norm": 0.1617114692792796, | |
| "learning_rate": 0.000999959117130623, | |
| "loss": 1.0057, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.10989010989010989, | |
| "grad_norm": 0.15209285146918505, | |
| "learning_rate": 0.000999709301584265, | |
| "loss": 0.9982, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.115995115995116, | |
| "grad_norm": 0.15560054183114133, | |
| "learning_rate": 0.0009992324965361792, | |
| "loss": 0.9988, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.1221001221001221, | |
| "grad_norm": 0.12326520201606891, | |
| "learning_rate": 0.0009985289185717684, | |
| "loss": 0.9868, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1282051282051282, | |
| "grad_norm": 0.13506004498847854, | |
| "learning_rate": 0.000997598887286467, | |
| "loss": 0.99, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.1343101343101343, | |
| "grad_norm": 0.12846122121998493, | |
| "learning_rate": 0.000996442825140569, | |
| "loss": 0.981, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.14041514041514042, | |
| "grad_norm": 0.15572445817151304, | |
| "learning_rate": 0.0009950612572673255, | |
| "loss": 0.9849, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.14652014652014653, | |
| "grad_norm": 0.14660132838678952, | |
| "learning_rate": 0.0009934548112344088, | |
| "loss": 0.9883, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.15262515262515264, | |
| "grad_norm": 0.11705785841462868, | |
| "learning_rate": 0.0009916242167588433, | |
| "loss": 0.9879, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.15873015873015872, | |
| "grad_norm": 0.13642851783373758, | |
| "learning_rate": 0.0009895703053755364, | |
| "loss": 0.9798, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.16483516483516483, | |
| "grad_norm": 0.12472826943952521, | |
| "learning_rate": 0.0009872940100595598, | |
| "loss": 0.977, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.119735339518556, | |
| "learning_rate": 0.0009847963648023522, | |
| "loss": 0.9758, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.17704517704517705, | |
| "grad_norm": 0.12634642504923346, | |
| "learning_rate": 0.000982078504142035, | |
| "loss": 0.9637, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.18315018315018314, | |
| "grad_norm": 0.1313401316215934, | |
| "learning_rate": 0.000979141662648057, | |
| "loss": 0.9695, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.18925518925518925, | |
| "grad_norm": 0.10869766647138489, | |
| "learning_rate": 0.0009759871743604004, | |
| "loss": 0.9657, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.19536019536019536, | |
| "grad_norm": 0.11697532103244576, | |
| "learning_rate": 0.0009726164721835996, | |
| "loss": 0.9612, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.20146520146520147, | |
| "grad_norm": 0.13503159530521566, | |
| "learning_rate": 0.0009690310872358572, | |
| "loss": 0.9729, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.20757020757020758, | |
| "grad_norm": 0.14747150622124625, | |
| "learning_rate": 0.0009652326481535434, | |
| "loss": 0.9611, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.21367521367521367, | |
| "grad_norm": 0.15447081723038833, | |
| "learning_rate": 0.0009612228803513976, | |
| "loss": 0.9623, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.21978021978021978, | |
| "grad_norm": 0.15215752710313343, | |
| "learning_rate": 0.0009570036052387725, | |
| "loss": 0.9573, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2258852258852259, | |
| "grad_norm": 0.13642796511864827, | |
| "learning_rate": 0.0009525767393922706, | |
| "loss": 0.9461, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.231990231990232, | |
| "grad_norm": 0.10883830363461129, | |
| "learning_rate": 0.0009479442936851526, | |
| "loss": 0.949, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.23809523809523808, | |
| "grad_norm": 0.130236635303521, | |
| "learning_rate": 0.0009431083723739124, | |
| "loss": 0.9366, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.2442002442002442, | |
| "grad_norm": 0.10775194472971555, | |
| "learning_rate": 0.0009380711721424326, | |
| "loss": 0.9418, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2503052503052503, | |
| "grad_norm": 0.11905614657094514, | |
| "learning_rate": 0.0009328349811041565, | |
| "loss": 0.9428, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.11842679938361055, | |
| "learning_rate": 0.0009274021777627277, | |
| "loss": 0.9506, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.2625152625152625, | |
| "grad_norm": 0.13876037195742963, | |
| "learning_rate": 0.0009217752299315725, | |
| "loss": 0.9276, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.2686202686202686, | |
| "grad_norm": 0.21581360420007165, | |
| "learning_rate": 0.0009159566936129111, | |
| "loss": 0.9512, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.27472527472527475, | |
| "grad_norm": 0.15887906930846354, | |
| "learning_rate": 0.0009099492118367123, | |
| "loss": 0.9457, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.28083028083028083, | |
| "grad_norm": 0.13609412278446711, | |
| "learning_rate": 0.0009037555134601149, | |
| "loss": 0.929, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.2869352869352869, | |
| "grad_norm": 0.14025295501919074, | |
| "learning_rate": 0.000897378411927864, | |
| "loss": 0.9388, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.29304029304029305, | |
| "grad_norm": 0.10506266135979772, | |
| "learning_rate": 0.0008908208039943213, | |
| "loss": 0.9288, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.29914529914529914, | |
| "grad_norm": 0.10813079919343101, | |
| "learning_rate": 0.0008840856684076366, | |
| "loss": 0.9175, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.3052503052503053, | |
| "grad_norm": 0.15791808529464318, | |
| "learning_rate": 0.0008771760645566706, | |
| "loss": 0.9246, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.31135531135531136, | |
| "grad_norm": 2.0370648707444725, | |
| "learning_rate": 0.000870095131081289, | |
| "loss": 0.9449, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.31746031746031744, | |
| "grad_norm": 0.1311182760192241, | |
| "learning_rate": 0.0008628460844466573, | |
| "loss": 0.9253, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.3235653235653236, | |
| "grad_norm": 0.14312834396261354, | |
| "learning_rate": 0.0008554322174821833, | |
| "loss": 0.9278, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.32967032967032966, | |
| "grad_norm": 0.11428839304992285, | |
| "learning_rate": 0.0008478568978857722, | |
| "loss": 0.9283, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.33577533577533575, | |
| "grad_norm": 0.10818382932069733, | |
| "learning_rate": 0.0008401235666940728, | |
| "loss": 0.9284, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.3418803418803419, | |
| "grad_norm": 0.11567783999993994, | |
| "learning_rate": 0.0008322357367194109, | |
| "loss": 0.9182, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.34798534798534797, | |
| "grad_norm": 0.10294827848523892, | |
| "learning_rate": 0.0008241969909541184, | |
| "loss": 0.9139, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.3540903540903541, | |
| "grad_norm": 0.13672098058204363, | |
| "learning_rate": 0.0008160109809429835, | |
| "loss": 0.9217, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.3601953601953602, | |
| "grad_norm": 0.13807363255445734, | |
| "learning_rate": 0.0008076814251245613, | |
| "loss": 0.9153, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.3663003663003663, | |
| "grad_norm": 0.1034627930470886, | |
| "learning_rate": 0.0007992121071421001, | |
| "loss": 0.9287, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3724053724053724, | |
| "grad_norm": 0.1294524989308333, | |
| "learning_rate": 0.0007906068741248461, | |
| "loss": 0.9138, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.3785103785103785, | |
| "grad_norm": 0.09977607943662724, | |
| "learning_rate": 0.0007818696349405123, | |
| "loss": 0.9192, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.38461538461538464, | |
| "grad_norm": 0.12394897831693975, | |
| "learning_rate": 0.0007730043584197021, | |
| "loss": 0.9097, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.3907203907203907, | |
| "grad_norm": 0.11903071018799159, | |
| "learning_rate": 0.0007640150715530953, | |
| "loss": 0.9029, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3968253968253968, | |
| "grad_norm": 0.13131459819762914, | |
| "learning_rate": 0.0007549058576622157, | |
| "loss": 0.9163, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.40293040293040294, | |
| "grad_norm": 0.10951470254516554, | |
| "learning_rate": 0.0007456808545446102, | |
| "loss": 0.9077, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.409035409035409, | |
| "grad_norm": 0.09719747300206659, | |
| "learning_rate": 0.0007363442525942826, | |
| "loss": 0.9041, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.41514041514041516, | |
| "grad_norm": 0.11238853337044794, | |
| "learning_rate": 0.0007269002928982366, | |
| "loss": 0.9071, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.42124542124542125, | |
| "grad_norm": 0.11751659500081639, | |
| "learning_rate": 0.0007173532653099911, | |
| "loss": 0.8996, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.42735042735042733, | |
| "grad_norm": 0.11145184489879807, | |
| "learning_rate": 0.0007077075065009433, | |
| "loss": 0.9195, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.43345543345543347, | |
| "grad_norm": 0.12082613464058725, | |
| "learning_rate": 0.0006979673979904665, | |
| "loss": 0.9116, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.43956043956043955, | |
| "grad_norm": 0.11356706546924504, | |
| "learning_rate": 0.0006881373641556346, | |
| "loss": 0.8957, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4456654456654457, | |
| "grad_norm": 0.10550995720573654, | |
| "learning_rate": 0.0006782218702214797, | |
| "loss": 0.8967, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.4517704517704518, | |
| "grad_norm": 0.10623969934852533, | |
| "learning_rate": 0.000668225420232694, | |
| "loss": 0.8956, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.45787545787545786, | |
| "grad_norm": 0.09920329673826833, | |
| "learning_rate": 0.0006581525550076989, | |
| "loss": 0.8944, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.463980463980464, | |
| "grad_norm": 0.11720468030354501, | |
| "learning_rate": 0.0006480078500760096, | |
| "loss": 0.9046, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.4700854700854701, | |
| "grad_norm": 0.11313634978608422, | |
| "learning_rate": 0.0006377959135998322, | |
| "loss": 0.8989, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.47619047619047616, | |
| "grad_norm": 0.10072650234577825, | |
| "learning_rate": 0.0006275213842808383, | |
| "loss": 0.892, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4822954822954823, | |
| "grad_norm": 0.16427063748319404, | |
| "learning_rate": 0.0006171889292530655, | |
| "loss": 0.8923, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.4884004884004884, | |
| "grad_norm": 0.09685334068579918, | |
| "learning_rate": 0.0006068032419629059, | |
| "loss": 0.9026, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.4945054945054945, | |
| "grad_norm": 0.09871518532748647, | |
| "learning_rate": 0.0005963690400371386, | |
| "loss": 0.8923, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.5006105006105006, | |
| "grad_norm": 0.10299185446487583, | |
| "learning_rate": 0.0005858910631399817, | |
| "loss": 0.8934, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.5067155067155067, | |
| "grad_norm": 0.12753918898402714, | |
| "learning_rate": 0.0005753740708201315, | |
| "loss": 0.8855, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 0.12750913259702365, | |
| "learning_rate": 0.0005648228403487712, | |
| "loss": 0.8911, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.518925518925519, | |
| "grad_norm": 0.1274157898333562, | |
| "learning_rate": 0.0005542421645495279, | |
| "loss": 0.8943, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.525030525030525, | |
| "grad_norm": 0.1771370225873098, | |
| "learning_rate": 0.0005436368496213656, | |
| "loss": 0.8823, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.5311355311355311, | |
| "grad_norm": 0.11030418227435798, | |
| "learning_rate": 0.0005330117129554028, | |
| "loss": 0.8855, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.5372405372405372, | |
| "grad_norm": 0.10914376299241067, | |
| "learning_rate": 0.0005223715809466454, | |
| "loss": 0.8896, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.5433455433455433, | |
| "grad_norm": 0.105079916260377, | |
| "learning_rate": 0.0005117212868016303, | |
| "loss": 0.8829, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.5494505494505495, | |
| "grad_norm": 0.09038201415584558, | |
| "learning_rate": 0.0005010656683429746, | |
| "loss": 0.8875, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.10067313064197672, | |
| "learning_rate": 0.0004904095658118283, | |
| "loss": 0.8744, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.5616605616605617, | |
| "grad_norm": 0.09677024273019037, | |
| "learning_rate": 0.0004797578196692281, | |
| "loss": 0.886, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5677655677655677, | |
| "grad_norm": 0.1010893098260069, | |
| "learning_rate": 0.00046911526839735093, | |
| "loss": 0.8914, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.5738705738705738, | |
| "grad_norm": 0.1016579599480523, | |
| "learning_rate": 0.0004584867463016671, | |
| "loss": 0.8821, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.57997557997558, | |
| "grad_norm": 0.10945662085952625, | |
| "learning_rate": 0.00044787708131499104, | |
| "loss": 0.8698, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.5860805860805861, | |
| "grad_norm": 0.11552520773703621, | |
| "learning_rate": 0.0004372910928044249, | |
| "loss": 0.8761, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5921855921855922, | |
| "grad_norm": 0.10307537673383473, | |
| "learning_rate": 0.00042673358938219544, | |
| "loss": 0.8743, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.5982905982905983, | |
| "grad_norm": 0.09087654917065777, | |
| "learning_rate": 0.00041620936672137393, | |
| "loss": 0.8758, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.6043956043956044, | |
| "grad_norm": 0.09850681791384697, | |
| "learning_rate": 0.00040572320537747656, | |
| "loss": 0.8728, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.6105006105006106, | |
| "grad_norm": 0.0992318941745092, | |
| "learning_rate": 0.0003952798686169279, | |
| "loss": 0.8876, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.6166056166056166, | |
| "grad_norm": 0.11916562636988841, | |
| "learning_rate": 0.00038488410025338133, | |
| "loss": 0.8799, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.6227106227106227, | |
| "grad_norm": 0.1102419615016477, | |
| "learning_rate": 0.00037454062249287477, | |
| "loss": 0.8748, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.6288156288156288, | |
| "grad_norm": 0.08376386530120562, | |
| "learning_rate": 0.0003642541337887999, | |
| "loss": 0.8782, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.6349206349206349, | |
| "grad_norm": 0.12657317900189496, | |
| "learning_rate": 0.00035402930670766296, | |
| "loss": 0.8634, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.6410256410256411, | |
| "grad_norm": 0.08636544191631769, | |
| "learning_rate": 0.00034387078580660346, | |
| "loss": 0.8649, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.6471306471306472, | |
| "grad_norm": 0.11450664347824203, | |
| "learning_rate": 0.00033378318552363664, | |
| "loss": 0.8655, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.6532356532356532, | |
| "grad_norm": 0.09878839008559168, | |
| "learning_rate": 0.0003237710880815756, | |
| "loss": 0.8751, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.6593406593406593, | |
| "grad_norm": 0.09052163701573301, | |
| "learning_rate": 0.00031383904140658986, | |
| "loss": 0.8628, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.6654456654456654, | |
| "grad_norm": 0.11374009475099364, | |
| "learning_rate": 0.0003039915570623396, | |
| "loss": 0.8702, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.6715506715506715, | |
| "grad_norm": 0.09096994547360551, | |
| "learning_rate": 0.0002942331082006308, | |
| "loss": 0.8606, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6776556776556777, | |
| "grad_norm": 0.09829912484792226, | |
| "learning_rate": 0.00028456812752951485, | |
| "loss": 0.8613, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.6837606837606838, | |
| "grad_norm": 0.09918852355520438, | |
| "learning_rate": 0.0002750010052997635, | |
| "loss": 0.8651, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6898656898656899, | |
| "grad_norm": 0.08703719318631921, | |
| "learning_rate": 0.00026553608731062604, | |
| "loss": 0.8634, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.6959706959706959, | |
| "grad_norm": 0.08958256157163819, | |
| "learning_rate": 0.00025617767293578176, | |
| "loss": 0.8569, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.702075702075702, | |
| "grad_norm": 0.08871557325816307, | |
| "learning_rate": 0.0002469300131703773, | |
| "loss": 0.861, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.7081807081807082, | |
| "grad_norm": 0.08822413460387163, | |
| "learning_rate": 0.00023779730870004235, | |
| "loss": 0.8494, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 0.09103503298034178, | |
| "learning_rate": 0.00022878370799275777, | |
| "loss": 0.8645, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.7203907203907204, | |
| "grad_norm": 0.09228123975601896, | |
| "learning_rate": 0.0002198933054144414, | |
| "loss": 0.8477, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.7264957264957265, | |
| "grad_norm": 0.11537298722683907, | |
| "learning_rate": 0.00021113013936911113, | |
| "loss": 0.8559, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.7326007326007326, | |
| "grad_norm": 0.12133130861088819, | |
| "learning_rate": 0.00020249819046446837, | |
| "loss": 0.855, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.7387057387057387, | |
| "grad_norm": 0.08762132815499236, | |
| "learning_rate": 0.00019400137970373356, | |
| "loss": 0.8598, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.7448107448107448, | |
| "grad_norm": 0.09591981770315502, | |
| "learning_rate": 0.00018564356670455767, | |
| "loss": 0.8623, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.7509157509157509, | |
| "grad_norm": 0.08440244551483579, | |
| "learning_rate": 0.00017742854794581785, | |
| "loss": 0.8629, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.757020757020757, | |
| "grad_norm": 0.08667278234179086, | |
| "learning_rate": 0.00016936005504309342, | |
| "loss": 0.8593, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.7631257631257631, | |
| "grad_norm": 0.09670164531050161, | |
| "learning_rate": 0.0001614417530536042, | |
| "loss": 0.8577, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.7692307692307693, | |
| "grad_norm": 0.1264104247325156, | |
| "learning_rate": 0.00015367723881138434, | |
| "loss": 0.8617, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.7753357753357754, | |
| "grad_norm": 0.08224555292780504, | |
| "learning_rate": 0.00014607003929344492, | |
| "loss": 0.8582, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.7814407814407814, | |
| "grad_norm": 0.08581860223147199, | |
| "learning_rate": 0.00013862361001766972, | |
| "loss": 0.8528, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7875457875457875, | |
| "grad_norm": 0.11871698275680992, | |
| "learning_rate": 0.00013134133347316885, | |
| "loss": 0.8437, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.7936507936507936, | |
| "grad_norm": 0.08356164913957449, | |
| "learning_rate": 0.0001242265175838072, | |
| "loss": 0.845, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7997557997557998, | |
| "grad_norm": 0.08792516275954312, | |
| "learning_rate": 0.00011728239420560316, | |
| "loss": 0.8504, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.8058608058608059, | |
| "grad_norm": 0.0839189452160314, | |
| "learning_rate": 0.0001105121176586793, | |
| "loss": 0.8492, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.811965811965812, | |
| "grad_norm": 0.07899895706535247, | |
| "learning_rate": 0.00010391876329443534, | |
| "loss": 0.846, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.818070818070818, | |
| "grad_norm": 0.09342601930472154, | |
| "learning_rate": 9.750532609858991e-05, | |
| "loss": 0.8513, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.8241758241758241, | |
| "grad_norm": 0.08506450364705921, | |
| "learning_rate": 9.127471933073007e-05, | |
| "loss": 0.8551, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.8302808302808303, | |
| "grad_norm": 0.08591775034557968, | |
| "learning_rate": 8.522977320098224e-05, | |
| "loss": 0.8457, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.8363858363858364, | |
| "grad_norm": 0.08883987592383243, | |
| "learning_rate": 7.937323358440934e-05, | |
| "loss": 0.8481, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.8424908424908425, | |
| "grad_norm": 0.09241014546560397, | |
| "learning_rate": 7.370776077371622e-05, | |
| "loss": 0.842, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.8485958485958486, | |
| "grad_norm": 0.08970361710526982, | |
| "learning_rate": 6.82359282708292e-05, | |
| "loss": 0.8515, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.8547008547008547, | |
| "grad_norm": 0.07963231871623425, | |
| "learning_rate": 6.296022161790149e-05, | |
| "loss": 0.8542, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.8608058608058609, | |
| "grad_norm": 0.08013240789229244, | |
| "learning_rate": 5.78830372682721e-05, | |
| "loss": 0.8467, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.8669108669108669, | |
| "grad_norm": 0.0759688508386286, | |
| "learning_rate": 5.300668149789417e-05, | |
| "loss": 0.847, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.873015873015873, | |
| "grad_norm": 0.07886102369723931, | |
| "learning_rate": 4.833336935772442e-05, | |
| "loss": 0.8425, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.8791208791208791, | |
| "grad_norm": 0.08173627877043077, | |
| "learning_rate": 4.386522366755169e-05, | |
| "loss": 0.8392, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.8852258852258852, | |
| "grad_norm": 0.0752411428468848, | |
| "learning_rate": 3.960427405172079e-05, | |
| "loss": 0.8469, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.8913308913308914, | |
| "grad_norm": 0.08853754561324295, | |
| "learning_rate": 3.5552456017189926e-05, | |
| "loss": 0.8477, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8974358974358975, | |
| "grad_norm": 0.07850504504773986, | |
| "learning_rate": 3.171161007433937e-05, | |
| "loss": 0.8428, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.9035409035409036, | |
| "grad_norm": 0.0779225305884226, | |
| "learning_rate": 2.808348090093277e-05, | |
| "loss": 0.8496, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.9096459096459096, | |
| "grad_norm": 0.08610580397739691, | |
| "learning_rate": 2.466971654960931e-05, | |
| "loss": 0.8485, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.9157509157509157, | |
| "grad_norm": 0.08126442173982612, | |
| "learning_rate": 2.147186769926712e-05, | |
| "loss": 0.8404, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.9218559218559218, | |
| "grad_norm": 0.07309643357333985, | |
| "learning_rate": 1.8491386950677812e-05, | |
| "loss": 0.8441, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.927960927960928, | |
| "grad_norm": 0.09343176187392903, | |
| "learning_rate": 1.572962816665302e-05, | |
| "loss": 0.8433, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.9340659340659341, | |
| "grad_norm": 0.07826041939717969, | |
| "learning_rate": 1.3187845857061508e-05, | |
| "loss": 0.8359, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.9401709401709402, | |
| "grad_norm": 0.08304159121172228, | |
| "learning_rate": 1.0867194608976228e-05, | |
| "loss": 0.8591, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.9462759462759462, | |
| "grad_norm": 0.08259928200183242, | |
| "learning_rate": 8.768728562211947e-06, | |
| "loss": 0.8454, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.9523809523809523, | |
| "grad_norm": 0.08219547432164107, | |
| "learning_rate": 6.893400930488569e-06, | |
| "loss": 0.8486, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.9584859584859585, | |
| "grad_norm": 0.07862593185208377, | |
| "learning_rate": 5.242063568441313e-06, | |
| "loss": 0.8483, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.9645909645909646, | |
| "grad_norm": 0.07766701411413329, | |
| "learning_rate": 3.815466584670746e-06, | |
| "loss": 0.8408, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.9706959706959707, | |
| "grad_norm": 0.07999354583215297, | |
| "learning_rate": 2.6142580010117823e-06, | |
| "loss": 0.8455, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.9768009768009768, | |
| "grad_norm": 0.07593923199320168, | |
| "learning_rate": 1.6389834581739814e-06, | |
| "loss": 0.8475, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.9829059829059829, | |
| "grad_norm": 0.09079049550630383, | |
| "learning_rate": 8.900859678879769e-07, | |
| "loss": 0.8463, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.989010989010989, | |
| "grad_norm": 0.08014122984645816, | |
| "learning_rate": 3.6790571167061305e-07, | |
| "loss": 0.8472, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.9951159951159951, | |
| "grad_norm": 0.08774528880462228, | |
| "learning_rate": 7.26798862996092e-08, | |
| "loss": 0.8393, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.2005486488342285, | |
| "eval_runtime": 120.1446, | |
| "eval_samples_per_second": 174.723, | |
| "eval_steps_per_second": 5.46, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 819, | |
| "total_flos": 80357621760000.0, | |
| "train_loss": 0.9138513950492291, | |
| "train_runtime": 1997.4789, | |
| "train_samples_per_second": 52.475, | |
| "train_steps_per_second": 0.41 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 819, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 80357621760000.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |