| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 17.77459749552773, | |
| "eval_steps": 500, | |
| "global_step": 1242, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14311270125223613, | |
| "grad_norm": 7.146514892578125, | |
| "learning_rate": 0.00039677938808373593, | |
| "loss": 3.5751, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28622540250447226, | |
| "grad_norm": 2.1325223445892334, | |
| "learning_rate": 0.00039355877616747184, | |
| "loss": 0.939, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4293381037567084, | |
| "grad_norm": 0.8520782589912415, | |
| "learning_rate": 0.00039033816425120774, | |
| "loss": 0.2653, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5724508050089445, | |
| "grad_norm": 0.7653748393058777, | |
| "learning_rate": 0.00038711755233494365, | |
| "loss": 0.1603, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7155635062611807, | |
| "grad_norm": 0.661469578742981, | |
| "learning_rate": 0.00038389694041867956, | |
| "loss": 0.1886, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8586762075134168, | |
| "grad_norm": 0.39610955119132996, | |
| "learning_rate": 0.00038067632850241547, | |
| "loss": 0.1859, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0017889087656529, | |
| "grad_norm": 0.4488755464553833, | |
| "learning_rate": 0.0003774557165861514, | |
| "loss": 0.1538, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.144901610017889, | |
| "grad_norm": 0.2944377362728119, | |
| "learning_rate": 0.00037423510466988734, | |
| "loss": 0.1195, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.2880143112701252, | |
| "grad_norm": 0.29124024510383606, | |
| "learning_rate": 0.0003710144927536232, | |
| "loss": 0.1271, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4311270125223614, | |
| "grad_norm": 0.42328736186027527, | |
| "learning_rate": 0.0003677938808373591, | |
| "loss": 0.1018, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.5742397137745976, | |
| "grad_norm": 0.3259565234184265, | |
| "learning_rate": 0.00036457326892109506, | |
| "loss": 0.0848, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7173524150268338, | |
| "grad_norm": 0.479124516248703, | |
| "learning_rate": 0.0003613526570048309, | |
| "loss": 0.106, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 0.40788090229034424, | |
| "learning_rate": 0.0003581320450885668, | |
| "loss": 0.0969, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0035778175313057, | |
| "grad_norm": 0.3574964106082916, | |
| "learning_rate": 0.0003549114331723028, | |
| "loss": 0.124, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.146690518783542, | |
| "grad_norm": 0.37805065512657166, | |
| "learning_rate": 0.0003516908212560387, | |
| "loss": 0.0491, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.289803220035778, | |
| "grad_norm": 0.25937220454216003, | |
| "learning_rate": 0.00034847020933977455, | |
| "loss": 0.0669, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.4329159212880143, | |
| "grad_norm": 0.34056201577186584, | |
| "learning_rate": 0.00034524959742351046, | |
| "loss": 0.0595, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.5760286225402504, | |
| "grad_norm": 0.30211707949638367, | |
| "learning_rate": 0.0003420289855072464, | |
| "loss": 0.0648, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.7191413237924866, | |
| "grad_norm": 0.18458786606788635, | |
| "learning_rate": 0.0003388083735909823, | |
| "loss": 0.0545, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.862254025044723, | |
| "grad_norm": 0.27384912967681885, | |
| "learning_rate": 0.0003355877616747182, | |
| "loss": 0.0684, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.005366726296959, | |
| "grad_norm": 0.16877304017543793, | |
| "learning_rate": 0.00033236714975845414, | |
| "loss": 0.0695, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.148479427549195, | |
| "grad_norm": 0.07739146798849106, | |
| "learning_rate": 0.00032914653784219005, | |
| "loss": 0.0256, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.2915921288014314, | |
| "grad_norm": 0.2832132577896118, | |
| "learning_rate": 0.0003259259259259259, | |
| "loss": 0.0263, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.434704830053667, | |
| "grad_norm": 0.21412289142608643, | |
| "learning_rate": 0.00032270531400966187, | |
| "loss": 0.0287, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.5778175313059033, | |
| "grad_norm": 0.1840696483850479, | |
| "learning_rate": 0.0003194847020933978, | |
| "loss": 0.0469, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.7209302325581395, | |
| "grad_norm": 0.34246236085891724, | |
| "learning_rate": 0.00031626409017713363, | |
| "loss": 0.0243, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.8640429338103757, | |
| "grad_norm": 0.056173525750637054, | |
| "learning_rate": 0.0003130434782608696, | |
| "loss": 0.0252, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.007155635062611, | |
| "grad_norm": 0.09256428480148315, | |
| "learning_rate": 0.0003098228663446055, | |
| "loss": 0.0216, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.150268336314848, | |
| "grad_norm": 0.20085078477859497, | |
| "learning_rate": 0.0003066022544283414, | |
| "loss": 0.0102, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.293381037567084, | |
| "grad_norm": 0.021982286125421524, | |
| "learning_rate": 0.0003033816425120773, | |
| "loss": 0.0131, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.43649373881932, | |
| "grad_norm": 0.054368916898965836, | |
| "learning_rate": 0.0003001610305958132, | |
| "loss": 0.0145, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.579606440071556, | |
| "grad_norm": 0.0868581086397171, | |
| "learning_rate": 0.00029694041867954913, | |
| "loss": 0.0181, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.722719141323792, | |
| "grad_norm": 0.24308475852012634, | |
| "learning_rate": 0.00029371980676328504, | |
| "loss": 0.0125, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 4.8658318425760285, | |
| "grad_norm": 0.14394602179527283, | |
| "learning_rate": 0.00029049919484702095, | |
| "loss": 0.0149, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.008944543828265, | |
| "grad_norm": 0.05040862783789635, | |
| "learning_rate": 0.00028727858293075686, | |
| "loss": 0.0096, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.152057245080501, | |
| "grad_norm": 0.28047820925712585, | |
| "learning_rate": 0.00028405797101449276, | |
| "loss": 0.0032, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.295169946332737, | |
| "grad_norm": 0.07502233237028122, | |
| "learning_rate": 0.0002808373590982287, | |
| "loss": 0.0038, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.438282647584973, | |
| "grad_norm": 0.8537871837615967, | |
| "learning_rate": 0.0002776167471819646, | |
| "loss": 0.0073, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.5813953488372094, | |
| "grad_norm": 0.005727715790271759, | |
| "learning_rate": 0.0002743961352657005, | |
| "loss": 0.0106, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.724508050089446, | |
| "grad_norm": 0.04042937234044075, | |
| "learning_rate": 0.0002711755233494364, | |
| "loss": 0.0041, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 5.867620751341682, | |
| "grad_norm": 0.11248348653316498, | |
| "learning_rate": 0.0002679549114331723, | |
| "loss": 0.003, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.010733452593918, | |
| "grad_norm": 0.014976495876908302, | |
| "learning_rate": 0.00026473429951690827, | |
| "loss": 0.0067, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.153846153846154, | |
| "grad_norm": 0.15070898830890656, | |
| "learning_rate": 0.0002615136876006441, | |
| "loss": 0.0035, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.29695885509839, | |
| "grad_norm": 0.0066925715655088425, | |
| "learning_rate": 0.00025829307568438003, | |
| "loss": 0.0027, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.440071556350626, | |
| "grad_norm": 0.015314973890781403, | |
| "learning_rate": 0.00025507246376811594, | |
| "loss": 0.0045, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.583184257602863, | |
| "grad_norm": 0.030470581725239754, | |
| "learning_rate": 0.00025185185185185185, | |
| "loss": 0.0029, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.726296958855098, | |
| "grad_norm": 0.0092542115598917, | |
| "learning_rate": 0.00024863123993558775, | |
| "loss": 0.0043, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 6.869409660107334, | |
| "grad_norm": 0.016118695959448814, | |
| "learning_rate": 0.00024541062801932366, | |
| "loss": 0.0011, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.01252236135957, | |
| "grad_norm": 0.01760493591427803, | |
| "learning_rate": 0.0002421900161030596, | |
| "loss": 0.004, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.155635062611807, | |
| "grad_norm": 0.0077838534489274025, | |
| "learning_rate": 0.0002389694041867955, | |
| "loss": 0.0004, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.298747763864043, | |
| "grad_norm": 0.006766254547983408, | |
| "learning_rate": 0.00023574879227053139, | |
| "loss": 0.0015, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.441860465116279, | |
| "grad_norm": 0.009164445102214813, | |
| "learning_rate": 0.00023252818035426732, | |
| "loss": 0.0006, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.584973166368515, | |
| "grad_norm": 0.002783432835713029, | |
| "learning_rate": 0.00022930756843800323, | |
| "loss": 0.0005, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.728085867620751, | |
| "grad_norm": 0.15486985445022583, | |
| "learning_rate": 0.0002260869565217391, | |
| "loss": 0.0036, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 7.8711985688729875, | |
| "grad_norm": 0.042650897055864334, | |
| "learning_rate": 0.00022286634460547507, | |
| "loss": 0.0006, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.014311270125223, | |
| "grad_norm": 0.0018309111474081874, | |
| "learning_rate": 0.00021964573268921095, | |
| "loss": 0.0011, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.15742397137746, | |
| "grad_norm": 0.005560223013162613, | |
| "learning_rate": 0.00021642512077294686, | |
| "loss": 0.001, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.300536672629695, | |
| "grad_norm": 0.03727242350578308, | |
| "learning_rate": 0.0002132045088566828, | |
| "loss": 0.0015, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.443649373881932, | |
| "grad_norm": 0.34321093559265137, | |
| "learning_rate": 0.00020998389694041868, | |
| "loss": 0.0031, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.586762075134168, | |
| "grad_norm": 0.020942572504281998, | |
| "learning_rate": 0.00020676328502415459, | |
| "loss": 0.0022, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 8.729874776386405, | |
| "grad_norm": 0.010578208602964878, | |
| "learning_rate": 0.00020354267310789052, | |
| "loss": 0.0006, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 8.87298747763864, | |
| "grad_norm": 0.004323468543589115, | |
| "learning_rate": 0.00020032206119162643, | |
| "loss": 0.0005, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 9.016100178890877, | |
| "grad_norm": 0.1614646017551422, | |
| "learning_rate": 0.00019710144927536234, | |
| "loss": 0.0011, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.159212880143112, | |
| "grad_norm": 0.0012326347641646862, | |
| "learning_rate": 0.00019388083735909825, | |
| "loss": 0.0005, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.30232558139535, | |
| "grad_norm": 0.006543063558638096, | |
| "learning_rate": 0.00019066022544283415, | |
| "loss": 0.0002, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.445438282647585, | |
| "grad_norm": 0.21280421316623688, | |
| "learning_rate": 0.00018743961352657006, | |
| "loss": 0.0003, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.588550983899822, | |
| "grad_norm": 0.006327577400952578, | |
| "learning_rate": 0.00018421900161030597, | |
| "loss": 0.0002, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 9.731663685152057, | |
| "grad_norm": 0.0025285291485488415, | |
| "learning_rate": 0.00018099838969404188, | |
| "loss": 0.0001, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 9.874776386404294, | |
| "grad_norm": 0.0014309959951788187, | |
| "learning_rate": 0.00017777777777777779, | |
| "loss": 0.0001, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.01788908765653, | |
| "grad_norm": 0.0024150668177753687, | |
| "learning_rate": 0.0001745571658615137, | |
| "loss": 0.0001, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.161001788908766, | |
| "grad_norm": 0.0025761763099581003, | |
| "learning_rate": 0.0001713365539452496, | |
| "loss": 0.0001, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.304114490161002, | |
| "grad_norm": 0.0017020882805809379, | |
| "learning_rate": 0.0001681159420289855, | |
| "loss": 0.0001, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.447227191413237, | |
| "grad_norm": 0.0028596080373972654, | |
| "learning_rate": 0.00016489533011272142, | |
| "loss": 0.0001, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.590339892665474, | |
| "grad_norm": 0.0019378801807761192, | |
| "learning_rate": 0.00016167471819645735, | |
| "loss": 0.0001, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 10.73345259391771, | |
| "grad_norm": 0.001211544731631875, | |
| "learning_rate": 0.00015845410628019323, | |
| "loss": 0.0001, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 10.876565295169947, | |
| "grad_norm": 0.0033484594896435738, | |
| "learning_rate": 0.00015523349436392914, | |
| "loss": 0.0001, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.019677996422182, | |
| "grad_norm": 0.001493943389505148, | |
| "learning_rate": 0.00015201288244766508, | |
| "loss": 0.0001, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.162790697674419, | |
| "grad_norm": 0.0019909776747226715, | |
| "learning_rate": 0.00014879227053140096, | |
| "loss": 0.0001, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.305903398926654, | |
| "grad_norm": 0.0011982638388872147, | |
| "learning_rate": 0.0001455716586151369, | |
| "loss": 0.0001, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.449016100178891, | |
| "grad_norm": 0.0015958467265591025, | |
| "learning_rate": 0.0001423510466988728, | |
| "loss": 0.0001, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 11.592128801431127, | |
| "grad_norm": 0.0008461058023385704, | |
| "learning_rate": 0.0001391304347826087, | |
| "loss": 0.0001, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 11.735241502683364, | |
| "grad_norm": 0.0005576548865064979, | |
| "learning_rate": 0.00013590982286634462, | |
| "loss": 0.0001, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 11.878354203935599, | |
| "grad_norm": 0.0017713948618620634, | |
| "learning_rate": 0.0001326892109500805, | |
| "loss": 0.0001, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 12.021466905187836, | |
| "grad_norm": 0.001206880551762879, | |
| "learning_rate": 0.00012946859903381643, | |
| "loss": 0.0001, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.164579606440071, | |
| "grad_norm": 0.0013083606027066708, | |
| "learning_rate": 0.00012624798711755234, | |
| "loss": 0.0001, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 12.307692307692308, | |
| "grad_norm": 0.0008201482123695314, | |
| "learning_rate": 0.00012302737520128825, | |
| "loss": 0.0001, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.450805008944544, | |
| "grad_norm": 0.0006802495336160064, | |
| "learning_rate": 0.00011980676328502416, | |
| "loss": 0.0001, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 12.59391771019678, | |
| "grad_norm": 0.0017911783652380109, | |
| "learning_rate": 0.00011658615136876008, | |
| "loss": 0.0001, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 12.737030411449016, | |
| "grad_norm": 0.0007388959056697786, | |
| "learning_rate": 0.00011336553945249598, | |
| "loss": 0.0, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 12.880143112701251, | |
| "grad_norm": 0.0007727427291683853, | |
| "learning_rate": 0.00011014492753623188, | |
| "loss": 0.0001, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.023255813953488, | |
| "grad_norm": 0.0008818788919597864, | |
| "learning_rate": 0.0001069243156199678, | |
| "loss": 0.0001, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 13.166368515205724, | |
| "grad_norm": 0.0005572364898398519, | |
| "learning_rate": 0.0001037037037037037, | |
| "loss": 0.0, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 13.30948121645796, | |
| "grad_norm": 0.0009758470696397126, | |
| "learning_rate": 0.00010048309178743962, | |
| "loss": 0.0001, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.452593917710196, | |
| "grad_norm": 0.0003166435344610363, | |
| "learning_rate": 9.726247987117553e-05, | |
| "loss": 0.0001, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 13.595706618962433, | |
| "grad_norm": 0.0005005749990232289, | |
| "learning_rate": 9.404186795491144e-05, | |
| "loss": 0.0, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 13.738819320214668, | |
| "grad_norm": 0.0003304154670331627, | |
| "learning_rate": 9.082125603864735e-05, | |
| "loss": 0.0001, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 13.881932021466906, | |
| "grad_norm": 0.0005377003108151257, | |
| "learning_rate": 8.760064412238325e-05, | |
| "loss": 0.0001, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 14.02504472271914, | |
| "grad_norm": 0.0015913191018626094, | |
| "learning_rate": 8.438003220611916e-05, | |
| "loss": 0.0001, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 14.168157423971378, | |
| "grad_norm": 0.000676720985211432, | |
| "learning_rate": 8.115942028985508e-05, | |
| "loss": 0.0001, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.311270125223613, | |
| "grad_norm": 0.0007494900492019951, | |
| "learning_rate": 7.793880837359099e-05, | |
| "loss": 0.0001, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 14.45438282647585, | |
| "grad_norm": 0.0015422647120431066, | |
| "learning_rate": 7.47181964573269e-05, | |
| "loss": 0.0, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 14.597495527728086, | |
| "grad_norm": 0.0005012313486076891, | |
| "learning_rate": 7.14975845410628e-05, | |
| "loss": 0.0, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 14.740608228980323, | |
| "grad_norm": 0.0008338551269844174, | |
| "learning_rate": 6.827697262479872e-05, | |
| "loss": 0.0, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 14.883720930232558, | |
| "grad_norm": 0.0006810138584114611, | |
| "learning_rate": 6.505636070853462e-05, | |
| "loss": 0.0001, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 15.026833631484795, | |
| "grad_norm": 0.00043299293611198664, | |
| "learning_rate": 6.183574879227053e-05, | |
| "loss": 0.0, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 15.16994633273703, | |
| "grad_norm": 0.0005277034360915422, | |
| "learning_rate": 5.861513687600645e-05, | |
| "loss": 0.0, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 15.313059033989267, | |
| "grad_norm": 0.0006858156993985176, | |
| "learning_rate": 5.5394524959742355e-05, | |
| "loss": 0.0001, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 15.456171735241503, | |
| "grad_norm": 0.0008438636432401836, | |
| "learning_rate": 5.217391304347826e-05, | |
| "loss": 0.0, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 15.59928443649374, | |
| "grad_norm": 0.0012173138093203306, | |
| "learning_rate": 4.895330112721417e-05, | |
| "loss": 0.0001, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 15.742397137745975, | |
| "grad_norm": 0.002290137577801943, | |
| "learning_rate": 4.573268921095008e-05, | |
| "loss": 0.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 15.88550983899821, | |
| "grad_norm": 0.0005496228695847094, | |
| "learning_rate": 4.2512077294685994e-05, | |
| "loss": 0.0, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 16.028622540250446, | |
| "grad_norm": 0.0018827420426532626, | |
| "learning_rate": 3.92914653784219e-05, | |
| "loss": 0.0, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 16.171735241502684, | |
| "grad_norm": 0.00045006562140770257, | |
| "learning_rate": 3.607085346215781e-05, | |
| "loss": 0.0001, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 16.31484794275492, | |
| "grad_norm": 0.0005126325413584709, | |
| "learning_rate": 3.2850241545893725e-05, | |
| "loss": 0.0, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 16.457960644007155, | |
| "grad_norm": 0.00035093360929749906, | |
| "learning_rate": 2.962962962962963e-05, | |
| "loss": 0.0, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 16.60107334525939, | |
| "grad_norm": 0.0010109692811965942, | |
| "learning_rate": 2.640901771336554e-05, | |
| "loss": 0.0001, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 16.74418604651163, | |
| "grad_norm": 0.0006910230731591582, | |
| "learning_rate": 2.318840579710145e-05, | |
| "loss": 0.0, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 16.887298747763865, | |
| "grad_norm": 0.0004351095121819526, | |
| "learning_rate": 1.996779388083736e-05, | |
| "loss": 0.0, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 17.0304114490161, | |
| "grad_norm": 0.0006468660430982709, | |
| "learning_rate": 1.674718196457327e-05, | |
| "loss": 0.0, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 17.173524150268335, | |
| "grad_norm": 0.0002576902334112674, | |
| "learning_rate": 1.3526570048309179e-05, | |
| "loss": 0.0, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 17.316636851520574, | |
| "grad_norm": 0.0010522498050704598, | |
| "learning_rate": 1.0305958132045089e-05, | |
| "loss": 0.0, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 17.45974955277281, | |
| "grad_norm": 0.0007789513911120594, | |
| "learning_rate": 7.0853462157809985e-06, | |
| "loss": 0.0001, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 17.602862254025045, | |
| "grad_norm": 0.0009570368565618992, | |
| "learning_rate": 3.864734299516908e-06, | |
| "loss": 0.0, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 17.74597495527728, | |
| "grad_norm": 0.0009920781012624502, | |
| "learning_rate": 6.44122383252818e-07, | |
| "loss": 0.0, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 17.77459749552773, | |
| "step": 1242, | |
| "total_flos": 6.807580263736934e+16, | |
| "train_loss": 0.056659956144777014, | |
| "train_runtime": 9770.217, | |
| "train_samples_per_second": 6.177, | |
| "train_steps_per_second": 0.127 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1242, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 18, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.807580263736934e+16, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |