| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 500, |
| "global_step": 2094240, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.009550003820001528, |
| "grad_norm": 1.1688205003738403, |
| "learning_rate": 0.00028647758200830823, |
| "loss": 4.7726, |
| "mean_token_accuracy": 0.29613289506579993, |
| "num_tokens": 716800000.0, |
| "step": 20000 |
| }, |
| { |
| "epoch": 0.019100007640003056, |
| "grad_norm": 1.0122355222702026, |
| "learning_rate": 0.00029724265264455594, |
| "loss": 3.5064, |
| "mean_token_accuracy": 0.39106567760258915, |
| "num_tokens": 1433600000.0, |
| "step": 40000 |
| }, |
| { |
| "epoch": 0.028650011460004583, |
| "grad_norm": 0.9957022070884705, |
| "learning_rate": 0.0002943487112555509, |
| "loss": 3.4122, |
| "mean_token_accuracy": 0.40039802242666483, |
| "num_tokens": 2150400000.0, |
| "step": 60000 |
| }, |
| { |
| "epoch": 0.03820001528000611, |
| "grad_norm": 1.2025322914123535, |
| "learning_rate": 0.00029145476986654586, |
| "loss": 3.3766, |
| "mean_token_accuracy": 0.404039168266952, |
| "num_tokens": 2867200000.0, |
| "step": 80000 |
| }, |
| { |
| "epoch": 0.04775001910000764, |
| "grad_norm": 1.0380007028579712, |
| "learning_rate": 0.0002885608284775408, |
| "loss": 3.3565, |
| "mean_token_accuracy": 0.40606449462026356, |
| "num_tokens": 3584000000.0, |
| "step": 100000 |
| }, |
| { |
| "epoch": 0.057300022920009165, |
| "grad_norm": 1.1203994750976562, |
| "learning_rate": 0.0002856668870885358, |
| "loss": 3.3421, |
| "mean_token_accuracy": 0.40754339938014744, |
| "num_tokens": 4300800000.0, |
| "step": 120000 |
| }, |
| { |
| "epoch": 0.0668500267400107, |
| "grad_norm": 1.1507455110549927, |
| "learning_rate": 0.0002827729456995307, |
| "loss": 3.3327, |
| "mean_token_accuracy": 0.40846395269036295, |
| "num_tokens": 5017600000.0, |
| "step": 140000 |
| }, |
| { |
| "epoch": 0.07640003056001222, |
| "grad_norm": 1.2616394758224487, |
| "learning_rate": 0.0002798790043105257, |
| "loss": 3.3239, |
| "mean_token_accuracy": 0.40932240092903377, |
| "num_tokens": 5734400000.0, |
| "step": 160000 |
| }, |
| { |
| "epoch": 0.08595003438001375, |
| "grad_norm": 1.2600022554397583, |
| "learning_rate": 0.00027698506292152063, |
| "loss": 3.3172, |
| "mean_token_accuracy": 0.41004598908573386, |
| "num_tokens": 6451200000.0, |
| "step": 180000 |
| }, |
| { |
| "epoch": 0.09550003820001528, |
| "grad_norm": 1.1764442920684814, |
| "learning_rate": 0.00027409112153251557, |
| "loss": 3.3119, |
| "mean_token_accuracy": 0.410561589974165, |
| "num_tokens": 7168000000.0, |
| "step": 200000 |
| }, |
| { |
| "epoch": 0.1050500420200168, |
| "grad_norm": 1.2408899068832397, |
| "learning_rate": 0.00027119718014351055, |
| "loss": 3.3061, |
| "mean_token_accuracy": 0.411199274918437, |
| "num_tokens": 7884800000.0, |
| "step": 220000 |
| }, |
| { |
| "epoch": 0.11460004584001833, |
| "grad_norm": 1.2953583002090454, |
| "learning_rate": 0.0002683032387545055, |
| "loss": 3.3012, |
| "mean_token_accuracy": 0.41174386738538743, |
| "num_tokens": 8601600000.0, |
| "step": 240000 |
| }, |
| { |
| "epoch": 0.12415004966001987, |
| "grad_norm": 1.3780796527862549, |
| "learning_rate": 0.0002654092973655004, |
| "loss": 3.2974, |
| "mean_token_accuracy": 0.41211788419932127, |
| "num_tokens": 9318400000.0, |
| "step": 260000 |
| }, |
| { |
| "epoch": 0.1337000534800214, |
| "grad_norm": 1.2816623449325562, |
| "learning_rate": 0.0002625153559764954, |
| "loss": 3.2952, |
| "mean_token_accuracy": 0.4122900270193815, |
| "num_tokens": 10035200000.0, |
| "step": 280000 |
| }, |
| { |
| "epoch": 0.1432500573000229, |
| "grad_norm": 1.462896466255188, |
| "learning_rate": 0.00025962141458749034, |
| "loss": 3.2898, |
| "mean_token_accuracy": 0.4128769779801369, |
| "num_tokens": 10752000000.0, |
| "step": 300000 |
| }, |
| { |
| "epoch": 0.15280006112002445, |
| "grad_norm": 1.4050343036651611, |
| "learning_rate": 0.0002567274731984853, |
| "loss": 3.2866, |
| "mean_token_accuracy": 0.4132985157236457, |
| "num_tokens": 11468800000.0, |
| "step": 320000 |
| }, |
| { |
| "epoch": 0.162350064940026, |
| "grad_norm": 1.3888232707977295, |
| "learning_rate": 0.00025383353180948026, |
| "loss": 3.2839, |
| "mean_token_accuracy": 0.41356196113973853, |
| "num_tokens": 12185600000.0, |
| "step": 340000 |
| }, |
| { |
| "epoch": 0.1719000687600275, |
| "grad_norm": 1.3985786437988281, |
| "learning_rate": 0.0002509395904204752, |
| "loss": 3.2824, |
| "mean_token_accuracy": 0.4136822006031871, |
| "num_tokens": 12902400000.0, |
| "step": 360000 |
| }, |
| { |
| "epoch": 0.18145007258002904, |
| "grad_norm": 1.5853444337844849, |
| "learning_rate": 0.00024804564903147013, |
| "loss": 3.2796, |
| "mean_token_accuracy": 0.41403463195711376, |
| "num_tokens": 13619200000.0, |
| "step": 380000 |
| }, |
| { |
| "epoch": 0.19100007640003056, |
| "grad_norm": 1.5639410018920898, |
| "learning_rate": 0.00024515170764246506, |
| "loss": 3.2773, |
| "mean_token_accuracy": 0.4142179542243481, |
| "num_tokens": 14336000000.0, |
| "step": 400000 |
| }, |
| { |
| "epoch": 0.2005500802200321, |
| "grad_norm": 1.4351433515548706, |
| "learning_rate": 0.00024225776625346005, |
| "loss": 3.2752, |
| "mean_token_accuracy": 0.41444926087111233, |
| "num_tokens": 15052800000.0, |
| "step": 420000 |
| }, |
| { |
| "epoch": 0.2101000840400336, |
| "grad_norm": 1.3414918184280396, |
| "learning_rate": 0.00023936382486445498, |
| "loss": 3.2725, |
| "mean_token_accuracy": 0.41476476649940014, |
| "num_tokens": 15769600000.0, |
| "step": 440000 |
| }, |
| { |
| "epoch": 0.21965008786003515, |
| "grad_norm": 1.3302001953125, |
| "learning_rate": 0.00023646988347544994, |
| "loss": 3.2696, |
| "mean_token_accuracy": 0.4150806698143482, |
| "num_tokens": 16486400000.0, |
| "step": 460000 |
| }, |
| { |
| "epoch": 0.22920009168003666, |
| "grad_norm": 1.3756541013717651, |
| "learning_rate": 0.00023357594208644488, |
| "loss": 3.2683, |
| "mean_token_accuracy": 0.4152164765149355, |
| "num_tokens": 17203200000.0, |
| "step": 480000 |
| }, |
| { |
| "epoch": 0.2387500955000382, |
| "grad_norm": 1.330269694328308, |
| "learning_rate": 0.00023068200069743984, |
| "loss": 3.2665, |
| "mean_token_accuracy": 0.4154003126785159, |
| "num_tokens": 17920000000.0, |
| "step": 500000 |
| }, |
| { |
| "epoch": 0.24830009932003974, |
| "grad_norm": 1.7756025791168213, |
| "learning_rate": 0.00022778805930843483, |
| "loss": 3.2648, |
| "mean_token_accuracy": 0.4155686768323183, |
| "num_tokens": 18636800000.0, |
| "step": 520000 |
| }, |
| { |
| "epoch": 0.25785010314004125, |
| "grad_norm": 1.6679662466049194, |
| "learning_rate": 0.00022489411791942976, |
| "loss": 3.2617, |
| "mean_token_accuracy": 0.41595828180462124, |
| "num_tokens": 19353600000.0, |
| "step": 540000 |
| }, |
| { |
| "epoch": 0.2674001069600428, |
| "grad_norm": 1.5160603523254395, |
| "learning_rate": 0.00022200017653042472, |
| "loss": 3.2601, |
| "mean_token_accuracy": 0.4160811348050833, |
| "num_tokens": 716800000.0, |
| "step": 560000 |
| }, |
| { |
| "epoch": 0.27695011078004433, |
| "grad_norm": 2.128943681716919, |
| "learning_rate": 0.00021910623514141968, |
| "loss": 3.259, |
| "mean_token_accuracy": 0.41622272021621465, |
| "num_tokens": 1433600000.0, |
| "step": 580000 |
| }, |
| { |
| "epoch": 0.2865001146000458, |
| "grad_norm": 1.550946593284607, |
| "learning_rate": 0.00021621229375241461, |
| "loss": 3.2555, |
| "mean_token_accuracy": 0.4166563056409359, |
| "num_tokens": 2150400000.0, |
| "step": 600000 |
| }, |
| { |
| "epoch": 0.29605011842004736, |
| "grad_norm": 1.5084576606750488, |
| "learning_rate": 0.00021331835236340957, |
| "loss": 3.2543, |
| "mean_token_accuracy": 0.4167668910384178, |
| "num_tokens": 2867200000.0, |
| "step": 620000 |
| }, |
| { |
| "epoch": 0.3056001222400489, |
| "grad_norm": 1.7308917045593262, |
| "learning_rate": 0.00021042441097440454, |
| "loss": 3.2531, |
| "mean_token_accuracy": 0.416923209066689, |
| "num_tokens": 3584000000.0, |
| "step": 640000 |
| }, |
| { |
| "epoch": 0.31515012606005044, |
| "grad_norm": 1.6496219635009766, |
| "learning_rate": 0.00020753046958539947, |
| "loss": 3.2503, |
| "mean_token_accuracy": 0.4171900423392653, |
| "num_tokens": 4300800000.0, |
| "step": 660000 |
| }, |
| { |
| "epoch": 0.324700129880052, |
| "grad_norm": 1.911421537399292, |
| "learning_rate": 0.00020463652819639443, |
| "loss": 3.2494, |
| "mean_token_accuracy": 0.4172973266944289, |
| "num_tokens": 5017600000.0, |
| "step": 680000 |
| }, |
| { |
| "epoch": 0.33425013370005346, |
| "grad_norm": 1.625441074371338, |
| "learning_rate": 0.00020174258680738936, |
| "loss": 3.2485, |
| "mean_token_accuracy": 0.4173892762258649, |
| "num_tokens": 5734400000.0, |
| "step": 700000 |
| }, |
| { |
| "epoch": 0.343800137520055, |
| "grad_norm": 1.570096731185913, |
| "learning_rate": 0.00019884864541838432, |
| "loss": 3.2467, |
| "mean_token_accuracy": 0.4176161937117577, |
| "num_tokens": 6451200000.0, |
| "step": 720000 |
| }, |
| { |
| "epoch": 0.35335014134005654, |
| "grad_norm": 1.5831801891326904, |
| "learning_rate": 0.00019595470402937928, |
| "loss": 3.2441, |
| "mean_token_accuracy": 0.41793804090470077, |
| "num_tokens": 7168000000.0, |
| "step": 740000 |
| }, |
| { |
| "epoch": 0.3629001451600581, |
| "grad_norm": 1.6359102725982666, |
| "learning_rate": 0.00019306076264037422, |
| "loss": 3.2439, |
| "mean_token_accuracy": 0.41790355779081584, |
| "num_tokens": 7884800000.0, |
| "step": 760000 |
| }, |
| { |
| "epoch": 0.37245014898005957, |
| "grad_norm": 1.9125442504882812, |
| "learning_rate": 0.00019016682125136918, |
| "loss": 3.2416, |
| "mean_token_accuracy": 0.4181554499194026, |
| "num_tokens": 8601600000.0, |
| "step": 780000 |
| }, |
| { |
| "epoch": 0.3820001528000611, |
| "grad_norm": 1.6356027126312256, |
| "learning_rate": 0.0001872728798623641, |
| "loss": 3.2392, |
| "mean_token_accuracy": 0.41842390780746935, |
| "num_tokens": 9318400000.0, |
| "step": 800000 |
| }, |
| { |
| "epoch": 0.39155015662006265, |
| "grad_norm": 1.69579017162323, |
| "learning_rate": 0.00018437893847335907, |
| "loss": 3.2381, |
| "mean_token_accuracy": 0.41857809690237047, |
| "num_tokens": 10035200000.0, |
| "step": 820000 |
| }, |
| { |
| "epoch": 0.4011001604400642, |
| "grad_norm": 1.7878586053848267, |
| "learning_rate": 0.00018148499708435403, |
| "loss": 3.2375, |
| "mean_token_accuracy": 0.41865148201435803, |
| "num_tokens": 10752000000.0, |
| "step": 840000 |
| }, |
| { |
| "epoch": 0.41065016426006573, |
| "grad_norm": 1.7767938375473022, |
| "learning_rate": 0.00017859105569534897, |
| "loss": 3.2353, |
| "mean_token_accuracy": 0.41889262205660344, |
| "num_tokens": 11468800000.0, |
| "step": 860000 |
| }, |
| { |
| "epoch": 0.4202001680800672, |
| "grad_norm": 1.6678400039672852, |
| "learning_rate": 0.00017569711430634393, |
| "loss": 3.2337, |
| "mean_token_accuracy": 0.41908056329786775, |
| "num_tokens": 12185600000.0, |
| "step": 880000 |
| }, |
| { |
| "epoch": 0.42975017190006876, |
| "grad_norm": 1.862349033355713, |
| "learning_rate": 0.00017280317291733891, |
| "loss": 3.2329, |
| "mean_token_accuracy": 0.4191736038953066, |
| "num_tokens": 12902400000.0, |
| "step": 900000 |
| }, |
| { |
| "epoch": 0.4393001757200703, |
| "grad_norm": 1.8526560068130493, |
| "learning_rate": 0.00016990923152833385, |
| "loss": 3.232, |
| "mean_token_accuracy": 0.4192189232364297, |
| "num_tokens": 13619200000.0, |
| "step": 920000 |
| }, |
| { |
| "epoch": 0.44885017954007184, |
| "grad_norm": 1.7189236879348755, |
| "learning_rate": 0.0001670152901393288, |
| "loss": 3.2302, |
| "mean_token_accuracy": 0.4194715451017022, |
| "num_tokens": 14336000000.0, |
| "step": 940000 |
| }, |
| { |
| "epoch": 0.4584001833600733, |
| "grad_norm": 2.0065693855285645, |
| "learning_rate": 0.00016412134875032377, |
| "loss": 3.2277, |
| "mean_token_accuracy": 0.419769259378314, |
| "num_tokens": 15052800000.0, |
| "step": 960000 |
| }, |
| { |
| "epoch": 0.46795018718007486, |
| "grad_norm": 1.647645354270935, |
| "learning_rate": 0.0001612274073613187, |
| "loss": 3.2272, |
| "mean_token_accuracy": 0.41980642325282097, |
| "num_tokens": 15769600000.0, |
| "step": 980000 |
| }, |
| { |
| "epoch": 0.4775001910000764, |
| "grad_norm": 1.8431377410888672, |
| "learning_rate": 0.00015833346597231366, |
| "loss": 3.2244, |
| "mean_token_accuracy": 0.42018424404114485, |
| "num_tokens": 16486400000.0, |
| "step": 1000000 |
| }, |
| { |
| "epoch": 0.48705019482007794, |
| "grad_norm": 1.8152481317520142, |
| "learning_rate": 0.0001554395245833086, |
| "loss": 3.2239, |
| "mean_token_accuracy": 0.42016951968967914, |
| "num_tokens": 17203200000.0, |
| "step": 1020000 |
| }, |
| { |
| "epoch": 0.4966001986400795, |
| "grad_norm": 1.979134440422058, |
| "learning_rate": 0.00015254558319430356, |
| "loss": 3.2226, |
| "mean_token_accuracy": 0.42036232096105813, |
| "num_tokens": 17920000000.0, |
| "step": 1040000 |
| }, |
| { |
| "epoch": 0.506150202460081, |
| "grad_norm": 2.2059521675109863, |
| "learning_rate": 0.00014965164180529852, |
| "loss": 3.2199, |
| "mean_token_accuracy": 0.4206514175161719, |
| "num_tokens": 18636800000.0, |
| "step": 1060000 |
| }, |
| { |
| "epoch": 0.5157002062800825, |
| "grad_norm": 2.0843093395233154, |
| "learning_rate": 0.00014675770041629345, |
| "loss": 3.2192, |
| "mean_token_accuracy": 0.42072975924313066, |
| "num_tokens": 19353600000.0, |
| "step": 1080000 |
| }, |
| { |
| "epoch": 0.525250210100084, |
| "grad_norm": 1.7924293279647827, |
| "learning_rate": 0.0001438637590272884, |
| "loss": 3.2178, |
| "mean_token_accuracy": 0.4209353769227862, |
| "num_tokens": 20070400000.0, |
| "step": 1100000 |
| }, |
| { |
| "epoch": 0.5348002139200856, |
| "grad_norm": 1.8186842203140259, |
| "learning_rate": 0.00014096981763828334, |
| "loss": 3.2166, |
| "mean_token_accuracy": 0.42104669906646014, |
| "num_tokens": 20787200000.0, |
| "step": 1120000 |
| }, |
| { |
| "epoch": 0.5443502177400871, |
| "grad_norm": 2.0781736373901367, |
| "learning_rate": 0.0001380758762492783, |
| "loss": 3.2147, |
| "mean_token_accuracy": 0.42130602815449236, |
| "num_tokens": 21504000000.0, |
| "step": 1140000 |
| }, |
| { |
| "epoch": 0.5539002215600887, |
| "grad_norm": 2.1371679306030273, |
| "learning_rate": 0.00013518193486027327, |
| "loss": 3.2135, |
| "mean_token_accuracy": 0.421437505723536, |
| "num_tokens": 22220800000.0, |
| "step": 1160000 |
| }, |
| { |
| "epoch": 0.5634502253800902, |
| "grad_norm": 1.9272387027740479, |
| "learning_rate": 0.00013228799347126823, |
| "loss": 3.2129, |
| "mean_token_accuracy": 0.42148565844893454, |
| "num_tokens": 22937600000.0, |
| "step": 1180000 |
| }, |
| { |
| "epoch": 0.5730002292000916, |
| "grad_norm": 1.975583553314209, |
| "learning_rate": 0.00012939405208226316, |
| "loss": 3.2101, |
| "mean_token_accuracy": 0.42179442739486694, |
| "num_tokens": 23654400000.0, |
| "step": 1200000 |
| }, |
| { |
| "epoch": 0.5825502330200932, |
| "grad_norm": 1.8845446109771729, |
| "learning_rate": 0.00012650011069325812, |
| "loss": 3.209, |
| "mean_token_accuracy": 0.42191650020480154, |
| "num_tokens": 24371200000.0, |
| "step": 1220000 |
| }, |
| { |
| "epoch": 0.5921002368400947, |
| "grad_norm": 1.8266512155532837, |
| "learning_rate": 0.00012360616930425308, |
| "loss": 3.2075, |
| "mean_token_accuracy": 0.4220881850525737, |
| "num_tokens": 25088000000.0, |
| "step": 1240000 |
| }, |
| { |
| "epoch": 0.6016502406600963, |
| "grad_norm": 1.9238523244857788, |
| "learning_rate": 0.00012071222791524803, |
| "loss": 3.2051, |
| "mean_token_accuracy": 0.42236345537304876, |
| "num_tokens": 25804800000.0, |
| "step": 1260000 |
| }, |
| { |
| "epoch": 0.6112002444800978, |
| "grad_norm": 1.8870298862457275, |
| "learning_rate": 0.00011781828652624297, |
| "loss": 3.2044, |
| "mean_token_accuracy": 0.4224274314776063, |
| "num_tokens": 26521600000.0, |
| "step": 1280000 |
| }, |
| { |
| "epoch": 0.6207502483000993, |
| "grad_norm": 2.10017991065979, |
| "learning_rate": 0.00011492434513723792, |
| "loss": 3.2038, |
| "mean_token_accuracy": 0.4225288334354758, |
| "num_tokens": 27238400000.0, |
| "step": 1300000 |
| }, |
| { |
| "epoch": 0.6303002521201009, |
| "grad_norm": 2.2103898525238037, |
| "learning_rate": 0.00011203040374823287, |
| "loss": 3.2006, |
| "mean_token_accuracy": 0.42296220604628326, |
| "num_tokens": 27955200000.0, |
| "step": 1320000 |
| }, |
| { |
| "epoch": 0.6398502559401024, |
| "grad_norm": 2.1420845985412598, |
| "learning_rate": 0.00010913646235922783, |
| "loss": 3.1995, |
| "mean_token_accuracy": 0.42305554908663034, |
| "num_tokens": 28672000000.0, |
| "step": 1340000 |
| }, |
| { |
| "epoch": 0.649400259760104, |
| "grad_norm": 2.468029737472534, |
| "learning_rate": 0.00010624252097022279, |
| "loss": 3.1994, |
| "mean_token_accuracy": 0.4230162718191743, |
| "num_tokens": 29388800000.0, |
| "step": 1360000 |
| }, |
| { |
| "epoch": 0.6589502635801054, |
| "grad_norm": 2.0718960762023926, |
| "learning_rate": 0.00010334857958121774, |
| "loss": 3.1964, |
| "mean_token_accuracy": 0.4234230771496892, |
| "num_tokens": 30105600000.0, |
| "step": 1380000 |
| }, |
| { |
| "epoch": 0.6685002674001069, |
| "grad_norm": 2.7991926670074463, |
| "learning_rate": 0.00010045463819221268, |
| "loss": 3.1943, |
| "mean_token_accuracy": 0.4237000042423606, |
| "num_tokens": 30822400000.0, |
| "step": 1400000 |
| }, |
| { |
| "epoch": 0.6780502712201085, |
| "grad_norm": 2.4362847805023193, |
| "learning_rate": 9.756069680320764e-05, |
| "loss": 3.1922, |
| "mean_token_accuracy": 0.4239600421443582, |
| "num_tokens": 31539200000.0, |
| "step": 1420000 |
| }, |
| { |
| "epoch": 0.68760027504011, |
| "grad_norm": 2.591127872467041, |
| "learning_rate": 9.466675541420259e-05, |
| "loss": 3.191, |
| "mean_token_accuracy": 0.4240850882053375, |
| "num_tokens": 32256000000.0, |
| "step": 1440000 |
| }, |
| { |
| "epoch": 0.6971502788601115, |
| "grad_norm": 2.234511375427246, |
| "learning_rate": 9.177281402519754e-05, |
| "loss": 3.1897, |
| "mean_token_accuracy": 0.4242406051442027, |
| "num_tokens": 32972800000.0, |
| "step": 1460000 |
| }, |
| { |
| "epoch": 0.7067002826801131, |
| "grad_norm": 2.165247917175293, |
| "learning_rate": 8.887887263619248e-05, |
| "loss": 3.1876, |
| "mean_token_accuracy": 0.42447070305049417, |
| "num_tokens": 33689600000.0, |
| "step": 1480000 |
| }, |
| { |
| "epoch": 0.7162502865001146, |
| "grad_norm": 2.373894453048706, |
| "learning_rate": 8.598493124718745e-05, |
| "loss": 3.1858, |
| "mean_token_accuracy": 0.4246869832932949, |
| "num_tokens": 34406400000.0, |
| "step": 1500000 |
| }, |
| { |
| "epoch": 0.7258002903201162, |
| "grad_norm": 2.232844352722168, |
| "learning_rate": 8.309098985818239e-05, |
| "loss": 3.1842, |
| "mean_token_accuracy": 0.424876312276721, |
| "num_tokens": 35123200000.0, |
| "step": 1520000 |
| }, |
| { |
| "epoch": 0.7353502941401177, |
| "grad_norm": 2.4994523525238037, |
| "learning_rate": 8.019704846917734e-05, |
| "loss": 3.1827, |
| "mean_token_accuracy": 0.42511233622431754, |
| "num_tokens": 35840000000.0, |
| "step": 1540000 |
| }, |
| { |
| "epoch": 0.7449002979601191, |
| "grad_norm": 2.4633235931396484, |
| "learning_rate": 7.73031070801723e-05, |
| "loss": 3.1798, |
| "mean_token_accuracy": 0.4254420336738229, |
| "num_tokens": 36556800000.0, |
| "step": 1560000 |
| }, |
| { |
| "epoch": 0.7544503017801207, |
| "grad_norm": 2.386373281478882, |
| "learning_rate": 7.440916569116725e-05, |
| "loss": 3.1786, |
| "mean_token_accuracy": 0.4255216441363096, |
| "num_tokens": 37273600000.0, |
| "step": 1580000 |
| }, |
| { |
| "epoch": 0.7640003056001222, |
| "grad_norm": 2.4472737312316895, |
| "learning_rate": 7.151522430216221e-05, |
| "loss": 3.1767, |
| "mean_token_accuracy": 0.4258053430899978, |
| "num_tokens": 37990400000.0, |
| "step": 1600000 |
| }, |
| { |
| "epoch": 0.7735503094201238, |
| "grad_norm": 2.5622825622558594, |
| "learning_rate": 6.862128291315715e-05, |
| "loss": 3.1746, |
| "mean_token_accuracy": 0.4260344804123044, |
| "num_tokens": 38707200000.0, |
| "step": 1620000 |
| }, |
| { |
| "epoch": 0.7831003132401253, |
| "grad_norm": 2.4821906089782715, |
| "learning_rate": 6.57273415241521e-05, |
| "loss": 3.1723, |
| "mean_token_accuracy": 0.4263139396473765, |
| "num_tokens": 39424000000.0, |
| "step": 1640000 |
| }, |
| { |
| "epoch": 0.7926503170601268, |
| "grad_norm": 2.5140678882598877, |
| "learning_rate": 6.283340013514706e-05, |
| "loss": 3.1701, |
| "mean_token_accuracy": 0.42658785569369795, |
| "num_tokens": 40140800000.0, |
| "step": 1660000 |
| }, |
| { |
| "epoch": 0.8022003208801284, |
| "grad_norm": 2.634791851043701, |
| "learning_rate": 5.9939458746142e-05, |
| "loss": 3.1678, |
| "mean_token_accuracy": 0.42689967503100634, |
| "num_tokens": 40857600000.0, |
| "step": 1680000 |
| }, |
| { |
| "epoch": 0.8117503247001299, |
| "grad_norm": 3.0459752082824707, |
| "learning_rate": 5.704551735713696e-05, |
| "loss": 3.1672, |
| "mean_token_accuracy": 0.42699285422861577, |
| "num_tokens": 41574400000.0, |
| "step": 1700000 |
| }, |
| { |
| "epoch": 0.8213003285201315, |
| "grad_norm": 2.686730146408081, |
| "learning_rate": 5.4151575968131916e-05, |
| "loss": 3.1642, |
| "mean_token_accuracy": 0.42733070581257343, |
| "num_tokens": 42291200000.0, |
| "step": 1720000 |
| }, |
| { |
| "epoch": 0.830850332340133, |
| "grad_norm": 2.967567205429077, |
| "learning_rate": 5.125763457912686e-05, |
| "loss": 3.1618, |
| "mean_token_accuracy": 0.42769208399355413, |
| "num_tokens": 43008000000.0, |
| "step": 1740000 |
| }, |
| { |
| "epoch": 0.8404003361601344, |
| "grad_norm": 2.7259535789489746, |
| "learning_rate": 4.836369319012181e-05, |
| "loss": 3.1596, |
| "mean_token_accuracy": 0.42790325200855733, |
| "num_tokens": 43724800000.0, |
| "step": 1760000 |
| }, |
| { |
| "epoch": 0.849950339980136, |
| "grad_norm": 2.709784746170044, |
| "learning_rate": 4.546975180111677e-05, |
| "loss": 3.1567, |
| "mean_token_accuracy": 0.42829815539866684, |
| "num_tokens": 44441600000.0, |
| "step": 1780000 |
| }, |
| { |
| "epoch": 0.8595003438001375, |
| "grad_norm": 3.054241418838501, |
| "learning_rate": 4.2575810412111724e-05, |
| "loss": 3.1551, |
| "mean_token_accuracy": 0.42849865667670967, |
| "num_tokens": 45158400000.0, |
| "step": 1800000 |
| }, |
| { |
| "epoch": 0.869050347620139, |
| "grad_norm": 2.976240873336792, |
| "learning_rate": 3.968186902310667e-05, |
| "loss": 3.1519, |
| "mean_token_accuracy": 0.42887963571995497, |
| "num_tokens": 45875200000.0, |
| "step": 1820000 |
| }, |
| { |
| "epoch": 0.8786003514401406, |
| "grad_norm": 2.723175525665283, |
| "learning_rate": 3.678792763410162e-05, |
| "loss": 3.1498, |
| "mean_token_accuracy": 0.42917205161750316, |
| "num_tokens": 46592000000.0, |
| "step": 1840000 |
| }, |
| { |
| "epoch": 0.8881503552601421, |
| "grad_norm": 2.917259693145752, |
| "learning_rate": 3.389398624509658e-05, |
| "loss": 3.146, |
| "mean_token_accuracy": 0.42966016797572376, |
| "num_tokens": 47308800000.0, |
| "step": 1860000 |
| }, |
| { |
| "epoch": 0.8977003590801437, |
| "grad_norm": 3.254523515701294, |
| "learning_rate": 3.1000044856091526e-05, |
| "loss": 3.1442, |
| "mean_token_accuracy": 0.42988122535943984, |
| "num_tokens": 48025600000.0, |
| "step": 1880000 |
| }, |
| { |
| "epoch": 0.9072503629001452, |
| "grad_norm": 2.9410157203674316, |
| "learning_rate": 2.810610346708648e-05, |
| "loss": 3.1408, |
| "mean_token_accuracy": 0.43033207250982525, |
| "num_tokens": 48742400000.0, |
| "step": 1900000 |
| }, |
| { |
| "epoch": 0.9168003667201466, |
| "grad_norm": 3.0534310340881348, |
| "learning_rate": 2.521216207808143e-05, |
| "loss": 3.1383, |
| "mean_token_accuracy": 0.43062722102552653, |
| "num_tokens": 49459200000.0, |
| "step": 1920000 |
| }, |
| { |
| "epoch": 0.9263503705401482, |
| "grad_norm": 3.0121352672576904, |
| "learning_rate": 2.2318220689076384e-05, |
| "loss": 3.1352, |
| "mean_token_accuracy": 0.43105802639722823, |
| "num_tokens": 50176000000.0, |
| "step": 1940000 |
| }, |
| { |
| "epoch": 0.9359003743601497, |
| "grad_norm": 3.4966187477111816, |
| "learning_rate": 1.9424279300071334e-05, |
| "loss": 3.1317, |
| "mean_token_accuracy": 0.43149784843176603, |
| "num_tokens": 50892800000.0, |
| "step": 1960000 |
| }, |
| { |
| "epoch": 0.9454503781801513, |
| "grad_norm": 3.3833205699920654, |
| "learning_rate": 1.6530337911066284e-05, |
| "loss": 3.1285, |
| "mean_token_accuracy": 0.4319396187588572, |
| "num_tokens": 51609600000.0, |
| "step": 1980000 |
| }, |
| { |
| "epoch": 0.9550003820001528, |
| "grad_norm": 3.30391001701355, |
| "learning_rate": 1.3636396522061238e-05, |
| "loss": 3.1248, |
| "mean_token_accuracy": 0.43242690176963805, |
| "num_tokens": 52326400000.0, |
| "step": 2000000 |
| }, |
| { |
| "epoch": 0.9645503858201543, |
| "grad_norm": 3.326011896133423, |
| "learning_rate": 1.074245513305619e-05, |
| "loss": 3.1213, |
| "mean_token_accuracy": 0.4328598498493433, |
| "num_tokens": 53043200000.0, |
| "step": 2020000 |
| }, |
| { |
| "epoch": 0.9741003896401559, |
| "grad_norm": 3.2196035385131836, |
| "learning_rate": 7.84851374405114e-06, |
| "loss": 3.1176, |
| "mean_token_accuracy": 0.4334187435388565, |
| "num_tokens": 53760000000.0, |
| "step": 2040000 |
| }, |
| { |
| "epoch": 0.9836503934601574, |
| "grad_norm": 3.748178720474243, |
| "learning_rate": 4.9545723550460936e-06, |
| "loss": 3.1139, |
| "mean_token_accuracy": 0.43390719720572235, |
| "num_tokens": 54476800000.0, |
| "step": 2060000 |
| }, |
| { |
| "epoch": 0.993200397280159, |
| "grad_norm": 3.283731460571289, |
| "learning_rate": 2.0606309660410444e-06, |
| "loss": 3.1103, |
| "mean_token_accuracy": 0.4344122279688716, |
| "num_tokens": 55193600000.0, |
| "step": 2080000 |
| } |
| ], |
| "logging_steps": 20000, |
| "max_steps": 2094240, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 20000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1815907720024556e+18, |
| "train_batch_size": 140, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
