| { |
| "best_global_step": null, |
| "best_metric": 0.4038073718547821, |
| "best_model_checkpoint": null, |
| "epoch": 3.899815440331511, |
| "eval_steps": 500, |
| "global_step": 14000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0002785806316815823, |
| "grad_norm": 0.4645193815231323, |
| "learning_rate": 0.0, |
| "loss": 2.3986, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.027858063168158233, |
| "grad_norm": 0.3897116482257843, |
| "learning_rate": 1.9800000000000004e-05, |
| "loss": 2.4541, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.055716126336316465, |
| "grad_norm": 0.9093355536460876, |
| "learning_rate": 3.9800000000000005e-05, |
| "loss": 1.4843, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.0835741895044747, |
| "grad_norm": 1.0977619886398315, |
| "learning_rate": 4.9826364280652023e-05, |
| "loss": 0.9759, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.11143225267263293, |
| "grad_norm": 1.0786027908325195, |
| "learning_rate": 4.9472005669737774e-05, |
| "loss": 0.8439, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.13929031584079116, |
| "grad_norm": 1.2702925205230713, |
| "learning_rate": 4.911764705882353e-05, |
| "loss": 0.7883, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.13929031584079116, |
| "eval_loss": 0.65428227186203, |
| "eval_runtime": 591.887, |
| "eval_samples_per_second": 48.518, |
| "eval_steps_per_second": 3.033, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.1671483790089494, |
| "grad_norm": 1.3737353086471558, |
| "learning_rate": 4.876328844790929e-05, |
| "loss": 0.746, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.19500644217710764, |
| "grad_norm": 1.3053338527679443, |
| "learning_rate": 4.840892983699504e-05, |
| "loss": 0.7122, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.22286450534526586, |
| "grad_norm": 1.814271092414856, |
| "learning_rate": 4.80545712260808e-05, |
| "loss": 0.6914, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.2507225685134241, |
| "grad_norm": 1.3019365072250366, |
| "learning_rate": 4.770021261516655e-05, |
| "loss": 0.6831, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.2785806316815823, |
| "grad_norm": 1.2910503149032593, |
| "learning_rate": 4.7345854004252306e-05, |
| "loss": 0.6714, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2785806316815823, |
| "eval_loss": 0.5705545544624329, |
| "eval_runtime": 592.3805, |
| "eval_samples_per_second": 48.477, |
| "eval_steps_per_second": 3.03, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.30643869484974057, |
| "grad_norm": 1.4649542570114136, |
| "learning_rate": 4.699149539333806e-05, |
| "loss": 0.6487, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.3342967580178988, |
| "grad_norm": 1.7467780113220215, |
| "learning_rate": 4.6637136782423815e-05, |
| "loss": 0.6456, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.362154821186057, |
| "grad_norm": 1.33451247215271, |
| "learning_rate": 4.628277817150957e-05, |
| "loss": 0.637, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.3900128843542153, |
| "grad_norm": 1.7314374446868896, |
| "learning_rate": 4.592841956059532e-05, |
| "loss": 0.6295, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.4178709475223735, |
| "grad_norm": 1.344909906387329, |
| "learning_rate": 4.557406094968108e-05, |
| "loss": 0.621, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.4178709475223735, |
| "eval_loss": 0.5306675434112549, |
| "eval_runtime": 592.5408, |
| "eval_samples_per_second": 48.464, |
| "eval_steps_per_second": 3.029, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.4457290106905317, |
| "grad_norm": 1.3075149059295654, |
| "learning_rate": 4.521970233876683e-05, |
| "loss": 0.6229, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.47358707385869, |
| "grad_norm": 1.4076815843582153, |
| "learning_rate": 4.486534372785259e-05, |
| "loss": 0.6109, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.5014451370268482, |
| "grad_norm": 1.3399609327316284, |
| "learning_rate": 4.451098511693834e-05, |
| "loss": 0.6024, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.5293032001950064, |
| "grad_norm": 1.3271087408065796, |
| "learning_rate": 4.41566265060241e-05, |
| "loss": 0.5997, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.5571612633631646, |
| "grad_norm": 1.412111520767212, |
| "learning_rate": 4.3802267895109855e-05, |
| "loss": 0.5839, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5571612633631646, |
| "eval_loss": 0.5096445679664612, |
| "eval_runtime": 594.5376, |
| "eval_samples_per_second": 48.301, |
| "eval_steps_per_second": 3.019, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.5850193265313229, |
| "grad_norm": 1.2040321826934814, |
| "learning_rate": 4.3447909284195606e-05, |
| "loss": 0.5789, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.6128773896994811, |
| "grad_norm": 1.2207297086715698, |
| "learning_rate": 4.3093550673281363e-05, |
| "loss": 0.5761, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.6407354528676393, |
| "grad_norm": 1.205450177192688, |
| "learning_rate": 4.2739192062367114e-05, |
| "loss": 0.5709, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.6685935160357976, |
| "grad_norm": 1.3946952819824219, |
| "learning_rate": 4.238483345145287e-05, |
| "loss": 0.5696, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.6964515792039558, |
| "grad_norm": 1.1846948862075806, |
| "learning_rate": 4.203047484053862e-05, |
| "loss": 0.5552, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.6964515792039558, |
| "eval_loss": 0.4957100749015808, |
| "eval_runtime": 593.2402, |
| "eval_samples_per_second": 48.407, |
| "eval_steps_per_second": 3.026, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.724309642372114, |
| "grad_norm": 1.2646228075027466, |
| "learning_rate": 4.167611622962439e-05, |
| "loss": 0.5573, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.7521677055402723, |
| "grad_norm": 1.2027941942214966, |
| "learning_rate": 4.132175761871014e-05, |
| "loss": 0.5568, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.7800257687084305, |
| "grad_norm": 1.2179590463638306, |
| "learning_rate": 4.0967399007795895e-05, |
| "loss": 0.5579, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.8078838318765887, |
| "grad_norm": 1.2543010711669922, |
| "learning_rate": 4.0613040396881646e-05, |
| "loss": 0.5632, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.835741895044747, |
| "grad_norm": 1.2597264051437378, |
| "learning_rate": 4.02586817859674e-05, |
| "loss": 0.545, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.835741895044747, |
| "eval_loss": 0.4792587161064148, |
| "eval_runtime": 592.7585, |
| "eval_samples_per_second": 48.446, |
| "eval_steps_per_second": 3.028, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.8635999582129052, |
| "grad_norm": 1.3292843103408813, |
| "learning_rate": 3.9904323175053155e-05, |
| "loss": 0.5571, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.8914580213810634, |
| "grad_norm": 1.3142098188400269, |
| "learning_rate": 3.9549964564138906e-05, |
| "loss": 0.5397, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.9193160845492218, |
| "grad_norm": 1.389565348625183, |
| "learning_rate": 3.919560595322467e-05, |
| "loss": 0.5478, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.94717414771738, |
| "grad_norm": 1.1616095304489136, |
| "learning_rate": 3.884124734231042e-05, |
| "loss": 0.5396, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.9750322108855382, |
| "grad_norm": 1.24950110912323, |
| "learning_rate": 3.848688873139618e-05, |
| "loss": 0.5337, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.9750322108855382, |
| "eval_loss": 0.4686237871646881, |
| "eval_runtime": 593.0319, |
| "eval_samples_per_second": 48.424, |
| "eval_steps_per_second": 3.027, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.0027858063168158, |
| "grad_norm": 1.3192429542541504, |
| "learning_rate": 3.813253012048193e-05, |
| "loss": 0.5301, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.030643869484974, |
| "grad_norm": 1.465832233428955, |
| "learning_rate": 3.777817150956769e-05, |
| "loss": 0.5272, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.0585019326531322, |
| "grad_norm": 1.4403393268585205, |
| "learning_rate": 3.742381289865344e-05, |
| "loss": 0.5236, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.0863599958212906, |
| "grad_norm": 1.3801666498184204, |
| "learning_rate": 3.706945428773919e-05, |
| "loss": 0.5242, |
| "step": 3900 |
| }, |
| { |
| "epoch": 1.1142180589894488, |
| "grad_norm": 1.076539397239685, |
| "learning_rate": 3.671509567682495e-05, |
| "loss": 0.5224, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.1142180589894488, |
| "eval_loss": 0.46663618087768555, |
| "eval_runtime": 592.8183, |
| "eval_samples_per_second": 48.441, |
| "eval_steps_per_second": 3.028, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.142076122157607, |
| "grad_norm": 1.3829838037490845, |
| "learning_rate": 3.6360737065910704e-05, |
| "loss": 0.5217, |
| "step": 4100 |
| }, |
| { |
| "epoch": 1.1699341853257652, |
| "grad_norm": 1.098763108253479, |
| "learning_rate": 3.600637845499646e-05, |
| "loss": 0.5169, |
| "step": 4200 |
| }, |
| { |
| "epoch": 1.1977922484939234, |
| "grad_norm": 1.260761022567749, |
| "learning_rate": 3.565201984408221e-05, |
| "loss": 0.5116, |
| "step": 4300 |
| }, |
| { |
| "epoch": 1.2256503116620816, |
| "grad_norm": 1.3205015659332275, |
| "learning_rate": 3.529766123316797e-05, |
| "loss": 0.518, |
| "step": 4400 |
| }, |
| { |
| "epoch": 1.2535083748302398, |
| "grad_norm": 1.3871066570281982, |
| "learning_rate": 3.494330262225372e-05, |
| "loss": 0.5181, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.2535083748302398, |
| "eval_loss": 0.45501282811164856, |
| "eval_runtime": 592.8496, |
| "eval_samples_per_second": 48.439, |
| "eval_steps_per_second": 3.028, |
| "step": 4500 |
| }, |
| { |
| "epoch": 1.2813664379983982, |
| "grad_norm": 1.1054390668869019, |
| "learning_rate": 3.458894401133948e-05, |
| "loss": 0.5148, |
| "step": 4600 |
| }, |
| { |
| "epoch": 1.3092245011665564, |
| "grad_norm": 1.0034719705581665, |
| "learning_rate": 3.4234585400425235e-05, |
| "loss": 0.5109, |
| "step": 4700 |
| }, |
| { |
| "epoch": 1.3370825643347146, |
| "grad_norm": 1.417938232421875, |
| "learning_rate": 3.3880226789510986e-05, |
| "loss": 0.5104, |
| "step": 4800 |
| }, |
| { |
| "epoch": 1.3649406275028728, |
| "grad_norm": 1.243116855621338, |
| "learning_rate": 3.3525868178596744e-05, |
| "loss": 0.4988, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.392798690671031, |
| "grad_norm": 1.1632623672485352, |
| "learning_rate": 3.3171509567682495e-05, |
| "loss": 0.5072, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.392798690671031, |
| "eval_loss": 0.45067891478538513, |
| "eval_runtime": 593.6193, |
| "eval_samples_per_second": 48.376, |
| "eval_steps_per_second": 3.024, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.4206567538391894, |
| "grad_norm": 1.3165979385375977, |
| "learning_rate": 3.281715095676825e-05, |
| "loss": 0.4934, |
| "step": 5100 |
| }, |
| { |
| "epoch": 1.4485148170073476, |
| "grad_norm": 1.3166348934173584, |
| "learning_rate": 3.2462792345854e-05, |
| "loss": 0.51, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.4763728801755058, |
| "grad_norm": 1.737769365310669, |
| "learning_rate": 3.210843373493976e-05, |
| "loss": 0.5079, |
| "step": 5300 |
| }, |
| { |
| "epoch": 1.504230943343664, |
| "grad_norm": 1.0135122537612915, |
| "learning_rate": 3.175407512402552e-05, |
| "loss": 0.4915, |
| "step": 5400 |
| }, |
| { |
| "epoch": 1.5320890065118222, |
| "grad_norm": 1.161383032798767, |
| "learning_rate": 3.139971651311127e-05, |
| "loss": 0.4972, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.5320890065118222, |
| "eval_loss": 0.4426087737083435, |
| "eval_runtime": 592.4939, |
| "eval_samples_per_second": 48.468, |
| "eval_steps_per_second": 3.03, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.5599470696799806, |
| "grad_norm": 1.2716448307037354, |
| "learning_rate": 3.104535790219703e-05, |
| "loss": 0.4904, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.5878051328481386, |
| "grad_norm": 1.2625107765197754, |
| "learning_rate": 3.069099929128278e-05, |
| "loss": 0.4943, |
| "step": 5700 |
| }, |
| { |
| "epoch": 1.615663196016297, |
| "grad_norm": 1.2053842544555664, |
| "learning_rate": 3.0336640680368532e-05, |
| "loss": 0.5028, |
| "step": 5800 |
| }, |
| { |
| "epoch": 1.6435212591844552, |
| "grad_norm": 1.1495795249938965, |
| "learning_rate": 2.9982282069454286e-05, |
| "loss": 0.4929, |
| "step": 5900 |
| }, |
| { |
| "epoch": 1.6713793223526134, |
| "grad_norm": 1.1481202840805054, |
| "learning_rate": 2.9627923458540047e-05, |
| "loss": 0.4926, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.6713793223526134, |
| "eval_loss": 0.444801926612854, |
| "eval_runtime": 592.9633, |
| "eval_samples_per_second": 48.43, |
| "eval_steps_per_second": 3.027, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.6992373855207716, |
| "grad_norm": 1.3731409311294556, |
| "learning_rate": 2.92735648476258e-05, |
| "loss": 0.5006, |
| "step": 6100 |
| }, |
| { |
| "epoch": 1.7270954486889298, |
| "grad_norm": 1.0181461572647095, |
| "learning_rate": 2.8919206236711555e-05, |
| "loss": 0.4855, |
| "step": 6200 |
| }, |
| { |
| "epoch": 1.7549535118570883, |
| "grad_norm": 1.5491364002227783, |
| "learning_rate": 2.856484762579731e-05, |
| "loss": 0.4994, |
| "step": 6300 |
| }, |
| { |
| "epoch": 1.7828115750252462, |
| "grad_norm": 1.149021029472351, |
| "learning_rate": 2.8210489014883064e-05, |
| "loss": 0.4918, |
| "step": 6400 |
| }, |
| { |
| "epoch": 1.8106696381934047, |
| "grad_norm": 1.0654308795928955, |
| "learning_rate": 2.7856130403968818e-05, |
| "loss": 0.487, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.8106696381934047, |
| "eval_loss": 0.4356010854244232, |
| "eval_runtime": 593.5091, |
| "eval_samples_per_second": 48.385, |
| "eval_steps_per_second": 3.024, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.8385277013615628, |
| "grad_norm": 1.2700181007385254, |
| "learning_rate": 2.750177179305457e-05, |
| "loss": 0.4869, |
| "step": 6600 |
| }, |
| { |
| "epoch": 1.866385764529721, |
| "grad_norm": 1.0347015857696533, |
| "learning_rate": 2.714741318214033e-05, |
| "loss": 0.4861, |
| "step": 6700 |
| }, |
| { |
| "epoch": 1.8942438276978795, |
| "grad_norm": 1.08585786819458, |
| "learning_rate": 2.6793054571226084e-05, |
| "loss": 0.4884, |
| "step": 6800 |
| }, |
| { |
| "epoch": 1.9221018908660374, |
| "grad_norm": 1.2477092742919922, |
| "learning_rate": 2.6438695960311838e-05, |
| "loss": 0.478, |
| "step": 6900 |
| }, |
| { |
| "epoch": 1.9499599540341959, |
| "grad_norm": 1.1088532209396362, |
| "learning_rate": 2.6084337349397592e-05, |
| "loss": 0.4919, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.9499599540341959, |
| "eval_loss": 0.43220457434654236, |
| "eval_runtime": 593.2416, |
| "eval_samples_per_second": 48.407, |
| "eval_steps_per_second": 3.026, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.977818017202354, |
| "grad_norm": 1.0134484767913818, |
| "learning_rate": 2.5729978738483347e-05, |
| "loss": 0.4861, |
| "step": 7100 |
| }, |
| { |
| "epoch": 2.0055716126336316, |
| "grad_norm": 1.185179591178894, |
| "learning_rate": 2.53756201275691e-05, |
| "loss": 0.4805, |
| "step": 7200 |
| }, |
| { |
| "epoch": 2.03342967580179, |
| "grad_norm": 1.2651209831237793, |
| "learning_rate": 2.5021261516654855e-05, |
| "loss": 0.4785, |
| "step": 7300 |
| }, |
| { |
| "epoch": 2.061287738969948, |
| "grad_norm": 1.0275731086730957, |
| "learning_rate": 2.466690290574061e-05, |
| "loss": 0.4767, |
| "step": 7400 |
| }, |
| { |
| "epoch": 2.0891458021381064, |
| "grad_norm": 1.0938606262207031, |
| "learning_rate": 2.4312544294826363e-05, |
| "loss": 0.4682, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.0891458021381064, |
| "eval_loss": 0.4292644262313843, |
| "eval_runtime": 592.5766, |
| "eval_samples_per_second": 48.461, |
| "eval_steps_per_second": 3.029, |
| "step": 7500 |
| }, |
| { |
| "epoch": 2.1170038653062644, |
| "grad_norm": 1.1097854375839233, |
| "learning_rate": 2.395818568391212e-05, |
| "loss": 0.4703, |
| "step": 7600 |
| }, |
| { |
| "epoch": 2.144861928474423, |
| "grad_norm": 1.3471382856369019, |
| "learning_rate": 2.3603827072997875e-05, |
| "loss": 0.4843, |
| "step": 7700 |
| }, |
| { |
| "epoch": 2.1727199916425812, |
| "grad_norm": 1.351805329322815, |
| "learning_rate": 2.324946846208363e-05, |
| "loss": 0.4776, |
| "step": 7800 |
| }, |
| { |
| "epoch": 2.200578054810739, |
| "grad_norm": 1.1416364908218384, |
| "learning_rate": 2.2895109851169387e-05, |
| "loss": 0.4714, |
| "step": 7900 |
| }, |
| { |
| "epoch": 2.2284361179788976, |
| "grad_norm": 1.1691741943359375, |
| "learning_rate": 2.254075124025514e-05, |
| "loss": 0.4734, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.2284361179788976, |
| "eval_loss": 0.4240116477012634, |
| "eval_runtime": 594.3246, |
| "eval_samples_per_second": 48.319, |
| "eval_steps_per_second": 3.02, |
| "step": 8000 |
| }, |
| { |
| "epoch": 2.2562941811470556, |
| "grad_norm": 1.0872358083724976, |
| "learning_rate": 2.2186392629340892e-05, |
| "loss": 0.4711, |
| "step": 8100 |
| }, |
| { |
| "epoch": 2.284152244315214, |
| "grad_norm": 1.166755199432373, |
| "learning_rate": 2.1832034018426646e-05, |
| "loss": 0.4674, |
| "step": 8200 |
| }, |
| { |
| "epoch": 2.312010307483372, |
| "grad_norm": 1.397355556488037, |
| "learning_rate": 2.1477675407512404e-05, |
| "loss": 0.4741, |
| "step": 8300 |
| }, |
| { |
| "epoch": 2.3398683706515304, |
| "grad_norm": 1.0663005113601685, |
| "learning_rate": 2.1123316796598158e-05, |
| "loss": 0.4741, |
| "step": 8400 |
| }, |
| { |
| "epoch": 2.367726433819689, |
| "grad_norm": 1.2197699546813965, |
| "learning_rate": 2.0768958185683912e-05, |
| "loss": 0.4691, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.367726433819689, |
| "eval_loss": 0.4226415753364563, |
| "eval_runtime": 592.9032, |
| "eval_samples_per_second": 48.435, |
| "eval_steps_per_second": 3.027, |
| "step": 8500 |
| }, |
| { |
| "epoch": 2.395584496987847, |
| "grad_norm": 1.4034844636917114, |
| "learning_rate": 2.041459957476967e-05, |
| "loss": 0.4749, |
| "step": 8600 |
| }, |
| { |
| "epoch": 2.4234425601560052, |
| "grad_norm": 1.2953102588653564, |
| "learning_rate": 2.0060240963855424e-05, |
| "loss": 0.4757, |
| "step": 8700 |
| }, |
| { |
| "epoch": 2.451300623324163, |
| "grad_norm": 1.3071800470352173, |
| "learning_rate": 1.9705882352941178e-05, |
| "loss": 0.4668, |
| "step": 8800 |
| }, |
| { |
| "epoch": 2.4791586864923216, |
| "grad_norm": 1.1789804697036743, |
| "learning_rate": 1.9351523742026932e-05, |
| "loss": 0.4729, |
| "step": 8900 |
| }, |
| { |
| "epoch": 2.5070167496604796, |
| "grad_norm": 1.2676748037338257, |
| "learning_rate": 1.8997165131112687e-05, |
| "loss": 0.4679, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.5070167496604796, |
| "eval_loss": 0.4187828004360199, |
| "eval_runtime": 592.1014, |
| "eval_samples_per_second": 48.5, |
| "eval_steps_per_second": 3.032, |
| "step": 9000 |
| }, |
| { |
| "epoch": 2.534874812828638, |
| "grad_norm": 1.3900854587554932, |
| "learning_rate": 1.864280652019844e-05, |
| "loss": 0.4677, |
| "step": 9100 |
| }, |
| { |
| "epoch": 2.5627328759967964, |
| "grad_norm": 1.2864222526550293, |
| "learning_rate": 1.8288447909284195e-05, |
| "loss": 0.4584, |
| "step": 9200 |
| }, |
| { |
| "epoch": 2.5905909391649544, |
| "grad_norm": 1.0441097021102905, |
| "learning_rate": 1.7934089298369953e-05, |
| "loss": 0.4654, |
| "step": 9300 |
| }, |
| { |
| "epoch": 2.618449002333113, |
| "grad_norm": 1.1249713897705078, |
| "learning_rate": 1.7579730687455707e-05, |
| "loss": 0.4674, |
| "step": 9400 |
| }, |
| { |
| "epoch": 2.6463070655012713, |
| "grad_norm": 1.2885221242904663, |
| "learning_rate": 1.722537207654146e-05, |
| "loss": 0.4694, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.6463070655012713, |
| "eval_loss": 0.4162205457687378, |
| "eval_runtime": 593.1028, |
| "eval_samples_per_second": 48.418, |
| "eval_steps_per_second": 3.026, |
| "step": 9500 |
| }, |
| { |
| "epoch": 2.6741651286694292, |
| "grad_norm": 1.1028586626052856, |
| "learning_rate": 1.6871013465627215e-05, |
| "loss": 0.4573, |
| "step": 9600 |
| }, |
| { |
| "epoch": 2.7020231918375877, |
| "grad_norm": 1.3248066902160645, |
| "learning_rate": 1.651665485471297e-05, |
| "loss": 0.4609, |
| "step": 9700 |
| }, |
| { |
| "epoch": 2.7298812550057456, |
| "grad_norm": 1.073268175125122, |
| "learning_rate": 1.6162296243798724e-05, |
| "loss": 0.4543, |
| "step": 9800 |
| }, |
| { |
| "epoch": 2.757739318173904, |
| "grad_norm": 1.0753856897354126, |
| "learning_rate": 1.5807937632884478e-05, |
| "loss": 0.4667, |
| "step": 9900 |
| }, |
| { |
| "epoch": 2.785597381342062, |
| "grad_norm": 1.2315281629562378, |
| "learning_rate": 1.5453579021970235e-05, |
| "loss": 0.4573, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.785597381342062, |
| "eval_loss": 0.41505932807922363, |
| "eval_runtime": 592.7426, |
| "eval_samples_per_second": 48.448, |
| "eval_steps_per_second": 3.028, |
| "step": 10000 |
| }, |
| { |
| "epoch": 2.8134554445102204, |
| "grad_norm": 1.1854623556137085, |
| "learning_rate": 1.509922041105599e-05, |
| "loss": 0.4579, |
| "step": 10100 |
| }, |
| { |
| "epoch": 2.841313507678379, |
| "grad_norm": 1.1797943115234375, |
| "learning_rate": 1.4744861800141744e-05, |
| "loss": 0.4512, |
| "step": 10200 |
| }, |
| { |
| "epoch": 2.869171570846537, |
| "grad_norm": 1.2852693796157837, |
| "learning_rate": 1.43905031892275e-05, |
| "loss": 0.4657, |
| "step": 10300 |
| }, |
| { |
| "epoch": 2.8970296340146953, |
| "grad_norm": 1.4903700351715088, |
| "learning_rate": 1.4036144578313254e-05, |
| "loss": 0.4565, |
| "step": 10400 |
| }, |
| { |
| "epoch": 2.9248876971828532, |
| "grad_norm": 1.1999119520187378, |
| "learning_rate": 1.3681785967399008e-05, |
| "loss": 0.4505, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.9248876971828532, |
| "eval_loss": 0.41494467854499817, |
| "eval_runtime": 594.0624, |
| "eval_samples_per_second": 48.34, |
| "eval_steps_per_second": 3.022, |
| "step": 10500 |
| }, |
| { |
| "epoch": 2.9527457603510117, |
| "grad_norm": 1.1072437763214111, |
| "learning_rate": 1.3327427356484764e-05, |
| "loss": 0.4636, |
| "step": 10600 |
| }, |
| { |
| "epoch": 2.9806038235191696, |
| "grad_norm": 1.0771669149398804, |
| "learning_rate": 1.2973068745570518e-05, |
| "loss": 0.4666, |
| "step": 10700 |
| }, |
| { |
| "epoch": 3.0083574189504474, |
| "grad_norm": 1.1003024578094482, |
| "learning_rate": 1.2618710134656272e-05, |
| "loss": 0.4456, |
| "step": 10800 |
| }, |
| { |
| "epoch": 3.036215482118606, |
| "grad_norm": 1.417353630065918, |
| "learning_rate": 1.2264351523742028e-05, |
| "loss": 0.4594, |
| "step": 10900 |
| }, |
| { |
| "epoch": 3.064073545286764, |
| "grad_norm": 1.1961385011672974, |
| "learning_rate": 1.1909992912827782e-05, |
| "loss": 0.4478, |
| "step": 11000 |
| }, |
| { |
| "epoch": 3.064073545286764, |
| "eval_loss": 0.4131682813167572, |
| "eval_runtime": 592.6765, |
| "eval_samples_per_second": 48.453, |
| "eval_steps_per_second": 3.029, |
| "step": 11000 |
| }, |
| { |
| "epoch": 3.091931608454922, |
| "grad_norm": 1.3566352128982544, |
| "learning_rate": 1.1555634301913537e-05, |
| "loss": 0.4416, |
| "step": 11100 |
| }, |
| { |
| "epoch": 3.1197896716230806, |
| "grad_norm": 1.3073431253433228, |
| "learning_rate": 1.1201275690999293e-05, |
| "loss": 0.4509, |
| "step": 11200 |
| }, |
| { |
| "epoch": 3.1476477347912386, |
| "grad_norm": 1.3190025091171265, |
| "learning_rate": 1.0846917080085047e-05, |
| "loss": 0.4513, |
| "step": 11300 |
| }, |
| { |
| "epoch": 3.175505797959397, |
| "grad_norm": 1.3781085014343262, |
| "learning_rate": 1.0492558469170801e-05, |
| "loss": 0.4437, |
| "step": 11400 |
| }, |
| { |
| "epoch": 3.203363861127555, |
| "grad_norm": 1.306618332862854, |
| "learning_rate": 1.0138199858256555e-05, |
| "loss": 0.4454, |
| "step": 11500 |
| }, |
| { |
| "epoch": 3.203363861127555, |
| "eval_loss": 0.4108191132545471, |
| "eval_runtime": 593.9192, |
| "eval_samples_per_second": 48.352, |
| "eval_steps_per_second": 3.022, |
| "step": 11500 |
| }, |
| { |
| "epoch": 3.2312219242957134, |
| "grad_norm": 1.4700162410736084, |
| "learning_rate": 9.783841247342311e-06, |
| "loss": 0.4471, |
| "step": 11600 |
| }, |
| { |
| "epoch": 3.2590799874638714, |
| "grad_norm": 1.1304278373718262, |
| "learning_rate": 9.429482636428065e-06, |
| "loss": 0.4536, |
| "step": 11700 |
| }, |
| { |
| "epoch": 3.28693805063203, |
| "grad_norm": 1.4289369583129883, |
| "learning_rate": 9.075124025513821e-06, |
| "loss": 0.4474, |
| "step": 11800 |
| }, |
| { |
| "epoch": 3.3147961138001882, |
| "grad_norm": 1.3017057180404663, |
| "learning_rate": 8.720765414599575e-06, |
| "loss": 0.4449, |
| "step": 11900 |
| }, |
| { |
| "epoch": 3.342654176968346, |
| "grad_norm": 1.4927443265914917, |
| "learning_rate": 8.36640680368533e-06, |
| "loss": 0.4557, |
| "step": 12000 |
| }, |
| { |
| "epoch": 3.342654176968346, |
| "eval_loss": 0.4085528552532196, |
| "eval_runtime": 592.2863, |
| "eval_samples_per_second": 48.485, |
| "eval_steps_per_second": 3.031, |
| "step": 12000 |
| }, |
| { |
| "epoch": 3.3705122401365046, |
| "grad_norm": 1.4530751705169678, |
| "learning_rate": 8.012048192771085e-06, |
| "loss": 0.455, |
| "step": 12100 |
| }, |
| { |
| "epoch": 3.3983703033046626, |
| "grad_norm": 1.4134407043457031, |
| "learning_rate": 7.65768958185684e-06, |
| "loss": 0.4504, |
| "step": 12200 |
| }, |
| { |
| "epoch": 3.426228366472821, |
| "grad_norm": 1.2031890153884888, |
| "learning_rate": 7.303330970942594e-06, |
| "loss": 0.4473, |
| "step": 12300 |
| }, |
| { |
| "epoch": 3.454086429640979, |
| "grad_norm": 1.3506805896759033, |
| "learning_rate": 6.94897236002835e-06, |
| "loss": 0.4452, |
| "step": 12400 |
| }, |
| { |
| "epoch": 3.4819444928091374, |
| "grad_norm": 1.6460970640182495, |
| "learning_rate": 6.594613749114104e-06, |
| "loss": 0.4475, |
| "step": 12500 |
| }, |
| { |
| "epoch": 3.4819444928091374, |
| "eval_loss": 0.40733858942985535, |
| "eval_runtime": 593.8096, |
| "eval_samples_per_second": 48.361, |
| "eval_steps_per_second": 3.023, |
| "step": 12500 |
| }, |
| { |
| "epoch": 3.509802555977296, |
| "grad_norm": 1.34632408618927, |
| "learning_rate": 6.240255138199858e-06, |
| "loss": 0.4472, |
| "step": 12600 |
| }, |
| { |
| "epoch": 3.537660619145454, |
| "grad_norm": 1.1388472318649292, |
| "learning_rate": 5.885896527285613e-06, |
| "loss": 0.4504, |
| "step": 12700 |
| }, |
| { |
| "epoch": 3.5655186823136122, |
| "grad_norm": 1.3838173151016235, |
| "learning_rate": 5.531537916371368e-06, |
| "loss": 0.4509, |
| "step": 12800 |
| }, |
| { |
| "epoch": 3.59337674548177, |
| "grad_norm": 1.2048169374465942, |
| "learning_rate": 5.1771793054571225e-06, |
| "loss": 0.4484, |
| "step": 12900 |
| }, |
| { |
| "epoch": 3.6212348086499286, |
| "grad_norm": 1.337014079093933, |
| "learning_rate": 4.8228206945428775e-06, |
| "loss": 0.4514, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.6212348086499286, |
| "eval_loss": 0.40576237440109253, |
| "eval_runtime": 592.3205, |
| "eval_samples_per_second": 48.482, |
| "eval_steps_per_second": 3.03, |
| "step": 13000 |
| }, |
| { |
| "epoch": 3.6490928718180866, |
| "grad_norm": 1.2974600791931152, |
| "learning_rate": 4.4684620836286326e-06, |
| "loss": 0.4449, |
| "step": 13100 |
| }, |
| { |
| "epoch": 3.676950934986245, |
| "grad_norm": 1.1322963237762451, |
| "learning_rate": 4.114103472714388e-06, |
| "loss": 0.4514, |
| "step": 13200 |
| }, |
| { |
| "epoch": 3.7048089981544035, |
| "grad_norm": 1.2485069036483765, |
| "learning_rate": 3.7597448618001422e-06, |
| "loss": 0.441, |
| "step": 13300 |
| }, |
| { |
| "epoch": 3.7326670613225614, |
| "grad_norm": 1.3043463230133057, |
| "learning_rate": 3.405386250885897e-06, |
| "loss": 0.4429, |
| "step": 13400 |
| }, |
| { |
| "epoch": 3.76052512449072, |
| "grad_norm": 1.22727632522583, |
| "learning_rate": 3.0510276399716515e-06, |
| "loss": 0.4461, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.76052512449072, |
| "eval_loss": 0.40465712547302246, |
| "eval_runtime": 593.0804, |
| "eval_samples_per_second": 48.42, |
| "eval_steps_per_second": 3.027, |
| "step": 13500 |
| }, |
| { |
| "epoch": 3.7883831876588783, |
| "grad_norm": 1.322852611541748, |
| "learning_rate": 2.696669029057406e-06, |
| "loss": 0.4495, |
| "step": 13600 |
| }, |
| { |
| "epoch": 3.8162412508270362, |
| "grad_norm": 1.18853759765625, |
| "learning_rate": 2.342310418143161e-06, |
| "loss": 0.4363, |
| "step": 13700 |
| }, |
| { |
| "epoch": 3.8440993139951942, |
| "grad_norm": 1.22146475315094, |
| "learning_rate": 1.987951807228916e-06, |
| "loss": 0.4393, |
| "step": 13800 |
| }, |
| { |
| "epoch": 3.8719573771633526, |
| "grad_norm": 1.3995431661605835, |
| "learning_rate": 1.6335931963146704e-06, |
| "loss": 0.4475, |
| "step": 13900 |
| }, |
| { |
| "epoch": 3.899815440331511, |
| "grad_norm": 1.402491807937622, |
| "learning_rate": 1.2792345854004253e-06, |
| "loss": 0.445, |
| "step": 14000 |
| }, |
| { |
| "epoch": 3.899815440331511, |
| "eval_loss": 0.4038073718547821, |
| "eval_runtime": 594.2622, |
| "eval_samples_per_second": 48.324, |
| "eval_steps_per_second": 3.021, |
| "step": 14000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 14360, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 4, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 4.932896695826283e+21, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
