| { | |
| "best_metric": 1.2978554964065552, | |
| "best_model_checkpoint": "./output/checkpoint-3900", | |
| "epoch": 2.3255813953488373, | |
| "eval_steps": 150, | |
| "global_step": 4800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0048449612403100775, | |
| "grad_norm": 33.16083526611328, | |
| "learning_rate": 1.25e-05, | |
| "loss": 3.9099, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009689922480620155, | |
| "grad_norm": 14.680173873901367, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.7088, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.014534883720930232, | |
| "grad_norm": 11.869793891906738, | |
| "learning_rate": 3.75e-05, | |
| "loss": 1.8952, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01937984496124031, | |
| "grad_norm": 9.641575813293457, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6699, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02422480620155039, | |
| "grad_norm": 8.119805335998535, | |
| "learning_rate": 6.25e-05, | |
| "loss": 1.6491, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.029069767441860465, | |
| "grad_norm": 8.050493240356445, | |
| "learning_rate": 7.5e-05, | |
| "loss": 1.5062, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.03391472868217054, | |
| "grad_norm": 7.072201251983643, | |
| "learning_rate": 8.75e-05, | |
| "loss": 1.535, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.03875968992248062, | |
| "grad_norm": 7.6121931076049805, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4697, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0436046511627907, | |
| "grad_norm": 6.530114650726318, | |
| "learning_rate": 0.00011250000000000001, | |
| "loss": 1.5404, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.04844961240310078, | |
| "grad_norm": 7.183197975158691, | |
| "learning_rate": 0.000125, | |
| "loss": 1.5182, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05329457364341085, | |
| "grad_norm": 6.398809909820557, | |
| "learning_rate": 0.00012499871543489787, | |
| "loss": 1.4754, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.05813953488372093, | |
| "grad_norm": 5.547942638397217, | |
| "learning_rate": 0.00012499486179239495, | |
| "loss": 1.5071, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.06298449612403101, | |
| "grad_norm": 5.425671577453613, | |
| "learning_rate": 0.00012498843923089938, | |
| "loss": 1.4976, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.06782945736434108, | |
| "grad_norm": 5.802628993988037, | |
| "learning_rate": 0.0001249794480144175, | |
| "loss": 1.5023, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.07267441860465117, | |
| "grad_norm": 6.187611103057861, | |
| "learning_rate": 0.000124967888512543, | |
| "loss": 1.4752, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07267441860465117, | |
| "eval_loss": 1.4769259691238403, | |
| "eval_runtime": 34.5162, | |
| "eval_samples_per_second": 14.486, | |
| "eval_steps_per_second": 14.486, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.07751937984496124, | |
| "grad_norm": 5.855692386627197, | |
| "learning_rate": 0.00012495376120044173, | |
| "loss": 1.4765, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.08236434108527131, | |
| "grad_norm": 5.552834510803223, | |
| "learning_rate": 0.00012493706665883217, | |
| "loss": 1.4861, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.0872093023255814, | |
| "grad_norm": 5.825935363769531, | |
| "learning_rate": 0.00012491780557396154, | |
| "loss": 1.5161, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.09205426356589147, | |
| "grad_norm": 5.047133922576904, | |
| "learning_rate": 0.00012489597873757756, | |
| "loss": 1.4709, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.09689922480620156, | |
| "grad_norm": 5.497174263000488, | |
| "learning_rate": 0.00012487158704689602, | |
| "loss": 1.5179, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10174418604651163, | |
| "grad_norm": 5.359213352203369, | |
| "learning_rate": 0.0001248446315045638, | |
| "loss": 1.4926, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.1065891472868217, | |
| "grad_norm": 4.8698410987854, | |
| "learning_rate": 0.00012481511321861763, | |
| "loss": 1.4917, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.11143410852713179, | |
| "grad_norm": 5.268365383148193, | |
| "learning_rate": 0.00012478303340243864, | |
| "loss": 1.4716, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.11627906976744186, | |
| "grad_norm": 5.6616129875183105, | |
| "learning_rate": 0.00012474839337470246, | |
| "loss": 1.4198, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.12112403100775193, | |
| "grad_norm": 4.87906551361084, | |
| "learning_rate": 0.0001247111945593249, | |
| "loss": 1.4401, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.12596899224806202, | |
| "grad_norm": 5.170640468597412, | |
| "learning_rate": 0.00012467143848540359, | |
| "loss": 1.4238, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.1308139534883721, | |
| "grad_norm": 5.322551727294922, | |
| "learning_rate": 0.000124629126787155, | |
| "loss": 1.4508, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.13565891472868216, | |
| "grad_norm": 5.429434776306152, | |
| "learning_rate": 0.00012458426120384738, | |
| "loss": 1.4353, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.14050387596899225, | |
| "grad_norm": 5.199410438537598, | |
| "learning_rate": 0.00012453684357972906, | |
| "loss": 1.461, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.14534883720930233, | |
| "grad_norm": 5.171191692352295, | |
| "learning_rate": 0.00012448687586395289, | |
| "loss": 1.4664, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.14534883720930233, | |
| "eval_loss": 1.4425313472747803, | |
| "eval_runtime": 36.0012, | |
| "eval_samples_per_second": 13.888, | |
| "eval_steps_per_second": 13.888, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.1501937984496124, | |
| "grad_norm": 4.924413681030273, | |
| "learning_rate": 0.00012443436011049593, | |
| "loss": 1.4615, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.15503875968992248, | |
| "grad_norm": 4.954301834106445, | |
| "learning_rate": 0.0001243792984780751, | |
| "loss": 1.4509, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.15988372093023256, | |
| "grad_norm": 4.462923526763916, | |
| "learning_rate": 0.00012432169323005853, | |
| "loss": 1.4489, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.16472868217054262, | |
| "grad_norm": 4.328495502471924, | |
| "learning_rate": 0.00012426154673437223, | |
| "loss": 1.4734, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.1695736434108527, | |
| "grad_norm": 4.499818801879883, | |
| "learning_rate": 0.00012419886146340314, | |
| "loss": 1.4282, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.1744186046511628, | |
| "grad_norm": 4.927942276000977, | |
| "learning_rate": 0.0001241336399938972, | |
| "loss": 1.4036, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.17926356589147288, | |
| "grad_norm": 4.415456295013428, | |
| "learning_rate": 0.00012406588500685355, | |
| "loss": 1.4121, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.18410852713178294, | |
| "grad_norm": 4.326357841491699, | |
| "learning_rate": 0.00012399559928741435, | |
| "loss": 1.4743, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.18895348837209303, | |
| "grad_norm": 4.8075408935546875, | |
| "learning_rate": 0.00012392278572475023, | |
| "loss": 1.4212, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.1937984496124031, | |
| "grad_norm": 5.174283027648926, | |
| "learning_rate": 0.0001238474473119416, | |
| "loss": 1.4244, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.19864341085271317, | |
| "grad_norm": 5.053370952606201, | |
| "learning_rate": 0.00012376958714585545, | |
| "loss": 1.4763, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.20348837209302326, | |
| "grad_norm": 4.216630458831787, | |
| "learning_rate": 0.0001236892084270183, | |
| "loss": 1.4072, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.20833333333333334, | |
| "grad_norm": 4.96584939956665, | |
| "learning_rate": 0.00012360631445948448, | |
| "loss": 1.3984, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.2131782945736434, | |
| "grad_norm": 4.817144393920898, | |
| "learning_rate": 0.00012352090865070026, | |
| "loss": 1.3884, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.2180232558139535, | |
| "grad_norm": 4.395285129547119, | |
| "learning_rate": 0.00012343299451136397, | |
| "loss": 1.4737, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2180232558139535, | |
| "eval_loss": 1.437117576599121, | |
| "eval_runtime": 34.379, | |
| "eval_samples_per_second": 14.544, | |
| "eval_steps_per_second": 14.544, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.22286821705426357, | |
| "grad_norm": 4.261348247528076, | |
| "learning_rate": 0.00012334257565528155, | |
| "loss": 1.4427, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.22771317829457363, | |
| "grad_norm": 4.141024589538574, | |
| "learning_rate": 0.000123249655799218, | |
| "loss": 1.345, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.23255813953488372, | |
| "grad_norm": 5.018428802490234, | |
| "learning_rate": 0.00012315423876274468, | |
| "loss": 1.3671, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.2374031007751938, | |
| "grad_norm": 4.942126274108887, | |
| "learning_rate": 0.0001230563284680822, | |
| "loss": 1.3863, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.24224806201550386, | |
| "grad_norm": 4.775027275085449, | |
| "learning_rate": 0.00012295592893993935, | |
| "loss": 1.3574, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.24709302325581395, | |
| "grad_norm": 4.757259845733643, | |
| "learning_rate": 0.00012285304430534745, | |
| "loss": 1.3904, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.25193798449612403, | |
| "grad_norm": 4.785523414611816, | |
| "learning_rate": 0.00012274767879349083, | |
| "loss": 1.4255, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.2567829457364341, | |
| "grad_norm": 4.766105651855469, | |
| "learning_rate": 0.00012263983673553306, | |
| "loss": 1.4344, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.2616279069767442, | |
| "grad_norm": 4.429969310760498, | |
| "learning_rate": 0.0001225295225644387, | |
| "loss": 1.3928, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.26647286821705424, | |
| "grad_norm": 4.636560440063477, | |
| "learning_rate": 0.0001224167408147913, | |
| "loss": 1.4041, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.2713178294573643, | |
| "grad_norm": 4.649174213409424, | |
| "learning_rate": 0.0001223014961226068, | |
| "loss": 1.4014, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.2761627906976744, | |
| "grad_norm": 4.894825458526611, | |
| "learning_rate": 0.00012218379322514317, | |
| "loss": 1.4221, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.2810077519379845, | |
| "grad_norm": 4.615547180175781, | |
| "learning_rate": 0.00012206363696070545, | |
| "loss": 1.4099, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.2858527131782946, | |
| "grad_norm": 5.573257923126221, | |
| "learning_rate": 0.0001219410322684471, | |
| "loss": 1.3943, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.29069767441860467, | |
| "grad_norm": 4.57981538772583, | |
| "learning_rate": 0.0001218159841881668, | |
| "loss": 1.356, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.29069767441860467, | |
| "eval_loss": 1.4054266214370728, | |
| "eval_runtime": 34.2312, | |
| "eval_samples_per_second": 14.607, | |
| "eval_steps_per_second": 14.607, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.29554263565891475, | |
| "grad_norm": 4.497678756713867, | |
| "learning_rate": 0.00012168849786010133, | |
| "loss": 1.4294, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.3003875968992248, | |
| "grad_norm": 4.548286437988281, | |
| "learning_rate": 0.00012155857852471433, | |
| "loss": 1.3586, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.30523255813953487, | |
| "grad_norm": 4.280961036682129, | |
| "learning_rate": 0.0001214262315224808, | |
| "loss": 1.4012, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.31007751937984496, | |
| "grad_norm": 4.456599712371826, | |
| "learning_rate": 0.00012129146229366766, | |
| "loss": 1.3864, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.31492248062015504, | |
| "grad_norm": 4.1045026779174805, | |
| "learning_rate": 0.00012115427637811003, | |
| "loss": 1.3577, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.31976744186046513, | |
| "grad_norm": 4.406848907470703, | |
| "learning_rate": 0.00012101467941498357, | |
| "loss": 1.4146, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.3246124031007752, | |
| "grad_norm": 4.694105625152588, | |
| "learning_rate": 0.0001208726771425727, | |
| "loss": 1.4122, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.32945736434108525, | |
| "grad_norm": 4.289068222045898, | |
| "learning_rate": 0.00012072827539803463, | |
| "loss": 1.3991, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.33430232558139533, | |
| "grad_norm": 4.505423069000244, | |
| "learning_rate": 0.00012058148011715949, | |
| "loss": 1.3951, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.3391472868217054, | |
| "grad_norm": 4.226860523223877, | |
| "learning_rate": 0.00012043229733412636, | |
| "loss": 1.4685, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3439922480620155, | |
| "grad_norm": 4.11680269241333, | |
| "learning_rate": 0.0001202807331812551, | |
| "loss": 1.3788, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.3488372093023256, | |
| "grad_norm": 3.9299204349517822, | |
| "learning_rate": 0.00012012679388875441, | |
| "loss": 1.3745, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.3536821705426357, | |
| "grad_norm": 4.7261128425598145, | |
| "learning_rate": 0.00011997048578446568, | |
| "loss": 1.4027, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.35852713178294576, | |
| "grad_norm": 4.087492942810059, | |
| "learning_rate": 0.00011981181529360282, | |
| "loss": 1.3779, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.3633720930232558, | |
| "grad_norm": 3.9707279205322266, | |
| "learning_rate": 0.00011965078893848828, | |
| "loss": 1.3969, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3633720930232558, | |
| "eval_loss": 1.3779653310775757, | |
| "eval_runtime": 35.15, | |
| "eval_samples_per_second": 14.225, | |
| "eval_steps_per_second": 14.225, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.3682170542635659, | |
| "grad_norm": 4.034614086151123, | |
| "learning_rate": 0.00011948741333828481, | |
| "loss": 1.3493, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.37306201550387597, | |
| "grad_norm": 4.590168476104736, | |
| "learning_rate": 0.00011932169520872344, | |
| "loss": 1.3591, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.37790697674418605, | |
| "grad_norm": 3.9696972370147705, | |
| "learning_rate": 0.00011915364136182738, | |
| "loss": 1.3723, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.38275193798449614, | |
| "grad_norm": 4.8090362548828125, | |
| "learning_rate": 0.0001189832587056321, | |
| "loss": 1.3493, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.3875968992248062, | |
| "grad_norm": 4.091393947601318, | |
| "learning_rate": 0.00011881055424390119, | |
| "loss": 1.3971, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.39244186046511625, | |
| "grad_norm": 4.403999328613281, | |
| "learning_rate": 0.00011863553507583869, | |
| "loss": 1.4213, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.39728682170542634, | |
| "grad_norm": 4.0738935470581055, | |
| "learning_rate": 0.00011845820839579708, | |
| "loss": 1.408, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.4021317829457364, | |
| "grad_norm": 4.7122273445129395, | |
| "learning_rate": 0.00011827858149298162, | |
| "loss": 1.373, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.4069767441860465, | |
| "grad_norm": 4.809484958648682, | |
| "learning_rate": 0.00011809666175115075, | |
| "loss": 1.3717, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.4118217054263566, | |
| "grad_norm": 4.254739284515381, | |
| "learning_rate": 0.00011791245664831251, | |
| "loss": 1.4034, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4166666666666667, | |
| "grad_norm": 4.524000644683838, | |
| "learning_rate": 0.0001177259737564172, | |
| "loss": 1.4208, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.42151162790697677, | |
| "grad_norm": 4.406377792358398, | |
| "learning_rate": 0.00011753722074104613, | |
| "loss": 1.4435, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.4263565891472868, | |
| "grad_norm": 4.082479000091553, | |
| "learning_rate": 0.00011734620536109644, | |
| "loss": 1.4212, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.4312015503875969, | |
| "grad_norm": 4.172248363494873, | |
| "learning_rate": 0.00011715293546846223, | |
| "loss": 1.3903, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.436046511627907, | |
| "grad_norm": 3.921027898788452, | |
| "learning_rate": 0.00011695741900771184, | |
| "loss": 1.3914, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.436046511627907, | |
| "eval_loss": 1.3852204084396362, | |
| "eval_runtime": 34.9476, | |
| "eval_samples_per_second": 14.307, | |
| "eval_steps_per_second": 14.307, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.44089147286821706, | |
| "grad_norm": 4.309497833251953, | |
| "learning_rate": 0.00011675966401576116, | |
| "loss": 1.3977, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.44573643410852715, | |
| "grad_norm": 4.024077415466309, | |
| "learning_rate": 0.00011655967862154335, | |
| "loss": 1.3745, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.45058139534883723, | |
| "grad_norm": 4.421174049377441, | |
| "learning_rate": 0.0001163574710456747, | |
| "loss": 1.3927, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.45542635658914726, | |
| "grad_norm": 4.4601569175720215, | |
| "learning_rate": 0.00011615304960011663, | |
| "loss": 1.3895, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.46027131782945735, | |
| "grad_norm": 4.016902923583984, | |
| "learning_rate": 0.00011594642268783415, | |
| "loss": 1.3343, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.46511627906976744, | |
| "grad_norm": 4.68607759475708, | |
| "learning_rate": 0.00011573759880245027, | |
| "loss": 1.4032, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.4699612403100775, | |
| "grad_norm": 4.8534979820251465, | |
| "learning_rate": 0.00011552658652789703, | |
| "loss": 1.39, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.4748062015503876, | |
| "grad_norm": 4.396952152252197, | |
| "learning_rate": 0.00011531339453806258, | |
| "loss": 1.3895, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.4796511627906977, | |
| "grad_norm": 4.624823093414307, | |
| "learning_rate": 0.00011509803159643458, | |
| "loss": 1.3998, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.4844961240310077, | |
| "grad_norm": 4.828771114349365, | |
| "learning_rate": 0.00011488050655574003, | |
| "loss": 1.3768, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.4893410852713178, | |
| "grad_norm": 4.6348137855529785, | |
| "learning_rate": 0.00011466082835758141, | |
| "loss": 1.3654, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.4941860465116279, | |
| "grad_norm": 4.274475574493408, | |
| "learning_rate": 0.000114439006032069, | |
| "loss": 1.3733, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.499031007751938, | |
| "grad_norm": 4.305916786193848, | |
| "learning_rate": 0.00011421504869744978, | |
| "loss": 1.3546, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.5038759689922481, | |
| "grad_norm": 3.968743085861206, | |
| "learning_rate": 0.0001139889655597326, | |
| "loss": 1.415, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 0.5087209302325582, | |
| "grad_norm": 4.156125068664551, | |
| "learning_rate": 0.00011376076591230974, | |
| "loss": 1.3696, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5087209302325582, | |
| "eval_loss": 1.3692814111709595, | |
| "eval_runtime": 34.9432, | |
| "eval_samples_per_second": 14.309, | |
| "eval_steps_per_second": 14.309, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5135658914728682, | |
| "grad_norm": 4.3611369132995605, | |
| "learning_rate": 0.00011353045913557492, | |
| "loss": 1.3592, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 0.5184108527131783, | |
| "grad_norm": 4.626410007476807, | |
| "learning_rate": 0.00011329805469653768, | |
| "loss": 1.4033, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 0.5232558139534884, | |
| "grad_norm": 4.445812702178955, | |
| "learning_rate": 0.00011306356214843422, | |
| "loss": 1.4163, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 0.5281007751937985, | |
| "grad_norm": 4.1766252517700195, | |
| "learning_rate": 0.00011282699113033477, | |
| "loss": 1.3933, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 0.5329457364341085, | |
| "grad_norm": 4.215488910675049, | |
| "learning_rate": 0.00011258835136674729, | |
| "loss": 1.4096, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5377906976744186, | |
| "grad_norm": 4.028621196746826, | |
| "learning_rate": 0.00011234765266721778, | |
| "loss": 1.3521, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 0.5426356589147286, | |
| "grad_norm": 4.436669826507568, | |
| "learning_rate": 0.00011210490492592703, | |
| "loss": 1.3729, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 0.5474806201550387, | |
| "grad_norm": 4.071181297302246, | |
| "learning_rate": 0.0001118601181212839, | |
| "loss": 1.3735, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 0.5523255813953488, | |
| "grad_norm": 4.056524276733398, | |
| "learning_rate": 0.00011161330231551515, | |
| "loss": 1.3438, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 0.5571705426356589, | |
| "grad_norm": 4.2103657722473145, | |
| "learning_rate": 0.00011136446765425187, | |
| "loss": 1.4084, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.562015503875969, | |
| "grad_norm": 3.7534801959991455, | |
| "learning_rate": 0.00011111362436611234, | |
| "loss": 1.3764, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 0.5668604651162791, | |
| "grad_norm": 4.244382858276367, | |
| "learning_rate": 0.00011086078276228167, | |
| "loss": 1.337, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 0.5717054263565892, | |
| "grad_norm": 4.235080242156982, | |
| "learning_rate": 0.00011060595323608789, | |
| "loss": 1.4298, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 0.5765503875968992, | |
| "grad_norm": 4.290858268737793, | |
| "learning_rate": 0.00011034914626257467, | |
| "loss": 1.3565, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "grad_norm": 4.229033470153809, | |
| "learning_rate": 0.0001100903723980709, | |
| "loss": 1.3638, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5813953488372093, | |
| "eval_loss": 1.3742729425430298, | |
| "eval_runtime": 34.3543, | |
| "eval_samples_per_second": 14.554, | |
| "eval_steps_per_second": 14.554, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.5862403100775194, | |
| "grad_norm": 4.066321849822998, | |
| "learning_rate": 0.00010982964227975658, | |
| "loss": 1.3564, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 0.5910852713178295, | |
| "grad_norm": 4.3556718826293945, | |
| "learning_rate": 0.00010956696662522569, | |
| "loss": 1.4185, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 0.5959302325581395, | |
| "grad_norm": 4.408959865570068, | |
| "learning_rate": 0.00010930235623204551, | |
| "loss": 1.3674, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 0.6007751937984496, | |
| "grad_norm": 3.7719295024871826, | |
| "learning_rate": 0.00010903582197731294, | |
| "loss": 1.3014, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 0.6056201550387597, | |
| "grad_norm": 3.8520030975341797, | |
| "learning_rate": 0.00010876737481720722, | |
| "loss": 1.3433, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6104651162790697, | |
| "grad_norm": 4.325175762176514, | |
| "learning_rate": 0.0001084970257865397, | |
| "loss": 1.4005, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 0.6153100775193798, | |
| "grad_norm": 3.8847227096557617, | |
| "learning_rate": 0.00010822478599830008, | |
| "loss": 1.4091, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 0.6201550387596899, | |
| "grad_norm": 3.9878618717193604, | |
| "learning_rate": 0.00010795066664319983, | |
| "loss": 1.3832, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 0.625, | |
| "grad_norm": 4.19332218170166, | |
| "learning_rate": 0.00010767467898921197, | |
| "loss": 1.3659, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 0.6298449612403101, | |
| "grad_norm": 4.531820774078369, | |
| "learning_rate": 0.00010739683438110797, | |
| "loss": 1.3475, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6346899224806202, | |
| "grad_norm": 3.9032485485076904, | |
| "learning_rate": 0.00010711714423999145, | |
| "loss": 1.3598, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 0.6395348837209303, | |
| "grad_norm": 4.083787441253662, | |
| "learning_rate": 0.00010683562006282861, | |
| "loss": 1.3636, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 0.6443798449612403, | |
| "grad_norm": 4.280800819396973, | |
| "learning_rate": 0.00010655227342197574, | |
| "loss": 1.3343, | |
| "step": 1330 | |
| }, | |
| { | |
| "epoch": 0.6492248062015504, | |
| "grad_norm": 4.18052864074707, | |
| "learning_rate": 0.00010626711596470343, | |
| "loss": 1.3454, | |
| "step": 1340 | |
| }, | |
| { | |
| "epoch": 0.6540697674418605, | |
| "grad_norm": 4.2066121101379395, | |
| "learning_rate": 0.0001059801594127179, | |
| "loss": 1.3608, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6540697674418605, | |
| "eval_loss": 1.3640578985214233, | |
| "eval_runtime": 35.1187, | |
| "eval_samples_per_second": 14.237, | |
| "eval_steps_per_second": 14.237, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.6589147286821705, | |
| "grad_norm": 4.734892845153809, | |
| "learning_rate": 0.00010569141556167905, | |
| "loss": 1.3878, | |
| "step": 1360 | |
| }, | |
| { | |
| "epoch": 0.6637596899224806, | |
| "grad_norm": 4.622696399688721, | |
| "learning_rate": 0.00010540089628071566, | |
| "loss": 1.3813, | |
| "step": 1370 | |
| }, | |
| { | |
| "epoch": 0.6686046511627907, | |
| "grad_norm": 4.379586219787598, | |
| "learning_rate": 0.00010510861351193747, | |
| "loss": 1.338, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 0.6734496124031008, | |
| "grad_norm": 4.084921836853027, | |
| "learning_rate": 0.00010481457926994435, | |
| "loss": 1.3616, | |
| "step": 1390 | |
| }, | |
| { | |
| "epoch": 0.6782945736434108, | |
| "grad_norm": 4.132017612457275, | |
| "learning_rate": 0.0001045188056413323, | |
| "loss": 1.3917, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.6831395348837209, | |
| "grad_norm": 4.240015506744385, | |
| "learning_rate": 0.00010422130478419676, | |
| "loss": 1.3694, | |
| "step": 1410 | |
| }, | |
| { | |
| "epoch": 0.687984496124031, | |
| "grad_norm": 4.058047771453857, | |
| "learning_rate": 0.00010392208892763269, | |
| "loss": 1.3665, | |
| "step": 1420 | |
| }, | |
| { | |
| "epoch": 0.6928294573643411, | |
| "grad_norm": 4.3433837890625, | |
| "learning_rate": 0.00010362117037123204, | |
| "loss": 1.3495, | |
| "step": 1430 | |
| }, | |
| { | |
| "epoch": 0.6976744186046512, | |
| "grad_norm": 4.379434108734131, | |
| "learning_rate": 0.00010331856148457803, | |
| "loss": 1.3792, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 0.7025193798449613, | |
| "grad_norm": 4.294039726257324, | |
| "learning_rate": 0.00010301427470673678, | |
| "loss": 1.3507, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7073643410852714, | |
| "grad_norm": 3.8750815391540527, | |
| "learning_rate": 0.00010270832254574588, | |
| "loss": 1.3536, | |
| "step": 1460 | |
| }, | |
| { | |
| "epoch": 0.7122093023255814, | |
| "grad_norm": 4.3442182540893555, | |
| "learning_rate": 0.00010240071757810036, | |
| "loss": 1.3499, | |
| "step": 1470 | |
| }, | |
| { | |
| "epoch": 0.7170542635658915, | |
| "grad_norm": 4.361018657684326, | |
| "learning_rate": 0.00010209147244823564, | |
| "loss": 1.3458, | |
| "step": 1480 | |
| }, | |
| { | |
| "epoch": 0.7218992248062015, | |
| "grad_norm": 4.097925186157227, | |
| "learning_rate": 0.00010178059986800773, | |
| "loss": 1.3349, | |
| "step": 1490 | |
| }, | |
| { | |
| "epoch": 0.7267441860465116, | |
| "grad_norm": 4.0469841957092285, | |
| "learning_rate": 0.00010146811261617085, | |
| "loss": 1.3563, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7267441860465116, | |
| "eval_loss": 1.3613923788070679, | |
| "eval_runtime": 35.3447, | |
| "eval_samples_per_second": 14.146, | |
| "eval_steps_per_second": 14.146, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7315891472868217, | |
| "grad_norm": 4.677872180938721, | |
| "learning_rate": 0.00010115402353785197, | |
| "loss": 1.3768, | |
| "step": 1510 | |
| }, | |
| { | |
| "epoch": 0.7364341085271318, | |
| "grad_norm": 4.105203628540039, | |
| "learning_rate": 0.00010083834554402292, | |
| "loss": 1.3539, | |
| "step": 1520 | |
| }, | |
| { | |
| "epoch": 0.7412790697674418, | |
| "grad_norm": 4.328856468200684, | |
| "learning_rate": 0.00010052109161096958, | |
| "loss": 1.3719, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 0.7461240310077519, | |
| "grad_norm": 3.782973051071167, | |
| "learning_rate": 0.00010020227477975852, | |
| "loss": 1.3682, | |
| "step": 1540 | |
| }, | |
| { | |
| "epoch": 0.750968992248062, | |
| "grad_norm": 4.47057580947876, | |
| "learning_rate": 9.9881908155701e-05, | |
| "loss": 1.3408, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.7558139534883721, | |
| "grad_norm": 4.271434307098389, | |
| "learning_rate": 9.956000490781411e-05, | |
| "loss": 1.3304, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 0.7606589147286822, | |
| "grad_norm": 4.192820072174072, | |
| "learning_rate": 9.923657826827957e-05, | |
| "loss": 1.3259, | |
| "step": 1570 | |
| }, | |
| { | |
| "epoch": 0.7655038759689923, | |
| "grad_norm": 3.813554286956787, | |
| "learning_rate": 9.891164153189976e-05, | |
| "loss": 1.3234, | |
| "step": 1580 | |
| }, | |
| { | |
| "epoch": 0.7703488372093024, | |
| "grad_norm": 3.9348225593566895, | |
| "learning_rate": 9.858520805555123e-05, | |
| "loss": 1.3185, | |
| "step": 1590 | |
| }, | |
| { | |
| "epoch": 0.7751937984496124, | |
| "grad_norm": 4.340898513793945, | |
| "learning_rate": 9.825729125763561e-05, | |
| "loss": 1.3518, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.7800387596899225, | |
| "grad_norm": 4.097005844116211, | |
| "learning_rate": 9.792790461752813e-05, | |
| "loss": 1.3641, | |
| "step": 1610 | |
| }, | |
| { | |
| "epoch": 0.7848837209302325, | |
| "grad_norm": 4.03990364074707, | |
| "learning_rate": 9.759706167502343e-05, | |
| "loss": 1.3761, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 0.7897286821705426, | |
| "grad_norm": 4.171065330505371, | |
| "learning_rate": 9.726477602977905e-05, | |
| "loss": 1.326, | |
| "step": 1630 | |
| }, | |
| { | |
| "epoch": 0.7945736434108527, | |
| "grad_norm": 3.930081605911255, | |
| "learning_rate": 9.69310613407564e-05, | |
| "loss": 1.3669, | |
| "step": 1640 | |
| }, | |
| { | |
| "epoch": 0.7994186046511628, | |
| "grad_norm": 4.125776290893555, | |
| "learning_rate": 9.659593132565929e-05, | |
| "loss": 1.3572, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.7994186046511628, | |
| "eval_loss": 1.3497689962387085, | |
| "eval_runtime": 34.7157, | |
| "eval_samples_per_second": 14.403, | |
| "eval_steps_per_second": 14.403, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.8042635658914729, | |
| "grad_norm": 4.123137950897217, | |
| "learning_rate": 9.625939976037002e-05, | |
| "loss": 1.3696, | |
| "step": 1660 | |
| }, | |
| { | |
| "epoch": 0.8091085271317829, | |
| "grad_norm": 4.232200622558594, | |
| "learning_rate": 9.59214804783831e-05, | |
| "loss": 1.3692, | |
| "step": 1670 | |
| }, | |
| { | |
| "epoch": 0.813953488372093, | |
| "grad_norm": 4.422992706298828, | |
| "learning_rate": 9.558218737023671e-05, | |
| "loss": 1.3037, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 0.8187984496124031, | |
| "grad_norm": 4.27236795425415, | |
| "learning_rate": 9.524153438294159e-05, | |
| "loss": 1.3327, | |
| "step": 1690 | |
| }, | |
| { | |
| "epoch": 0.8236434108527132, | |
| "grad_norm": 3.908616542816162, | |
| "learning_rate": 9.489953551940783e-05, | |
| "loss": 1.3689, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8284883720930233, | |
| "grad_norm": 3.9563255310058594, | |
| "learning_rate": 9.455620483786914e-05, | |
| "loss": 1.3409, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 4.521614074707031, | |
| "learning_rate": 9.421155645130514e-05, | |
| "loss": 1.3727, | |
| "step": 1720 | |
| }, | |
| { | |
| "epoch": 0.8381782945736435, | |
| "grad_norm": 4.471999645233154, | |
| "learning_rate": 9.38656045268611e-05, | |
| "loss": 1.3606, | |
| "step": 1730 | |
| }, | |
| { | |
| "epoch": 0.8430232558139535, | |
| "grad_norm": 3.7059531211853027, | |
| "learning_rate": 9.351836328526563e-05, | |
| "loss": 1.3842, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 0.8478682170542635, | |
| "grad_norm": 4.375723838806152, | |
| "learning_rate": 9.316984700024612e-05, | |
| "loss": 1.3258, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.8527131782945736, | |
| "grad_norm": 4.4300994873046875, | |
| "learning_rate": 9.2820069997942e-05, | |
| "loss": 1.3815, | |
| "step": 1760 | |
| }, | |
| { | |
| "epoch": 0.8575581395348837, | |
| "grad_norm": 4.2471394538879395, | |
| "learning_rate": 9.246904665631588e-05, | |
| "loss": 1.3335, | |
| "step": 1770 | |
| }, | |
| { | |
| "epoch": 0.8624031007751938, | |
| "grad_norm": 4.115731239318848, | |
| "learning_rate": 9.211679140456242e-05, | |
| "loss": 1.3587, | |
| "step": 1780 | |
| }, | |
| { | |
| "epoch": 0.8672480620155039, | |
| "grad_norm": 4.372647762298584, | |
| "learning_rate": 9.176331872251536e-05, | |
| "loss": 1.3888, | |
| "step": 1790 | |
| }, | |
| { | |
| "epoch": 0.872093023255814, | |
| "grad_norm": 3.9626224040985107, | |
| "learning_rate": 9.140864314005222e-05, | |
| "loss": 1.3868, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.872093023255814, | |
| "eval_loss": 1.3441931009292603, | |
| "eval_runtime": 34.1493, | |
| "eval_samples_per_second": 14.642, | |
| "eval_steps_per_second": 14.642, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.876937984496124, | |
| "grad_norm": 4.511176586151123, | |
| "learning_rate": 9.105277923649698e-05, | |
| "loss": 1.3216, | |
| "step": 1810 | |
| }, | |
| { | |
| "epoch": 0.8817829457364341, | |
| "grad_norm": 4.154355525970459, | |
| "learning_rate": 9.06957416400209e-05, | |
| "loss": 1.3409, | |
| "step": 1820 | |
| }, | |
| { | |
| "epoch": 0.8866279069767442, | |
| "grad_norm": 4.167087078094482, | |
| "learning_rate": 9.03375450270412e-05, | |
| "loss": 1.3284, | |
| "step": 1830 | |
| }, | |
| { | |
| "epoch": 0.8914728682170543, | |
| "grad_norm": 4.253835678100586, | |
| "learning_rate": 8.997820412161764e-05, | |
| "loss": 1.3555, | |
| "step": 1840 | |
| }, | |
| { | |
| "epoch": 0.8963178294573644, | |
| "grad_norm": 4.122718334197998, | |
| "learning_rate": 8.961773369484738e-05, | |
| "loss": 1.3109, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9011627906976745, | |
| "grad_norm": 4.078066825866699, | |
| "learning_rate": 8.925614856425786e-05, | |
| "loss": 1.3114, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 0.9060077519379846, | |
| "grad_norm": 4.012754917144775, | |
| "learning_rate": 8.88934635931975e-05, | |
| "loss": 1.3685, | |
| "step": 1870 | |
| }, | |
| { | |
| "epoch": 0.9108527131782945, | |
| "grad_norm": 4.192358016967773, | |
| "learning_rate": 8.852969369022494e-05, | |
| "loss": 1.3869, | |
| "step": 1880 | |
| }, | |
| { | |
| "epoch": 0.9156976744186046, | |
| "grad_norm": 4.08505916595459, | |
| "learning_rate": 8.816485380849613e-05, | |
| "loss": 1.3766, | |
| "step": 1890 | |
| }, | |
| { | |
| "epoch": 0.9205426356589147, | |
| "grad_norm": 4.077611923217773, | |
| "learning_rate": 8.779895894514961e-05, | |
| "loss": 1.3243, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9253875968992248, | |
| "grad_norm": 4.200951099395752, | |
| "learning_rate": 8.743202414069011e-05, | |
| "loss": 1.364, | |
| "step": 1910 | |
| }, | |
| { | |
| "epoch": 0.9302325581395349, | |
| "grad_norm": 3.8946659564971924, | |
| "learning_rate": 8.706406447837023e-05, | |
| "loss": 1.3445, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 0.935077519379845, | |
| "grad_norm": 4.817138195037842, | |
| "learning_rate": 8.669509508357052e-05, | |
| "loss": 1.3452, | |
| "step": 1930 | |
| }, | |
| { | |
| "epoch": 0.939922480620155, | |
| "grad_norm": 3.7811405658721924, | |
| "learning_rate": 8.632513112317761e-05, | |
| "loss": 1.2988, | |
| "step": 1940 | |
| }, | |
| { | |
| "epoch": 0.9447674418604651, | |
| "grad_norm": 4.025355815887451, | |
| "learning_rate": 8.59541878049609e-05, | |
| "loss": 1.2931, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9447674418604651, | |
| "eval_loss": 1.342638373374939, | |
| "eval_runtime": 34.8923, | |
| "eval_samples_per_second": 14.33, | |
| "eval_steps_per_second": 14.33, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.9496124031007752, | |
| "grad_norm": 4.080333709716797, | |
| "learning_rate": 8.558228037694728e-05, | |
| "loss": 1.3605, | |
| "step": 1960 | |
| }, | |
| { | |
| "epoch": 0.9544573643410853, | |
| "grad_norm": 4.330687046051025, | |
| "learning_rate": 8.520942412679447e-05, | |
| "loss": 1.358, | |
| "step": 1970 | |
| }, | |
| { | |
| "epoch": 0.9593023255813954, | |
| "grad_norm": 3.8246426582336426, | |
| "learning_rate": 8.483563438116257e-05, | |
| "loss": 1.3954, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 0.9641472868217055, | |
| "grad_norm": 4.163506984710693, | |
| "learning_rate": 8.446092650508393e-05, | |
| "loss": 1.3248, | |
| "step": 1990 | |
| }, | |
| { | |
| "epoch": 0.9689922480620154, | |
| "grad_norm": 4.115441799163818, | |
| "learning_rate": 8.408531590133172e-05, | |
| "loss": 1.336, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.9738372093023255, | |
| "grad_norm": 4.257992744445801, | |
| "learning_rate": 8.370881800978673e-05, | |
| "loss": 1.3192, | |
| "step": 2010 | |
| }, | |
| { | |
| "epoch": 0.9786821705426356, | |
| "grad_norm": 4.327164649963379, | |
| "learning_rate": 8.333144830680262e-05, | |
| "loss": 1.3805, | |
| "step": 2020 | |
| }, | |
| { | |
| "epoch": 0.9835271317829457, | |
| "grad_norm": 4.227909564971924, | |
| "learning_rate": 8.29532223045698e-05, | |
| "loss": 1.3663, | |
| "step": 2030 | |
| }, | |
| { | |
| "epoch": 0.9883720930232558, | |
| "grad_norm": 4.192224502563477, | |
| "learning_rate": 8.257415555047785e-05, | |
| "loss": 1.2889, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 0.9932170542635659, | |
| "grad_norm": 4.218623161315918, | |
| "learning_rate": 8.21942636264763e-05, | |
| "loss": 1.341, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.998062015503876, | |
| "grad_norm": 4.5620503425598145, | |
| "learning_rate": 8.181356214843422e-05, | |
| "loss": 1.3425, | |
| "step": 2060 | |
| }, | |
| { | |
| "epoch": 1.002906976744186, | |
| "grad_norm": 3.8904709815979004, | |
| "learning_rate": 8.143206676549826e-05, | |
| "loss": 1.2196, | |
| "step": 2070 | |
| }, | |
| { | |
| "epoch": 1.0077519379844961, | |
| "grad_norm": 3.8977930545806885, | |
| "learning_rate": 8.10497931594494e-05, | |
| "loss": 1.1792, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 1.0125968992248062, | |
| "grad_norm": 4.280106544494629, | |
| "learning_rate": 8.066675704405836e-05, | |
| "loss": 1.1339, | |
| "step": 2090 | |
| }, | |
| { | |
| "epoch": 1.0174418604651163, | |
| "grad_norm": 4.202190399169922, | |
| "learning_rate": 8.028297416443952e-05, | |
| "loss": 1.2182, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0174418604651163, | |
| "eval_loss": 1.3388093709945679, | |
| "eval_runtime": 35.4199, | |
| "eval_samples_per_second": 14.116, | |
| "eval_steps_per_second": 14.116, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0222868217054264, | |
| "grad_norm": 4.183404922485352, | |
| "learning_rate": 7.989846029640397e-05, | |
| "loss": 1.1741, | |
| "step": 2110 | |
| }, | |
| { | |
| "epoch": 1.0271317829457365, | |
| "grad_norm": 3.9871344566345215, | |
| "learning_rate": 7.951323124581069e-05, | |
| "loss": 1.1608, | |
| "step": 2120 | |
| }, | |
| { | |
| "epoch": 1.0319767441860466, | |
| "grad_norm": 4.37944221496582, | |
| "learning_rate": 7.91273028479172e-05, | |
| "loss": 1.209, | |
| "step": 2130 | |
| }, | |
| { | |
| "epoch": 1.0368217054263567, | |
| "grad_norm": 4.377804279327393, | |
| "learning_rate": 7.874069096672831e-05, | |
| "loss": 1.193, | |
| "step": 2140 | |
| }, | |
| { | |
| "epoch": 1.0416666666666667, | |
| "grad_norm": 4.7681074142456055, | |
| "learning_rate": 7.83534114943442e-05, | |
| "loss": 1.1636, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.0465116279069768, | |
| "grad_norm": 4.442102432250977, | |
| "learning_rate": 7.796548035030715e-05, | |
| "loss": 1.1814, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 1.051356589147287, | |
| "grad_norm": 4.541327476501465, | |
| "learning_rate": 7.757691348094703e-05, | |
| "loss": 1.202, | |
| "step": 2170 | |
| }, | |
| { | |
| "epoch": 1.056201550387597, | |
| "grad_norm": 4.2842698097229, | |
| "learning_rate": 7.718772685872595e-05, | |
| "loss": 1.2073, | |
| "step": 2180 | |
| }, | |
| { | |
| "epoch": 1.0610465116279069, | |
| "grad_norm": 4.021533966064453, | |
| "learning_rate": 7.679793648158159e-05, | |
| "loss": 1.21, | |
| "step": 2190 | |
| }, | |
| { | |
| "epoch": 1.0658914728682172, | |
| "grad_norm": 4.059267520904541, | |
| "learning_rate": 7.640755837226965e-05, | |
| "loss": 1.1831, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.070736434108527, | |
| "grad_norm": 4.384668827056885, | |
| "learning_rate": 7.601660857770522e-05, | |
| "loss": 1.1574, | |
| "step": 2210 | |
| }, | |
| { | |
| "epoch": 1.0755813953488371, | |
| "grad_norm": 4.469862937927246, | |
| "learning_rate": 7.562510316830308e-05, | |
| "loss": 1.1677, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 1.0804263565891472, | |
| "grad_norm": 3.912555456161499, | |
| "learning_rate": 7.523305823731723e-05, | |
| "loss": 1.1334, | |
| "step": 2230 | |
| }, | |
| { | |
| "epoch": 1.0852713178294573, | |
| "grad_norm": 4.685311794281006, | |
| "learning_rate": 7.484048990017919e-05, | |
| "loss": 1.1501, | |
| "step": 2240 | |
| }, | |
| { | |
| "epoch": 1.0901162790697674, | |
| "grad_norm": 4.790440559387207, | |
| "learning_rate": 7.444741429383578e-05, | |
| "loss": 1.1735, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.0901162790697674, | |
| "eval_loss": 1.3379790782928467, | |
| "eval_runtime": 35.4837, | |
| "eval_samples_per_second": 14.091, | |
| "eval_steps_per_second": 14.091, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.0949612403100775, | |
| "grad_norm": 4.603212833404541, | |
| "learning_rate": 7.405384757608555e-05, | |
| "loss": 1.2212, | |
| "step": 2260 | |
| }, | |
| { | |
| "epoch": 1.0998062015503876, | |
| "grad_norm": 4.408427715301514, | |
| "learning_rate": 7.36598059249148e-05, | |
| "loss": 1.22, | |
| "step": 2270 | |
| }, | |
| { | |
| "epoch": 1.1046511627906976, | |
| "grad_norm": 4.194492340087891, | |
| "learning_rate": 7.326530553783243e-05, | |
| "loss": 1.1911, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 1.1094961240310077, | |
| "grad_norm": 4.090687274932861, | |
| "learning_rate": 7.287036263120425e-05, | |
| "loss": 1.1692, | |
| "step": 2290 | |
| }, | |
| { | |
| "epoch": 1.1143410852713178, | |
| "grad_norm": 4.440927028656006, | |
| "learning_rate": 7.247499343958621e-05, | |
| "loss": 1.1881, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.119186046511628, | |
| "grad_norm": 4.5461745262146, | |
| "learning_rate": 7.207921421505724e-05, | |
| "loss": 1.1476, | |
| "step": 2310 | |
| }, | |
| { | |
| "epoch": 1.124031007751938, | |
| "grad_norm": 4.559352874755859, | |
| "learning_rate": 7.168304122655113e-05, | |
| "loss": 1.183, | |
| "step": 2320 | |
| }, | |
| { | |
| "epoch": 1.128875968992248, | |
| "grad_norm": 4.365304470062256, | |
| "learning_rate": 7.128649075918768e-05, | |
| "loss": 1.1699, | |
| "step": 2330 | |
| }, | |
| { | |
| "epoch": 1.1337209302325582, | |
| "grad_norm": 4.1360063552856445, | |
| "learning_rate": 7.088957911360347e-05, | |
| "loss": 1.23, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 1.1385658914728682, | |
| "grad_norm": 4.621219635009766, | |
| "learning_rate": 7.049232260528163e-05, | |
| "loss": 1.2519, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.1434108527131783, | |
| "grad_norm": 3.837965726852417, | |
| "learning_rate": 7.009473756388128e-05, | |
| "loss": 1.1412, | |
| "step": 2360 | |
| }, | |
| { | |
| "epoch": 1.1482558139534884, | |
| "grad_norm": 4.362300872802734, | |
| "learning_rate": 6.969684033256622e-05, | |
| "loss": 1.156, | |
| "step": 2370 | |
| }, | |
| { | |
| "epoch": 1.1531007751937985, | |
| "grad_norm": 4.805346488952637, | |
| "learning_rate": 6.92986472673332e-05, | |
| "loss": 1.1887, | |
| "step": 2380 | |
| }, | |
| { | |
| "epoch": 1.1579457364341086, | |
| "grad_norm": 4.508747100830078, | |
| "learning_rate": 6.890017473633946e-05, | |
| "loss": 1.2109, | |
| "step": 2390 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "grad_norm": 4.3871026039123535, | |
| "learning_rate": 6.850143911923011e-05, | |
| "loss": 1.2054, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.1627906976744187, | |
| "eval_loss": 1.337631344795227, | |
| "eval_runtime": 34.3514, | |
| "eval_samples_per_second": 14.555, | |
| "eval_steps_per_second": 14.555, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.1676356589147288, | |
| "grad_norm": 4.372729301452637, | |
| "learning_rate": 6.81024568064646e-05, | |
| "loss": 1.1381, | |
| "step": 2410 | |
| }, | |
| { | |
| "epoch": 1.1724806201550388, | |
| "grad_norm": 4.620536804199219, | |
| "learning_rate": 6.770324419864309e-05, | |
| "loss": 1.1852, | |
| "step": 2420 | |
| }, | |
| { | |
| "epoch": 1.177325581395349, | |
| "grad_norm": 4.0550312995910645, | |
| "learning_rate": 6.73038177058323e-05, | |
| "loss": 1.2378, | |
| "step": 2430 | |
| }, | |
| { | |
| "epoch": 1.1821705426356588, | |
| "grad_norm": 4.528865814208984, | |
| "learning_rate": 6.690419374689087e-05, | |
| "loss": 1.2158, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 1.187015503875969, | |
| "grad_norm": 4.868921756744385, | |
| "learning_rate": 6.650438874879456e-05, | |
| "loss": 1.1556, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.191860465116279, | |
| "grad_norm": 4.525996208190918, | |
| "learning_rate": 6.61044191459609e-05, | |
| "loss": 1.2004, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 1.196705426356589, | |
| "grad_norm": 4.129622459411621, | |
| "learning_rate": 6.57043013795737e-05, | |
| "loss": 1.1904, | |
| "step": 2470 | |
| }, | |
| { | |
| "epoch": 1.2015503875968991, | |
| "grad_norm": 4.325841903686523, | |
| "learning_rate": 6.530405189690719e-05, | |
| "loss": 1.1473, | |
| "step": 2480 | |
| }, | |
| { | |
| "epoch": 1.2063953488372092, | |
| "grad_norm": 4.778893947601318, | |
| "learning_rate": 6.49036871506499e-05, | |
| "loss": 1.1831, | |
| "step": 2490 | |
| }, | |
| { | |
| "epoch": 1.2112403100775193, | |
| "grad_norm": 5.402483940124512, | |
| "learning_rate": 6.450322359822846e-05, | |
| "loss": 1.1794, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2160852713178294, | |
| "grad_norm": 4.464822292327881, | |
| "learning_rate": 6.410267770113098e-05, | |
| "loss": 1.1906, | |
| "step": 2510 | |
| }, | |
| { | |
| "epoch": 1.2209302325581395, | |
| "grad_norm": 4.59386682510376, | |
| "learning_rate": 6.370206592423045e-05, | |
| "loss": 1.2027, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 1.2257751937984496, | |
| "grad_norm": 4.05305290222168, | |
| "learning_rate": 6.330140473510796e-05, | |
| "loss": 1.1652, | |
| "step": 2530 | |
| }, | |
| { | |
| "epoch": 1.2306201550387597, | |
| "grad_norm": 4.635653018951416, | |
| "learning_rate": 6.29007106033757e-05, | |
| "loss": 1.2091, | |
| "step": 2540 | |
| }, | |
| { | |
| "epoch": 1.2354651162790697, | |
| "grad_norm": 4.434372901916504, | |
| "learning_rate": 6.25e-05, | |
| "loss": 1.2082, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.2354651162790697, | |
| "eval_loss": 1.3322062492370605, | |
| "eval_runtime": 34.4713, | |
| "eval_samples_per_second": 14.505, | |
| "eval_steps_per_second": 14.505, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.2403100775193798, | |
| "grad_norm": 4.956961631774902, | |
| "learning_rate": 6.20992893966243e-05, | |
| "loss": 1.1897, | |
| "step": 2560 | |
| }, | |
| { | |
| "epoch": 1.24515503875969, | |
| "grad_norm": 3.7832202911376953, | |
| "learning_rate": 6.169859526489204e-05, | |
| "loss": 1.1915, | |
| "step": 2570 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 4.197141647338867, | |
| "learning_rate": 6.129793407576955e-05, | |
| "loss": 1.161, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 1.25484496124031, | |
| "grad_norm": 5.222776889801025, | |
| "learning_rate": 6.089732229886904e-05, | |
| "loss": 1.1943, | |
| "step": 2590 | |
| }, | |
| { | |
| "epoch": 1.2596899224806202, | |
| "grad_norm": 4.98862361907959, | |
| "learning_rate": 6.049677640177155e-05, | |
| "loss": 1.2317, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.2645348837209303, | |
| "grad_norm": 4.635793209075928, | |
| "learning_rate": 6.00963128493501e-05, | |
| "loss": 1.1987, | |
| "step": 2610 | |
| }, | |
| { | |
| "epoch": 1.2693798449612403, | |
| "grad_norm": 4.15401029586792, | |
| "learning_rate": 5.969594810309284e-05, | |
| "loss": 1.2063, | |
| "step": 2620 | |
| }, | |
| { | |
| "epoch": 1.2742248062015504, | |
| "grad_norm": 4.845739841461182, | |
| "learning_rate": 5.929569862042631e-05, | |
| "loss": 1.2207, | |
| "step": 2630 | |
| }, | |
| { | |
| "epoch": 1.2790697674418605, | |
| "grad_norm": 4.469569206237793, | |
| "learning_rate": 5.889558085403911e-05, | |
| "loss": 1.1866, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 1.2839147286821706, | |
| "grad_norm": 4.760675430297852, | |
| "learning_rate": 5.849561125120545e-05, | |
| "loss": 1.1932, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.2887596899224807, | |
| "grad_norm": 4.755754470825195, | |
| "learning_rate": 5.809580625310912e-05, | |
| "loss": 1.0994, | |
| "step": 2660 | |
| }, | |
| { | |
| "epoch": 1.2936046511627908, | |
| "grad_norm": 4.62287712097168, | |
| "learning_rate": 5.769618229416773e-05, | |
| "loss": 1.1789, | |
| "step": 2670 | |
| }, | |
| { | |
| "epoch": 1.2984496124031009, | |
| "grad_norm": 4.824830055236816, | |
| "learning_rate": 5.7296755801356926e-05, | |
| "loss": 1.2136, | |
| "step": 2680 | |
| }, | |
| { | |
| "epoch": 1.3032945736434107, | |
| "grad_norm": 4.84926700592041, | |
| "learning_rate": 5.6897543193535414e-05, | |
| "loss": 1.2006, | |
| "step": 2690 | |
| }, | |
| { | |
| "epoch": 1.308139534883721, | |
| "grad_norm": 4.716812610626221, | |
| "learning_rate": 5.649856088076989e-05, | |
| "loss": 1.161, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.308139534883721, | |
| "eval_loss": 1.3203985691070557, | |
| "eval_runtime": 37.0313, | |
| "eval_samples_per_second": 13.502, | |
| "eval_steps_per_second": 13.502, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.312984496124031, | |
| "grad_norm": 4.2137651443481445, | |
| "learning_rate": 5.609982526366054e-05, | |
| "loss": 1.167, | |
| "step": 2710 | |
| }, | |
| { | |
| "epoch": 1.3178294573643412, | |
| "grad_norm": 4.377100944519043, | |
| "learning_rate": 5.570135273266683e-05, | |
| "loss": 1.1736, | |
| "step": 2720 | |
| }, | |
| { | |
| "epoch": 1.322674418604651, | |
| "grad_norm": 4.399763584136963, | |
| "learning_rate": 5.53031596674338e-05, | |
| "loss": 1.2068, | |
| "step": 2730 | |
| }, | |
| { | |
| "epoch": 1.3275193798449614, | |
| "grad_norm": 4.772261619567871, | |
| "learning_rate": 5.490526243611873e-05, | |
| "loss": 1.1748, | |
| "step": 2740 | |
| }, | |
| { | |
| "epoch": 1.3323643410852712, | |
| "grad_norm": 4.910473346710205, | |
| "learning_rate": 5.450767739471837e-05, | |
| "loss": 1.1514, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.3372093023255813, | |
| "grad_norm": 4.758593559265137, | |
| "learning_rate": 5.411042088639655e-05, | |
| "loss": 1.1768, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 1.3420542635658914, | |
| "grad_norm": 4.396140098571777, | |
| "learning_rate": 5.371350924081234e-05, | |
| "loss": 1.2153, | |
| "step": 2770 | |
| }, | |
| { | |
| "epoch": 1.3468992248062015, | |
| "grad_norm": 4.715628147125244, | |
| "learning_rate": 5.331695877344888e-05, | |
| "loss": 1.1453, | |
| "step": 2780 | |
| }, | |
| { | |
| "epoch": 1.3517441860465116, | |
| "grad_norm": 4.38018798828125, | |
| "learning_rate": 5.292078578494275e-05, | |
| "loss": 1.1688, | |
| "step": 2790 | |
| }, | |
| { | |
| "epoch": 1.3565891472868217, | |
| "grad_norm": 4.341307163238525, | |
| "learning_rate": 5.2525006560413816e-05, | |
| "loss": 1.1549, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.3614341085271318, | |
| "grad_norm": 4.443046569824219, | |
| "learning_rate": 5.212963736879578e-05, | |
| "loss": 1.1985, | |
| "step": 2810 | |
| }, | |
| { | |
| "epoch": 1.3662790697674418, | |
| "grad_norm": 4.29320764541626, | |
| "learning_rate": 5.173469446216757e-05, | |
| "loss": 1.1957, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 1.371124031007752, | |
| "grad_norm": 4.762570858001709, | |
| "learning_rate": 5.134019407508521e-05, | |
| "loss": 1.1626, | |
| "step": 2830 | |
| }, | |
| { | |
| "epoch": 1.375968992248062, | |
| "grad_norm": 4.549506664276123, | |
| "learning_rate": 5.0946152423914456e-05, | |
| "loss": 1.1377, | |
| "step": 2840 | |
| }, | |
| { | |
| "epoch": 1.380813953488372, | |
| "grad_norm": 4.547486782073975, | |
| "learning_rate": 5.0552585706164246e-05, | |
| "loss": 1.1764, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.380813953488372, | |
| "eval_loss": 1.3321481943130493, | |
| "eval_runtime": 37.0386, | |
| "eval_samples_per_second": 13.499, | |
| "eval_steps_per_second": 13.499, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.3856589147286822, | |
| "grad_norm": 4.949843883514404, | |
| "learning_rate": 5.015951009982081e-05, | |
| "loss": 1.1557, | |
| "step": 2860 | |
| }, | |
| { | |
| "epoch": 1.3905038759689923, | |
| "grad_norm": 5.2824602127075195, | |
| "learning_rate": 4.976694176268278e-05, | |
| "loss": 1.2206, | |
| "step": 2870 | |
| }, | |
| { | |
| "epoch": 1.3953488372093024, | |
| "grad_norm": 4.623624801635742, | |
| "learning_rate": 4.937489683169692e-05, | |
| "loss": 1.2192, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 1.4001937984496124, | |
| "grad_norm": 4.3337626457214355, | |
| "learning_rate": 4.8983391422294786e-05, | |
| "loss": 1.1753, | |
| "step": 2890 | |
| }, | |
| { | |
| "epoch": 1.4050387596899225, | |
| "grad_norm": 5.181596755981445, | |
| "learning_rate": 4.8592441627730355e-05, | |
| "loss": 1.2189, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.4098837209302326, | |
| "grad_norm": 4.476628303527832, | |
| "learning_rate": 4.820206351841842e-05, | |
| "loss": 1.2062, | |
| "step": 2910 | |
| }, | |
| { | |
| "epoch": 1.4147286821705427, | |
| "grad_norm": 4.46708869934082, | |
| "learning_rate": 4.781227314127405e-05, | |
| "loss": 1.1427, | |
| "step": 2920 | |
| }, | |
| { | |
| "epoch": 1.4195736434108528, | |
| "grad_norm": 4.566659450531006, | |
| "learning_rate": 4.7423086519052966e-05, | |
| "loss": 1.158, | |
| "step": 2930 | |
| }, | |
| { | |
| "epoch": 1.4244186046511627, | |
| "grad_norm": 4.646278381347656, | |
| "learning_rate": 4.703451964969287e-05, | |
| "loss": 1.1786, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 1.429263565891473, | |
| "grad_norm": 4.6226277351379395, | |
| "learning_rate": 4.66465885056558e-05, | |
| "loss": 1.2042, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.4341085271317828, | |
| "grad_norm": 4.581994533538818, | |
| "learning_rate": 4.62593090332717e-05, | |
| "loss": 1.1456, | |
| "step": 2960 | |
| }, | |
| { | |
| "epoch": 1.4389534883720931, | |
| "grad_norm": 4.573033332824707, | |
| "learning_rate": 4.587269715208281e-05, | |
| "loss": 1.2082, | |
| "step": 2970 | |
| }, | |
| { | |
| "epoch": 1.443798449612403, | |
| "grad_norm": 4.8347649574279785, | |
| "learning_rate": 4.5486768754189305e-05, | |
| "loss": 1.2103, | |
| "step": 2980 | |
| }, | |
| { | |
| "epoch": 1.4486434108527133, | |
| "grad_norm": 4.730405330657959, | |
| "learning_rate": 4.510153970359606e-05, | |
| "loss": 1.1868, | |
| "step": 2990 | |
| }, | |
| { | |
| "epoch": 1.4534883720930232, | |
| "grad_norm": 4.4655561447143555, | |
| "learning_rate": 4.4717025835560476e-05, | |
| "loss": 1.1379, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4534883720930232, | |
| "eval_loss": 1.3219256401062012, | |
| "eval_runtime": 34.7991, | |
| "eval_samples_per_second": 14.368, | |
| "eval_steps_per_second": 14.368, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4583333333333333, | |
| "grad_norm": 4.40006160736084, | |
| "learning_rate": 4.433324295594166e-05, | |
| "loss": 1.1494, | |
| "step": 3010 | |
| }, | |
| { | |
| "epoch": 1.4631782945736433, | |
| "grad_norm": 4.606269836425781, | |
| "learning_rate": 4.3950206840550585e-05, | |
| "loss": 1.1849, | |
| "step": 3020 | |
| }, | |
| { | |
| "epoch": 1.4680232558139534, | |
| "grad_norm": 4.411858558654785, | |
| "learning_rate": 4.3567933234501746e-05, | |
| "loss": 1.1973, | |
| "step": 3030 | |
| }, | |
| { | |
| "epoch": 1.4728682170542635, | |
| "grad_norm": 4.655940055847168, | |
| "learning_rate": 4.318643785156579e-05, | |
| "loss": 1.146, | |
| "step": 3040 | |
| }, | |
| { | |
| "epoch": 1.4777131782945736, | |
| "grad_norm": 4.7272233963012695, | |
| "learning_rate": 4.280573637352371e-05, | |
| "loss": 1.1986, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.4825581395348837, | |
| "grad_norm": 4.558550834655762, | |
| "learning_rate": 4.242584444952216e-05, | |
| "loss": 1.1522, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 1.4874031007751938, | |
| "grad_norm": 4.483912467956543, | |
| "learning_rate": 4.204677769543019e-05, | |
| "loss": 1.132, | |
| "step": 3070 | |
| }, | |
| { | |
| "epoch": 1.4922480620155039, | |
| "grad_norm": 4.158421516418457, | |
| "learning_rate": 4.16685516931974e-05, | |
| "loss": 1.1468, | |
| "step": 3080 | |
| }, | |
| { | |
| "epoch": 1.497093023255814, | |
| "grad_norm": 5.205226898193359, | |
| "learning_rate": 4.1291181990213286e-05, | |
| "loss": 1.238, | |
| "step": 3090 | |
| }, | |
| { | |
| "epoch": 1.501937984496124, | |
| "grad_norm": 4.967478275299072, | |
| "learning_rate": 4.0914684098668286e-05, | |
| "loss": 1.1865, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.5067829457364341, | |
| "grad_norm": 4.679478645324707, | |
| "learning_rate": 4.053907349491608e-05, | |
| "loss": 1.1713, | |
| "step": 3110 | |
| }, | |
| { | |
| "epoch": 1.5116279069767442, | |
| "grad_norm": 4.585414886474609, | |
| "learning_rate": 4.016436561883746e-05, | |
| "loss": 1.1352, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 1.5164728682170543, | |
| "grad_norm": 4.369693279266357, | |
| "learning_rate": 3.979057587320554e-05, | |
| "loss": 1.1918, | |
| "step": 3130 | |
| }, | |
| { | |
| "epoch": 1.5213178294573644, | |
| "grad_norm": 5.233042240142822, | |
| "learning_rate": 3.941771962305274e-05, | |
| "loss": 1.19, | |
| "step": 3140 | |
| }, | |
| { | |
| "epoch": 1.5261627906976745, | |
| "grad_norm": 4.907647132873535, | |
| "learning_rate": 3.9045812195039125e-05, | |
| "loss": 1.1569, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.5261627906976745, | |
| "eval_loss": 1.3149200677871704, | |
| "eval_runtime": 34.7411, | |
| "eval_samples_per_second": 14.392, | |
| "eval_steps_per_second": 14.392, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.5310077519379846, | |
| "grad_norm": 4.570740222930908, | |
| "learning_rate": 3.8674868876822395e-05, | |
| "loss": 1.1619, | |
| "step": 3160 | |
| }, | |
| { | |
| "epoch": 1.5358527131782944, | |
| "grad_norm": 4.761332035064697, | |
| "learning_rate": 3.83049049164295e-05, | |
| "loss": 1.1719, | |
| "step": 3170 | |
| }, | |
| { | |
| "epoch": 1.5406976744186047, | |
| "grad_norm": 4.39130973815918, | |
| "learning_rate": 3.793593552162978e-05, | |
| "loss": 1.1727, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 1.5455426356589146, | |
| "grad_norm": 4.595332145690918, | |
| "learning_rate": 3.75679758593099e-05, | |
| "loss": 1.1708, | |
| "step": 3190 | |
| }, | |
| { | |
| "epoch": 1.550387596899225, | |
| "grad_norm": 4.71079683303833, | |
| "learning_rate": 3.720104105485039e-05, | |
| "loss": 1.1967, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.5552325581395348, | |
| "grad_norm": 4.250856876373291, | |
| "learning_rate": 3.6835146191503885e-05, | |
| "loss": 1.1726, | |
| "step": 3210 | |
| }, | |
| { | |
| "epoch": 1.560077519379845, | |
| "grad_norm": 4.2891364097595215, | |
| "learning_rate": 3.647030630977508e-05, | |
| "loss": 1.164, | |
| "step": 3220 | |
| }, | |
| { | |
| "epoch": 1.564922480620155, | |
| "grad_norm": 4.25226354598999, | |
| "learning_rate": 3.6106536406802524e-05, | |
| "loss": 1.1522, | |
| "step": 3230 | |
| }, | |
| { | |
| "epoch": 1.5697674418604652, | |
| "grad_norm": 4.491365909576416, | |
| "learning_rate": 3.5743851435742176e-05, | |
| "loss": 1.1693, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 1.574612403100775, | |
| "grad_norm": 4.436107158660889, | |
| "learning_rate": 3.538226630515262e-05, | |
| "loss": 1.2205, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.5794573643410854, | |
| "grad_norm": 4.75892972946167, | |
| "learning_rate": 3.502179587838238e-05, | |
| "loss": 1.1412, | |
| "step": 3260 | |
| }, | |
| { | |
| "epoch": 1.5843023255813953, | |
| "grad_norm": 4.313481330871582, | |
| "learning_rate": 3.46624549729588e-05, | |
| "loss": 1.1621, | |
| "step": 3270 | |
| }, | |
| { | |
| "epoch": 1.5891472868217056, | |
| "grad_norm": 4.274176120758057, | |
| "learning_rate": 3.430425835997908e-05, | |
| "loss": 1.1676, | |
| "step": 3280 | |
| }, | |
| { | |
| "epoch": 1.5939922480620154, | |
| "grad_norm": 4.709112644195557, | |
| "learning_rate": 3.394722076350302e-05, | |
| "loss": 1.1514, | |
| "step": 3290 | |
| }, | |
| { | |
| "epoch": 1.5988372093023255, | |
| "grad_norm": 4.2664079666137695, | |
| "learning_rate": 3.359135685994781e-05, | |
| "loss": 1.2006, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.5988372093023255, | |
| "eval_loss": 1.308353066444397, | |
| "eval_runtime": 36.1139, | |
| "eval_samples_per_second": 13.845, | |
| "eval_steps_per_second": 13.845, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.6036821705426356, | |
| "grad_norm": 4.822900772094727, | |
| "learning_rate": 3.3236681277484654e-05, | |
| "loss": 1.1643, | |
| "step": 3310 | |
| }, | |
| { | |
| "epoch": 1.6085271317829457, | |
| "grad_norm": 4.587668418884277, | |
| "learning_rate": 3.2883208595437584e-05, | |
| "loss": 1.1914, | |
| "step": 3320 | |
| }, | |
| { | |
| "epoch": 1.6133720930232558, | |
| "grad_norm": 4.759604454040527, | |
| "learning_rate": 3.2530953343684136e-05, | |
| "loss": 1.1826, | |
| "step": 3330 | |
| }, | |
| { | |
| "epoch": 1.6182170542635659, | |
| "grad_norm": 4.67030668258667, | |
| "learning_rate": 3.217993000205799e-05, | |
| "loss": 1.1793, | |
| "step": 3340 | |
| }, | |
| { | |
| "epoch": 1.623062015503876, | |
| "grad_norm": 4.612665176391602, | |
| "learning_rate": 3.1830152999753903e-05, | |
| "loss": 1.198, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.627906976744186, | |
| "grad_norm": 4.420239448547363, | |
| "learning_rate": 3.148163671473439e-05, | |
| "loss": 1.1513, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 1.6327519379844961, | |
| "grad_norm": 4.726665496826172, | |
| "learning_rate": 3.113439547313892e-05, | |
| "loss": 1.145, | |
| "step": 3370 | |
| }, | |
| { | |
| "epoch": 1.6375968992248062, | |
| "grad_norm": 5.277156352996826, | |
| "learning_rate": 3.0788443548694874e-05, | |
| "loss": 1.1698, | |
| "step": 3380 | |
| }, | |
| { | |
| "epoch": 1.6424418604651163, | |
| "grad_norm": 4.7339630126953125, | |
| "learning_rate": 3.0443795162130876e-05, | |
| "loss": 1.1492, | |
| "step": 3390 | |
| }, | |
| { | |
| "epoch": 1.6472868217054264, | |
| "grad_norm": 4.68505334854126, | |
| "learning_rate": 3.0100464480592185e-05, | |
| "loss": 1.158, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.6521317829457365, | |
| "grad_norm": 5.142575740814209, | |
| "learning_rate": 2.9758465617058404e-05, | |
| "loss": 1.224, | |
| "step": 3410 | |
| }, | |
| { | |
| "epoch": 1.6569767441860463, | |
| "grad_norm": 4.73928165435791, | |
| "learning_rate": 2.9417812629763285e-05, | |
| "loss": 1.1897, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 1.6618217054263567, | |
| "grad_norm": 4.277917385101318, | |
| "learning_rate": 2.9078519521616894e-05, | |
| "loss": 1.1559, | |
| "step": 3430 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 4.362334251403809, | |
| "learning_rate": 2.8740600239630002e-05, | |
| "loss": 1.1269, | |
| "step": 3440 | |
| }, | |
| { | |
| "epoch": 1.6715116279069768, | |
| "grad_norm": 4.715338706970215, | |
| "learning_rate": 2.8404068674340714e-05, | |
| "loss": 1.1224, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.6715116279069768, | |
| "eval_loss": 1.3105417490005493, | |
| "eval_runtime": 36.9202, | |
| "eval_samples_per_second": 13.543, | |
| "eval_steps_per_second": 13.543, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.6763565891472867, | |
| "grad_norm": 4.6475138664245605, | |
| "learning_rate": 2.80689386592436e-05, | |
| "loss": 1.1789, | |
| "step": 3460 | |
| }, | |
| { | |
| "epoch": 1.681201550387597, | |
| "grad_norm": 4.647360324859619, | |
| "learning_rate": 2.7735223970220955e-05, | |
| "loss": 1.1575, | |
| "step": 3470 | |
| }, | |
| { | |
| "epoch": 1.6860465116279069, | |
| "grad_norm": 5.539259433746338, | |
| "learning_rate": 2.7402938324976576e-05, | |
| "loss": 1.1573, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 1.6908914728682172, | |
| "grad_norm": 5.069607257843018, | |
| "learning_rate": 2.70720953824719e-05, | |
| "loss": 1.2175, | |
| "step": 3490 | |
| }, | |
| { | |
| "epoch": 1.695736434108527, | |
| "grad_norm": 4.86273193359375, | |
| "learning_rate": 2.674270874236441e-05, | |
| "loss": 1.1546, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.7005813953488373, | |
| "grad_norm": 4.686957359313965, | |
| "learning_rate": 2.64147919444488e-05, | |
| "loss": 1.1283, | |
| "step": 3510 | |
| }, | |
| { | |
| "epoch": 1.7054263565891472, | |
| "grad_norm": 4.801562309265137, | |
| "learning_rate": 2.6088358468100247e-05, | |
| "loss": 1.1535, | |
| "step": 3520 | |
| }, | |
| { | |
| "epoch": 1.7102713178294575, | |
| "grad_norm": 4.969239711761475, | |
| "learning_rate": 2.5763421731720435e-05, | |
| "loss": 1.1932, | |
| "step": 3530 | |
| }, | |
| { | |
| "epoch": 1.7151162790697674, | |
| "grad_norm": 4.972625255584717, | |
| "learning_rate": 2.5439995092185892e-05, | |
| "loss": 1.2001, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 1.7199612403100775, | |
| "grad_norm": 4.53269624710083, | |
| "learning_rate": 2.5118091844299e-05, | |
| "loss": 1.1269, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 1.7248062015503876, | |
| "grad_norm": 4.459876537322998, | |
| "learning_rate": 2.479772522024147e-05, | |
| "loss": 1.1612, | |
| "step": 3560 | |
| }, | |
| { | |
| "epoch": 1.7296511627906976, | |
| "grad_norm": 4.202701091766357, | |
| "learning_rate": 2.4478908389030427e-05, | |
| "loss": 1.1336, | |
| "step": 3570 | |
| }, | |
| { | |
| "epoch": 1.7344961240310077, | |
| "grad_norm": 4.356159210205078, | |
| "learning_rate": 2.41616544559771e-05, | |
| "loss": 1.1813, | |
| "step": 3580 | |
| }, | |
| { | |
| "epoch": 1.7393410852713178, | |
| "grad_norm": 4.778804779052734, | |
| "learning_rate": 2.3845976462148033e-05, | |
| "loss": 1.1568, | |
| "step": 3590 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "grad_norm": 4.015143871307373, | |
| "learning_rate": 2.3531887383829157e-05, | |
| "loss": 1.1537, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.744186046511628, | |
| "eval_loss": 1.303134560585022, | |
| "eval_runtime": 35.466, | |
| "eval_samples_per_second": 14.098, | |
| "eval_steps_per_second": 14.098, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.749031007751938, | |
| "grad_norm": 4.870272636413574, | |
| "learning_rate": 2.3219400131992273e-05, | |
| "loss": 1.1905, | |
| "step": 3610 | |
| }, | |
| { | |
| "epoch": 1.753875968992248, | |
| "grad_norm": 4.328778266906738, | |
| "learning_rate": 2.2908527551764404e-05, | |
| "loss": 1.1212, | |
| "step": 3620 | |
| }, | |
| { | |
| "epoch": 1.7587209302325582, | |
| "grad_norm": 4.691504955291748, | |
| "learning_rate": 2.259928242189966e-05, | |
| "loss": 1.1463, | |
| "step": 3630 | |
| }, | |
| { | |
| "epoch": 1.7635658914728682, | |
| "grad_norm": 4.509458065032959, | |
| "learning_rate": 2.2291677454254136e-05, | |
| "loss": 1.1534, | |
| "step": 3640 | |
| }, | |
| { | |
| "epoch": 1.7684108527131783, | |
| "grad_norm": 4.431001663208008, | |
| "learning_rate": 2.1985725293263237e-05, | |
| "loss": 1.1404, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.7732558139534884, | |
| "grad_norm": 4.709799766540527, | |
| "learning_rate": 2.1681438515421953e-05, | |
| "loss": 1.1536, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 1.7781007751937985, | |
| "grad_norm": 4.597837448120117, | |
| "learning_rate": 2.1378829628767965e-05, | |
| "loss": 1.1385, | |
| "step": 3670 | |
| }, | |
| { | |
| "epoch": 1.7829457364341086, | |
| "grad_norm": 4.932100296020508, | |
| "learning_rate": 2.1077911072367317e-05, | |
| "loss": 1.112, | |
| "step": 3680 | |
| }, | |
| { | |
| "epoch": 1.7877906976744184, | |
| "grad_norm": 4.695112705230713, | |
| "learning_rate": 2.077869521580325e-05, | |
| "loss": 1.1437, | |
| "step": 3690 | |
| }, | |
| { | |
| "epoch": 1.7926356589147288, | |
| "grad_norm": 4.614483833312988, | |
| "learning_rate": 2.0481194358667695e-05, | |
| "loss": 1.1403, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.7974806201550386, | |
| "grad_norm": 4.5487141609191895, | |
| "learning_rate": 2.018542073005567e-05, | |
| "loss": 1.2048, | |
| "step": 3710 | |
| }, | |
| { | |
| "epoch": 1.802325581395349, | |
| "grad_norm": 4.563633441925049, | |
| "learning_rate": 1.9891386488062538e-05, | |
| "loss": 1.1905, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 1.8071705426356588, | |
| "grad_norm": 4.88431978225708, | |
| "learning_rate": 1.959910371928436e-05, | |
| "loss": 1.1999, | |
| "step": 3730 | |
| }, | |
| { | |
| "epoch": 1.812015503875969, | |
| "grad_norm": 4.790411472320557, | |
| "learning_rate": 1.930858443832096e-05, | |
| "loss": 1.1908, | |
| "step": 3740 | |
| }, | |
| { | |
| "epoch": 1.816860465116279, | |
| "grad_norm": 4.809146404266357, | |
| "learning_rate": 1.90198405872821e-05, | |
| "loss": 1.1942, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.816860465116279, | |
| "eval_loss": 1.3001154661178589, | |
| "eval_runtime": 35.3757, | |
| "eval_samples_per_second": 14.134, | |
| "eval_steps_per_second": 14.134, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.8217054263565893, | |
| "grad_norm": 4.622406959533691, | |
| "learning_rate": 1.8732884035296582e-05, | |
| "loss": 1.171, | |
| "step": 3760 | |
| }, | |
| { | |
| "epoch": 1.8265503875968991, | |
| "grad_norm": 4.658726692199707, | |
| "learning_rate": 1.844772657802428e-05, | |
| "loss": 1.1856, | |
| "step": 3770 | |
| }, | |
| { | |
| "epoch": 1.8313953488372094, | |
| "grad_norm": 4.213481903076172, | |
| "learning_rate": 1.8164379937171382e-05, | |
| "loss": 1.1396, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 1.8362403100775193, | |
| "grad_norm": 4.337812900543213, | |
| "learning_rate": 1.7882855760008547e-05, | |
| "loss": 1.1649, | |
| "step": 3790 | |
| }, | |
| { | |
| "epoch": 1.8410852713178296, | |
| "grad_norm": 4.894495010375977, | |
| "learning_rate": 1.760316561889203e-05, | |
| "loss": 1.1902, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.8459302325581395, | |
| "grad_norm": 4.742762565612793, | |
| "learning_rate": 1.7325321010788034e-05, | |
| "loss": 1.2039, | |
| "step": 3810 | |
| }, | |
| { | |
| "epoch": 1.8507751937984496, | |
| "grad_norm": 4.0735859870910645, | |
| "learning_rate": 1.7049333356800167e-05, | |
| "loss": 1.1367, | |
| "step": 3820 | |
| }, | |
| { | |
| "epoch": 1.8556201550387597, | |
| "grad_norm": 4.980224609375, | |
| "learning_rate": 1.6775214001699914e-05, | |
| "loss": 1.1802, | |
| "step": 3830 | |
| }, | |
| { | |
| "epoch": 1.8604651162790697, | |
| "grad_norm": 4.273513317108154, | |
| "learning_rate": 1.6502974213460316e-05, | |
| "loss": 1.179, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 1.8653100775193798, | |
| "grad_norm": 4.441263198852539, | |
| "learning_rate": 1.623262518279279e-05, | |
| "loss": 1.1551, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.87015503875969, | |
| "grad_norm": 4.667087554931641, | |
| "learning_rate": 1.596417802268707e-05, | |
| "loss": 1.142, | |
| "step": 3860 | |
| }, | |
| { | |
| "epoch": 1.875, | |
| "grad_norm": 4.452362537384033, | |
| "learning_rate": 1.5697643767954488e-05, | |
| "loss": 1.1323, | |
| "step": 3870 | |
| }, | |
| { | |
| "epoch": 1.87984496124031, | |
| "grad_norm": 4.532679557800293, | |
| "learning_rate": 1.543303337477432e-05, | |
| "loss": 1.1637, | |
| "step": 3880 | |
| }, | |
| { | |
| "epoch": 1.8846899224806202, | |
| "grad_norm": 4.801875114440918, | |
| "learning_rate": 1.517035772024343e-05, | |
| "loss": 1.1405, | |
| "step": 3890 | |
| }, | |
| { | |
| "epoch": 1.8895348837209303, | |
| "grad_norm": 4.448420524597168, | |
| "learning_rate": 1.49096276019291e-05, | |
| "loss": 1.1664, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.8895348837209303, | |
| "eval_loss": 1.2978554964065552, | |
| "eval_runtime": 35.0871, | |
| "eval_samples_per_second": 14.25, | |
| "eval_steps_per_second": 14.25, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.8943798449612403, | |
| "grad_norm": 4.431020736694336, | |
| "learning_rate": 1.4650853737425327e-05, | |
| "loss": 1.1702, | |
| "step": 3910 | |
| }, | |
| { | |
| "epoch": 1.8992248062015504, | |
| "grad_norm": 4.734516143798828, | |
| "learning_rate": 1.4394046763912122e-05, | |
| "loss": 1.1383, | |
| "step": 3920 | |
| }, | |
| { | |
| "epoch": 1.9040697674418605, | |
| "grad_norm": 4.348439693450928, | |
| "learning_rate": 1.413921723771832e-05, | |
| "loss": 1.1701, | |
| "step": 3930 | |
| }, | |
| { | |
| "epoch": 1.9089147286821704, | |
| "grad_norm": 4.6349263191223145, | |
| "learning_rate": 1.3886375633887665e-05, | |
| "loss": 1.1877, | |
| "step": 3940 | |
| }, | |
| { | |
| "epoch": 1.9137596899224807, | |
| "grad_norm": 4.767696857452393, | |
| "learning_rate": 1.3635532345748137e-05, | |
| "loss": 1.1573, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.9186046511627906, | |
| "grad_norm": 4.602748394012451, | |
| "learning_rate": 1.3386697684484853e-05, | |
| "loss": 1.1472, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 1.9234496124031009, | |
| "grad_norm": 4.704031467437744, | |
| "learning_rate": 1.3139881878716107e-05, | |
| "loss": 1.1425, | |
| "step": 3970 | |
| }, | |
| { | |
| "epoch": 1.9282945736434107, | |
| "grad_norm": 4.546751022338867, | |
| "learning_rate": 1.2895095074072986e-05, | |
| "loss": 1.1796, | |
| "step": 3980 | |
| }, | |
| { | |
| "epoch": 1.933139534883721, | |
| "grad_norm": 4.875455379486084, | |
| "learning_rate": 1.2652347332782227e-05, | |
| "loss": 1.1565, | |
| "step": 3990 | |
| }, | |
| { | |
| "epoch": 1.937984496124031, | |
| "grad_norm": 4.274509429931641, | |
| "learning_rate": 1.2411648633252719e-05, | |
| "loss": 1.1479, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.9428294573643412, | |
| "grad_norm": 5.224791049957275, | |
| "learning_rate": 1.2173008869665241e-05, | |
| "loss": 1.1812, | |
| "step": 4010 | |
| }, | |
| { | |
| "epoch": 1.947674418604651, | |
| "grad_norm": 4.49781608581543, | |
| "learning_rate": 1.1936437851565791e-05, | |
| "loss": 1.0814, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 1.9525193798449614, | |
| "grad_norm": 4.98948335647583, | |
| "learning_rate": 1.1701945303462337e-05, | |
| "loss": 1.135, | |
| "step": 4030 | |
| }, | |
| { | |
| "epoch": 1.9573643410852712, | |
| "grad_norm": 4.684279918670654, | |
| "learning_rate": 1.146954086442508e-05, | |
| "loss": 1.139, | |
| "step": 4040 | |
| }, | |
| { | |
| "epoch": 1.9622093023255816, | |
| "grad_norm": 4.083446502685547, | |
| "learning_rate": 1.1239234087690252e-05, | |
| "loss": 1.1605, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.9622093023255816, | |
| "eval_loss": 1.3004401922225952, | |
| "eval_runtime": 36.7898, | |
| "eval_samples_per_second": 13.591, | |
| "eval_steps_per_second": 13.591, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.9670542635658914, | |
| "grad_norm": 4.628580093383789, | |
| "learning_rate": 1.1011034440267395e-05, | |
| "loss": 1.1282, | |
| "step": 4060 | |
| }, | |
| { | |
| "epoch": 1.9718992248062015, | |
| "grad_norm": 4.7327399253845215, | |
| "learning_rate": 1.078495130255023e-05, | |
| "loss": 1.1448, | |
| "step": 4070 | |
| }, | |
| { | |
| "epoch": 1.9767441860465116, | |
| "grad_norm": 4.666077136993408, | |
| "learning_rate": 1.0560993967931004e-05, | |
| "loss": 1.165, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 1.9815891472868217, | |
| "grad_norm": 4.282505989074707, | |
| "learning_rate": 1.0339171642418585e-05, | |
| "loss": 1.1501, | |
| "step": 4090 | |
| }, | |
| { | |
| "epoch": 1.9864341085271318, | |
| "grad_norm": 5.030765056610107, | |
| "learning_rate": 1.0119493444259963e-05, | |
| "loss": 1.1606, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.9912790697674418, | |
| "grad_norm": 4.556647777557373, | |
| "learning_rate": 9.901968403565428e-06, | |
| "loss": 1.1273, | |
| "step": 4110 | |
| }, | |
| { | |
| "epoch": 1.996124031007752, | |
| "grad_norm": 4.7390289306640625, | |
| "learning_rate": 9.686605461937441e-06, | |
| "loss": 1.1746, | |
| "step": 4120 | |
| }, | |
| { | |
| "epoch": 2.000968992248062, | |
| "grad_norm": 4.468574523925781, | |
| "learning_rate": 9.473413472102982e-06, | |
| "loss": 1.1559, | |
| "step": 4130 | |
| }, | |
| { | |
| "epoch": 2.005813953488372, | |
| "grad_norm": 4.097834587097168, | |
| "learning_rate": 9.262401197549744e-06, | |
| "loss": 1.0378, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 2.010658914728682, | |
| "grad_norm": 4.449402809143066, | |
| "learning_rate": 9.05357731216587e-06, | |
| "loss": 1.0429, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.0155038759689923, | |
| "grad_norm": 4.115217685699463, | |
| "learning_rate": 8.846950399883368e-06, | |
| "loss": 1.0474, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 2.020348837209302, | |
| "grad_norm": 4.607194423675537, | |
| "learning_rate": 8.64252895432531e-06, | |
| "loss": 1.053, | |
| "step": 4170 | |
| }, | |
| { | |
| "epoch": 2.0251937984496124, | |
| "grad_norm": 4.8986029624938965, | |
| "learning_rate": 8.440321378456656e-06, | |
| "loss": 1.0119, | |
| "step": 4180 | |
| }, | |
| { | |
| "epoch": 2.0300387596899223, | |
| "grad_norm": 4.387269973754883, | |
| "learning_rate": 8.240335984238844e-06, | |
| "loss": 0.9652, | |
| "step": 4190 | |
| }, | |
| { | |
| "epoch": 2.0348837209302326, | |
| "grad_norm": 4.39861536026001, | |
| "learning_rate": 8.042580992288163e-06, | |
| "loss": 1.0401, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.0348837209302326, | |
| "eval_loss": 1.3077232837677002, | |
| "eval_runtime": 36.5162, | |
| "eval_samples_per_second": 13.693, | |
| "eval_steps_per_second": 13.693, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.0397286821705425, | |
| "grad_norm": 4.842596054077148, | |
| "learning_rate": 7.847064531537774e-06, | |
| "loss": 1.0324, | |
| "step": 4210 | |
| }, | |
| { | |
| "epoch": 2.044573643410853, | |
| "grad_norm": 4.725849628448486, | |
| "learning_rate": 7.653794638903574e-06, | |
| "loss": 1.06, | |
| "step": 4220 | |
| }, | |
| { | |
| "epoch": 2.0494186046511627, | |
| "grad_norm": 4.722954750061035, | |
| "learning_rate": 7.462779258953875e-06, | |
| "loss": 1.0461, | |
| "step": 4230 | |
| }, | |
| { | |
| "epoch": 2.054263565891473, | |
| "grad_norm": 4.449377536773682, | |
| "learning_rate": 7.274026243582796e-06, | |
| "loss": 1.0381, | |
| "step": 4240 | |
| }, | |
| { | |
| "epoch": 2.059108527131783, | |
| "grad_norm": 4.836928367614746, | |
| "learning_rate": 7.087543351687493e-06, | |
| "loss": 1.0541, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.063953488372093, | |
| "grad_norm": 4.825849533081055, | |
| "learning_rate": 6.903338248849269e-06, | |
| "loss": 1.0178, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 2.068798449612403, | |
| "grad_norm": 4.556478977203369, | |
| "learning_rate": 6.7214185070183925e-06, | |
| "loss": 1.0202, | |
| "step": 4270 | |
| }, | |
| { | |
| "epoch": 2.0736434108527133, | |
| "grad_norm": 5.168104648590088, | |
| "learning_rate": 6.541791604202936e-06, | |
| "loss": 1.0212, | |
| "step": 4280 | |
| }, | |
| { | |
| "epoch": 2.078488372093023, | |
| "grad_norm": 4.436131000518799, | |
| "learning_rate": 6.364464924161311e-06, | |
| "loss": 1.035, | |
| "step": 4290 | |
| }, | |
| { | |
| "epoch": 2.0833333333333335, | |
| "grad_norm": 4.729435443878174, | |
| "learning_rate": 6.1894457560988106e-06, | |
| "loss": 1.0691, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.0881782945736433, | |
| "grad_norm": 4.654105186462402, | |
| "learning_rate": 6.016741294367911e-06, | |
| "loss": 0.9836, | |
| "step": 4310 | |
| }, | |
| { | |
| "epoch": 2.0930232558139537, | |
| "grad_norm": 4.738863945007324, | |
| "learning_rate": 5.846358638172615e-06, | |
| "loss": 1.059, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 2.0978682170542635, | |
| "grad_norm": 4.768299102783203, | |
| "learning_rate": 5.678304791276567e-06, | |
| "loss": 1.0208, | |
| "step": 4330 | |
| }, | |
| { | |
| "epoch": 2.102713178294574, | |
| "grad_norm": 4.950557231903076, | |
| "learning_rate": 5.51258666171519e-06, | |
| "loss": 1.0373, | |
| "step": 4340 | |
| }, | |
| { | |
| "epoch": 2.1075581395348837, | |
| "grad_norm": 4.744584083557129, | |
| "learning_rate": 5.349211061511726e-06, | |
| "loss": 1.0382, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.1075581395348837, | |
| "eval_loss": 1.318005084991455, | |
| "eval_runtime": 34.8879, | |
| "eval_samples_per_second": 14.332, | |
| "eval_steps_per_second": 14.332, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.112403100775194, | |
| "grad_norm": 4.970248222351074, | |
| "learning_rate": 5.188184706397182e-06, | |
| "loss": 1.0336, | |
| "step": 4360 | |
| }, | |
| { | |
| "epoch": 2.117248062015504, | |
| "grad_norm": 4.452147483825684, | |
| "learning_rate": 5.029514215534339e-06, | |
| "loss": 1.0783, | |
| "step": 4370 | |
| }, | |
| { | |
| "epoch": 2.1220930232558137, | |
| "grad_norm": 5.069756507873535, | |
| "learning_rate": 4.873206111245594e-06, | |
| "loss": 1.0183, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 2.126937984496124, | |
| "grad_norm": 5.139758586883545, | |
| "learning_rate": 4.719266818744912e-06, | |
| "loss": 1.0064, | |
| "step": 4390 | |
| }, | |
| { | |
| "epoch": 2.1317829457364343, | |
| "grad_norm": 4.728250980377197, | |
| "learning_rate": 4.567702665873648e-06, | |
| "loss": 1.0729, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.136627906976744, | |
| "grad_norm": 4.994308948516846, | |
| "learning_rate": 4.418519882840505e-06, | |
| "loss": 1.0429, | |
| "step": 4410 | |
| }, | |
| { | |
| "epoch": 2.141472868217054, | |
| "grad_norm": 5.102052211761475, | |
| "learning_rate": 4.271724601965371e-06, | |
| "loss": 0.9935, | |
| "step": 4420 | |
| }, | |
| { | |
| "epoch": 2.1463178294573644, | |
| "grad_norm": 4.426207065582275, | |
| "learning_rate": 4.127322857427306e-06, | |
| "loss": 1.0107, | |
| "step": 4430 | |
| }, | |
| { | |
| "epoch": 2.1511627906976742, | |
| "grad_norm": 4.988846302032471, | |
| "learning_rate": 3.985320585016425e-06, | |
| "loss": 1.053, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 2.1560077519379846, | |
| "grad_norm": 4.7682600021362305, | |
| "learning_rate": 3.845723621889973e-06, | |
| "loss": 1.0547, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.1608527131782944, | |
| "grad_norm": 4.747420787811279, | |
| "learning_rate": 3.7085377063323447e-06, | |
| "loss": 1.0372, | |
| "step": 4460 | |
| }, | |
| { | |
| "epoch": 2.1656976744186047, | |
| "grad_norm": 5.47692346572876, | |
| "learning_rate": 3.5737684775191887e-06, | |
| "loss": 1.0329, | |
| "step": 4470 | |
| }, | |
| { | |
| "epoch": 2.1705426356589146, | |
| "grad_norm": 4.682116508483887, | |
| "learning_rate": 3.441421475285679e-06, | |
| "loss": 1.0207, | |
| "step": 4480 | |
| }, | |
| { | |
| "epoch": 2.175387596899225, | |
| "grad_norm": 4.9538421630859375, | |
| "learning_rate": 3.3115021398986768e-06, | |
| "loss": 1.0312, | |
| "step": 4490 | |
| }, | |
| { | |
| "epoch": 2.1802325581395348, | |
| "grad_norm": 4.703029155731201, | |
| "learning_rate": 3.18401581183321e-06, | |
| "loss": 1.0013, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.1802325581395348, | |
| "eval_loss": 1.3207753896713257, | |
| "eval_runtime": 34.0398, | |
| "eval_samples_per_second": 14.689, | |
| "eval_steps_per_second": 14.689, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.185077519379845, | |
| "grad_norm": 5.3770599365234375, | |
| "learning_rate": 3.0589677315529044e-06, | |
| "loss": 1.0393, | |
| "step": 4510 | |
| }, | |
| { | |
| "epoch": 2.189922480620155, | |
| "grad_norm": 5.012081146240234, | |
| "learning_rate": 2.9363630392945513e-06, | |
| "loss": 1.0691, | |
| "step": 4520 | |
| }, | |
| { | |
| "epoch": 2.1947674418604652, | |
| "grad_norm": 4.9033589363098145, | |
| "learning_rate": 2.816206774856854e-06, | |
| "loss": 1.0394, | |
| "step": 4530 | |
| }, | |
| { | |
| "epoch": 2.199612403100775, | |
| "grad_norm": 5.1483001708984375, | |
| "learning_rate": 2.6985038773932046e-06, | |
| "loss": 1.0717, | |
| "step": 4540 | |
| }, | |
| { | |
| "epoch": 2.2044573643410854, | |
| "grad_norm": 4.764675617218018, | |
| "learning_rate": 2.583259185208714e-06, | |
| "loss": 1.0564, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.2093023255813953, | |
| "grad_norm": 5.014820575714111, | |
| "learning_rate": 2.4704774355612943e-06, | |
| "loss": 1.0331, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 2.2141472868217056, | |
| "grad_norm": 4.7594099044799805, | |
| "learning_rate": 2.3601632644669536e-06, | |
| "loss": 1.0387, | |
| "step": 4570 | |
| }, | |
| { | |
| "epoch": 2.2189922480620154, | |
| "grad_norm": 4.573930740356445, | |
| "learning_rate": 2.2523212065091723e-06, | |
| "loss": 1.0151, | |
| "step": 4580 | |
| }, | |
| { | |
| "epoch": 2.2238372093023258, | |
| "grad_norm": 4.81765079498291, | |
| "learning_rate": 2.1469556946525706e-06, | |
| "loss": 1.0812, | |
| "step": 4590 | |
| }, | |
| { | |
| "epoch": 2.2286821705426356, | |
| "grad_norm": 4.986940383911133, | |
| "learning_rate": 2.0440710600606595e-06, | |
| "loss": 1.008, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.233527131782946, | |
| "grad_norm": 5.306875705718994, | |
| "learning_rate": 1.9436715319177956e-06, | |
| "loss": 0.9869, | |
| "step": 4610 | |
| }, | |
| { | |
| "epoch": 2.238372093023256, | |
| "grad_norm": 5.1074395179748535, | |
| "learning_rate": 1.8457612372553348e-06, | |
| "loss": 1.056, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 2.2432170542635657, | |
| "grad_norm": 4.792019367218018, | |
| "learning_rate": 1.75034420078201e-06, | |
| "loss": 1.0536, | |
| "step": 4630 | |
| }, | |
| { | |
| "epoch": 2.248062015503876, | |
| "grad_norm": 5.631920337677002, | |
| "learning_rate": 1.6574243447184597e-06, | |
| "loss": 1.0099, | |
| "step": 4640 | |
| }, | |
| { | |
| "epoch": 2.2529069767441863, | |
| "grad_norm": 4.535787105560303, | |
| "learning_rate": 1.567005488636024e-06, | |
| "loss": 1.0242, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.2529069767441863, | |
| "eval_loss": 1.321666955947876, | |
| "eval_runtime": 34.8681, | |
| "eval_samples_per_second": 14.34, | |
| "eval_steps_per_second": 14.34, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.257751937984496, | |
| "grad_norm": 5.02518367767334, | |
| "learning_rate": 1.4790913492997438e-06, | |
| "loss": 1.0151, | |
| "step": 4660 | |
| }, | |
| { | |
| "epoch": 2.262596899224806, | |
| "grad_norm": 4.680893421173096, | |
| "learning_rate": 1.3936855405155408e-06, | |
| "loss": 1.0531, | |
| "step": 4670 | |
| }, | |
| { | |
| "epoch": 2.2674418604651163, | |
| "grad_norm": 4.825300216674805, | |
| "learning_rate": 1.3107915729816954e-06, | |
| "loss": 0.963, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 2.272286821705426, | |
| "grad_norm": 4.554722785949707, | |
| "learning_rate": 1.230412854144547e-06, | |
| "loss": 1.0193, | |
| "step": 4690 | |
| }, | |
| { | |
| "epoch": 2.2771317829457365, | |
| "grad_norm": 4.723803520202637, | |
| "learning_rate": 1.15255268805841e-06, | |
| "loss": 1.0079, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.2819767441860463, | |
| "grad_norm": 5.480154514312744, | |
| "learning_rate": 1.0772142752497604e-06, | |
| "loss": 1.0737, | |
| "step": 4710 | |
| }, | |
| { | |
| "epoch": 2.2868217054263567, | |
| "grad_norm": 5.367369651794434, | |
| "learning_rate": 1.004400712585646e-06, | |
| "loss": 1.0406, | |
| "step": 4720 | |
| }, | |
| { | |
| "epoch": 2.2916666666666665, | |
| "grad_norm": 4.804909706115723, | |
| "learning_rate": 9.341149931464537e-07, | |
| "loss": 1.037, | |
| "step": 4730 | |
| }, | |
| { | |
| "epoch": 2.296511627906977, | |
| "grad_norm": 5.131532192230225, | |
| "learning_rate": 8.663600061028162e-07, | |
| "loss": 1.0684, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 2.3013565891472867, | |
| "grad_norm": 4.939748287200928, | |
| "learning_rate": 8.011385365968641e-07, | |
| "loss": 1.0439, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.306201550387597, | |
| "grad_norm": 4.985282897949219, | |
| "learning_rate": 7.384532656277698e-07, | |
| "loss": 1.0066, | |
| "step": 4760 | |
| }, | |
| { | |
| "epoch": 2.311046511627907, | |
| "grad_norm": 5.235836505889893, | |
| "learning_rate": 6.783067699414891e-07, | |
| "loss": 1.0223, | |
| "step": 4770 | |
| }, | |
| { | |
| "epoch": 2.315891472868217, | |
| "grad_norm": 5.52247953414917, | |
| "learning_rate": 6.207015219248866e-07, | |
| "loss": 1.0469, | |
| "step": 4780 | |
| }, | |
| { | |
| "epoch": 2.320736434108527, | |
| "grad_norm": 4.918477535247803, | |
| "learning_rate": 5.656398895040813e-07, | |
| "loss": 1.0399, | |
| "step": 4790 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "grad_norm": 4.3925628662109375, | |
| "learning_rate": 5.131241360471217e-07, | |
| "loss": 1.0114, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.3255813953488373, | |
| "eval_loss": 1.3223485946655273, | |
| "eval_runtime": 34.8062, | |
| "eval_samples_per_second": 14.365, | |
| "eval_steps_per_second": 14.365, | |
| "step": 4800 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 5000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 150, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.570336699071898e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |