| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6337188923939713, |
| "eval_steps": 500, |
| "global_step": 904, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0035050823694356818, |
| "grad_norm": 34.28617477416992, |
| "learning_rate": 1.6634586466165415e-06, |
| "loss": 0.3831, |
| "mean_token_accuracy": 0.8712963074445724, |
| "num_tokens": 344200.0, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0070101647388713636, |
| "grad_norm": 2.2588274478912354, |
| "learning_rate": 3.7427819548872183e-06, |
| "loss": 0.1348, |
| "mean_token_accuracy": 0.9599537253379822, |
| "num_tokens": 689149.0, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.010515247108307046, |
| "grad_norm": 0.7412953972816467, |
| "learning_rate": 5.822105263157896e-06, |
| "loss": 0.1038, |
| "mean_token_accuracy": 0.9601852089166641, |
| "num_tokens": 1035106.0, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.014020329477742727, |
| "grad_norm": 0.8367692828178406, |
| "learning_rate": 7.901428571428572e-06, |
| "loss": 0.092, |
| "mean_token_accuracy": 0.9664351999759674, |
| "num_tokens": 1384179.0, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.01752541184717841, |
| "grad_norm": 0.9332820773124695, |
| "learning_rate": 9.98075187969925e-06, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9747685253620147, |
| "num_tokens": 1731414.0, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.02103049421661409, |
| "grad_norm": 1.3677386045455933, |
| "learning_rate": 1.2060075187969928e-05, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.977314829826355, |
| "num_tokens": 2081016.0, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.02453557658604977, |
| "grad_norm": 0.9507705569267273, |
| "learning_rate": 1.4139398496240603e-05, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9782407462596894, |
| "num_tokens": 2425641.0, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.028040658955485454, |
| "grad_norm": 0.9917059540748596, |
| "learning_rate": 1.4555208926572781e-05, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9810185313224793, |
| "num_tokens": 2772582.0, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.031545741324921134, |
| "grad_norm": 0.5380669236183167, |
| "learning_rate": 1.4554988613674284e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9784722357988358, |
| "num_tokens": 3116560.0, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.03505082369435682, |
| "grad_norm": 0.6936527490615845, |
| "learning_rate": 1.4554598836576865e-05, |
| "loss": 0.052, |
| "mean_token_accuracy": 0.9803240865468978, |
| "num_tokens": 3462279.0, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.0385559060637925, |
| "grad_norm": 0.7106812596321106, |
| "learning_rate": 1.4554039607382746e-05, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9807870477437973, |
| "num_tokens": 3807370.0, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.04206098843322818, |
| "grad_norm": 1.0563263893127441, |
| "learning_rate": 1.4553310943455462e-05, |
| "loss": 0.0398, |
| "mean_token_accuracy": 0.9849537283182144, |
| "num_tokens": 4153983.0, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.04556607080266386, |
| "grad_norm": 0.7298295497894287, |
| "learning_rate": 1.4552412867419349e-05, |
| "loss": 0.0467, |
| "mean_token_accuracy": 0.9833333402872085, |
| "num_tokens": 4499283.0, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.04907115317209954, |
| "grad_norm": 0.5817667841911316, |
| "learning_rate": 1.4551345407158823e-05, |
| "loss": 0.0488, |
| "mean_token_accuracy": 0.9791666716337204, |
| "num_tokens": 4843821.0, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.052576235541535225, |
| "grad_norm": 0.4315837025642395, |
| "learning_rate": 1.455010859581752e-05, |
| "loss": 0.0381, |
| "mean_token_accuracy": 0.9861111283302307, |
| "num_tokens": 5189702.0, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.05608131791097091, |
| "grad_norm": 0.6540916562080383, |
| "learning_rate": 1.4548702471797281e-05, |
| "loss": 0.0364, |
| "mean_token_accuracy": 0.9872685372829437, |
| "num_tokens": 5536282.0, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.05958640028040659, |
| "grad_norm": 0.6374391317367554, |
| "learning_rate": 1.4547127078756926e-05, |
| "loss": 0.0319, |
| "mean_token_accuracy": 0.9879629909992218, |
| "num_tokens": 5880437.0, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.06309148264984227, |
| "grad_norm": 0.6164258718490601, |
| "learning_rate": 1.4545382465610937e-05, |
| "loss": 0.0288, |
| "mean_token_accuracy": 0.987500011920929, |
| "num_tokens": 6229654.0, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.06659656501927795, |
| "grad_norm": 0.5443395972251892, |
| "learning_rate": 1.4543468686527915e-05, |
| "loss": 0.0452, |
| "mean_token_accuracy": 0.9826389074325561, |
| "num_tokens": 6574571.0, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.07010164738871363, |
| "grad_norm": 0.40494611859321594, |
| "learning_rate": 1.45413858009289e-05, |
| "loss": 0.0369, |
| "mean_token_accuracy": 0.9851852089166642, |
| "num_tokens": 6922334.0, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07360672975814932, |
| "grad_norm": 0.4939163029193878, |
| "learning_rate": 1.453913387348554e-05, |
| "loss": 0.0338, |
| "mean_token_accuracy": 0.9858796447515488, |
| "num_tokens": 7267485.0, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.077111812127585, |
| "grad_norm": 0.5785835981369019, |
| "learning_rate": 1.453671297411807e-05, |
| "loss": 0.0402, |
| "mean_token_accuracy": 0.9858796387910843, |
| "num_tokens": 7613308.0, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.08061689449702068, |
| "grad_norm": 0.6168781518936157, |
| "learning_rate": 1.4534123177993137e-05, |
| "loss": 0.0355, |
| "mean_token_accuracy": 0.9856481611728668, |
| "num_tokens": 7959953.0, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.08412197686645637, |
| "grad_norm": 0.5103176832199097, |
| "learning_rate": 1.4531364565521482e-05, |
| "loss": 0.0333, |
| "mean_token_accuracy": 0.9861111402511596, |
| "num_tokens": 8307851.0, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.08762705923589205, |
| "grad_norm": 0.6440109610557556, |
| "learning_rate": 1.452843722235544e-05, |
| "loss": 0.0406, |
| "mean_token_accuracy": 0.9840277969837189, |
| "num_tokens": 8652302.0, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.09113214160532772, |
| "grad_norm": 0.38599690794944763, |
| "learning_rate": 1.4525341239386265e-05, |
| "loss": 0.0338, |
| "mean_token_accuracy": 0.9877315014600754, |
| "num_tokens": 8997305.0, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.0946372239747634, |
| "grad_norm": 0.3226912021636963, |
| "learning_rate": 1.452207671274132e-05, |
| "loss": 0.0316, |
| "mean_token_accuracy": 0.9886574268341064, |
| "num_tokens": 9343578.0, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.09814230634419908, |
| "grad_norm": 0.3602822422981262, |
| "learning_rate": 1.45186437437811e-05, |
| "loss": 0.0264, |
| "mean_token_accuracy": 0.9881944715976715, |
| "num_tokens": 9689335.0, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.10164738871363477, |
| "grad_norm": 0.5718931555747986, |
| "learning_rate": 1.4515042439096063e-05, |
| "loss": 0.0393, |
| "mean_token_accuracy": 0.9849537163972855, |
| "num_tokens": 10035392.0, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.10515247108307045, |
| "grad_norm": 0.4808923006057739, |
| "learning_rate": 1.4511272910503343e-05, |
| "loss": 0.0319, |
| "mean_token_accuracy": 0.9875000268220901, |
| "num_tokens": 10381828.0, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.10865755345250613, |
| "grad_norm": 0.2157701849937439, |
| "learning_rate": 1.4507335275043267e-05, |
| "loss": 0.0254, |
| "mean_token_accuracy": 0.9898148387670517, |
| "num_tokens": 10728103.0, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.11216263582194182, |
| "grad_norm": 0.4944171905517578, |
| "learning_rate": 1.4503229654975717e-05, |
| "loss": 0.032, |
| "mean_token_accuracy": 0.9877315104007721, |
| "num_tokens": 11074857.0, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.1156677181913775, |
| "grad_norm": 0.4375927448272705, |
| "learning_rate": 1.449895617777635e-05, |
| "loss": 0.0318, |
| "mean_token_accuracy": 0.9868055731058121, |
| "num_tokens": 11420935.0, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.11917280056081318, |
| "grad_norm": 0.3322710692882538, |
| "learning_rate": 1.4494514976132613e-05, |
| "loss": 0.0285, |
| "mean_token_accuracy": 0.9891203850507736, |
| "num_tokens": 11767206.0, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.12267788293024887, |
| "grad_norm": 0.32739579677581787, |
| "learning_rate": 1.4489906187939658e-05, |
| "loss": 0.0256, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 12113613.0, |
| "step": 175 |
| }, |
| { |
| "epoch": 0.12618296529968454, |
| "grad_norm": 0.46730878949165344, |
| "learning_rate": 1.4485129956296029e-05, |
| "loss": 0.0328, |
| "mean_token_accuracy": 0.9870370507240296, |
| "num_tokens": 12458188.0, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.12968804766912023, |
| "grad_norm": 0.546477735042572, |
| "learning_rate": 1.4480186429499237e-05, |
| "loss": 0.0324, |
| "mean_token_accuracy": 0.9870370596647262, |
| "num_tokens": 12804081.0, |
| "step": 185 |
| }, |
| { |
| "epoch": 0.1331931300385559, |
| "grad_norm": 0.5323887467384338, |
| "learning_rate": 1.4475075761041149e-05, |
| "loss": 0.0274, |
| "mean_token_accuracy": 0.9879629820585251, |
| "num_tokens": 13150545.0, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.1366982124079916, |
| "grad_norm": 0.38450950384140015, |
| "learning_rate": 1.4469798109603229e-05, |
| "loss": 0.0317, |
| "mean_token_accuracy": 0.9868055820465088, |
| "num_tokens": 13495797.0, |
| "step": 195 |
| }, |
| { |
| "epoch": 0.14020329477742727, |
| "grad_norm": 0.4323956370353699, |
| "learning_rate": 1.4464353639051596e-05, |
| "loss": 0.0299, |
| "mean_token_accuracy": 0.9884259521961212, |
| "num_tokens": 13841841.0, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.14370837714686296, |
| "grad_norm": 0.2992998957633972, |
| "learning_rate": 1.4458742518431953e-05, |
| "loss": 0.0264, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 14190171.0, |
| "step": 205 |
| }, |
| { |
| "epoch": 0.14721345951629863, |
| "grad_norm": 0.5052563548088074, |
| "learning_rate": 1.4452964921964331e-05, |
| "loss": 0.0318, |
| "mean_token_accuracy": 0.9898148447275161, |
| "num_tokens": 14535839.0, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.1507185418857343, |
| "grad_norm": 0.4144446849822998, |
| "learning_rate": 1.444702102903768e-05, |
| "loss": 0.0303, |
| "mean_token_accuracy": 0.9875000178813934, |
| "num_tokens": 14881253.0, |
| "step": 215 |
| }, |
| { |
| "epoch": 0.15422362425517, |
| "grad_norm": 0.5403540134429932, |
| "learning_rate": 1.4440911024204294e-05, |
| "loss": 0.0283, |
| "mean_token_accuracy": 0.9875000298023224, |
| "num_tokens": 15226228.0, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.15772870662460567, |
| "grad_norm": 0.4785594046115875, |
| "learning_rate": 1.443463509717409e-05, |
| "loss": 0.031, |
| "mean_token_accuracy": 0.9865740895271301, |
| "num_tokens": 15571620.0, |
| "step": 225 |
| }, |
| { |
| "epoch": 0.16123378899404137, |
| "grad_norm": 0.41378340125083923, |
| "learning_rate": 1.442819344280871e-05, |
| "loss": 0.0238, |
| "mean_token_accuracy": 0.9907407611608505, |
| "num_tokens": 15918913.0, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.16473887136347704, |
| "grad_norm": 0.4847274124622345, |
| "learning_rate": 1.4421586261115488e-05, |
| "loss": 0.0278, |
| "mean_token_accuracy": 0.9893518805503845, |
| "num_tokens": 16267955.0, |
| "step": 235 |
| }, |
| { |
| "epoch": 0.16824395373291273, |
| "grad_norm": 0.31813815236091614, |
| "learning_rate": 1.4414813757241202e-05, |
| "loss": 0.0313, |
| "mean_token_accuracy": 0.9881944686174393, |
| "num_tokens": 16612410.0, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.1717490361023484, |
| "grad_norm": 0.3177052438259125, |
| "learning_rate": 1.4407876141465748e-05, |
| "loss": 0.0266, |
| "mean_token_accuracy": 0.9891204059123992, |
| "num_tokens": 16957764.0, |
| "step": 245 |
| }, |
| { |
| "epoch": 0.1752541184717841, |
| "grad_norm": 0.3826673924922943, |
| "learning_rate": 1.4400773629195588e-05, |
| "loss": 0.0357, |
| "mean_token_accuracy": 0.9847222417593002, |
| "num_tokens": 17304294.0, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.17875920084121977, |
| "grad_norm": 0.48539939522743225, |
| "learning_rate": 1.4393506440957055e-05, |
| "loss": 0.0278, |
| "mean_token_accuracy": 0.9884259581565857, |
| "num_tokens": 17650961.0, |
| "step": 255 |
| }, |
| { |
| "epoch": 0.18226428321065544, |
| "grad_norm": 0.626573383808136, |
| "learning_rate": 1.4386074802389532e-05, |
| "loss": 0.0337, |
| "mean_token_accuracy": 0.9875000298023224, |
| "num_tokens": 17995184.0, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.18576936558009113, |
| "grad_norm": 0.5070188641548157, |
| "learning_rate": 1.4378478944238419e-05, |
| "loss": 0.0326, |
| "mean_token_accuracy": 0.9877315104007721, |
| "num_tokens": 18341450.0, |
| "step": 265 |
| }, |
| { |
| "epoch": 0.1892744479495268, |
| "grad_norm": 0.41273266077041626, |
| "learning_rate": 1.4370719102347984e-05, |
| "loss": 0.0321, |
| "mean_token_accuracy": 0.9879629909992218, |
| "num_tokens": 18688049.0, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.1927795303189625, |
| "grad_norm": 0.2910098433494568, |
| "learning_rate": 1.4362795517654034e-05, |
| "loss": 0.024, |
| "mean_token_accuracy": 0.9907407641410828, |
| "num_tokens": 19033873.0, |
| "step": 275 |
| }, |
| { |
| "epoch": 0.19628461268839817, |
| "grad_norm": 0.4974495768547058, |
| "learning_rate": 1.435470843617644e-05, |
| "loss": 0.0267, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 19378640.0, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.19978969505783387, |
| "grad_norm": 0.36540356278419495, |
| "learning_rate": 1.4346458109011491e-05, |
| "loss": 0.027, |
| "mean_token_accuracy": 0.9888889104127884, |
| "num_tokens": 19723286.0, |
| "step": 285 |
| }, |
| { |
| "epoch": 0.20329477742726954, |
| "grad_norm": 0.47516849637031555, |
| "learning_rate": 1.4338044792324107e-05, |
| "loss": 0.0269, |
| "mean_token_accuracy": 0.9900463163852692, |
| "num_tokens": 20069296.0, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.20679985979670523, |
| "grad_norm": 0.4357232451438904, |
| "learning_rate": 1.432946874733987e-05, |
| "loss": 0.0331, |
| "mean_token_accuracy": 0.9884259551763535, |
| "num_tokens": 20416004.0, |
| "step": 295 |
| }, |
| { |
| "epoch": 0.2103049421661409, |
| "grad_norm": 0.4937360882759094, |
| "learning_rate": 1.4320730240336934e-05, |
| "loss": 0.0187, |
| "mean_token_accuracy": 0.9937500208616257, |
| "num_tokens": 20764277.0, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.2138100245355766, |
| "grad_norm": 0.276079386472702, |
| "learning_rate": 1.4311829542637738e-05, |
| "loss": 0.0267, |
| "mean_token_accuracy": 0.98935187458992, |
| "num_tokens": 21112041.0, |
| "step": 305 |
| }, |
| { |
| "epoch": 0.21731510690501227, |
| "grad_norm": 0.42910081148147583, |
| "learning_rate": 1.4302766930600593e-05, |
| "loss": 0.0291, |
| "mean_token_accuracy": 0.9891203969717026, |
| "num_tokens": 21458856.0, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.22082018927444794, |
| "grad_norm": 0.6333709359169006, |
| "learning_rate": 1.42935426856111e-05, |
| "loss": 0.0327, |
| "mean_token_accuracy": 0.9886574298143387, |
| "num_tokens": 21806361.0, |
| "step": 315 |
| }, |
| { |
| "epoch": 0.22432527164388363, |
| "grad_norm": 0.23009836673736572, |
| "learning_rate": 1.4284157094073407e-05, |
| "loss": 0.0165, |
| "mean_token_accuracy": 0.9932870596647263, |
| "num_tokens": 22152746.0, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.2278303540133193, |
| "grad_norm": 0.3802606463432312, |
| "learning_rate": 1.4274610447401327e-05, |
| "loss": 0.0263, |
| "mean_token_accuracy": 0.9891203939914703, |
| "num_tokens": 22499422.0, |
| "step": 325 |
| }, |
| { |
| "epoch": 0.231335436382755, |
| "grad_norm": 0.4347723722457886, |
| "learning_rate": 1.4264903042009281e-05, |
| "loss": 0.0278, |
| "mean_token_accuracy": 0.9886574298143387, |
| "num_tokens": 22844958.0, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.23484051875219067, |
| "grad_norm": 0.49451401829719543, |
| "learning_rate": 1.4255035179303093e-05, |
| "loss": 0.0223, |
| "mean_token_accuracy": 0.9916666865348815, |
| "num_tokens": 23190999.0, |
| "step": 335 |
| }, |
| { |
| "epoch": 0.23834560112162637, |
| "grad_norm": 0.24139922857284546, |
| "learning_rate": 1.4245007165670638e-05, |
| "loss": 0.0282, |
| "mean_token_accuracy": 0.988657432794571, |
| "num_tokens": 23537740.0, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.24185068349106204, |
| "grad_norm": 0.32044461369514465, |
| "learning_rate": 1.4234819312472335e-05, |
| "loss": 0.0225, |
| "mean_token_accuracy": 0.9909722447395325, |
| "num_tokens": 23883934.0, |
| "step": 345 |
| }, |
| { |
| "epoch": 0.24535576586049773, |
| "grad_norm": 0.18548811972141266, |
| "learning_rate": 1.422447193603146e-05, |
| "loss": 0.0235, |
| "mean_token_accuracy": 0.9912037342786789, |
| "num_tokens": 24231722.0, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.2488608482299334, |
| "grad_norm": 0.45737743377685547, |
| "learning_rate": 1.4213965357624343e-05, |
| "loss": 0.0253, |
| "mean_token_accuracy": 0.9905092865228653, |
| "num_tokens": 24577887.0, |
| "step": 355 |
| }, |
| { |
| "epoch": 0.25236593059936907, |
| "grad_norm": 0.3616850972175598, |
| "learning_rate": 1.4203299903470387e-05, |
| "loss": 0.0263, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 24922653.0, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.25587101296880477, |
| "grad_norm": 0.4848349094390869, |
| "learning_rate": 1.419247590472193e-05, |
| "loss": 0.0242, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 25269418.0, |
| "step": 365 |
| }, |
| { |
| "epoch": 0.25937609533824046, |
| "grad_norm": 0.2585952877998352, |
| "learning_rate": 1.4181493697453978e-05, |
| "loss": 0.0203, |
| "mean_token_accuracy": 0.993055573105812, |
| "num_tokens": 25616271.0, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.2628811777076761, |
| "grad_norm": 0.35240036249160767, |
| "learning_rate": 1.417035362265376e-05, |
| "loss": 0.0246, |
| "mean_token_accuracy": 0.9902778029441833, |
| "num_tokens": 25961709.0, |
| "step": 375 |
| }, |
| { |
| "epoch": 0.2663862600771118, |
| "grad_norm": 0.4934576749801636, |
| "learning_rate": 1.4159056026210145e-05, |
| "loss": 0.0245, |
| "mean_token_accuracy": 0.9907407611608505, |
| "num_tokens": 26305582.0, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.2698913424465475, |
| "grad_norm": 0.5466775298118591, |
| "learning_rate": 1.41476012589029e-05, |
| "loss": 0.0276, |
| "mean_token_accuracy": 0.988425949215889, |
| "num_tokens": 26651187.0, |
| "step": 385 |
| }, |
| { |
| "epoch": 0.2733964248159832, |
| "grad_norm": 0.38013315200805664, |
| "learning_rate": 1.4135989676391804e-05, |
| "loss": 0.0228, |
| "mean_token_accuracy": 0.9916666835546494, |
| "num_tokens": 26998191.0, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.27690150718541884, |
| "grad_norm": 0.28799182176589966, |
| "learning_rate": 1.4124221639205589e-05, |
| "loss": 0.0227, |
| "mean_token_accuracy": 0.9912037283182145, |
| "num_tokens": 27343339.0, |
| "step": 395 |
| }, |
| { |
| "epoch": 0.28040658955485454, |
| "grad_norm": 0.42601919174194336, |
| "learning_rate": 1.4112297512730775e-05, |
| "loss": 0.0306, |
| "mean_token_accuracy": 0.989814841747284, |
| "num_tokens": 27688319.0, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.28391167192429023, |
| "grad_norm": 0.4378221333026886, |
| "learning_rate": 1.4100217667200293e-05, |
| "loss": 0.0312, |
| "mean_token_accuracy": 0.9886574268341064, |
| "num_tokens": 28033195.0, |
| "step": 405 |
| }, |
| { |
| "epoch": 0.28741675429372593, |
| "grad_norm": 0.3670158386230469, |
| "learning_rate": 1.4087982477682015e-05, |
| "loss": 0.0245, |
| "mean_token_accuracy": 0.9912037223577499, |
| "num_tokens": 28380397.0, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.29092183666316157, |
| "grad_norm": 0.26418375968933105, |
| "learning_rate": 1.4075592324067092e-05, |
| "loss": 0.0277, |
| "mean_token_accuracy": 0.9891203969717026, |
| "num_tokens": 28727209.0, |
| "step": 415 |
| }, |
| { |
| "epoch": 0.29442691903259727, |
| "grad_norm": 0.207740917801857, |
| "learning_rate": 1.4063047591058165e-05, |
| "loss": 0.0218, |
| "mean_token_accuracy": 0.9912037253379822, |
| "num_tokens": 29073179.0, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.29793200140203296, |
| "grad_norm": 0.2558346688747406, |
| "learning_rate": 1.4050348668157424e-05, |
| "loss": 0.0252, |
| "mean_token_accuracy": 0.990972250699997, |
| "num_tokens": 29419021.0, |
| "step": 425 |
| }, |
| { |
| "epoch": 0.3014370837714686, |
| "grad_norm": 0.4200788736343384, |
| "learning_rate": 1.4037495949654506e-05, |
| "loss": 0.0293, |
| "mean_token_accuracy": 0.9900463193655014, |
| "num_tokens": 29762751.0, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.3049421661409043, |
| "grad_norm": 0.2755083739757538, |
| "learning_rate": 1.4024489834614261e-05, |
| "loss": 0.0273, |
| "mean_token_accuracy": 0.9884259551763535, |
| "num_tokens": 30107869.0, |
| "step": 435 |
| }, |
| { |
| "epoch": 0.30844724851034, |
| "grad_norm": 0.456945538520813, |
| "learning_rate": 1.4011330726864357e-05, |
| "loss": 0.0266, |
| "mean_token_accuracy": 0.9900463163852692, |
| "num_tokens": 30454247.0, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.3119523308797757, |
| "grad_norm": 0.3265325427055359, |
| "learning_rate": 1.3998019034982736e-05, |
| "loss": 0.0209, |
| "mean_token_accuracy": 0.992129647731781, |
| "num_tokens": 30801926.0, |
| "step": 445 |
| }, |
| { |
| "epoch": 0.31545741324921134, |
| "grad_norm": 0.2476506531238556, |
| "learning_rate": 1.3984555172284941e-05, |
| "loss": 0.0261, |
| "mean_token_accuracy": 0.9900463283061981, |
| "num_tokens": 31148230.0, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.31896249561864704, |
| "grad_norm": 0.36999770998954773, |
| "learning_rate": 1.3970939556811277e-05, |
| "loss": 0.0281, |
| "mean_token_accuracy": 0.9907407641410828, |
| "num_tokens": 31495694.0, |
| "step": 455 |
| }, |
| { |
| "epoch": 0.32246757798808273, |
| "grad_norm": 0.2715221643447876, |
| "learning_rate": 1.3957172611313823e-05, |
| "loss": 0.0218, |
| "mean_token_accuracy": 0.9925926178693771, |
| "num_tokens": 31840699.0, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.32597266035751843, |
| "grad_norm": 0.2700594365596771, |
| "learning_rate": 1.394325476324332e-05, |
| "loss": 0.0271, |
| "mean_token_accuracy": 0.9912037342786789, |
| "num_tokens": 32185556.0, |
| "step": 465 |
| }, |
| { |
| "epoch": 0.32947774272695407, |
| "grad_norm": 0.21484653651714325, |
| "learning_rate": 1.392918644473589e-05, |
| "loss": 0.0259, |
| "mean_token_accuracy": 0.9902777999639512, |
| "num_tokens": 32530728.0, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.33298282509638977, |
| "grad_norm": 0.22852717339992523, |
| "learning_rate": 1.391496809259962e-05, |
| "loss": 0.0202, |
| "mean_token_accuracy": 0.9914352059364319, |
| "num_tokens": 32876136.0, |
| "step": 475 |
| }, |
| { |
| "epoch": 0.33648790746582546, |
| "grad_norm": 0.19366268813610077, |
| "learning_rate": 1.3900600148300999e-05, |
| "loss": 0.0198, |
| "mean_token_accuracy": 0.9925926148891449, |
| "num_tokens": 33224897.0, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.3399929898352611, |
| "grad_norm": 0.34376469254493713, |
| "learning_rate": 1.3886083057951215e-05, |
| "loss": 0.0221, |
| "mean_token_accuracy": 0.9909722477197647, |
| "num_tokens": 33569560.0, |
| "step": 485 |
| }, |
| { |
| "epoch": 0.3434980722046968, |
| "grad_norm": 0.3154052197933197, |
| "learning_rate": 1.3871417272292302e-05, |
| "loss": 0.0165, |
| "mean_token_accuracy": 0.9932870537042617, |
| "num_tokens": 33917915.0, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.3470031545741325, |
| "grad_norm": 0.7269891500473022, |
| "learning_rate": 1.3856603246683142e-05, |
| "loss": 0.0259, |
| "mean_token_accuracy": 0.9900463134050369, |
| "num_tokens": 34266968.0, |
| "step": 495 |
| }, |
| { |
| "epoch": 0.3505082369435682, |
| "grad_norm": 0.295919805765152, |
| "learning_rate": 1.3841641441085326e-05, |
| "loss": 0.0244, |
| "mean_token_accuracy": 0.9905092865228653, |
| "num_tokens": 34610972.0, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.35401331931300384, |
| "grad_norm": 0.29701659083366394, |
| "learning_rate": 1.3826532320048878e-05, |
| "loss": 0.0286, |
| "mean_token_accuracy": 0.9891203939914703, |
| "num_tokens": 34957824.0, |
| "step": 505 |
| }, |
| { |
| "epoch": 0.35751840168243953, |
| "grad_norm": 0.2628810703754425, |
| "learning_rate": 1.3811276352697828e-05, |
| "loss": 0.0244, |
| "mean_token_accuracy": 0.9905092865228653, |
| "num_tokens": 35303692.0, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.36102348405187523, |
| "grad_norm": 0.3597927689552307, |
| "learning_rate": 1.3795874012715648e-05, |
| "loss": 0.028, |
| "mean_token_accuracy": 0.9879629820585251, |
| "num_tokens": 35645530.0, |
| "step": 515 |
| }, |
| { |
| "epoch": 0.3645285664213109, |
| "grad_norm": 0.32699424028396606, |
| "learning_rate": 1.3780325778330534e-05, |
| "loss": 0.0228, |
| "mean_token_accuracy": 0.9907407641410828, |
| "num_tokens": 35991177.0, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.36803364879074657, |
| "grad_norm": 0.15913930535316467, |
| "learning_rate": 1.3764632132300581e-05, |
| "loss": 0.0198, |
| "mean_token_accuracy": 0.9918981730937958, |
| "num_tokens": 36337605.0, |
| "step": 525 |
| }, |
| { |
| "epoch": 0.37153873116018227, |
| "grad_norm": 0.3119915723800659, |
| "learning_rate": 1.3748793561898764e-05, |
| "loss": 0.0251, |
| "mean_token_accuracy": 0.9895833522081375, |
| "num_tokens": 36681421.0, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.37504381352961796, |
| "grad_norm": 0.39117053151130676, |
| "learning_rate": 1.3732810558897835e-05, |
| "loss": 0.0211, |
| "mean_token_accuracy": 0.9928241014480591, |
| "num_tokens": 37026944.0, |
| "step": 535 |
| }, |
| { |
| "epoch": 0.3785488958990536, |
| "grad_norm": 0.3502909541130066, |
| "learning_rate": 1.3716683619555033e-05, |
| "loss": 0.0263, |
| "mean_token_accuracy": 0.9900463253259659, |
| "num_tokens": 37370755.0, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.3820539782684893, |
| "grad_norm": 0.31072738766670227, |
| "learning_rate": 1.3700413244596699e-05, |
| "loss": 0.0216, |
| "mean_token_accuracy": 0.9909722477197647, |
| "num_tokens": 37714729.0, |
| "step": 545 |
| }, |
| { |
| "epoch": 0.385559060637925, |
| "grad_norm": 0.48028165102005005, |
| "learning_rate": 1.3683999939202699e-05, |
| "loss": 0.0204, |
| "mean_token_accuracy": 0.9930555760860443, |
| "num_tokens": 38060011.0, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.3890641430073607, |
| "grad_norm": 0.23708078265190125, |
| "learning_rate": 1.3667444212990769e-05, |
| "loss": 0.0233, |
| "mean_token_accuracy": 0.9907407701015473, |
| "num_tokens": 38406163.0, |
| "step": 555 |
| }, |
| { |
| "epoch": 0.39256922537679634, |
| "grad_norm": 0.27202486991882324, |
| "learning_rate": 1.3650746580000666e-05, |
| "loss": 0.0317, |
| "mean_token_accuracy": 0.9884259521961212, |
| "num_tokens": 38751788.0, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.39607430774623203, |
| "grad_norm": 0.282675564289093, |
| "learning_rate": 1.3633907558678228e-05, |
| "loss": 0.0203, |
| "mean_token_accuracy": 0.9912037312984466, |
| "num_tokens": 39099308.0, |
| "step": 565 |
| }, |
| { |
| "epoch": 0.39957939011566773, |
| "grad_norm": 0.24003824591636658, |
| "learning_rate": 1.3616927671859265e-05, |
| "loss": 0.0287, |
| "mean_token_accuracy": 0.9895833551883697, |
| "num_tokens": 39444954.0, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.4030844724851034, |
| "grad_norm": 0.3294246196746826, |
| "learning_rate": 1.3599807446753329e-05, |
| "loss": 0.025, |
| "mean_token_accuracy": 0.9914352089166641, |
| "num_tokens": 39791492.0, |
| "step": 575 |
| }, |
| { |
| "epoch": 0.40658955485453907, |
| "grad_norm": 0.22785353660583496, |
| "learning_rate": 1.3582547414927342e-05, |
| "loss": 0.023, |
| "mean_token_accuracy": 0.9909722536802292, |
| "num_tokens": 40135708.0, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.41009463722397477, |
| "grad_norm": 0.21163974702358246, |
| "learning_rate": 1.3565148112289092e-05, |
| "loss": 0.0208, |
| "mean_token_accuracy": 0.9914352118968963, |
| "num_tokens": 40482309.0, |
| "step": 585 |
| }, |
| { |
| "epoch": 0.41359971959341046, |
| "grad_norm": 0.1579979658126831, |
| "learning_rate": 1.3547610079070603e-05, |
| "loss": 0.0226, |
| "mean_token_accuracy": 0.9907407611608505, |
| "num_tokens": 40827349.0, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.4171048019628461, |
| "grad_norm": 0.3718387484550476, |
| "learning_rate": 1.3529933859811347e-05, |
| "loss": 0.0145, |
| "mean_token_accuracy": 0.9944444596767426, |
| "num_tokens": 41173619.0, |
| "step": 595 |
| }, |
| { |
| "epoch": 0.4206098843322818, |
| "grad_norm": 0.350474089384079, |
| "learning_rate": 1.3512120003341342e-05, |
| "loss": 0.0197, |
| "mean_token_accuracy": 0.993055573105812, |
| "num_tokens": 41521399.0, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.4241149667017175, |
| "grad_norm": 0.32240647077560425, |
| "learning_rate": 1.349416906276412e-05, |
| "loss": 0.0182, |
| "mean_token_accuracy": 0.9928241014480591, |
| "num_tokens": 41867601.0, |
| "step": 605 |
| }, |
| { |
| "epoch": 0.4276200490711532, |
| "grad_norm": 0.22535887360572815, |
| "learning_rate": 1.3476081595439533e-05, |
| "loss": 0.0187, |
| "mean_token_accuracy": 0.9921296536922455, |
| "num_tokens": 42213052.0, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.43112513144058884, |
| "grad_norm": 0.215674489736557, |
| "learning_rate": 1.3457858162966473e-05, |
| "loss": 0.021, |
| "mean_token_accuracy": 0.9923611342906952, |
| "num_tokens": 42560556.0, |
| "step": 615 |
| }, |
| { |
| "epoch": 0.43463021381002453, |
| "grad_norm": 0.320464164018631, |
| "learning_rate": 1.3439499331165413e-05, |
| "loss": 0.0264, |
| "mean_token_accuracy": 0.9905092895030976, |
| "num_tokens": 42905238.0, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.43813529617946023, |
| "grad_norm": 0.34197351336479187, |
| "learning_rate": 1.3421005670060854e-05, |
| "loss": 0.0226, |
| "mean_token_accuracy": 0.9918981701135635, |
| "num_tokens": 43251741.0, |
| "step": 625 |
| }, |
| { |
| "epoch": 0.4416403785488959, |
| "grad_norm": 0.20396408438682556, |
| "learning_rate": 1.340237775386362e-05, |
| "loss": 0.0212, |
| "mean_token_accuracy": 0.9918981671333313, |
| "num_tokens": 43597173.0, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.44514546091833157, |
| "grad_norm": 0.23026834428310394, |
| "learning_rate": 1.3383616160953025e-05, |
| "loss": 0.0244, |
| "mean_token_accuracy": 0.990740767121315, |
| "num_tokens": 43942748.0, |
| "step": 635 |
| }, |
| { |
| "epoch": 0.44865054328776727, |
| "grad_norm": 0.39719080924987793, |
| "learning_rate": 1.3364721473858925e-05, |
| "loss": 0.0268, |
| "mean_token_accuracy": 0.9891203939914703, |
| "num_tokens": 44286026.0, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.45215562565720296, |
| "grad_norm": 0.1993078738451004, |
| "learning_rate": 1.334569427924362e-05, |
| "loss": 0.0263, |
| "mean_token_accuracy": 0.9893518805503845, |
| "num_tokens": 44630973.0, |
| "step": 645 |
| }, |
| { |
| "epoch": 0.4556607080266386, |
| "grad_norm": 0.2192801535129547, |
| "learning_rate": 1.332653516788365e-05, |
| "loss": 0.0203, |
| "mean_token_accuracy": 0.9932870596647263, |
| "num_tokens": 44977716.0, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.4591657903960743, |
| "grad_norm": 0.16559746861457825, |
| "learning_rate": 1.3307244734651444e-05, |
| "loss": 0.0205, |
| "mean_token_accuracy": 0.992361131310463, |
| "num_tokens": 45323673.0, |
| "step": 655 |
| }, |
| { |
| "epoch": 0.46267087276551, |
| "grad_norm": 0.39821863174438477, |
| "learning_rate": 1.3287823578496848e-05, |
| "loss": 0.0225, |
| "mean_token_accuracy": 0.9912037283182145, |
| "num_tokens": 45668268.0, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.4661759551349457, |
| "grad_norm": 0.30601146817207336, |
| "learning_rate": 1.3268272302428538e-05, |
| "loss": 0.0238, |
| "mean_token_accuracy": 0.9918981730937958, |
| "num_tokens": 46012933.0, |
| "step": 665 |
| }, |
| { |
| "epoch": 0.46968103750438134, |
| "grad_norm": 0.1988631635904312, |
| "learning_rate": 1.3248591513495287e-05, |
| "loss": 0.0227, |
| "mean_token_accuracy": 0.9918981790542603, |
| "num_tokens": 46359392.0, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.47318611987381703, |
| "grad_norm": 0.21044372022151947, |
| "learning_rate": 1.3228781822767123e-05, |
| "loss": 0.0197, |
| "mean_token_accuracy": 0.9932870537042617, |
| "num_tokens": 46708087.0, |
| "step": 675 |
| }, |
| { |
| "epoch": 0.47669120224325273, |
| "grad_norm": 0.246845081448555, |
| "learning_rate": 1.3208843845316351e-05, |
| "loss": 0.0262, |
| "mean_token_accuracy": 0.9902777969837189, |
| "num_tokens": 47053413.0, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.4801962846126884, |
| "grad_norm": 0.304241418838501, |
| "learning_rate": 1.3188778200198464e-05, |
| "loss": 0.0199, |
| "mean_token_accuracy": 0.9930555760860443, |
| "num_tokens": 47399096.0, |
| "step": 685 |
| }, |
| { |
| "epoch": 0.48370136698212407, |
| "grad_norm": 0.3896429240703583, |
| "learning_rate": 1.3168585510432912e-05, |
| "loss": 0.0239, |
| "mean_token_accuracy": 0.9907407611608505, |
| "num_tokens": 47746091.0, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.48720644935155977, |
| "grad_norm": 0.19101302325725555, |
| "learning_rate": 1.3148266402983764e-05, |
| "loss": 0.0241, |
| "mean_token_accuracy": 0.9909722536802292, |
| "num_tokens": 48093067.0, |
| "step": 695 |
| }, |
| { |
| "epoch": 0.49071153172099546, |
| "grad_norm": 0.3942578434944153, |
| "learning_rate": 1.3127821508740234e-05, |
| "loss": 0.0237, |
| "mean_token_accuracy": 0.9909722477197647, |
| "num_tokens": 48440358.0, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.4942166140904311, |
| "grad_norm": 0.25786906480789185, |
| "learning_rate": 1.3107251462497104e-05, |
| "loss": 0.0172, |
| "mean_token_accuracy": 0.9937500178813934, |
| "num_tokens": 48785888.0, |
| "step": 705 |
| }, |
| { |
| "epoch": 0.4977216964598668, |
| "grad_norm": 0.25595828890800476, |
| "learning_rate": 1.308655690293501e-05, |
| "loss": 0.0211, |
| "mean_token_accuracy": 0.9921296566724778, |
| "num_tokens": 49133883.0, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.5012267788293024, |
| "grad_norm": 0.4982813000679016, |
| "learning_rate": 1.30657384726006e-05, |
| "loss": 0.0246, |
| "mean_token_accuracy": 0.9907407641410828, |
| "num_tokens": 49479461.0, |
| "step": 715 |
| }, |
| { |
| "epoch": 0.5047318611987381, |
| "grad_norm": 0.17003466188907623, |
| "learning_rate": 1.3044796817886604e-05, |
| "loss": 0.0231, |
| "mean_token_accuracy": 0.990740767121315, |
| "num_tokens": 49826669.0, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.5082369435681738, |
| "grad_norm": 0.48894596099853516, |
| "learning_rate": 1.302373258901175e-05, |
| "loss": 0.0271, |
| "mean_token_accuracy": 0.9895833522081375, |
| "num_tokens": 50173702.0, |
| "step": 725 |
| }, |
| { |
| "epoch": 0.5117420259376095, |
| "grad_norm": 0.19587291777133942, |
| "learning_rate": 1.3002546440000574e-05, |
| "loss": 0.0203, |
| "mean_token_accuracy": 0.9928240954875946, |
| "num_tokens": 50520986.0, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.5152471083070452, |
| "grad_norm": 0.16303904354572296, |
| "learning_rate": 1.2981239028663118e-05, |
| "loss": 0.02, |
| "mean_token_accuracy": 0.9928240984678268, |
| "num_tokens": 50869887.0, |
| "step": 735 |
| }, |
| { |
| "epoch": 0.5187521906764809, |
| "grad_norm": 0.40286949276924133, |
| "learning_rate": 1.2959811016574516e-05, |
| "loss": 0.0202, |
| "mean_token_accuracy": 0.9925926148891449, |
| "num_tokens": 51215571.0, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.5222572730459166, |
| "grad_norm": 0.28973695635795593, |
| "learning_rate": 1.293826306905443e-05, |
| "loss": 0.0151, |
| "mean_token_accuracy": 0.9956018686294555, |
| "num_tokens": 51565405.0, |
| "step": 745 |
| }, |
| { |
| "epoch": 0.5257623554153522, |
| "grad_norm": 0.22685499489307404, |
| "learning_rate": 1.291659585514641e-05, |
| "loss": 0.0238, |
| "mean_token_accuracy": 0.9909722477197647, |
| "num_tokens": 51909491.0, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.5292674377847879, |
| "grad_norm": 0.3714602589607239, |
| "learning_rate": 1.2894810047597117e-05, |
| "loss": 0.0216, |
| "mean_token_accuracy": 0.9916666924953461, |
| "num_tokens": 52254972.0, |
| "step": 755 |
| }, |
| { |
| "epoch": 0.5327725201542236, |
| "grad_norm": 0.3512303829193115, |
| "learning_rate": 1.2872906322835427e-05, |
| "loss": 0.0216, |
| "mean_token_accuracy": 0.9912037342786789, |
| "num_tokens": 52600661.0, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.5362776025236593, |
| "grad_norm": 0.40395596623420715, |
| "learning_rate": 1.2850885360951444e-05, |
| "loss": 0.0238, |
| "mean_token_accuracy": 0.9912037253379822, |
| "num_tokens": 52947400.0, |
| "step": 765 |
| }, |
| { |
| "epoch": 0.539782684893095, |
| "grad_norm": 0.17548592388629913, |
| "learning_rate": 1.2828747845675365e-05, |
| "loss": 0.0209, |
| "mean_token_accuracy": 0.9921296536922455, |
| "num_tokens": 53292011.0, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.5432877672625307, |
| "grad_norm": 0.2115519940853119, |
| "learning_rate": 1.2806494464356268e-05, |
| "loss": 0.0202, |
| "mean_token_accuracy": 0.9925926208496094, |
| "num_tokens": 53637287.0, |
| "step": 775 |
| }, |
| { |
| "epoch": 0.5467928496319664, |
| "grad_norm": 0.23128850758075714, |
| "learning_rate": 1.2784125907940757e-05, |
| "loss": 0.0228, |
| "mean_token_accuracy": 0.9916666895151138, |
| "num_tokens": 53984793.0, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.550297932001402, |
| "grad_norm": 0.18116140365600586, |
| "learning_rate": 1.2761642870951521e-05, |
| "loss": 0.024, |
| "mean_token_accuracy": 0.9916666895151138, |
| "num_tokens": 54332790.0, |
| "step": 785 |
| }, |
| { |
| "epoch": 0.5538030143708377, |
| "grad_norm": 0.17702384293079376, |
| "learning_rate": 1.2739046051465753e-05, |
| "loss": 0.0257, |
| "mean_token_accuracy": 0.992361131310463, |
| "num_tokens": 54676947.0, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.5573080967402734, |
| "grad_norm": 0.1663278341293335, |
| "learning_rate": 1.2716336151093504e-05, |
| "loss": 0.0239, |
| "mean_token_accuracy": 0.9907407641410828, |
| "num_tokens": 55022329.0, |
| "step": 795 |
| }, |
| { |
| "epoch": 0.5608131791097091, |
| "grad_norm": 0.203016459941864, |
| "learning_rate": 1.2693513874955856e-05, |
| "loss": 0.0192, |
| "mean_token_accuracy": 0.9925926119089127, |
| "num_tokens": 55370670.0, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.5643182614791448, |
| "grad_norm": 0.22700652480125427, |
| "learning_rate": 1.2670579931663075e-05, |
| "loss": 0.021, |
| "mean_token_accuracy": 0.9912037283182145, |
| "num_tokens": 55714180.0, |
| "step": 805 |
| }, |
| { |
| "epoch": 0.5678233438485805, |
| "grad_norm": 0.14696234464645386, |
| "learning_rate": 1.2647535033292579e-05, |
| "loss": 0.0179, |
| "mean_token_accuracy": 0.993750023841858, |
| "num_tokens": 56058942.0, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.5713284262180162, |
| "grad_norm": 0.19595181941986084, |
| "learning_rate": 1.2624379895366826e-05, |
| "loss": 0.0207, |
| "mean_token_accuracy": 0.9932870596647263, |
| "num_tokens": 56405485.0, |
| "step": 815 |
| }, |
| { |
| "epoch": 0.5748335085874519, |
| "grad_norm": 0.3681330680847168, |
| "learning_rate": 1.2601115236831133e-05, |
| "loss": 0.0211, |
| "mean_token_accuracy": 0.9923611283302307, |
| "num_tokens": 56751094.0, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.5783385909568874, |
| "grad_norm": 0.18621279299259186, |
| "learning_rate": 1.2577741780031305e-05, |
| "loss": 0.0212, |
| "mean_token_accuracy": 0.991898176074028, |
| "num_tokens": 57098566.0, |
| "step": 825 |
| }, |
| { |
| "epoch": 0.5818436733263231, |
| "grad_norm": 0.5042465329170227, |
| "learning_rate": 1.2554260250691247e-05, |
| "loss": 0.0262, |
| "mean_token_accuracy": 0.9900463193655014, |
| "num_tokens": 57444269.0, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.5853487556957588, |
| "grad_norm": 0.34705427289009094, |
| "learning_rate": 1.2530671377890408e-05, |
| "loss": 0.0248, |
| "mean_token_accuracy": 0.990972250699997, |
| "num_tokens": 57788886.0, |
| "step": 835 |
| }, |
| { |
| "epoch": 0.5888538380651945, |
| "grad_norm": 0.21251268684864044, |
| "learning_rate": 1.2506975894041152e-05, |
| "loss": 0.0185, |
| "mean_token_accuracy": 0.9930555760860443, |
| "num_tokens": 58135230.0, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.5923589204346302, |
| "grad_norm": 0.32092639803886414, |
| "learning_rate": 1.2483174534866015e-05, |
| "loss": 0.0222, |
| "mean_token_accuracy": 0.9925926089286804, |
| "num_tokens": 58477843.0, |
| "step": 845 |
| }, |
| { |
| "epoch": 0.5958640028040659, |
| "grad_norm": 0.3195016086101532, |
| "learning_rate": 1.2459268039374866e-05, |
| "loss": 0.0227, |
| "mean_token_accuracy": 0.9916666895151138, |
| "num_tokens": 58822570.0, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.5993690851735016, |
| "grad_norm": 0.39674413204193115, |
| "learning_rate": 1.2435257149841951e-05, |
| "loss": 0.019, |
| "mean_token_accuracy": 0.9932870626449585, |
| "num_tokens": 59171737.0, |
| "step": 855 |
| }, |
| { |
| "epoch": 0.6028741675429372, |
| "grad_norm": 0.1586899757385254, |
| "learning_rate": 1.2411142611782862e-05, |
| "loss": 0.0213, |
| "mean_token_accuracy": 0.9912037283182145, |
| "num_tokens": 59517800.0, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.6063792499123729, |
| "grad_norm": 0.284656822681427, |
| "learning_rate": 1.2386925173931375e-05, |
| "loss": 0.0209, |
| "mean_token_accuracy": 0.9928240954875946, |
| "num_tokens": 59862858.0, |
| "step": 865 |
| }, |
| { |
| "epoch": 0.6098843322818086, |
| "grad_norm": 0.6032276153564453, |
| "learning_rate": 1.2362605588216207e-05, |
| "loss": 0.0215, |
| "mean_token_accuracy": 0.9928241014480591, |
| "num_tokens": 60210881.0, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.6133894146512443, |
| "grad_norm": 0.15096986293792725, |
| "learning_rate": 1.2338184609737674e-05, |
| "loss": 0.0232, |
| "mean_token_accuracy": 0.9914351999759674, |
| "num_tokens": 60553976.0, |
| "step": 875 |
| }, |
| { |
| "epoch": 0.61689449702068, |
| "grad_norm": 0.23778441548347473, |
| "learning_rate": 1.2313662996744242e-05, |
| "loss": 0.0249, |
| "mean_token_accuracy": 0.990740767121315, |
| "num_tokens": 60900821.0, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.6203995793901157, |
| "grad_norm": 0.22427886724472046, |
| "learning_rate": 1.228904151060898e-05, |
| "loss": 0.0181, |
| "mean_token_accuracy": 0.9930555790662765, |
| "num_tokens": 61247776.0, |
| "step": 885 |
| }, |
| { |
| "epoch": 0.6239046617595514, |
| "grad_norm": 0.1573123037815094, |
| "learning_rate": 1.226432091580593e-05, |
| "loss": 0.0199, |
| "mean_token_accuracy": 0.9923611402511596, |
| "num_tokens": 61593112.0, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.627409744128987, |
| "grad_norm": 0.2529422342777252, |
| "learning_rate": 1.2239501979886356e-05, |
| "loss": 0.0256, |
| "mean_token_accuracy": 0.9900463223457336, |
| "num_tokens": 61937169.0, |
| "step": 895 |
| }, |
| { |
| "epoch": 0.6309148264984227, |
| "grad_norm": 0.1565939337015152, |
| "learning_rate": 1.2214585473454935e-05, |
| "loss": 0.0223, |
| "mean_token_accuracy": 0.9923611372709275, |
| "num_tokens": 62283554.0, |
| "step": 900 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 2854, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.1493963380099645e+18, |
| "train_batch_size": 6, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
