| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.18002726127099247, |
| "eval_steps": 500, |
| "global_step": 3500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 10.742102813720702, |
| "epoch": 0.0002571818018157035, |
| "grad_norm": 5.21875, |
| "learning_rate": 2e-06, |
| "loss": 10.7614, |
| "mean_token_accuracy": 8.620689623057842e-05, |
| "num_tokens": 9573.0, |
| "step": 5 |
| }, |
| { |
| "entropy": 10.742151069641114, |
| "epoch": 0.000514363603631407, |
| "grad_norm": 4.84375, |
| "learning_rate": 4.5e-06, |
| "loss": 10.7583, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 18933.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 10.742130088806153, |
| "epoch": 0.0007715454054471106, |
| "grad_norm": 5.21875, |
| "learning_rate": 7e-06, |
| "loss": 10.7448, |
| "mean_token_accuracy": 0.0, |
| "num_tokens": 29028.0, |
| "step": 15 |
| }, |
| { |
| "entropy": 10.742134284973144, |
| "epoch": 0.001028727207262814, |
| "grad_norm": 4.9375, |
| "learning_rate": 9.5e-06, |
| "loss": 10.6881, |
| "mean_token_accuracy": 0.00012970168609172106, |
| "num_tokens": 37987.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 10.742049884796142, |
| "epoch": 0.0012859090090785177, |
| "grad_norm": 4.4375, |
| "learning_rate": 1.2e-05, |
| "loss": 10.5852, |
| "mean_token_accuracy": 0.0029032987426035107, |
| "num_tokens": 47163.0, |
| "step": 25 |
| }, |
| { |
| "entropy": 10.741710948944093, |
| "epoch": 0.0015430908108942211, |
| "grad_norm": 4.25, |
| "learning_rate": 1.4500000000000002e-05, |
| "loss": 10.4809, |
| "mean_token_accuracy": 0.02479298785328865, |
| "num_tokens": 56096.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 10.740671920776368, |
| "epoch": 0.0018002726127099246, |
| "grad_norm": 3.296875, |
| "learning_rate": 1.7000000000000003e-05, |
| "loss": 10.3641, |
| "mean_token_accuracy": 0.03960379287600517, |
| "num_tokens": 65823.0, |
| "step": 35 |
| }, |
| { |
| "entropy": 10.737626838684083, |
| "epoch": 0.002057454414525628, |
| "grad_norm": 2.578125, |
| "learning_rate": 1.95e-05, |
| "loss": 10.2147, |
| "mean_token_accuracy": 0.04078627172857523, |
| "num_tokens": 75005.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 10.73199462890625, |
| "epoch": 0.0023146362163413317, |
| "grad_norm": 2.53125, |
| "learning_rate": 2.2e-05, |
| "loss": 10.1015, |
| "mean_token_accuracy": 0.04431910365819931, |
| "num_tokens": 83340.0, |
| "step": 45 |
| }, |
| { |
| "entropy": 10.72521743774414, |
| "epoch": 0.0025718180181570354, |
| "grad_norm": 2.140625, |
| "learning_rate": 2.4500000000000003e-05, |
| "loss": 10.0212, |
| "mean_token_accuracy": 0.049253365769982335, |
| "num_tokens": 92004.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 10.719530010223389, |
| "epoch": 0.0028289998199727386, |
| "grad_norm": 2.078125, |
| "learning_rate": 2.7e-05, |
| "loss": 9.9673, |
| "mean_token_accuracy": 0.04715999849140644, |
| "num_tokens": 101196.0, |
| "step": 55 |
| }, |
| { |
| "entropy": 10.713758850097657, |
| "epoch": 0.0030861816217884423, |
| "grad_norm": 2.078125, |
| "learning_rate": 2.95e-05, |
| "loss": 9.8887, |
| "mean_token_accuracy": 0.04930844120681286, |
| "num_tokens": 109931.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 10.709882545471192, |
| "epoch": 0.003343363423604146, |
| "grad_norm": 2.0625, |
| "learning_rate": 3.2e-05, |
| "loss": 9.8563, |
| "mean_token_accuracy": 0.046213630586862564, |
| "num_tokens": 118450.0, |
| "step": 65 |
| }, |
| { |
| "entropy": 10.70816535949707, |
| "epoch": 0.003600545225419849, |
| "grad_norm": 1.96875, |
| "learning_rate": 3.4500000000000005e-05, |
| "loss": 9.7843, |
| "mean_token_accuracy": 0.04638329595327377, |
| "num_tokens": 127311.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 10.705178928375243, |
| "epoch": 0.003857727027235553, |
| "grad_norm": 1.875, |
| "learning_rate": 3.7e-05, |
| "loss": 9.7153, |
| "mean_token_accuracy": 0.05029761902987957, |
| "num_tokens": 136529.0, |
| "step": 75 |
| }, |
| { |
| "entropy": 10.696865940093994, |
| "epoch": 0.004114908829051256, |
| "grad_norm": 1.828125, |
| "learning_rate": 3.95e-05, |
| "loss": 9.6593, |
| "mean_token_accuracy": 0.050337107852101326, |
| "num_tokens": 145754.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 10.685219669342041, |
| "epoch": 0.00437209063086696, |
| "grad_norm": 1.8046875, |
| "learning_rate": 4.2000000000000004e-05, |
| "loss": 9.6217, |
| "mean_token_accuracy": 0.04981501027941704, |
| "num_tokens": 155229.0, |
| "step": 85 |
| }, |
| { |
| "entropy": 10.669653797149659, |
| "epoch": 0.004629272432682663, |
| "grad_norm": 1.8984375, |
| "learning_rate": 4.45e-05, |
| "loss": 9.4894, |
| "mean_token_accuracy": 0.06370054408907891, |
| "num_tokens": 163766.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 10.649745845794678, |
| "epoch": 0.004886454234498367, |
| "grad_norm": 1.7265625, |
| "learning_rate": 4.7000000000000004e-05, |
| "loss": 9.4341, |
| "mean_token_accuracy": 0.05732584930956364, |
| "num_tokens": 172309.0, |
| "step": 95 |
| }, |
| { |
| "entropy": 10.618613624572754, |
| "epoch": 0.005143636036314071, |
| "grad_norm": 1.7421875, |
| "learning_rate": 4.9500000000000004e-05, |
| "loss": 9.2855, |
| "mean_token_accuracy": 0.06327233165502548, |
| "num_tokens": 180242.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 10.569914817810059, |
| "epoch": 0.0054008178381297735, |
| "grad_norm": 1.75, |
| "learning_rate": 5.2e-05, |
| "loss": 9.2324, |
| "mean_token_accuracy": 0.060527439787983896, |
| "num_tokens": 189044.0, |
| "step": 105 |
| }, |
| { |
| "entropy": 10.520080757141113, |
| "epoch": 0.005657999639945477, |
| "grad_norm": 1.5390625, |
| "learning_rate": 5.45e-05, |
| "loss": 9.1122, |
| "mean_token_accuracy": 0.06187737137079239, |
| "num_tokens": 197779.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 10.468755054473878, |
| "epoch": 0.005915181441761181, |
| "grad_norm": 1.5859375, |
| "learning_rate": 5.7e-05, |
| "loss": 8.9561, |
| "mean_token_accuracy": 0.06379008032381535, |
| "num_tokens": 206025.0, |
| "step": 115 |
| }, |
| { |
| "entropy": 10.407035160064698, |
| "epoch": 0.0061723632435768845, |
| "grad_norm": 1.453125, |
| "learning_rate": 5.9499999999999996e-05, |
| "loss": 8.9663, |
| "mean_token_accuracy": 0.05617102049291134, |
| "num_tokens": 216620.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 10.3653733253479, |
| "epoch": 0.006429545045392588, |
| "grad_norm": 1.375, |
| "learning_rate": 6.2e-05, |
| "loss": 8.7968, |
| "mean_token_accuracy": 0.059108608216047284, |
| "num_tokens": 225654.0, |
| "step": 125 |
| }, |
| { |
| "entropy": 10.301421070098877, |
| "epoch": 0.006686726847208292, |
| "grad_norm": 1.4609375, |
| "learning_rate": 6.450000000000001e-05, |
| "loss": 8.6036, |
| "mean_token_accuracy": 0.06164416745305061, |
| "num_tokens": 233967.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 10.185540676116943, |
| "epoch": 0.006943908649023995, |
| "grad_norm": 1.4140625, |
| "learning_rate": 6.7e-05, |
| "loss": 8.5469, |
| "mean_token_accuracy": 0.06072752773761749, |
| "num_tokens": 241911.0, |
| "step": 135 |
| }, |
| { |
| "entropy": 10.0550705909729, |
| "epoch": 0.007201090450839698, |
| "grad_norm": 1.25, |
| "learning_rate": 6.950000000000001e-05, |
| "loss": 8.4323, |
| "mean_token_accuracy": 0.06439580023288727, |
| "num_tokens": 250771.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 9.967238235473634, |
| "epoch": 0.007458272252655402, |
| "grad_norm": 1.1171875, |
| "learning_rate": 7.2e-05, |
| "loss": 8.3391, |
| "mean_token_accuracy": 0.06209088861942291, |
| "num_tokens": 260036.0, |
| "step": 145 |
| }, |
| { |
| "entropy": 9.832792282104492, |
| "epoch": 0.007715454054471106, |
| "grad_norm": 1.1875, |
| "learning_rate": 7.45e-05, |
| "loss": 8.2272, |
| "mean_token_accuracy": 0.06231529638171196, |
| "num_tokens": 268614.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 9.642397022247314, |
| "epoch": 0.00797263585628681, |
| "grad_norm": 1.0546875, |
| "learning_rate": 7.7e-05, |
| "loss": 8.085, |
| "mean_token_accuracy": 0.06268828995525837, |
| "num_tokens": 278205.0, |
| "step": 155 |
| }, |
| { |
| "entropy": 9.471720123291016, |
| "epoch": 0.008229817658102512, |
| "grad_norm": 1.109375, |
| "learning_rate": 7.950000000000001e-05, |
| "loss": 8.0285, |
| "mean_token_accuracy": 0.054571619257330894, |
| "num_tokens": 287369.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 9.277729606628418, |
| "epoch": 0.008486999459918217, |
| "grad_norm": 0.9765625, |
| "learning_rate": 8.2e-05, |
| "loss": 7.8389, |
| "mean_token_accuracy": 0.0658249743282795, |
| "num_tokens": 295469.0, |
| "step": 165 |
| }, |
| { |
| "entropy": 9.065653324127197, |
| "epoch": 0.00874418126173392, |
| "grad_norm": 0.875, |
| "learning_rate": 8.450000000000001e-05, |
| "loss": 7.8802, |
| "mean_token_accuracy": 0.05946259275078773, |
| "num_tokens": 304108.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 8.9242995262146, |
| "epoch": 0.009001363063549624, |
| "grad_norm": 0.83203125, |
| "learning_rate": 8.7e-05, |
| "loss": 7.7549, |
| "mean_token_accuracy": 0.06102342195808887, |
| "num_tokens": 312797.0, |
| "step": 175 |
| }, |
| { |
| "entropy": 8.724368000030518, |
| "epoch": 0.009258544865365327, |
| "grad_norm": 0.89453125, |
| "learning_rate": 8.95e-05, |
| "loss": 7.726, |
| "mean_token_accuracy": 0.05993276461958885, |
| "num_tokens": 321947.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 8.550490474700927, |
| "epoch": 0.00951572666718103, |
| "grad_norm": 0.859375, |
| "learning_rate": 9.2e-05, |
| "loss": 7.7268, |
| "mean_token_accuracy": 0.06107203662395477, |
| "num_tokens": 330881.0, |
| "step": 185 |
| }, |
| { |
| "entropy": 8.48734483718872, |
| "epoch": 0.009772908468996734, |
| "grad_norm": 0.8125, |
| "learning_rate": 9.45e-05, |
| "loss": 7.6738, |
| "mean_token_accuracy": 0.06392239518463612, |
| "num_tokens": 339615.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 8.382297706604003, |
| "epoch": 0.010030090270812437, |
| "grad_norm": 0.9765625, |
| "learning_rate": 9.7e-05, |
| "loss": 7.5319, |
| "mean_token_accuracy": 0.0668424092233181, |
| "num_tokens": 347445.0, |
| "step": 195 |
| }, |
| { |
| "entropy": 8.23064022064209, |
| "epoch": 0.010287272072628141, |
| "grad_norm": 0.81640625, |
| "learning_rate": 9.95e-05, |
| "loss": 7.6527, |
| "mean_token_accuracy": 0.0642503272742033, |
| "num_tokens": 356466.0, |
| "step": 200 |
| }, |
| { |
| "entropy": 8.293260860443116, |
| "epoch": 0.010544453874443844, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.000102, |
| "loss": 7.6586, |
| "mean_token_accuracy": 0.06924829706549644, |
| "num_tokens": 364582.0, |
| "step": 205 |
| }, |
| { |
| "entropy": 8.233483600616456, |
| "epoch": 0.010801635676259547, |
| "grad_norm": 0.87890625, |
| "learning_rate": 0.00010449999999999999, |
| "loss": 7.5999, |
| "mean_token_accuracy": 0.06699038669466972, |
| "num_tokens": 373816.0, |
| "step": 210 |
| }, |
| { |
| "entropy": 8.192768096923828, |
| "epoch": 0.011058817478075252, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.000107, |
| "loss": 7.6079, |
| "mean_token_accuracy": 0.06721281111240388, |
| "num_tokens": 382663.0, |
| "step": 215 |
| }, |
| { |
| "entropy": 8.15766954421997, |
| "epoch": 0.011315999279890954, |
| "grad_norm": 0.875, |
| "learning_rate": 0.0001095, |
| "loss": 7.5084, |
| "mean_token_accuracy": 0.06859233565628528, |
| "num_tokens": 391146.0, |
| "step": 220 |
| }, |
| { |
| "entropy": 8.103716373443604, |
| "epoch": 0.011573181081706659, |
| "grad_norm": 0.8125, |
| "learning_rate": 0.000112, |
| "loss": 7.5845, |
| "mean_token_accuracy": 0.06810487173497677, |
| "num_tokens": 400693.0, |
| "step": 225 |
| }, |
| { |
| "entropy": 8.105987453460694, |
| "epoch": 0.011830362883522362, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0001145, |
| "loss": 7.539, |
| "mean_token_accuracy": 0.06601319462060928, |
| "num_tokens": 409706.0, |
| "step": 230 |
| }, |
| { |
| "entropy": 8.056668090820313, |
| "epoch": 0.012087544685338066, |
| "grad_norm": 0.9140625, |
| "learning_rate": 0.00011700000000000001, |
| "loss": 7.4696, |
| "mean_token_accuracy": 0.06857900470495223, |
| "num_tokens": 418717.0, |
| "step": 235 |
| }, |
| { |
| "entropy": 8.077108192443848, |
| "epoch": 0.012344726487153769, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00011949999999999999, |
| "loss": 7.5335, |
| "mean_token_accuracy": 0.06780378967523575, |
| "num_tokens": 428630.0, |
| "step": 240 |
| }, |
| { |
| "entropy": 8.065593910217284, |
| "epoch": 0.012601908288969472, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.000122, |
| "loss": 7.559, |
| "mean_token_accuracy": 0.06397245228290557, |
| "num_tokens": 438762.0, |
| "step": 245 |
| }, |
| { |
| "entropy": 8.016668844223023, |
| "epoch": 0.012859090090785176, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001245, |
| "loss": 7.4803, |
| "mean_token_accuracy": 0.06500645838677883, |
| "num_tokens": 447419.0, |
| "step": 250 |
| }, |
| { |
| "entropy": 8.066792869567871, |
| "epoch": 0.01311627189260088, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.000127, |
| "loss": 7.4872, |
| "mean_token_accuracy": 0.07560092583298683, |
| "num_tokens": 455818.0, |
| "step": 255 |
| }, |
| { |
| "entropy": 8.00608172416687, |
| "epoch": 0.013373453694416584, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0001295, |
| "loss": 7.4407, |
| "mean_token_accuracy": 0.0703579068183899, |
| "num_tokens": 464411.0, |
| "step": 260 |
| }, |
| { |
| "entropy": 8.006528282165528, |
| "epoch": 0.013630635496232286, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.000132, |
| "loss": 7.4791, |
| "mean_token_accuracy": 0.07310711704194546, |
| "num_tokens": 473181.0, |
| "step": 265 |
| }, |
| { |
| "entropy": 7.954403877258301, |
| "epoch": 0.01388781729804799, |
| "grad_norm": 0.890625, |
| "learning_rate": 0.00013450000000000002, |
| "loss": 7.3802, |
| "mean_token_accuracy": 0.07561531476676464, |
| "num_tokens": 481776.0, |
| "step": 270 |
| }, |
| { |
| "entropy": 7.960335302352905, |
| "epoch": 0.014144999099863694, |
| "grad_norm": 0.91796875, |
| "learning_rate": 0.00013700000000000002, |
| "loss": 7.3739, |
| "mean_token_accuracy": 0.07225163355469703, |
| "num_tokens": 490482.0, |
| "step": 275 |
| }, |
| { |
| "entropy": 7.908543682098388, |
| "epoch": 0.014402180901679397, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0001395, |
| "loss": 7.3373, |
| "mean_token_accuracy": 0.08000247925519943, |
| "num_tokens": 498394.0, |
| "step": 280 |
| }, |
| { |
| "entropy": 7.912304162979126, |
| "epoch": 0.014659362703495101, |
| "grad_norm": 1.3671875, |
| "learning_rate": 0.00014199999999999998, |
| "loss": 7.3847, |
| "mean_token_accuracy": 0.07234559133648873, |
| "num_tokens": 507194.0, |
| "step": 285 |
| }, |
| { |
| "entropy": 7.905929660797119, |
| "epoch": 0.014916544505310804, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0001445, |
| "loss": 7.3824, |
| "mean_token_accuracy": 0.07954801470041276, |
| "num_tokens": 515538.0, |
| "step": 290 |
| }, |
| { |
| "entropy": 7.906702852249145, |
| "epoch": 0.015173726307126508, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.000147, |
| "loss": 7.4258, |
| "mean_token_accuracy": 0.0705490980297327, |
| "num_tokens": 524544.0, |
| "step": 295 |
| }, |
| { |
| "entropy": 7.956319189071655, |
| "epoch": 0.015430908108942211, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.0001495, |
| "loss": 7.3581, |
| "mean_token_accuracy": 0.0792141430079937, |
| "num_tokens": 533096.0, |
| "step": 300 |
| }, |
| { |
| "entropy": 7.908858060836792, |
| "epoch": 0.015688089910757916, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.000152, |
| "loss": 7.2829, |
| "mean_token_accuracy": 0.07599962502717972, |
| "num_tokens": 542254.0, |
| "step": 305 |
| }, |
| { |
| "entropy": 7.929060173034668, |
| "epoch": 0.01594527171257362, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.00015450000000000001, |
| "loss": 7.3804, |
| "mean_token_accuracy": 0.07816362082958221, |
| "num_tokens": 550985.0, |
| "step": 310 |
| }, |
| { |
| "entropy": 7.865027332305909, |
| "epoch": 0.01620245351438932, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000157, |
| "loss": 7.3625, |
| "mean_token_accuracy": 0.07863678447902203, |
| "num_tokens": 560224.0, |
| "step": 315 |
| }, |
| { |
| "entropy": 7.856458759307861, |
| "epoch": 0.016459635316205024, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.0001595, |
| "loss": 7.2099, |
| "mean_token_accuracy": 0.0831373617053032, |
| "num_tokens": 569268.0, |
| "step": 320 |
| }, |
| { |
| "entropy": 7.8261981964111325, |
| "epoch": 0.01671681711802073, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000162, |
| "loss": 7.305, |
| "mean_token_accuracy": 0.07629284039139747, |
| "num_tokens": 577876.0, |
| "step": 325 |
| }, |
| { |
| "entropy": 7.825508499145508, |
| "epoch": 0.016973998919836433, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.00016450000000000001, |
| "loss": 7.1964, |
| "mean_token_accuracy": 0.08476228266954422, |
| "num_tokens": 586622.0, |
| "step": 330 |
| }, |
| { |
| "entropy": 7.87431845664978, |
| "epoch": 0.017231180721652136, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00016700000000000002, |
| "loss": 7.3968, |
| "mean_token_accuracy": 0.07733883932232857, |
| "num_tokens": 596544.0, |
| "step": 335 |
| }, |
| { |
| "entropy": 7.786734390258789, |
| "epoch": 0.01748836252346784, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00016950000000000003, |
| "loss": 7.2342, |
| "mean_token_accuracy": 0.07911348566412926, |
| "num_tokens": 605349.0, |
| "step": 340 |
| }, |
| { |
| "entropy": 7.809148788452148, |
| "epoch": 0.01774554432528354, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.00017199999999999998, |
| "loss": 7.2457, |
| "mean_token_accuracy": 0.07915201708674431, |
| "num_tokens": 614266.0, |
| "step": 345 |
| }, |
| { |
| "entropy": 7.771593856811523, |
| "epoch": 0.018002726127099248, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00017449999999999999, |
| "loss": 7.2829, |
| "mean_token_accuracy": 0.07773459404706955, |
| "num_tokens": 622534.0, |
| "step": 350 |
| }, |
| { |
| "entropy": 7.822271633148193, |
| "epoch": 0.01825990792891495, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000177, |
| "loss": 7.2365, |
| "mean_token_accuracy": 0.08085938617587089, |
| "num_tokens": 631838.0, |
| "step": 355 |
| }, |
| { |
| "entropy": 7.698997259140015, |
| "epoch": 0.018517089730730654, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0001795, |
| "loss": 7.2539, |
| "mean_token_accuracy": 0.08351444229483604, |
| "num_tokens": 641386.0, |
| "step": 360 |
| }, |
| { |
| "entropy": 7.703382873535157, |
| "epoch": 0.018774271532546356, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000182, |
| "loss": 7.2384, |
| "mean_token_accuracy": 0.0824521966278553, |
| "num_tokens": 650465.0, |
| "step": 365 |
| }, |
| { |
| "entropy": 7.835447978973389, |
| "epoch": 0.01903145333436206, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001845, |
| "loss": 7.1401, |
| "mean_token_accuracy": 0.08636756986379623, |
| "num_tokens": 659509.0, |
| "step": 370 |
| }, |
| { |
| "entropy": 7.586853075027466, |
| "epoch": 0.019288635136177765, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000187, |
| "loss": 7.1678, |
| "mean_token_accuracy": 0.08730523958802223, |
| "num_tokens": 668137.0, |
| "step": 375 |
| }, |
| { |
| "entropy": 7.862004041671753, |
| "epoch": 0.019545816937993468, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0001895, |
| "loss": 7.2499, |
| "mean_token_accuracy": 0.0831152357161045, |
| "num_tokens": 677784.0, |
| "step": 380 |
| }, |
| { |
| "entropy": 7.637575674057007, |
| "epoch": 0.01980299873980917, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000192, |
| "loss": 7.1701, |
| "mean_token_accuracy": 0.08491914793848991, |
| "num_tokens": 686088.0, |
| "step": 385 |
| }, |
| { |
| "entropy": 7.752926158905029, |
| "epoch": 0.020060180541624874, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0001945, |
| "loss": 7.3326, |
| "mean_token_accuracy": 0.08027631081640721, |
| "num_tokens": 695131.0, |
| "step": 390 |
| }, |
| { |
| "entropy": 7.793869876861573, |
| "epoch": 0.020317362343440577, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00019700000000000002, |
| "loss": 7.1152, |
| "mean_token_accuracy": 0.08675874844193458, |
| "num_tokens": 703976.0, |
| "step": 395 |
| }, |
| { |
| "entropy": 7.674239635467529, |
| "epoch": 0.020574544145256283, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.00019950000000000002, |
| "loss": 7.1607, |
| "mean_token_accuracy": 0.08738962039351464, |
| "num_tokens": 712080.0, |
| "step": 400 |
| }, |
| { |
| "entropy": 7.662798118591309, |
| "epoch": 0.020831725947071986, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000202, |
| "loss": 7.2073, |
| "mean_token_accuracy": 0.08529370948672295, |
| "num_tokens": 721151.0, |
| "step": 405 |
| }, |
| { |
| "entropy": 7.703192710876465, |
| "epoch": 0.02108890774888769, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00020449999999999998, |
| "loss": 7.2059, |
| "mean_token_accuracy": 0.08231882154941558, |
| "num_tokens": 730957.0, |
| "step": 410 |
| }, |
| { |
| "entropy": 7.6682192325592045, |
| "epoch": 0.02134608955070339, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.000207, |
| "loss": 7.115, |
| "mean_token_accuracy": 0.09367254376411438, |
| "num_tokens": 740054.0, |
| "step": 415 |
| }, |
| { |
| "entropy": 7.710998058319092, |
| "epoch": 0.021603271352519094, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002095, |
| "loss": 7.1138, |
| "mean_token_accuracy": 0.0901214174926281, |
| "num_tokens": 748576.0, |
| "step": 420 |
| }, |
| { |
| "entropy": 7.615434312820435, |
| "epoch": 0.0218604531543348, |
| "grad_norm": 0.91015625, |
| "learning_rate": 0.000212, |
| "loss": 7.1257, |
| "mean_token_accuracy": 0.08843043595552444, |
| "num_tokens": 758078.0, |
| "step": 425 |
| }, |
| { |
| "entropy": 7.6622356414794925, |
| "epoch": 0.022117634956150503, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002145, |
| "loss": 7.1976, |
| "mean_token_accuracy": 0.08554179668426513, |
| "num_tokens": 767041.0, |
| "step": 430 |
| }, |
| { |
| "entropy": 7.6705575466156, |
| "epoch": 0.022374816757966206, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00021700000000000002, |
| "loss": 7.192, |
| "mean_token_accuracy": 0.08901726603507995, |
| "num_tokens": 775675.0, |
| "step": 435 |
| }, |
| { |
| "entropy": 7.627669334411621, |
| "epoch": 0.02263199855978191, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0002195, |
| "loss": 7.0133, |
| "mean_token_accuracy": 0.09209411665797233, |
| "num_tokens": 784105.0, |
| "step": 440 |
| }, |
| { |
| "entropy": 7.484321117401123, |
| "epoch": 0.022889180361597615, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000222, |
| "loss": 6.9712, |
| "mean_token_accuracy": 0.09117011949419976, |
| "num_tokens": 792861.0, |
| "step": 445 |
| }, |
| { |
| "entropy": 7.594349336624146, |
| "epoch": 0.023146362163413318, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002245, |
| "loss": 7.0314, |
| "mean_token_accuracy": 0.08824475556612014, |
| "num_tokens": 801642.0, |
| "step": 450 |
| }, |
| { |
| "entropy": 7.497442388534546, |
| "epoch": 0.02340354396522902, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00022700000000000002, |
| "loss": 6.9939, |
| "mean_token_accuracy": 0.08806813433766365, |
| "num_tokens": 811105.0, |
| "step": 455 |
| }, |
| { |
| "entropy": 7.556538200378418, |
| "epoch": 0.023660725767044723, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.00022950000000000002, |
| "loss": 7.0195, |
| "mean_token_accuracy": 0.09214109480381012, |
| "num_tokens": 819989.0, |
| "step": 460 |
| }, |
| { |
| "entropy": 7.516587781906128, |
| "epoch": 0.023917907568860426, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00023200000000000003, |
| "loss": 7.0303, |
| "mean_token_accuracy": 0.0912808708846569, |
| "num_tokens": 829532.0, |
| "step": 465 |
| }, |
| { |
| "entropy": 7.524700498580932, |
| "epoch": 0.024175089370676132, |
| "grad_norm": 1.3046875, |
| "learning_rate": 0.00023449999999999998, |
| "loss": 6.9313, |
| "mean_token_accuracy": 0.09493043571710587, |
| "num_tokens": 838071.0, |
| "step": 470 |
| }, |
| { |
| "entropy": 7.6139366149902346, |
| "epoch": 0.024432271172491835, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000237, |
| "loss": 7.1399, |
| "mean_token_accuracy": 0.0876034751534462, |
| "num_tokens": 848094.0, |
| "step": 475 |
| }, |
| { |
| "entropy": 7.520268821716309, |
| "epoch": 0.024689452974307538, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0002395, |
| "loss": 7.0461, |
| "mean_token_accuracy": 0.09003157168626785, |
| "num_tokens": 856585.0, |
| "step": 480 |
| }, |
| { |
| "entropy": 7.4084981918334964, |
| "epoch": 0.02494663477612324, |
| "grad_norm": 1.0, |
| "learning_rate": 0.000242, |
| "loss": 7.0064, |
| "mean_token_accuracy": 0.09524489566683769, |
| "num_tokens": 865866.0, |
| "step": 485 |
| }, |
| { |
| "entropy": 7.565576791763306, |
| "epoch": 0.025203816577938944, |
| "grad_norm": 1.390625, |
| "learning_rate": 0.0002445, |
| "loss": 7.0857, |
| "mean_token_accuracy": 0.09243087470531464, |
| "num_tokens": 874963.0, |
| "step": 490 |
| }, |
| { |
| "entropy": 7.522153425216675, |
| "epoch": 0.02546099837975465, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000247, |
| "loss": 7.0253, |
| "mean_token_accuracy": 0.09747636616230011, |
| "num_tokens": 883670.0, |
| "step": 495 |
| }, |
| { |
| "entropy": 7.411280775070191, |
| "epoch": 0.025718180181570353, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0002495, |
| "loss": 6.9456, |
| "mean_token_accuracy": 0.09364836364984512, |
| "num_tokens": 892322.0, |
| "step": 500 |
| }, |
| { |
| "entropy": 7.502190637588501, |
| "epoch": 0.025975361983386056, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.000252, |
| "loss": 7.0, |
| "mean_token_accuracy": 0.09010454788804054, |
| "num_tokens": 901450.0, |
| "step": 505 |
| }, |
| { |
| "entropy": 7.450657367706299, |
| "epoch": 0.02623254378520176, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0002545, |
| "loss": 6.9258, |
| "mean_token_accuracy": 0.0917640596628189, |
| "num_tokens": 910499.0, |
| "step": 510 |
| }, |
| { |
| "entropy": 7.4553405284881595, |
| "epoch": 0.02648972558701746, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.000257, |
| "loss": 7.042, |
| "mean_token_accuracy": 0.08597794771194459, |
| "num_tokens": 920223.0, |
| "step": 515 |
| }, |
| { |
| "entropy": 7.50772066116333, |
| "epoch": 0.026746907388833167, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0002595, |
| "loss": 7.014, |
| "mean_token_accuracy": 0.08768303692340851, |
| "num_tokens": 929414.0, |
| "step": 520 |
| }, |
| { |
| "entropy": 7.4105640888214115, |
| "epoch": 0.02700408919064887, |
| "grad_norm": 1.28125, |
| "learning_rate": 0.000262, |
| "loss": 6.98, |
| "mean_token_accuracy": 0.08690723404288292, |
| "num_tokens": 938059.0, |
| "step": 525 |
| }, |
| { |
| "entropy": 7.362936401367188, |
| "epoch": 0.027261270992464573, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.00026450000000000003, |
| "loss": 7.0251, |
| "mean_token_accuracy": 0.08964922651648521, |
| "num_tokens": 946868.0, |
| "step": 530 |
| }, |
| { |
| "entropy": 7.468600177764893, |
| "epoch": 0.027518452794280276, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00026700000000000004, |
| "loss": 6.867, |
| "mean_token_accuracy": 0.09712589457631111, |
| "num_tokens": 954997.0, |
| "step": 535 |
| }, |
| { |
| "entropy": 7.428448724746704, |
| "epoch": 0.02777563459609598, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.00026950000000000005, |
| "loss": 6.9816, |
| "mean_token_accuracy": 0.09053401798009872, |
| "num_tokens": 964488.0, |
| "step": 540 |
| }, |
| { |
| "entropy": 7.317347574234009, |
| "epoch": 0.028032816397911685, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00027200000000000005, |
| "loss": 6.8074, |
| "mean_token_accuracy": 0.10062685832381249, |
| "num_tokens": 972901.0, |
| "step": 545 |
| }, |
| { |
| "entropy": 7.45094141960144, |
| "epoch": 0.028289998199727388, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0002745, |
| "loss": 7.0093, |
| "mean_token_accuracy": 0.09124675542116165, |
| "num_tokens": 981922.0, |
| "step": 550 |
| }, |
| { |
| "entropy": 7.441890525817871, |
| "epoch": 0.02854718000154309, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000277, |
| "loss": 6.9774, |
| "mean_token_accuracy": 0.09369566291570663, |
| "num_tokens": 990419.0, |
| "step": 555 |
| }, |
| { |
| "entropy": 7.304813051223755, |
| "epoch": 0.028804361803358793, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0002795, |
| "loss": 6.8424, |
| "mean_token_accuracy": 0.09960516914725304, |
| "num_tokens": 998236.0, |
| "step": 560 |
| }, |
| { |
| "entropy": 7.3862227439880375, |
| "epoch": 0.0290615436051745, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00028199999999999997, |
| "loss": 6.8905, |
| "mean_token_accuracy": 0.09915700182318687, |
| "num_tokens": 1008258.0, |
| "step": 565 |
| }, |
| { |
| "entropy": 7.355383062362671, |
| "epoch": 0.029318725406990202, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0002845, |
| "loss": 6.8729, |
| "mean_token_accuracy": 0.09238902553915977, |
| "num_tokens": 1017029.0, |
| "step": 570 |
| }, |
| { |
| "entropy": 7.315412712097168, |
| "epoch": 0.029575907208805905, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.000287, |
| "loss": 6.9067, |
| "mean_token_accuracy": 0.09177370145916938, |
| "num_tokens": 1026497.0, |
| "step": 575 |
| }, |
| { |
| "entropy": 7.337841367721557, |
| "epoch": 0.029833089010621608, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0002895, |
| "loss": 6.8092, |
| "mean_token_accuracy": 0.10336045101284981, |
| "num_tokens": 1034728.0, |
| "step": 580 |
| }, |
| { |
| "entropy": 7.256781911849975, |
| "epoch": 0.03009027081243731, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000292, |
| "loss": 6.8645, |
| "mean_token_accuracy": 0.09807764887809753, |
| "num_tokens": 1043556.0, |
| "step": 585 |
| }, |
| { |
| "entropy": 7.315465259552002, |
| "epoch": 0.030347452614253017, |
| "grad_norm": 1.25, |
| "learning_rate": 0.0002945, |
| "loss": 6.7914, |
| "mean_token_accuracy": 0.10462642684578896, |
| "num_tokens": 1053449.0, |
| "step": 590 |
| }, |
| { |
| "entropy": 7.294723844528198, |
| "epoch": 0.03060463441606872, |
| "grad_norm": 1.25, |
| "learning_rate": 0.000297, |
| "loss": 6.8701, |
| "mean_token_accuracy": 0.09261535704135895, |
| "num_tokens": 1062691.0, |
| "step": 595 |
| }, |
| { |
| "entropy": 7.328425025939941, |
| "epoch": 0.030861816217884423, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0002995, |
| "loss": 6.8732, |
| "mean_token_accuracy": 0.09672143906354905, |
| "num_tokens": 1072194.0, |
| "step": 600 |
| }, |
| { |
| "entropy": 7.280484533309936, |
| "epoch": 0.031118998019700125, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000302, |
| "loss": 6.7832, |
| "mean_token_accuracy": 0.09872276112437248, |
| "num_tokens": 1080781.0, |
| "step": 605 |
| }, |
| { |
| "entropy": 7.2788474559783936, |
| "epoch": 0.03137617982151583, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0003045, |
| "loss": 6.9191, |
| "mean_token_accuracy": 0.09485599771142006, |
| "num_tokens": 1090048.0, |
| "step": 610 |
| }, |
| { |
| "entropy": 7.34011402130127, |
| "epoch": 0.03163336162333153, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000307, |
| "loss": 6.9368, |
| "mean_token_accuracy": 0.09523111060261727, |
| "num_tokens": 1100121.0, |
| "step": 615 |
| }, |
| { |
| "entropy": 7.326197099685669, |
| "epoch": 0.03189054342514724, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0003095, |
| "loss": 6.8036, |
| "mean_token_accuracy": 0.09568134695291519, |
| "num_tokens": 1108569.0, |
| "step": 620 |
| }, |
| { |
| "entropy": 7.213407182693482, |
| "epoch": 0.032147725226962943, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000312, |
| "loss": 6.776, |
| "mean_token_accuracy": 0.09914244189858437, |
| "num_tokens": 1118247.0, |
| "step": 625 |
| }, |
| { |
| "entropy": 7.210325479507446, |
| "epoch": 0.03240490702877864, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.0003145, |
| "loss": 6.7999, |
| "mean_token_accuracy": 0.09887302219867707, |
| "num_tokens": 1126951.0, |
| "step": 630 |
| }, |
| { |
| "entropy": 7.209123611450195, |
| "epoch": 0.03266208883059435, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000317, |
| "loss": 6.7651, |
| "mean_token_accuracy": 0.10773184821009636, |
| "num_tokens": 1135390.0, |
| "step": 635 |
| }, |
| { |
| "entropy": 7.2418413162231445, |
| "epoch": 0.03291927063241005, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0003195, |
| "loss": 6.8057, |
| "mean_token_accuracy": 0.09772193506360054, |
| "num_tokens": 1143911.0, |
| "step": 640 |
| }, |
| { |
| "entropy": 7.288219833374024, |
| "epoch": 0.033176452434225755, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.000322, |
| "loss": 6.7833, |
| "mean_token_accuracy": 0.10312128961086273, |
| "num_tokens": 1152957.0, |
| "step": 645 |
| }, |
| { |
| "entropy": 7.144729995727539, |
| "epoch": 0.03343363423604146, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00032450000000000003, |
| "loss": 6.7073, |
| "mean_token_accuracy": 0.10490344762802124, |
| "num_tokens": 1161911.0, |
| "step": 650 |
| }, |
| { |
| "entropy": 7.214617156982422, |
| "epoch": 0.03369081603785716, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.00032700000000000003, |
| "loss": 6.7621, |
| "mean_token_accuracy": 0.10395861864089966, |
| "num_tokens": 1170932.0, |
| "step": 655 |
| }, |
| { |
| "entropy": 7.226040458679199, |
| "epoch": 0.03394799783967287, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00032950000000000004, |
| "loss": 6.8979, |
| "mean_token_accuracy": 0.09301602616906166, |
| "num_tokens": 1180417.0, |
| "step": 660 |
| }, |
| { |
| "entropy": 7.148654270172119, |
| "epoch": 0.034205179641488566, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00033200000000000005, |
| "loss": 6.7629, |
| "mean_token_accuracy": 0.09860587194561958, |
| "num_tokens": 1189153.0, |
| "step": 665 |
| }, |
| { |
| "entropy": 7.214554643630981, |
| "epoch": 0.03446236144330427, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00033450000000000005, |
| "loss": 6.7476, |
| "mean_token_accuracy": 0.1043582171201706, |
| "num_tokens": 1197903.0, |
| "step": 670 |
| }, |
| { |
| "entropy": 7.1135680198669435, |
| "epoch": 0.03471954324511998, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000337, |
| "loss": 6.7435, |
| "mean_token_accuracy": 0.10275317579507828, |
| "num_tokens": 1207310.0, |
| "step": 675 |
| }, |
| { |
| "entropy": 7.197217321395874, |
| "epoch": 0.03497672504693568, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.0003395, |
| "loss": 6.7117, |
| "mean_token_accuracy": 0.10364129021763802, |
| "num_tokens": 1215577.0, |
| "step": 680 |
| }, |
| { |
| "entropy": 7.160997724533081, |
| "epoch": 0.035233906848751384, |
| "grad_norm": 1.2578125, |
| "learning_rate": 0.000342, |
| "loss": 6.801, |
| "mean_token_accuracy": 0.10323198661208152, |
| "num_tokens": 1223906.0, |
| "step": 685 |
| }, |
| { |
| "entropy": 7.1171308040618895, |
| "epoch": 0.03549108865056708, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00034449999999999997, |
| "loss": 6.7434, |
| "mean_token_accuracy": 0.10217863768339157, |
| "num_tokens": 1232689.0, |
| "step": 690 |
| }, |
| { |
| "entropy": 7.243052577972412, |
| "epoch": 0.03574827045238279, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000347, |
| "loss": 6.777, |
| "mean_token_accuracy": 0.10172305777668952, |
| "num_tokens": 1241079.0, |
| "step": 695 |
| }, |
| { |
| "entropy": 7.0958874225616455, |
| "epoch": 0.036005452254198496, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003495, |
| "loss": 6.6994, |
| "mean_token_accuracy": 0.10428043976426124, |
| "num_tokens": 1249540.0, |
| "step": 700 |
| }, |
| { |
| "entropy": 7.236631059646607, |
| "epoch": 0.036262634056014195, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000352, |
| "loss": 6.767, |
| "mean_token_accuracy": 0.10423633679747582, |
| "num_tokens": 1257823.0, |
| "step": 705 |
| }, |
| { |
| "entropy": 7.162586879730225, |
| "epoch": 0.0365198158578299, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003545, |
| "loss": 6.7752, |
| "mean_token_accuracy": 0.10328136906027793, |
| "num_tokens": 1267242.0, |
| "step": 710 |
| }, |
| { |
| "entropy": 7.095451688766479, |
| "epoch": 0.0367769976596456, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.000357, |
| "loss": 6.6616, |
| "mean_token_accuracy": 0.10539852529764175, |
| "num_tokens": 1275942.0, |
| "step": 715 |
| }, |
| { |
| "entropy": 7.087832736968994, |
| "epoch": 0.03703417946146131, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003595, |
| "loss": 6.716, |
| "mean_token_accuracy": 0.10562722086906433, |
| "num_tokens": 1284840.0, |
| "step": 720 |
| }, |
| { |
| "entropy": 7.123103380203247, |
| "epoch": 0.03729136126327701, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000362, |
| "loss": 6.6864, |
| "mean_token_accuracy": 0.10260284543037415, |
| "num_tokens": 1293592.0, |
| "step": 725 |
| }, |
| { |
| "entropy": 7.171104860305786, |
| "epoch": 0.03754854306509271, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003645, |
| "loss": 6.8006, |
| "mean_token_accuracy": 0.10065393671393394, |
| "num_tokens": 1301903.0, |
| "step": 730 |
| }, |
| { |
| "entropy": 7.110880374908447, |
| "epoch": 0.03780572486690842, |
| "grad_norm": 1.265625, |
| "learning_rate": 0.000367, |
| "loss": 6.6262, |
| "mean_token_accuracy": 0.105719206482172, |
| "num_tokens": 1310230.0, |
| "step": 735 |
| }, |
| { |
| "entropy": 7.178726625442505, |
| "epoch": 0.03806290666872412, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0003695, |
| "loss": 6.7676, |
| "mean_token_accuracy": 0.10490798503160477, |
| "num_tokens": 1320029.0, |
| "step": 740 |
| }, |
| { |
| "entropy": 7.001174449920654, |
| "epoch": 0.038320088470539825, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000372, |
| "loss": 6.6133, |
| "mean_token_accuracy": 0.10703234896063804, |
| "num_tokens": 1329155.0, |
| "step": 745 |
| }, |
| { |
| "entropy": 7.125448083877563, |
| "epoch": 0.03857727027235553, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0003745, |
| "loss": 6.8029, |
| "mean_token_accuracy": 0.1019430361688137, |
| "num_tokens": 1337958.0, |
| "step": 750 |
| }, |
| { |
| "entropy": 7.109465599060059, |
| "epoch": 0.03883445207417123, |
| "grad_norm": 1.3125, |
| "learning_rate": 0.000377, |
| "loss": 6.7375, |
| "mean_token_accuracy": 0.09966553151607513, |
| "num_tokens": 1347105.0, |
| "step": 755 |
| }, |
| { |
| "entropy": 7.161317777633667, |
| "epoch": 0.039091633875986936, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0003795, |
| "loss": 6.6791, |
| "mean_token_accuracy": 0.10060147866606713, |
| "num_tokens": 1356161.0, |
| "step": 760 |
| }, |
| { |
| "entropy": 6.9970433712005615, |
| "epoch": 0.039348815677802636, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000382, |
| "loss": 6.6891, |
| "mean_token_accuracy": 0.10932381451129913, |
| "num_tokens": 1365291.0, |
| "step": 765 |
| }, |
| { |
| "entropy": 7.0630707263946535, |
| "epoch": 0.03960599747961834, |
| "grad_norm": 1.2578125, |
| "learning_rate": 0.0003845, |
| "loss": 6.6481, |
| "mean_token_accuracy": 0.1059026412665844, |
| "num_tokens": 1374057.0, |
| "step": 770 |
| }, |
| { |
| "entropy": 7.118219041824341, |
| "epoch": 0.03986317928143405, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.00038700000000000003, |
| "loss": 6.6895, |
| "mean_token_accuracy": 0.09991606175899506, |
| "num_tokens": 1383204.0, |
| "step": 775 |
| }, |
| { |
| "entropy": 7.0793726444244385, |
| "epoch": 0.04012036108324975, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.00038950000000000003, |
| "loss": 6.7114, |
| "mean_token_accuracy": 0.1018392451107502, |
| "num_tokens": 1392303.0, |
| "step": 780 |
| }, |
| { |
| "entropy": 7.041213703155518, |
| "epoch": 0.040377542885065454, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00039200000000000004, |
| "loss": 6.6789, |
| "mean_token_accuracy": 0.10870900377631187, |
| "num_tokens": 1401955.0, |
| "step": 785 |
| }, |
| { |
| "entropy": 7.127471685409546, |
| "epoch": 0.04063472468688115, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00039450000000000005, |
| "loss": 6.6934, |
| "mean_token_accuracy": 0.10036104544997215, |
| "num_tokens": 1410467.0, |
| "step": 790 |
| }, |
| { |
| "entropy": 6.975720405578613, |
| "epoch": 0.04089190648869686, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00039700000000000005, |
| "loss": 6.6748, |
| "mean_token_accuracy": 0.09731148779392243, |
| "num_tokens": 1420337.0, |
| "step": 795 |
| }, |
| { |
| "entropy": 7.059706926345825, |
| "epoch": 0.041149088290512566, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003995, |
| "loss": 6.6711, |
| "mean_token_accuracy": 0.10144198536872864, |
| "num_tokens": 1429453.0, |
| "step": 800 |
| }, |
| { |
| "entropy": 7.094644546508789, |
| "epoch": 0.041406270092328265, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000402, |
| "loss": 6.6208, |
| "mean_token_accuracy": 0.10604123547673225, |
| "num_tokens": 1438417.0, |
| "step": 805 |
| }, |
| { |
| "entropy": 6.986465740203857, |
| "epoch": 0.04166345189414397, |
| "grad_norm": 1.40625, |
| "learning_rate": 0.0004045, |
| "loss": 6.6667, |
| "mean_token_accuracy": 0.10473878160119057, |
| "num_tokens": 1446480.0, |
| "step": 810 |
| }, |
| { |
| "entropy": 6.946633005142212, |
| "epoch": 0.04192063369595967, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00040699999999999997, |
| "loss": 6.6306, |
| "mean_token_accuracy": 0.10496868267655372, |
| "num_tokens": 1455102.0, |
| "step": 815 |
| }, |
| { |
| "entropy": 7.14404935836792, |
| "epoch": 0.04217781549777538, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004095, |
| "loss": 6.6538, |
| "mean_token_accuracy": 0.10508396551012993, |
| "num_tokens": 1463839.0, |
| "step": 820 |
| }, |
| { |
| "entropy": 7.024435377120971, |
| "epoch": 0.04243499729959108, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000412, |
| "loss": 6.6836, |
| "mean_token_accuracy": 0.10788170769810676, |
| "num_tokens": 1472806.0, |
| "step": 825 |
| }, |
| { |
| "entropy": 6.979895305633545, |
| "epoch": 0.04269217910140678, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004145, |
| "loss": 6.6016, |
| "mean_token_accuracy": 0.10319365486502648, |
| "num_tokens": 1481707.0, |
| "step": 830 |
| }, |
| { |
| "entropy": 6.948284530639649, |
| "epoch": 0.04294936090322249, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.000417, |
| "loss": 6.6068, |
| "mean_token_accuracy": 0.10952205657958984, |
| "num_tokens": 1491057.0, |
| "step": 835 |
| }, |
| { |
| "entropy": 6.963069152832031, |
| "epoch": 0.04320654270503819, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004195, |
| "loss": 6.5666, |
| "mean_token_accuracy": 0.10177317038178443, |
| "num_tokens": 1500331.0, |
| "step": 840 |
| }, |
| { |
| "entropy": 6.964898347854614, |
| "epoch": 0.043463724506853894, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000422, |
| "loss": 6.6376, |
| "mean_token_accuracy": 0.10519776120781898, |
| "num_tokens": 1509051.0, |
| "step": 845 |
| }, |
| { |
| "entropy": 7.032815408706665, |
| "epoch": 0.0437209063086696, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.0004245, |
| "loss": 6.5931, |
| "mean_token_accuracy": 0.10714114159345627, |
| "num_tokens": 1517082.0, |
| "step": 850 |
| }, |
| { |
| "entropy": 6.869009304046631, |
| "epoch": 0.0439780881104853, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.000427, |
| "loss": 6.5338, |
| "mean_token_accuracy": 0.11201286613941193, |
| "num_tokens": 1525498.0, |
| "step": 855 |
| }, |
| { |
| "entropy": 6.827907609939575, |
| "epoch": 0.044235269912301006, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004295, |
| "loss": 6.4978, |
| "mean_token_accuracy": 0.11273056790232658, |
| "num_tokens": 1534476.0, |
| "step": 860 |
| }, |
| { |
| "entropy": 6.958985805511475, |
| "epoch": 0.04449245171411671, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000432, |
| "loss": 6.5896, |
| "mean_token_accuracy": 0.10771357268095016, |
| "num_tokens": 1542905.0, |
| "step": 865 |
| }, |
| { |
| "entropy": 6.942825794219971, |
| "epoch": 0.04474963351593241, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004345, |
| "loss": 6.583, |
| "mean_token_accuracy": 0.10546278730034828, |
| "num_tokens": 1551763.0, |
| "step": 870 |
| }, |
| { |
| "entropy": 6.906496191024781, |
| "epoch": 0.04500681531774812, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.000437, |
| "loss": 6.5085, |
| "mean_token_accuracy": 0.11341241300106049, |
| "num_tokens": 1560520.0, |
| "step": 875 |
| }, |
| { |
| "entropy": 6.904255485534668, |
| "epoch": 0.04526399711956382, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004395, |
| "loss": 6.4871, |
| "mean_token_accuracy": 0.11152468100190163, |
| "num_tokens": 1569401.0, |
| "step": 880 |
| }, |
| { |
| "entropy": 6.922533941268921, |
| "epoch": 0.045521178921379524, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000442, |
| "loss": 6.5564, |
| "mean_token_accuracy": 0.10919757708907127, |
| "num_tokens": 1578440.0, |
| "step": 885 |
| }, |
| { |
| "entropy": 6.789845991134643, |
| "epoch": 0.04577836072319523, |
| "grad_norm": 1.234375, |
| "learning_rate": 0.0004445, |
| "loss": 6.4462, |
| "mean_token_accuracy": 0.11144870221614837, |
| "num_tokens": 1587551.0, |
| "step": 890 |
| }, |
| { |
| "entropy": 6.944276809692383, |
| "epoch": 0.04603554252501093, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.000447, |
| "loss": 6.6154, |
| "mean_token_accuracy": 0.10818377807736397, |
| "num_tokens": 1596314.0, |
| "step": 895 |
| }, |
| { |
| "entropy": 6.900253582000732, |
| "epoch": 0.046292724326826636, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00044950000000000003, |
| "loss": 6.4889, |
| "mean_token_accuracy": 0.1112966388463974, |
| "num_tokens": 1605025.0, |
| "step": 900 |
| }, |
| { |
| "entropy": 6.905750894546509, |
| "epoch": 0.046549906128642335, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.00045200000000000004, |
| "loss": 6.5348, |
| "mean_token_accuracy": 0.10826415568590164, |
| "num_tokens": 1613295.0, |
| "step": 905 |
| }, |
| { |
| "entropy": 6.862349224090576, |
| "epoch": 0.04680708793045804, |
| "grad_norm": 1.328125, |
| "learning_rate": 0.00045450000000000004, |
| "loss": 6.5131, |
| "mean_token_accuracy": 0.1080511450767517, |
| "num_tokens": 1621865.0, |
| "step": 910 |
| }, |
| { |
| "entropy": 6.87268099784851, |
| "epoch": 0.04706426973227375, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00045700000000000005, |
| "loss": 6.517, |
| "mean_token_accuracy": 0.11334388554096222, |
| "num_tokens": 1631036.0, |
| "step": 915 |
| }, |
| { |
| "entropy": 6.960796642303467, |
| "epoch": 0.04732145153408945, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00045950000000000006, |
| "loss": 6.6083, |
| "mean_token_accuracy": 0.10900305211544037, |
| "num_tokens": 1640311.0, |
| "step": 920 |
| }, |
| { |
| "entropy": 6.877505731582642, |
| "epoch": 0.04757863333590515, |
| "grad_norm": 1.2578125, |
| "learning_rate": 0.000462, |
| "loss": 6.5707, |
| "mean_token_accuracy": 0.11122839301824569, |
| "num_tokens": 1648651.0, |
| "step": 925 |
| }, |
| { |
| "entropy": 6.814219570159912, |
| "epoch": 0.04783581513772085, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0004645, |
| "loss": 6.5091, |
| "mean_token_accuracy": 0.11311314180493355, |
| "num_tokens": 1657493.0, |
| "step": 930 |
| }, |
| { |
| "entropy": 6.919810724258423, |
| "epoch": 0.04809299693953656, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.000467, |
| "loss": 6.5672, |
| "mean_token_accuracy": 0.10320627093315124, |
| "num_tokens": 1666909.0, |
| "step": 935 |
| }, |
| { |
| "entropy": 6.835229587554932, |
| "epoch": 0.048350178741352265, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004695, |
| "loss": 6.5857, |
| "mean_token_accuracy": 0.10411025136709214, |
| "num_tokens": 1676071.0, |
| "step": 940 |
| }, |
| { |
| "entropy": 6.990052223205566, |
| "epoch": 0.048607360543167964, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.000472, |
| "loss": 6.6305, |
| "mean_token_accuracy": 0.10452140420675278, |
| "num_tokens": 1685240.0, |
| "step": 945 |
| }, |
| { |
| "entropy": 6.916949987411499, |
| "epoch": 0.04886454234498367, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004745, |
| "loss": 6.5346, |
| "mean_token_accuracy": 0.117493636906147, |
| "num_tokens": 1694441.0, |
| "step": 950 |
| }, |
| { |
| "entropy": 6.721475076675415, |
| "epoch": 0.04912172414679937, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000477, |
| "loss": 6.4578, |
| "mean_token_accuracy": 0.1129125975072384, |
| "num_tokens": 1702925.0, |
| "step": 955 |
| }, |
| { |
| "entropy": 6.895248603820801, |
| "epoch": 0.049378905948615076, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004795, |
| "loss": 6.4835, |
| "mean_token_accuracy": 0.10699952915310859, |
| "num_tokens": 1711708.0, |
| "step": 960 |
| }, |
| { |
| "entropy": 6.799575614929199, |
| "epoch": 0.04963608775043078, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.000482, |
| "loss": 6.4901, |
| "mean_token_accuracy": 0.10597067773342132, |
| "num_tokens": 1720543.0, |
| "step": 965 |
| }, |
| { |
| "entropy": 6.862289619445801, |
| "epoch": 0.04989326955224648, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004845, |
| "loss": 6.4988, |
| "mean_token_accuracy": 0.11304299309849739, |
| "num_tokens": 1729776.0, |
| "step": 970 |
| }, |
| { |
| "entropy": 6.8804943561553955, |
| "epoch": 0.05015045135406219, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000487, |
| "loss": 6.4822, |
| "mean_token_accuracy": 0.11637242883443832, |
| "num_tokens": 1738249.0, |
| "step": 975 |
| }, |
| { |
| "entropy": 6.828695917129517, |
| "epoch": 0.05040763315587789, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004895, |
| "loss": 6.5063, |
| "mean_token_accuracy": 0.11184739843010902, |
| "num_tokens": 1747262.0, |
| "step": 980 |
| }, |
| { |
| "entropy": 6.891150426864624, |
| "epoch": 0.050664814957693594, |
| "grad_norm": 1.2890625, |
| "learning_rate": 0.000492, |
| "loss": 6.5072, |
| "mean_token_accuracy": 0.11530979126691818, |
| "num_tokens": 1755320.0, |
| "step": 985 |
| }, |
| { |
| "entropy": 6.7496922492980955, |
| "epoch": 0.0509219967595093, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004945, |
| "loss": 6.5038, |
| "mean_token_accuracy": 0.11211839094758033, |
| "num_tokens": 1763798.0, |
| "step": 990 |
| }, |
| { |
| "entropy": 6.788990116119384, |
| "epoch": 0.051179178561325, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.000497, |
| "loss": 6.4671, |
| "mean_token_accuracy": 0.11327328234910965, |
| "num_tokens": 1773862.0, |
| "step": 995 |
| }, |
| { |
| "entropy": 6.837374210357666, |
| "epoch": 0.051436360363140705, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004995, |
| "loss": 6.5248, |
| "mean_token_accuracy": 0.11146914437413216, |
| "num_tokens": 1783552.0, |
| "step": 1000 |
| }, |
| { |
| "entropy": 6.746343898773193, |
| "epoch": 0.051693542164956405, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.000499998026082006, |
| "loss": 6.426, |
| "mean_token_accuracy": 0.11493942067027092, |
| "num_tokens": 1792245.0, |
| "step": 1005 |
| }, |
| { |
| "entropy": 6.774056434631348, |
| "epoch": 0.05195072396677211, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004999900070995136, |
| "loss": 6.5069, |
| "mean_token_accuracy": 0.11212562620639802, |
| "num_tokens": 1800813.0, |
| "step": 1010 |
| }, |
| { |
| "entropy": 6.852898216247558, |
| "epoch": 0.05220790576858782, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004999758199023239, |
| "loss": 6.5207, |
| "mean_token_accuracy": 0.11174971088767052, |
| "num_tokens": 1809671.0, |
| "step": 1015 |
| }, |
| { |
| "entropy": 6.741954612731933, |
| "epoch": 0.05246508757040352, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004999554648793858, |
| "loss": 6.4463, |
| "mean_token_accuracy": 0.11097860932350159, |
| "num_tokens": 1817968.0, |
| "step": 1020 |
| }, |
| { |
| "entropy": 6.815918350219727, |
| "epoch": 0.05272226937221922, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004999289425887425, |
| "loss": 6.529, |
| "mean_token_accuracy": 0.10783923268318177, |
| "num_tokens": 1826302.0, |
| "step": 1025 |
| }, |
| { |
| "entropy": 6.708252668380737, |
| "epoch": 0.05297945117403492, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004998962537575161, |
| "loss": 6.4088, |
| "mean_token_accuracy": 0.11643101274967194, |
| "num_tokens": 1836008.0, |
| "step": 1030 |
| }, |
| { |
| "entropy": 6.737126874923706, |
| "epoch": 0.05323663297585063, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.0004998573992818874, |
| "loss": 6.4282, |
| "mean_token_accuracy": 0.11566728353500366, |
| "num_tokens": 1844730.0, |
| "step": 1035 |
| }, |
| { |
| "entropy": 6.724181604385376, |
| "epoch": 0.053493814777666335, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004998123802270715, |
| "loss": 6.402, |
| "mean_token_accuracy": 0.11093823388218879, |
| "num_tokens": 1853186.0, |
| "step": 1040 |
| }, |
| { |
| "entropy": 6.778470802307129, |
| "epoch": 0.053750996579482034, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.0004997611978272886, |
| "loss": 6.376, |
| "mean_token_accuracy": 0.1124820165336132, |
| "num_tokens": 1861579.0, |
| "step": 1045 |
| }, |
| { |
| "entropy": 6.778669786453247, |
| "epoch": 0.05400817838129774, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004997038534857298, |
| "loss": 6.5295, |
| "mean_token_accuracy": 0.1051288291811943, |
| "num_tokens": 1871948.0, |
| "step": 1050 |
| }, |
| { |
| "entropy": 6.779291105270386, |
| "epoch": 0.05426536018311344, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004996403487745194, |
| "loss": 6.4291, |
| "mean_token_accuracy": 0.11674032881855964, |
| "num_tokens": 1880142.0, |
| "step": 1055 |
| }, |
| { |
| "entropy": 6.749887180328369, |
| "epoch": 0.054522541984929146, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.000499570685434671, |
| "loss": 6.4415, |
| "mean_token_accuracy": 0.10835661590099335, |
| "num_tokens": 1888929.0, |
| "step": 1060 |
| }, |
| { |
| "entropy": 6.763294887542725, |
| "epoch": 0.05477972378674485, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0004994948653760405, |
| "loss": 6.4847, |
| "mean_token_accuracy": 0.10644253864884376, |
| "num_tokens": 1897982.0, |
| "step": 1065 |
| }, |
| { |
| "entropy": 6.66923336982727, |
| "epoch": 0.05503690558856055, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004994128906772729, |
| "loss": 6.3776, |
| "mean_token_accuracy": 0.11694736555218696, |
| "num_tokens": 1906583.0, |
| "step": 1070 |
| }, |
| { |
| "entropy": 6.752908086776733, |
| "epoch": 0.05529408739037626, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000499324763585746, |
| "loss": 6.4433, |
| "mean_token_accuracy": 0.11435103714466095, |
| "num_tokens": 1915457.0, |
| "step": 1075 |
| }, |
| { |
| "entropy": 6.66996021270752, |
| "epoch": 0.05555126919219196, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004992304865175085, |
| "loss": 6.3785, |
| "mean_token_accuracy": 0.12019199803471566, |
| "num_tokens": 1923802.0, |
| "step": 1080 |
| }, |
| { |
| "entropy": 6.735610485076904, |
| "epoch": 0.05580845099400766, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004991300620572138, |
| "loss": 6.3917, |
| "mean_token_accuracy": 0.11757480353116989, |
| "num_tokens": 1933097.0, |
| "step": 1085 |
| }, |
| { |
| "entropy": 6.72240138053894, |
| "epoch": 0.05606563279582337, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004990234929580494, |
| "loss": 6.3646, |
| "mean_token_accuracy": 0.11228772699832916, |
| "num_tokens": 1942240.0, |
| "step": 1090 |
| }, |
| { |
| "entropy": 6.5773022174835205, |
| "epoch": 0.05632281459763907, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004989107821416609, |
| "loss": 6.3542, |
| "mean_token_accuracy": 0.11520460173487664, |
| "num_tokens": 1950501.0, |
| "step": 1095 |
| }, |
| { |
| "entropy": 6.835616827011108, |
| "epoch": 0.056579996399454775, |
| "grad_norm": 1.2421875, |
| "learning_rate": 0.0004987919326980723, |
| "loss": 6.4121, |
| "mean_token_accuracy": 0.11566629931330681, |
| "num_tokens": 1958621.0, |
| "step": 1100 |
| }, |
| { |
| "entropy": 6.723128461837769, |
| "epoch": 0.05683717820127048, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004986669478856011, |
| "loss": 6.5071, |
| "mean_token_accuracy": 0.11123462915420532, |
| "num_tokens": 1966836.0, |
| "step": 1105 |
| }, |
| { |
| "entropy": 6.7716064453125, |
| "epoch": 0.05709436000308618, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004985358311307688, |
| "loss": 6.4827, |
| "mean_token_accuracy": 0.11127110049128533, |
| "num_tokens": 1976046.0, |
| "step": 1110 |
| }, |
| { |
| "entropy": 6.752973651885986, |
| "epoch": 0.05735154180490189, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004983985860282081, |
| "loss": 6.4645, |
| "mean_token_accuracy": 0.11258459836244583, |
| "num_tokens": 1984074.0, |
| "step": 1115 |
| }, |
| { |
| "entropy": 6.730236387252807, |
| "epoch": 0.057608723606717586, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004982552163405623, |
| "loss": 6.539, |
| "mean_token_accuracy": 0.11384548544883728, |
| "num_tokens": 1992898.0, |
| "step": 1120 |
| }, |
| { |
| "entropy": 6.832723760604859, |
| "epoch": 0.05786590540853329, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004981057259983839, |
| "loss": 6.4669, |
| "mean_token_accuracy": 0.11225469931960105, |
| "num_tokens": 2002390.0, |
| "step": 1125 |
| }, |
| { |
| "entropy": 6.657161140441895, |
| "epoch": 0.058123087210349, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004979501191000262, |
| "loss": 6.3538, |
| "mean_token_accuracy": 0.1199690505862236, |
| "num_tokens": 2011499.0, |
| "step": 1130 |
| }, |
| { |
| "entropy": 6.6502784252166744, |
| "epoch": 0.0583802690121647, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004977883999115311, |
| "loss": 6.4782, |
| "mean_token_accuracy": 0.11357165277004241, |
| "num_tokens": 2021336.0, |
| "step": 1135 |
| }, |
| { |
| "entropy": 6.731290435791015, |
| "epoch": 0.058637450813980405, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004976205728665113, |
| "loss": 6.3638, |
| "mean_token_accuracy": 0.11489428207278252, |
| "num_tokens": 2029706.0, |
| "step": 1140 |
| }, |
| { |
| "entropy": 6.830005741119384, |
| "epoch": 0.058894632615796104, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0004974466425660307, |
| "loss": 6.5844, |
| "mean_token_accuracy": 0.10661658570170403, |
| "num_tokens": 2038915.0, |
| "step": 1145 |
| }, |
| { |
| "entropy": 6.701237726211548, |
| "epoch": 0.05915181441761181, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004972666137784759, |
| "loss": 6.418, |
| "mean_token_accuracy": 0.11196302473545075, |
| "num_tokens": 2047661.0, |
| "step": 1150 |
| }, |
| { |
| "entropy": 6.637448024749756, |
| "epoch": 0.059408996219427516, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004970804914394271, |
| "loss": 6.4053, |
| "mean_token_accuracy": 0.11128832325339318, |
| "num_tokens": 2056768.0, |
| "step": 1155 |
| }, |
| { |
| "entropy": 6.7576159000396725, |
| "epoch": 0.059666178021243216, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004968882806515225, |
| "loss": 6.4509, |
| "mean_token_accuracy": 0.11101424172520638, |
| "num_tokens": 2066862.0, |
| "step": 1160 |
| }, |
| { |
| "entropy": 6.65157413482666, |
| "epoch": 0.05992335982305892, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004966899866843177, |
| "loss": 6.2771, |
| "mean_token_accuracy": 0.11530844420194626, |
| "num_tokens": 2075794.0, |
| "step": 1165 |
| }, |
| { |
| "entropy": 6.693396663665771, |
| "epoch": 0.06018054162487462, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000496485614974142, |
| "loss": 6.4464, |
| "mean_token_accuracy": 0.11457487121224404, |
| "num_tokens": 2084806.0, |
| "step": 1170 |
| }, |
| { |
| "entropy": 6.578125905990601, |
| "epoch": 0.06043772342669033, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004962751711239492, |
| "loss": 6.3015, |
| "mean_token_accuracy": 0.11791201233863831, |
| "num_tokens": 2093884.0, |
| "step": 1175 |
| }, |
| { |
| "entropy": 6.601912546157837, |
| "epoch": 0.060694905228506034, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004960586609031636, |
| "loss": 6.2546, |
| "mean_token_accuracy": 0.12269692420959473, |
| "num_tokens": 2103716.0, |
| "step": 1180 |
| }, |
| { |
| "entropy": 6.633868169784546, |
| "epoch": 0.06095208703032173, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004958360902475224, |
| "loss": 6.3092, |
| "mean_token_accuracy": 0.11640048250555993, |
| "num_tokens": 2113627.0, |
| "step": 1185 |
| }, |
| { |
| "entropy": 6.588856792449951, |
| "epoch": 0.06120926883213744, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0004956074652589125, |
| "loss": 6.2842, |
| "mean_token_accuracy": 0.1199034109711647, |
| "num_tokens": 2121455.0, |
| "step": 1190 |
| }, |
| { |
| "entropy": 6.636424875259399, |
| "epoch": 0.06146645063395314, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004953727922052035, |
| "loss": 6.2933, |
| "mean_token_accuracy": 0.11959701478481292, |
| "num_tokens": 2130364.0, |
| "step": 1195 |
| }, |
| { |
| "entropy": 6.704743337631226, |
| "epoch": 0.061723632435768845, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.0004951320775200756, |
| "loss": 6.4765, |
| "mean_token_accuracy": 0.11397643610835076, |
| "num_tokens": 2138893.0, |
| "step": 1200 |
| }, |
| { |
| "entropy": 6.7864457130432125, |
| "epoch": 0.06198081423758455, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004948853278028436, |
| "loss": 6.4775, |
| "mean_token_accuracy": 0.11080277115106582, |
| "num_tokens": 2148441.0, |
| "step": 1205 |
| }, |
| { |
| "entropy": 6.467393255233764, |
| "epoch": 0.06223799603940025, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004946325498182755, |
| "loss": 6.3488, |
| "mean_token_accuracy": 0.11968965232372283, |
| "num_tokens": 2157566.0, |
| "step": 1210 |
| }, |
| { |
| "entropy": 6.594685506820679, |
| "epoch": 0.06249517784121596, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004943737504964076, |
| "loss": 6.2783, |
| "mean_token_accuracy": 0.12351583763957023, |
| "num_tokens": 2166652.0, |
| "step": 1215 |
| }, |
| { |
| "entropy": 6.595351934432983, |
| "epoch": 0.06275235964303166, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.000494108936932354, |
| "loss": 6.3271, |
| "mean_token_accuracy": 0.11962940394878388, |
| "num_tokens": 2175786.0, |
| "step": 1220 |
| }, |
| { |
| "entropy": 6.599175357818604, |
| "epoch": 0.06300954144484737, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004938381163861124, |
| "loss": 6.3318, |
| "mean_token_accuracy": 0.11382425799965859, |
| "num_tokens": 2184282.0, |
| "step": 1225 |
| }, |
| { |
| "entropy": 6.65804877281189, |
| "epoch": 0.06326672324666306, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004935612962823645, |
| "loss": 6.2634, |
| "mean_token_accuracy": 0.1293702930212021, |
| "num_tokens": 2192588.0, |
| "step": 1230 |
| }, |
| { |
| "entropy": 6.570264053344727, |
| "epoch": 0.06352390504847877, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004932784842102739, |
| "loss": 6.224, |
| "mean_token_accuracy": 0.1252226300537586, |
| "num_tokens": 2201247.0, |
| "step": 1235 |
| }, |
| { |
| "entropy": 6.581180286407471, |
| "epoch": 0.06378108685029447, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004929896879232758, |
| "loss": 6.4, |
| "mean_token_accuracy": 0.11070948839187622, |
| "num_tokens": 2210096.0, |
| "step": 1240 |
| }, |
| { |
| "entropy": 6.548767185211181, |
| "epoch": 0.06403826865211018, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004926949153388668, |
| "loss": 6.2372, |
| "mean_token_accuracy": 0.12190242633223533, |
| "num_tokens": 2219221.0, |
| "step": 1245 |
| }, |
| { |
| "entropy": 6.613304138183594, |
| "epoch": 0.06429545045392589, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0004923941745383859, |
| "loss": 6.3914, |
| "mean_token_accuracy": 0.11916265785694122, |
| "num_tokens": 2229094.0, |
| "step": 1250 |
| }, |
| { |
| "entropy": 6.622950220108033, |
| "epoch": 0.06455263225574158, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000492087473766794, |
| "loss": 6.2814, |
| "mean_token_accuracy": 0.12494359165430069, |
| "num_tokens": 2236964.0, |
| "step": 1255 |
| }, |
| { |
| "entropy": 6.639262056350708, |
| "epoch": 0.06480981405755729, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000491774821432448, |
| "loss": 6.2964, |
| "mean_token_accuracy": 0.11379757001996041, |
| "num_tokens": 2247044.0, |
| "step": 1260 |
| }, |
| { |
| "entropy": 6.578648328781128, |
| "epoch": 0.06506699585937299, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004914562261068693, |
| "loss": 6.3464, |
| "mean_token_accuracy": 0.11853989958763123, |
| "num_tokens": 2256106.0, |
| "step": 1265 |
| }, |
| { |
| "entropy": 6.5819896221160885, |
| "epoch": 0.0653241776611887, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0004911316965245098, |
| "loss": 6.333, |
| "mean_token_accuracy": 0.1119878426194191, |
| "num_tokens": 2265432.0, |
| "step": 1270 |
| }, |
| { |
| "entropy": 6.685585260391235, |
| "epoch": 0.0655813594630044, |
| "grad_norm": 1.125, |
| "learning_rate": 0.000490801241582512, |
| "loss": 6.3091, |
| "mean_token_accuracy": 0.11969617679715157, |
| "num_tokens": 2273882.0, |
| "step": 1275 |
| }, |
| { |
| "entropy": 6.507035255432129, |
| "epoch": 0.0658385412648201, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000490464870340465, |
| "loss": 6.2311, |
| "mean_token_accuracy": 0.12235765084624291, |
| "num_tokens": 2282754.0, |
| "step": 1280 |
| }, |
| { |
| "entropy": 6.6120068550109865, |
| "epoch": 0.0660957230666358, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004901225920201563, |
| "loss": 6.2385, |
| "mean_token_accuracy": 0.11968952193856239, |
| "num_tokens": 2291637.0, |
| "step": 1285 |
| }, |
| { |
| "entropy": 6.5052814960479735, |
| "epoch": 0.06635290486845151, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.000489774416005319, |
| "loss": 6.2752, |
| "mean_token_accuracy": 0.1284623309969902, |
| "num_tokens": 2300279.0, |
| "step": 1290 |
| }, |
| { |
| "entropy": 6.605392360687256, |
| "epoch": 0.06661008667026722, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.0004894203518413742, |
| "loss": 6.3063, |
| "mean_token_accuracy": 0.11685983091592789, |
| "num_tokens": 2309413.0, |
| "step": 1295 |
| }, |
| { |
| "entropy": 6.453005313873291, |
| "epoch": 0.06686726847208292, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004890604092351701, |
| "loss": 6.2339, |
| "mean_token_accuracy": 0.12537124752998352, |
| "num_tokens": 2318284.0, |
| "step": 1300 |
| }, |
| { |
| "entropy": 6.663999080657959, |
| "epoch": 0.06712445027389861, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.000488694598054715, |
| "loss": 6.4158, |
| "mean_token_accuracy": 0.11596757918596268, |
| "num_tokens": 2327483.0, |
| "step": 1305 |
| }, |
| { |
| "entropy": 6.604641580581665, |
| "epoch": 0.06738163207571432, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004883229283289071, |
| "loss": 6.3298, |
| "mean_token_accuracy": 0.11663304418325424, |
| "num_tokens": 2336096.0, |
| "step": 1310 |
| }, |
| { |
| "entropy": 6.647005414962768, |
| "epoch": 0.06763881387753003, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00048794541024725993, |
| "loss": 6.2797, |
| "mean_token_accuracy": 0.11775869503617287, |
| "num_tokens": 2345393.0, |
| "step": 1315 |
| }, |
| { |
| "entropy": 6.554132890701294, |
| "epoch": 0.06789599567934573, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004875620541596221, |
| "loss": 6.2501, |
| "mean_token_accuracy": 0.12467899695038795, |
| "num_tokens": 2353824.0, |
| "step": 1320 |
| }, |
| { |
| "entropy": 6.465411710739136, |
| "epoch": 0.06815317748116144, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00048717287057589454, |
| "loss": 6.2802, |
| "mean_token_accuracy": 0.12414587661623955, |
| "num_tokens": 2361992.0, |
| "step": 1325 |
| }, |
| { |
| "entropy": 6.607723951339722, |
| "epoch": 0.06841035928297713, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0004867778701657417, |
| "loss": 6.1856, |
| "mean_token_accuracy": 0.12355614453554153, |
| "num_tokens": 2370849.0, |
| "step": 1330 |
| }, |
| { |
| "entropy": 6.542122459411621, |
| "epoch": 0.06866754108479284, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00048637706375829955, |
| "loss": 6.2951, |
| "mean_token_accuracy": 0.125213223695755, |
| "num_tokens": 2379460.0, |
| "step": 1335 |
| }, |
| { |
| "entropy": 6.524771022796631, |
| "epoch": 0.06892472288660854, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000485970462341878, |
| "loss": 6.1841, |
| "mean_token_accuracy": 0.12624969705939293, |
| "num_tokens": 2388236.0, |
| "step": 1340 |
| }, |
| { |
| "entropy": 6.408080244064331, |
| "epoch": 0.06918190468842425, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00048555807706366044, |
| "loss": 6.2347, |
| "mean_token_accuracy": 0.12203069031238556, |
| "num_tokens": 2397598.0, |
| "step": 1345 |
| }, |
| { |
| "entropy": 6.627772331237793, |
| "epoch": 0.06943908649023996, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00048513991922939756, |
| "loss": 6.2066, |
| "mean_token_accuracy": 0.12295120730996131, |
| "num_tokens": 2406097.0, |
| "step": 1350 |
| }, |
| { |
| "entropy": 6.502293634414673, |
| "epoch": 0.06969626829205565, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00048471600030309744, |
| "loss": 6.3098, |
| "mean_token_accuracy": 0.11426047384738922, |
| "num_tokens": 2414590.0, |
| "step": 1355 |
| }, |
| { |
| "entropy": 6.440834903717041, |
| "epoch": 0.06995345009387136, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00048428633190671186, |
| "loss": 6.1354, |
| "mean_token_accuracy": 0.1235704205930233, |
| "num_tokens": 2424100.0, |
| "step": 1360 |
| }, |
| { |
| "entropy": 6.563741016387939, |
| "epoch": 0.07021063189568706, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004838509258198167, |
| "loss": 6.2091, |
| "mean_token_accuracy": 0.121873689442873, |
| "num_tokens": 2432751.0, |
| "step": 1365 |
| }, |
| { |
| "entropy": 6.543551826477051, |
| "epoch": 0.07046781369750277, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00048340979397929, |
| "loss": 6.1861, |
| "mean_token_accuracy": 0.12034041285514832, |
| "num_tokens": 2442054.0, |
| "step": 1370 |
| }, |
| { |
| "entropy": 6.375408792495728, |
| "epoch": 0.07072499549931847, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00048296294847898386, |
| "loss": 6.1099, |
| "mean_token_accuracy": 0.12799823582172393, |
| "num_tokens": 2450711.0, |
| "step": 1375 |
| }, |
| { |
| "entropy": 6.405136442184448, |
| "epoch": 0.07098217730113417, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004825104015693934, |
| "loss": 6.1895, |
| "mean_token_accuracy": 0.12983948215842248, |
| "num_tokens": 2460203.0, |
| "step": 1380 |
| }, |
| { |
| "entropy": 6.558651971817016, |
| "epoch": 0.07123935910294987, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004820521656573208, |
| "loss": 6.2482, |
| "mean_token_accuracy": 0.12185781002044678, |
| "num_tokens": 2469656.0, |
| "step": 1385 |
| }, |
| { |
| "entropy": 6.4783261775970455, |
| "epoch": 0.07149654090476558, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00048158825330553505, |
| "loss": 6.1986, |
| "mean_token_accuracy": 0.12839986979961396, |
| "num_tokens": 2478359.0, |
| "step": 1390 |
| }, |
| { |
| "entropy": 6.440516662597656, |
| "epoch": 0.07175372270658129, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00048111867723242763, |
| "loss": 6.1319, |
| "mean_token_accuracy": 0.12275411933660507, |
| "num_tokens": 2487330.0, |
| "step": 1395 |
| }, |
| { |
| "entropy": 6.464969682693481, |
| "epoch": 0.07201090450839699, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004806434503116637, |
| "loss": 6.1196, |
| "mean_token_accuracy": 0.12776034623384475, |
| "num_tokens": 2495445.0, |
| "step": 1400 |
| }, |
| { |
| "entropy": 6.352128219604492, |
| "epoch": 0.07226808631021268, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004801625855718296, |
| "loss": 6.1221, |
| "mean_token_accuracy": 0.129915539175272, |
| "num_tokens": 2504061.0, |
| "step": 1405 |
| }, |
| { |
| "entropy": 6.479479789733887, |
| "epoch": 0.07252526811202839, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00047967609619607477, |
| "loss": 6.1634, |
| "mean_token_accuracy": 0.12523439154028893, |
| "num_tokens": 2513044.0, |
| "step": 1410 |
| }, |
| { |
| "entropy": 6.456380176544189, |
| "epoch": 0.0727824499138441, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004791839955217513, |
| "loss": 6.2452, |
| "mean_token_accuracy": 0.12148747369647026, |
| "num_tokens": 2522027.0, |
| "step": 1415 |
| }, |
| { |
| "entropy": 6.455992269515991, |
| "epoch": 0.0730396317156598, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00047868629704004786, |
| "loss": 6.1438, |
| "mean_token_accuracy": 0.12664651721715928, |
| "num_tokens": 2530888.0, |
| "step": 1420 |
| }, |
| { |
| "entropy": 6.309210348129272, |
| "epoch": 0.07329681351747551, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00047818301439561965, |
| "loss": 6.1205, |
| "mean_token_accuracy": 0.13230895176529883, |
| "num_tokens": 2540210.0, |
| "step": 1425 |
| }, |
| { |
| "entropy": 6.500010251998901, |
| "epoch": 0.0735539953192912, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00047767416138621454, |
| "loss": 6.1576, |
| "mean_token_accuracy": 0.13035310953855514, |
| "num_tokens": 2547943.0, |
| "step": 1430 |
| }, |
| { |
| "entropy": 6.4128905773162845, |
| "epoch": 0.07381117712110691, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000477159751962295, |
| "loss": 6.1758, |
| "mean_token_accuracy": 0.12096773236989974, |
| "num_tokens": 2557174.0, |
| "step": 1435 |
| }, |
| { |
| "entropy": 6.467635154724121, |
| "epoch": 0.07406835892292261, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00047663980022665507, |
| "loss": 6.1847, |
| "mean_token_accuracy": 0.12423764616250992, |
| "num_tokens": 2566139.0, |
| "step": 1440 |
| }, |
| { |
| "entropy": 6.443244886398316, |
| "epoch": 0.07432554072473832, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00047611432043403437, |
| "loss": 6.1833, |
| "mean_token_accuracy": 0.12400569245219231, |
| "num_tokens": 2574701.0, |
| "step": 1445 |
| }, |
| { |
| "entropy": 6.48380708694458, |
| "epoch": 0.07458272252655403, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004755833269907267, |
| "loss": 6.1683, |
| "mean_token_accuracy": 0.13298066854476928, |
| "num_tokens": 2583065.0, |
| "step": 1450 |
| }, |
| { |
| "entropy": 6.337066030502319, |
| "epoch": 0.07483990432836972, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004750468344541857, |
| "loss": 6.0415, |
| "mean_token_accuracy": 0.13096242472529412, |
| "num_tokens": 2592619.0, |
| "step": 1455 |
| }, |
| { |
| "entropy": 6.387078046798706, |
| "epoch": 0.07509708613018543, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00047450485753262525, |
| "loss": 6.1234, |
| "mean_token_accuracy": 0.12428422570228577, |
| "num_tokens": 2601434.0, |
| "step": 1460 |
| }, |
| { |
| "entropy": 6.404777574539184, |
| "epoch": 0.07535426793200113, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00047395741108461633, |
| "loss": 6.247, |
| "mean_token_accuracy": 0.11993053182959557, |
| "num_tokens": 2610925.0, |
| "step": 1465 |
| }, |
| { |
| "entropy": 6.445322704315186, |
| "epoch": 0.07561144973381684, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00047340451011867985, |
| "loss": 6.2036, |
| "mean_token_accuracy": 0.1239316701889038, |
| "num_tokens": 2620275.0, |
| "step": 1470 |
| }, |
| { |
| "entropy": 6.519756078720093, |
| "epoch": 0.07586863153563254, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00047284616979287515, |
| "loss": 6.2099, |
| "mean_token_accuracy": 0.1233117938041687, |
| "num_tokens": 2629826.0, |
| "step": 1475 |
| }, |
| { |
| "entropy": 6.344198274612427, |
| "epoch": 0.07612581333744824, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00047228240541438433, |
| "loss": 5.9902, |
| "mean_token_accuracy": 0.13270971104502677, |
| "num_tokens": 2638680.0, |
| "step": 1480 |
| }, |
| { |
| "entropy": 6.357509803771973, |
| "epoch": 0.07638299513926394, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00047171323243909257, |
| "loss": 6.1679, |
| "mean_token_accuracy": 0.12576281726360322, |
| "num_tokens": 2647739.0, |
| "step": 1485 |
| }, |
| { |
| "entropy": 6.3423261642456055, |
| "epoch": 0.07664017694107965, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00047113866647116457, |
| "loss": 6.0689, |
| "mean_token_accuracy": 0.12693566605448722, |
| "num_tokens": 2656137.0, |
| "step": 1490 |
| }, |
| { |
| "entropy": 6.399060344696045, |
| "epoch": 0.07689735874289536, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0004705587232626164, |
| "loss": 6.1868, |
| "mean_token_accuracy": 0.1253664128482342, |
| "num_tokens": 2665173.0, |
| "step": 1495 |
| }, |
| { |
| "entropy": 6.466083621978759, |
| "epoch": 0.07715454054471106, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00046997341871288424, |
| "loss": 6.1583, |
| "mean_token_accuracy": 0.13294297680258751, |
| "num_tokens": 2673574.0, |
| "step": 1500 |
| }, |
| { |
| "entropy": 6.281017255783081, |
| "epoch": 0.07741172234652675, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0004693827688683879, |
| "loss": 6.0623, |
| "mean_token_accuracy": 0.1325296178460121, |
| "num_tokens": 2682550.0, |
| "step": 1505 |
| }, |
| { |
| "entropy": 6.448086404800415, |
| "epoch": 0.07766890414834246, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004687867899220914, |
| "loss": 6.1484, |
| "mean_token_accuracy": 0.1286767065525055, |
| "num_tokens": 2691473.0, |
| "step": 1510 |
| }, |
| { |
| "entropy": 6.355803918838501, |
| "epoch": 0.07792608595015817, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00046818549821305846, |
| "loss": 6.1298, |
| "mean_token_accuracy": 0.12500087693333625, |
| "num_tokens": 2700351.0, |
| "step": 1515 |
| }, |
| { |
| "entropy": 6.375854969024658, |
| "epoch": 0.07818326775197387, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00046757891022600494, |
| "loss": 6.134, |
| "mean_token_accuracy": 0.13383759930729866, |
| "num_tokens": 2709286.0, |
| "step": 1520 |
| }, |
| { |
| "entropy": 6.397713947296142, |
| "epoch": 0.07844044955378958, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004669670425908471, |
| "loss": 6.1319, |
| "mean_token_accuracy": 0.1305990234017372, |
| "num_tokens": 2718003.0, |
| "step": 1525 |
| }, |
| { |
| "entropy": 6.5097356796264645, |
| "epoch": 0.07869763135560527, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004663499120822451, |
| "loss": 6.1401, |
| "mean_token_accuracy": 0.13283091709017752, |
| "num_tokens": 2726488.0, |
| "step": 1530 |
| }, |
| { |
| "entropy": 6.442542362213135, |
| "epoch": 0.07895481315742098, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004657275356191437, |
| "loss": 6.2381, |
| "mean_token_accuracy": 0.12060219943523406, |
| "num_tokens": 2735183.0, |
| "step": 1535 |
| }, |
| { |
| "entropy": 6.431625938415527, |
| "epoch": 0.07921199495923668, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00046509993026430804, |
| "loss": 6.1846, |
| "mean_token_accuracy": 0.13017381876707076, |
| "num_tokens": 2744730.0, |
| "step": 1540 |
| }, |
| { |
| "entropy": 6.391227769851684, |
| "epoch": 0.07946917676105239, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004644671132238558, |
| "loss": 6.078, |
| "mean_token_accuracy": 0.13144444525241852, |
| "num_tokens": 2753148.0, |
| "step": 1545 |
| }, |
| { |
| "entropy": 6.3710565090179445, |
| "epoch": 0.0797263585628681, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00046382910184678585, |
| "loss": 6.1304, |
| "mean_token_accuracy": 0.12514668405056, |
| "num_tokens": 2762394.0, |
| "step": 1550 |
| }, |
| { |
| "entropy": 6.383265018463135, |
| "epoch": 0.07998354036468379, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004631859136245025, |
| "loss": 6.0604, |
| "mean_token_accuracy": 0.13881182968616484, |
| "num_tokens": 2770778.0, |
| "step": 1555 |
| }, |
| { |
| "entropy": 6.303916597366333, |
| "epoch": 0.0802407221664995, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004625375661903357, |
| "loss": 6.0143, |
| "mean_token_accuracy": 0.1306192882359028, |
| "num_tokens": 2779530.0, |
| "step": 1560 |
| }, |
| { |
| "entropy": 6.338508129119873, |
| "epoch": 0.0804979039683152, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00046188407731905787, |
| "loss": 6.0973, |
| "mean_token_accuracy": 0.12936475947499276, |
| "num_tokens": 2788587.0, |
| "step": 1565 |
| }, |
| { |
| "entropy": 6.286006164550781, |
| "epoch": 0.08075508577013091, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00046122546492639643, |
| "loss": 6.0359, |
| "mean_token_accuracy": 0.13100264444947243, |
| "num_tokens": 2797759.0, |
| "step": 1570 |
| }, |
| { |
| "entropy": 6.315873813629151, |
| "epoch": 0.08101226757194661, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000460561747068543, |
| "loss": 5.9986, |
| "mean_token_accuracy": 0.13158408626914025, |
| "num_tokens": 2806030.0, |
| "step": 1575 |
| }, |
| { |
| "entropy": 6.338774108886719, |
| "epoch": 0.0812694493737623, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004598929419416578, |
| "loss": 6.0144, |
| "mean_token_accuracy": 0.13145786076784133, |
| "num_tokens": 2815051.0, |
| "step": 1580 |
| }, |
| { |
| "entropy": 6.2580437660217285, |
| "epoch": 0.08152663117557801, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00045921906788137123, |
| "loss": 6.0245, |
| "mean_token_accuracy": 0.1368385747075081, |
| "num_tokens": 2824019.0, |
| "step": 1585 |
| }, |
| { |
| "entropy": 6.473824882507325, |
| "epoch": 0.08178381297739372, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00045854014336228115, |
| "loss": 6.1763, |
| "mean_token_accuracy": 0.12589069753885268, |
| "num_tokens": 2832494.0, |
| "step": 1590 |
| }, |
| { |
| "entropy": 6.306181764602661, |
| "epoch": 0.08204099477920943, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00045785618699744615, |
| "loss": 6.0168, |
| "mean_token_accuracy": 0.13415324538946152, |
| "num_tokens": 2841314.0, |
| "step": 1595 |
| }, |
| { |
| "entropy": 6.2222880840301515, |
| "epoch": 0.08229817658102513, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00045716721753787543, |
| "loss": 5.9476, |
| "mean_token_accuracy": 0.13951284289360047, |
| "num_tokens": 2849635.0, |
| "step": 1600 |
| }, |
| { |
| "entropy": 6.297337532043457, |
| "epoch": 0.08255535838284082, |
| "grad_norm": 1.2265625, |
| "learning_rate": 0.0004564732538720148, |
| "loss": 6.094, |
| "mean_token_accuracy": 0.12806924805045128, |
| "num_tokens": 2859306.0, |
| "step": 1605 |
| }, |
| { |
| "entropy": 6.361379623413086, |
| "epoch": 0.08281254018465653, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00045577431502522877, |
| "loss": 6.1886, |
| "mean_token_accuracy": 0.1268698565661907, |
| "num_tokens": 2868316.0, |
| "step": 1610 |
| }, |
| { |
| "entropy": 6.415389966964722, |
| "epoch": 0.08306972198647224, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004550704201592787, |
| "loss": 6.1611, |
| "mean_token_accuracy": 0.12649422660470008, |
| "num_tokens": 2877508.0, |
| "step": 1615 |
| }, |
| { |
| "entropy": 6.425594854354858, |
| "epoch": 0.08332690378828794, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.0004543615885717981, |
| "loss": 6.1123, |
| "mean_token_accuracy": 0.1241836428642273, |
| "num_tokens": 2886927.0, |
| "step": 1620 |
| }, |
| { |
| "entropy": 6.364439010620117, |
| "epoch": 0.08358408559010365, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00045364783969576296, |
| "loss": 6.1434, |
| "mean_token_accuracy": 0.12308017164468765, |
| "num_tokens": 2896484.0, |
| "step": 1625 |
| }, |
| { |
| "entropy": 6.411374950408936, |
| "epoch": 0.08384126739191934, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004529291930989592, |
| "loss": 6.0181, |
| "mean_token_accuracy": 0.13011238351464272, |
| "num_tokens": 2905298.0, |
| "step": 1630 |
| }, |
| { |
| "entropy": 6.292522811889649, |
| "epoch": 0.08409844919373505, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0004522056684834464, |
| "loss": 6.0992, |
| "mean_token_accuracy": 0.1334770753979683, |
| "num_tokens": 2913811.0, |
| "step": 1635 |
| }, |
| { |
| "entropy": 6.370844841003418, |
| "epoch": 0.08435563099555075, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004514772856850173, |
| "loss": 6.0902, |
| "mean_token_accuracy": 0.128910331428051, |
| "num_tokens": 2922531.0, |
| "step": 1640 |
| }, |
| { |
| "entropy": 6.311898422241211, |
| "epoch": 0.08461281279736646, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0004507440646726542, |
| "loss": 6.0567, |
| "mean_token_accuracy": 0.13458428382873536, |
| "num_tokens": 2931178.0, |
| "step": 1645 |
| }, |
| { |
| "entropy": 6.309841632843018, |
| "epoch": 0.08486999459918217, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004500060255479818, |
| "loss": 6.0937, |
| "mean_token_accuracy": 0.13025279939174653, |
| "num_tokens": 2940419.0, |
| "step": 1650 |
| }, |
| { |
| "entropy": 6.36889328956604, |
| "epoch": 0.08512717640099786, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004492631885447151, |
| "loss": 5.9964, |
| "mean_token_accuracy": 0.1294368840754032, |
| "num_tokens": 2949119.0, |
| "step": 1655 |
| }, |
| { |
| "entropy": 6.307538890838623, |
| "epoch": 0.08538435820281357, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00044851557402810616, |
| "loss": 6.1656, |
| "mean_token_accuracy": 0.12390446290373802, |
| "num_tokens": 2957775.0, |
| "step": 1660 |
| }, |
| { |
| "entropy": 6.376241397857666, |
| "epoch": 0.08564154000462927, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00044776320249438444, |
| "loss": 6.0929, |
| "mean_token_accuracy": 0.1286988750100136, |
| "num_tokens": 2967644.0, |
| "step": 1665 |
| }, |
| { |
| "entropy": 6.352219152450561, |
| "epoch": 0.08589872180644498, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00044700609457019565, |
| "loss": 6.0603, |
| "mean_token_accuracy": 0.13165615424513816, |
| "num_tokens": 2975608.0, |
| "step": 1670 |
| }, |
| { |
| "entropy": 6.289653968811035, |
| "epoch": 0.08615590360826068, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0004462442710120359, |
| "loss": 6.0552, |
| "mean_token_accuracy": 0.1328391693532467, |
| "num_tokens": 2984138.0, |
| "step": 1675 |
| }, |
| { |
| "entropy": 6.410796213150024, |
| "epoch": 0.08641308541007638, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000445477752705683, |
| "loss": 6.1551, |
| "mean_token_accuracy": 0.12801553606986998, |
| "num_tokens": 2992770.0, |
| "step": 1680 |
| }, |
| { |
| "entropy": 6.379126834869385, |
| "epoch": 0.08667026721189208, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00044470656066562336, |
| "loss": 5.9911, |
| "mean_token_accuracy": 0.1325019121170044, |
| "num_tokens": 3001685.0, |
| "step": 1685 |
| }, |
| { |
| "entropy": 6.266774129867554, |
| "epoch": 0.08692744901370779, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0004439307160344765, |
| "loss": 6.0246, |
| "mean_token_accuracy": 0.13351587057113648, |
| "num_tokens": 3010905.0, |
| "step": 1690 |
| }, |
| { |
| "entropy": 6.312497520446778, |
| "epoch": 0.0871846308155235, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00044315024008241473, |
| "loss": 6.0822, |
| "mean_token_accuracy": 0.12986138314008713, |
| "num_tokens": 3020257.0, |
| "step": 1695 |
| }, |
| { |
| "entropy": 6.329559803009033, |
| "epoch": 0.0874418126173392, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0004423651542065806, |
| "loss": 6.086, |
| "mean_token_accuracy": 0.1287504680454731, |
| "num_tokens": 3029397.0, |
| "step": 1700 |
| }, |
| { |
| "entropy": 6.40656681060791, |
| "epoch": 0.0876989944191549, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00044157547993050006, |
| "loss": 6.0878, |
| "mean_token_accuracy": 0.12193093374371529, |
| "num_tokens": 3038822.0, |
| "step": 1705 |
| }, |
| { |
| "entropy": 6.286016368865967, |
| "epoch": 0.0879561762209706, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00044078123890349227, |
| "loss": 5.9675, |
| "mean_token_accuracy": 0.13392331525683404, |
| "num_tokens": 3047435.0, |
| "step": 1710 |
| }, |
| { |
| "entropy": 6.301493215560913, |
| "epoch": 0.0882133580227863, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00043998245290007606, |
| "loss": 6.1045, |
| "mean_token_accuracy": 0.13060200214385986, |
| "num_tokens": 3056011.0, |
| "step": 1715 |
| }, |
| { |
| "entropy": 6.378498220443726, |
| "epoch": 0.08847053982460201, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00043917914381937323, |
| "loss": 6.0839, |
| "mean_token_accuracy": 0.1344021290540695, |
| "num_tokens": 3064182.0, |
| "step": 1720 |
| }, |
| { |
| "entropy": 6.304371786117554, |
| "epoch": 0.08872772162641772, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00043837133368450815, |
| "loss": 6.0605, |
| "mean_token_accuracy": 0.13042551502585412, |
| "num_tokens": 3072669.0, |
| "step": 1725 |
| }, |
| { |
| "entropy": 6.319208002090454, |
| "epoch": 0.08898490342823343, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0004375590446420037, |
| "loss": 6.0262, |
| "mean_token_accuracy": 0.13751724287867545, |
| "num_tokens": 3081024.0, |
| "step": 1730 |
| }, |
| { |
| "entropy": 6.245740699768066, |
| "epoch": 0.08924208523004912, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004367422989611743, |
| "loss": 5.9442, |
| "mean_token_accuracy": 0.13434263542294503, |
| "num_tokens": 3089747.0, |
| "step": 1735 |
| }, |
| { |
| "entropy": 6.31815619468689, |
| "epoch": 0.08949926703186482, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004359211190335153, |
| "loss": 6.0425, |
| "mean_token_accuracy": 0.13445181101560594, |
| "num_tokens": 3099011.0, |
| "step": 1740 |
| }, |
| { |
| "entropy": 6.286892604827881, |
| "epoch": 0.08975644883368053, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00043509552737208923, |
| "loss": 5.9967, |
| "mean_token_accuracy": 0.13267636224627494, |
| "num_tokens": 3107645.0, |
| "step": 1745 |
| }, |
| { |
| "entropy": 6.278048324584961, |
| "epoch": 0.09001363063549624, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00043426554661090853, |
| "loss": 6.0557, |
| "mean_token_accuracy": 0.1316031478345394, |
| "num_tokens": 3116292.0, |
| "step": 1750 |
| }, |
| { |
| "entropy": 6.359972858428955, |
| "epoch": 0.09027081243731194, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00043343119950431516, |
| "loss": 6.0723, |
| "mean_token_accuracy": 0.13226044401526452, |
| "num_tokens": 3126356.0, |
| "step": 1755 |
| }, |
| { |
| "entropy": 6.250633955001831, |
| "epoch": 0.09052799423912763, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00043259250892635644, |
| "loss": 6.0472, |
| "mean_token_accuracy": 0.12974994629621506, |
| "num_tokens": 3135685.0, |
| "step": 1760 |
| }, |
| { |
| "entropy": 6.314090394973755, |
| "epoch": 0.09078517604094334, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004317494978701582, |
| "loss": 6.0026, |
| "mean_token_accuracy": 0.12911238446831702, |
| "num_tokens": 3144788.0, |
| "step": 1765 |
| }, |
| { |
| "entropy": 6.288527154922486, |
| "epoch": 0.09104235784275905, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004309021894472943, |
| "loss": 6.0151, |
| "mean_token_accuracy": 0.1408878244459629, |
| "num_tokens": 3153273.0, |
| "step": 1770 |
| }, |
| { |
| "entropy": 6.267010736465454, |
| "epoch": 0.09129953964457475, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0004300506068871534, |
| "loss": 6.0249, |
| "mean_token_accuracy": 0.1345413491129875, |
| "num_tokens": 3161806.0, |
| "step": 1775 |
| }, |
| { |
| "entropy": 6.174133968353272, |
| "epoch": 0.09155672144639046, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00042919477353630135, |
| "loss": 5.8371, |
| "mean_token_accuracy": 0.14690690338611603, |
| "num_tokens": 3170401.0, |
| "step": 1780 |
| }, |
| { |
| "entropy": 6.2911989212036135, |
| "epoch": 0.09181390324820615, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.000428334712857842, |
| "loss": 5.9583, |
| "mean_token_accuracy": 0.13602055236697197, |
| "num_tokens": 3179742.0, |
| "step": 1785 |
| }, |
| { |
| "entropy": 6.309875202178955, |
| "epoch": 0.09207108505002186, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00042747044843077304, |
| "loss": 6.1082, |
| "mean_token_accuracy": 0.13044340386986733, |
| "num_tokens": 3188898.0, |
| "step": 1790 |
| }, |
| { |
| "entropy": 6.30495662689209, |
| "epoch": 0.09232826685183756, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00042660200394934047, |
| "loss": 6.0906, |
| "mean_token_accuracy": 0.12872936055064202, |
| "num_tokens": 3197860.0, |
| "step": 1795 |
| }, |
| { |
| "entropy": 6.351209688186645, |
| "epoch": 0.09258544865365327, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00042572940322238844, |
| "loss": 6.0633, |
| "mean_token_accuracy": 0.133078370988369, |
| "num_tokens": 3206779.0, |
| "step": 1800 |
| }, |
| { |
| "entropy": 6.252921724319458, |
| "epoch": 0.09284263045546898, |
| "grad_norm": 1.1875, |
| "learning_rate": 0.00042485267017270664, |
| "loss": 5.9835, |
| "mean_token_accuracy": 0.1363011360168457, |
| "num_tokens": 3215051.0, |
| "step": 1805 |
| }, |
| { |
| "entropy": 6.277395391464234, |
| "epoch": 0.09309981225728467, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0004239718288363745, |
| "loss": 5.9666, |
| "mean_token_accuracy": 0.1378926604986191, |
| "num_tokens": 3223977.0, |
| "step": 1810 |
| }, |
| { |
| "entropy": 6.305054616928101, |
| "epoch": 0.09335699405910038, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004230869033621023, |
| "loss": 5.9981, |
| "mean_token_accuracy": 0.1367839142680168, |
| "num_tokens": 3232714.0, |
| "step": 1815 |
| }, |
| { |
| "entropy": 6.307405042648315, |
| "epoch": 0.09361417586091608, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0004221979180105688, |
| "loss": 5.9666, |
| "mean_token_accuracy": 0.13633009940385818, |
| "num_tokens": 3241405.0, |
| "step": 1820 |
| }, |
| { |
| "entropy": 6.269251775741577, |
| "epoch": 0.09387135766273179, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00042130489715375645, |
| "loss": 6.0106, |
| "mean_token_accuracy": 0.13501947596669198, |
| "num_tokens": 3249846.0, |
| "step": 1825 |
| }, |
| { |
| "entropy": 6.296307373046875, |
| "epoch": 0.0941285394645475, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00042040786527428335, |
| "loss": 5.9188, |
| "mean_token_accuracy": 0.13773071020841599, |
| "num_tokens": 3258231.0, |
| "step": 1830 |
| }, |
| { |
| "entropy": 6.150211763381958, |
| "epoch": 0.09438572126636319, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0004195068469647315, |
| "loss": 5.9593, |
| "mean_token_accuracy": 0.1389425627887249, |
| "num_tokens": 3267333.0, |
| "step": 1835 |
| }, |
| { |
| "entropy": 6.298181486129761, |
| "epoch": 0.0946429030681789, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00041860186692697297, |
| "loss": 6.1112, |
| "mean_token_accuracy": 0.12236591503024101, |
| "num_tokens": 3276575.0, |
| "step": 1840 |
| }, |
| { |
| "entropy": 6.347346067428589, |
| "epoch": 0.0949000848699946, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00041769294997149264, |
| "loss": 6.1014, |
| "mean_token_accuracy": 0.12974566370248794, |
| "num_tokens": 3284771.0, |
| "step": 1845 |
| }, |
| { |
| "entropy": 6.261059379577636, |
| "epoch": 0.0951572666718103, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.0004167801210167081, |
| "loss": 6.0138, |
| "mean_token_accuracy": 0.13305832222104072, |
| "num_tokens": 3294091.0, |
| "step": 1850 |
| }, |
| { |
| "entropy": 6.248409795761108, |
| "epoch": 0.09541444847362601, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004158634050882861, |
| "loss": 5.8796, |
| "mean_token_accuracy": 0.13779047578573228, |
| "num_tokens": 3302572.0, |
| "step": 1855 |
| }, |
| { |
| "entropy": 6.177290248870849, |
| "epoch": 0.0956716302754417, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0004149428273184569, |
| "loss": 5.9015, |
| "mean_token_accuracy": 0.14134511575102807, |
| "num_tokens": 3310709.0, |
| "step": 1860 |
| }, |
| { |
| "entropy": 6.239241313934326, |
| "epoch": 0.09592881207725741, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0004140184129453253, |
| "loss": 5.9881, |
| "mean_token_accuracy": 0.13656110763549806, |
| "num_tokens": 3319959.0, |
| "step": 1865 |
| }, |
| { |
| "entropy": 6.237763357162476, |
| "epoch": 0.09618599387907312, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.000413090187312178, |
| "loss": 5.9338, |
| "mean_token_accuracy": 0.1348011650145054, |
| "num_tokens": 3328475.0, |
| "step": 1870 |
| }, |
| { |
| "entropy": 6.189648580551148, |
| "epoch": 0.09644317568088882, |
| "grad_norm": 0.97265625, |
| "learning_rate": 0.0004121581758667898, |
| "loss": 6.0114, |
| "mean_token_accuracy": 0.1303848333656788, |
| "num_tokens": 3337785.0, |
| "step": 1875 |
| }, |
| { |
| "entropy": 6.246728134155274, |
| "epoch": 0.09670035748270453, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00041122240416072533, |
| "loss": 5.9514, |
| "mean_token_accuracy": 0.13871703594923018, |
| "num_tokens": 3347102.0, |
| "step": 1880 |
| }, |
| { |
| "entropy": 6.295105886459351, |
| "epoch": 0.09695753928452022, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0004102828978486385, |
| "loss": 5.9854, |
| "mean_token_accuracy": 0.13081275448203086, |
| "num_tokens": 3356787.0, |
| "step": 1885 |
| }, |
| { |
| "entropy": 6.240402698516846, |
| "epoch": 0.09721472108633593, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0004093396826875695, |
| "loss": 6.058, |
| "mean_token_accuracy": 0.1320380300283432, |
| "num_tokens": 3365497.0, |
| "step": 1890 |
| }, |
| { |
| "entropy": 6.231711196899414, |
| "epoch": 0.09747190288815163, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00040839278453623837, |
| "loss": 6.0093, |
| "mean_token_accuracy": 0.13135660141706468, |
| "num_tokens": 3373622.0, |
| "step": 1895 |
| }, |
| { |
| "entropy": 6.235841464996338, |
| "epoch": 0.09772908468996734, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0004074422293543363, |
| "loss": 5.9967, |
| "mean_token_accuracy": 0.13504694923758506, |
| "num_tokens": 3382563.0, |
| "step": 1900 |
| }, |
| { |
| "entropy": 6.295864820480347, |
| "epoch": 0.09798626649178305, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0004064880432018137, |
| "loss": 5.8712, |
| "mean_token_accuracy": 0.14425868391990662, |
| "num_tokens": 3390686.0, |
| "step": 1905 |
| }, |
| { |
| "entropy": 6.186135339736938, |
| "epoch": 0.09824344829359874, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00040553025223816615, |
| "loss": 5.9351, |
| "mean_token_accuracy": 0.13617005720734596, |
| "num_tokens": 3399616.0, |
| "step": 1910 |
| }, |
| { |
| "entropy": 6.16251573562622, |
| "epoch": 0.09850063009541445, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00040456888272171653, |
| "loss": 5.834, |
| "mean_token_accuracy": 0.1381289020180702, |
| "num_tokens": 3407572.0, |
| "step": 1915 |
| }, |
| { |
| "entropy": 6.25083360671997, |
| "epoch": 0.09875781189723015, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00040360396100889577, |
| "loss": 5.9848, |
| "mean_token_accuracy": 0.13736421391367912, |
| "num_tokens": 3416174.0, |
| "step": 1920 |
| }, |
| { |
| "entropy": 6.121949052810669, |
| "epoch": 0.09901499369904586, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0004026355135535202, |
| "loss": 5.844, |
| "mean_token_accuracy": 0.1408976547420025, |
| "num_tokens": 3425115.0, |
| "step": 1925 |
| }, |
| { |
| "entropy": 6.129916381835938, |
| "epoch": 0.09927217550086156, |
| "grad_norm": 0.98828125, |
| "learning_rate": 0.000401663566906066, |
| "loss": 5.8997, |
| "mean_token_accuracy": 0.14465468153357505, |
| "num_tokens": 3433589.0, |
| "step": 1930 |
| }, |
| { |
| "entropy": 6.251618909835815, |
| "epoch": 0.09952935730267726, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00040068814771294134, |
| "loss": 5.9948, |
| "mean_token_accuracy": 0.14055624082684517, |
| "num_tokens": 3443205.0, |
| "step": 1935 |
| }, |
| { |
| "entropy": 6.300161504745484, |
| "epoch": 0.09978653910449296, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0003997092827157562, |
| "loss": 5.9464, |
| "mean_token_accuracy": 0.136979528516531, |
| "num_tokens": 3451738.0, |
| "step": 1940 |
| }, |
| { |
| "entropy": 6.163929224014282, |
| "epoch": 0.10004372090630867, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000398726998750589, |
| "loss": 5.9042, |
| "mean_token_accuracy": 0.1414563961327076, |
| "num_tokens": 3461201.0, |
| "step": 1945 |
| }, |
| { |
| "entropy": 6.146855640411377, |
| "epoch": 0.10030090270812438, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00039774132274725076, |
| "loss": 5.9047, |
| "mean_token_accuracy": 0.1325928770005703, |
| "num_tokens": 3470788.0, |
| "step": 1950 |
| }, |
| { |
| "entropy": 6.3281749248504635, |
| "epoch": 0.10055808450994008, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00039675228172854707, |
| "loss": 6.0299, |
| "mean_token_accuracy": 0.13255303725600243, |
| "num_tokens": 3480143.0, |
| "step": 1955 |
| }, |
| { |
| "entropy": 6.215788984298706, |
| "epoch": 0.10081526631175577, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003957599028095371, |
| "loss": 5.9038, |
| "mean_token_accuracy": 0.14231238663196563, |
| "num_tokens": 3488217.0, |
| "step": 1960 |
| }, |
| { |
| "entropy": 6.2849045753479, |
| "epoch": 0.10107244811357148, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00039476421319679017, |
| "loss": 6.0992, |
| "mean_token_accuracy": 0.1307053431868553, |
| "num_tokens": 3496960.0, |
| "step": 1965 |
| }, |
| { |
| "entropy": 6.365100383758545, |
| "epoch": 0.10132962991538719, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00039376524018764, |
| "loss": 6.0058, |
| "mean_token_accuracy": 0.1358587734401226, |
| "num_tokens": 3506314.0, |
| "step": 1970 |
| }, |
| { |
| "entropy": 6.257384538650513, |
| "epoch": 0.1015868117172029, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00039276301116943616, |
| "loss": 5.9707, |
| "mean_token_accuracy": 0.14363735169172287, |
| "num_tokens": 3514425.0, |
| "step": 1975 |
| }, |
| { |
| "entropy": 6.19381799697876, |
| "epoch": 0.1018439935190186, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0003917575536187936, |
| "loss": 5.9653, |
| "mean_token_accuracy": 0.1379447251558304, |
| "num_tokens": 3524153.0, |
| "step": 1980 |
| }, |
| { |
| "entropy": 6.209758520126343, |
| "epoch": 0.10210117532083429, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00039074889510083894, |
| "loss": 5.8675, |
| "mean_token_accuracy": 0.14806670546531678, |
| "num_tokens": 3532252.0, |
| "step": 1985 |
| }, |
| { |
| "entropy": 6.207709884643554, |
| "epoch": 0.10235835712265, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00038973706326845495, |
| "loss": 5.9073, |
| "mean_token_accuracy": 0.13528766930103303, |
| "num_tokens": 3540689.0, |
| "step": 1990 |
| }, |
| { |
| "entropy": 6.209512042999267, |
| "epoch": 0.1026155389244657, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0003887220858615225, |
| "loss": 5.9125, |
| "mean_token_accuracy": 0.14427549242973328, |
| "num_tokens": 3549110.0, |
| "step": 1995 |
| }, |
| { |
| "entropy": 6.194009447097779, |
| "epoch": 0.10287272072628141, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0003877039907061597, |
| "loss": 5.8742, |
| "mean_token_accuracy": 0.14361105114221573, |
| "num_tokens": 3558252.0, |
| "step": 2000 |
| }, |
| { |
| "entropy": 6.208440446853638, |
| "epoch": 0.10312990252809712, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003866828057139598, |
| "loss": 5.9402, |
| "mean_token_accuracy": 0.1397227793931961, |
| "num_tokens": 3568072.0, |
| "step": 2005 |
| }, |
| { |
| "entropy": 6.253045082092285, |
| "epoch": 0.10338708432991281, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00038565855888122503, |
| "loss": 6.021, |
| "mean_token_accuracy": 0.13711158484220504, |
| "num_tokens": 3577757.0, |
| "step": 2010 |
| }, |
| { |
| "entropy": 6.093878173828125, |
| "epoch": 0.10364426613172852, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00038463127828819975, |
| "loss": 5.8341, |
| "mean_token_accuracy": 0.14332005605101586, |
| "num_tokens": 3586473.0, |
| "step": 2015 |
| }, |
| { |
| "entropy": 6.080322933197022, |
| "epoch": 0.10390144793354422, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00038360099209830043, |
| "loss": 5.8541, |
| "mean_token_accuracy": 0.14548535346984864, |
| "num_tokens": 3595613.0, |
| "step": 2020 |
| }, |
| { |
| "entropy": 6.200949335098267, |
| "epoch": 0.10415862973535993, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0003825677285573433, |
| "loss": 5.9442, |
| "mean_token_accuracy": 0.13252340257167816, |
| "num_tokens": 3604419.0, |
| "step": 2025 |
| }, |
| { |
| "entropy": 6.329448604583741, |
| "epoch": 0.10441581153717563, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00038153151599277027, |
| "loss": 5.9729, |
| "mean_token_accuracy": 0.13593906685709953, |
| "num_tokens": 3613772.0, |
| "step": 2030 |
| }, |
| { |
| "entropy": 6.2032801628112795, |
| "epoch": 0.10467299333899133, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0003804923828128723, |
| "loss": 6.0718, |
| "mean_token_accuracy": 0.13485433906316757, |
| "num_tokens": 3622257.0, |
| "step": 2035 |
| }, |
| { |
| "entropy": 6.277687215805054, |
| "epoch": 0.10493017514080703, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.0003794503575060104, |
| "loss": 5.9344, |
| "mean_token_accuracy": 0.1399565353989601, |
| "num_tokens": 3631533.0, |
| "step": 2040 |
| }, |
| { |
| "entropy": 6.321326494216919, |
| "epoch": 0.10518735694262274, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00037840546863983484, |
| "loss": 5.9758, |
| "mean_token_accuracy": 0.13514216914772986, |
| "num_tokens": 3640564.0, |
| "step": 2045 |
| }, |
| { |
| "entropy": 6.106148338317871, |
| "epoch": 0.10544453874443845, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003773577448605015, |
| "loss": 5.922, |
| "mean_token_accuracy": 0.13465480357408524, |
| "num_tokens": 3649679.0, |
| "step": 2050 |
| }, |
| { |
| "entropy": 6.29543514251709, |
| "epoch": 0.10570172054625415, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003763072148918872, |
| "loss": 5.9724, |
| "mean_token_accuracy": 0.1324113592505455, |
| "num_tokens": 3658621.0, |
| "step": 2055 |
| }, |
| { |
| "entropy": 6.238194513320923, |
| "epoch": 0.10595890234806984, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0003752539075348017, |
| "loss": 6.024, |
| "mean_token_accuracy": 0.1338699772953987, |
| "num_tokens": 3668219.0, |
| "step": 2060 |
| }, |
| { |
| "entropy": 6.18192138671875, |
| "epoch": 0.10621608414988555, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00037419785166619817, |
| "loss": 5.8913, |
| "mean_token_accuracy": 0.13923754915595055, |
| "num_tokens": 3676602.0, |
| "step": 2065 |
| }, |
| { |
| "entropy": 6.2596415996551515, |
| "epoch": 0.10647326595170126, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0003731390762383818, |
| "loss": 5.9881, |
| "mean_token_accuracy": 0.13510461896657944, |
| "num_tokens": 3686392.0, |
| "step": 2070 |
| }, |
| { |
| "entropy": 6.222888374328614, |
| "epoch": 0.10673044775351696, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003720776102782158, |
| "loss": 5.8973, |
| "mean_token_accuracy": 0.13920920044183732, |
| "num_tokens": 3695074.0, |
| "step": 2075 |
| }, |
| { |
| "entropy": 6.2563300132751465, |
| "epoch": 0.10698762955533267, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00037101348288632555, |
| "loss": 5.8753, |
| "mean_token_accuracy": 0.1440456449985504, |
| "num_tokens": 3703908.0, |
| "step": 2080 |
| }, |
| { |
| "entropy": 6.156075954437256, |
| "epoch": 0.10724481135714836, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003699467232363012, |
| "loss": 5.9132, |
| "mean_token_accuracy": 0.13406357616186143, |
| "num_tokens": 3712000.0, |
| "step": 2085 |
| }, |
| { |
| "entropy": 6.140146207809448, |
| "epoch": 0.10750199315896407, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0003688773605738973, |
| "loss": 5.8851, |
| "mean_token_accuracy": 0.14217042103409766, |
| "num_tokens": 3721301.0, |
| "step": 2090 |
| }, |
| { |
| "entropy": 6.304942989349366, |
| "epoch": 0.10775917496077977, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00036780542421623134, |
| "loss": 6.0298, |
| "mean_token_accuracy": 0.136605616658926, |
| "num_tokens": 3730636.0, |
| "step": 2095 |
| }, |
| { |
| "entropy": 6.104683065414429, |
| "epoch": 0.10801635676259548, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.0003667309435509802, |
| "loss": 5.73, |
| "mean_token_accuracy": 0.1420333556830883, |
| "num_tokens": 3738311.0, |
| "step": 2100 |
| }, |
| { |
| "entropy": 6.134877014160156, |
| "epoch": 0.10827353856441119, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0003656539480355741, |
| "loss": 5.8763, |
| "mean_token_accuracy": 0.13897452130913734, |
| "num_tokens": 3747197.0, |
| "step": 2105 |
| }, |
| { |
| "entropy": 6.17093939781189, |
| "epoch": 0.10853072036622688, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003645744671963891, |
| "loss": 5.9254, |
| "mean_token_accuracy": 0.13887861073017121, |
| "num_tokens": 3755969.0, |
| "step": 2110 |
| }, |
| { |
| "entropy": 6.148559951782227, |
| "epoch": 0.10878790216804259, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0003634925306279376, |
| "loss": 5.812, |
| "mean_token_accuracy": 0.14322378635406494, |
| "num_tokens": 3764948.0, |
| "step": 2115 |
| }, |
| { |
| "entropy": 6.172179412841797, |
| "epoch": 0.10904508396985829, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003624081679920574, |
| "loss": 5.8337, |
| "mean_token_accuracy": 0.13975358232855797, |
| "num_tokens": 3773754.0, |
| "step": 2120 |
| }, |
| { |
| "entropy": 6.159363317489624, |
| "epoch": 0.109302265771674, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0003613214090170977, |
| "loss": 5.8353, |
| "mean_token_accuracy": 0.1497413322329521, |
| "num_tokens": 3781905.0, |
| "step": 2125 |
| }, |
| { |
| "entropy": 6.148782062530517, |
| "epoch": 0.1095594475734897, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0003602322834971048, |
| "loss": 5.8991, |
| "mean_token_accuracy": 0.14403253346681594, |
| "num_tokens": 3790307.0, |
| "step": 2130 |
| }, |
| { |
| "entropy": 6.127641010284424, |
| "epoch": 0.1098166293753054, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003591408212910051, |
| "loss": 5.9209, |
| "mean_token_accuracy": 0.14021317809820175, |
| "num_tokens": 3799199.0, |
| "step": 2135 |
| }, |
| { |
| "entropy": 6.133929204940796, |
| "epoch": 0.1100738111771211, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0003580470523217863, |
| "loss": 5.8442, |
| "mean_token_accuracy": 0.14296304285526276, |
| "num_tokens": 3807403.0, |
| "step": 2140 |
| }, |
| { |
| "entropy": 6.101861524581909, |
| "epoch": 0.11033099297893681, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003569510065756771, |
| "loss": 5.8176, |
| "mean_token_accuracy": 0.13919469639658927, |
| "num_tokens": 3815370.0, |
| "step": 2145 |
| }, |
| { |
| "entropy": 6.13363208770752, |
| "epoch": 0.11058817478075252, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.0003558527141013254, |
| "loss": 5.8868, |
| "mean_token_accuracy": 0.1460254706442356, |
| "num_tokens": 3823898.0, |
| "step": 2150 |
| }, |
| { |
| "entropy": 6.295628023147583, |
| "epoch": 0.11084535658256822, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003547522050089742, |
| "loss": 5.9489, |
| "mean_token_accuracy": 0.13447053879499435, |
| "num_tokens": 3832696.0, |
| "step": 2155 |
| }, |
| { |
| "entropy": 6.227541112899781, |
| "epoch": 0.11110253838438391, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00035364950946963606, |
| "loss": 5.8739, |
| "mean_token_accuracy": 0.14524781927466393, |
| "num_tokens": 3841471.0, |
| "step": 2160 |
| }, |
| { |
| "entropy": 6.183211803436279, |
| "epoch": 0.11135972018619962, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003525446577142663, |
| "loss": 5.9008, |
| "mean_token_accuracy": 0.13683849573135376, |
| "num_tokens": 3850130.0, |
| "step": 2165 |
| }, |
| { |
| "entropy": 6.173109722137451, |
| "epoch": 0.11161690198801533, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00035143768003293395, |
| "loss": 6.01, |
| "mean_token_accuracy": 0.12651673927903176, |
| "num_tokens": 3860394.0, |
| "step": 2170 |
| }, |
| { |
| "entropy": 6.257704448699951, |
| "epoch": 0.11187408378983103, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003503286067739913, |
| "loss": 5.9061, |
| "mean_token_accuracy": 0.13790714517235755, |
| "num_tokens": 3868993.0, |
| "step": 2175 |
| }, |
| { |
| "entropy": 6.10837755203247, |
| "epoch": 0.11213126559164674, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00034921746834324193, |
| "loss": 5.8262, |
| "mean_token_accuracy": 0.15659269988536834, |
| "num_tokens": 3877745.0, |
| "step": 2180 |
| }, |
| { |
| "entropy": 6.189111042022705, |
| "epoch": 0.11238844739346243, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0003481042952031072, |
| "loss": 5.8607, |
| "mean_token_accuracy": 0.13797383308410643, |
| "num_tokens": 3887068.0, |
| "step": 2185 |
| }, |
| { |
| "entropy": 6.209196662902832, |
| "epoch": 0.11264562919527814, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0003469891178717911, |
| "loss": 5.9913, |
| "mean_token_accuracy": 0.13593252301216124, |
| "num_tokens": 3895403.0, |
| "step": 2190 |
| }, |
| { |
| "entropy": 6.156927394866943, |
| "epoch": 0.11290281099709384, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.0003458719669224436, |
| "loss": 5.8408, |
| "mean_token_accuracy": 0.14746169596910477, |
| "num_tokens": 3903798.0, |
| "step": 2195 |
| }, |
| { |
| "entropy": 6.206697273254394, |
| "epoch": 0.11315999279890955, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0003447528729823221, |
| "loss": 5.9597, |
| "mean_token_accuracy": 0.1433746412396431, |
| "num_tokens": 3912751.0, |
| "step": 2200 |
| }, |
| { |
| "entropy": 6.076588773727417, |
| "epoch": 0.11341717460072526, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0003436318667319525, |
| "loss": 5.7543, |
| "mean_token_accuracy": 0.1400095760822296, |
| "num_tokens": 3921502.0, |
| "step": 2205 |
| }, |
| { |
| "entropy": 6.126876497268677, |
| "epoch": 0.11367435640254096, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00034250897890428716, |
| "loss": 5.922, |
| "mean_token_accuracy": 0.1335408255457878, |
| "num_tokens": 3931099.0, |
| "step": 2210 |
| }, |
| { |
| "entropy": 6.200241422653198, |
| "epoch": 0.11393153820435666, |
| "grad_norm": 1.15625, |
| "learning_rate": 0.0003413842402838633, |
| "loss": 5.8709, |
| "mean_token_accuracy": 0.1449990078806877, |
| "num_tokens": 3939538.0, |
| "step": 2215 |
| }, |
| { |
| "entropy": 6.136349296569824, |
| "epoch": 0.11418872000617236, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00034025768170595834, |
| "loss": 5.9215, |
| "mean_token_accuracy": 0.14497197270393372, |
| "num_tokens": 3948701.0, |
| "step": 2220 |
| }, |
| { |
| "entropy": 6.2472795963287355, |
| "epoch": 0.11444590180798807, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0003391293340557446, |
| "loss": 5.9705, |
| "mean_token_accuracy": 0.13799142315983773, |
| "num_tokens": 3957965.0, |
| "step": 2225 |
| }, |
| { |
| "entropy": 6.13825831413269, |
| "epoch": 0.11470308360980377, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0003379992282674431, |
| "loss": 5.8944, |
| "mean_token_accuracy": 0.14160045757889747, |
| "num_tokens": 3966962.0, |
| "step": 2230 |
| }, |
| { |
| "entropy": 6.167397356033325, |
| "epoch": 0.11496026541161948, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0003368673953234749, |
| "loss": 5.7864, |
| "mean_token_accuracy": 0.14587752521038055, |
| "num_tokens": 3975741.0, |
| "step": 2235 |
| }, |
| { |
| "entropy": 6.161203241348266, |
| "epoch": 0.11521744721343517, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00033573386625361176, |
| "loss": 5.8719, |
| "mean_token_accuracy": 0.1401590384542942, |
| "num_tokens": 3984830.0, |
| "step": 2240 |
| }, |
| { |
| "entropy": 6.026100111007691, |
| "epoch": 0.11547462901525088, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00033459867213412567, |
| "loss": 5.6256, |
| "mean_token_accuracy": 0.15952029898762704, |
| "num_tokens": 3993104.0, |
| "step": 2245 |
| }, |
| { |
| "entropy": 6.058082246780396, |
| "epoch": 0.11573181081706659, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.000333461844086937, |
| "loss": 5.8719, |
| "mean_token_accuracy": 0.14272833094000817, |
| "num_tokens": 4001678.0, |
| "step": 2250 |
| }, |
| { |
| "entropy": 6.116197872161865, |
| "epoch": 0.11598899261888229, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00033232341327876097, |
| "loss": 5.8636, |
| "mean_token_accuracy": 0.14887568205595017, |
| "num_tokens": 4011218.0, |
| "step": 2255 |
| }, |
| { |
| "entropy": 6.199584913253784, |
| "epoch": 0.116246174420698, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0003311834109202531, |
| "loss": 5.8447, |
| "mean_token_accuracy": 0.14249034374952316, |
| "num_tokens": 4020258.0, |
| "step": 2260 |
| }, |
| { |
| "entropy": 6.155461072921753, |
| "epoch": 0.11650335622251369, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00033004186826515416, |
| "loss": 5.8353, |
| "mean_token_accuracy": 0.1443696789443493, |
| "num_tokens": 4028355.0, |
| "step": 2265 |
| }, |
| { |
| "entropy": 6.152818250656128, |
| "epoch": 0.1167605380243294, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0003288988166094324, |
| "loss": 5.8444, |
| "mean_token_accuracy": 0.13612361401319503, |
| "num_tokens": 4037145.0, |
| "step": 2270 |
| }, |
| { |
| "entropy": 6.142724227905274, |
| "epoch": 0.1170177198261451, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00032775428729042656, |
| "loss": 5.8171, |
| "mean_token_accuracy": 0.1471778340637684, |
| "num_tokens": 4046230.0, |
| "step": 2275 |
| }, |
| { |
| "entropy": 6.125968647003174, |
| "epoch": 0.11727490162796081, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.000326608311685986, |
| "loss": 5.8729, |
| "mean_token_accuracy": 0.1469054862856865, |
| "num_tokens": 4055467.0, |
| "step": 2280 |
| }, |
| { |
| "entropy": 6.100337886810303, |
| "epoch": 0.11753208342977652, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0003254609212136108, |
| "loss": 5.8141, |
| "mean_token_accuracy": 0.13736606016755104, |
| "num_tokens": 4063828.0, |
| "step": 2285 |
| }, |
| { |
| "entropy": 6.159852075576782, |
| "epoch": 0.11778926523159221, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00032431214732959036, |
| "loss": 5.902, |
| "mean_token_accuracy": 0.14734955057501792, |
| "num_tokens": 4072865.0, |
| "step": 2290 |
| }, |
| { |
| "entropy": 6.191168689727784, |
| "epoch": 0.11804644703340791, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.000323162021528141, |
| "loss": 5.8601, |
| "mean_token_accuracy": 0.13956545367836953, |
| "num_tokens": 4081235.0, |
| "step": 2295 |
| }, |
| { |
| "entropy": 6.155593776702881, |
| "epoch": 0.11830362883522362, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00032201057534054264, |
| "loss": 5.8385, |
| "mean_token_accuracy": 0.14236045479774476, |
| "num_tokens": 4090247.0, |
| "step": 2300 |
| }, |
| { |
| "entropy": 6.152824115753174, |
| "epoch": 0.11856081063703933, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.00032085784033427414, |
| "loss": 5.852, |
| "mean_token_accuracy": 0.15017105489969254, |
| "num_tokens": 4098606.0, |
| "step": 2305 |
| }, |
| { |
| "entropy": 6.128818655014038, |
| "epoch": 0.11881799243885503, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0003197038481121478, |
| "loss": 5.7669, |
| "mean_token_accuracy": 0.15097088515758514, |
| "num_tokens": 4107481.0, |
| "step": 2310 |
| }, |
| { |
| "entropy": 6.099108076095581, |
| "epoch": 0.11907517424067073, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.0003185486303114436, |
| "loss": 5.7593, |
| "mean_token_accuracy": 0.14285657182335854, |
| "num_tokens": 4116037.0, |
| "step": 2315 |
| }, |
| { |
| "entropy": 6.12216420173645, |
| "epoch": 0.11933235604248643, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0003173922186030409, |
| "loss": 5.7993, |
| "mean_token_accuracy": 0.14858456403017045, |
| "num_tokens": 4124682.0, |
| "step": 2320 |
| }, |
| { |
| "entropy": 6.0839282989501955, |
| "epoch": 0.11958953784430214, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.000316234644690551, |
| "loss": 5.8346, |
| "mean_token_accuracy": 0.1418820232152939, |
| "num_tokens": 4133612.0, |
| "step": 2325 |
| }, |
| { |
| "entropy": 6.101235389709473, |
| "epoch": 0.11984671964611784, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0003150759403094473, |
| "loss": 5.7475, |
| "mean_token_accuracy": 0.1433684967458248, |
| "num_tokens": 4142775.0, |
| "step": 2330 |
| }, |
| { |
| "entropy": 6.110289812088013, |
| "epoch": 0.12010390144793355, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00031391613722619587, |
| "loss": 5.7719, |
| "mean_token_accuracy": 0.14431484937667846, |
| "num_tokens": 4151873.0, |
| "step": 2335 |
| }, |
| { |
| "entropy": 6.161650466918945, |
| "epoch": 0.12036108324974924, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000312755267237384, |
| "loss": 5.9519, |
| "mean_token_accuracy": 0.13633776605129241, |
| "num_tokens": 4161470.0, |
| "step": 2340 |
| }, |
| { |
| "entropy": 6.173916959762574, |
| "epoch": 0.12061826505156495, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0003115933621688488, |
| "loss": 5.8239, |
| "mean_token_accuracy": 0.15275202244520186, |
| "num_tokens": 4169664.0, |
| "step": 2345 |
| }, |
| { |
| "entropy": 6.123827505111694, |
| "epoch": 0.12087544685338066, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00031043045387480487, |
| "loss": 5.964, |
| "mean_token_accuracy": 0.13960720747709274, |
| "num_tokens": 4178397.0, |
| "step": 2350 |
| }, |
| { |
| "entropy": 6.191739654541015, |
| "epoch": 0.12113262865519636, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0003092665742369703, |
| "loss": 5.896, |
| "mean_token_accuracy": 0.14157116487622262, |
| "num_tokens": 4187551.0, |
| "step": 2355 |
| }, |
| { |
| "entropy": 6.15434422492981, |
| "epoch": 0.12138981045701207, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00030810175516369343, |
| "loss": 5.818, |
| "mean_token_accuracy": 0.13805030509829522, |
| "num_tokens": 4196697.0, |
| "step": 2360 |
| }, |
| { |
| "entropy": 6.1531494617462155, |
| "epoch": 0.12164699225882776, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0003069360285890775, |
| "loss": 5.8564, |
| "mean_token_accuracy": 0.1423615410923958, |
| "num_tokens": 4205530.0, |
| "step": 2365 |
| }, |
| { |
| "entropy": 6.09589467048645, |
| "epoch": 0.12190417406064347, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00030576942647210547, |
| "loss": 5.8047, |
| "mean_token_accuracy": 0.1489998519420624, |
| "num_tokens": 4214564.0, |
| "step": 2370 |
| }, |
| { |
| "entropy": 6.1903626918792725, |
| "epoch": 0.12216135586245917, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00030460198079576355, |
| "loss": 5.9357, |
| "mean_token_accuracy": 0.13416276052594184, |
| "num_tokens": 4223957.0, |
| "step": 2375 |
| }, |
| { |
| "entropy": 6.0572864532470705, |
| "epoch": 0.12241853766427488, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0003034337235661648, |
| "loss": 5.7472, |
| "mean_token_accuracy": 0.1455870173871517, |
| "num_tokens": 4233105.0, |
| "step": 2380 |
| }, |
| { |
| "entropy": 6.176725435256958, |
| "epoch": 0.12267571946609059, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0003022646868116714, |
| "loss": 5.8695, |
| "mean_token_accuracy": 0.14357127174735068, |
| "num_tokens": 4242472.0, |
| "step": 2385 |
| }, |
| { |
| "entropy": 6.1465983390808105, |
| "epoch": 0.12293290126790628, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.0003010949025820163, |
| "loss": 5.8276, |
| "mean_token_accuracy": 0.14387768656015396, |
| "num_tokens": 4251363.0, |
| "step": 2390 |
| }, |
| { |
| "entropy": 6.032785367965698, |
| "epoch": 0.12319008306972198, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0002999244029474252, |
| "loss": 5.7531, |
| "mean_token_accuracy": 0.14737599790096284, |
| "num_tokens": 4260733.0, |
| "step": 2395 |
| }, |
| { |
| "entropy": 6.063091135025024, |
| "epoch": 0.12344726487153769, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00029875321999773684, |
| "loss": 5.8539, |
| "mean_token_accuracy": 0.14762932285666466, |
| "num_tokens": 4269455.0, |
| "step": 2400 |
| }, |
| { |
| "entropy": 6.0816483974456785, |
| "epoch": 0.1237044466733534, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00029758138584152333, |
| "loss": 5.7568, |
| "mean_token_accuracy": 0.15133200883865355, |
| "num_tokens": 4278332.0, |
| "step": 2405 |
| }, |
| { |
| "entropy": 6.196329832077026, |
| "epoch": 0.1239616284751691, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0002964089326052102, |
| "loss": 5.8745, |
| "mean_token_accuracy": 0.1448479786515236, |
| "num_tokens": 4287781.0, |
| "step": 2410 |
| }, |
| { |
| "entropy": 6.160340070724487, |
| "epoch": 0.1242188102769848, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0002952358924321949, |
| "loss": 5.7965, |
| "mean_token_accuracy": 0.14277244806289674, |
| "num_tokens": 4297171.0, |
| "step": 2415 |
| }, |
| { |
| "entropy": 6.039106607437134, |
| "epoch": 0.1244759920788005, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00029406229748196657, |
| "loss": 5.788, |
| "mean_token_accuracy": 0.14443129375576974, |
| "num_tokens": 4305473.0, |
| "step": 2420 |
| }, |
| { |
| "entropy": 6.137777709960938, |
| "epoch": 0.12473317388061621, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0002928881799292235, |
| "loss": 5.8192, |
| "mean_token_accuracy": 0.14160926043987274, |
| "num_tokens": 4314003.0, |
| "step": 2425 |
| }, |
| { |
| "entropy": 6.105625486373901, |
| "epoch": 0.12499035568243191, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00029171357196299154, |
| "loss": 5.7514, |
| "mean_token_accuracy": 0.14833177328109742, |
| "num_tokens": 4322744.0, |
| "step": 2430 |
| }, |
| { |
| "entropy": 6.062592554092407, |
| "epoch": 0.1252475374842476, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0002905385057857414, |
| "loss": 5.8066, |
| "mean_token_accuracy": 0.14402533546090127, |
| "num_tokens": 4331303.0, |
| "step": 2435 |
| }, |
| { |
| "entropy": 6.111597061157227, |
| "epoch": 0.12550471928606333, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0002893630136125058, |
| "loss": 5.728, |
| "mean_token_accuracy": 0.15074336379766465, |
| "num_tokens": 4339871.0, |
| "step": 2440 |
| }, |
| { |
| "entropy": 6.137169075012207, |
| "epoch": 0.12576190108787902, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.0002881871276699967, |
| "loss": 5.7845, |
| "mean_token_accuracy": 0.14363497421145438, |
| "num_tokens": 4348638.0, |
| "step": 2445 |
| }, |
| { |
| "entropy": 6.01448884010315, |
| "epoch": 0.12601908288969474, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00028701088019572114, |
| "loss": 5.709, |
| "mean_token_accuracy": 0.14238154217600824, |
| "num_tokens": 4358040.0, |
| "step": 2450 |
| }, |
| { |
| "entropy": 6.151875448226929, |
| "epoch": 0.12627626469151043, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002858343034370977, |
| "loss": 5.8973, |
| "mean_token_accuracy": 0.1396283470094204, |
| "num_tokens": 4366965.0, |
| "step": 2455 |
| }, |
| { |
| "entropy": 6.087133121490479, |
| "epoch": 0.12653344649332612, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00028465742965057267, |
| "loss": 5.6815, |
| "mean_token_accuracy": 0.14499414041638375, |
| "num_tokens": 4375609.0, |
| "step": 2460 |
| }, |
| { |
| "entropy": 6.088481092453003, |
| "epoch": 0.12679062829514184, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00028348029110073533, |
| "loss": 5.7926, |
| "mean_token_accuracy": 0.14089812636375426, |
| "num_tokens": 4384520.0, |
| "step": 2465 |
| }, |
| { |
| "entropy": 6.167114162445069, |
| "epoch": 0.12704781009695754, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00028230292005943365, |
| "loss": 5.8324, |
| "mean_token_accuracy": 0.14488873034715652, |
| "num_tokens": 4394558.0, |
| "step": 2470 |
| }, |
| { |
| "entropy": 6.037402009963989, |
| "epoch": 0.12730499189877326, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00028112534880488945, |
| "loss": 5.6738, |
| "mean_token_accuracy": 0.15287157893180847, |
| "num_tokens": 4402484.0, |
| "step": 2475 |
| }, |
| { |
| "entropy": 5.993755102157593, |
| "epoch": 0.12756217370058895, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0002799476096208137, |
| "loss": 5.8099, |
| "mean_token_accuracy": 0.1522637389600277, |
| "num_tokens": 4411713.0, |
| "step": 2480 |
| }, |
| { |
| "entropy": 6.067369174957276, |
| "epoch": 0.12781935550240464, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00027876973479552087, |
| "loss": 5.7044, |
| "mean_token_accuracy": 0.14507870823144914, |
| "num_tokens": 4420980.0, |
| "step": 2485 |
| }, |
| { |
| "entropy": 6.151381731033325, |
| "epoch": 0.12807653730422036, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00027759175662104424, |
| "loss": 5.7618, |
| "mean_token_accuracy": 0.15688059180974961, |
| "num_tokens": 4429686.0, |
| "step": 2490 |
| }, |
| { |
| "entropy": 6.101734590530396, |
| "epoch": 0.12833371910603605, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0002764137073922508, |
| "loss": 5.767, |
| "mean_token_accuracy": 0.15205710679292678, |
| "num_tokens": 4437761.0, |
| "step": 2495 |
| }, |
| { |
| "entropy": 6.08014030456543, |
| "epoch": 0.12859090090785177, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00027523561940595505, |
| "loss": 5.7794, |
| "mean_token_accuracy": 0.14667339026927947, |
| "num_tokens": 4447035.0, |
| "step": 2500 |
| }, |
| { |
| "entropy": 6.087471866607666, |
| "epoch": 0.12884808270966747, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0002740575249600342, |
| "loss": 5.8589, |
| "mean_token_accuracy": 0.14450928941369057, |
| "num_tokens": 4456666.0, |
| "step": 2505 |
| }, |
| { |
| "entropy": 6.173044443130493, |
| "epoch": 0.12910526451148316, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00027287945635254263, |
| "loss": 5.8582, |
| "mean_token_accuracy": 0.14389320015907286, |
| "num_tokens": 4465310.0, |
| "step": 2510 |
| }, |
| { |
| "entropy": 6.153860759735108, |
| "epoch": 0.12936244631329888, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00027170144588082635, |
| "loss": 5.8622, |
| "mean_token_accuracy": 0.14058634638786316, |
| "num_tokens": 4474904.0, |
| "step": 2515 |
| }, |
| { |
| "entropy": 6.084224796295166, |
| "epoch": 0.12961962811511457, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00027052352584063763, |
| "loss": 5.7497, |
| "mean_token_accuracy": 0.14958999156951905, |
| "num_tokens": 4484126.0, |
| "step": 2520 |
| }, |
| { |
| "entropy": 6.160521697998047, |
| "epoch": 0.1298768099169303, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00026934572852524907, |
| "loss": 5.8709, |
| "mean_token_accuracy": 0.15014255195856094, |
| "num_tokens": 4493517.0, |
| "step": 2525 |
| }, |
| { |
| "entropy": 6.117522954940796, |
| "epoch": 0.13013399171874598, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00026816808622456937, |
| "loss": 5.8084, |
| "mean_token_accuracy": 0.15210048705339432, |
| "num_tokens": 4502287.0, |
| "step": 2530 |
| }, |
| { |
| "entropy": 6.152761363983155, |
| "epoch": 0.13039117352056168, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0002669906312242569, |
| "loss": 5.8285, |
| "mean_token_accuracy": 0.1432643160223961, |
| "num_tokens": 4511725.0, |
| "step": 2535 |
| }, |
| { |
| "entropy": 6.1779975414276125, |
| "epoch": 0.1306483553223774, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00026581339580483525, |
| "loss": 5.9058, |
| "mean_token_accuracy": 0.13740246295928954, |
| "num_tokens": 4521034.0, |
| "step": 2540 |
| }, |
| { |
| "entropy": 6.1182639598846436, |
| "epoch": 0.1309055371241931, |
| "grad_norm": 0.9765625, |
| "learning_rate": 0.0002646364122408082, |
| "loss": 5.7954, |
| "mean_token_accuracy": 0.1469892755150795, |
| "num_tokens": 4530000.0, |
| "step": 2545 |
| }, |
| { |
| "entropy": 6.127992963790893, |
| "epoch": 0.1311627189260088, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0002634597127997749, |
| "loss": 5.8107, |
| "mean_token_accuracy": 0.14748405069112777, |
| "num_tokens": 4539261.0, |
| "step": 2550 |
| }, |
| { |
| "entropy": 6.126268100738526, |
| "epoch": 0.1314199007278245, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.0002622833297415445, |
| "loss": 5.787, |
| "mean_token_accuracy": 0.14389605522155763, |
| "num_tokens": 4548136.0, |
| "step": 2555 |
| }, |
| { |
| "entropy": 6.03954815864563, |
| "epoch": 0.1316770825296402, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0002611072953172531, |
| "loss": 5.6491, |
| "mean_token_accuracy": 0.1580216631293297, |
| "num_tokens": 4556821.0, |
| "step": 2560 |
| }, |
| { |
| "entropy": 6.08048415184021, |
| "epoch": 0.1319342643314559, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00025993164176847845, |
| "loss": 5.8445, |
| "mean_token_accuracy": 0.14462381452322007, |
| "num_tokens": 4566212.0, |
| "step": 2565 |
| }, |
| { |
| "entropy": 6.159459590911865, |
| "epoch": 0.1321914461332716, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.0002587564013263564, |
| "loss": 5.7714, |
| "mean_token_accuracy": 0.15497603118419648, |
| "num_tokens": 4574768.0, |
| "step": 2570 |
| }, |
| { |
| "entropy": 6.093240785598755, |
| "epoch": 0.13244862793508733, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.0002575816062106974, |
| "loss": 5.7048, |
| "mean_token_accuracy": 0.14752707481384278, |
| "num_tokens": 4583537.0, |
| "step": 2575 |
| }, |
| { |
| "entropy": 6.0544486999511715, |
| "epoch": 0.13270580973690302, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00025640728862910293, |
| "loss": 5.7222, |
| "mean_token_accuracy": 0.14990747570991517, |
| "num_tokens": 4591393.0, |
| "step": 2580 |
| }, |
| { |
| "entropy": 6.122651529312134, |
| "epoch": 0.1329629915387187, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00025523348077608285, |
| "loss": 5.8978, |
| "mean_token_accuracy": 0.14079949036240577, |
| "num_tokens": 4600629.0, |
| "step": 2585 |
| }, |
| { |
| "entropy": 6.104698419570923, |
| "epoch": 0.13322017334053443, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00025406021483217225, |
| "loss": 5.8008, |
| "mean_token_accuracy": 0.14822616279125214, |
| "num_tokens": 4610124.0, |
| "step": 2590 |
| }, |
| { |
| "entropy": 6.177899312973023, |
| "epoch": 0.13347735514235012, |
| "grad_norm": 0.96484375, |
| "learning_rate": 0.00025288752296304963, |
| "loss": 5.8059, |
| "mean_token_accuracy": 0.14366786256432534, |
| "num_tokens": 4619540.0, |
| "step": 2595 |
| }, |
| { |
| "entropy": 6.1752338886260985, |
| "epoch": 0.13373453694416584, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.000251715437318655, |
| "loss": 5.8555, |
| "mean_token_accuracy": 0.14017964005470276, |
| "num_tokens": 4628416.0, |
| "step": 2600 |
| }, |
| { |
| "entropy": 6.122747802734375, |
| "epoch": 0.13399171874598154, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002505439900323084, |
| "loss": 5.7838, |
| "mean_token_accuracy": 0.14850689172744752, |
| "num_tokens": 4636960.0, |
| "step": 2605 |
| }, |
| { |
| "entropy": 6.063931083679199, |
| "epoch": 0.13424890054779723, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00024937321321982894, |
| "loss": 5.7311, |
| "mean_token_accuracy": 0.1498788923025131, |
| "num_tokens": 4645078.0, |
| "step": 2610 |
| }, |
| { |
| "entropy": 6.055330562591553, |
| "epoch": 0.13450608234961295, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00024820313897865433, |
| "loss": 5.763, |
| "mean_token_accuracy": 0.1456884853541851, |
| "num_tokens": 4653493.0, |
| "step": 2615 |
| }, |
| { |
| "entropy": 6.108834505081177, |
| "epoch": 0.13476326415142864, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00024703379938696105, |
| "loss": 5.7954, |
| "mean_token_accuracy": 0.1481550857424736, |
| "num_tokens": 4662399.0, |
| "step": 2620 |
| }, |
| { |
| "entropy": 6.09889440536499, |
| "epoch": 0.13502044595324436, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00024586522650278447, |
| "loss": 5.7285, |
| "mean_token_accuracy": 0.15264491140842437, |
| "num_tokens": 4670373.0, |
| "step": 2625 |
| }, |
| { |
| "entropy": 6.04096417427063, |
| "epoch": 0.13527762775506005, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00024469745236314064, |
| "loss": 5.7215, |
| "mean_token_accuracy": 0.15325826555490493, |
| "num_tokens": 4679569.0, |
| "step": 2630 |
| }, |
| { |
| "entropy": 6.129749059677124, |
| "epoch": 0.13553480955687575, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00024353050898314767, |
| "loss": 5.6703, |
| "mean_token_accuracy": 0.15401824712753295, |
| "num_tokens": 4687619.0, |
| "step": 2635 |
| }, |
| { |
| "entropy": 6.116965055465698, |
| "epoch": 0.13579199135869147, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00024236442835514743, |
| "loss": 5.7883, |
| "mean_token_accuracy": 0.14248116537928582, |
| "num_tokens": 4697249.0, |
| "step": 2640 |
| }, |
| { |
| "entropy": 5.9908223152160645, |
| "epoch": 0.13604917316050716, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.00024119924244782965, |
| "loss": 5.7243, |
| "mean_token_accuracy": 0.14905789047479628, |
| "num_tokens": 4706385.0, |
| "step": 2645 |
| }, |
| { |
| "entropy": 6.07071475982666, |
| "epoch": 0.13630635496232288, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00024003498320535462, |
| "loss": 5.6449, |
| "mean_token_accuracy": 0.15249079763889312, |
| "num_tokens": 4715017.0, |
| "step": 2650 |
| }, |
| { |
| "entropy": 6.115285348892212, |
| "epoch": 0.13656353676413857, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00023887168254647727, |
| "loss": 5.7935, |
| "mean_token_accuracy": 0.14969302117824554, |
| "num_tokens": 4723671.0, |
| "step": 2655 |
| }, |
| { |
| "entropy": 6.125974464416504, |
| "epoch": 0.13682071856595426, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00023770937236367308, |
| "loss": 5.707, |
| "mean_token_accuracy": 0.14687229990959166, |
| "num_tokens": 4732789.0, |
| "step": 2660 |
| }, |
| { |
| "entropy": 6.072940444946289, |
| "epoch": 0.13707790036776998, |
| "grad_norm": 1.1796875, |
| "learning_rate": 0.00023654808452226278, |
| "loss": 5.8, |
| "mean_token_accuracy": 0.1471541166305542, |
| "num_tokens": 4741120.0, |
| "step": 2665 |
| }, |
| { |
| "entropy": 6.088577651977539, |
| "epoch": 0.13733508216958568, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00023538785085953912, |
| "loss": 5.7295, |
| "mean_token_accuracy": 0.1562255248427391, |
| "num_tokens": 4749562.0, |
| "step": 2670 |
| }, |
| { |
| "entropy": 6.067140245437622, |
| "epoch": 0.1375922639714014, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00023422870318389404, |
| "loss": 5.6582, |
| "mean_token_accuracy": 0.15040153563022612, |
| "num_tokens": 4758851.0, |
| "step": 2675 |
| }, |
| { |
| "entropy": 6.042630386352539, |
| "epoch": 0.1378494457732171, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.0002330706732739468, |
| "loss": 5.8031, |
| "mean_token_accuracy": 0.14683737456798554, |
| "num_tokens": 4768002.0, |
| "step": 2680 |
| }, |
| { |
| "entropy": 6.123049592971801, |
| "epoch": 0.13810662757503278, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.00023191379287767211, |
| "loss": 5.7932, |
| "mean_token_accuracy": 0.14382962211966516, |
| "num_tokens": 4777398.0, |
| "step": 2685 |
| }, |
| { |
| "entropy": 6.05987401008606, |
| "epoch": 0.1383638093768485, |
| "grad_norm": 0.99609375, |
| "learning_rate": 0.0002307580937115305, |
| "loss": 5.6786, |
| "mean_token_accuracy": 0.149133113771677, |
| "num_tokens": 4786670.0, |
| "step": 2690 |
| }, |
| { |
| "entropy": 6.1101315975189205, |
| "epoch": 0.1386209911786642, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00022960360745959846, |
| "loss": 5.7711, |
| "mean_token_accuracy": 0.14630099162459373, |
| "num_tokens": 4796029.0, |
| "step": 2695 |
| }, |
| { |
| "entropy": 6.063817548751831, |
| "epoch": 0.1388781729804799, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00022845036577269972, |
| "loss": 5.7533, |
| "mean_token_accuracy": 0.15278576463460922, |
| "num_tokens": 4805347.0, |
| "step": 2700 |
| }, |
| { |
| "entropy": 6.068688106536865, |
| "epoch": 0.1391353547822956, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00022729840026753777, |
| "loss": 5.7372, |
| "mean_token_accuracy": 0.1488709568977356, |
| "num_tokens": 4813812.0, |
| "step": 2705 |
| }, |
| { |
| "entropy": 6.100601530075073, |
| "epoch": 0.1393925365841113, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0002261477425258287, |
| "loss": 5.8707, |
| "mean_token_accuracy": 0.14431559592485427, |
| "num_tokens": 4823065.0, |
| "step": 2710 |
| }, |
| { |
| "entropy": 6.141161584854126, |
| "epoch": 0.13964971838592702, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0002249984240934358, |
| "loss": 5.8177, |
| "mean_token_accuracy": 0.14645303189754486, |
| "num_tokens": 4831593.0, |
| "step": 2715 |
| }, |
| { |
| "entropy": 6.172276401519776, |
| "epoch": 0.1399069001877427, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00022385047647950464, |
| "loss": 5.7571, |
| "mean_token_accuracy": 0.1497072234749794, |
| "num_tokens": 4840361.0, |
| "step": 2720 |
| }, |
| { |
| "entropy": 6.1089259624481205, |
| "epoch": 0.14016408198955843, |
| "grad_norm": 1.0, |
| "learning_rate": 0.0002227039311555986, |
| "loss": 5.7274, |
| "mean_token_accuracy": 0.15788735672831536, |
| "num_tokens": 4848639.0, |
| "step": 2725 |
| }, |
| { |
| "entropy": 6.185072565078736, |
| "epoch": 0.14042126379137412, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0002215588195548372, |
| "loss": 5.8421, |
| "mean_token_accuracy": 0.14097240045666695, |
| "num_tokens": 4859096.0, |
| "step": 2730 |
| }, |
| { |
| "entropy": 6.087200117111206, |
| "epoch": 0.14067844559318982, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00022041517307103337, |
| "loss": 5.7201, |
| "mean_token_accuracy": 0.15250880122184754, |
| "num_tokens": 4868491.0, |
| "step": 2735 |
| }, |
| { |
| "entropy": 5.981367111206055, |
| "epoch": 0.14093562739500554, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0002192730230578331, |
| "loss": 5.6205, |
| "mean_token_accuracy": 0.16045419424772261, |
| "num_tokens": 4877871.0, |
| "step": 2740 |
| }, |
| { |
| "entropy": 6.029149770736694, |
| "epoch": 0.14119280919682123, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0002181324008278559, |
| "loss": 5.7381, |
| "mean_token_accuracy": 0.14955741986632348, |
| "num_tokens": 4886697.0, |
| "step": 2745 |
| }, |
| { |
| "entropy": 6.076590156555175, |
| "epoch": 0.14144999099863695, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00021699333765183655, |
| "loss": 5.7129, |
| "mean_token_accuracy": 0.15347884297370912, |
| "num_tokens": 4895540.0, |
| "step": 2750 |
| }, |
| { |
| "entropy": 6.142263317108155, |
| "epoch": 0.14170717280045264, |
| "grad_norm": 1.203125, |
| "learning_rate": 0.0002158558647577673, |
| "loss": 5.8009, |
| "mean_token_accuracy": 0.14876136928796768, |
| "num_tokens": 4904570.0, |
| "step": 2755 |
| }, |
| { |
| "entropy": 6.051943826675415, |
| "epoch": 0.14196435460226833, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00021472001333004215, |
| "loss": 5.7279, |
| "mean_token_accuracy": 0.15683121085166932, |
| "num_tokens": 4913647.0, |
| "step": 2760 |
| }, |
| { |
| "entropy": 6.0783342838287355, |
| "epoch": 0.14222153640408405, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00021358581450860186, |
| "loss": 5.7146, |
| "mean_token_accuracy": 0.14434474259614943, |
| "num_tokens": 4923415.0, |
| "step": 2765 |
| }, |
| { |
| "entropy": 6.092839479446411, |
| "epoch": 0.14247871820589975, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.0002124532993880799, |
| "loss": 5.7974, |
| "mean_token_accuracy": 0.1496799871325493, |
| "num_tokens": 4932759.0, |
| "step": 2770 |
| }, |
| { |
| "entropy": 6.189432048797608, |
| "epoch": 0.14273590000771547, |
| "grad_norm": 0.9921875, |
| "learning_rate": 0.00021132249901695044, |
| "loss": 5.8992, |
| "mean_token_accuracy": 0.14657394140958785, |
| "num_tokens": 4942020.0, |
| "step": 2775 |
| }, |
| { |
| "entropy": 6.1244882106781, |
| "epoch": 0.14299308180953116, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00021019344439667705, |
| "loss": 5.741, |
| "mean_token_accuracy": 0.15104521065950394, |
| "num_tokens": 4951565.0, |
| "step": 2780 |
| }, |
| { |
| "entropy": 6.043192148208618, |
| "epoch": 0.14325026361134685, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00020906616648086213, |
| "loss": 5.7554, |
| "mean_token_accuracy": 0.1443242684006691, |
| "num_tokens": 4960900.0, |
| "step": 2785 |
| }, |
| { |
| "entropy": 6.105488014221192, |
| "epoch": 0.14350744541316257, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00020794069617439942, |
| "loss": 5.7922, |
| "mean_token_accuracy": 0.14633723646402358, |
| "num_tokens": 4970015.0, |
| "step": 2790 |
| }, |
| { |
| "entropy": 6.153280210494995, |
| "epoch": 0.14376462721497826, |
| "grad_norm": 1.2109375, |
| "learning_rate": 0.00020681706433262593, |
| "loss": 5.6592, |
| "mean_token_accuracy": 0.1489225521683693, |
| "num_tokens": 4978581.0, |
| "step": 2795 |
| }, |
| { |
| "entropy": 6.054395151138306, |
| "epoch": 0.14402180901679398, |
| "grad_norm": 0.95703125, |
| "learning_rate": 0.00020569530176047602, |
| "loss": 5.7687, |
| "mean_token_accuracy": 0.1470100998878479, |
| "num_tokens": 4987991.0, |
| "step": 2800 |
| }, |
| { |
| "entropy": 5.986433506011963, |
| "epoch": 0.14427899081860968, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0002045754392116374, |
| "loss": 5.6326, |
| "mean_token_accuracy": 0.15278421938419343, |
| "num_tokens": 4996381.0, |
| "step": 2805 |
| }, |
| { |
| "entropy": 6.066991376876831, |
| "epoch": 0.14453617262042537, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00020345750738770757, |
| "loss": 5.7466, |
| "mean_token_accuracy": 0.15142902210354806, |
| "num_tokens": 5005038.0, |
| "step": 2810 |
| }, |
| { |
| "entropy": 6.174243927001953, |
| "epoch": 0.1447933544222411, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00020234153693735214, |
| "loss": 5.8406, |
| "mean_token_accuracy": 0.14394895732402802, |
| "num_tokens": 5014215.0, |
| "step": 2815 |
| }, |
| { |
| "entropy": 6.053258419036865, |
| "epoch": 0.14505053622405678, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0002012275584554647, |
| "loss": 5.7079, |
| "mean_token_accuracy": 0.14920954704284667, |
| "num_tokens": 5023068.0, |
| "step": 2820 |
| }, |
| { |
| "entropy": 6.021562004089356, |
| "epoch": 0.1453077180258725, |
| "grad_norm": 1.21875, |
| "learning_rate": 0.00020011560248232803, |
| "loss": 5.5973, |
| "mean_token_accuracy": 0.1581226259469986, |
| "num_tokens": 5032835.0, |
| "step": 2825 |
| }, |
| { |
| "entropy": 6.067530250549316, |
| "epoch": 0.1455648998276882, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.00019900569950277692, |
| "loss": 5.6839, |
| "mean_token_accuracy": 0.15836838483810425, |
| "num_tokens": 5041513.0, |
| "step": 2830 |
| }, |
| { |
| "entropy": 6.075325965881348, |
| "epoch": 0.14582208162950389, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00019789787994536228, |
| "loss": 5.7247, |
| "mean_token_accuracy": 0.14836459010839462, |
| "num_tokens": 5050226.0, |
| "step": 2835 |
| }, |
| { |
| "entropy": 6.085581350326538, |
| "epoch": 0.1460792634313196, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00019679217418151667, |
| "loss": 5.7324, |
| "mean_token_accuracy": 0.14982028156518937, |
| "num_tokens": 5059263.0, |
| "step": 2840 |
| }, |
| { |
| "entropy": 6.006525611877441, |
| "epoch": 0.1463364452331353, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00019568861252472236, |
| "loss": 5.6467, |
| "mean_token_accuracy": 0.15969533771276473, |
| "num_tokens": 5068035.0, |
| "step": 2845 |
| }, |
| { |
| "entropy": 6.149723052978516, |
| "epoch": 0.14659362703495102, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00019458722522967952, |
| "loss": 5.7821, |
| "mean_token_accuracy": 0.14641618430614473, |
| "num_tokens": 5077007.0, |
| "step": 2850 |
| }, |
| { |
| "entropy": 6.12144365310669, |
| "epoch": 0.1468508088367667, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00019348804249147723, |
| "loss": 5.7168, |
| "mean_token_accuracy": 0.1498103730380535, |
| "num_tokens": 5085428.0, |
| "step": 2855 |
| }, |
| { |
| "entropy": 6.108307647705078, |
| "epoch": 0.1471079906385824, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001923910944447655, |
| "loss": 5.7682, |
| "mean_token_accuracy": 0.15273086205124856, |
| "num_tokens": 5093972.0, |
| "step": 2860 |
| }, |
| { |
| "entropy": 6.033883333206177, |
| "epoch": 0.14736517244039812, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00019129641116292928, |
| "loss": 5.7242, |
| "mean_token_accuracy": 0.1502732053399086, |
| "num_tokens": 5103254.0, |
| "step": 2865 |
| }, |
| { |
| "entropy": 6.052216100692749, |
| "epoch": 0.14762235424221382, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00019020402265726343, |
| "loss": 5.6929, |
| "mean_token_accuracy": 0.15873962938785552, |
| "num_tokens": 5112379.0, |
| "step": 2870 |
| }, |
| { |
| "entropy": 6.069576168060303, |
| "epoch": 0.14787953604402954, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0001891139588761509, |
| "loss": 5.6962, |
| "mean_token_accuracy": 0.14680043384432792, |
| "num_tokens": 5121574.0, |
| "step": 2875 |
| }, |
| { |
| "entropy": 6.066564130783081, |
| "epoch": 0.14813671784584523, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00018802624970424076, |
| "loss": 5.6867, |
| "mean_token_accuracy": 0.15274660885334015, |
| "num_tokens": 5129987.0, |
| "step": 2880 |
| }, |
| { |
| "entropy": 6.07275710105896, |
| "epoch": 0.14839389964766092, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00018694092496162945, |
| "loss": 5.7249, |
| "mean_token_accuracy": 0.1485137440264225, |
| "num_tokens": 5139693.0, |
| "step": 2885 |
| }, |
| { |
| "entropy": 6.068764925003052, |
| "epoch": 0.14865108144947664, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00018585801440304306, |
| "loss": 5.7089, |
| "mean_token_accuracy": 0.1488506242632866, |
| "num_tokens": 5148970.0, |
| "step": 2890 |
| }, |
| { |
| "entropy": 6.158687973022461, |
| "epoch": 0.14890826325129233, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00018477754771702165, |
| "loss": 5.7683, |
| "mean_token_accuracy": 0.14795275628566742, |
| "num_tokens": 5158074.0, |
| "step": 2895 |
| }, |
| { |
| "entropy": 6.201472425460816, |
| "epoch": 0.14916544505310805, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00018369955452510506, |
| "loss": 5.844, |
| "mean_token_accuracy": 0.1411036416888237, |
| "num_tokens": 5167232.0, |
| "step": 2900 |
| }, |
| { |
| "entropy": 6.044641494750977, |
| "epoch": 0.14942262685492375, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.0001826240643810212, |
| "loss": 5.7595, |
| "mean_token_accuracy": 0.14772264882922173, |
| "num_tokens": 5175937.0, |
| "step": 2905 |
| }, |
| { |
| "entropy": 6.099119091033936, |
| "epoch": 0.14967980865673944, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0001815511067698758, |
| "loss": 5.6969, |
| "mean_token_accuracy": 0.1572198435664177, |
| "num_tokens": 5185160.0, |
| "step": 2910 |
| }, |
| { |
| "entropy": 6.082510089874267, |
| "epoch": 0.14993699045855516, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0001804807111073436, |
| "loss": 5.6964, |
| "mean_token_accuracy": 0.15368552058935164, |
| "num_tokens": 5194041.0, |
| "step": 2915 |
| }, |
| { |
| "entropy": 6.054811429977417, |
| "epoch": 0.15019417226037085, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.0001794129067388625, |
| "loss": 5.7748, |
| "mean_token_accuracy": 0.1470634326338768, |
| "num_tokens": 5202451.0, |
| "step": 2920 |
| }, |
| { |
| "entropy": 6.085486936569214, |
| "epoch": 0.15045135406218657, |
| "grad_norm": 1.015625, |
| "learning_rate": 0.00017834772293882868, |
| "loss": 5.7482, |
| "mean_token_accuracy": 0.148094991594553, |
| "num_tokens": 5211619.0, |
| "step": 2925 |
| }, |
| { |
| "entropy": 6.115034484863282, |
| "epoch": 0.15070853586400226, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.000177285188909794, |
| "loss": 5.7095, |
| "mean_token_accuracy": 0.15634109675884247, |
| "num_tokens": 5220884.0, |
| "step": 2930 |
| }, |
| { |
| "entropy": 6.133270692825318, |
| "epoch": 0.15096571766581796, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.0001762253337816656, |
| "loss": 5.7206, |
| "mean_token_accuracy": 0.1495368480682373, |
| "num_tokens": 5230087.0, |
| "step": 2935 |
| }, |
| { |
| "entropy": 6.04415192604065, |
| "epoch": 0.15122289946763368, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00017516818661090738, |
| "loss": 5.6859, |
| "mean_token_accuracy": 0.15155497640371324, |
| "num_tokens": 5239745.0, |
| "step": 2940 |
| }, |
| { |
| "entropy": 6.018107271194458, |
| "epoch": 0.15148008126944937, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0001741137763797428, |
| "loss": 5.6319, |
| "mean_token_accuracy": 0.1561276137828827, |
| "num_tokens": 5248474.0, |
| "step": 2945 |
| }, |
| { |
| "entropy": 6.076938199996948, |
| "epoch": 0.1517372630712651, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00017306213199536115, |
| "loss": 5.6324, |
| "mean_token_accuracy": 0.1571225941181183, |
| "num_tokens": 5257874.0, |
| "step": 2950 |
| }, |
| { |
| "entropy": 6.045232534408569, |
| "epoch": 0.15199444487308078, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0001720132822891243, |
| "loss": 5.5987, |
| "mean_token_accuracy": 0.16427121460437774, |
| "num_tokens": 5266863.0, |
| "step": 2955 |
| }, |
| { |
| "entropy": 5.916203927993775, |
| "epoch": 0.15225162667489647, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0001709672560157769, |
| "loss": 5.5982, |
| "mean_token_accuracy": 0.16422740668058394, |
| "num_tokens": 5275488.0, |
| "step": 2960 |
| }, |
| { |
| "entropy": 6.0525675296783445, |
| "epoch": 0.1525088084767122, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.00016992408185265758, |
| "loss": 5.6859, |
| "mean_token_accuracy": 0.1529119446873665, |
| "num_tokens": 5284122.0, |
| "step": 2965 |
| }, |
| { |
| "entropy": 6.080022764205933, |
| "epoch": 0.15276599027852789, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.00016888378839891298, |
| "loss": 5.6777, |
| "mean_token_accuracy": 0.15771500319242476, |
| "num_tokens": 5292142.0, |
| "step": 2970 |
| }, |
| { |
| "entropy": 5.962907218933106, |
| "epoch": 0.1530231720803436, |
| "grad_norm": 1.0078125, |
| "learning_rate": 0.0001678464041747137, |
| "loss": 5.5697, |
| "mean_token_accuracy": 0.16219161450862885, |
| "num_tokens": 5301107.0, |
| "step": 2975 |
| }, |
| { |
| "entropy": 6.023697137832642, |
| "epoch": 0.1532803538821593, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00016681195762047223, |
| "loss": 5.5878, |
| "mean_token_accuracy": 0.15488499104976655, |
| "num_tokens": 5309757.0, |
| "step": 2980 |
| }, |
| { |
| "entropy": 6.115173292160034, |
| "epoch": 0.153537535683975, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.00016578047709606337, |
| "loss": 5.6427, |
| "mean_token_accuracy": 0.15932161509990692, |
| "num_tokens": 5318587.0, |
| "step": 2985 |
| }, |
| { |
| "entropy": 6.061873197555542, |
| "epoch": 0.1537947174857907, |
| "grad_norm": 0.9609375, |
| "learning_rate": 0.00016475199088004678, |
| "loss": 5.7114, |
| "mean_token_accuracy": 0.14534699767827988, |
| "num_tokens": 5328803.0, |
| "step": 2990 |
| }, |
| { |
| "entropy": 6.132055187225342, |
| "epoch": 0.1540518992876064, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00016372652716889163, |
| "loss": 5.724, |
| "mean_token_accuracy": 0.15180520191788674, |
| "num_tokens": 5337671.0, |
| "step": 2995 |
| }, |
| { |
| "entropy": 6.087587594985962, |
| "epoch": 0.15430908108942212, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0001627041140762035, |
| "loss": 5.6851, |
| "mean_token_accuracy": 0.1564175456762314, |
| "num_tokens": 5346840.0, |
| "step": 3000 |
| }, |
| { |
| "entropy": 6.061629104614258, |
| "epoch": 0.15456626289123782, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00016168477963195382, |
| "loss": 5.6917, |
| "mean_token_accuracy": 0.1516722172498703, |
| "num_tokens": 5355657.0, |
| "step": 3005 |
| }, |
| { |
| "entropy": 6.0160637378692625, |
| "epoch": 0.1548234446930535, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.0001606685517817114, |
| "loss": 5.7006, |
| "mean_token_accuracy": 0.15100913494825363, |
| "num_tokens": 5364962.0, |
| "step": 3010 |
| }, |
| { |
| "entropy": 6.009352350234986, |
| "epoch": 0.15508062649486923, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00015965545838587592, |
| "loss": 5.6205, |
| "mean_token_accuracy": 0.15738046616315843, |
| "num_tokens": 5373680.0, |
| "step": 3015 |
| }, |
| { |
| "entropy": 6.092876386642456, |
| "epoch": 0.15533780829668492, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00015864552721891467, |
| "loss": 5.7602, |
| "mean_token_accuracy": 0.15348234474658967, |
| "num_tokens": 5383322.0, |
| "step": 3020 |
| }, |
| { |
| "entropy": 6.1229761123657225, |
| "epoch": 0.15559499009850064, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00015763878596860076, |
| "loss": 5.6947, |
| "mean_token_accuracy": 0.15612949132919313, |
| "num_tokens": 5392094.0, |
| "step": 3025 |
| }, |
| { |
| "entropy": 6.084302663803101, |
| "epoch": 0.15585217190031633, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00015663526223525412, |
| "loss": 5.6446, |
| "mean_token_accuracy": 0.15363571643829346, |
| "num_tokens": 5401080.0, |
| "step": 3030 |
| }, |
| { |
| "entropy": 6.058415412902832, |
| "epoch": 0.15610935370213203, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.0001556349835309848, |
| "loss": 5.7229, |
| "mean_token_accuracy": 0.14779178202152252, |
| "num_tokens": 5410398.0, |
| "step": 3035 |
| }, |
| { |
| "entropy": 6.010592794418335, |
| "epoch": 0.15636653550394775, |
| "grad_norm": 0.984375, |
| "learning_rate": 0.0001546379772789389, |
| "loss": 5.622, |
| "mean_token_accuracy": 0.15021681636571885, |
| "num_tokens": 5419161.0, |
| "step": 3040 |
| }, |
| { |
| "entropy": 6.023690700531006, |
| "epoch": 0.15662371730576344, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00015364427081254622, |
| "loss": 5.663, |
| "mean_token_accuracy": 0.15661261081695557, |
| "num_tokens": 5427830.0, |
| "step": 3045 |
| }, |
| { |
| "entropy": 6.0662956714630125, |
| "epoch": 0.15688089910757916, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00015265389137477165, |
| "loss": 5.5916, |
| "mean_token_accuracy": 0.15561202466487883, |
| "num_tokens": 5436338.0, |
| "step": 3050 |
| }, |
| { |
| "entropy": 6.096805191040039, |
| "epoch": 0.15713808090939485, |
| "grad_norm": 1.1953125, |
| "learning_rate": 0.00015166686611736786, |
| "loss": 5.6729, |
| "mean_token_accuracy": 0.1547914043068886, |
| "num_tokens": 5443874.0, |
| "step": 3055 |
| }, |
| { |
| "entropy": 6.0510979175567625, |
| "epoch": 0.15739526271121054, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00015068322210013064, |
| "loss": 5.7851, |
| "mean_token_accuracy": 0.1516324445605278, |
| "num_tokens": 5453930.0, |
| "step": 3060 |
| }, |
| { |
| "entropy": 6.046182918548584, |
| "epoch": 0.15765244451302626, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.0001497029862901578, |
| "loss": 5.6957, |
| "mean_token_accuracy": 0.1572821095585823, |
| "num_tokens": 5463509.0, |
| "step": 3065 |
| }, |
| { |
| "entropy": 6.074911451339721, |
| "epoch": 0.15790962631484196, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00014872618556110905, |
| "loss": 5.6678, |
| "mean_token_accuracy": 0.1605235144495964, |
| "num_tokens": 5471927.0, |
| "step": 3070 |
| }, |
| { |
| "entropy": 6.096590423583985, |
| "epoch": 0.15816680811665768, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00014775284669246992, |
| "loss": 5.5956, |
| "mean_token_accuracy": 0.15980406403541564, |
| "num_tokens": 5480379.0, |
| "step": 3075 |
| }, |
| { |
| "entropy": 6.082154035568237, |
| "epoch": 0.15842398991847337, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00014678299636881716, |
| "loss": 5.7243, |
| "mean_token_accuracy": 0.1544443905353546, |
| "num_tokens": 5489386.0, |
| "step": 3080 |
| }, |
| { |
| "entropy": 6.0593400478363035, |
| "epoch": 0.15868117172028906, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0001458166611790873, |
| "loss": 5.7404, |
| "mean_token_accuracy": 0.14763626158237458, |
| "num_tokens": 5498772.0, |
| "step": 3085 |
| }, |
| { |
| "entropy": 6.062345695495606, |
| "epoch": 0.15893835352210478, |
| "grad_norm": 0.953125, |
| "learning_rate": 0.00014485386761584773, |
| "loss": 5.6463, |
| "mean_token_accuracy": 0.15483846738934517, |
| "num_tokens": 5508737.0, |
| "step": 3090 |
| }, |
| { |
| "entropy": 6.062005853652954, |
| "epoch": 0.15919553532392047, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00014389464207457042, |
| "loss": 5.7387, |
| "mean_token_accuracy": 0.15153988748788833, |
| "num_tokens": 5518159.0, |
| "step": 3095 |
| }, |
| { |
| "entropy": 6.035994386672973, |
| "epoch": 0.1594527171257362, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00014293901085290795, |
| "loss": 5.5998, |
| "mean_token_accuracy": 0.16290214657783508, |
| "num_tokens": 5527584.0, |
| "step": 3100 |
| }, |
| { |
| "entropy": 6.029916143417358, |
| "epoch": 0.15970989892755189, |
| "grad_norm": 0.94921875, |
| "learning_rate": 0.00014198700014997307, |
| "loss": 5.719, |
| "mean_token_accuracy": 0.15757740736007692, |
| "num_tokens": 5537024.0, |
| "step": 3105 |
| }, |
| { |
| "entropy": 6.079221582412719, |
| "epoch": 0.15996708072936758, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00014103863606562016, |
| "loss": 5.6796, |
| "mean_token_accuracy": 0.1564470648765564, |
| "num_tokens": 5545517.0, |
| "step": 3110 |
| }, |
| { |
| "entropy": 6.1210731029510494, |
| "epoch": 0.1602242625311833, |
| "grad_norm": 1.0703125, |
| "learning_rate": 0.00014009394459972964, |
| "loss": 5.7685, |
| "mean_token_accuracy": 0.1430550329387188, |
| "num_tokens": 5553867.0, |
| "step": 3115 |
| }, |
| { |
| "entropy": 6.084968566894531, |
| "epoch": 0.160481444332999, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00013915295165149513, |
| "loss": 5.6783, |
| "mean_token_accuracy": 0.15583407431840895, |
| "num_tokens": 5563095.0, |
| "step": 3120 |
| }, |
| { |
| "entropy": 6.116517400741577, |
| "epoch": 0.1607386261348147, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00013821568301871384, |
| "loss": 5.7409, |
| "mean_token_accuracy": 0.15116296708583832, |
| "num_tokens": 5572422.0, |
| "step": 3125 |
| }, |
| { |
| "entropy": 6.045165491104126, |
| "epoch": 0.1609958079366304, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00013728216439707862, |
| "loss": 5.6104, |
| "mean_token_accuracy": 0.1608249843120575, |
| "num_tokens": 5580925.0, |
| "step": 3130 |
| }, |
| { |
| "entropy": 6.031289052963257, |
| "epoch": 0.1612529897384461, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00013635242137947419, |
| "loss": 5.6055, |
| "mean_token_accuracy": 0.16040494441986083, |
| "num_tokens": 5589404.0, |
| "step": 3135 |
| }, |
| { |
| "entropy": 6.0568376064300535, |
| "epoch": 0.16151017154026182, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00013542647945527498, |
| "loss": 5.6837, |
| "mean_token_accuracy": 0.15595041066408158, |
| "num_tokens": 5598244.0, |
| "step": 3140 |
| }, |
| { |
| "entropy": 6.061366128921509, |
| "epoch": 0.1617673533420775, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0001345043640096465, |
| "loss": 5.71, |
| "mean_token_accuracy": 0.15352889746427537, |
| "num_tokens": 5606508.0, |
| "step": 3145 |
| }, |
| { |
| "entropy": 5.998555421829224, |
| "epoch": 0.16202453514389323, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00013358610032284957, |
| "loss": 5.5801, |
| "mean_token_accuracy": 0.157723768055439, |
| "num_tokens": 5615733.0, |
| "step": 3150 |
| }, |
| { |
| "entropy": 6.004820728302002, |
| "epoch": 0.16228171694570892, |
| "grad_norm": 1.1328125, |
| "learning_rate": 0.000132671713569547, |
| "loss": 5.5398, |
| "mean_token_accuracy": 0.16117623299360276, |
| "num_tokens": 5623964.0, |
| "step": 3155 |
| }, |
| { |
| "entropy": 6.082151937484741, |
| "epoch": 0.1625388987475246, |
| "grad_norm": 1.171875, |
| "learning_rate": 0.0001317612288181136, |
| "loss": 5.6951, |
| "mean_token_accuracy": 0.155268594622612, |
| "num_tokens": 5632127.0, |
| "step": 3160 |
| }, |
| { |
| "entropy": 6.020006322860718, |
| "epoch": 0.16279608054934033, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00013085467102994864, |
| "loss": 5.6441, |
| "mean_token_accuracy": 0.15653787404298783, |
| "num_tokens": 5641138.0, |
| "step": 3165 |
| }, |
| { |
| "entropy": 6.07370891571045, |
| "epoch": 0.16305326235115603, |
| "grad_norm": 1.1015625, |
| "learning_rate": 0.00012995206505879198, |
| "loss": 5.7089, |
| "mean_token_accuracy": 0.15212901383638383, |
| "num_tokens": 5650291.0, |
| "step": 3170 |
| }, |
| { |
| "entropy": 6.078808927536011, |
| "epoch": 0.16331044415297175, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001290534356500421, |
| "loss": 5.6216, |
| "mean_token_accuracy": 0.15991827100515366, |
| "num_tokens": 5659471.0, |
| "step": 3175 |
| }, |
| { |
| "entropy": 6.110206365585327, |
| "epoch": 0.16356762595478744, |
| "grad_norm": 1.109375, |
| "learning_rate": 0.00012815880744007827, |
| "loss": 5.7288, |
| "mean_token_accuracy": 0.14586359933018683, |
| "num_tokens": 5668669.0, |
| "step": 3180 |
| }, |
| { |
| "entropy": 6.113463354110718, |
| "epoch": 0.16382480775660313, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00012726820495558483, |
| "loss": 5.6974, |
| "mean_token_accuracy": 0.15229963064193724, |
| "num_tokens": 5678091.0, |
| "step": 3185 |
| }, |
| { |
| "entropy": 6.044578981399536, |
| "epoch": 0.16408198955841885, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00012638165261287868, |
| "loss": 5.6573, |
| "mean_token_accuracy": 0.16073704659938812, |
| "num_tokens": 5687074.0, |
| "step": 3190 |
| }, |
| { |
| "entropy": 6.035308361053467, |
| "epoch": 0.16433917136023454, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.0001254991747172402, |
| "loss": 5.6159, |
| "mean_token_accuracy": 0.15784968435764313, |
| "num_tokens": 5696174.0, |
| "step": 3195 |
| }, |
| { |
| "entropy": 6.096799516677857, |
| "epoch": 0.16459635316205026, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.00012462079546224662, |
| "loss": 5.6816, |
| "mean_token_accuracy": 0.14943348318338395, |
| "num_tokens": 5705128.0, |
| "step": 3200 |
| }, |
| { |
| "entropy": 6.127086877822876, |
| "epoch": 0.16485353496386596, |
| "grad_norm": 1.140625, |
| "learning_rate": 0.00012374653892910896, |
| "loss": 5.7553, |
| "mean_token_accuracy": 0.1506531372666359, |
| "num_tokens": 5713583.0, |
| "step": 3205 |
| }, |
| { |
| "entropy": 6.11700406074524, |
| "epoch": 0.16511071676568165, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00012287642908601166, |
| "loss": 5.6915, |
| "mean_token_accuracy": 0.15564704537391663, |
| "num_tokens": 5722416.0, |
| "step": 3210 |
| }, |
| { |
| "entropy": 6.023195552825928, |
| "epoch": 0.16536789856749737, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00012201048978745569, |
| "loss": 5.6684, |
| "mean_token_accuracy": 0.15468333214521407, |
| "num_tokens": 5732087.0, |
| "step": 3215 |
| }, |
| { |
| "entropy": 6.011887645721435, |
| "epoch": 0.16562508036931306, |
| "grad_norm": 1.125, |
| "learning_rate": 0.00012114874477360427, |
| "loss": 5.5195, |
| "mean_token_accuracy": 0.16267940104007722, |
| "num_tokens": 5740325.0, |
| "step": 3220 |
| }, |
| { |
| "entropy": 6.022515058517456, |
| "epoch": 0.16588226217112878, |
| "grad_norm": 1.0, |
| "learning_rate": 0.00012029121766963236, |
| "loss": 5.6966, |
| "mean_token_accuracy": 0.15148866772651673, |
| "num_tokens": 5749813.0, |
| "step": 3225 |
| }, |
| { |
| "entropy": 6.116925382614136, |
| "epoch": 0.16613944397294447, |
| "grad_norm": 1.03125, |
| "learning_rate": 0.00011943793198507858, |
| "loss": 5.6799, |
| "mean_token_accuracy": 0.16098382323980331, |
| "num_tokens": 5758804.0, |
| "step": 3230 |
| }, |
| { |
| "entropy": 6.106556463241577, |
| "epoch": 0.16639662577476017, |
| "grad_norm": 1.1640625, |
| "learning_rate": 0.00011858891111320104, |
| "loss": 5.6791, |
| "mean_token_accuracy": 0.15249733179807662, |
| "num_tokens": 5767684.0, |
| "step": 3235 |
| }, |
| { |
| "entropy": 6.048175382614136, |
| "epoch": 0.16665380757657589, |
| "grad_norm": 1.0546875, |
| "learning_rate": 0.0001177441783303359, |
| "loss": 5.683, |
| "mean_token_accuracy": 0.1550045818090439, |
| "num_tokens": 5776727.0, |
| "step": 3240 |
| }, |
| { |
| "entropy": 6.081117820739746, |
| "epoch": 0.16691098937839158, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00011690375679525896, |
| "loss": 5.762, |
| "mean_token_accuracy": 0.15465280413627625, |
| "num_tokens": 5785426.0, |
| "step": 3245 |
| }, |
| { |
| "entropy": 6.025855541229248, |
| "epoch": 0.1671681711802073, |
| "grad_norm": 1.0625, |
| "learning_rate": 0.00011606766954855124, |
| "loss": 5.6172, |
| "mean_token_accuracy": 0.1613987222313881, |
| "num_tokens": 5794451.0, |
| "step": 3250 |
| }, |
| { |
| "entropy": 6.060605764389038, |
| "epoch": 0.167425352982023, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00011523593951196702, |
| "loss": 5.624, |
| "mean_token_accuracy": 0.1564696580171585, |
| "num_tokens": 5803591.0, |
| "step": 3255 |
| }, |
| { |
| "entropy": 6.068727779388428, |
| "epoch": 0.16768253478383868, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00011440858948780523, |
| "loss": 5.6692, |
| "mean_token_accuracy": 0.15473415851593017, |
| "num_tokens": 5812656.0, |
| "step": 3260 |
| }, |
| { |
| "entropy": 6.090125608444214, |
| "epoch": 0.1679397165856544, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00011358564215828484, |
| "loss": 5.7161, |
| "mean_token_accuracy": 0.15418897569179535, |
| "num_tokens": 5821368.0, |
| "step": 3265 |
| }, |
| { |
| "entropy": 6.057437801361084, |
| "epoch": 0.1681968983874701, |
| "grad_norm": 1.1171875, |
| "learning_rate": 0.00011276712008492254, |
| "loss": 5.6083, |
| "mean_token_accuracy": 0.16170768886804582, |
| "num_tokens": 5829959.0, |
| "step": 3270 |
| }, |
| { |
| "entropy": 6.029361391067505, |
| "epoch": 0.16845408018928582, |
| "grad_norm": 1.0234375, |
| "learning_rate": 0.00011195304570791451, |
| "loss": 5.7291, |
| "mean_token_accuracy": 0.14855351001024247, |
| "num_tokens": 5839241.0, |
| "step": 3275 |
| }, |
| { |
| "entropy": 6.039411163330078, |
| "epoch": 0.1687112619911015, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00011114344134552094, |
| "loss": 5.6955, |
| "mean_token_accuracy": 0.15026117861270905, |
| "num_tokens": 5847976.0, |
| "step": 3280 |
| }, |
| { |
| "entropy": 6.059234285354615, |
| "epoch": 0.1689684437929172, |
| "grad_norm": 1.125, |
| "learning_rate": 0.0001103383291934545, |
| "loss": 5.6389, |
| "mean_token_accuracy": 0.15315767526626586, |
| "num_tokens": 5856652.0, |
| "step": 3285 |
| }, |
| { |
| "entropy": 6.12897515296936, |
| "epoch": 0.16922562559473292, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00010953773132427141, |
| "loss": 5.7315, |
| "mean_token_accuracy": 0.1536328211426735, |
| "num_tokens": 5865705.0, |
| "step": 3290 |
| }, |
| { |
| "entropy": 6.011892080307007, |
| "epoch": 0.1694828073965486, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00010874166968676677, |
| "loss": 5.5434, |
| "mean_token_accuracy": 0.16169371753931044, |
| "num_tokens": 5875326.0, |
| "step": 3295 |
| }, |
| { |
| "entropy": 6.039876461029053, |
| "epoch": 0.16973998919836433, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00010795016610537251, |
| "loss": 5.5533, |
| "mean_token_accuracy": 0.16209474354982376, |
| "num_tokens": 5883893.0, |
| "step": 3300 |
| }, |
| { |
| "entropy": 6.023108100891113, |
| "epoch": 0.16999717100018003, |
| "grad_norm": 1.1484375, |
| "learning_rate": 0.00010716324227955904, |
| "loss": 5.5773, |
| "mean_token_accuracy": 0.15962564796209336, |
| "num_tokens": 5892362.0, |
| "step": 3305 |
| }, |
| { |
| "entropy": 6.022583436965943, |
| "epoch": 0.17025435280199572, |
| "grad_norm": 1.078125, |
| "learning_rate": 0.0001063809197832406, |
| "loss": 5.6619, |
| "mean_token_accuracy": 0.15854102820158006, |
| "num_tokens": 5901474.0, |
| "step": 3310 |
| }, |
| { |
| "entropy": 6.031818532943726, |
| "epoch": 0.17051153460381144, |
| "grad_norm": 1.0859375, |
| "learning_rate": 0.00010560322006418368, |
| "loss": 5.7243, |
| "mean_token_accuracy": 0.15724352225661278, |
| "num_tokens": 5910595.0, |
| "step": 3315 |
| }, |
| { |
| "entropy": 6.043930196762085, |
| "epoch": 0.17076871640562713, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00010483016444341887, |
| "loss": 5.6277, |
| "mean_token_accuracy": 0.1515536427497864, |
| "num_tokens": 5920094.0, |
| "step": 3320 |
| }, |
| { |
| "entropy": 6.020736646652222, |
| "epoch": 0.17102589820744285, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00010406177411465654, |
| "loss": 5.5541, |
| "mean_token_accuracy": 0.16486092507839203, |
| "num_tokens": 5929113.0, |
| "step": 3325 |
| }, |
| { |
| "entropy": 6.046477508544922, |
| "epoch": 0.17128308000925854, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00010329807014370562, |
| "loss": 5.6259, |
| "mean_token_accuracy": 0.15476777404546738, |
| "num_tokens": 5938730.0, |
| "step": 3330 |
| }, |
| { |
| "entropy": 6.049705600738525, |
| "epoch": 0.17154026181107423, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.00010253907346789632, |
| "loss": 5.6484, |
| "mean_token_accuracy": 0.15401506945490837, |
| "num_tokens": 5947699.0, |
| "step": 3335 |
| }, |
| { |
| "entropy": 6.0582891464233395, |
| "epoch": 0.17179744361288996, |
| "grad_norm": 1.09375, |
| "learning_rate": 0.00010178480489550596, |
| "loss": 5.6585, |
| "mean_token_accuracy": 0.14900300800800323, |
| "num_tokens": 5956281.0, |
| "step": 3340 |
| }, |
| { |
| "entropy": 6.088191127777099, |
| "epoch": 0.17205462541470565, |
| "grad_norm": 1.0390625, |
| "learning_rate": 0.00010103528510518836, |
| "loss": 5.6475, |
| "mean_token_accuracy": 0.15165127515792848, |
| "num_tokens": 5965017.0, |
| "step": 3345 |
| }, |
| { |
| "entropy": 6.091164493560791, |
| "epoch": 0.17231180721652137, |
| "grad_norm": 1.046875, |
| "learning_rate": 0.0001002905346454073, |
| "loss": 5.7213, |
| "mean_token_accuracy": 0.15189325511455537, |
| "num_tokens": 5974454.0, |
| "step": 3350 |
| }, |
| { |
| "entropy": 6.064612340927124, |
| "epoch": 0.17256898901833706, |
| "grad_norm": 1.1796875, |
| "learning_rate": 9.955057393387285e-05, |
| "loss": 5.6392, |
| "mean_token_accuracy": 0.16015583425760269, |
| "num_tokens": 5983220.0, |
| "step": 3355 |
| }, |
| { |
| "entropy": 6.106249618530273, |
| "epoch": 0.17282617082015275, |
| "grad_norm": 1.15625, |
| "learning_rate": 9.88154232569816e-05, |
| "loss": 5.6918, |
| "mean_token_accuracy": 0.15452673137187958, |
| "num_tokens": 5992346.0, |
| "step": 3360 |
| }, |
| { |
| "entropy": 6.1094602108001705, |
| "epoch": 0.17308335262196847, |
| "grad_norm": 1.0, |
| "learning_rate": 9.808510276926075e-05, |
| "loss": 5.6077, |
| "mean_token_accuracy": 0.1605488032102585, |
| "num_tokens": 6000578.0, |
| "step": 3365 |
| }, |
| { |
| "entropy": 6.138419151306152, |
| "epoch": 0.17334053442378416, |
| "grad_norm": 1.0703125, |
| "learning_rate": 9.735963249281549e-05, |
| "loss": 5.688, |
| "mean_token_accuracy": 0.15041821151971818, |
| "num_tokens": 6009713.0, |
| "step": 3370 |
| }, |
| { |
| "entropy": 6.048241090774536, |
| "epoch": 0.17359771622559989, |
| "grad_norm": 1.109375, |
| "learning_rate": 9.663903231677974e-05, |
| "loss": 5.6872, |
| "mean_token_accuracy": 0.15479934439063073, |
| "num_tokens": 6018644.0, |
| "step": 3375 |
| }, |
| { |
| "entropy": 6.054699516296386, |
| "epoch": 0.17385489802741558, |
| "grad_norm": 1.125, |
| "learning_rate": 9.592332199677145e-05, |
| "loss": 5.6459, |
| "mean_token_accuracy": 0.1520386055111885, |
| "num_tokens": 6028461.0, |
| "step": 3380 |
| }, |
| { |
| "entropy": 6.119726276397705, |
| "epoch": 0.17411207982923127, |
| "grad_norm": 1.28125, |
| "learning_rate": 9.521252115435061e-05, |
| "loss": 5.7106, |
| "mean_token_accuracy": 0.15589750558137894, |
| "num_tokens": 6037576.0, |
| "step": 3385 |
| }, |
| { |
| "entropy": 6.089563465118408, |
| "epoch": 0.174369261631047, |
| "grad_norm": 0.99609375, |
| "learning_rate": 9.450664927648126e-05, |
| "loss": 5.7558, |
| "mean_token_accuracy": 0.15028124749660493, |
| "num_tokens": 6047762.0, |
| "step": 3390 |
| }, |
| { |
| "entropy": 6.16429443359375, |
| "epoch": 0.17462644343286268, |
| "grad_norm": 1.078125, |
| "learning_rate": 9.380572571499758e-05, |
| "loss": 5.7751, |
| "mean_token_accuracy": 0.1476622514426708, |
| "num_tokens": 6057538.0, |
| "step": 3395 |
| }, |
| { |
| "entropy": 6.082699155807495, |
| "epoch": 0.1748836252346784, |
| "grad_norm": 1.03125, |
| "learning_rate": 9.310976968607307e-05, |
| "loss": 5.6233, |
| "mean_token_accuracy": 0.16030136346817017, |
| "num_tokens": 6066140.0, |
| "step": 3400 |
| }, |
| { |
| "entropy": 6.00179615020752, |
| "epoch": 0.1751408070364941, |
| "grad_norm": 1.0625, |
| "learning_rate": 9.241880026969381e-05, |
| "loss": 5.5588, |
| "mean_token_accuracy": 0.1648190751671791, |
| "num_tokens": 6075250.0, |
| "step": 3405 |
| }, |
| { |
| "entropy": 6.05587363243103, |
| "epoch": 0.1753979888383098, |
| "grad_norm": 1.1328125, |
| "learning_rate": 9.173283640913537e-05, |
| "loss": 5.6223, |
| "mean_token_accuracy": 0.15902888625860215, |
| "num_tokens": 6083660.0, |
| "step": 3410 |
| }, |
| { |
| "entropy": 6.0504176139831545, |
| "epoch": 0.1756551706401255, |
| "grad_norm": 1.140625, |
| "learning_rate": 9.10518969104436e-05, |
| "loss": 5.6532, |
| "mean_token_accuracy": 0.14977732598781585, |
| "num_tokens": 6093177.0, |
| "step": 3415 |
| }, |
| { |
| "entropy": 6.058867311477661, |
| "epoch": 0.1759123524419412, |
| "grad_norm": 1.0234375, |
| "learning_rate": 9.037600044191868e-05, |
| "loss": 5.6467, |
| "mean_token_accuracy": 0.15975452214479446, |
| "num_tokens": 6102066.0, |
| "step": 3420 |
| }, |
| { |
| "entropy": 6.056565189361573, |
| "epoch": 0.17616953424375692, |
| "grad_norm": 1.0859375, |
| "learning_rate": 8.970516553360383e-05, |
| "loss": 5.629, |
| "mean_token_accuracy": 0.15534522980451584, |
| "num_tokens": 6110871.0, |
| "step": 3425 |
| }, |
| { |
| "entropy": 6.047246503829956, |
| "epoch": 0.1764267160455726, |
| "grad_norm": 1.0, |
| "learning_rate": 8.903941057677692e-05, |
| "loss": 5.6651, |
| "mean_token_accuracy": 0.16005419790744782, |
| "num_tokens": 6119963.0, |
| "step": 3430 |
| }, |
| { |
| "entropy": 6.047842502593994, |
| "epoch": 0.17668389784738833, |
| "grad_norm": 1.1015625, |
| "learning_rate": 8.837875382344635e-05, |
| "loss": 5.5966, |
| "mean_token_accuracy": 0.15555885583162307, |
| "num_tokens": 6129241.0, |
| "step": 3435 |
| }, |
| { |
| "entropy": 6.042540216445923, |
| "epoch": 0.17694107964920402, |
| "grad_norm": 0.9609375, |
| "learning_rate": 8.772321338585076e-05, |
| "loss": 5.6497, |
| "mean_token_accuracy": 0.15830232053995133, |
| "num_tokens": 6138098.0, |
| "step": 3440 |
| }, |
| { |
| "entropy": 6.0757143020629885, |
| "epoch": 0.17719826145101972, |
| "grad_norm": 1.1015625, |
| "learning_rate": 8.707280723596242e-05, |
| "loss": 5.7256, |
| "mean_token_accuracy": 0.1568673923611641, |
| "num_tokens": 6147235.0, |
| "step": 3445 |
| }, |
| { |
| "entropy": 5.994702434539795, |
| "epoch": 0.17745544325283544, |
| "grad_norm": 1.171875, |
| "learning_rate": 8.64275532049944e-05, |
| "loss": 5.4986, |
| "mean_token_accuracy": 0.16098511964082718, |
| "num_tokens": 6155837.0, |
| "step": 3450 |
| }, |
| { |
| "entropy": 6.002437019348145, |
| "epoch": 0.17771262505465113, |
| "grad_norm": 1.125, |
| "learning_rate": 8.578746898291198e-05, |
| "loss": 5.6305, |
| "mean_token_accuracy": 0.15675635188817977, |
| "num_tokens": 6164329.0, |
| "step": 3455 |
| }, |
| { |
| "entropy": 6.094465970993042, |
| "epoch": 0.17796980685646685, |
| "grad_norm": 1.1328125, |
| "learning_rate": 8.515257211794742e-05, |
| "loss": 5.714, |
| "mean_token_accuracy": 0.15470660626888275, |
| "num_tokens": 6172835.0, |
| "step": 3460 |
| }, |
| { |
| "entropy": 6.046740770339966, |
| "epoch": 0.17822698865828254, |
| "grad_norm": 1.0234375, |
| "learning_rate": 8.452288001611896e-05, |
| "loss": 5.6164, |
| "mean_token_accuracy": 0.15798363983631133, |
| "num_tokens": 6182369.0, |
| "step": 3465 |
| }, |
| { |
| "entropy": 6.0431455135345455, |
| "epoch": 0.17848417046009823, |
| "grad_norm": 1.109375, |
| "learning_rate": 8.389840994075379e-05, |
| "loss": 5.5391, |
| "mean_token_accuracy": 0.16320235878229142, |
| "num_tokens": 6191623.0, |
| "step": 3470 |
| }, |
| { |
| "entropy": 6.0026098728179935, |
| "epoch": 0.17874135226191395, |
| "grad_norm": 1.1953125, |
| "learning_rate": 8.327917901201435e-05, |
| "loss": 5.6225, |
| "mean_token_accuracy": 0.15640424489974974, |
| "num_tokens": 6200388.0, |
| "step": 3475 |
| }, |
| { |
| "entropy": 6.029439163208008, |
| "epoch": 0.17899853406372965, |
| "grad_norm": 1.1015625, |
| "learning_rate": 8.266520420642931e-05, |
| "loss": 5.6566, |
| "mean_token_accuracy": 0.1595880627632141, |
| "num_tokens": 6208913.0, |
| "step": 3480 |
| }, |
| { |
| "entropy": 6.050599193572998, |
| "epoch": 0.17925571586554537, |
| "grad_norm": 1.0703125, |
| "learning_rate": 8.205650235642828e-05, |
| "loss": 5.6079, |
| "mean_token_accuracy": 0.15639622658491134, |
| "num_tokens": 6218291.0, |
| "step": 3485 |
| }, |
| { |
| "entropy": 6.114253568649292, |
| "epoch": 0.17951289766736106, |
| "grad_norm": 1.1640625, |
| "learning_rate": 8.145309014987978e-05, |
| "loss": 5.6589, |
| "mean_token_accuracy": 0.15421286076307297, |
| "num_tokens": 6226939.0, |
| "step": 3490 |
| }, |
| { |
| "entropy": 6.098499774932861, |
| "epoch": 0.17977007946917675, |
| "grad_norm": 1.0390625, |
| "learning_rate": 8.085498412963437e-05, |
| "loss": 5.741, |
| "mean_token_accuracy": 0.14972428232431412, |
| "num_tokens": 6236515.0, |
| "step": 3495 |
| }, |
| { |
| "entropy": 6.0787252426147464, |
| "epoch": 0.18002726127099247, |
| "grad_norm": 1.0859375, |
| "learning_rate": 8.026220069307078e-05, |
| "loss": 5.6437, |
| "mean_token_accuracy": 0.1560056820511818, |
| "num_tokens": 6245016.0, |
| "step": 3500 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 4000, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 1243605406187520.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
