| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.051436360363140705, |
| "eval_steps": 500, |
| "global_step": 1000, |
| "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 |
| } |
| ], |
| "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": 353654176481280.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
