| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.025718180181570353, |
| "eval_steps": 500, |
| "global_step": 500, |
| "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 |
| } |
| ], |
| "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": 178115181281280.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
