Invalid JSON:Unexpected token 'N', ..."ad_norm": NaN,
"... is not valid JSON
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.935483870967742, | |
| "eval_steps": 30, | |
| "global_step": 240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008064516129032258, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 4.423851013183594, | |
| "num_input_tokens_seen": 3376, | |
| "step": 1, | |
| "train_runtime": 66.7001, | |
| "train_tokens_per_second": 50.615 | |
| }, | |
| { | |
| "epoch": 0.016129032258064516, | |
| "grad_norm": 6.203426361083984, | |
| "learning_rate": 0.0, | |
| "loss": 4.399973392486572, | |
| "num_input_tokens_seen": 6750, | |
| "step": 2, | |
| "train_runtime": 76.9504, | |
| "train_tokens_per_second": 87.719 | |
| }, | |
| { | |
| "epoch": 0.024193548387096774, | |
| "grad_norm": 6.417575359344482, | |
| "learning_rate": 4e-05, | |
| "loss": 4.3025593757629395, | |
| "num_input_tokens_seen": 10132, | |
| "step": 3, | |
| "train_runtime": 83.942, | |
| "train_tokens_per_second": 120.702 | |
| }, | |
| { | |
| "epoch": 0.03225806451612903, | |
| "grad_norm": 5.7837066650390625, | |
| "learning_rate": 8e-05, | |
| "loss": 4.235351085662842, | |
| "num_input_tokens_seen": 13496, | |
| "step": 4, | |
| "train_runtime": 90.8369, | |
| "train_tokens_per_second": 148.574 | |
| }, | |
| { | |
| "epoch": 0.04032258064516129, | |
| "grad_norm": 6.007510662078857, | |
| "learning_rate": 0.00012, | |
| "loss": 3.714757204055786, | |
| "num_input_tokens_seen": 16978, | |
| "step": 5, | |
| "train_runtime": 97.7335, | |
| "train_tokens_per_second": 173.717 | |
| }, | |
| { | |
| "epoch": 0.04838709677419355, | |
| "grad_norm": 5.7335405349731445, | |
| "learning_rate": 0.00016, | |
| "loss": 2.894195795059204, | |
| "num_input_tokens_seen": 20170, | |
| "step": 6, | |
| "train_runtime": 104.1089, | |
| "train_tokens_per_second": 193.739 | |
| }, | |
| { | |
| "epoch": 0.056451612903225805, | |
| "grad_norm": 3.857361078262329, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3366570472717285, | |
| "num_input_tokens_seen": 23566, | |
| "step": 7, | |
| "train_runtime": 110.8035, | |
| "train_tokens_per_second": 212.683 | |
| }, | |
| { | |
| "epoch": 0.06451612903225806, | |
| "grad_norm": 3.2568986415863037, | |
| "learning_rate": 0.00019999967645432384, | |
| "loss": 1.862092137336731, | |
| "num_input_tokens_seen": 26930, | |
| "step": 8, | |
| "train_runtime": 117.3062, | |
| "train_tokens_per_second": 229.57 | |
| }, | |
| { | |
| "epoch": 0.07258064516129033, | |
| "grad_norm": 2.912194013595581, | |
| "learning_rate": 0.00019999870581938894, | |
| "loss": 1.5545849800109863, | |
| "num_input_tokens_seen": 30108, | |
| "step": 9, | |
| "train_runtime": 123.6618, | |
| "train_tokens_per_second": 243.47 | |
| }, | |
| { | |
| "epoch": 0.08064516129032258, | |
| "grad_norm": 2.0680058002471924, | |
| "learning_rate": 0.0001999970881014762, | |
| "loss": 1.4453465938568115, | |
| "num_input_tokens_seen": 33254, | |
| "step": 10, | |
| "train_runtime": 129.8936, | |
| "train_tokens_per_second": 256.01 | |
| }, | |
| { | |
| "epoch": 0.08870967741935484, | |
| "grad_norm": 1.753443717956543, | |
| "learning_rate": 0.00019999482331105377, | |
| "loss": 1.3031213283538818, | |
| "num_input_tokens_seen": 36458, | |
| "step": 11, | |
| "train_runtime": 136.2063, | |
| "train_tokens_per_second": 267.667 | |
| }, | |
| { | |
| "epoch": 0.0967741935483871, | |
| "grad_norm": 1.311978816986084, | |
| "learning_rate": 0.0001999919114627769, | |
| "loss": 1.155328631401062, | |
| "num_input_tokens_seen": 39848, | |
| "step": 12, | |
| "train_runtime": 142.7896, | |
| "train_tokens_per_second": 279.068 | |
| }, | |
| { | |
| "epoch": 0.10483870967741936, | |
| "grad_norm": 1.408735990524292, | |
| "learning_rate": 0.00019998835257548786, | |
| "loss": 1.1732935905456543, | |
| "num_input_tokens_seen": 42964, | |
| "step": 13, | |
| "train_runtime": 149.0986, | |
| "train_tokens_per_second": 288.158 | |
| }, | |
| { | |
| "epoch": 0.11290322580645161, | |
| "grad_norm": 1.0793702602386475, | |
| "learning_rate": 0.00019998414667221596, | |
| "loss": 1.071805715560913, | |
| "num_input_tokens_seen": 46336, | |
| "step": 14, | |
| "train_runtime": 155.6938, | |
| "train_tokens_per_second": 297.61 | |
| }, | |
| { | |
| "epoch": 0.12096774193548387, | |
| "grad_norm": 0.9536115527153015, | |
| "learning_rate": 0.00019997929378017725, | |
| "loss": 1.0273140668869019, | |
| "num_input_tokens_seen": 49524, | |
| "step": 15, | |
| "train_runtime": 162.1537, | |
| "train_tokens_per_second": 305.414 | |
| }, | |
| { | |
| "epoch": 0.12903225806451613, | |
| "grad_norm": 1.0113959312438965, | |
| "learning_rate": 0.00019997379393077428, | |
| "loss": 0.9971197247505188, | |
| "num_input_tokens_seen": 52878, | |
| "step": 16, | |
| "train_runtime": 168.7668, | |
| "train_tokens_per_second": 313.32 | |
| }, | |
| { | |
| "epoch": 0.13709677419354838, | |
| "grad_norm": 1.0217102766036987, | |
| "learning_rate": 0.00019996764715959618, | |
| "loss": 0.8978726267814636, | |
| "num_input_tokens_seen": 56342, | |
| "step": 17, | |
| "train_runtime": 175.5152, | |
| "train_tokens_per_second": 321.009 | |
| }, | |
| { | |
| "epoch": 0.14516129032258066, | |
| "grad_norm": 0.9274588227272034, | |
| "learning_rate": 0.0001999608535064182, | |
| "loss": 0.8967312574386597, | |
| "num_input_tokens_seen": 59734, | |
| "step": 18, | |
| "train_runtime": 182.3718, | |
| "train_tokens_per_second": 327.54 | |
| }, | |
| { | |
| "epoch": 0.1532258064516129, | |
| "grad_norm": 0.9428430795669556, | |
| "learning_rate": 0.0001999534130152014, | |
| "loss": 0.8502129912376404, | |
| "num_input_tokens_seen": 63022, | |
| "step": 19, | |
| "train_runtime": 189.0546, | |
| "train_tokens_per_second": 333.353 | |
| }, | |
| { | |
| "epoch": 0.16129032258064516, | |
| "grad_norm": 1.0413854122161865, | |
| "learning_rate": 0.00019994532573409262, | |
| "loss": 0.8611021041870117, | |
| "num_input_tokens_seen": 66380, | |
| "step": 20, | |
| "train_runtime": 195.6702, | |
| "train_tokens_per_second": 339.244 | |
| }, | |
| { | |
| "epoch": 0.1693548387096774, | |
| "grad_norm": 1.1126433610916138, | |
| "learning_rate": 0.0001999365917154239, | |
| "loss": 0.8235692977905273, | |
| "num_input_tokens_seen": 69412, | |
| "step": 21, | |
| "train_runtime": 201.791, | |
| "train_tokens_per_second": 343.98 | |
| }, | |
| { | |
| "epoch": 0.1774193548387097, | |
| "grad_norm": 1.0743067264556885, | |
| "learning_rate": 0.00019992721101571236, | |
| "loss": 0.8540856242179871, | |
| "num_input_tokens_seen": 72682, | |
| "step": 22, | |
| "train_runtime": 208.1813, | |
| "train_tokens_per_second": 349.128 | |
| }, | |
| { | |
| "epoch": 0.18548387096774194, | |
| "grad_norm": 0.9999114274978638, | |
| "learning_rate": 0.0001999171836956597, | |
| "loss": 0.8636960983276367, | |
| "num_input_tokens_seen": 75880, | |
| "step": 23, | |
| "train_runtime": 214.6214, | |
| "train_tokens_per_second": 353.553 | |
| }, | |
| { | |
| "epoch": 0.1935483870967742, | |
| "grad_norm": 0.8346990942955017, | |
| "learning_rate": 0.0001999065098201518, | |
| "loss": 0.7936219573020935, | |
| "num_input_tokens_seen": 79364, | |
| "step": 24, | |
| "train_runtime": 221.3966, | |
| "train_tokens_per_second": 358.47 | |
| }, | |
| { | |
| "epoch": 0.20161290322580644, | |
| "grad_norm": 0.9597648978233337, | |
| "learning_rate": 0.00019989518945825844, | |
| "loss": 0.7347128987312317, | |
| "num_input_tokens_seen": 82600, | |
| "step": 25, | |
| "train_runtime": 227.963, | |
| "train_tokens_per_second": 362.34 | |
| }, | |
| { | |
| "epoch": 0.20967741935483872, | |
| "grad_norm": 0.9161474704742432, | |
| "learning_rate": 0.00019988322268323268, | |
| "loss": 0.7401193976402283, | |
| "num_input_tokens_seen": 85954, | |
| "step": 26, | |
| "train_runtime": 234.5417, | |
| "train_tokens_per_second": 366.476 | |
| }, | |
| { | |
| "epoch": 0.21774193548387097, | |
| "grad_norm": 0.8665032386779785, | |
| "learning_rate": 0.00019987060957251047, | |
| "loss": 0.7189968228340149, | |
| "num_input_tokens_seen": 89314, | |
| "step": 27, | |
| "train_runtime": 241.1219, | |
| "train_tokens_per_second": 370.41 | |
| }, | |
| { | |
| "epoch": 0.22580645161290322, | |
| "grad_norm": 0.9274927377700806, | |
| "learning_rate": 0.00019985735020771017, | |
| "loss": 0.7693567276000977, | |
| "num_input_tokens_seen": 92550, | |
| "step": 28, | |
| "train_runtime": 247.6164, | |
| "train_tokens_per_second": 373.764 | |
| }, | |
| { | |
| "epoch": 0.23387096774193547, | |
| "grad_norm": 0.9395021796226501, | |
| "learning_rate": 0.00019984344467463197, | |
| "loss": 0.6852114200592041, | |
| "num_input_tokens_seen": 95904, | |
| "step": 29, | |
| "train_runtime": 254.2268, | |
| "train_tokens_per_second": 377.238 | |
| }, | |
| { | |
| "epoch": 0.24193548387096775, | |
| "grad_norm": 0.7659223079681396, | |
| "learning_rate": 0.0001998288930632574, | |
| "loss": 0.7528179883956909, | |
| "num_input_tokens_seen": 99314, | |
| "step": 30, | |
| "train_runtime": 260.9489, | |
| "train_tokens_per_second": 380.588 | |
| }, | |
| { | |
| "epoch": 0.24193548387096775, | |
| "eval_loss": 2.828965902328491, | |
| "eval_runtime": 19.7056, | |
| "eval_samples_per_second": 2.639, | |
| "eval_steps_per_second": 1.319, | |
| "num_input_tokens_seen": 99314, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.8182386755943298, | |
| "learning_rate": 0.00019981369546774865, | |
| "loss": 0.7148607969284058, | |
| "num_input_tokens_seen": 102632, | |
| "step": 31, | |
| "train_runtime": 292.7626, | |
| "train_tokens_per_second": 350.564 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 0.8975741863250732, | |
| "learning_rate": 0.00019979785198644806, | |
| "loss": 0.7239475250244141, | |
| "num_input_tokens_seen": 106032, | |
| "step": 32, | |
| "train_runtime": 299.4571, | |
| "train_tokens_per_second": 354.081 | |
| }, | |
| { | |
| "epoch": 0.2661290322580645, | |
| "grad_norm": 0.8582456707954407, | |
| "learning_rate": 0.00019978136272187747, | |
| "loss": 0.6491944789886475, | |
| "num_input_tokens_seen": 109374, | |
| "step": 33, | |
| "train_runtime": 306.0795, | |
| "train_tokens_per_second": 357.339 | |
| }, | |
| { | |
| "epoch": 0.27419354838709675, | |
| "grad_norm": 0.8682915568351746, | |
| "learning_rate": 0.0001997642277807374, | |
| "loss": 0.726476788520813, | |
| "num_input_tokens_seen": 112780, | |
| "step": 34, | |
| "train_runtime": 312.8542, | |
| "train_tokens_per_second": 360.487 | |
| }, | |
| { | |
| "epoch": 0.28225806451612906, | |
| "grad_norm": 0.7901797294616699, | |
| "learning_rate": 0.00019974644727390665, | |
| "loss": 0.6442930698394775, | |
| "num_input_tokens_seen": 116154, | |
| "step": 35, | |
| "train_runtime": 319.5272, | |
| "train_tokens_per_second": 363.518 | |
| }, | |
| { | |
| "epoch": 0.2903225806451613, | |
| "grad_norm": 0.7850049138069153, | |
| "learning_rate": 0.00019972802131644127, | |
| "loss": 0.6595083475112915, | |
| "num_input_tokens_seen": 119350, | |
| "step": 36, | |
| "train_runtime": 325.9376, | |
| "train_tokens_per_second": 366.174 | |
| }, | |
| { | |
| "epoch": 0.29838709677419356, | |
| "grad_norm": 0.8906070590019226, | |
| "learning_rate": 0.00019970895002757413, | |
| "loss": 0.6988556385040283, | |
| "num_input_tokens_seen": 122566, | |
| "step": 37, | |
| "train_runtime": 332.3189, | |
| "train_tokens_per_second": 368.82 | |
| }, | |
| { | |
| "epoch": 0.3064516129032258, | |
| "grad_norm": 0.7804127335548401, | |
| "learning_rate": 0.00019968923353071377, | |
| "loss": 0.6648477911949158, | |
| "num_input_tokens_seen": 125906, | |
| "step": 38, | |
| "train_runtime": 339.1293, | |
| "train_tokens_per_second": 371.262 | |
| }, | |
| { | |
| "epoch": 0.31451612903225806, | |
| "grad_norm": 0.796406090259552, | |
| "learning_rate": 0.00019966887195344403, | |
| "loss": 0.6134414076805115, | |
| "num_input_tokens_seen": 129178, | |
| "step": 39, | |
| "train_runtime": 345.6909, | |
| "train_tokens_per_second": 373.681 | |
| }, | |
| { | |
| "epoch": 0.3225806451612903, | |
| "grad_norm": 0.8360472917556763, | |
| "learning_rate": 0.0001996478654275229, | |
| "loss": 0.6537702679634094, | |
| "num_input_tokens_seen": 132242, | |
| "step": 40, | |
| "train_runtime": 351.9107, | |
| "train_tokens_per_second": 375.783 | |
| }, | |
| { | |
| "epoch": 0.33064516129032256, | |
| "grad_norm": 0.7299121618270874, | |
| "learning_rate": 0.00019962621408888177, | |
| "loss": 0.6415868997573853, | |
| "num_input_tokens_seen": 135598, | |
| "step": 41, | |
| "train_runtime": 358.5853, | |
| "train_tokens_per_second": 378.147 | |
| }, | |
| { | |
| "epoch": 0.3387096774193548, | |
| "grad_norm": 0.7271934747695923, | |
| "learning_rate": 0.00019960391807762463, | |
| "loss": 0.6368349194526672, | |
| "num_input_tokens_seen": 139036, | |
| "step": 42, | |
| "train_runtime": 365.2471, | |
| "train_tokens_per_second": 380.663 | |
| }, | |
| { | |
| "epoch": 0.3467741935483871, | |
| "grad_norm": 0.7471262216567993, | |
| "learning_rate": 0.00019958097753802693, | |
| "loss": 0.6261013746261597, | |
| "num_input_tokens_seen": 142314, | |
| "step": 43, | |
| "train_runtime": 371.8635, | |
| "train_tokens_per_second": 382.705 | |
| }, | |
| { | |
| "epoch": 0.3548387096774194, | |
| "grad_norm": 0.7209194302558899, | |
| "learning_rate": 0.00019955739261853504, | |
| "loss": 0.6236422061920166, | |
| "num_input_tokens_seen": 145730, | |
| "step": 44, | |
| "train_runtime": 378.5663, | |
| "train_tokens_per_second": 384.952 | |
| }, | |
| { | |
| "epoch": 0.3629032258064516, | |
| "grad_norm": 0.7694782018661499, | |
| "learning_rate": 0.00019953316347176488, | |
| "loss": 0.6035186052322388, | |
| "num_input_tokens_seen": 148950, | |
| "step": 45, | |
| "train_runtime": 384.9456, | |
| "train_tokens_per_second": 386.938 | |
| }, | |
| { | |
| "epoch": 0.3709677419354839, | |
| "grad_norm": 0.701684832572937, | |
| "learning_rate": 0.00019950829025450114, | |
| "loss": 0.621403694152832, | |
| "num_input_tokens_seen": 152208, | |
| "step": 46, | |
| "train_runtime": 391.4835, | |
| "train_tokens_per_second": 388.798 | |
| }, | |
| { | |
| "epoch": 0.3790322580645161, | |
| "grad_norm": 0.6461907625198364, | |
| "learning_rate": 0.0001994827731276963, | |
| "loss": 0.5377134084701538, | |
| "num_input_tokens_seen": 155494, | |
| "step": 47, | |
| "train_runtime": 398.103, | |
| "train_tokens_per_second": 390.587 | |
| }, | |
| { | |
| "epoch": 0.3870967741935484, | |
| "grad_norm": 0.7744601368904114, | |
| "learning_rate": 0.00019945661225646946, | |
| "loss": 0.5798584222793579, | |
| "num_input_tokens_seen": 158822, | |
| "step": 48, | |
| "train_runtime": 404.6934, | |
| "train_tokens_per_second": 392.45 | |
| }, | |
| { | |
| "epoch": 0.3951612903225806, | |
| "grad_norm": 0.6859694123268127, | |
| "learning_rate": 0.0001994298078101054, | |
| "loss": 0.584874153137207, | |
| "num_input_tokens_seen": 162234, | |
| "step": 49, | |
| "train_runtime": 411.3749, | |
| "train_tokens_per_second": 394.37 | |
| }, | |
| { | |
| "epoch": 0.4032258064516129, | |
| "grad_norm": 0.810454249382019, | |
| "learning_rate": 0.00019940235996205333, | |
| "loss": 0.6668200492858887, | |
| "num_input_tokens_seen": 165674, | |
| "step": 50, | |
| "train_runtime": 418.1504, | |
| "train_tokens_per_second": 396.207 | |
| }, | |
| { | |
| "epoch": 0.4112903225806452, | |
| "grad_norm": 0.7270381450653076, | |
| "learning_rate": 0.0001993742688899259, | |
| "loss": 0.5657421350479126, | |
| "num_input_tokens_seen": 169012, | |
| "step": 51, | |
| "train_runtime": 424.8113, | |
| "train_tokens_per_second": 397.852 | |
| }, | |
| { | |
| "epoch": 0.41935483870967744, | |
| "grad_norm": 0.727074384689331, | |
| "learning_rate": 0.00019934553477549794, | |
| "loss": 0.573532223701477, | |
| "num_input_tokens_seen": 172396, | |
| "step": 52, | |
| "train_runtime": 431.419, | |
| "train_tokens_per_second": 399.602 | |
| }, | |
| { | |
| "epoch": 0.4274193548387097, | |
| "grad_norm": 0.7226607203483582, | |
| "learning_rate": 0.00019931615780470558, | |
| "loss": 0.5972438454627991, | |
| "num_input_tokens_seen": 175766, | |
| "step": 53, | |
| "train_runtime": 438.0204, | |
| "train_tokens_per_second": 401.274 | |
| }, | |
| { | |
| "epoch": 0.43548387096774194, | |
| "grad_norm": 0.815791130065918, | |
| "learning_rate": 0.00019928613816764458, | |
| "loss": 0.5655015707015991, | |
| "num_input_tokens_seen": 179034, | |
| "step": 54, | |
| "train_runtime": 444.5345, | |
| "train_tokens_per_second": 402.745 | |
| }, | |
| { | |
| "epoch": 0.4435483870967742, | |
| "grad_norm": 0.8063026666641235, | |
| "learning_rate": 0.00019925547605856934, | |
| "loss": 0.6497899293899536, | |
| "num_input_tokens_seen": 182380, | |
| "step": 55, | |
| "train_runtime": 451.1643, | |
| "train_tokens_per_second": 404.243 | |
| }, | |
| { | |
| "epoch": 0.45161290322580644, | |
| "grad_norm": 0.7375481128692627, | |
| "learning_rate": 0.00019922417167589183, | |
| "loss": 0.5818440914154053, | |
| "num_input_tokens_seen": 185574, | |
| "step": 56, | |
| "train_runtime": 457.5126, | |
| "train_tokens_per_second": 405.615 | |
| }, | |
| { | |
| "epoch": 0.4596774193548387, | |
| "grad_norm": 0.711955726146698, | |
| "learning_rate": 0.00019919222522217996, | |
| "loss": 0.615460991859436, | |
| "num_input_tokens_seen": 188970, | |
| "step": 57, | |
| "train_runtime": 464.1955, | |
| "train_tokens_per_second": 407.091 | |
| }, | |
| { | |
| "epoch": 0.46774193548387094, | |
| "grad_norm": 0.8263280391693115, | |
| "learning_rate": 0.00019915963690415647, | |
| "loss": 0.5618603229522705, | |
| "num_input_tokens_seen": 192282, | |
| "step": 58, | |
| "train_runtime": 470.7669, | |
| "train_tokens_per_second": 408.444 | |
| }, | |
| { | |
| "epoch": 0.47580645161290325, | |
| "grad_norm": 0.7747593522071838, | |
| "learning_rate": 0.00019912640693269752, | |
| "loss": 0.572489857673645, | |
| "num_input_tokens_seen": 195644, | |
| "step": 59, | |
| "train_runtime": 477.353, | |
| "train_tokens_per_second": 409.852 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "grad_norm": 0.6882827877998352, | |
| "learning_rate": 0.00019909253552283143, | |
| "loss": 0.6016375422477722, | |
| "num_input_tokens_seen": 198956, | |
| "step": 60, | |
| "train_runtime": 484.0262, | |
| "train_tokens_per_second": 411.044 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "eval_loss": 2.4849510192871094, | |
| "eval_runtime": 17.0161, | |
| "eval_samples_per_second": 3.056, | |
| "eval_steps_per_second": 1.528, | |
| "num_input_tokens_seen": 198956, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.49193548387096775, | |
| "grad_norm": 0.7103594541549683, | |
| "learning_rate": 0.00019905802289373715, | |
| "loss": 0.5619174838066101, | |
| "num_input_tokens_seen": 202314, | |
| "step": 61, | |
| "train_runtime": 511.5866, | |
| "train_tokens_per_second": 395.464 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.6471914052963257, | |
| "learning_rate": 0.0001990228692687429, | |
| "loss": 0.5455653667449951, | |
| "num_input_tokens_seen": 205722, | |
| "step": 62, | |
| "train_runtime": 518.1512, | |
| "train_tokens_per_second": 397.031 | |
| }, | |
| { | |
| "epoch": 0.5080645161290323, | |
| "grad_norm": 0.6389148235321045, | |
| "learning_rate": 0.00019898707487532474, | |
| "loss": 0.5808655619621277, | |
| "num_input_tokens_seen": 208882, | |
| "step": 63, | |
| "train_runtime": 524.5777, | |
| "train_tokens_per_second": 398.191 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.7594767212867737, | |
| "learning_rate": 0.0001989506399451051, | |
| "loss": 0.547818124294281, | |
| "num_input_tokens_seen": 212198, | |
| "step": 64, | |
| "train_runtime": 531.1436, | |
| "train_tokens_per_second": 399.512 | |
| }, | |
| { | |
| "epoch": 0.5241935483870968, | |
| "grad_norm": 0.739295244216919, | |
| "learning_rate": 0.0001989135647138513, | |
| "loss": 0.5600237846374512, | |
| "num_input_tokens_seen": 215586, | |
| "step": 65, | |
| "train_runtime": 537.8144, | |
| "train_tokens_per_second": 400.856 | |
| }, | |
| { | |
| "epoch": 0.532258064516129, | |
| "grad_norm": 0.9398884773254395, | |
| "learning_rate": 0.00019887584942147394, | |
| "loss": 0.6664551496505737, | |
| "num_input_tokens_seen": 218732, | |
| "step": 66, | |
| "train_runtime": 544.2058, | |
| "train_tokens_per_second": 401.929 | |
| }, | |
| { | |
| "epoch": 0.5403225806451613, | |
| "grad_norm": 0.731681764125824, | |
| "learning_rate": 0.0001988374943120254, | |
| "loss": 0.5805746912956238, | |
| "num_input_tokens_seen": 221938, | |
| "step": 67, | |
| "train_runtime": 550.7126, | |
| "train_tokens_per_second": 403.001 | |
| }, | |
| { | |
| "epoch": 0.5483870967741935, | |
| "grad_norm": 0.666251003742218, | |
| "learning_rate": 0.00019879849963369827, | |
| "loss": 0.5634634494781494, | |
| "num_input_tokens_seen": 225362, | |
| "step": 68, | |
| "train_runtime": 557.4868, | |
| "train_tokens_per_second": 404.246 | |
| }, | |
| { | |
| "epoch": 0.5564516129032258, | |
| "grad_norm": 0.6615156531333923, | |
| "learning_rate": 0.00019875886563882375, | |
| "loss": 0.5425825119018555, | |
| "num_input_tokens_seen": 228656, | |
| "step": 69, | |
| "train_runtime": 564.2058, | |
| "train_tokens_per_second": 405.271 | |
| }, | |
| { | |
| "epoch": 0.5645161290322581, | |
| "grad_norm": 0.7001394033432007, | |
| "learning_rate": 0.00019871859258387, | |
| "loss": 0.5410492420196533, | |
| "num_input_tokens_seen": 232052, | |
| "step": 70, | |
| "train_runtime": 570.8999, | |
| "train_tokens_per_second": 406.467 | |
| }, | |
| { | |
| "epoch": 0.5725806451612904, | |
| "grad_norm": 0.7109778523445129, | |
| "learning_rate": 0.00019867768072944045, | |
| "loss": 0.5101571083068848, | |
| "num_input_tokens_seen": 235430, | |
| "step": 71, | |
| "train_runtime": 577.493, | |
| "train_tokens_per_second": 407.676 | |
| }, | |
| { | |
| "epoch": 0.5806451612903226, | |
| "grad_norm": 0.606921911239624, | |
| "learning_rate": 0.00019863613034027224, | |
| "loss": 0.5397766828536987, | |
| "num_input_tokens_seen": 238792, | |
| "step": 72, | |
| "train_runtime": 584.0864, | |
| "train_tokens_per_second": 408.83 | |
| }, | |
| { | |
| "epoch": 0.5887096774193549, | |
| "grad_norm": 0.7634878754615784, | |
| "learning_rate": 0.0001985939416852343, | |
| "loss": 0.5851086378097534, | |
| "num_input_tokens_seen": 242136, | |
| "step": 73, | |
| "train_runtime": 590.6152, | |
| "train_tokens_per_second": 409.972 | |
| }, | |
| { | |
| "epoch": 0.5967741935483871, | |
| "grad_norm": 0.8077980875968933, | |
| "learning_rate": 0.00019855111503732574, | |
| "loss": 0.5656052231788635, | |
| "num_input_tokens_seen": 245502, | |
| "step": 74, | |
| "train_runtime": 597.2223, | |
| "train_tokens_per_second": 411.073 | |
| }, | |
| { | |
| "epoch": 0.6048387096774194, | |
| "grad_norm": 0.8043028712272644, | |
| "learning_rate": 0.00019850765067367412, | |
| "loss": 0.5640852451324463, | |
| "num_input_tokens_seen": 248724, | |
| "step": 75, | |
| "train_runtime": 603.5128, | |
| "train_tokens_per_second": 412.127 | |
| }, | |
| { | |
| "epoch": 0.6129032258064516, | |
| "grad_norm": 0.7303769588470459, | |
| "learning_rate": 0.00019846354887553358, | |
| "loss": 0.532991886138916, | |
| "num_input_tokens_seen": 252068, | |
| "step": 76, | |
| "train_runtime": 610.0683, | |
| "train_tokens_per_second": 413.18 | |
| }, | |
| { | |
| "epoch": 0.6209677419354839, | |
| "grad_norm": 0.7212783098220825, | |
| "learning_rate": 0.00019841880992828306, | |
| "loss": 0.5575728416442871, | |
| "num_input_tokens_seen": 255328, | |
| "step": 77, | |
| "train_runtime": 616.4056, | |
| "train_tokens_per_second": 414.221 | |
| }, | |
| { | |
| "epoch": 0.6290322580645161, | |
| "grad_norm": 0.7219402194023132, | |
| "learning_rate": 0.0001983734341214244, | |
| "loss": 0.5064490437507629, | |
| "num_input_tokens_seen": 258440, | |
| "step": 78, | |
| "train_runtime": 622.5559, | |
| "train_tokens_per_second": 415.127 | |
| }, | |
| { | |
| "epoch": 0.6370967741935484, | |
| "grad_norm": 0.7140385508537292, | |
| "learning_rate": 0.00019832742174858052, | |
| "loss": 0.4704212546348572, | |
| "num_input_tokens_seen": 261670, | |
| "step": 79, | |
| "train_runtime": 628.8997, | |
| "train_tokens_per_second": 416.076 | |
| }, | |
| { | |
| "epoch": 0.6451612903225806, | |
| "grad_norm": 0.752485990524292, | |
| "learning_rate": 0.0001982807731074935, | |
| "loss": 0.5312367677688599, | |
| "num_input_tokens_seen": 265042, | |
| "step": 80, | |
| "train_runtime": 635.5329, | |
| "train_tokens_per_second": 417.039 | |
| }, | |
| { | |
| "epoch": 0.6532258064516129, | |
| "grad_norm": 0.7832441926002502, | |
| "learning_rate": 0.00019823348850002268, | |
| "loss": 0.5208355188369751, | |
| "num_input_tokens_seen": 268396, | |
| "step": 81, | |
| "train_runtime": 642.0933, | |
| "train_tokens_per_second": 418.002 | |
| }, | |
| { | |
| "epoch": 0.6612903225806451, | |
| "grad_norm": 0.8507868051528931, | |
| "learning_rate": 0.00019818556823214268, | |
| "loss": 0.5739681124687195, | |
| "num_input_tokens_seen": 271554, | |
| "step": 82, | |
| "train_runtime": 648.5667, | |
| "train_tokens_per_second": 418.699 | |
| }, | |
| { | |
| "epoch": 0.6693548387096774, | |
| "grad_norm": 0.8015562295913696, | |
| "learning_rate": 0.00019813701261394136, | |
| "loss": 0.564713180065155, | |
| "num_input_tokens_seen": 274730, | |
| "step": 83, | |
| "train_runtime": 654.8764, | |
| "train_tokens_per_second": 419.514 | |
| }, | |
| { | |
| "epoch": 0.6774193548387096, | |
| "grad_norm": 0.6441566348075867, | |
| "learning_rate": 0.00019808782195961797, | |
| "loss": 0.5123165845870972, | |
| "num_input_tokens_seen": 278100, | |
| "step": 84, | |
| "train_runtime": 661.5162, | |
| "train_tokens_per_second": 420.398 | |
| }, | |
| { | |
| "epoch": 0.6854838709677419, | |
| "grad_norm": 0.6195685267448425, | |
| "learning_rate": 0.00019803799658748094, | |
| "loss": 0.4935515522956848, | |
| "num_input_tokens_seen": 281468, | |
| "step": 85, | |
| "train_runtime": 668.1642, | |
| "train_tokens_per_second": 421.256 | |
| }, | |
| { | |
| "epoch": 0.6935483870967742, | |
| "grad_norm": 0.6841112375259399, | |
| "learning_rate": 0.000197987536819946, | |
| "loss": 0.5896198153495789, | |
| "num_input_tokens_seen": 284944, | |
| "step": 86, | |
| "train_runtime": 675.0131, | |
| "train_tokens_per_second": 422.131 | |
| }, | |
| { | |
| "epoch": 0.7016129032258065, | |
| "grad_norm": 0.661755383014679, | |
| "learning_rate": 0.0001979364429835339, | |
| "loss": 0.4884531795978546, | |
| "num_input_tokens_seen": 288252, | |
| "step": 87, | |
| "train_runtime": 681.6095, | |
| "train_tokens_per_second": 422.899 | |
| }, | |
| { | |
| "epoch": 0.7096774193548387, | |
| "grad_norm": 0.5935579538345337, | |
| "learning_rate": 0.00019788471540886844, | |
| "loss": 0.47178950905799866, | |
| "num_input_tokens_seen": 291674, | |
| "step": 88, | |
| "train_runtime": 688.3131, | |
| "train_tokens_per_second": 423.752 | |
| }, | |
| { | |
| "epoch": 0.717741935483871, | |
| "grad_norm": 0.6006376147270203, | |
| "learning_rate": 0.0001978323544306743, | |
| "loss": 0.48318639397621155, | |
| "num_input_tokens_seen": 295054, | |
| "step": 89, | |
| "train_runtime": 695.0099, | |
| "train_tokens_per_second": 424.532 | |
| }, | |
| { | |
| "epoch": 0.7258064516129032, | |
| "grad_norm": 0.8534025549888611, | |
| "learning_rate": 0.00019777936038777483, | |
| "loss": 0.5595048666000366, | |
| "num_input_tokens_seen": 298162, | |
| "step": 90, | |
| "train_runtime": 701.2865, | |
| "train_tokens_per_second": 425.164 | |
| }, | |
| { | |
| "epoch": 0.7258064516129032, | |
| "eval_loss": 2.394501209259033, | |
| "eval_runtime": 16.981, | |
| "eval_samples_per_second": 3.062, | |
| "eval_steps_per_second": 1.531, | |
| "num_input_tokens_seen": 298162, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7338709677419355, | |
| "grad_norm": 0.6207215189933777, | |
| "learning_rate": 0.0001977257336230899, | |
| "loss": 0.4640101492404938, | |
| "num_input_tokens_seen": 301500, | |
| "step": 91, | |
| "train_runtime": 729.0133, | |
| "train_tokens_per_second": 413.573 | |
| }, | |
| { | |
| "epoch": 0.7419354838709677, | |
| "grad_norm": 0.7542288899421692, | |
| "learning_rate": 0.00019767147448363366, | |
| "loss": 0.49243515729904175, | |
| "num_input_tokens_seen": 304624, | |
| "step": 92, | |
| "train_runtime": 735.2559, | |
| "train_tokens_per_second": 414.31 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.7016634941101074, | |
| "learning_rate": 0.00019761658332051235, | |
| "loss": 0.5259037017822266, | |
| "num_input_tokens_seen": 307956, | |
| "step": 93, | |
| "train_runtime": 741.7904, | |
| "train_tokens_per_second": 415.152 | |
| }, | |
| { | |
| "epoch": 0.7580645161290323, | |
| "grad_norm": 0.6728646159172058, | |
| "learning_rate": 0.00019756106048892186, | |
| "loss": 0.5248728394508362, | |
| "num_input_tokens_seen": 311354, | |
| "step": 94, | |
| "train_runtime": 748.457, | |
| "train_tokens_per_second": 415.995 | |
| }, | |
| { | |
| "epoch": 0.7661290322580645, | |
| "grad_norm": 0.723591685295105, | |
| "learning_rate": 0.00019750490634814572, | |
| "loss": 0.5338126420974731, | |
| "num_input_tokens_seen": 314592, | |
| "step": 95, | |
| "train_runtime": 754.9632, | |
| "train_tokens_per_second": 416.698 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.7161297798156738, | |
| "learning_rate": 0.00019744812126155245, | |
| "loss": 0.5010942220687866, | |
| "num_input_tokens_seen": 317960, | |
| "step": 96, | |
| "train_runtime": 761.6717, | |
| "train_tokens_per_second": 417.45 | |
| }, | |
| { | |
| "epoch": 0.782258064516129, | |
| "grad_norm": 0.6660385131835938, | |
| "learning_rate": 0.00019739070559659347, | |
| "loss": 0.526728093624115, | |
| "num_input_tokens_seen": 321274, | |
| "step": 97, | |
| "train_runtime": 768.2895, | |
| "train_tokens_per_second": 418.168 | |
| }, | |
| { | |
| "epoch": 0.7903225806451613, | |
| "grad_norm": 0.724772572517395, | |
| "learning_rate": 0.0001973326597248006, | |
| "loss": 0.548335611820221, | |
| "num_input_tokens_seen": 324480, | |
| "step": 98, | |
| "train_runtime": 774.6668, | |
| "train_tokens_per_second": 418.864 | |
| }, | |
| { | |
| "epoch": 0.7983870967741935, | |
| "grad_norm": 0.6925802230834961, | |
| "learning_rate": 0.0001972739840217836, | |
| "loss": 0.4738383889198303, | |
| "num_input_tokens_seen": 327678, | |
| "step": 99, | |
| "train_runtime": 781.1283, | |
| "train_tokens_per_second": 419.493 | |
| }, | |
| { | |
| "epoch": 0.8064516129032258, | |
| "grad_norm": 0.6755756139755249, | |
| "learning_rate": 0.00019721467886722792, | |
| "loss": 0.5126165151596069, | |
| "num_input_tokens_seen": 330914, | |
| "step": 100, | |
| "train_runtime": 787.5258, | |
| "train_tokens_per_second": 420.195 | |
| }, | |
| { | |
| "epoch": 0.8145161290322581, | |
| "grad_norm": 0.7228033542633057, | |
| "learning_rate": 0.00019715474464489208, | |
| "loss": 0.51287442445755, | |
| "num_input_tokens_seen": 334256, | |
| "step": 101, | |
| "train_runtime": 794.2459, | |
| "train_tokens_per_second": 420.847 | |
| }, | |
| { | |
| "epoch": 0.8225806451612904, | |
| "grad_norm": 0.636013925075531, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.5042312741279602, | |
| "num_input_tokens_seen": 337722, | |
| "step": 102, | |
| "train_runtime": 800.8987, | |
| "train_tokens_per_second": 421.679 | |
| }, | |
| { | |
| "epoch": 0.8306451612903226, | |
| "grad_norm": 0.64854496717453, | |
| "learning_rate": 0.00019703299055226468, | |
| "loss": 0.49396568536758423, | |
| "num_input_tokens_seen": 341038, | |
| "step": 103, | |
| "train_runtime": 807.5236, | |
| "train_tokens_per_second": 422.326 | |
| }, | |
| { | |
| "epoch": 0.8387096774193549, | |
| "grad_norm": 0.7666099667549133, | |
| "learning_rate": 0.00019697117146983334, | |
| "loss": 0.5051327347755432, | |
| "num_input_tokens_seen": 344066, | |
| "step": 104, | |
| "train_runtime": 813.5636, | |
| "train_tokens_per_second": 422.912 | |
| }, | |
| { | |
| "epoch": 0.8467741935483871, | |
| "grad_norm": 0.7877888679504395, | |
| "learning_rate": 0.0001969087248953371, | |
| "loss": 0.5758072137832642, | |
| "num_input_tokens_seen": 347352, | |
| "step": 105, | |
| "train_runtime": 820.2344, | |
| "train_tokens_per_second": 423.479 | |
| }, | |
| { | |
| "epoch": 0.8548387096774194, | |
| "grad_norm": 0.6786578893661499, | |
| "learning_rate": 0.00019684565123286244, | |
| "loss": 0.4985409080982208, | |
| "num_input_tokens_seen": 350654, | |
| "step": 106, | |
| "train_runtime": 826.7619, | |
| "train_tokens_per_second": 424.129 | |
| }, | |
| { | |
| "epoch": 0.8629032258064516, | |
| "grad_norm": 0.7095152735710144, | |
| "learning_rate": 0.00019678195089055346, | |
| "loss": 0.5382249355316162, | |
| "num_input_tokens_seen": 353954, | |
| "step": 107, | |
| "train_runtime": 833.2825, | |
| "train_tokens_per_second": 424.771 | |
| }, | |
| { | |
| "epoch": 0.8709677419354839, | |
| "grad_norm": 0.6485514044761658, | |
| "learning_rate": 0.00019671762428060966, | |
| "loss": 0.5011004209518433, | |
| "num_input_tokens_seen": 357348, | |
| "step": 108, | |
| "train_runtime": 839.895, | |
| "train_tokens_per_second": 425.467 | |
| }, | |
| { | |
| "epoch": 0.8790322580645161, | |
| "grad_norm": 0.6399499773979187, | |
| "learning_rate": 0.00019665267181928292, | |
| "loss": 0.5171963572502136, | |
| "num_input_tokens_seen": 360628, | |
| "step": 109, | |
| "train_runtime": 846.4457, | |
| "train_tokens_per_second": 426.05 | |
| }, | |
| { | |
| "epoch": 0.8870967741935484, | |
| "grad_norm": 0.6398491263389587, | |
| "learning_rate": 0.00019658709392687506, | |
| "loss": 0.5169506669044495, | |
| "num_input_tokens_seen": 364030, | |
| "step": 110, | |
| "train_runtime": 853.0569, | |
| "train_tokens_per_second": 426.736 | |
| }, | |
| { | |
| "epoch": 0.8951612903225806, | |
| "grad_norm": 0.6788223385810852, | |
| "learning_rate": 0.00019652089102773488, | |
| "loss": 0.5841289758682251, | |
| "num_input_tokens_seen": 367360, | |
| "step": 111, | |
| "train_runtime": 859.6357, | |
| "train_tokens_per_second": 427.344 | |
| }, | |
| { | |
| "epoch": 0.9032258064516129, | |
| "grad_norm": 0.6092165112495422, | |
| "learning_rate": 0.00019645406355025565, | |
| "loss": 0.4721071720123291, | |
| "num_input_tokens_seen": 370518, | |
| "step": 112, | |
| "train_runtime": 865.9187, | |
| "train_tokens_per_second": 427.89 | |
| }, | |
| { | |
| "epoch": 0.9112903225806451, | |
| "grad_norm": 0.5953733325004578, | |
| "learning_rate": 0.00019638661192687216, | |
| "loss": 0.4920331835746765, | |
| "num_input_tokens_seen": 373828, | |
| "step": 113, | |
| "train_runtime": 872.4705, | |
| "train_tokens_per_second": 428.471 | |
| }, | |
| { | |
| "epoch": 0.9193548387096774, | |
| "grad_norm": 0.6158846020698547, | |
| "learning_rate": 0.00019631853659405807, | |
| "loss": 0.5007290840148926, | |
| "num_input_tokens_seen": 377226, | |
| "step": 114, | |
| "train_runtime": 879.1582, | |
| "train_tokens_per_second": 429.076 | |
| }, | |
| { | |
| "epoch": 0.9274193548387096, | |
| "grad_norm": 0.5616441369056702, | |
| "learning_rate": 0.000196249837992323, | |
| "loss": 0.4844634234905243, | |
| "num_input_tokens_seen": 380624, | |
| "step": 115, | |
| "train_runtime": 885.8971, | |
| "train_tokens_per_second": 429.648 | |
| }, | |
| { | |
| "epoch": 0.9354838709677419, | |
| "grad_norm": 0.616858184337616, | |
| "learning_rate": 0.0001961805165662096, | |
| "loss": 0.4595881402492523, | |
| "num_input_tokens_seen": 384012, | |
| "step": 116, | |
| "train_runtime": 892.5519, | |
| "train_tokens_per_second": 430.241 | |
| }, | |
| { | |
| "epoch": 0.9435483870967742, | |
| "grad_norm": 0.6438707113265991, | |
| "learning_rate": 0.00019611057276429085, | |
| "loss": 0.5118931531906128, | |
| "num_input_tokens_seen": 387364, | |
| "step": 117, | |
| "train_runtime": 899.1551, | |
| "train_tokens_per_second": 430.809 | |
| }, | |
| { | |
| "epoch": 0.9516129032258065, | |
| "grad_norm": 0.6319488883018494, | |
| "learning_rate": 0.00019604000703916705, | |
| "loss": 0.479214072227478, | |
| "num_input_tokens_seen": 390740, | |
| "step": 118, | |
| "train_runtime": 905.8859, | |
| "train_tokens_per_second": 431.335 | |
| }, | |
| { | |
| "epoch": 0.9596774193548387, | |
| "grad_norm": 0.7468289136886597, | |
| "learning_rate": 0.00019596881984746287, | |
| "loss": 0.49020278453826904, | |
| "num_input_tokens_seen": 394002, | |
| "step": 119, | |
| "train_runtime": 912.4634, | |
| "train_tokens_per_second": 431.8 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "grad_norm": 0.795864462852478, | |
| "learning_rate": 0.00019589701164982452, | |
| "loss": 0.49333739280700684, | |
| "num_input_tokens_seen": 397036, | |
| "step": 120, | |
| "train_runtime": 918.6599, | |
| "train_tokens_per_second": 432.19 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "eval_loss": 2.3108139038085938, | |
| "eval_runtime": 17.0317, | |
| "eval_samples_per_second": 3.053, | |
| "eval_steps_per_second": 1.527, | |
| "num_input_tokens_seen": 397036, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.9758064516129032, | |
| "grad_norm": 0.7513642907142639, | |
| "learning_rate": 0.00019582458291091663, | |
| "loss": 0.5653488636016846, | |
| "num_input_tokens_seen": 400216, | |
| "step": 121, | |
| "train_runtime": 946.0725, | |
| "train_tokens_per_second": 423.029 | |
| }, | |
| { | |
| "epoch": 0.9838709677419355, | |
| "grad_norm": 0.6150530576705933, | |
| "learning_rate": 0.0001957515340994193, | |
| "loss": 0.48984086513519287, | |
| "num_input_tokens_seen": 403522, | |
| "step": 122, | |
| "train_runtime": 952.5907, | |
| "train_tokens_per_second": 423.605 | |
| }, | |
| { | |
| "epoch": 0.9919354838709677, | |
| "grad_norm": 0.6230205297470093, | |
| "learning_rate": 0.000195677865688025, | |
| "loss": 0.52336186170578, | |
| "num_input_tokens_seen": 406874, | |
| "step": 123, | |
| "train_runtime": 959.2256, | |
| "train_tokens_per_second": 424.169 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.684869110584259, | |
| "learning_rate": 0.00019560357815343577, | |
| "loss": 0.4886379539966583, | |
| "num_input_tokens_seen": 410114, | |
| "step": 124, | |
| "train_runtime": 965.6844, | |
| "train_tokens_per_second": 424.687 | |
| }, | |
| { | |
| "epoch": 1.0080645161290323, | |
| "grad_norm": 0.597822904586792, | |
| "learning_rate": 0.00019552867197635974, | |
| "loss": 0.41038113832473755, | |
| "num_input_tokens_seen": 413264, | |
| "step": 125, | |
| "train_runtime": 972.0355, | |
| "train_tokens_per_second": 425.153 | |
| }, | |
| { | |
| "epoch": 1.0161290322580645, | |
| "grad_norm": 0.6053985357284546, | |
| "learning_rate": 0.00019545314764150837, | |
| "loss": 0.3999386131763458, | |
| "num_input_tokens_seen": 416432, | |
| "step": 126, | |
| "train_runtime": 978.3998, | |
| "train_tokens_per_second": 425.626 | |
| }, | |
| { | |
| "epoch": 1.0241935483870968, | |
| "grad_norm": 0.5770310759544373, | |
| "learning_rate": 0.00019537700563759304, | |
| "loss": 0.43007850646972656, | |
| "num_input_tokens_seen": 419814, | |
| "step": 127, | |
| "train_runtime": 985.1414, | |
| "train_tokens_per_second": 426.146 | |
| }, | |
| { | |
| "epoch": 1.032258064516129, | |
| "grad_norm": 0.6475788354873657, | |
| "learning_rate": 0.00019530024645732206, | |
| "loss": 0.4416751563549042, | |
| "num_input_tokens_seen": 423168, | |
| "step": 128, | |
| "train_runtime": 991.8066, | |
| "train_tokens_per_second": 426.664 | |
| }, | |
| { | |
| "epoch": 1.0403225806451613, | |
| "grad_norm": 0.6236942410469055, | |
| "learning_rate": 0.00019522287059739753, | |
| "loss": 0.4056033790111542, | |
| "num_input_tokens_seen": 426248, | |
| "step": 129, | |
| "train_runtime": 997.974, | |
| "train_tokens_per_second": 427.113 | |
| }, | |
| { | |
| "epoch": 1.0483870967741935, | |
| "grad_norm": 0.6982079148292542, | |
| "learning_rate": 0.00019514487855851184, | |
| "loss": 0.4574550986289978, | |
| "num_input_tokens_seen": 429726, | |
| "step": 130, | |
| "train_runtime": 1004.7068, | |
| "train_tokens_per_second": 427.713 | |
| }, | |
| { | |
| "epoch": 1.0564516129032258, | |
| "grad_norm": 0.6114121079444885, | |
| "learning_rate": 0.00019506627084534483, | |
| "loss": 0.4151981472969055, | |
| "num_input_tokens_seen": 432912, | |
| "step": 131, | |
| "train_runtime": 1011.1009, | |
| "train_tokens_per_second": 428.159 | |
| }, | |
| { | |
| "epoch": 1.064516129032258, | |
| "grad_norm": 0.6755998730659485, | |
| "learning_rate": 0.00019498704796656018, | |
| "loss": 0.4350915551185608, | |
| "num_input_tokens_seen": 436246, | |
| "step": 132, | |
| "train_runtime": 1017.7642, | |
| "train_tokens_per_second": 428.632 | |
| }, | |
| { | |
| "epoch": 1.0725806451612903, | |
| "grad_norm": 0.7091481685638428, | |
| "learning_rate": 0.00019490721043480226, | |
| "loss": 0.44581809639930725, | |
| "num_input_tokens_seen": 439446, | |
| "step": 133, | |
| "train_runtime": 1024.1345, | |
| "train_tokens_per_second": 429.09 | |
| }, | |
| { | |
| "epoch": 1.0806451612903225, | |
| "grad_norm": 0.6453033685684204, | |
| "learning_rate": 0.00019482675876669286, | |
| "loss": 0.41440466046333313, | |
| "num_input_tokens_seen": 442716, | |
| "step": 134, | |
| "train_runtime": 1030.6631, | |
| "train_tokens_per_second": 429.545 | |
| }, | |
| { | |
| "epoch": 1.0887096774193548, | |
| "grad_norm": 0.6018978357315063, | |
| "learning_rate": 0.00019474569348282774, | |
| "loss": 0.41350579261779785, | |
| "num_input_tokens_seen": 445948, | |
| "step": 135, | |
| "train_runtime": 1037.0128, | |
| "train_tokens_per_second": 430.031 | |
| }, | |
| { | |
| "epoch": 1.096774193548387, | |
| "grad_norm": 0.7258074879646301, | |
| "learning_rate": 0.0001946640151077734, | |
| "loss": 0.44569528102874756, | |
| "num_input_tokens_seen": 449172, | |
| "step": 136, | |
| "train_runtime": 1043.4434, | |
| "train_tokens_per_second": 430.471 | |
| }, | |
| { | |
| "epoch": 1.1048387096774193, | |
| "grad_norm": 0.7976507544517517, | |
| "learning_rate": 0.00019458172417006347, | |
| "loss": 0.5195361375808716, | |
| "num_input_tokens_seen": 452512, | |
| "step": 137, | |
| "train_runtime": 1050.0077, | |
| "train_tokens_per_second": 430.961 | |
| }, | |
| { | |
| "epoch": 1.1129032258064515, | |
| "grad_norm": 0.7825067639350891, | |
| "learning_rate": 0.00019449882120219555, | |
| "loss": 0.44283729791641235, | |
| "num_input_tokens_seen": 455922, | |
| "step": 138, | |
| "train_runtime": 1056.6883, | |
| "train_tokens_per_second": 431.463 | |
| }, | |
| { | |
| "epoch": 1.120967741935484, | |
| "grad_norm": 0.66150963306427, | |
| "learning_rate": 0.00019441530674062753, | |
| "loss": 0.42789438366889954, | |
| "num_input_tokens_seen": 459246, | |
| "step": 139, | |
| "train_runtime": 1063.2307, | |
| "train_tokens_per_second": 431.934 | |
| }, | |
| { | |
| "epoch": 1.129032258064516, | |
| "grad_norm": 0.645460307598114, | |
| "learning_rate": 0.0001943311813257743, | |
| "loss": 0.38796648383140564, | |
| "num_input_tokens_seen": 462644, | |
| "step": 140, | |
| "train_runtime": 1069.8507, | |
| "train_tokens_per_second": 432.438 | |
| }, | |
| { | |
| "epoch": 1.1370967741935485, | |
| "grad_norm": 0.6324282884597778, | |
| "learning_rate": 0.00019424644550200415, | |
| "loss": 0.43011078238487244, | |
| "num_input_tokens_seen": 466004, | |
| "step": 141, | |
| "train_runtime": 1076.4369, | |
| "train_tokens_per_second": 432.913 | |
| }, | |
| { | |
| "epoch": 1.1451612903225807, | |
| "grad_norm": 0.6442665457725525, | |
| "learning_rate": 0.00019416109981763526, | |
| "loss": 0.4545246958732605, | |
| "num_input_tokens_seen": 469474, | |
| "step": 142, | |
| "train_runtime": 1083.2686, | |
| "train_tokens_per_second": 433.386 | |
| }, | |
| { | |
| "epoch": 1.153225806451613, | |
| "grad_norm": 0.6576758623123169, | |
| "learning_rate": 0.00019407514482493214, | |
| "loss": 0.4253957271575928, | |
| "num_input_tokens_seen": 472830, | |
| "step": 143, | |
| "train_runtime": 1089.8639, | |
| "train_tokens_per_second": 433.843 | |
| }, | |
| { | |
| "epoch": 1.1612903225806452, | |
| "grad_norm": 0.7580392956733704, | |
| "learning_rate": 0.00019398858108010217, | |
| "loss": 0.45867177844047546, | |
| "num_input_tokens_seen": 476146, | |
| "step": 144, | |
| "train_runtime": 1096.4187, | |
| "train_tokens_per_second": 434.274 | |
| }, | |
| { | |
| "epoch": 1.1693548387096775, | |
| "grad_norm": 0.7474371790885925, | |
| "learning_rate": 0.0001939014091432918, | |
| "loss": 0.46455514430999756, | |
| "num_input_tokens_seen": 479388, | |
| "step": 145, | |
| "train_runtime": 1102.8261, | |
| "train_tokens_per_second": 434.69 | |
| }, | |
| { | |
| "epoch": 1.1774193548387097, | |
| "grad_norm": 0.636562168598175, | |
| "learning_rate": 0.00019381362957858312, | |
| "loss": 0.4370546340942383, | |
| "num_input_tokens_seen": 482820, | |
| "step": 146, | |
| "train_runtime": 1109.5311, | |
| "train_tokens_per_second": 435.157 | |
| }, | |
| { | |
| "epoch": 1.185483870967742, | |
| "grad_norm": 0.6858648061752319, | |
| "learning_rate": 0.00019372524295399013, | |
| "loss": 0.3828548491001129, | |
| "num_input_tokens_seen": 485956, | |
| "step": 147, | |
| "train_runtime": 1115.864, | |
| "train_tokens_per_second": 435.498 | |
| }, | |
| { | |
| "epoch": 1.1935483870967742, | |
| "grad_norm": 0.7505737543106079, | |
| "learning_rate": 0.00019363624984145502, | |
| "loss": 0.43668264150619507, | |
| "num_input_tokens_seen": 489266, | |
| "step": 148, | |
| "train_runtime": 1122.4445, | |
| "train_tokens_per_second": 435.893 | |
| }, | |
| { | |
| "epoch": 1.2016129032258065, | |
| "grad_norm": 0.6092221140861511, | |
| "learning_rate": 0.00019354665081684446, | |
| "loss": 0.36623674631118774, | |
| "num_input_tokens_seen": 492712, | |
| "step": 149, | |
| "train_runtime": 1129.2289, | |
| "train_tokens_per_second": 436.326 | |
| }, | |
| { | |
| "epoch": 1.2096774193548387, | |
| "grad_norm": 0.6618177890777588, | |
| "learning_rate": 0.0001934564464599461, | |
| "loss": 0.36393943428993225, | |
| "num_input_tokens_seen": 496182, | |
| "step": 150, | |
| "train_runtime": 1135.9402, | |
| "train_tokens_per_second": 436.803 | |
| }, | |
| { | |
| "epoch": 1.2096774193548387, | |
| "eval_loss": 2.468383550643921, | |
| "eval_runtime": 16.9717, | |
| "eval_samples_per_second": 3.064, | |
| "eval_steps_per_second": 1.532, | |
| "num_input_tokens_seen": 496182, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.217741935483871, | |
| "grad_norm": 0.7288278341293335, | |
| "learning_rate": 0.00019336563735446446, | |
| "loss": 0.47049954533576965, | |
| "num_input_tokens_seen": 499482, | |
| "step": 151, | |
| "train_runtime": 1163.8126, | |
| "train_tokens_per_second": 429.177 | |
| }, | |
| { | |
| "epoch": 1.2258064516129032, | |
| "grad_norm": 0.6693354845046997, | |
| "learning_rate": 0.00019327422408801744, | |
| "loss": 0.4141227900981903, | |
| "num_input_tokens_seen": 502832, | |
| "step": 152, | |
| "train_runtime": 1170.3921, | |
| "train_tokens_per_second": 429.627 | |
| }, | |
| { | |
| "epoch": 1.2338709677419355, | |
| "grad_norm": 0.7173429727554321, | |
| "learning_rate": 0.0001931822072521323, | |
| "loss": 0.4298741817474365, | |
| "num_input_tokens_seen": 506196, | |
| "step": 153, | |
| "train_runtime": 1176.9716, | |
| "train_tokens_per_second": 430.083 | |
| }, | |
| { | |
| "epoch": 1.2419354838709677, | |
| "grad_norm": 0.7945153117179871, | |
| "learning_rate": 0.00019308958744224217, | |
| "loss": 0.4285031855106354, | |
| "num_input_tokens_seen": 509348, | |
| "step": 154, | |
| "train_runtime": 1183.3919, | |
| "train_tokens_per_second": 430.414 | |
| }, | |
| { | |
| "epoch": 1.25, | |
| "grad_norm": 0.6567854285240173, | |
| "learning_rate": 0.00019299636525768173, | |
| "loss": 0.40128999948501587, | |
| "num_input_tokens_seen": 512728, | |
| "step": 155, | |
| "train_runtime": 1190.0997, | |
| "train_tokens_per_second": 430.828 | |
| }, | |
| { | |
| "epoch": 1.2580645161290323, | |
| "grad_norm": 0.6827821135520935, | |
| "learning_rate": 0.00019290254130168374, | |
| "loss": 0.3844904899597168, | |
| "num_input_tokens_seen": 516078, | |
| "step": 156, | |
| "train_runtime": 1196.7623, | |
| "train_tokens_per_second": 431.229 | |
| }, | |
| { | |
| "epoch": 1.2661290322580645, | |
| "grad_norm": 0.6366832256317139, | |
| "learning_rate": 0.00019280811618137484, | |
| "loss": 0.42982959747314453, | |
| "num_input_tokens_seen": 519482, | |
| "step": 157, | |
| "train_runtime": 1203.4902, | |
| "train_tokens_per_second": 431.646 | |
| }, | |
| { | |
| "epoch": 1.2741935483870968, | |
| "grad_norm": 0.6760056614875793, | |
| "learning_rate": 0.00019271309050777183, | |
| "loss": 0.4195765256881714, | |
| "num_input_tokens_seen": 522758, | |
| "step": 158, | |
| "train_runtime": 1209.9586, | |
| "train_tokens_per_second": 432.046 | |
| }, | |
| { | |
| "epoch": 1.282258064516129, | |
| "grad_norm": 0.7459661960601807, | |
| "learning_rate": 0.00019261746489577765, | |
| "loss": 0.4203264117240906, | |
| "num_input_tokens_seen": 525784, | |
| "step": 159, | |
| "train_runtime": 1216.0785, | |
| "train_tokens_per_second": 432.36 | |
| }, | |
| { | |
| "epoch": 1.2903225806451613, | |
| "grad_norm": 0.5943926572799683, | |
| "learning_rate": 0.00019252123996417738, | |
| "loss": 0.3937755525112152, | |
| "num_input_tokens_seen": 529130, | |
| "step": 160, | |
| "train_runtime": 1222.6742, | |
| "train_tokens_per_second": 432.765 | |
| }, | |
| { | |
| "epoch": 1.2983870967741935, | |
| "grad_norm": 0.6527149677276611, | |
| "learning_rate": 0.00019242441633563417, | |
| "loss": 0.4311143755912781, | |
| "num_input_tokens_seen": 532308, | |
| "step": 161, | |
| "train_runtime": 1229.0914, | |
| "train_tokens_per_second": 433.091 | |
| }, | |
| { | |
| "epoch": 1.3064516129032258, | |
| "grad_norm": 0.6006942987442017, | |
| "learning_rate": 0.00019232699463668542, | |
| "loss": 0.4009702205657959, | |
| "num_input_tokens_seen": 535662, | |
| "step": 162, | |
| "train_runtime": 1235.7182, | |
| "train_tokens_per_second": 433.482 | |
| }, | |
| { | |
| "epoch": 1.314516129032258, | |
| "grad_norm": 0.708247721195221, | |
| "learning_rate": 0.00019222897549773848, | |
| "loss": 0.4113525152206421, | |
| "num_input_tokens_seen": 539056, | |
| "step": 163, | |
| "train_runtime": 1242.3294, | |
| "train_tokens_per_second": 433.907 | |
| }, | |
| { | |
| "epoch": 1.3225806451612903, | |
| "grad_norm": 0.5651199221611023, | |
| "learning_rate": 0.0001921303595530667, | |
| "loss": 0.36679160594940186, | |
| "num_input_tokens_seen": 542450, | |
| "step": 164, | |
| "train_runtime": 1248.9434, | |
| "train_tokens_per_second": 434.327 | |
| }, | |
| { | |
| "epoch": 1.3306451612903225, | |
| "grad_norm": 0.7649331092834473, | |
| "learning_rate": 0.00019203114744080542, | |
| "loss": 0.449223130941391, | |
| "num_input_tokens_seen": 545796, | |
| "step": 165, | |
| "train_runtime": 1255.5695, | |
| "train_tokens_per_second": 434.7 | |
| }, | |
| { | |
| "epoch": 1.3387096774193548, | |
| "grad_norm": 0.7255364656448364, | |
| "learning_rate": 0.0001919313398029475, | |
| "loss": 0.4195847511291504, | |
| "num_input_tokens_seen": 548960, | |
| "step": 166, | |
| "train_runtime": 1261.8368, | |
| "train_tokens_per_second": 435.048 | |
| }, | |
| { | |
| "epoch": 1.346774193548387, | |
| "grad_norm": 0.7223755717277527, | |
| "learning_rate": 0.00019183093728533966, | |
| "loss": 0.41058725118637085, | |
| "num_input_tokens_seen": 552310, | |
| "step": 167, | |
| "train_runtime": 1268.4105, | |
| "train_tokens_per_second": 435.435 | |
| }, | |
| { | |
| "epoch": 1.3548387096774195, | |
| "grad_norm": 0.6943632364273071, | |
| "learning_rate": 0.00019172994053767784, | |
| "loss": 0.41625842452049255, | |
| "num_input_tokens_seen": 555660, | |
| "step": 168, | |
| "train_runtime": 1274.9504, | |
| "train_tokens_per_second": 435.829 | |
| }, | |
| { | |
| "epoch": 1.3629032258064515, | |
| "grad_norm": 0.7306869626045227, | |
| "learning_rate": 0.0001916283502135033, | |
| "loss": 0.4193657636642456, | |
| "num_input_tokens_seen": 558942, | |
| "step": 169, | |
| "train_runtime": 1281.4937, | |
| "train_tokens_per_second": 436.164 | |
| }, | |
| { | |
| "epoch": 1.370967741935484, | |
| "grad_norm": 0.9073975682258606, | |
| "learning_rate": 0.00019152616697019822, | |
| "loss": 0.48369550704956055, | |
| "num_input_tokens_seen": 561914, | |
| "step": 170, | |
| "train_runtime": 1287.5106, | |
| "train_tokens_per_second": 436.434 | |
| }, | |
| { | |
| "epoch": 1.379032258064516, | |
| "grad_norm": 0.6838721632957458, | |
| "learning_rate": 0.0001914233914689815, | |
| "loss": 0.44988489151000977, | |
| "num_input_tokens_seen": 565128, | |
| "step": 171, | |
| "train_runtime": 1293.994, | |
| "train_tokens_per_second": 436.732 | |
| }, | |
| { | |
| "epoch": 1.3870967741935485, | |
| "grad_norm": 0.7812486886978149, | |
| "learning_rate": 0.00019132002437490458, | |
| "loss": 0.40069717168807983, | |
| "num_input_tokens_seen": 568492, | |
| "step": 172, | |
| "train_runtime": 1300.6183, | |
| "train_tokens_per_second": 437.094 | |
| }, | |
| { | |
| "epoch": 1.3951612903225805, | |
| "grad_norm": 0.7606605291366577, | |
| "learning_rate": 0.00019121606635684696, | |
| "loss": 0.46690768003463745, | |
| "num_input_tokens_seen": 571838, | |
| "step": 173, | |
| "train_runtime": 1307.2362, | |
| "train_tokens_per_second": 437.44 | |
| }, | |
| { | |
| "epoch": 1.403225806451613, | |
| "grad_norm": 0.6010671854019165, | |
| "learning_rate": 0.00019111151808751196, | |
| "loss": 0.36060816049575806, | |
| "num_input_tokens_seen": 575172, | |
| "step": 174, | |
| "train_runtime": 1313.8279, | |
| "train_tokens_per_second": 437.783 | |
| }, | |
| { | |
| "epoch": 1.4112903225806452, | |
| "grad_norm": 0.7686548829078674, | |
| "learning_rate": 0.00019100638024342244, | |
| "loss": 0.42185837030410767, | |
| "num_input_tokens_seen": 578472, | |
| "step": 175, | |
| "train_runtime": 1320.4302, | |
| "train_tokens_per_second": 438.094 | |
| }, | |
| { | |
| "epoch": 1.4193548387096775, | |
| "grad_norm": 0.7026260495185852, | |
| "learning_rate": 0.00019090065350491626, | |
| "loss": 0.4178864061832428, | |
| "num_input_tokens_seen": 581854, | |
| "step": 176, | |
| "train_runtime": 1327.0726, | |
| "train_tokens_per_second": 438.449 | |
| }, | |
| { | |
| "epoch": 1.4274193548387097, | |
| "grad_norm": 0.64774090051651, | |
| "learning_rate": 0.00019079433855614201, | |
| "loss": 0.40213117003440857, | |
| "num_input_tokens_seen": 585240, | |
| "step": 177, | |
| "train_runtime": 1333.7896, | |
| "train_tokens_per_second": 438.78 | |
| }, | |
| { | |
| "epoch": 1.435483870967742, | |
| "grad_norm": 0.7670486569404602, | |
| "learning_rate": 0.00019068743608505455, | |
| "loss": 0.4300892651081085, | |
| "num_input_tokens_seen": 588466, | |
| "step": 178, | |
| "train_runtime": 1340.1622, | |
| "train_tokens_per_second": 439.101 | |
| }, | |
| { | |
| "epoch": 1.4435483870967742, | |
| "grad_norm": 0.7370812296867371, | |
| "learning_rate": 0.0001905799467834105, | |
| "loss": 0.4132138788700104, | |
| "num_input_tokens_seen": 591716, | |
| "step": 179, | |
| "train_runtime": 1346.5699, | |
| "train_tokens_per_second": 439.425 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "grad_norm": 0.6373615860939026, | |
| "learning_rate": 0.00019047187134676387, | |
| "loss": 0.4021753668785095, | |
| "num_input_tokens_seen": 595124, | |
| "step": 180, | |
| "train_runtime": 1353.3295, | |
| "train_tokens_per_second": 439.748 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "eval_loss": 2.275111675262451, | |
| "eval_runtime": 17.0147, | |
| "eval_samples_per_second": 3.056, | |
| "eval_steps_per_second": 1.528, | |
| "num_input_tokens_seen": 595124, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.4596774193548387, | |
| "grad_norm": 0.6791172623634338, | |
| "learning_rate": 0.0001903632104744614, | |
| "loss": 0.4088537395000458, | |
| "num_input_tokens_seen": 598560, | |
| "step": 181, | |
| "train_runtime": 1383.6055, | |
| "train_tokens_per_second": 432.609 | |
| }, | |
| { | |
| "epoch": 1.467741935483871, | |
| "grad_norm": 0.8019388318061829, | |
| "learning_rate": 0.00019025396486963827, | |
| "loss": 0.43525320291519165, | |
| "num_input_tokens_seen": 601832, | |
| "step": 182, | |
| "train_runtime": 1390.1876, | |
| "train_tokens_per_second": 432.914 | |
| }, | |
| { | |
| "epoch": 1.4758064516129032, | |
| "grad_norm": 0.7230949997901917, | |
| "learning_rate": 0.0001901441352392133, | |
| "loss": 0.4377875030040741, | |
| "num_input_tokens_seen": 605124, | |
| "step": 183, | |
| "train_runtime": 1396.7627, | |
| "train_tokens_per_second": 433.233 | |
| }, | |
| { | |
| "epoch": 1.4838709677419355, | |
| "grad_norm": 0.7066268920898438, | |
| "learning_rate": 0.00019003372229388452, | |
| "loss": 0.4358859956264496, | |
| "num_input_tokens_seen": 608550, | |
| "step": 184, | |
| "train_runtime": 1403.4877, | |
| "train_tokens_per_second": 433.598 | |
| }, | |
| { | |
| "epoch": 1.4919354838709677, | |
| "grad_norm": 0.6805543899536133, | |
| "learning_rate": 0.0001899227267481246, | |
| "loss": 0.4511941969394684, | |
| "num_input_tokens_seen": 611912, | |
| "step": 185, | |
| "train_runtime": 1410.0797, | |
| "train_tokens_per_second": 433.956 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "grad_norm": 0.7089034914970398, | |
| "learning_rate": 0.00018981114932017609, | |
| "loss": 0.4455965757369995, | |
| "num_input_tokens_seen": 615114, | |
| "step": 186, | |
| "train_runtime": 1416.5446, | |
| "train_tokens_per_second": 434.236 | |
| }, | |
| { | |
| "epoch": 1.5080645161290323, | |
| "grad_norm": 0.6060784459114075, | |
| "learning_rate": 0.00018969899073204686, | |
| "loss": 0.40845364332199097, | |
| "num_input_tokens_seen": 618532, | |
| "step": 187, | |
| "train_runtime": 1423.1876, | |
| "train_tokens_per_second": 434.61 | |
| }, | |
| { | |
| "epoch": 1.5161290322580645, | |
| "grad_norm": 0.6854289174079895, | |
| "learning_rate": 0.00018958625170950545, | |
| "loss": 0.43267232179641724, | |
| "num_input_tokens_seen": 621584, | |
| "step": 188, | |
| "train_runtime": 1429.4206, | |
| "train_tokens_per_second": 434.85 | |
| }, | |
| { | |
| "epoch": 1.5241935483870968, | |
| "grad_norm": 0.641149640083313, | |
| "learning_rate": 0.00018947293298207635, | |
| "loss": 0.44395285844802856, | |
| "num_input_tokens_seen": 624890, | |
| "step": 189, | |
| "train_runtime": 1435.9579, | |
| "train_tokens_per_second": 435.173 | |
| }, | |
| { | |
| "epoch": 1.532258064516129, | |
| "grad_norm": 0.761741578578949, | |
| "learning_rate": 0.00018935903528303523, | |
| "loss": 0.44854938983917236, | |
| "num_input_tokens_seen": 627898, | |
| "step": 190, | |
| "train_runtime": 1442.0928, | |
| "train_tokens_per_second": 435.407 | |
| }, | |
| { | |
| "epoch": 1.5403225806451613, | |
| "grad_norm": 0.6175191402435303, | |
| "learning_rate": 0.0001892445593494042, | |
| "loss": 0.38872429728507996, | |
| "num_input_tokens_seen": 631260, | |
| "step": 191, | |
| "train_runtime": 1448.6619, | |
| "train_tokens_per_second": 435.754 | |
| }, | |
| { | |
| "epoch": 1.5483870967741935, | |
| "grad_norm": 0.6766597032546997, | |
| "learning_rate": 0.0001891295059219472, | |
| "loss": 0.39698436856269836, | |
| "num_input_tokens_seen": 634598, | |
| "step": 192, | |
| "train_runtime": 1455.2728, | |
| "train_tokens_per_second": 436.068 | |
| }, | |
| { | |
| "epoch": 1.5564516129032258, | |
| "grad_norm": 0.7066875100135803, | |
| "learning_rate": 0.00018901387574516497, | |
| "loss": 0.4259159564971924, | |
| "num_input_tokens_seen": 637776, | |
| "step": 193, | |
| "train_runtime": 1461.5701, | |
| "train_tokens_per_second": 436.364 | |
| }, | |
| { | |
| "epoch": 1.564516129032258, | |
| "grad_norm": 0.7477712035179138, | |
| "learning_rate": 0.00018889766956729044, | |
| "loss": 0.41065987944602966, | |
| "num_input_tokens_seen": 641100, | |
| "step": 194, | |
| "train_runtime": 1468.1552, | |
| "train_tokens_per_second": 436.67 | |
| }, | |
| { | |
| "epoch": 1.5725806451612905, | |
| "grad_norm": 0.7463842630386353, | |
| "learning_rate": 0.00018878088814028364, | |
| "loss": 0.42325031757354736, | |
| "num_input_tokens_seen": 644472, | |
| "step": 195, | |
| "train_runtime": 1474.7266, | |
| "train_tokens_per_second": 437.011 | |
| }, | |
| { | |
| "epoch": 1.5806451612903225, | |
| "grad_norm": 0.6973960399627686, | |
| "learning_rate": 0.00018866353221982718, | |
| "loss": 0.36401230096817017, | |
| "num_input_tokens_seen": 647738, | |
| "step": 196, | |
| "train_runtime": 1481.2508, | |
| "train_tokens_per_second": 437.291 | |
| }, | |
| { | |
| "epoch": 1.588709677419355, | |
| "grad_norm": 0.7673096656799316, | |
| "learning_rate": 0.000188545602565321, | |
| "loss": 0.4327010214328766, | |
| "num_input_tokens_seen": 651030, | |
| "step": 197, | |
| "train_runtime": 1487.7683, | |
| "train_tokens_per_second": 437.588 | |
| }, | |
| { | |
| "epoch": 1.596774193548387, | |
| "grad_norm": 0.7988507151603699, | |
| "learning_rate": 0.00018842709993987776, | |
| "loss": 0.4233095347881317, | |
| "num_input_tokens_seen": 654362, | |
| "step": 198, | |
| "train_runtime": 1494.4203, | |
| "train_tokens_per_second": 437.87 | |
| }, | |
| { | |
| "epoch": 1.6048387096774195, | |
| "grad_norm": 0.764127254486084, | |
| "learning_rate": 0.00018830802511031762, | |
| "loss": 0.3952127695083618, | |
| "num_input_tokens_seen": 657668, | |
| "step": 199, | |
| "train_runtime": 1500.9816, | |
| "train_tokens_per_second": 438.159 | |
| }, | |
| { | |
| "epoch": 1.6129032258064515, | |
| "grad_norm": 0.7098085284233093, | |
| "learning_rate": 0.0001881883788471636, | |
| "loss": 0.40977275371551514, | |
| "num_input_tokens_seen": 661006, | |
| "step": 200, | |
| "train_runtime": 1507.5559, | |
| "train_tokens_per_second": 438.462 | |
| }, | |
| { | |
| "epoch": 1.620967741935484, | |
| "grad_norm": 0.7413765788078308, | |
| "learning_rate": 0.00018806816192463625, | |
| "loss": 0.42479950189590454, | |
| "num_input_tokens_seen": 664466, | |
| "step": 201, | |
| "train_runtime": 1514.302, | |
| "train_tokens_per_second": 438.794 | |
| }, | |
| { | |
| "epoch": 1.629032258064516, | |
| "grad_norm": 0.8011177778244019, | |
| "learning_rate": 0.0001879473751206489, | |
| "loss": 0.4388383626937866, | |
| "num_input_tokens_seen": 667634, | |
| "step": 202, | |
| "train_runtime": 1520.6629, | |
| "train_tokens_per_second": 439.041 | |
| }, | |
| { | |
| "epoch": 1.6370967741935485, | |
| "grad_norm": 0.6176231503486633, | |
| "learning_rate": 0.00018782601921680256, | |
| "loss": 0.4233701825141907, | |
| "num_input_tokens_seen": 671080, | |
| "step": 203, | |
| "train_runtime": 1527.319, | |
| "train_tokens_per_second": 439.384 | |
| }, | |
| { | |
| "epoch": 1.6451612903225805, | |
| "grad_norm": 0.6928187012672424, | |
| "learning_rate": 0.00018770409499838073, | |
| "loss": 0.4532501995563507, | |
| "num_input_tokens_seen": 674508, | |
| "step": 204, | |
| "train_runtime": 1534.0098, | |
| "train_tokens_per_second": 439.703 | |
| }, | |
| { | |
| "epoch": 1.653225806451613, | |
| "grad_norm": 0.710063636302948, | |
| "learning_rate": 0.0001875816032543445, | |
| "loss": 0.37533634901046753, | |
| "num_input_tokens_seen": 677700, | |
| "step": 205, | |
| "train_runtime": 1540.4655, | |
| "train_tokens_per_second": 439.932 | |
| }, | |
| { | |
| "epoch": 1.661290322580645, | |
| "grad_norm": 0.6659166216850281, | |
| "learning_rate": 0.00018745854477732733, | |
| "loss": 0.3989948630332947, | |
| "num_input_tokens_seen": 680978, | |
| "step": 206, | |
| "train_runtime": 1546.9747, | |
| "train_tokens_per_second": 440.2 | |
| }, | |
| { | |
| "epoch": 1.6693548387096775, | |
| "grad_norm": 0.5847692489624023, | |
| "learning_rate": 0.00018733492036363005, | |
| "loss": 0.39292144775390625, | |
| "num_input_tokens_seen": 684328, | |
| "step": 207, | |
| "train_runtime": 1553.5704, | |
| "train_tokens_per_second": 440.487 | |
| }, | |
| { | |
| "epoch": 1.6774193548387095, | |
| "grad_norm": 0.6828010082244873, | |
| "learning_rate": 0.0001872107308132155, | |
| "loss": 0.4327988028526306, | |
| "num_input_tokens_seen": 687676, | |
| "step": 208, | |
| "train_runtime": 1560.1397, | |
| "train_tokens_per_second": 440.778 | |
| }, | |
| { | |
| "epoch": 1.685483870967742, | |
| "grad_norm": 0.6712137460708618, | |
| "learning_rate": 0.00018708597692970353, | |
| "loss": 0.38148653507232666, | |
| "num_input_tokens_seen": 691000, | |
| "step": 209, | |
| "train_runtime": 1566.7698, | |
| "train_tokens_per_second": 441.035 | |
| }, | |
| { | |
| "epoch": 1.6935483870967742, | |
| "grad_norm": 0.8174690008163452, | |
| "learning_rate": 0.00018696065952036571, | |
| "loss": 0.4306122660636902, | |
| "num_input_tokens_seen": 694156, | |
| "step": 210, | |
| "train_runtime": 1573.041, | |
| "train_tokens_per_second": 441.283 | |
| }, | |
| { | |
| "epoch": 1.6935483870967742, | |
| "eval_loss": 2.281032085418701, | |
| "eval_runtime": 16.9723, | |
| "eval_samples_per_second": 3.064, | |
| "eval_steps_per_second": 1.532, | |
| "num_input_tokens_seen": 694156, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.7016129032258065, | |
| "grad_norm": 0.641558825969696, | |
| "learning_rate": 0.00018683477939612021, | |
| "loss": 0.390179306268692, | |
| "num_input_tokens_seen": 697510, | |
| "step": 211, | |
| "train_runtime": 1600.5748, | |
| "train_tokens_per_second": 435.787 | |
| }, | |
| { | |
| "epoch": 1.7096774193548387, | |
| "grad_norm": 0.6440213918685913, | |
| "learning_rate": 0.0001867083373715264, | |
| "loss": 0.3886089622974396, | |
| "num_input_tokens_seen": 700884, | |
| "step": 212, | |
| "train_runtime": 1607.2259, | |
| "train_tokens_per_second": 436.083 | |
| }, | |
| { | |
| "epoch": 1.717741935483871, | |
| "grad_norm": 0.6989295482635498, | |
| "learning_rate": 0.00018658133426477965, | |
| "loss": 0.41528093814849854, | |
| "num_input_tokens_seen": 704288, | |
| "step": 213, | |
| "train_runtime": 1613.9043, | |
| "train_tokens_per_second": 436.388 | |
| }, | |
| { | |
| "epoch": 1.7258064516129032, | |
| "grad_norm": 0.785047173500061, | |
| "learning_rate": 0.00018645377089770616, | |
| "loss": 0.4055544435977936, | |
| "num_input_tokens_seen": 707404, | |
| "step": 214, | |
| "train_runtime": 1620.1995, | |
| "train_tokens_per_second": 436.615 | |
| }, | |
| { | |
| "epoch": 1.7338709677419355, | |
| "grad_norm": 0.7163392305374146, | |
| "learning_rate": 0.00018632564809575742, | |
| "loss": 0.417140930891037, | |
| "num_input_tokens_seen": 710738, | |
| "step": 215, | |
| "train_runtime": 1626.8303, | |
| "train_tokens_per_second": 436.885 | |
| }, | |
| { | |
| "epoch": 1.7419354838709677, | |
| "grad_norm": 0.8293558955192566, | |
| "learning_rate": 0.00018619696668800492, | |
| "loss": 0.4728226959705353, | |
| "num_input_tokens_seen": 714052, | |
| "step": 216, | |
| "train_runtime": 1633.4113, | |
| "train_tokens_per_second": 437.154 | |
| }, | |
| { | |
| "epoch": 1.75, | |
| "grad_norm": 0.6450289487838745, | |
| "learning_rate": 0.00018606772750713504, | |
| "loss": 0.38246041536331177, | |
| "num_input_tokens_seen": 717406, | |
| "step": 217, | |
| "train_runtime": 1640.0928, | |
| "train_tokens_per_second": 437.418 | |
| }, | |
| { | |
| "epoch": 1.7580645161290323, | |
| "grad_norm": 0.64801424741745, | |
| "learning_rate": 0.00018593793138944328, | |
| "loss": 0.37994423508644104, | |
| "num_input_tokens_seen": 720724, | |
| "step": 218, | |
| "train_runtime": 1646.6497, | |
| "train_tokens_per_second": 437.691 | |
| }, | |
| { | |
| "epoch": 1.7661290322580645, | |
| "grad_norm": 0.7920657396316528, | |
| "learning_rate": 0.0001858075791748291, | |
| "loss": 0.48340174555778503, | |
| "num_input_tokens_seen": 724156, | |
| "step": 219, | |
| "train_runtime": 1653.296, | |
| "train_tokens_per_second": 438.007 | |
| }, | |
| { | |
| "epoch": 1.7741935483870968, | |
| "grad_norm": 0.7000712156295776, | |
| "learning_rate": 0.0001856766717067904, | |
| "loss": 0.42204493284225464, | |
| "num_input_tokens_seen": 727386, | |
| "step": 220, | |
| "train_runtime": 1659.7156, | |
| "train_tokens_per_second": 438.259 | |
| }, | |
| { | |
| "epoch": 1.782258064516129, | |
| "grad_norm": 0.6280332803726196, | |
| "learning_rate": 0.00018554520983241814, | |
| "loss": 0.4031910002231598, | |
| "num_input_tokens_seen": 730576, | |
| "step": 221, | |
| "train_runtime": 1666.2385, | |
| "train_tokens_per_second": 438.458 | |
| }, | |
| { | |
| "epoch": 1.7903225806451613, | |
| "grad_norm": 0.5951255559921265, | |
| "learning_rate": 0.00018541319440239066, | |
| "loss": 0.37358546257019043, | |
| "num_input_tokens_seen": 734042, | |
| "step": 222, | |
| "train_runtime": 1672.8824, | |
| "train_tokens_per_second": 438.789 | |
| }, | |
| { | |
| "epoch": 1.7983870967741935, | |
| "grad_norm": 0.6634789109230042, | |
| "learning_rate": 0.00018528062627096845, | |
| "loss": 0.4016473889350891, | |
| "num_input_tokens_seen": 737388, | |
| "step": 223, | |
| "train_runtime": 1679.4447, | |
| "train_tokens_per_second": 439.067 | |
| }, | |
| { | |
| "epoch": 1.8064516129032258, | |
| "grad_norm": 0.6808019876480103, | |
| "learning_rate": 0.0001851475062959884, | |
| "loss": 0.40531060099601746, | |
| "num_input_tokens_seen": 740714, | |
| "step": 224, | |
| "train_runtime": 1686.0689, | |
| "train_tokens_per_second": 439.314 | |
| }, | |
| { | |
| "epoch": 1.814516129032258, | |
| "grad_norm": 0.6066514849662781, | |
| "learning_rate": 0.00018501383533885837, | |
| "loss": 0.3812728524208069, | |
| "num_input_tokens_seen": 743952, | |
| "step": 225, | |
| "train_runtime": 1692.602, | |
| "train_tokens_per_second": 439.532 | |
| }, | |
| { | |
| "epoch": 1.8225806451612905, | |
| "grad_norm": 0.6962650418281555, | |
| "learning_rate": 0.00018487961426455157, | |
| "loss": 0.4498329162597656, | |
| "num_input_tokens_seen": 747324, | |
| "step": 226, | |
| "train_runtime": 1699.2428, | |
| "train_tokens_per_second": 439.798 | |
| }, | |
| { | |
| "epoch": 1.8306451612903225, | |
| "grad_norm": 0.7276473641395569, | |
| "learning_rate": 0.0001847448439416009, | |
| "loss": 0.4539956748485565, | |
| "num_input_tokens_seen": 750660, | |
| "step": 227, | |
| "train_runtime": 1705.825, | |
| "train_tokens_per_second": 440.057 | |
| }, | |
| { | |
| "epoch": 1.838709677419355, | |
| "grad_norm": 0.7871230244636536, | |
| "learning_rate": 0.00018460952524209355, | |
| "loss": 0.4766373038291931, | |
| "num_input_tokens_seen": 753890, | |
| "step": 228, | |
| "train_runtime": 1712.1642, | |
| "train_tokens_per_second": 440.314 | |
| }, | |
| { | |
| "epoch": 1.846774193548387, | |
| "grad_norm": 0.6592321991920471, | |
| "learning_rate": 0.0001844736590416651, | |
| "loss": 0.3986653983592987, | |
| "num_input_tokens_seen": 757196, | |
| "step": 229, | |
| "train_runtime": 1718.7529, | |
| "train_tokens_per_second": 440.55 | |
| }, | |
| { | |
| "epoch": 1.8548387096774195, | |
| "grad_norm": 0.6650552153587341, | |
| "learning_rate": 0.00018433724621949392, | |
| "loss": 0.39142435789108276, | |
| "num_input_tokens_seen": 760606, | |
| "step": 230, | |
| "train_runtime": 1725.4681, | |
| "train_tokens_per_second": 440.811 | |
| }, | |
| { | |
| "epoch": 1.8629032258064515, | |
| "grad_norm": 0.6583918929100037, | |
| "learning_rate": 0.00018420028765829568, | |
| "loss": 0.4003082811832428, | |
| "num_input_tokens_seen": 763910, | |
| "step": 231, | |
| "train_runtime": 1732.022, | |
| "train_tokens_per_second": 441.051 | |
| }, | |
| { | |
| "epoch": 1.870967741935484, | |
| "grad_norm": 0.7142671942710876, | |
| "learning_rate": 0.00018406278424431736, | |
| "loss": 0.4203531742095947, | |
| "num_input_tokens_seen": 767166, | |
| "step": 232, | |
| "train_runtime": 1738.4018, | |
| "train_tokens_per_second": 441.305 | |
| }, | |
| { | |
| "epoch": 1.879032258064516, | |
| "grad_norm": 0.6280651688575745, | |
| "learning_rate": 0.00018392473686733163, | |
| "loss": 0.40257829427719116, | |
| "num_input_tokens_seen": 770592, | |
| "step": 233, | |
| "train_runtime": 1745.0525, | |
| "train_tokens_per_second": 441.587 | |
| }, | |
| { | |
| "epoch": 1.8870967741935485, | |
| "grad_norm": 0.8258600234985352, | |
| "learning_rate": 0.00018378614642063115, | |
| "loss": 0.4191328287124634, | |
| "num_input_tokens_seen": 773594, | |
| "step": 234, | |
| "train_runtime": 1751.2771, | |
| "train_tokens_per_second": 441.731 | |
| }, | |
| { | |
| "epoch": 1.8951612903225805, | |
| "grad_norm": 0.7963438034057617, | |
| "learning_rate": 0.00018364701380102266, | |
| "loss": 0.42885884642601013, | |
| "num_input_tokens_seen": 776592, | |
| "step": 235, | |
| "train_runtime": 1757.3069, | |
| "train_tokens_per_second": 441.922 | |
| }, | |
| { | |
| "epoch": 1.903225806451613, | |
| "grad_norm": 0.7623209357261658, | |
| "learning_rate": 0.0001835073399088214, | |
| "loss": 0.4639081358909607, | |
| "num_input_tokens_seen": 779942, | |
| "step": 236, | |
| "train_runtime": 1763.9906, | |
| "train_tokens_per_second": 442.146 | |
| }, | |
| { | |
| "epoch": 1.911290322580645, | |
| "grad_norm": 0.6425145864486694, | |
| "learning_rate": 0.00018336712564784503, | |
| "loss": 0.3997993469238281, | |
| "num_input_tokens_seen": 783252, | |
| "step": 237, | |
| "train_runtime": 1770.5413, | |
| "train_tokens_per_second": 442.38 | |
| }, | |
| { | |
| "epoch": 1.9193548387096775, | |
| "grad_norm": 0.7987529039382935, | |
| "learning_rate": 0.00018322637192540785, | |
| "loss": 0.4364495277404785, | |
| "num_input_tokens_seen": 786556, | |
| "step": 238, | |
| "train_runtime": 1777.0794, | |
| "train_tokens_per_second": 442.612 | |
| }, | |
| { | |
| "epoch": 1.9274193548387095, | |
| "grad_norm": 0.7024737000465393, | |
| "learning_rate": 0.00018308507965231508, | |
| "loss": 0.4188304543495178, | |
| "num_input_tokens_seen": 789882, | |
| "step": 239, | |
| "train_runtime": 1783.6117, | |
| "train_tokens_per_second": 442.855 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "grad_norm": 0.6291638612747192, | |
| "learning_rate": 0.00018294324974285677, | |
| "loss": 0.37665027379989624, | |
| "num_input_tokens_seen": 793254, | |
| "step": 240, | |
| "train_runtime": 1790.3001, | |
| "train_tokens_per_second": 443.084 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "eval_loss": 2.1662468910217285, | |
| "eval_runtime": 16.9567, | |
| "eval_samples_per_second": 3.067, | |
| "eval_steps_per_second": 1.533, | |
| "num_input_tokens_seen": 793254, | |
| "step": 240 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 1240, | |
| "num_input_tokens_seen": 793254, | |
| "num_train_epochs": 10, | |
| "save_steps": 30, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1549679756665984e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |