text-normalization-ru-new / trainer_state.json
alexue4's picture
End of training
a310d9d
raw
history blame
27.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 237010,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.219231256065145e-09,
"loss": 0.0425,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 5.004008269693263e-06,
"loss": 0.1718,
"step": 1186
},
{
"epoch": 0.1,
"learning_rate": 1.0008016539386525e-05,
"loss": 0.0835,
"step": 2372
},
{
"epoch": 0.15,
"learning_rate": 1.5012024809079786e-05,
"loss": 0.0432,
"step": 3558
},
{
"epoch": 0.2,
"learning_rate": 2.001603307877305e-05,
"loss": 0.0324,
"step": 4744
},
{
"epoch": 0.25,
"learning_rate": 2.5020041348466312e-05,
"loss": 0.03,
"step": 5930
},
{
"epoch": 0.3,
"learning_rate": 3.0024049618159573e-05,
"loss": 0.0266,
"step": 7116
},
{
"epoch": 0.35,
"learning_rate": 3.5028057887852834e-05,
"loss": 0.0236,
"step": 8302
},
{
"epoch": 0.4,
"learning_rate": 4.00320661575461e-05,
"loss": 0.0219,
"step": 9488
},
{
"epoch": 0.45,
"learning_rate": 4.503607442723936e-05,
"loss": 0.0202,
"step": 10674
},
{
"epoch": 0.5,
"learning_rate": 5.0040082696932624e-05,
"loss": 0.0196,
"step": 11860
},
{
"epoch": 0.55,
"learning_rate": 5.5044090966625885e-05,
"loss": 0.0195,
"step": 13046
},
{
"epoch": 0.6,
"learning_rate": 6.0048099236319146e-05,
"loss": 0.0183,
"step": 14232
},
{
"epoch": 0.65,
"learning_rate": 6.50521075060124e-05,
"loss": 0.0181,
"step": 15418
},
{
"epoch": 0.7,
"learning_rate": 7.005611577570567e-05,
"loss": 0.0174,
"step": 16604
},
{
"epoch": 0.75,
"learning_rate": 7.506012404539893e-05,
"loss": 0.0175,
"step": 17790
},
{
"epoch": 0.8,
"learning_rate": 8.00641323150922e-05,
"loss": 0.0159,
"step": 18976
},
{
"epoch": 0.85,
"learning_rate": 8.506814058478546e-05,
"loss": 0.0165,
"step": 20162
},
{
"epoch": 0.9,
"learning_rate": 9.007214885447873e-05,
"loss": 0.0164,
"step": 21348
},
{
"epoch": 0.95,
"learning_rate": 9.507615712417199e-05,
"loss": 0.0163,
"step": 22534
},
{
"epoch": 1.0,
"eval_loss": 0.04283371567726135,
"eval_max_distance": 43,
"eval_mean_distance": 0,
"eval_runtime": 16.0673,
"eval_samples_per_second": 15.56,
"eval_steps_per_second": 1.058,
"step": 23701
},
{
"epoch": 1.0,
"learning_rate": 9.999109273401498e-05,
"loss": 0.0161,
"step": 23720
},
{
"epoch": 1.05,
"learning_rate": 9.943509181516017e-05,
"loss": 0.0146,
"step": 24906
},
{
"epoch": 1.1,
"learning_rate": 9.887909089630536e-05,
"loss": 0.0151,
"step": 26092
},
{
"epoch": 1.15,
"learning_rate": 9.832308997745055e-05,
"loss": 0.0144,
"step": 27278
},
{
"epoch": 1.2,
"learning_rate": 9.776708905859574e-05,
"loss": 0.0135,
"step": 28464
},
{
"epoch": 1.25,
"learning_rate": 9.721108813974095e-05,
"loss": 0.0146,
"step": 29650
},
{
"epoch": 1.3,
"learning_rate": 9.665508722088614e-05,
"loss": 0.0139,
"step": 30836
},
{
"epoch": 1.35,
"learning_rate": 9.609908630203133e-05,
"loss": 0.0135,
"step": 32022
},
{
"epoch": 1.4,
"learning_rate": 9.554308538317653e-05,
"loss": 0.0137,
"step": 33208
},
{
"epoch": 1.45,
"learning_rate": 9.498708446432172e-05,
"loss": 0.0137,
"step": 34394
},
{
"epoch": 1.5,
"learning_rate": 9.443108354546691e-05,
"loss": 0.0141,
"step": 35580
},
{
"epoch": 1.55,
"learning_rate": 9.38750826266121e-05,
"loss": 0.0126,
"step": 36766
},
{
"epoch": 1.6,
"learning_rate": 9.331908170775729e-05,
"loss": 0.014,
"step": 37952
},
{
"epoch": 1.65,
"learning_rate": 9.276308078890248e-05,
"loss": 0.0133,
"step": 39138
},
{
"epoch": 1.7,
"learning_rate": 9.220707987004769e-05,
"loss": 0.0134,
"step": 40324
},
{
"epoch": 1.75,
"learning_rate": 9.165107895119287e-05,
"loss": 0.0126,
"step": 41510
},
{
"epoch": 1.8,
"learning_rate": 9.109507803233807e-05,
"loss": 0.0137,
"step": 42696
},
{
"epoch": 1.85,
"learning_rate": 9.053907711348326e-05,
"loss": 0.0145,
"step": 43882
},
{
"epoch": 1.9,
"learning_rate": 8.998307619462846e-05,
"loss": 0.0126,
"step": 45068
},
{
"epoch": 1.95,
"learning_rate": 8.942707527577365e-05,
"loss": 0.0132,
"step": 46254
},
{
"epoch": 2.0,
"eval_loss": 0.042018186300992966,
"eval_max_distance": 44,
"eval_mean_distance": 0,
"eval_runtime": 15.8905,
"eval_samples_per_second": 15.733,
"eval_steps_per_second": 1.07,
"step": 47402
},
{
"epoch": 2.0,
"learning_rate": 8.887107435691884e-05,
"loss": 0.0132,
"step": 47440
},
{
"epoch": 2.05,
"learning_rate": 8.831507343806403e-05,
"loss": 0.0107,
"step": 48626
},
{
"epoch": 2.1,
"learning_rate": 8.775907251920922e-05,
"loss": 0.0108,
"step": 49812
},
{
"epoch": 2.15,
"learning_rate": 8.720307160035443e-05,
"loss": 0.0115,
"step": 50998
},
{
"epoch": 2.2,
"learning_rate": 8.66470706814996e-05,
"loss": 0.0107,
"step": 52184
},
{
"epoch": 2.25,
"learning_rate": 8.609106976264481e-05,
"loss": 0.0113,
"step": 53370
},
{
"epoch": 2.3,
"learning_rate": 8.553506884379e-05,
"loss": 0.011,
"step": 54556
},
{
"epoch": 2.35,
"learning_rate": 8.49790679249352e-05,
"loss": 0.0119,
"step": 55742
},
{
"epoch": 2.4,
"learning_rate": 8.442306700608039e-05,
"loss": 0.0106,
"step": 56928
},
{
"epoch": 2.45,
"learning_rate": 8.386706608722558e-05,
"loss": 0.0118,
"step": 58114
},
{
"epoch": 2.5,
"learning_rate": 8.331106516837077e-05,
"loss": 0.0116,
"step": 59300
},
{
"epoch": 2.55,
"learning_rate": 8.275506424951596e-05,
"loss": 0.0111,
"step": 60486
},
{
"epoch": 2.6,
"learning_rate": 8.219906333066115e-05,
"loss": 0.0112,
"step": 61672
},
{
"epoch": 2.65,
"learning_rate": 8.164306241180635e-05,
"loss": 0.0111,
"step": 62858
},
{
"epoch": 2.7,
"learning_rate": 8.108706149295155e-05,
"loss": 0.0109,
"step": 64044
},
{
"epoch": 2.75,
"learning_rate": 8.053106057409674e-05,
"loss": 0.0113,
"step": 65230
},
{
"epoch": 2.8,
"learning_rate": 7.997505965524193e-05,
"loss": 0.0117,
"step": 66416
},
{
"epoch": 2.85,
"learning_rate": 7.941905873638713e-05,
"loss": 0.0108,
"step": 67602
},
{
"epoch": 2.9,
"learning_rate": 7.886305781753232e-05,
"loss": 0.011,
"step": 68788
},
{
"epoch": 2.95,
"learning_rate": 7.830705689867751e-05,
"loss": 0.0111,
"step": 69974
},
{
"epoch": 3.0,
"eval_loss": 0.04441571980714798,
"eval_max_distance": 35,
"eval_mean_distance": 0,
"eval_runtime": 15.9553,
"eval_samples_per_second": 15.669,
"eval_steps_per_second": 1.065,
"step": 71103
},
{
"epoch": 3.0,
"learning_rate": 7.77510559798227e-05,
"loss": 0.0115,
"step": 71160
},
{
"epoch": 3.05,
"learning_rate": 7.719505506096789e-05,
"loss": 0.0101,
"step": 72346
},
{
"epoch": 3.1,
"learning_rate": 7.663905414211308e-05,
"loss": 0.0093,
"step": 73532
},
{
"epoch": 3.15,
"learning_rate": 7.608305322325828e-05,
"loss": 0.0091,
"step": 74718
},
{
"epoch": 3.2,
"learning_rate": 7.552705230440348e-05,
"loss": 0.0094,
"step": 75904
},
{
"epoch": 3.25,
"learning_rate": 7.497105138554866e-05,
"loss": 0.0099,
"step": 77090
},
{
"epoch": 3.3,
"learning_rate": 7.441505046669386e-05,
"loss": 0.01,
"step": 78276
},
{
"epoch": 3.35,
"learning_rate": 7.385904954783906e-05,
"loss": 0.0097,
"step": 79462
},
{
"epoch": 3.4,
"learning_rate": 7.330304862898425e-05,
"loss": 0.0099,
"step": 80648
},
{
"epoch": 3.45,
"learning_rate": 7.274704771012944e-05,
"loss": 0.0098,
"step": 81834
},
{
"epoch": 3.5,
"learning_rate": 7.219104679127463e-05,
"loss": 0.0095,
"step": 83020
},
{
"epoch": 3.55,
"learning_rate": 7.163504587241982e-05,
"loss": 0.0097,
"step": 84206
},
{
"epoch": 3.6,
"learning_rate": 7.107904495356501e-05,
"loss": 0.0094,
"step": 85392
},
{
"epoch": 3.65,
"learning_rate": 7.052304403471022e-05,
"loss": 0.0093,
"step": 86578
},
{
"epoch": 3.7,
"learning_rate": 6.99670431158554e-05,
"loss": 0.0103,
"step": 87764
},
{
"epoch": 3.75,
"learning_rate": 6.94110421970006e-05,
"loss": 0.0091,
"step": 88950
},
{
"epoch": 3.8,
"learning_rate": 6.88550412781458e-05,
"loss": 0.0094,
"step": 90136
},
{
"epoch": 3.85,
"learning_rate": 6.829904035929099e-05,
"loss": 0.0099,
"step": 91322
},
{
"epoch": 3.9,
"learning_rate": 6.774303944043618e-05,
"loss": 0.0095,
"step": 92508
},
{
"epoch": 3.95,
"learning_rate": 6.718703852158137e-05,
"loss": 0.0095,
"step": 93694
},
{
"epoch": 4.0,
"eval_loss": 0.04494529217481613,
"eval_max_distance": 43,
"eval_mean_distance": 0,
"eval_runtime": 15.8606,
"eval_samples_per_second": 15.762,
"eval_steps_per_second": 1.072,
"step": 94804
},
{
"epoch": 4.0,
"learning_rate": 6.663103760272656e-05,
"loss": 0.0102,
"step": 94880
},
{
"epoch": 4.05,
"learning_rate": 6.607503668387175e-05,
"loss": 0.0085,
"step": 96066
},
{
"epoch": 4.1,
"learning_rate": 6.551903576501695e-05,
"loss": 0.0084,
"step": 97252
},
{
"epoch": 4.15,
"learning_rate": 6.496303484616214e-05,
"loss": 0.0086,
"step": 98438
},
{
"epoch": 4.2,
"learning_rate": 6.440703392730734e-05,
"loss": 0.008,
"step": 99624
},
{
"epoch": 4.25,
"learning_rate": 6.385103300845253e-05,
"loss": 0.0084,
"step": 100810
},
{
"epoch": 4.3,
"learning_rate": 6.329503208959773e-05,
"loss": 0.0088,
"step": 101996
},
{
"epoch": 4.35,
"learning_rate": 6.273903117074292e-05,
"loss": 0.0087,
"step": 103182
},
{
"epoch": 4.4,
"learning_rate": 6.218303025188811e-05,
"loss": 0.0086,
"step": 104368
},
{
"epoch": 4.45,
"learning_rate": 6.16270293330333e-05,
"loss": 0.0087,
"step": 105554
},
{
"epoch": 4.5,
"learning_rate": 6.107102841417849e-05,
"loss": 0.0086,
"step": 106740
},
{
"epoch": 4.55,
"learning_rate": 6.0515027495323685e-05,
"loss": 0.0092,
"step": 107926
},
{
"epoch": 4.6,
"learning_rate": 5.9959026576468876e-05,
"loss": 0.0087,
"step": 109112
},
{
"epoch": 4.65,
"learning_rate": 5.9403025657614075e-05,
"loss": 0.0091,
"step": 110298
},
{
"epoch": 4.7,
"learning_rate": 5.884702473875927e-05,
"loss": 0.0084,
"step": 111484
},
{
"epoch": 4.75,
"learning_rate": 5.829102381990446e-05,
"loss": 0.0083,
"step": 112670
},
{
"epoch": 4.8,
"learning_rate": 5.773502290104965e-05,
"loss": 0.0085,
"step": 113856
},
{
"epoch": 4.85,
"learning_rate": 5.717902198219485e-05,
"loss": 0.0092,
"step": 115042
},
{
"epoch": 4.9,
"learning_rate": 5.662302106334004e-05,
"loss": 0.0083,
"step": 116228
},
{
"epoch": 4.95,
"learning_rate": 5.606702014448524e-05,
"loss": 0.0088,
"step": 117414
},
{
"epoch": 5.0,
"eval_loss": 0.0445968434214592,
"eval_max_distance": 40,
"eval_mean_distance": 0,
"eval_runtime": 15.8709,
"eval_samples_per_second": 15.752,
"eval_steps_per_second": 1.071,
"step": 118505
},
{
"epoch": 5.0,
"learning_rate": 5.5511019225630424e-05,
"loss": 0.0084,
"step": 118600
},
{
"epoch": 5.05,
"learning_rate": 5.4955018306775615e-05,
"loss": 0.0072,
"step": 119786
},
{
"epoch": 5.1,
"learning_rate": 5.4399017387920814e-05,
"loss": 0.0078,
"step": 120972
},
{
"epoch": 5.15,
"learning_rate": 5.384301646906601e-05,
"loss": 0.0082,
"step": 122158
},
{
"epoch": 5.2,
"learning_rate": 5.32870155502112e-05,
"loss": 0.0079,
"step": 123344
},
{
"epoch": 5.25,
"learning_rate": 5.273101463135639e-05,
"loss": 0.008,
"step": 124530
},
{
"epoch": 5.3,
"learning_rate": 5.217501371250159e-05,
"loss": 0.008,
"step": 125716
},
{
"epoch": 5.35,
"learning_rate": 5.161901279364678e-05,
"loss": 0.0081,
"step": 126902
},
{
"epoch": 5.4,
"learning_rate": 5.1063011874791964e-05,
"loss": 0.0078,
"step": 128088
},
{
"epoch": 5.45,
"learning_rate": 5.050701095593716e-05,
"loss": 0.0076,
"step": 129274
},
{
"epoch": 5.5,
"learning_rate": 4.9951010037082354e-05,
"loss": 0.0079,
"step": 130460
},
{
"epoch": 5.55,
"learning_rate": 4.9395009118227546e-05,
"loss": 0.0074,
"step": 131646
},
{
"epoch": 5.6,
"learning_rate": 4.8839008199372745e-05,
"loss": 0.0077,
"step": 132832
},
{
"epoch": 5.65,
"learning_rate": 4.8283007280517936e-05,
"loss": 0.0079,
"step": 134018
},
{
"epoch": 5.7,
"learning_rate": 4.772700636166313e-05,
"loss": 0.0077,
"step": 135204
},
{
"epoch": 5.75,
"learning_rate": 4.7171005442808326e-05,
"loss": 0.0078,
"step": 136390
},
{
"epoch": 5.8,
"learning_rate": 4.661500452395352e-05,
"loss": 0.0081,
"step": 137576
},
{
"epoch": 5.85,
"learning_rate": 4.605900360509871e-05,
"loss": 0.0077,
"step": 138762
},
{
"epoch": 5.9,
"learning_rate": 4.55030026862439e-05,
"loss": 0.0075,
"step": 139948
},
{
"epoch": 5.95,
"learning_rate": 4.494700176738909e-05,
"loss": 0.0076,
"step": 141134
},
{
"epoch": 6.0,
"eval_loss": 0.046243954449892044,
"eval_max_distance": 33,
"eval_mean_distance": 0,
"eval_runtime": 15.8654,
"eval_samples_per_second": 15.758,
"eval_steps_per_second": 1.072,
"step": 142206
},
{
"epoch": 6.0,
"learning_rate": 4.4391000848534285e-05,
"loss": 0.0079,
"step": 142320
},
{
"epoch": 6.05,
"learning_rate": 4.3834999929679484e-05,
"loss": 0.0073,
"step": 143506
},
{
"epoch": 6.1,
"learning_rate": 4.3278999010824675e-05,
"loss": 0.007,
"step": 144692
},
{
"epoch": 6.15,
"learning_rate": 4.272299809196987e-05,
"loss": 0.0076,
"step": 145878
},
{
"epoch": 6.2,
"learning_rate": 4.216699717311506e-05,
"loss": 0.0072,
"step": 147064
},
{
"epoch": 6.26,
"learning_rate": 4.161099625426026e-05,
"loss": 0.007,
"step": 148250
},
{
"epoch": 6.31,
"learning_rate": 4.105499533540544e-05,
"loss": 0.0073,
"step": 149436
},
{
"epoch": 6.36,
"learning_rate": 4.049899441655064e-05,
"loss": 0.0073,
"step": 150622
},
{
"epoch": 6.41,
"learning_rate": 3.994299349769583e-05,
"loss": 0.0072,
"step": 151808
},
{
"epoch": 6.46,
"learning_rate": 3.9386992578841024e-05,
"loss": 0.0073,
"step": 152994
},
{
"epoch": 6.51,
"learning_rate": 3.883099165998622e-05,
"loss": 0.007,
"step": 154180
},
{
"epoch": 6.56,
"learning_rate": 3.8274990741131414e-05,
"loss": 0.0073,
"step": 155366
},
{
"epoch": 6.61,
"learning_rate": 3.7718989822276606e-05,
"loss": 0.0074,
"step": 156552
},
{
"epoch": 6.66,
"learning_rate": 3.71629889034218e-05,
"loss": 0.0071,
"step": 157738
},
{
"epoch": 6.71,
"learning_rate": 3.660698798456699e-05,
"loss": 0.0077,
"step": 158924
},
{
"epoch": 6.76,
"learning_rate": 3.605098706571218e-05,
"loss": 0.0072,
"step": 160110
},
{
"epoch": 6.81,
"learning_rate": 3.549498614685738e-05,
"loss": 0.0069,
"step": 161296
},
{
"epoch": 6.86,
"learning_rate": 3.493898522800257e-05,
"loss": 0.0074,
"step": 162482
},
{
"epoch": 6.91,
"learning_rate": 3.438298430914776e-05,
"loss": 0.0072,
"step": 163668
},
{
"epoch": 6.96,
"learning_rate": 3.3826983390292955e-05,
"loss": 0.0074,
"step": 164854
},
{
"epoch": 7.0,
"eval_loss": 0.046568483114242554,
"eval_max_distance": 38,
"eval_mean_distance": 0,
"eval_runtime": 15.7578,
"eval_samples_per_second": 15.865,
"eval_steps_per_second": 1.079,
"step": 165907
},
{
"epoch": 7.01,
"learning_rate": 3.327098247143815e-05,
"loss": 0.0071,
"step": 166040
},
{
"epoch": 7.06,
"learning_rate": 3.2714981552583345e-05,
"loss": 0.0065,
"step": 167226
},
{
"epoch": 7.11,
"learning_rate": 3.215898063372854e-05,
"loss": 0.0066,
"step": 168412
},
{
"epoch": 7.16,
"learning_rate": 3.160297971487373e-05,
"loss": 0.0067,
"step": 169598
},
{
"epoch": 7.21,
"learning_rate": 3.104697879601892e-05,
"loss": 0.0067,
"step": 170784
},
{
"epoch": 7.26,
"learning_rate": 3.049097787716412e-05,
"loss": 0.0066,
"step": 171970
},
{
"epoch": 7.31,
"learning_rate": 2.9934976958309307e-05,
"loss": 0.0071,
"step": 173156
},
{
"epoch": 7.36,
"learning_rate": 2.9378976039454502e-05,
"loss": 0.0067,
"step": 174342
},
{
"epoch": 7.41,
"learning_rate": 2.8822975120599694e-05,
"loss": 0.0064,
"step": 175528
},
{
"epoch": 7.46,
"learning_rate": 2.826697420174489e-05,
"loss": 0.0064,
"step": 176714
},
{
"epoch": 7.51,
"learning_rate": 2.771097328289008e-05,
"loss": 0.0067,
"step": 177900
},
{
"epoch": 7.56,
"learning_rate": 2.7154972364035276e-05,
"loss": 0.0068,
"step": 179086
},
{
"epoch": 7.61,
"learning_rate": 2.6598971445180464e-05,
"loss": 0.0071,
"step": 180272
},
{
"epoch": 7.66,
"learning_rate": 2.604297052632566e-05,
"loss": 0.0065,
"step": 181458
},
{
"epoch": 7.71,
"learning_rate": 2.548696960747085e-05,
"loss": 0.0065,
"step": 182644
},
{
"epoch": 7.76,
"learning_rate": 2.4930968688616046e-05,
"loss": 0.007,
"step": 183830
},
{
"epoch": 7.81,
"learning_rate": 2.437496776976124e-05,
"loss": 0.007,
"step": 185016
},
{
"epoch": 7.86,
"learning_rate": 2.3818966850906433e-05,
"loss": 0.007,
"step": 186202
},
{
"epoch": 7.91,
"learning_rate": 2.3262965932051624e-05,
"loss": 0.0069,
"step": 187388
},
{
"epoch": 7.96,
"learning_rate": 2.270696501319682e-05,
"loss": 0.0068,
"step": 188574
},
{
"epoch": 8.0,
"eval_loss": 0.04775545746088028,
"eval_max_distance": 39,
"eval_mean_distance": 0,
"eval_runtime": 15.8132,
"eval_samples_per_second": 15.81,
"eval_steps_per_second": 1.075,
"step": 189608
},
{
"epoch": 8.01,
"learning_rate": 2.215096409434201e-05,
"loss": 0.0067,
"step": 189760
},
{
"epoch": 8.06,
"learning_rate": 2.1594963175487203e-05,
"loss": 0.0062,
"step": 190946
},
{
"epoch": 8.11,
"learning_rate": 2.1038962256632398e-05,
"loss": 0.0066,
"step": 192132
},
{
"epoch": 8.16,
"learning_rate": 2.0482961337777593e-05,
"loss": 0.0062,
"step": 193318
},
{
"epoch": 8.21,
"learning_rate": 1.9926960418922785e-05,
"loss": 0.0064,
"step": 194504
},
{
"epoch": 8.26,
"learning_rate": 1.9370959500067977e-05,
"loss": 0.0062,
"step": 195690
},
{
"epoch": 8.31,
"learning_rate": 1.8814958581213172e-05,
"loss": 0.0063,
"step": 196876
},
{
"epoch": 8.36,
"learning_rate": 1.8258957662358363e-05,
"loss": 0.0068,
"step": 198062
},
{
"epoch": 8.41,
"learning_rate": 1.770295674350356e-05,
"loss": 0.0064,
"step": 199248
},
{
"epoch": 8.46,
"learning_rate": 1.714695582464875e-05,
"loss": 0.0066,
"step": 200434
},
{
"epoch": 8.51,
"learning_rate": 1.6590954905793942e-05,
"loss": 0.0062,
"step": 201620
},
{
"epoch": 8.56,
"learning_rate": 1.6034953986939137e-05,
"loss": 0.0068,
"step": 202806
},
{
"epoch": 8.61,
"learning_rate": 1.547895306808433e-05,
"loss": 0.0065,
"step": 203992
},
{
"epoch": 8.66,
"learning_rate": 1.4922952149229522e-05,
"loss": 0.0062,
"step": 205178
},
{
"epoch": 8.71,
"learning_rate": 1.4366951230374714e-05,
"loss": 0.0065,
"step": 206364
},
{
"epoch": 8.76,
"learning_rate": 1.3810950311519907e-05,
"loss": 0.0064,
"step": 207550
},
{
"epoch": 8.81,
"learning_rate": 1.32549493926651e-05,
"loss": 0.0066,
"step": 208736
},
{
"epoch": 8.86,
"learning_rate": 1.2698948473810296e-05,
"loss": 0.0064,
"step": 209922
},
{
"epoch": 8.91,
"learning_rate": 1.2142947554955488e-05,
"loss": 0.0061,
"step": 211108
},
{
"epoch": 8.96,
"learning_rate": 1.1586946636100681e-05,
"loss": 0.0069,
"step": 212294
},
{
"epoch": 9.0,
"eval_loss": 0.04885172098875046,
"eval_max_distance": 39,
"eval_mean_distance": 0,
"eval_runtime": 15.685,
"eval_samples_per_second": 15.939,
"eval_steps_per_second": 1.084,
"step": 213309
},
{
"epoch": 9.01,
"learning_rate": 1.1030945717245873e-05,
"loss": 0.0062,
"step": 213480
},
{
"epoch": 9.06,
"learning_rate": 1.0474944798391068e-05,
"loss": 0.006,
"step": 214666
},
{
"epoch": 9.11,
"learning_rate": 9.918943879536261e-06,
"loss": 0.0059,
"step": 215852
},
{
"epoch": 9.16,
"learning_rate": 9.362942960681453e-06,
"loss": 0.0059,
"step": 217038
},
{
"epoch": 9.21,
"learning_rate": 8.806942041826646e-06,
"loss": 0.0062,
"step": 218224
},
{
"epoch": 9.26,
"learning_rate": 8.25094112297184e-06,
"loss": 0.006,
"step": 219410
},
{
"epoch": 9.31,
"learning_rate": 7.694940204117032e-06,
"loss": 0.0062,
"step": 220596
},
{
"epoch": 9.36,
"learning_rate": 7.138939285262225e-06,
"loss": 0.0062,
"step": 221782
},
{
"epoch": 9.41,
"learning_rate": 6.582938366407419e-06,
"loss": 0.0064,
"step": 222968
},
{
"epoch": 9.46,
"learning_rate": 6.026937447552612e-06,
"loss": 0.0063,
"step": 224154
},
{
"epoch": 9.51,
"learning_rate": 5.470936528697805e-06,
"loss": 0.0064,
"step": 225340
},
{
"epoch": 9.56,
"learning_rate": 4.914935609842998e-06,
"loss": 0.0057,
"step": 226526
},
{
"epoch": 9.61,
"learning_rate": 4.358934690988191e-06,
"loss": 0.0065,
"step": 227712
},
{
"epoch": 9.66,
"learning_rate": 3.8029337721333837e-06,
"loss": 0.0062,
"step": 228898
},
{
"epoch": 9.71,
"learning_rate": 3.2469328532785775e-06,
"loss": 0.006,
"step": 230084
},
{
"epoch": 9.76,
"learning_rate": 2.69093193442377e-06,
"loss": 0.0062,
"step": 231270
},
{
"epoch": 9.81,
"learning_rate": 2.1349310155689635e-06,
"loss": 0.006,
"step": 232456
},
{
"epoch": 9.86,
"learning_rate": 1.5789300967141565e-06,
"loss": 0.0062,
"step": 233642
},
{
"epoch": 9.91,
"learning_rate": 1.0229291778593495e-06,
"loss": 0.0058,
"step": 234828
},
{
"epoch": 9.96,
"learning_rate": 4.669282590045427e-07,
"loss": 0.0061,
"step": 236014
},
{
"epoch": 10.0,
"eval_loss": 0.04803793504834175,
"eval_max_distance": 40,
"eval_mean_distance": 0,
"eval_runtime": 15.7597,
"eval_samples_per_second": 15.863,
"eval_steps_per_second": 1.079,
"step": 237010
},
{
"epoch": 10.0,
"step": 237010,
"total_flos": 5.639707743740928e+16,
"train_loss": 0.010972068954725507,
"train_runtime": 17115.447,
"train_samples_per_second": 207.713,
"train_steps_per_second": 13.848
}
],
"logging_steps": 1186,
"max_steps": 237010,
"num_train_epochs": 10,
"save_steps": 2371,
"total_flos": 5.639707743740928e+16,
"trial_name": null,
"trial_params": null
}