| { |
| "best_metric": 0.9975093399750934, |
| "best_model_checkpoint": "/media/cse/HDD/Shawon/shawon/10 fold timesformer/Timesformer_default_fold_10_10_epoch_noAug_batch8/checkpoint-4520", |
| "epoch": 9.099003322259136, |
| "eval_steps": 500, |
| "global_step": 9030, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01107419712070875, |
| "grad_norm": 12.269712448120117, |
| "learning_rate": 5.537098560354375e-06, |
| "loss": 4.1912, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.0221483942414175, |
| "grad_norm": 13.763405799865723, |
| "learning_rate": 1.107419712070875e-05, |
| "loss": 3.8166, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.03322259136212625, |
| "grad_norm": 16.058164596557617, |
| "learning_rate": 1.6611295681063124e-05, |
| "loss": 2.9676, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.044296788482835, |
| "grad_norm": 14.037968635559082, |
| "learning_rate": 2.21483942414175e-05, |
| "loss": 2.0805, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05537098560354374, |
| "grad_norm": 15.45093059539795, |
| "learning_rate": 2.7685492801771873e-05, |
| "loss": 1.2662, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.0664451827242525, |
| "grad_norm": 5.890250205993652, |
| "learning_rate": 3.322259136212625e-05, |
| "loss": 0.7708, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.07751937984496124, |
| "grad_norm": 8.48812484741211, |
| "learning_rate": 3.875968992248062e-05, |
| "loss": 0.4761, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.08859357696567, |
| "grad_norm": 3.3065390586853027, |
| "learning_rate": 4.4296788482835e-05, |
| "loss": 0.3097, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.09966777408637874, |
| "grad_norm": 4.770102024078369, |
| "learning_rate": 4.983388704318937e-05, |
| "loss": 0.2337, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.10011074197120709, |
| "eval_accuracy": 0.962640099626401, |
| "eval_loss": 0.18786028027534485, |
| "eval_runtime": 199.1827, |
| "eval_samples_per_second": 4.031, |
| "eval_steps_per_second": 0.507, |
| "step": 904 |
| }, |
| { |
| "epoch": 1.0106312292358803, |
| "grad_norm": 1.31089448928833, |
| "learning_rate": 4.940322382182848e-05, |
| "loss": 0.1491, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.0217054263565892, |
| "grad_norm": 0.30288809537887573, |
| "learning_rate": 4.878799064845577e-05, |
| "loss": 0.106, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.032779623477298, |
| "grad_norm": 0.8043572902679443, |
| "learning_rate": 4.8172757475083056e-05, |
| "loss": 0.1053, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.0438538205980066, |
| "grad_norm": 2.86224627494812, |
| "learning_rate": 4.755752430171035e-05, |
| "loss": 0.0642, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.0549280177187155, |
| "grad_norm": 1.9137568473815918, |
| "learning_rate": 4.694229112833764e-05, |
| "loss": 0.0543, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.0660022148394241, |
| "grad_norm": 0.646798849105835, |
| "learning_rate": 4.6327057954964936e-05, |
| "loss": 0.036, |
| "step": 1500 |
| }, |
| { |
| "epoch": 1.0770764119601328, |
| "grad_norm": 0.1015913337469101, |
| "learning_rate": 4.571182478159223e-05, |
| "loss": 0.0312, |
| "step": 1600 |
| }, |
| { |
| "epoch": 1.0881506090808417, |
| "grad_norm": 0.1494218111038208, |
| "learning_rate": 4.5096591608219516e-05, |
| "loss": 0.0345, |
| "step": 1700 |
| }, |
| { |
| "epoch": 1.0992248062015504, |
| "grad_norm": 0.09698224812746048, |
| "learning_rate": 4.448135843484681e-05, |
| "loss": 0.0508, |
| "step": 1800 |
| }, |
| { |
| "epoch": 1.100110741971207, |
| "eval_accuracy": 0.9937733499377335, |
| "eval_loss": 0.027358748018741608, |
| "eval_runtime": 196.0788, |
| "eval_samples_per_second": 4.095, |
| "eval_steps_per_second": 0.515, |
| "step": 1808 |
| }, |
| { |
| "epoch": 2.010188261351052, |
| "grad_norm": 0.015389556996524334, |
| "learning_rate": 4.38661252614741e-05, |
| "loss": 0.0149, |
| "step": 1900 |
| }, |
| { |
| "epoch": 2.0212624584717607, |
| "grad_norm": 0.03506704792380333, |
| "learning_rate": 4.325089208810139e-05, |
| "loss": 0.0056, |
| "step": 2000 |
| }, |
| { |
| "epoch": 2.0323366555924696, |
| "grad_norm": 0.01206329744309187, |
| "learning_rate": 4.263565891472868e-05, |
| "loss": 0.0027, |
| "step": 2100 |
| }, |
| { |
| "epoch": 2.0434108527131785, |
| "grad_norm": 0.12232516705989838, |
| "learning_rate": 4.2020425741355975e-05, |
| "loss": 0.0016, |
| "step": 2200 |
| }, |
| { |
| "epoch": 2.054485049833887, |
| "grad_norm": 0.007167478557676077, |
| "learning_rate": 4.140519256798327e-05, |
| "loss": 0.0103, |
| "step": 2300 |
| }, |
| { |
| "epoch": 2.065559246954596, |
| "grad_norm": 0.02364514209330082, |
| "learning_rate": 4.078995939461056e-05, |
| "loss": 0.0007, |
| "step": 2400 |
| }, |
| { |
| "epoch": 2.0766334440753047, |
| "grad_norm": 0.00806678831577301, |
| "learning_rate": 4.0174726221237855e-05, |
| "loss": 0.0007, |
| "step": 2500 |
| }, |
| { |
| "epoch": 2.087707641196013, |
| "grad_norm": 0.013363192789256573, |
| "learning_rate": 3.955949304786514e-05, |
| "loss": 0.005, |
| "step": 2600 |
| }, |
| { |
| "epoch": 2.098781838316722, |
| "grad_norm": 0.03008888103067875, |
| "learning_rate": 3.8944259874492434e-05, |
| "loss": 0.0191, |
| "step": 2700 |
| }, |
| { |
| "epoch": 2.100110741971207, |
| "eval_accuracy": 0.9925280199252802, |
| "eval_loss": 0.023914234712719917, |
| "eval_runtime": 202.6495, |
| "eval_samples_per_second": 3.963, |
| "eval_steps_per_second": 0.498, |
| "step": 2712 |
| }, |
| { |
| "epoch": 3.009745293466224, |
| "grad_norm": 0.0100622633472085, |
| "learning_rate": 3.832902670111973e-05, |
| "loss": 0.0038, |
| "step": 2800 |
| }, |
| { |
| "epoch": 3.0208194905869323, |
| "grad_norm": 0.010149353183805943, |
| "learning_rate": 3.7713793527747014e-05, |
| "loss": 0.0009, |
| "step": 2900 |
| }, |
| { |
| "epoch": 3.0318936877076412, |
| "grad_norm": 0.005930065177381039, |
| "learning_rate": 3.7098560354374314e-05, |
| "loss": 0.0005, |
| "step": 3000 |
| }, |
| { |
| "epoch": 3.04296788482835, |
| "grad_norm": 0.010781911201775074, |
| "learning_rate": 3.64833271810016e-05, |
| "loss": 0.0044, |
| "step": 3100 |
| }, |
| { |
| "epoch": 3.0540420819490586, |
| "grad_norm": 0.010279743000864983, |
| "learning_rate": 3.5868094007628894e-05, |
| "loss": 0.0121, |
| "step": 3200 |
| }, |
| { |
| "epoch": 3.0651162790697675, |
| "grad_norm": 0.013513376004993916, |
| "learning_rate": 3.525286083425619e-05, |
| "loss": 0.0025, |
| "step": 3300 |
| }, |
| { |
| "epoch": 3.0761904761904764, |
| "grad_norm": 0.05831762030720711, |
| "learning_rate": 3.463762766088347e-05, |
| "loss": 0.0012, |
| "step": 3400 |
| }, |
| { |
| "epoch": 3.087264673311185, |
| "grad_norm": 0.05180026963353157, |
| "learning_rate": 3.4022394487510767e-05, |
| "loss": 0.0272, |
| "step": 3500 |
| }, |
| { |
| "epoch": 3.0983388704318937, |
| "grad_norm": 0.016193652525544167, |
| "learning_rate": 3.340716131413806e-05, |
| "loss": 0.0169, |
| "step": 3600 |
| }, |
| { |
| "epoch": 3.100110741971207, |
| "eval_accuracy": 0.9912826899128269, |
| "eval_loss": 0.03048611246049404, |
| "eval_runtime": 186.7323, |
| "eval_samples_per_second": 4.3, |
| "eval_steps_per_second": 0.541, |
| "step": 3616 |
| }, |
| { |
| "epoch": 4.0093023255813955, |
| "grad_norm": 0.04684939235448837, |
| "learning_rate": 3.2791928140765346e-05, |
| "loss": 0.0018, |
| "step": 3700 |
| }, |
| { |
| "epoch": 4.020376522702104, |
| "grad_norm": 0.015213378705084324, |
| "learning_rate": 3.2176694967392646e-05, |
| "loss": 0.0084, |
| "step": 3800 |
| }, |
| { |
| "epoch": 4.0314507198228124, |
| "grad_norm": 0.008424785919487476, |
| "learning_rate": 3.156146179401994e-05, |
| "loss": 0.0063, |
| "step": 3900 |
| }, |
| { |
| "epoch": 4.042524916943521, |
| "grad_norm": 0.0028675757348537445, |
| "learning_rate": 3.0946228620647226e-05, |
| "loss": 0.0003, |
| "step": 4000 |
| }, |
| { |
| "epoch": 4.05359911406423, |
| "grad_norm": 0.009860913269221783, |
| "learning_rate": 3.033099544727452e-05, |
| "loss": 0.0018, |
| "step": 4100 |
| }, |
| { |
| "epoch": 4.064673311184939, |
| "grad_norm": 0.08612042665481567, |
| "learning_rate": 2.971576227390181e-05, |
| "loss": 0.0108, |
| "step": 4200 |
| }, |
| { |
| "epoch": 4.075747508305648, |
| "grad_norm": 0.015194080770015717, |
| "learning_rate": 2.91005291005291e-05, |
| "loss": 0.0023, |
| "step": 4300 |
| }, |
| { |
| "epoch": 4.086821705426357, |
| "grad_norm": 0.0368819497525692, |
| "learning_rate": 2.8485295927156392e-05, |
| "loss": 0.001, |
| "step": 4400 |
| }, |
| { |
| "epoch": 4.097895902547065, |
| "grad_norm": 0.014080989174544811, |
| "learning_rate": 2.787006275378369e-05, |
| "loss": 0.0008, |
| "step": 4500 |
| }, |
| { |
| "epoch": 4.100110741971207, |
| "eval_accuracy": 0.9975093399750934, |
| "eval_loss": 0.012555562891066074, |
| "eval_runtime": 182.9036, |
| "eval_samples_per_second": 4.39, |
| "eval_steps_per_second": 0.552, |
| "step": 4520 |
| }, |
| { |
| "epoch": 5.008859357696567, |
| "grad_norm": 0.026085326448082924, |
| "learning_rate": 2.725482958041098e-05, |
| "loss": 0.0019, |
| "step": 4600 |
| }, |
| { |
| "epoch": 5.019933554817276, |
| "grad_norm": 0.00664695305749774, |
| "learning_rate": 2.6639596407038268e-05, |
| "loss": 0.0033, |
| "step": 4700 |
| }, |
| { |
| "epoch": 5.0310077519379846, |
| "grad_norm": 0.0021630304399877787, |
| "learning_rate": 2.602436323366556e-05, |
| "loss": 0.0003, |
| "step": 4800 |
| }, |
| { |
| "epoch": 5.0420819490586934, |
| "grad_norm": 0.005731029435992241, |
| "learning_rate": 2.540913006029285e-05, |
| "loss": 0.0002, |
| "step": 4900 |
| }, |
| { |
| "epoch": 5.053156146179402, |
| "grad_norm": 0.0024967463687062263, |
| "learning_rate": 2.479389688692014e-05, |
| "loss": 0.0002, |
| "step": 5000 |
| }, |
| { |
| "epoch": 5.06423034330011, |
| "grad_norm": 0.003203805536031723, |
| "learning_rate": 2.4178663713547438e-05, |
| "loss": 0.0002, |
| "step": 5100 |
| }, |
| { |
| "epoch": 5.075304540420819, |
| "grad_norm": 0.001881565898656845, |
| "learning_rate": 2.3563430540174727e-05, |
| "loss": 0.0002, |
| "step": 5200 |
| }, |
| { |
| "epoch": 5.086378737541528, |
| "grad_norm": 0.0017551712226122618, |
| "learning_rate": 2.2948197366802017e-05, |
| "loss": 0.0002, |
| "step": 5300 |
| }, |
| { |
| "epoch": 5.097452934662237, |
| "grad_norm": 0.0013360229786485434, |
| "learning_rate": 2.233296419342931e-05, |
| "loss": 0.0001, |
| "step": 5400 |
| }, |
| { |
| "epoch": 5.100110741971207, |
| "eval_accuracy": 0.9962640099626401, |
| "eval_loss": 0.007705440279096365, |
| "eval_runtime": 177.5303, |
| "eval_samples_per_second": 4.523, |
| "eval_steps_per_second": 0.569, |
| "step": 5424 |
| }, |
| { |
| "epoch": 6.008416389811739, |
| "grad_norm": 0.0024486565962433815, |
| "learning_rate": 2.1717731020056604e-05, |
| "loss": 0.0001, |
| "step": 5500 |
| }, |
| { |
| "epoch": 6.019490586932448, |
| "grad_norm": 0.0011960830306634307, |
| "learning_rate": 2.1102497846683894e-05, |
| "loss": 0.0001, |
| "step": 5600 |
| }, |
| { |
| "epoch": 6.030564784053156, |
| "grad_norm": 0.002331072697415948, |
| "learning_rate": 2.0487264673311183e-05, |
| "loss": 0.0001, |
| "step": 5700 |
| }, |
| { |
| "epoch": 6.041638981173865, |
| "grad_norm": 0.0012679151259362698, |
| "learning_rate": 1.987203149993848e-05, |
| "loss": 0.0001, |
| "step": 5800 |
| }, |
| { |
| "epoch": 6.052713178294574, |
| "grad_norm": 0.0020030313171446323, |
| "learning_rate": 1.925679832656577e-05, |
| "loss": 0.0001, |
| "step": 5900 |
| }, |
| { |
| "epoch": 6.0637873754152825, |
| "grad_norm": 0.003349652513861656, |
| "learning_rate": 1.864156515319306e-05, |
| "loss": 0.015, |
| "step": 6000 |
| }, |
| { |
| "epoch": 6.074861572535991, |
| "grad_norm": 0.012170190922915936, |
| "learning_rate": 1.8026331979820353e-05, |
| "loss": 0.0042, |
| "step": 6100 |
| }, |
| { |
| "epoch": 6.0859357696567, |
| "grad_norm": 0.008038354106247425, |
| "learning_rate": 1.7411098806447646e-05, |
| "loss": 0.0002, |
| "step": 6200 |
| }, |
| { |
| "epoch": 6.097009966777408, |
| "grad_norm": 0.0046376571990549564, |
| "learning_rate": 1.6795865633074936e-05, |
| "loss": 0.0001, |
| "step": 6300 |
| }, |
| { |
| "epoch": 6.100110741971207, |
| "eval_accuracy": 0.9962640099626401, |
| "eval_loss": 0.022780200466513634, |
| "eval_runtime": 177.4915, |
| "eval_samples_per_second": 4.524, |
| "eval_steps_per_second": 0.569, |
| "step": 6328 |
| }, |
| { |
| "epoch": 7.00797342192691, |
| "grad_norm": 0.001398948603309691, |
| "learning_rate": 1.6180632459702226e-05, |
| "loss": 0.0001, |
| "step": 6400 |
| }, |
| { |
| "epoch": 7.019047619047619, |
| "grad_norm": 0.0018464713357388973, |
| "learning_rate": 1.556539928632952e-05, |
| "loss": 0.0001, |
| "step": 6500 |
| }, |
| { |
| "epoch": 7.030121816168328, |
| "grad_norm": 0.0012479424476623535, |
| "learning_rate": 1.4950166112956812e-05, |
| "loss": 0.0001, |
| "step": 6600 |
| }, |
| { |
| "epoch": 7.041196013289037, |
| "grad_norm": 0.0021251088473945856, |
| "learning_rate": 1.4334932939584104e-05, |
| "loss": 0.0001, |
| "step": 6700 |
| }, |
| { |
| "epoch": 7.052270210409746, |
| "grad_norm": 0.0013992477906867862, |
| "learning_rate": 1.3719699766211393e-05, |
| "loss": 0.0001, |
| "step": 6800 |
| }, |
| { |
| "epoch": 7.063344407530454, |
| "grad_norm": 0.002737658564001322, |
| "learning_rate": 1.3104466592838688e-05, |
| "loss": 0.0001, |
| "step": 6900 |
| }, |
| { |
| "epoch": 7.074418604651163, |
| "grad_norm": 0.003131190547719598, |
| "learning_rate": 1.2489233419465978e-05, |
| "loss": 0.0001, |
| "step": 7000 |
| }, |
| { |
| "epoch": 7.0854928017718715, |
| "grad_norm": 0.0008928414317779243, |
| "learning_rate": 1.187400024609327e-05, |
| "loss": 0.0001, |
| "step": 7100 |
| }, |
| { |
| "epoch": 7.09656699889258, |
| "grad_norm": 0.003003242425620556, |
| "learning_rate": 1.1258767072720563e-05, |
| "loss": 0.0001, |
| "step": 7200 |
| }, |
| { |
| "epoch": 7.100110741971207, |
| "eval_accuracy": 0.9975093399750934, |
| "eval_loss": 0.0162957850843668, |
| "eval_runtime": 175.2944, |
| "eval_samples_per_second": 4.581, |
| "eval_steps_per_second": 0.576, |
| "step": 7232 |
| }, |
| { |
| "epoch": 8.007530454042081, |
| "grad_norm": 0.0015305023407563567, |
| "learning_rate": 1.0643533899347853e-05, |
| "loss": 0.0001, |
| "step": 7300 |
| }, |
| { |
| "epoch": 8.018604651162791, |
| "grad_norm": 0.0009707214194349945, |
| "learning_rate": 1.0028300725975146e-05, |
| "loss": 0.0001, |
| "step": 7400 |
| }, |
| { |
| "epoch": 8.029678848283499, |
| "grad_norm": 0.0015318732475861907, |
| "learning_rate": 9.413067552602436e-06, |
| "loss": 0.0001, |
| "step": 7500 |
| }, |
| { |
| "epoch": 8.040753045404209, |
| "grad_norm": 0.0013183602131903172, |
| "learning_rate": 8.797834379229729e-06, |
| "loss": 0.0001, |
| "step": 7600 |
| }, |
| { |
| "epoch": 8.051827242524917, |
| "grad_norm": 0.0007716185064055026, |
| "learning_rate": 8.18260120585702e-06, |
| "loss": 0.0001, |
| "step": 7700 |
| }, |
| { |
| "epoch": 8.062901439645625, |
| "grad_norm": 0.0033044065348803997, |
| "learning_rate": 7.567368032484312e-06, |
| "loss": 0.0001, |
| "step": 7800 |
| }, |
| { |
| "epoch": 8.073975636766335, |
| "grad_norm": 0.0012280073715373874, |
| "learning_rate": 6.952134859111603e-06, |
| "loss": 0.0001, |
| "step": 7900 |
| }, |
| { |
| "epoch": 8.085049833887043, |
| "grad_norm": 0.0006749368621967733, |
| "learning_rate": 6.336901685738895e-06, |
| "loss": 0.0001, |
| "step": 8000 |
| }, |
| { |
| "epoch": 8.096124031007752, |
| "grad_norm": 0.0012479163706302643, |
| "learning_rate": 5.7216685123661875e-06, |
| "loss": 0.0001, |
| "step": 8100 |
| }, |
| { |
| "epoch": 8.100110741971207, |
| "eval_accuracy": 0.9975093399750934, |
| "eval_loss": 0.015746863558888435, |
| "eval_runtime": 167.1139, |
| "eval_samples_per_second": 4.805, |
| "eval_steps_per_second": 0.604, |
| "step": 8136 |
| }, |
| { |
| "epoch": 9.007087486157253, |
| "grad_norm": 0.0012506992788985372, |
| "learning_rate": 5.106435338993479e-06, |
| "loss": 0.0001, |
| "step": 8200 |
| }, |
| { |
| "epoch": 9.018161683277963, |
| "grad_norm": 0.0007666904130019248, |
| "learning_rate": 4.4912021656207705e-06, |
| "loss": 0.0001, |
| "step": 8300 |
| }, |
| { |
| "epoch": 9.029235880398671, |
| "grad_norm": 0.001267068088054657, |
| "learning_rate": 3.875968992248062e-06, |
| "loss": 0.0001, |
| "step": 8400 |
| }, |
| { |
| "epoch": 9.04031007751938, |
| "grad_norm": 0.0007247941102832556, |
| "learning_rate": 3.260735818875354e-06, |
| "loss": 0.0001, |
| "step": 8500 |
| }, |
| { |
| "epoch": 9.051384274640089, |
| "grad_norm": 0.000805841526016593, |
| "learning_rate": 2.6455026455026455e-06, |
| "loss": 0.0001, |
| "step": 8600 |
| }, |
| { |
| "epoch": 9.062458471760797, |
| "grad_norm": 0.0007739869179204106, |
| "learning_rate": 2.0302694721299375e-06, |
| "loss": 0.0001, |
| "step": 8700 |
| }, |
| { |
| "epoch": 9.073532668881507, |
| "grad_norm": 0.0008207521168515086, |
| "learning_rate": 1.415036298757229e-06, |
| "loss": 0.0001, |
| "step": 8800 |
| }, |
| { |
| "epoch": 9.084606866002215, |
| "grad_norm": 0.0008044055430218577, |
| "learning_rate": 7.998031253845208e-07, |
| "loss": 0.0001, |
| "step": 8900 |
| }, |
| { |
| "epoch": 9.095681063122923, |
| "grad_norm": 0.0007077198824845254, |
| "learning_rate": 1.8456995201181249e-07, |
| "loss": 0.0001, |
| "step": 9000 |
| }, |
| { |
| "epoch": 9.099003322259136, |
| "eval_accuracy": 0.9975093399750934, |
| "eval_loss": 0.01572454161942005, |
| "eval_runtime": 175.3925, |
| "eval_samples_per_second": 4.578, |
| "eval_steps_per_second": 0.576, |
| "step": 9030 |
| }, |
| { |
| "epoch": 9.099003322259136, |
| "step": 9030, |
| "total_flos": 6.328460909097596e+19, |
| "train_loss": 0.18755709112447544, |
| "train_runtime": 22812.8611, |
| "train_samples_per_second": 3.167, |
| "train_steps_per_second": 0.396 |
| }, |
| { |
| "epoch": 9.099003322259136, |
| "eval_accuracy": 0.7641065830721003, |
| "eval_loss": 0.8574168086051941, |
| "eval_runtime": 273.0523, |
| "eval_samples_per_second": 4.673, |
| "eval_steps_per_second": 0.586, |
| "step": 9030 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 9030, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6.328460909097596e+19, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
