| { | |
| "best_metric": 0.8055538535118103, | |
| "best_model_checkpoint": "./kd_results/apple/mobilevit-x-small_alpha0.5_temp5.0/checkpoint-1710", | |
| "epoch": 20.0, | |
| "eval_steps": 500, | |
| "global_step": 1800, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 2.9469170570373535, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 1.2674, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 2.080336332321167, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 1.2049, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 2.5571956634521484, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 1.1992, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.30533596837944665, | |
| "eval_loss": 1.381278157234192, | |
| "eval_runtime": 28.4132, | |
| "eval_samples_per_second": 35.617, | |
| "eval_steps_per_second": 0.563, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.1111111111111112, | |
| "grad_norm": 2.39298677444458, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 1.1882, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.3888888888888888, | |
| "grad_norm": 2.2335567474365234, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 1.1765, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 1.4417985677719116, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 1.1972, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.9444444444444444, | |
| "grad_norm": 3.157533645629883, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.1608, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.3774703557312253, | |
| "eval_loss": 1.316684365272522, | |
| "eval_runtime": 29.6651, | |
| "eval_samples_per_second": 34.114, | |
| "eval_steps_per_second": 0.539, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 4.490560531616211, | |
| "learning_rate": 4.938271604938271e-05, | |
| "loss": 1.115, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.5, | |
| "grad_norm": 3.1158812046051025, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.1037, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 2.7777777777777777, | |
| "grad_norm": 2.252438545227051, | |
| "learning_rate": 4.783950617283951e-05, | |
| "loss": 1.0525, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.47035573122529645, | |
| "eval_loss": 1.1715766191482544, | |
| "eval_runtime": 28.3741, | |
| "eval_samples_per_second": 35.666, | |
| "eval_steps_per_second": 0.564, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 3.0555555555555554, | |
| "grad_norm": 3.0625267028808594, | |
| "learning_rate": 4.70679012345679e-05, | |
| "loss": 1.0325, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 3.3333333333333335, | |
| "grad_norm": 3.476041793823242, | |
| "learning_rate": 4.62962962962963e-05, | |
| "loss": 0.9649, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 3.611111111111111, | |
| "grad_norm": 4.546514511108398, | |
| "learning_rate": 4.5524691358024696e-05, | |
| "loss": 0.9415, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 3.888888888888889, | |
| "grad_norm": 2.9131317138671875, | |
| "learning_rate": 4.4753086419753084e-05, | |
| "loss": 0.9202, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5296442687747036, | |
| "eval_loss": 1.0438213348388672, | |
| "eval_runtime": 28.0735, | |
| "eval_samples_per_second": 36.048, | |
| "eval_steps_per_second": 0.57, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 4.166666666666667, | |
| "grad_norm": 5.311016082763672, | |
| "learning_rate": 4.3981481481481486e-05, | |
| "loss": 0.8723, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 4.37046480178833, | |
| "learning_rate": 4.3209876543209875e-05, | |
| "loss": 0.821, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.722222222222222, | |
| "grad_norm": 4.072926044464111, | |
| "learning_rate": 4.243827160493827e-05, | |
| "loss": 0.8291, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 4.029878616333008, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.8105, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.5859683794466403, | |
| "eval_loss": 0.9462578296661377, | |
| "eval_runtime": 28.3122, | |
| "eval_samples_per_second": 35.744, | |
| "eval_steps_per_second": 0.565, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 5.277777777777778, | |
| "grad_norm": 3.004589319229126, | |
| "learning_rate": 4.089506172839506e-05, | |
| "loss": 0.7791, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 5.555555555555555, | |
| "grad_norm": 5.563127517700195, | |
| "learning_rate": 4.012345679012346e-05, | |
| "loss": 0.773, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 5.833333333333333, | |
| "grad_norm": 3.6668524742126465, | |
| "learning_rate": 3.935185185185186e-05, | |
| "loss": 0.7675, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5948616600790514, | |
| "eval_loss": 0.9054595828056335, | |
| "eval_runtime": 28.4443, | |
| "eval_samples_per_second": 35.578, | |
| "eval_steps_per_second": 0.563, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 6.111111111111111, | |
| "grad_norm": 3.786341667175293, | |
| "learning_rate": 3.8580246913580246e-05, | |
| "loss": 0.7253, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 6.388888888888889, | |
| "grad_norm": 4.171977519989014, | |
| "learning_rate": 3.780864197530865e-05, | |
| "loss": 0.7315, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 6.666666666666667, | |
| "grad_norm": 3.605607271194458, | |
| "learning_rate": 3.7037037037037037e-05, | |
| "loss": 0.7045, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 6.944444444444445, | |
| "grad_norm": 5.259735584259033, | |
| "learning_rate": 3.626543209876543e-05, | |
| "loss": 0.7178, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.6294466403162056, | |
| "eval_loss": 0.8651202321052551, | |
| "eval_runtime": 28.6025, | |
| "eval_samples_per_second": 35.381, | |
| "eval_steps_per_second": 0.559, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 7.222222222222222, | |
| "grad_norm": 4.372884273529053, | |
| "learning_rate": 3.5493827160493834e-05, | |
| "loss": 0.6765, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "grad_norm": 4.141205787658691, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.6915, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 7.777777777777778, | |
| "grad_norm": 7.093691349029541, | |
| "learning_rate": 3.395061728395062e-05, | |
| "loss": 0.6966, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.6205533596837944, | |
| "eval_loss": 0.8815840482711792, | |
| "eval_runtime": 28.5107, | |
| "eval_samples_per_second": 35.495, | |
| "eval_steps_per_second": 0.561, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 8.055555555555555, | |
| "grad_norm": 4.123745918273926, | |
| "learning_rate": 3.317901234567901e-05, | |
| "loss": 0.6865, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 8.333333333333334, | |
| "grad_norm": 6.377141952514648, | |
| "learning_rate": 3.240740740740741e-05, | |
| "loss": 0.6576, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 8.61111111111111, | |
| "grad_norm": 3.1896352767944336, | |
| "learning_rate": 3.16358024691358e-05, | |
| "loss": 0.6805, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 4.059895992279053, | |
| "learning_rate": 3.08641975308642e-05, | |
| "loss": 0.6529, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.6403162055335968, | |
| "eval_loss": 0.8389874696731567, | |
| "eval_runtime": 27.992, | |
| "eval_samples_per_second": 36.153, | |
| "eval_steps_per_second": 0.572, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 9.166666666666666, | |
| "grad_norm": 4.472728729248047, | |
| "learning_rate": 3.0092592592592593e-05, | |
| "loss": 0.6457, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 9.444444444444445, | |
| "grad_norm": 4.729041576385498, | |
| "learning_rate": 2.9320987654320992e-05, | |
| "loss": 0.6429, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 9.722222222222221, | |
| "grad_norm": 6.510581970214844, | |
| "learning_rate": 2.8549382716049384e-05, | |
| "loss": 0.629, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 9.386911392211914, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.6468, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.6393280632411067, | |
| "eval_loss": 0.8408231139183044, | |
| "eval_runtime": 28.3937, | |
| "eval_samples_per_second": 35.642, | |
| "eval_steps_per_second": 0.564, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 10.277777777777779, | |
| "grad_norm": 5.807169437408447, | |
| "learning_rate": 2.700617283950617e-05, | |
| "loss": 0.62, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 10.555555555555555, | |
| "grad_norm": 6.632133960723877, | |
| "learning_rate": 2.623456790123457e-05, | |
| "loss": 0.6115, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 10.833333333333334, | |
| "grad_norm": 4.720981597900391, | |
| "learning_rate": 2.5462962962962965e-05, | |
| "loss": 0.6115, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.6561264822134387, | |
| "eval_loss": 0.819645345211029, | |
| "eval_runtime": 28.2873, | |
| "eval_samples_per_second": 35.776, | |
| "eval_steps_per_second": 0.566, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 11.11111111111111, | |
| "grad_norm": 4.817243576049805, | |
| "learning_rate": 2.4691358024691357e-05, | |
| "loss": 0.6212, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 11.38888888888889, | |
| "grad_norm": 3.907813549041748, | |
| "learning_rate": 2.3919753086419755e-05, | |
| "loss": 0.5913, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 11.666666666666666, | |
| "grad_norm": 7.131424903869629, | |
| "learning_rate": 2.314814814814815e-05, | |
| "loss": 0.6017, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 11.944444444444445, | |
| "grad_norm": 5.066920280456543, | |
| "learning_rate": 2.2376543209876542e-05, | |
| "loss": 0.6059, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.6551383399209486, | |
| "eval_loss": 0.8352712988853455, | |
| "eval_runtime": 28.189, | |
| "eval_samples_per_second": 35.901, | |
| "eval_steps_per_second": 0.568, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 12.222222222222221, | |
| "grad_norm": 4.657469749450684, | |
| "learning_rate": 2.1604938271604937e-05, | |
| "loss": 0.5882, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "grad_norm": 3.6020100116729736, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.5797, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 12.777777777777779, | |
| "grad_norm": 3.7327208518981934, | |
| "learning_rate": 2.006172839506173e-05, | |
| "loss": 0.5808, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.6373517786561265, | |
| "eval_loss": 0.8467521071434021, | |
| "eval_runtime": 28.0971, | |
| "eval_samples_per_second": 36.018, | |
| "eval_steps_per_second": 0.569, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 13.055555555555555, | |
| "grad_norm": 3.4519283771514893, | |
| "learning_rate": 1.9290123456790123e-05, | |
| "loss": 0.568, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 4.435120582580566, | |
| "learning_rate": 1.8518518518518518e-05, | |
| "loss": 0.5737, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 13.61111111111111, | |
| "grad_norm": 6.875541687011719, | |
| "learning_rate": 1.7746913580246917e-05, | |
| "loss": 0.5679, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 13.88888888888889, | |
| "grad_norm": 4.120852470397949, | |
| "learning_rate": 1.697530864197531e-05, | |
| "loss": 0.5506, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.6452569169960475, | |
| "eval_loss": 0.826992392539978, | |
| "eval_runtime": 27.8418, | |
| "eval_samples_per_second": 36.348, | |
| "eval_steps_per_second": 0.575, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 14.166666666666666, | |
| "grad_norm": 6.546832084655762, | |
| "learning_rate": 1.6203703703703704e-05, | |
| "loss": 0.5609, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 14.444444444444445, | |
| "grad_norm": 3.1915016174316406, | |
| "learning_rate": 1.54320987654321e-05, | |
| "loss": 0.5386, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 14.722222222222221, | |
| "grad_norm": 4.805222034454346, | |
| "learning_rate": 1.4660493827160496e-05, | |
| "loss": 0.5494, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "grad_norm": 8.955787658691406, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.5535, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.6403162055335968, | |
| "eval_loss": 0.8425170183181763, | |
| "eval_runtime": 28.2606, | |
| "eval_samples_per_second": 35.81, | |
| "eval_steps_per_second": 0.566, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 15.277777777777779, | |
| "grad_norm": 4.203817844390869, | |
| "learning_rate": 1.3117283950617285e-05, | |
| "loss": 0.54, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 15.555555555555555, | |
| "grad_norm": 4.972456932067871, | |
| "learning_rate": 1.2345679012345678e-05, | |
| "loss": 0.5483, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 15.833333333333334, | |
| "grad_norm": 5.730295181274414, | |
| "learning_rate": 1.1574074074074075e-05, | |
| "loss": 0.5444, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6541501976284585, | |
| "eval_loss": 0.8188127279281616, | |
| "eval_runtime": 29.1289, | |
| "eval_samples_per_second": 34.742, | |
| "eval_steps_per_second": 0.549, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 16.11111111111111, | |
| "grad_norm": 3.0186612606048584, | |
| "learning_rate": 1.0802469135802469e-05, | |
| "loss": 0.5238, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 16.38888888888889, | |
| "grad_norm": 6.202972888946533, | |
| "learning_rate": 1.0030864197530866e-05, | |
| "loss": 0.526, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 16.666666666666668, | |
| "grad_norm": 5.40784215927124, | |
| "learning_rate": 9.259259259259259e-06, | |
| "loss": 0.5382, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 16.944444444444443, | |
| "grad_norm": 4.7741289138793945, | |
| "learning_rate": 8.487654320987654e-06, | |
| "loss": 0.5409, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.650197628458498, | |
| "eval_loss": 0.8201938271522522, | |
| "eval_runtime": 28.8112, | |
| "eval_samples_per_second": 35.125, | |
| "eval_steps_per_second": 0.555, | |
| "step": 1530 | |
| }, | |
| { | |
| "epoch": 17.22222222222222, | |
| "grad_norm": 3.855323076248169, | |
| "learning_rate": 7.71604938271605e-06, | |
| "loss": 0.5121, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 17.5, | |
| "grad_norm": 3.3022570610046387, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.5263, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 3.919414758682251, | |
| "learning_rate": 6.172839506172839e-06, | |
| "loss": 0.5296, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.6590909090909091, | |
| "eval_loss": 0.8192811608314514, | |
| "eval_runtime": 28.2571, | |
| "eval_samples_per_second": 35.814, | |
| "eval_steps_per_second": 0.566, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 18.055555555555557, | |
| "grad_norm": 3.4299302101135254, | |
| "learning_rate": 5.401234567901234e-06, | |
| "loss": 0.5327, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 18.333333333333332, | |
| "grad_norm": 5.236651420593262, | |
| "learning_rate": 4.6296296296296296e-06, | |
| "loss": 0.5256, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 18.61111111111111, | |
| "grad_norm": 5.799625873565674, | |
| "learning_rate": 3.858024691358025e-06, | |
| "loss": 0.5168, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 18.88888888888889, | |
| "grad_norm": 4.350020885467529, | |
| "learning_rate": 3.0864197530864196e-06, | |
| "loss": 0.5153, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.6669960474308301, | |
| "eval_loss": 0.8055538535118103, | |
| "eval_runtime": 27.5817, | |
| "eval_samples_per_second": 36.691, | |
| "eval_steps_per_second": 0.58, | |
| "step": 1710 | |
| }, | |
| { | |
| "epoch": 19.166666666666668, | |
| "grad_norm": 4.532427787780762, | |
| "learning_rate": 2.3148148148148148e-06, | |
| "loss": 0.5279, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 19.444444444444443, | |
| "grad_norm": 3.3536760807037354, | |
| "learning_rate": 1.5432098765432098e-06, | |
| "loss": 0.5003, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 19.72222222222222, | |
| "grad_norm": 5.3923187255859375, | |
| "learning_rate": 7.716049382716049e-07, | |
| "loss": 0.5386, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "grad_norm": 9.573280334472656, | |
| "learning_rate": 0.0, | |
| "loss": 0.5239, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6590909090909091, | |
| "eval_loss": 0.8193751573562622, | |
| "eval_runtime": 28.2869, | |
| "eval_samples_per_second": 35.776, | |
| "eval_steps_per_second": 0.566, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "step": 1800, | |
| "total_flos": 0.0, | |
| "train_loss": 0.7131537093056572, | |
| "train_runtime": 10327.1494, | |
| "train_samples_per_second": 11.097, | |
| "train_steps_per_second": 0.174 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1800, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "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": 0.0, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |