| { | |
| "best_metric": 0.8256880733944955, | |
| "best_model_checkpoint": "swiftformer-xs-dmae-va-U-80/checkpoint-480", | |
| "epoch": 72.25806451612904, | |
| "eval_steps": 500, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.9, | |
| "eval_accuracy": 0.28440366972477066, | |
| "eval_loss": 1.3862813711166382, | |
| "eval_runtime": 0.4815, | |
| "eval_samples_per_second": 226.357, | |
| "eval_steps_per_second": 8.307, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 1.4158, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.3119266055045872, | |
| "eval_loss": 1.376009225845337, | |
| "eval_runtime": 0.4374, | |
| "eval_samples_per_second": 249.207, | |
| "eval_steps_per_second": 9.145, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 1.3853, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 2.97, | |
| "eval_accuracy": 0.3853211009174312, | |
| "eval_loss": 1.3548262119293213, | |
| "eval_runtime": 0.4385, | |
| "eval_samples_per_second": 248.6, | |
| "eval_steps_per_second": 9.123, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 3.87, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 1.3745, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.3394495412844037, | |
| "eval_loss": 1.3327373266220093, | |
| "eval_runtime": 0.4339, | |
| "eval_samples_per_second": 251.182, | |
| "eval_steps_per_second": 9.218, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 4.9, | |
| "eval_accuracy": 0.42201834862385323, | |
| "eval_loss": 1.2938013076782227, | |
| "eval_runtime": 0.425, | |
| "eval_samples_per_second": 256.451, | |
| "eval_steps_per_second": 9.411, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 5.16, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 1.3435, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 5.94, | |
| "eval_accuracy": 0.46788990825688076, | |
| "eval_loss": 1.244996428489685, | |
| "eval_runtime": 0.4464, | |
| "eval_samples_per_second": 244.203, | |
| "eval_steps_per_second": 8.962, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 6.45, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 1.2681, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 6.97, | |
| "eval_accuracy": 0.5596330275229358, | |
| "eval_loss": 1.193323016166687, | |
| "eval_runtime": 0.4543, | |
| "eval_samples_per_second": 239.924, | |
| "eval_steps_per_second": 8.805, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 7.74, | |
| "learning_rate": 4.960317460317461e-05, | |
| "loss": 1.1803, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.47706422018348627, | |
| "eval_loss": 1.1410021781921387, | |
| "eval_runtime": 0.5443, | |
| "eval_samples_per_second": 200.245, | |
| "eval_steps_per_second": 7.348, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 8.9, | |
| "eval_accuracy": 0.5045871559633027, | |
| "eval_loss": 1.1014117002487183, | |
| "eval_runtime": 0.4243, | |
| "eval_samples_per_second": 256.877, | |
| "eval_steps_per_second": 9.427, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 4.8611111111111115e-05, | |
| "loss": 1.1277, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 9.94, | |
| "eval_accuracy": 0.5321100917431193, | |
| "eval_loss": 1.0785263776779175, | |
| "eval_runtime": 0.5813, | |
| "eval_samples_per_second": 187.522, | |
| "eval_steps_per_second": 6.882, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 10.32, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 1.0674, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "eval_accuracy": 0.5596330275229358, | |
| "eval_loss": 1.0439504384994507, | |
| "eval_runtime": 0.877, | |
| "eval_samples_per_second": 124.292, | |
| "eval_steps_per_second": 4.561, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 11.61, | |
| "learning_rate": 4.662698412698413e-05, | |
| "loss": 1.0353, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.5779816513761468, | |
| "eval_loss": 0.9961591362953186, | |
| "eval_runtime": 0.4276, | |
| "eval_samples_per_second": 254.912, | |
| "eval_steps_per_second": 9.355, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "learning_rate": 4.563492063492064e-05, | |
| "loss": 0.9859, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 12.9, | |
| "eval_accuracy": 0.5871559633027523, | |
| "eval_loss": 0.9699747562408447, | |
| "eval_runtime": 0.488, | |
| "eval_samples_per_second": 223.356, | |
| "eval_steps_per_second": 8.197, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 13.94, | |
| "eval_accuracy": 0.6422018348623854, | |
| "eval_loss": 0.9401906728744507, | |
| "eval_runtime": 0.426, | |
| "eval_samples_per_second": 255.868, | |
| "eval_steps_per_second": 9.39, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 14.19, | |
| "learning_rate": 4.464285714285715e-05, | |
| "loss": 0.9397, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 14.97, | |
| "eval_accuracy": 0.6238532110091743, | |
| "eval_loss": 0.9215461015701294, | |
| "eval_runtime": 0.595, | |
| "eval_samples_per_second": 183.202, | |
| "eval_steps_per_second": 6.723, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 15.48, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.8959, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.6605504587155964, | |
| "eval_loss": 0.8744844794273376, | |
| "eval_runtime": 0.4502, | |
| "eval_samples_per_second": 242.121, | |
| "eval_steps_per_second": 8.885, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 16.77, | |
| "learning_rate": 4.265873015873016e-05, | |
| "loss": 0.8663, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 16.9, | |
| "eval_accuracy": 0.6697247706422018, | |
| "eval_loss": 0.8560922145843506, | |
| "eval_runtime": 0.4537, | |
| "eval_samples_per_second": 240.261, | |
| "eval_steps_per_second": 8.817, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 17.94, | |
| "eval_accuracy": 0.6788990825688074, | |
| "eval_loss": 0.8181523084640503, | |
| "eval_runtime": 0.4306, | |
| "eval_samples_per_second": 253.131, | |
| "eval_steps_per_second": 9.289, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 18.06, | |
| "learning_rate": 4.166666666666667e-05, | |
| "loss": 0.8405, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 18.97, | |
| "eval_accuracy": 0.6513761467889908, | |
| "eval_loss": 0.8167656660079956, | |
| "eval_runtime": 0.4512, | |
| "eval_samples_per_second": 241.596, | |
| "eval_steps_per_second": 8.866, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 19.35, | |
| "learning_rate": 4.067460317460318e-05, | |
| "loss": 0.8093, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.6788990825688074, | |
| "eval_loss": 0.8038831949234009, | |
| "eval_runtime": 0.434, | |
| "eval_samples_per_second": 251.165, | |
| "eval_steps_per_second": 9.217, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 20.65, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.7396, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 20.9, | |
| "eval_accuracy": 0.7064220183486238, | |
| "eval_loss": 0.7477715015411377, | |
| "eval_runtime": 0.44, | |
| "eval_samples_per_second": 247.725, | |
| "eval_steps_per_second": 9.091, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "learning_rate": 3.8690476190476195e-05, | |
| "loss": 0.7588, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 21.94, | |
| "eval_accuracy": 0.6972477064220184, | |
| "eval_loss": 0.7236711978912354, | |
| "eval_runtime": 0.6128, | |
| "eval_samples_per_second": 177.862, | |
| "eval_steps_per_second": 6.527, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 22.97, | |
| "eval_accuracy": 0.7155963302752294, | |
| "eval_loss": 0.7030771374702454, | |
| "eval_runtime": 0.4488, | |
| "eval_samples_per_second": 242.893, | |
| "eval_steps_per_second": 8.913, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 23.23, | |
| "learning_rate": 3.76984126984127e-05, | |
| "loss": 0.7189, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.6972477064220184, | |
| "eval_loss": 0.6955855488777161, | |
| "eval_runtime": 0.4384, | |
| "eval_samples_per_second": 248.655, | |
| "eval_steps_per_second": 9.125, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 24.52, | |
| "learning_rate": 3.6706349206349205e-05, | |
| "loss": 0.7111, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 24.9, | |
| "eval_accuracy": 0.7247706422018348, | |
| "eval_loss": 0.6749173998832703, | |
| "eval_runtime": 0.4278, | |
| "eval_samples_per_second": 254.789, | |
| "eval_steps_per_second": 9.35, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 25.81, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.6577, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 25.94, | |
| "eval_accuracy": 0.6972477064220184, | |
| "eval_loss": 0.6757855415344238, | |
| "eval_runtime": 0.433, | |
| "eval_samples_per_second": 251.741, | |
| "eval_steps_per_second": 9.238, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 26.97, | |
| "eval_accuracy": 0.7339449541284404, | |
| "eval_loss": 0.6429359316825867, | |
| "eval_runtime": 0.6106, | |
| "eval_samples_per_second": 178.522, | |
| "eval_steps_per_second": 6.551, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 27.1, | |
| "learning_rate": 3.472222222222222e-05, | |
| "loss": 0.6681, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.7064220183486238, | |
| "eval_loss": 0.6450981497764587, | |
| "eval_runtime": 0.4394, | |
| "eval_samples_per_second": 248.065, | |
| "eval_steps_per_second": 9.103, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 28.39, | |
| "learning_rate": 3.3730158730158734e-05, | |
| "loss": 0.6238, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 28.9, | |
| "eval_accuracy": 0.7339449541284404, | |
| "eval_loss": 0.6367726922035217, | |
| "eval_runtime": 0.61, | |
| "eval_samples_per_second": 178.699, | |
| "eval_steps_per_second": 6.558, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 29.68, | |
| "learning_rate": 3.273809523809524e-05, | |
| "loss": 0.6136, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 29.94, | |
| "eval_accuracy": 0.7706422018348624, | |
| "eval_loss": 0.6232722997665405, | |
| "eval_runtime": 0.4356, | |
| "eval_samples_per_second": 250.256, | |
| "eval_steps_per_second": 9.184, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.5934, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 30.97, | |
| "eval_accuracy": 0.7706422018348624, | |
| "eval_loss": 0.6160764098167419, | |
| "eval_runtime": 0.4496, | |
| "eval_samples_per_second": 242.42, | |
| "eval_steps_per_second": 8.896, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.7431192660550459, | |
| "eval_loss": 0.626839816570282, | |
| "eval_runtime": 0.44, | |
| "eval_samples_per_second": 247.748, | |
| "eval_steps_per_second": 9.092, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 32.26, | |
| "learning_rate": 3.075396825396826e-05, | |
| "loss": 0.5807, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 32.9, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.5879014730453491, | |
| "eval_runtime": 0.449, | |
| "eval_samples_per_second": 242.778, | |
| "eval_steps_per_second": 8.909, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 33.55, | |
| "learning_rate": 2.9761904761904762e-05, | |
| "loss": 0.575, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 33.94, | |
| "eval_accuracy": 0.7706422018348624, | |
| "eval_loss": 0.5772398710250854, | |
| "eval_runtime": 0.4322, | |
| "eval_samples_per_second": 252.185, | |
| "eval_steps_per_second": 9.254, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "learning_rate": 2.876984126984127e-05, | |
| "loss": 0.5409, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 34.97, | |
| "eval_accuracy": 0.7798165137614679, | |
| "eval_loss": 0.5702607035636902, | |
| "eval_runtime": 0.4332, | |
| "eval_samples_per_second": 251.604, | |
| "eval_steps_per_second": 9.233, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.7889908256880734, | |
| "eval_loss": 0.5603441596031189, | |
| "eval_runtime": 0.6241, | |
| "eval_samples_per_second": 174.639, | |
| "eval_steps_per_second": 6.409, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 36.13, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.553, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 36.9, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.5560410022735596, | |
| "eval_runtime": 0.4375, | |
| "eval_samples_per_second": 249.161, | |
| "eval_steps_per_second": 9.144, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 37.42, | |
| "learning_rate": 2.6785714285714288e-05, | |
| "loss": 0.515, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 37.94, | |
| "eval_accuracy": 0.7706422018348624, | |
| "eval_loss": 0.5639447569847107, | |
| "eval_runtime": 0.4367, | |
| "eval_samples_per_second": 249.625, | |
| "eval_steps_per_second": 9.161, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 38.71, | |
| "learning_rate": 2.5793650793650796e-05, | |
| "loss": 0.5424, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 38.97, | |
| "eval_accuracy": 0.7889908256880734, | |
| "eval_loss": 0.5483418107032776, | |
| "eval_runtime": 0.4272, | |
| "eval_samples_per_second": 255.167, | |
| "eval_steps_per_second": 9.364, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "learning_rate": 2.4801587301587305e-05, | |
| "loss": 0.5193, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.7798165137614679, | |
| "eval_loss": 0.5505456924438477, | |
| "eval_runtime": 0.4357, | |
| "eval_samples_per_second": 250.151, | |
| "eval_steps_per_second": 9.18, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 40.9, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.5322768092155457, | |
| "eval_runtime": 0.438, | |
| "eval_samples_per_second": 248.859, | |
| "eval_steps_per_second": 9.132, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 41.29, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.5123, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 41.94, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.5257070064544678, | |
| "eval_runtime": 0.4489, | |
| "eval_samples_per_second": 242.816, | |
| "eval_steps_per_second": 8.911, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 42.58, | |
| "learning_rate": 2.281746031746032e-05, | |
| "loss": 0.4719, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 42.97, | |
| "eval_accuracy": 0.7798165137614679, | |
| "eval_loss": 0.5269966125488281, | |
| "eval_runtime": 0.7214, | |
| "eval_samples_per_second": 151.1, | |
| "eval_steps_per_second": 5.545, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 43.87, | |
| "learning_rate": 2.1825396825396827e-05, | |
| "loss": 0.4583, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.7706422018348624, | |
| "eval_loss": 0.5304660201072693, | |
| "eval_runtime": 0.4302, | |
| "eval_samples_per_second": 253.364, | |
| "eval_steps_per_second": 9.298, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 44.9, | |
| "eval_accuracy": 0.7798165137614679, | |
| "eval_loss": 0.5281646251678467, | |
| "eval_runtime": 0.6252, | |
| "eval_samples_per_second": 174.336, | |
| "eval_steps_per_second": 6.398, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 45.16, | |
| "learning_rate": 2.0833333333333336e-05, | |
| "loss": 0.4568, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 45.94, | |
| "eval_accuracy": 0.7889908256880734, | |
| "eval_loss": 0.5177940130233765, | |
| "eval_runtime": 0.4569, | |
| "eval_samples_per_second": 238.568, | |
| "eval_steps_per_second": 8.755, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 46.45, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.4717, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 46.97, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.49453452229499817, | |
| "eval_runtime": 0.4248, | |
| "eval_samples_per_second": 256.572, | |
| "eval_steps_per_second": 9.415, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 47.74, | |
| "learning_rate": 1.884920634920635e-05, | |
| "loss": 0.4587, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.4978266656398773, | |
| "eval_runtime": 0.4615, | |
| "eval_samples_per_second": 236.178, | |
| "eval_steps_per_second": 8.667, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 48.9, | |
| "eval_accuracy": 0.7889908256880734, | |
| "eval_loss": 0.4887874722480774, | |
| "eval_runtime": 0.4558, | |
| "eval_samples_per_second": 239.119, | |
| "eval_steps_per_second": 8.775, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 49.03, | |
| "learning_rate": 1.785714285714286e-05, | |
| "loss": 0.4314, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 49.94, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.48671984672546387, | |
| "eval_runtime": 0.4423, | |
| "eval_samples_per_second": 246.43, | |
| "eval_steps_per_second": 9.043, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 50.32, | |
| "learning_rate": 1.6865079365079367e-05, | |
| "loss": 0.4389, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 50.97, | |
| "eval_accuracy": 0.7889908256880734, | |
| "eval_loss": 0.4739398658275604, | |
| "eval_runtime": 0.4484, | |
| "eval_samples_per_second": 243.061, | |
| "eval_steps_per_second": 8.92, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 51.61, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.4115, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.4844360053539276, | |
| "eval_runtime": 0.6269, | |
| "eval_samples_per_second": 173.869, | |
| "eval_steps_per_second": 6.381, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 52.9, | |
| "learning_rate": 1.4880952380952381e-05, | |
| "loss": 0.4323, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 52.9, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.4818795323371887, | |
| "eval_runtime": 0.4584, | |
| "eval_samples_per_second": 237.796, | |
| "eval_steps_per_second": 8.726, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 53.94, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.45617520809173584, | |
| "eval_runtime": 0.4517, | |
| "eval_samples_per_second": 241.332, | |
| "eval_steps_per_second": 8.856, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 54.19, | |
| "learning_rate": 1.388888888888889e-05, | |
| "loss": 0.3855, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 54.97, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.4639626145362854, | |
| "eval_runtime": 0.4274, | |
| "eval_samples_per_second": 255.051, | |
| "eval_steps_per_second": 9.36, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 55.48, | |
| "learning_rate": 1.2896825396825398e-05, | |
| "loss": 0.4113, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.44737786054611206, | |
| "eval_runtime": 0.4453, | |
| "eval_samples_per_second": 244.764, | |
| "eval_steps_per_second": 8.982, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 56.77, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.4282, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 56.9, | |
| "eval_accuracy": 0.7981651376146789, | |
| "eval_loss": 0.45404085516929626, | |
| "eval_runtime": 0.4314, | |
| "eval_samples_per_second": 252.681, | |
| "eval_steps_per_second": 9.273, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 57.94, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.44497042894363403, | |
| "eval_runtime": 0.4614, | |
| "eval_samples_per_second": 236.26, | |
| "eval_steps_per_second": 8.67, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 58.06, | |
| "learning_rate": 1.0912698412698414e-05, | |
| "loss": 0.4499, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 58.97, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.44970786571502686, | |
| "eval_runtime": 0.633, | |
| "eval_samples_per_second": 172.2, | |
| "eval_steps_per_second": 6.319, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 59.35, | |
| "learning_rate": 9.92063492063492e-06, | |
| "loss": 0.4179, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.44003376364707947, | |
| "eval_runtime": 0.4509, | |
| "eval_samples_per_second": 241.755, | |
| "eval_steps_per_second": 8.872, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 60.65, | |
| "learning_rate": 8.92857142857143e-06, | |
| "loss": 0.4213, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 60.9, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.4391891658306122, | |
| "eval_runtime": 0.4498, | |
| "eval_samples_per_second": 242.327, | |
| "eval_steps_per_second": 8.893, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.4176, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 61.94, | |
| "eval_accuracy": 0.8256880733944955, | |
| "eval_loss": 0.43245241045951843, | |
| "eval_runtime": 0.4412, | |
| "eval_samples_per_second": 247.039, | |
| "eval_steps_per_second": 9.066, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 62.97, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.42957109212875366, | |
| "eval_runtime": 0.4491, | |
| "eval_samples_per_second": 242.688, | |
| "eval_steps_per_second": 8.906, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 63.23, | |
| "learning_rate": 6.944444444444445e-06, | |
| "loss": 0.4083, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.43877631425857544, | |
| "eval_runtime": 0.4459, | |
| "eval_samples_per_second": 244.475, | |
| "eval_steps_per_second": 8.972, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 64.52, | |
| "learning_rate": 5.9523809523809525e-06, | |
| "loss": 0.3853, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 64.9, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.43918871879577637, | |
| "eval_runtime": 0.4466, | |
| "eval_samples_per_second": 244.06, | |
| "eval_steps_per_second": 8.956, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 65.81, | |
| "learning_rate": 4.96031746031746e-06, | |
| "loss": 0.3647, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 65.94, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.4348970353603363, | |
| "eval_runtime": 0.6039, | |
| "eval_samples_per_second": 180.506, | |
| "eval_steps_per_second": 6.624, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 66.97, | |
| "eval_accuracy": 0.8256880733944955, | |
| "eval_loss": 0.4343608319759369, | |
| "eval_runtime": 0.4394, | |
| "eval_samples_per_second": 248.071, | |
| "eval_steps_per_second": 9.104, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 67.1, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.3927, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.43479177355766296, | |
| "eval_runtime": 0.4462, | |
| "eval_samples_per_second": 244.289, | |
| "eval_steps_per_second": 8.965, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 68.39, | |
| "learning_rate": 2.9761904761904763e-06, | |
| "loss": 0.3833, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 68.9, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.4351903796195984, | |
| "eval_runtime": 0.4439, | |
| "eval_samples_per_second": 245.538, | |
| "eval_steps_per_second": 9.011, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 69.68, | |
| "learning_rate": 1.984126984126984e-06, | |
| "loss": 0.3932, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 69.94, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.4294258952140808, | |
| "eval_runtime": 0.4336, | |
| "eval_samples_per_second": 251.361, | |
| "eval_steps_per_second": 9.224, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "learning_rate": 9.92063492063492e-07, | |
| "loss": 0.4085, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 70.97, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.42758503556251526, | |
| "eval_runtime": 0.4574, | |
| "eval_samples_per_second": 238.283, | |
| "eval_steps_per_second": 8.744, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8073394495412844, | |
| "eval_loss": 0.4231923222541809, | |
| "eval_runtime": 0.4385, | |
| "eval_samples_per_second": 248.573, | |
| "eval_steps_per_second": 9.122, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 72.26, | |
| "learning_rate": 0.0, | |
| "loss": 0.4029, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 72.26, | |
| "eval_accuracy": 0.8165137614678899, | |
| "eval_loss": 0.435944139957428, | |
| "eval_runtime": 0.466, | |
| "eval_samples_per_second": 233.911, | |
| "eval_steps_per_second": 8.584, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 72.26, | |
| "step": 560, | |
| "total_flos": 1.937282408715387e+17, | |
| "train_loss": 0.6618133915322167, | |
| "train_runtime": 514.9079, | |
| "train_samples_per_second": 151.95, | |
| "train_steps_per_second": 1.088 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 560, | |
| "num_train_epochs": 80, | |
| "save_steps": 500, | |
| "total_flos": 1.937282408715387e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |