| { | |
| "best_metric": 0.5057060886900621, | |
| "best_model_checkpoint": "./runtime-text-classification/paraphrase-MiniLM-L12-v2-CoLA/checkpoint-201", | |
| "epoch": 16.0, | |
| "global_step": 1072, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.2121212121212122e-05, | |
| "loss": 0.691, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 2.4242424242424244e-05, | |
| "loss": 0.6789, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.6487, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.848484848484849e-05, | |
| "loss": 0.6241, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 6.060606060606061e-05, | |
| "loss": 0.6337, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.5772, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 7.99992685960293e-05, | |
| "loss": 0.6126, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 7.99910406085351e-05, | |
| "loss": 0.6145, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 7.997367226544184e-05, | |
| "loss": 0.5957, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 7.994716753645944e-05, | |
| "loss": 0.6062, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 7.991153247951099e-05, | |
| "loss": 0.6065, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 7.986677523934811e-05, | |
| "loss": 0.5945, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 7.981290604568935e-05, | |
| "loss": 0.5747, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.539438784122467, | |
| "eval_matthews_correlation": 0.34550903174440106, | |
| "eval_runtime": 1.0831, | |
| "eval_samples_per_second": 962.985, | |
| "eval_steps_per_second": 60.937, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.04, | |
| "learning_rate": 7.974993721088216e-05, | |
| "loss": 0.5494, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 7.96778831270887e-05, | |
| "loss": 0.5121, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 7.95967602629964e-05, | |
| "loss": 0.5236, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 7.95065871600539e-05, | |
| "loss": 0.5188, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 7.940738442823318e-05, | |
| "loss": 0.5408, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.42, | |
| "learning_rate": 7.929917474131895e-05, | |
| "loss": 0.5426, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 7.918198283172634e-05, | |
| "loss": 0.5215, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 7.905583548484803e-05, | |
| "loss": 0.5201, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.64, | |
| "learning_rate": 7.892076153293224e-05, | |
| "loss": 0.5009, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.72, | |
| "learning_rate": 7.877679184849275e-05, | |
| "loss": 0.485, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.79, | |
| "learning_rate": 7.86239593372527e-05, | |
| "loss": 0.5062, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.846229893062373e-05, | |
| "loss": 0.5096, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.829184757772192e-05, | |
| "loss": 0.5025, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_loss": 0.4999140501022339, | |
| "eval_matthews_correlation": 0.42696977338948733, | |
| "eval_runtime": 1.0932, | |
| "eval_samples_per_second": 954.042, | |
| "eval_steps_per_second": 60.371, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "learning_rate": 7.811264423692282e-05, | |
| "loss": 0.4893, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.09, | |
| "learning_rate": 7.792472986695704e-05, | |
| "loss": 0.3651, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.16, | |
| "learning_rate": 7.772814741754875e-05, | |
| "loss": 0.4004, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 7.752294181959911e-05, | |
| "loss": 0.3846, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 7.730915997491679e-05, | |
| "loss": 0.3769, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.39, | |
| "learning_rate": 7.708685074549819e-05, | |
| "loss": 0.3736, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.46, | |
| "learning_rate": 7.685606494235943e-05, | |
| "loss": 0.3752, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.54, | |
| "learning_rate": 7.661685531392307e-05, | |
| "loss": 0.4007, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.61, | |
| "learning_rate": 7.636927653396184e-05, | |
| "loss": 0.3887, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.69, | |
| "learning_rate": 7.611338518910249e-05, | |
| "loss": 0.3895, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.76, | |
| "learning_rate": 7.584923976589229e-05, | |
| "loss": 0.3789, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.84, | |
| "learning_rate": 7.557690063743136e-05, | |
| "loss": 0.3876, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.91, | |
| "learning_rate": 7.529643004957372e-05, | |
| "loss": 0.3893, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.500789210670052e-05, | |
| "loss": 0.3698, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_loss": 0.46361204981803894, | |
| "eval_matthews_correlation": 0.5057060886900621, | |
| "eval_runtime": 1.0755, | |
| "eval_samples_per_second": 969.746, | |
| "eval_steps_per_second": 61.365, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 3.06, | |
| "learning_rate": 7.47113527570682e-05, | |
| "loss": 0.3288, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 3.13, | |
| "learning_rate": 7.44068797777354e-05, | |
| "loss": 0.283, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 3.21, | |
| "learning_rate": 7.409454275907184e-05, | |
| "loss": 0.2778, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 3.28, | |
| "learning_rate": 7.377441308885273e-05, | |
| "loss": 0.2891, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 3.36, | |
| "learning_rate": 7.344656393594239e-05, | |
| "loss": 0.2637, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 3.43, | |
| "learning_rate": 7.311107023357071e-05, | |
| "loss": 0.2877, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 3.51, | |
| "learning_rate": 7.27680086622065e-05, | |
| "loss": 0.2744, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 3.58, | |
| "learning_rate": 7.241745763203128e-05, | |
| "loss": 0.2728, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 3.66, | |
| "learning_rate": 7.205949726501796e-05, | |
| "loss": 0.2808, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 3.73, | |
| "learning_rate": 7.169420937661808e-05, | |
| "loss": 0.3497, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 3.81, | |
| "learning_rate": 7.132167745706208e-05, | |
| "loss": 0.3107, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 3.88, | |
| "learning_rate": 7.094198665227675e-05, | |
| "loss": 0.2813, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "learning_rate": 7.055522374442433e-05, | |
| "loss": 0.2969, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_loss": 0.5308544039726257, | |
| "eval_matthews_correlation": 0.4751366513569292, | |
| "eval_runtime": 1.4776, | |
| "eval_samples_per_second": 705.87, | |
| "eval_steps_per_second": 44.667, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 4.03, | |
| "learning_rate": 7.01614771320675e-05, | |
| "loss": 0.3118, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 6.976083680996507e-05, | |
| "loss": 0.2078, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 4.18, | |
| "learning_rate": 6.935339434850266e-05, | |
| "loss": 0.1871, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 4.25, | |
| "learning_rate": 6.89392428727635e-05, | |
| "loss": 0.2217, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 6.851847704124361e-05, | |
| "loss": 0.2802, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 4.4, | |
| "learning_rate": 6.809119302421682e-05, | |
| "loss": 0.2718, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 4.48, | |
| "learning_rate": 6.765748848175391e-05, | |
| "loss": 0.2333, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 4.55, | |
| "learning_rate": 6.721746254140152e-05, | |
| "loss": 0.2585, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 4.63, | |
| "learning_rate": 6.677121577552554e-05, | |
| "loss": 0.2538, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 4.7, | |
| "learning_rate": 6.631885017832421e-05, | |
| "loss": 0.2754, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 4.78, | |
| "learning_rate": 6.586046914251644e-05, | |
| "loss": 0.2585, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 4.85, | |
| "learning_rate": 6.539617743571023e-05, | |
| "loss": 0.2141, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 4.93, | |
| "learning_rate": 6.492608117645711e-05, | |
| "loss": 0.2563, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "learning_rate": 6.445028780999751e-05, | |
| "loss": 0.2275, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_loss": 0.623831033706665, | |
| "eval_matthews_correlation": 0.4774618517292431, | |
| "eval_runtime": 1.0964, | |
| "eval_samples_per_second": 951.284, | |
| "eval_steps_per_second": 60.196, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 5.07, | |
| "learning_rate": 6.396890608370326e-05, | |
| "loss": 0.1801, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 5.15, | |
| "learning_rate": 6.348204602222213e-05, | |
| "loss": 0.1687, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 5.22, | |
| "learning_rate": 6.298981890233062e-05, | |
| "loss": 0.1548, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 5.3, | |
| "learning_rate": 6.24923372275006e-05, | |
| "loss": 0.1502, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 5.37, | |
| "learning_rate": 6.198971470218543e-05, | |
| "loss": 0.1816, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 5.45, | |
| "learning_rate": 6.148206620583172e-05, | |
| "loss": 0.1695, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 5.52, | |
| "learning_rate": 6.096950776662239e-05, | |
| "loss": 0.1828, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 5.6, | |
| "learning_rate": 6.0452156534957336e-05, | |
| "loss": 0.1768, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 5.67, | |
| "learning_rate": 5.993013075667753e-05, | |
| "loss": 0.2368, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 5.75, | |
| "learning_rate": 5.940354974603868e-05, | |
| "loss": 0.1782, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 5.82, | |
| "learning_rate": 5.887253385844076e-05, | |
| "loss": 0.1508, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 5.9, | |
| "learning_rate": 5.8337204462919645e-05, | |
| "loss": 0.1778, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 5.97, | |
| "learning_rate": 5.779768391440693e-05, | |
| "loss": 0.1859, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_loss": 0.6314846873283386, | |
| "eval_matthews_correlation": 0.4867092923459376, | |
| "eval_runtime": 1.0756, | |
| "eval_samples_per_second": 969.736, | |
| "eval_steps_per_second": 61.364, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 6.04, | |
| "learning_rate": 5.725409552576445e-05, | |
| "loss": 0.1603, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 6.12, | |
| "learning_rate": 5.670656353959997e-05, | |
| "loss": 0.1204, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 6.19, | |
| "learning_rate": 5.615521309987022e-05, | |
| "loss": 0.1699, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 6.27, | |
| "learning_rate": 5.5600170223278e-05, | |
| "loss": 0.1502, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 6.34, | |
| "learning_rate": 5.5041561770469787e-05, | |
| "loss": 0.1389, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 6.42, | |
| "learning_rate": 5.4479515417040426e-05, | |
| "loss": 0.1567, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 6.49, | |
| "learning_rate": 5.391415962435167e-05, | |
| "loss": 0.1644, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 6.57, | |
| "learning_rate": 5.334562361017097e-05, | |
| "loss": 0.1748, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "learning_rate": 5.277403731913743e-05, | |
| "loss": 0.1308, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 6.72, | |
| "learning_rate": 5.2199531393061755e-05, | |
| "loss": 0.1034, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 6.79, | |
| "learning_rate": 5.162223714106661e-05, | |
| "loss": 0.1266, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 6.87, | |
| "learning_rate": 5.104228650957472e-05, | |
| "loss": 0.0935, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 6.94, | |
| "learning_rate": 5.0459812052151114e-05, | |
| "loss": 0.1517, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_loss": 0.7783187627792358, | |
| "eval_matthews_correlation": 0.4695101101903524, | |
| "eval_runtime": 1.0697, | |
| "eval_samples_per_second": 975.006, | |
| "eval_steps_per_second": 61.697, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "learning_rate": 4.9874946899206665e-05, | |
| "loss": 0.1364, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 7.09, | |
| "learning_rate": 4.928782472756985e-05, | |
| "loss": 0.1386, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 7.16, | |
| "learning_rate": 4.869857972993352e-05, | |
| "loss": 0.0828, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 7.24, | |
| "learning_rate": 4.810734658418377e-05, | |
| "loss": 0.123, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 7.31, | |
| "learning_rate": 4.751426042261806e-05, | |
| "loss": 0.0893, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 7.39, | |
| "learning_rate": 4.691945680105929e-05, | |
| "loss": 0.108, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 7.46, | |
| "learning_rate": 4.63230716678731e-05, | |
| "loss": 0.0797, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 7.54, | |
| "learning_rate": 4.5725241332895643e-05, | |
| "loss": 0.1078, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 7.61, | |
| "learning_rate": 4.512610243627845e-05, | |
| "loss": 0.1057, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 7.69, | |
| "learning_rate": 4.4525791917258025e-05, | |
| "loss": 0.0968, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 7.76, | |
| "learning_rate": 4.3924446982857027e-05, | |
| "loss": 0.1196, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 7.84, | |
| "learning_rate": 4.3322205076524145e-05, | |
| "loss": 0.1423, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 7.91, | |
| "learning_rate": 4.271920384672002e-05, | |
| "loss": 0.1203, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 7.99, | |
| "learning_rate": 4.21155811154564e-05, | |
| "loss": 0.1016, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_loss": 0.6762046813964844, | |
| "eval_matthews_correlation": 0.49007739162498226, | |
| "eval_runtime": 1.0748, | |
| "eval_samples_per_second": 970.453, | |
| "eval_steps_per_second": 61.409, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 8.06, | |
| "learning_rate": 4.151147484679541e-05, | |
| "loss": 0.0866, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 8.13, | |
| "learning_rate": 4.0907023115316525e-05, | |
| "loss": 0.0947, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 8.21, | |
| "learning_rate": 4.030236407455827e-05, | |
| "loss": 0.0718, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 8.28, | |
| "learning_rate": 3.969763592544173e-05, | |
| "loss": 0.0729, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 8.36, | |
| "learning_rate": 3.909297688468347e-05, | |
| "loss": 0.1148, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 8.43, | |
| "learning_rate": 3.84885251532046e-05, | |
| "loss": 0.1083, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 8.51, | |
| "learning_rate": 3.7884418884543614e-05, | |
| "loss": 0.1135, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 8.58, | |
| "learning_rate": 3.728079615327999e-05, | |
| "loss": 0.0581, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 8.66, | |
| "learning_rate": 3.667779492347588e-05, | |
| "loss": 0.0943, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 8.73, | |
| "learning_rate": 3.607555301714297e-05, | |
| "loss": 0.095, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 8.81, | |
| "learning_rate": 3.5474208082741975e-05, | |
| "loss": 0.1263, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 8.88, | |
| "learning_rate": 3.4873897563721565e-05, | |
| "loss": 0.1371, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "learning_rate": 3.427475866710437e-05, | |
| "loss": 0.1017, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_loss": 0.741180419921875, | |
| "eval_matthews_correlation": 0.5046330570516372, | |
| "eval_runtime": 1.0744, | |
| "eval_samples_per_second": 970.819, | |
| "eval_steps_per_second": 61.432, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 9.03, | |
| "learning_rate": 3.367692833212691e-05, | |
| "loss": 0.0929, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 9.1, | |
| "learning_rate": 3.308054319894074e-05, | |
| "loss": 0.0638, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 9.18, | |
| "learning_rate": 3.2485739577381946e-05, | |
| "loss": 0.1338, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 9.25, | |
| "learning_rate": 3.1892653415816245e-05, | |
| "loss": 0.0663, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 9.33, | |
| "learning_rate": 3.13014202700665e-05, | |
| "loss": 0.0767, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 9.4, | |
| "learning_rate": 3.071217527243016e-05, | |
| "loss": 0.1068, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 9.48, | |
| "learning_rate": 3.012505310079335e-05, | |
| "loss": 0.0818, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 9.55, | |
| "learning_rate": 2.9540187947848906e-05, | |
| "loss": 0.0527, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 9.63, | |
| "learning_rate": 2.8957713490425298e-05, | |
| "loss": 0.0837, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 9.7, | |
| "learning_rate": 2.837776285893339e-05, | |
| "loss": 0.0804, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 9.78, | |
| "learning_rate": 2.780046860693826e-05, | |
| "loss": 0.1138, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 9.85, | |
| "learning_rate": 2.7225962680862575e-05, | |
| "loss": 0.0705, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 9.93, | |
| "learning_rate": 2.6654376389829043e-05, | |
| "loss": 0.0562, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "learning_rate": 2.6085840375648337e-05, | |
| "loss": 0.0898, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_loss": 0.7719386219978333, | |
| "eval_matthews_correlation": 0.48769484136865787, | |
| "eval_runtime": 1.1003, | |
| "eval_samples_per_second": 947.882, | |
| "eval_steps_per_second": 59.981, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 10.07, | |
| "learning_rate": 2.5520484582959588e-05, | |
| "loss": 0.0739, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 10.15, | |
| "learning_rate": 2.4958438229530223e-05, | |
| "loss": 0.0927, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 10.22, | |
| "learning_rate": 2.4399829776722005e-05, | |
| "loss": 0.0731, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 10.3, | |
| "learning_rate": 2.384478690012978e-05, | |
| "loss": 0.051, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 10.37, | |
| "learning_rate": 2.3293436460400044e-05, | |
| "loss": 0.0647, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 10.45, | |
| "learning_rate": 2.2745904474235573e-05, | |
| "loss": 0.0704, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 10.52, | |
| "learning_rate": 2.2202316085593106e-05, | |
| "loss": 0.0479, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 10.6, | |
| "learning_rate": 2.1662795537080365e-05, | |
| "loss": 0.076, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 10.67, | |
| "learning_rate": 2.1127466141559257e-05, | |
| "loss": 0.0709, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 10.75, | |
| "learning_rate": 2.059645025396135e-05, | |
| "loss": 0.0698, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 10.82, | |
| "learning_rate": 2.006986924332247e-05, | |
| "loss": 0.0606, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 10.9, | |
| "learning_rate": 1.9547843465042664e-05, | |
| "loss": 0.096, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 10.97, | |
| "learning_rate": 1.9030492233377623e-05, | |
| "loss": 0.0527, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_loss": 0.8626514673233032, | |
| "eval_matthews_correlation": 0.49547617383910947, | |
| "eval_runtime": 1.0828, | |
| "eval_samples_per_second": 963.257, | |
| "eval_steps_per_second": 60.954, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 11.04, | |
| "learning_rate": 1.8517933794168294e-05, | |
| "loss": 0.0582, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 11.12, | |
| "learning_rate": 1.8010285297814563e-05, | |
| "loss": 0.0731, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 11.19, | |
| "learning_rate": 1.7507662772499406e-05, | |
| "loss": 0.0478, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 11.27, | |
| "learning_rate": 1.701018109766939e-05, | |
| "loss": 0.0564, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 11.34, | |
| "learning_rate": 1.6517953977777888e-05, | |
| "loss": 0.0413, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 11.42, | |
| "learning_rate": 1.603109391629675e-05, | |
| "loss": 0.0478, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 11.49, | |
| "learning_rate": 1.5549712190002498e-05, | |
| "loss": 0.0844, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 11.57, | |
| "learning_rate": 1.50739188235429e-05, | |
| "loss": 0.065, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 11.64, | |
| "learning_rate": 1.4603822564289764e-05, | |
| "loss": 0.068, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 11.72, | |
| "learning_rate": 1.4139530857483568e-05, | |
| "loss": 0.0324, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 11.79, | |
| "learning_rate": 1.3681149821675797e-05, | |
| "loss": 0.0436, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 11.87, | |
| "learning_rate": 1.322878422447448e-05, | |
| "loss": 0.0566, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 11.94, | |
| "learning_rate": 1.2782537458598489e-05, | |
| "loss": 0.0582, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_loss": 0.8985734581947327, | |
| "eval_matthews_correlation": 0.47375271850377065, | |
| "eval_runtime": 1.0831, | |
| "eval_samples_per_second": 962.944, | |
| "eval_steps_per_second": 60.934, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "learning_rate": 1.2342511518246095e-05, | |
| "loss": 0.0521, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 12.09, | |
| "learning_rate": 1.1908806975783192e-05, | |
| "loss": 0.0565, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 12.16, | |
| "learning_rate": 1.1481522958756383e-05, | |
| "loss": 0.0358, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 12.24, | |
| "learning_rate": 1.1060757127236514e-05, | |
| "loss": 0.0436, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 12.31, | |
| "learning_rate": 1.0646605651497342e-05, | |
| "loss": 0.06, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 12.39, | |
| "learning_rate": 1.0239163190034937e-05, | |
| "loss": 0.0439, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 12.46, | |
| "learning_rate": 9.838522867932499e-06, | |
| "loss": 0.0436, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 12.54, | |
| "learning_rate": 9.444776255575672e-06, | |
| "loss": 0.032, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 12.61, | |
| "learning_rate": 9.058013347723258e-06, | |
| "loss": 0.0623, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 12.69, | |
| "learning_rate": 8.678322542937941e-06, | |
| "loss": 0.0526, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 12.76, | |
| "learning_rate": 8.305790623381934e-06, | |
| "loss": 0.0231, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 12.84, | |
| "learning_rate": 7.94050273498205e-06, | |
| "loss": 0.035, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 12.91, | |
| "learning_rate": 7.582542367968733e-06, | |
| "loss": 0.0612, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 12.99, | |
| "learning_rate": 7.2319913377935096e-06, | |
| "loss": 0.074, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_loss": 0.9468681812286377, | |
| "eval_matthews_correlation": 0.49419533040588925, | |
| "eval_runtime": 1.0698, | |
| "eval_samples_per_second": 974.98, | |
| "eval_steps_per_second": 61.696, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 13.06, | |
| "learning_rate": 6.888929766429293e-06, | |
| "loss": 0.0266, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 13.13, | |
| "learning_rate": 6.553436064057619e-06, | |
| "loss": 0.0631, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 13.21, | |
| "learning_rate": 6.225586911147274e-06, | |
| "loss": 0.0549, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 13.28, | |
| "learning_rate": 5.9054572409281655e-06, | |
| "loss": 0.0212, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 13.36, | |
| "learning_rate": 5.5931202222646145e-06, | |
| "loss": 0.0404, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 13.43, | |
| "learning_rate": 5.288647242931815e-06, | |
| "loss": 0.0606, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 13.51, | |
| "learning_rate": 4.992107893299483e-06, | |
| "loss": 0.0523, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 13.58, | |
| "learning_rate": 4.703569950426285e-06, | |
| "loss": 0.0283, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 13.66, | |
| "learning_rate": 4.4230993625686616e-06, | |
| "loss": 0.0515, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 13.73, | |
| "learning_rate": 4.150760234107716e-06, | |
| "loss": 0.0333, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 13.81, | |
| "learning_rate": 3.88661481089752e-06, | |
| "loss": 0.0338, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 13.88, | |
| "learning_rate": 3.630723466038175e-06, | |
| "loss": 0.0344, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 13.96, | |
| "learning_rate": 3.3831446860769444e-06, | |
| "loss": 0.0508, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_loss": 0.9435966610908508, | |
| "eval_matthews_correlation": 0.49177365217771035, | |
| "eval_runtime": 1.082, | |
| "eval_samples_per_second": 963.975, | |
| "eval_steps_per_second": 60.999, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 14.03, | |
| "learning_rate": 3.1439350576405726e-06, | |
| "loss": 0.0513, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 14.1, | |
| "learning_rate": 2.913149254501817e-06, | |
| "loss": 0.0477, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 14.18, | |
| "learning_rate": 2.69084002508321e-06, | |
| "loss": 0.0403, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 14.25, | |
| "learning_rate": 2.477058180400902e-06, | |
| "loss": 0.0657, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 14.33, | |
| "learning_rate": 2.2718525824512614e-06, | |
| "loss": 0.0454, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 14.4, | |
| "learning_rate": 2.0752701330429702e-06, | |
| "loss": 0.0314, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 14.48, | |
| "learning_rate": 1.887355763077192e-06, | |
| "loss": 0.0261, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 14.55, | |
| "learning_rate": 1.7081524222780864e-06, | |
| "loss": 0.0366, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 14.63, | |
| "learning_rate": 1.5377010693762784e-06, | |
| "loss": 0.0307, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 14.7, | |
| "learning_rate": 1.3760406627473022e-06, | |
| "loss": 0.0604, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 14.78, | |
| "learning_rate": 1.2232081515072624e-06, | |
| "loss": 0.0477, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 14.85, | |
| "learning_rate": 1.0792384670677625e-06, | |
| "loss": 0.0303, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 14.93, | |
| "learning_rate": 9.441645151519708e-07, | |
| "loss": 0.032, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "learning_rate": 8.180171682736682e-07, | |
| "loss": 0.024, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_loss": 0.9390689730644226, | |
| "eval_matthews_correlation": 0.49194159281920924, | |
| "eval_runtime": 1.0846, | |
| "eval_samples_per_second": 961.661, | |
| "eval_steps_per_second": 60.853, | |
| "step": 1005 | |
| }, | |
| { | |
| "epoch": 15.07, | |
| "learning_rate": 7.008252586810571e-07, | |
| "loss": 0.0518, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 15.15, | |
| "learning_rate": 5.92615571766828e-07, | |
| "loss": 0.0266, | |
| "step": 1015 | |
| }, | |
| { | |
| "epoch": 15.22, | |
| "learning_rate": 4.934128399461057e-07, | |
| "loss": 0.0424, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 15.3, | |
| "learning_rate": 4.032397370036067e-07, | |
| "loss": 0.0441, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 15.37, | |
| "learning_rate": 3.221168729113089e-07, | |
| "loss": 0.0388, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 15.45, | |
| "learning_rate": 2.5006278911784643e-07, | |
| "loss": 0.0486, | |
| "step": 1035 | |
| }, | |
| { | |
| "epoch": 15.52, | |
| "learning_rate": 1.8709395431065535e-07, | |
| "loss": 0.0311, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 15.6, | |
| "learning_rate": 1.3322476065190438e-07, | |
| "loss": 0.023, | |
| "step": 1045 | |
| }, | |
| { | |
| "epoch": 15.67, | |
| "learning_rate": 8.846752048901952e-08, | |
| "loss": 0.0396, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 15.75, | |
| "learning_rate": 5.2832463540575254e-08, | |
| "loss": 0.0288, | |
| "step": 1055 | |
| }, | |
| { | |
| "epoch": 15.82, | |
| "learning_rate": 2.6327734558173613e-08, | |
| "loss": 0.028, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 15.9, | |
| "learning_rate": 8.95939146489777e-09, | |
| "loss": 0.0409, | |
| "step": 1065 | |
| }, | |
| { | |
| "epoch": 15.97, | |
| "learning_rate": 7.314039707040366e-10, | |
| "loss": 0.0458, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_loss": 0.9374607801437378, | |
| "eval_matthews_correlation": 0.49464326454019025, | |
| "eval_runtime": 1.0777, | |
| "eval_samples_per_second": 967.817, | |
| "eval_steps_per_second": 61.243, | |
| "step": 1072 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "step": 1072, | |
| "total_flos": 2253110874603520.0, | |
| "train_loss": 0.18462801172133925, | |
| "train_runtime": 361.7714, | |
| "train_samples_per_second": 378.184, | |
| "train_steps_per_second": 2.963 | |
| } | |
| ], | |
| "max_steps": 1072, | |
| "num_train_epochs": 16, | |
| "total_flos": 2253110874603520.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |