{ "best_metric": 0.7202531640577455, "best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/span-seq/run-42/checkpoints/checkpoint-3015", "epoch": 111.66666666666667, "global_step": 3015, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.56, "eval_loss": 0.4449886679649353, "eval_micro_f1": 0.0, "eval_runtime": 2.7132, "eval_samples_per_second": 371.889, "step": 15 }, { "epoch": 1.11, "eval_loss": 0.35815417766571045, "eval_micro_f1": 0.0, "eval_runtime": 2.547, "eval_samples_per_second": 396.151, "step": 30 }, { "epoch": 1.67, "eval_loss": 0.2850154936313629, "eval_micro_f1": 0.01382488472158041, "eval_runtime": 2.7364, "eval_samples_per_second": 368.732, "step": 45 }, { "epoch": 2.22, "eval_loss": 0.2488986700773239, "eval_micro_f1": 0.14247551164061406, "eval_runtime": 2.788, "eval_samples_per_second": 361.903, "step": 60 }, { "epoch": 2.78, "eval_loss": 0.223855659365654, "eval_micro_f1": 0.2990654201059384, "eval_runtime": 2.7079, "eval_samples_per_second": 372.609, "step": 75 }, { "epoch": 3.33, "eval_loss": 0.2030642032623291, "eval_micro_f1": 0.4665286399528825, "eval_runtime": 2.5397, "eval_samples_per_second": 397.284, "step": 90 }, { "epoch": 3.89, "eval_loss": 0.21036453545093536, "eval_micro_f1": 0.4642857138039245, "eval_runtime": 2.5326, "eval_samples_per_second": 398.4, "step": 105 }, { "epoch": 4.44, "eval_loss": 0.19268916547298431, "eval_micro_f1": 0.5437415876632256, "eval_runtime": 2.6489, "eval_samples_per_second": 380.919, "step": 120 }, { "epoch": 5.0, "eval_loss": 0.1872236430644989, "eval_micro_f1": 0.5716162938536454, "eval_runtime": 2.5461, "eval_samples_per_second": 396.295, "step": 135 }, { "epoch": 5.56, "eval_loss": 0.17781367897987366, "eval_micro_f1": 0.6071653043402561, "eval_runtime": 2.7488, "eval_samples_per_second": 367.074, "step": 150 }, { "epoch": 6.11, "eval_loss": 0.18171031773090363, "eval_micro_f1": 0.6197007476298017, "eval_runtime": 2.5883, "eval_samples_per_second": 389.829, "step": 165 }, { "epoch": 6.67, "eval_loss": 0.1990872174501419, "eval_micro_f1": 0.6190476185497054, "eval_runtime": 2.6809, "eval_samples_per_second": 376.364, "step": 180 }, { "epoch": 7.22, "eval_loss": 0.2064904421567917, "eval_micro_f1": 0.6235294112681976, "eval_runtime": 2.5393, "eval_samples_per_second": 397.348, "step": 195 }, { "epoch": 7.78, "eval_loss": 0.20159198343753815, "eval_micro_f1": 0.6295081962251318, "eval_runtime": 2.5885, "eval_samples_per_second": 389.795, "step": 210 }, { "epoch": 8.33, "eval_loss": 0.2152908444404602, "eval_micro_f1": 0.6255860678251702, "eval_runtime": 2.9467, "eval_samples_per_second": 342.416, "step": 225 }, { "epoch": 8.89, "eval_loss": 0.20098410546779633, "eval_micro_f1": 0.6382708195901708, "eval_runtime": 2.9964, "eval_samples_per_second": 336.738, "step": 240 }, { "epoch": 9.44, "eval_loss": 0.20521508157253265, "eval_micro_f1": 0.6405648262027532, "eval_runtime": 3.0468, "eval_samples_per_second": 331.163, "step": 255 }, { "epoch": 10.0, "eval_loss": 0.21223442256450653, "eval_micro_f1": 0.6406149898924826, "eval_runtime": 2.7522, "eval_samples_per_second": 366.61, "step": 270 }, { "epoch": 10.56, "eval_loss": 0.22155529260635376, "eval_micro_f1": 0.6459546920591765, "eval_runtime": 2.6185, "eval_samples_per_second": 385.336, "step": 285 }, { "epoch": 11.11, "eval_loss": 0.21812067925930023, "eval_micro_f1": 0.6526181348782133, "eval_runtime": 3.1522, "eval_samples_per_second": 320.091, "step": 300 }, { "epoch": 11.67, "eval_loss": 0.21506914496421814, "eval_micro_f1": 0.6588813762666285, "eval_runtime": 2.9513, "eval_samples_per_second": 341.881, "step": 315 }, { "epoch": 12.22, "eval_loss": 0.23697537183761597, "eval_micro_f1": 0.6535690892220545, "eval_runtime": 2.9217, "eval_samples_per_second": 345.351, "step": 330 }, { "epoch": 12.78, "eval_loss": 0.2327331155538559, "eval_micro_f1": 0.6619263084875412, "eval_runtime": 2.5788, "eval_samples_per_second": 391.266, "step": 345 }, { "epoch": 13.33, "eval_loss": 0.2416866421699524, "eval_micro_f1": 0.6449900459550384, "eval_runtime": 2.545, "eval_samples_per_second": 396.457, "step": 360 }, { "epoch": 13.89, "eval_loss": 0.26182571053504944, "eval_micro_f1": 0.6452476568020838, "eval_runtime": 2.5947, "eval_samples_per_second": 388.867, "step": 375 }, { "epoch": 14.44, "eval_loss": 0.251889705657959, "eval_micro_f1": 0.656147271035952, "eval_runtime": 2.6144, "eval_samples_per_second": 385.946, "step": 390 }, { "epoch": 15.0, "eval_loss": 0.23824955523014069, "eval_micro_f1": 0.6777706593350998, "eval_runtime": 2.6571, "eval_samples_per_second": 379.744, "step": 405 }, { "epoch": 15.56, "eval_loss": 0.23099806904792786, "eval_micro_f1": 0.6746231150783044, "eval_runtime": 2.5312, "eval_samples_per_second": 398.624, "step": 420 }, { "epoch": 16.11, "eval_loss": 0.2526591420173645, "eval_micro_f1": 0.6601562495030602, "eval_runtime": 2.6784, "eval_samples_per_second": 376.715, "step": 435 }, { "epoch": 16.67, "eval_loss": 0.26412394642829895, "eval_micro_f1": 0.6544741993727524, "eval_runtime": 2.7613, "eval_samples_per_second": 365.411, "step": 450 }, { "epoch": 17.22, "eval_loss": 0.2750824987888336, "eval_micro_f1": 0.6498002658171244, "eval_runtime": 2.6537, "eval_samples_per_second": 380.231, "step": 465 }, { "epoch": 17.78, "eval_loss": 0.27604979276657104, "eval_micro_f1": 0.6507304111917976, "eval_runtime": 2.836, "eval_samples_per_second": 355.783, "step": 480 }, { "epoch": 18.33, "eval_loss": 0.2546819746494293, "eval_micro_f1": 0.6679611645510575, "eval_runtime": 2.5593, "eval_samples_per_second": 394.252, "step": 495 }, { "epoch": 18.52, "learning_rate": 9.382716049382717e-06, "loss": 0.0569, "step": 500 }, { "epoch": 18.89, "eval_loss": 0.23573867976665497, "eval_micro_f1": 0.6815642453099265, "eval_runtime": 2.9711, "eval_samples_per_second": 339.606, "step": 510 }, { "epoch": 19.44, "eval_loss": 0.2684776782989502, "eval_micro_f1": 0.6662242861673526, "eval_runtime": 2.6364, "eval_samples_per_second": 382.721, "step": 525 }, { "epoch": 20.0, "eval_loss": 0.2825931906700134, "eval_micro_f1": 0.6706036740445177, "eval_runtime": 3.0088, "eval_samples_per_second": 335.353, "step": 540 }, { "epoch": 20.56, "eval_loss": 0.27100124955177307, "eval_micro_f1": 0.6930051808496889, "eval_runtime": 3.1949, "eval_samples_per_second": 315.82, "step": 555 }, { "epoch": 21.11, "eval_loss": 0.25783923268318176, "eval_micro_f1": 0.6941101958276444, "eval_runtime": 3.0609, "eval_samples_per_second": 329.64, "step": 570 }, { "epoch": 21.67, "eval_loss": 0.2624804973602295, "eval_micro_f1": 0.6856419982357669, "eval_runtime": 3.0022, "eval_samples_per_second": 336.087, "step": 585 }, { "epoch": 22.22, "eval_loss": 0.2892417013645172, "eval_micro_f1": 0.6732542814541932, "eval_runtime": 2.5864, "eval_samples_per_second": 390.122, "step": 600 }, { "epoch": 22.78, "eval_loss": 0.27463534474372864, "eval_micro_f1": 0.6870129865157683, "eval_runtime": 2.5961, "eval_samples_per_second": 388.661, "step": 615 }, { "epoch": 23.33, "eval_loss": 0.2794063985347748, "eval_micro_f1": 0.6881859259063958, "eval_runtime": 2.8701, "eval_samples_per_second": 351.555, "step": 630 }, { "epoch": 23.89, "eval_loss": 0.2783025801181793, "eval_micro_f1": 0.6839043304655347, "eval_runtime": 2.5212, "eval_samples_per_second": 400.21, "step": 645 }, { "epoch": 24.44, "eval_loss": 0.278982013463974, "eval_micro_f1": 0.6757105938175808, "eval_runtime": 2.5765, "eval_samples_per_second": 391.613, "step": 660 }, { "epoch": 25.0, "eval_loss": 0.2662263512611389, "eval_micro_f1": 0.6933333328343494, "eval_runtime": 2.6056, "eval_samples_per_second": 387.239, "step": 675 }, { "epoch": 25.56, "eval_loss": 0.27832865715026855, "eval_micro_f1": 0.7042253516142539, "eval_runtime": 2.5832, "eval_samples_per_second": 390.6, "step": 690 }, { "epoch": 26.11, "eval_loss": 0.28894326090812683, "eval_micro_f1": 0.6817878580781317, "eval_runtime": 2.5872, "eval_samples_per_second": 389.995, "step": 705 }, { "epoch": 26.67, "eval_loss": 0.27688196301460266, "eval_micro_f1": 0.6940874031008585, "eval_runtime": 2.6006, "eval_samples_per_second": 387.985, "step": 720 }, { "epoch": 27.22, "eval_loss": 0.2905151844024658, "eval_micro_f1": 0.689428758532114, "eval_runtime": 2.5788, "eval_samples_per_second": 391.264, "step": 735 }, { "epoch": 27.78, "eval_loss": 0.29111409187316895, "eval_micro_f1": 0.679369250489509, "eval_runtime": 2.5657, "eval_samples_per_second": 393.264, "step": 750 }, { "epoch": 28.33, "eval_loss": 0.2835485637187958, "eval_micro_f1": 0.6853055911804076, "eval_runtime": 2.6606, "eval_samples_per_second": 379.236, "step": 765 }, { "epoch": 28.89, "eval_loss": 0.2893398404121399, "eval_micro_f1": 0.6806009139383616, "eval_runtime": 2.68, "eval_samples_per_second": 376.494, "step": 780 }, { "epoch": 29.44, "eval_loss": 0.28132331371307373, "eval_micro_f1": 0.6880616169600735, "eval_runtime": 2.6036, "eval_samples_per_second": 387.543, "step": 795 }, { "epoch": 30.0, "eval_loss": 0.27432015538215637, "eval_micro_f1": 0.6917197447241591, "eval_runtime": 2.6652, "eval_samples_per_second": 378.576, "step": 810 }, { "epoch": 30.56, "eval_loss": 0.2931191325187683, "eval_micro_f1": 0.6863905320484041, "eval_runtime": 2.6802, "eval_samples_per_second": 376.464, "step": 825 }, { "epoch": 31.11, "eval_loss": 0.2865224778652191, "eval_micro_f1": 0.6921581330087543, "eval_runtime": 2.7173, "eval_samples_per_second": 371.32, "step": 840 }, { "epoch": 31.67, "eval_loss": 0.29402703046798706, "eval_micro_f1": 0.6781002633566425, "eval_runtime": 2.5435, "eval_samples_per_second": 396.695, "step": 855 }, { "epoch": 32.22, "eval_loss": 0.2912046015262604, "eval_micro_f1": 0.6908150059707328, "eval_runtime": 2.5884, "eval_samples_per_second": 389.813, "step": 870 }, { "epoch": 32.78, "eval_loss": 0.28634053468704224, "eval_micro_f1": 0.692993630074476, "eval_runtime": 2.603, "eval_samples_per_second": 387.636, "step": 885 }, { "epoch": 33.33, "eval_loss": 0.30072879791259766, "eval_micro_f1": 0.6823837585081989, "eval_runtime": 2.7246, "eval_samples_per_second": 370.328, "step": 900 }, { "epoch": 33.89, "eval_loss": 0.2997035086154938, "eval_micro_f1": 0.6819371722784171, "eval_runtime": 2.603, "eval_samples_per_second": 387.628, "step": 915 }, { "epoch": 34.44, "eval_loss": 0.2908560037612915, "eval_micro_f1": 0.6944801021975493, "eval_runtime": 2.7896, "eval_samples_per_second": 361.697, "step": 930 }, { "epoch": 35.0, "eval_loss": 0.3087254464626312, "eval_micro_f1": 0.6865473818773562, "eval_runtime": 2.5596, "eval_samples_per_second": 394.197, "step": 945 }, { "epoch": 35.56, "eval_loss": 0.28646770119667053, "eval_micro_f1": 0.7008222638903968, "eval_runtime": 3.1603, "eval_samples_per_second": 319.27, "step": 960 }, { "epoch": 36.11, "eval_loss": 0.30984804034233093, "eval_micro_f1": 0.6756032166645486, "eval_runtime": 2.541, "eval_samples_per_second": 397.093, "step": 975 }, { "epoch": 36.67, "eval_loss": 0.28725677728652954, "eval_micro_f1": 0.6999360199749846, "eval_runtime": 2.7415, "eval_samples_per_second": 368.041, "step": 990 }, { "epoch": 37.04, "learning_rate": 8.765432098765432e-06, "loss": 0.0045, "step": 1000 }, { "epoch": 37.22, "eval_loss": 0.3315005600452423, "eval_micro_f1": 0.661235573167427, "eval_runtime": 3.008, "eval_samples_per_second": 335.439, "step": 1005 }, { "epoch": 37.78, "eval_loss": 0.2967715859413147, "eval_micro_f1": 0.6945876283680734, "eval_runtime": 2.6498, "eval_samples_per_second": 380.782, "step": 1020 }, { "epoch": 38.33, "eval_loss": 0.3274470865726471, "eval_micro_f1": 0.671186440185975, "eval_runtime": 2.8444, "eval_samples_per_second": 354.737, "step": 1035 }, { "epoch": 38.89, "eval_loss": 0.2845298647880554, "eval_micro_f1": 0.7055137839614026, "eval_runtime": 2.5625, "eval_samples_per_second": 393.763, "step": 1050 }, { "epoch": 39.44, "eval_loss": 0.3300946354866028, "eval_micro_f1": 0.6734972672687356, "eval_runtime": 2.6841, "eval_samples_per_second": 375.924, "step": 1065 }, { "epoch": 40.0, "eval_loss": 0.29181015491485596, "eval_micro_f1": 0.6932826357493113, "eval_runtime": 2.5976, "eval_samples_per_second": 388.43, "step": 1080 }, { "epoch": 40.56, "eval_loss": 0.32671409845352173, "eval_micro_f1": 0.6778975736311001, "eval_runtime": 2.582, "eval_samples_per_second": 390.786, "step": 1095 }, { "epoch": 41.11, "eval_loss": 0.3009495139122009, "eval_micro_f1": 0.6903684545767093, "eval_runtime": 2.9683, "eval_samples_per_second": 339.925, "step": 1110 }, { "epoch": 41.67, "eval_loss": 0.3267247676849365, "eval_micro_f1": 0.6807065212474358, "eval_runtime": 2.5515, "eval_samples_per_second": 395.448, "step": 1125 }, { "epoch": 42.22, "eval_loss": 0.31274986267089844, "eval_micro_f1": 0.6836935162030237, "eval_runtime": 2.5976, "eval_samples_per_second": 388.438, "step": 1140 }, { "epoch": 42.78, "eval_loss": 0.3158775269985199, "eval_micro_f1": 0.681216930721629, "eval_runtime": 2.6281, "eval_samples_per_second": 383.927, "step": 1155 }, { "epoch": 43.33, "eval_loss": 0.3231891691684723, "eval_micro_f1": 0.6697736346586424, "eval_runtime": 2.7351, "eval_samples_per_second": 368.906, "step": 1170 }, { "epoch": 43.89, "eval_loss": 0.31868231296539307, "eval_micro_f1": 0.6790205157192055, "eval_runtime": 2.5799, "eval_samples_per_second": 391.107, "step": 1185 }, { "epoch": 44.44, "eval_loss": 0.30990493297576904, "eval_micro_f1": 0.6949706069494467, "eval_runtime": 2.5959, "eval_samples_per_second": 388.69, "step": 1200 }, { "epoch": 45.0, "eval_loss": 0.3237829804420471, "eval_micro_f1": 0.6798679863031519, "eval_runtime": 2.5913, "eval_samples_per_second": 389.385, "step": 1215 }, { "epoch": 45.56, "eval_loss": 0.3204224705696106, "eval_micro_f1": 0.6934023280923335, "eval_runtime": 2.556, "eval_samples_per_second": 394.76, "step": 1230 }, { "epoch": 46.11, "eval_loss": 0.3212703764438629, "eval_micro_f1": 0.696614582836346, "eval_runtime": 2.7418, "eval_samples_per_second": 368.0, "step": 1245 }, { "epoch": 46.67, "eval_loss": 0.3307257294654846, "eval_micro_f1": 0.693527080085771, "eval_runtime": 2.7028, "eval_samples_per_second": 373.314, "step": 1260 }, { "epoch": 47.22, "eval_loss": 0.3206096291542053, "eval_micro_f1": 0.6938775505217226, "eval_runtime": 2.7358, "eval_samples_per_second": 368.813, "step": 1275 }, { "epoch": 47.78, "eval_loss": 0.32562366127967834, "eval_micro_f1": 0.6903684545767093, "eval_runtime": 2.6828, "eval_samples_per_second": 376.1, "step": 1290 }, { "epoch": 48.33, "eval_loss": 0.32037821412086487, "eval_micro_f1": 0.6959328594118732, "eval_runtime": 2.5565, "eval_samples_per_second": 394.673, "step": 1305 }, { "epoch": 48.89, "eval_loss": 0.32871484756469727, "eval_micro_f1": 0.6866840726103287, "eval_runtime": 2.5936, "eval_samples_per_second": 389.029, "step": 1320 }, { "epoch": 49.44, "eval_loss": 0.31619834899902344, "eval_micro_f1": 0.6991661316377145, "eval_runtime": 2.6823, "eval_samples_per_second": 376.175, "step": 1335 }, { "epoch": 50.0, "eval_loss": 0.3305748999118805, "eval_micro_f1": 0.694117646562223, "eval_runtime": 2.5811, "eval_samples_per_second": 390.918, "step": 1350 }, { "epoch": 50.56, "eval_loss": 0.3143664300441742, "eval_micro_f1": 0.6984732819438827, "eval_runtime": 3.0219, "eval_samples_per_second": 333.892, "step": 1365 }, { "epoch": 51.11, "eval_loss": 0.3471008837223053, "eval_micro_f1": 0.6796769847020735, "eval_runtime": 2.5829, "eval_samples_per_second": 390.651, "step": 1380 }, { "epoch": 51.67, "eval_loss": 0.3140552341938019, "eval_micro_f1": 0.6866242033228919, "eval_runtime": 2.7692, "eval_samples_per_second": 364.369, "step": 1395 }, { "epoch": 52.22, "eval_loss": 0.32751619815826416, "eval_micro_f1": 0.6922077917105667, "eval_runtime": 3.0421, "eval_samples_per_second": 331.683, "step": 1410 }, { "epoch": 52.78, "eval_loss": 0.32787543535232544, "eval_micro_f1": 0.6916612793989442, "eval_runtime": 2.5692, "eval_samples_per_second": 392.722, "step": 1425 }, { "epoch": 53.33, "eval_loss": 0.3420737385749817, "eval_micro_f1": 0.6921555697086581, "eval_runtime": 2.9306, "eval_samples_per_second": 344.292, "step": 1440 }, { "epoch": 53.89, "eval_loss": 0.36443910002708435, "eval_micro_f1": 0.6675730790461573, "eval_runtime": 2.6681, "eval_samples_per_second": 378.17, "step": 1455 }, { "epoch": 54.44, "eval_loss": 0.32682710886001587, "eval_micro_f1": 0.6928525429663063, "eval_runtime": 5.618, "eval_samples_per_second": 179.601, "step": 1470 }, { "epoch": 55.0, "eval_loss": 0.335342675447464, "eval_micro_f1": 0.6962190347052247, "eval_runtime": 2.5535, "eval_samples_per_second": 395.147, "step": 1485 }, { "epoch": 55.56, "learning_rate": 8.148148148148148e-06, "loss": 0.0019, "step": 1500 }, { "epoch": 55.56, "eval_loss": 0.33263733983039856, "eval_micro_f1": 0.690909090411867, "eval_runtime": 2.5605, "eval_samples_per_second": 394.068, "step": 1500 }, { "epoch": 56.11, "eval_loss": 0.3214186429977417, "eval_micro_f1": 0.6896112168371584, "eval_runtime": 2.5655, "eval_samples_per_second": 393.289, "step": 1515 }, { "epoch": 56.67, "eval_loss": 0.3201906085014343, "eval_micro_f1": 0.6945876283680734, "eval_runtime": 2.5148, "eval_samples_per_second": 401.223, "step": 1530 }, { "epoch": 57.22, "eval_loss": 0.3486175835132599, "eval_micro_f1": 0.6752717386387476, "eval_runtime": 2.9392, "eval_samples_per_second": 343.296, "step": 1545 }, { "epoch": 57.78, "eval_loss": 0.3262138068675995, "eval_micro_f1": 0.6903684545767093, "eval_runtime": 2.5281, "eval_samples_per_second": 399.115, "step": 1560 }, { "epoch": 58.33, "eval_loss": 0.32193559408187866, "eval_micro_f1": 0.6948717943734812, "eval_runtime": 2.6026, "eval_samples_per_second": 387.683, "step": 1575 }, { "epoch": 58.89, "eval_loss": 0.35099563002586365, "eval_micro_f1": 0.6756032166645486, "eval_runtime": 2.5669, "eval_samples_per_second": 393.075, "step": 1590 }, { "epoch": 59.44, "eval_loss": 0.3329455256462097, "eval_micro_f1": 0.6848958328363612, "eval_runtime": 2.585, "eval_samples_per_second": 390.336, "step": 1605 }, { "epoch": 60.0, "eval_loss": 0.3253725469112396, "eval_micro_f1": 0.6926070033937061, "eval_runtime": 2.5692, "eval_samples_per_second": 392.733, "step": 1620 }, { "epoch": 60.56, "eval_loss": 0.3497498333454132, "eval_micro_f1": 0.6808794132297661, "eval_runtime": 2.6299, "eval_samples_per_second": 383.662, "step": 1635 }, { "epoch": 61.11, "eval_loss": 0.32785752415657043, "eval_micro_f1": 0.6976144417974368, "eval_runtime": 2.8838, "eval_samples_per_second": 349.883, "step": 1650 }, { "epoch": 61.67, "eval_loss": 0.34117451310157776, "eval_micro_f1": 0.7051114018627614, "eval_runtime": 2.6412, "eval_samples_per_second": 382.028, "step": 1665 }, { "epoch": 62.22, "eval_loss": 0.3263133466243744, "eval_micro_f1": 0.7001303775996134, "eval_runtime": 2.5665, "eval_samples_per_second": 393.136, "step": 1680 }, { "epoch": 62.78, "eval_loss": 0.32736286520957947, "eval_micro_f1": 0.7017994853630594, "eval_runtime": 2.68, "eval_samples_per_second": 376.496, "step": 1695 }, { "epoch": 63.33, "eval_loss": 0.3275659382343292, "eval_micro_f1": 0.7002617796082361, "eval_runtime": 2.6332, "eval_samples_per_second": 383.181, "step": 1710 }, { "epoch": 63.89, "eval_loss": 0.35345253348350525, "eval_micro_f1": 0.6809651469594478, "eval_runtime": 2.5501, "eval_samples_per_second": 395.677, "step": 1725 }, { "epoch": 64.44, "eval_loss": 0.3252473771572113, "eval_micro_f1": 0.6958762881618862, "eval_runtime": 2.5917, "eval_samples_per_second": 389.325, "step": 1740 }, { "epoch": 65.0, "eval_loss": 0.3239486515522003, "eval_micro_f1": 0.6923579354928857, "eval_runtime": 2.5613, "eval_samples_per_second": 393.944, "step": 1755 }, { "epoch": 65.56, "eval_loss": 0.3280043303966522, "eval_micro_f1": 0.6838283823427507, "eval_runtime": 2.7515, "eval_samples_per_second": 366.714, "step": 1770 }, { "epoch": 66.11, "eval_loss": 0.3252258598804474, "eval_micro_f1": 0.6933158579571413, "eval_runtime": 2.6889, "eval_samples_per_second": 375.251, "step": 1785 }, { "epoch": 66.67, "eval_loss": 0.33059778809547424, "eval_micro_f1": 0.6940639264438444, "eval_runtime": 2.6787, "eval_samples_per_second": 376.677, "step": 1800 }, { "epoch": 67.22, "eval_loss": 0.3445133864879608, "eval_micro_f1": 0.6859060397749956, "eval_runtime": 2.6726, "eval_samples_per_second": 377.54, "step": 1815 }, { "epoch": 67.78, "eval_loss": 0.3431583344936371, "eval_micro_f1": 0.6972477059256813, "eval_runtime": 3.1262, "eval_samples_per_second": 322.751, "step": 1830 }, { "epoch": 68.33, "eval_loss": 0.3375631272792816, "eval_micro_f1": 0.6987012982040648, "eval_runtime": 2.5597, "eval_samples_per_second": 394.194, "step": 1845 }, { "epoch": 68.89, "eval_loss": 0.36760658025741577, "eval_micro_f1": 0.6689466479362135, "eval_runtime": 2.9233, "eval_samples_per_second": 345.156, "step": 1860 }, { "epoch": 69.44, "eval_loss": 0.33935949206352234, "eval_micro_f1": 0.695137975850855, "eval_runtime": 2.576, "eval_samples_per_second": 391.687, "step": 1875 }, { "epoch": 70.0, "eval_loss": 0.3526156544685364, "eval_micro_f1": 0.6883720925284975, "eval_runtime": 2.5695, "eval_samples_per_second": 392.687, "step": 1890 }, { "epoch": 70.56, "eval_loss": 0.3570711612701416, "eval_micro_f1": 0.6859776163573624, "eval_runtime": 2.7208, "eval_samples_per_second": 370.848, "step": 1905 }, { "epoch": 71.11, "eval_loss": 0.3528156578540802, "eval_micro_f1": 0.6912928754938282, "eval_runtime": 2.6561, "eval_samples_per_second": 379.878, "step": 1920 }, { "epoch": 71.67, "eval_loss": 0.3491019606590271, "eval_micro_f1": 0.6915032674772591, "eval_runtime": 2.6293, "eval_samples_per_second": 383.754, "step": 1935 }, { "epoch": 72.22, "eval_loss": 0.35152795910835266, "eval_micro_f1": 0.695307335922316, "eval_runtime": 2.5632, "eval_samples_per_second": 393.643, "step": 1950 }, { "epoch": 72.78, "eval_loss": 0.354746550321579, "eval_micro_f1": 0.6990679089595354, "eval_runtime": 2.5637, "eval_samples_per_second": 393.571, "step": 1965 }, { "epoch": 73.33, "eval_loss": 0.34360215067863464, "eval_micro_f1": 0.7015706801317946, "eval_runtime": 2.554, "eval_samples_per_second": 395.062, "step": 1980 }, { "epoch": 73.89, "eval_loss": 0.34746265411376953, "eval_micro_f1": 0.7015706801317946, "eval_runtime": 2.5712, "eval_samples_per_second": 392.431, "step": 1995 }, { "epoch": 74.07, "learning_rate": 7.530864197530865e-06, "loss": 0.0014, "step": 2000 }, { "epoch": 74.44, "eval_loss": 0.35273224115371704, "eval_micro_f1": 0.7003942176379703, "eval_runtime": 2.9303, "eval_samples_per_second": 344.338, "step": 2010 }, { "epoch": 75.0, "eval_loss": 0.3567138910293579, "eval_micro_f1": 0.6908850721597507, "eval_runtime": 2.5774, "eval_samples_per_second": 391.483, "step": 2025 }, { "epoch": 75.56, "eval_loss": 0.33884572982788086, "eval_micro_f1": 0.6993464047321508, "eval_runtime": 2.6115, "eval_samples_per_second": 386.369, "step": 2040 }, { "epoch": 76.11, "eval_loss": 0.37058141827583313, "eval_micro_f1": 0.6797033036204883, "eval_runtime": 2.8141, "eval_samples_per_second": 358.548, "step": 2055 }, { "epoch": 76.67, "eval_loss": 0.3556163012981415, "eval_micro_f1": 0.6902887134145708, "eval_runtime": 2.5688, "eval_samples_per_second": 392.797, "step": 2070 }, { "epoch": 77.22, "eval_loss": 0.34995415806770325, "eval_micro_f1": 0.7031249995030042, "eval_runtime": 2.6615, "eval_samples_per_second": 379.105, "step": 2085 }, { "epoch": 77.78, "eval_loss": 0.34786102175712585, "eval_micro_f1": 0.7032679733595967, "eval_runtime": 2.6641, "eval_samples_per_second": 378.743, "step": 2100 }, { "epoch": 78.33, "eval_loss": 0.34595397114753723, "eval_micro_f1": 0.7046496393202195, "eval_runtime": 2.6812, "eval_samples_per_second": 376.33, "step": 2115 }, { "epoch": 78.89, "eval_loss": 0.3473433256149292, "eval_micro_f1": 0.7082521112636975, "eval_runtime": 2.7363, "eval_samples_per_second": 368.74, "step": 2130 }, { "epoch": 79.44, "eval_loss": 0.36449724435806274, "eval_micro_f1": 0.6909331563545306, "eval_runtime": 2.8416, "eval_samples_per_second": 355.08, "step": 2145 }, { "epoch": 80.0, "eval_loss": 0.3454570770263672, "eval_micro_f1": 0.7115135829435392, "eval_runtime": 2.9236, "eval_samples_per_second": 345.123, "step": 2160 }, { "epoch": 80.56, "eval_loss": 0.3559670150279999, "eval_micro_f1": 0.7011795538942215, "eval_runtime": 2.5167, "eval_samples_per_second": 400.923, "step": 2175 }, { "epoch": 81.11, "eval_loss": 0.334154337644577, "eval_micro_f1": 0.7093469905387033, "eval_runtime": 3.0216, "eval_samples_per_second": 333.924, "step": 2190 }, { "epoch": 81.67, "eval_loss": 0.3618710935115814, "eval_micro_f1": 0.684986594680622, "eval_runtime": 5.1103, "eval_samples_per_second": 197.442, "step": 2205 }, { "epoch": 82.22, "eval_loss": 0.3592054545879364, "eval_micro_f1": 0.6854082993723113, "eval_runtime": 2.6676, "eval_samples_per_second": 378.237, "step": 2220 }, { "epoch": 82.78, "eval_loss": 0.34084373712539673, "eval_micro_f1": 0.7000642255776152, "eval_runtime": 2.5549, "eval_samples_per_second": 394.935, "step": 2235 }, { "epoch": 83.33, "eval_loss": 0.35217487812042236, "eval_micro_f1": 0.6996098824677752, "eval_runtime": 2.5385, "eval_samples_per_second": 397.474, "step": 2250 }, { "epoch": 83.89, "eval_loss": 0.3753242492675781, "eval_micro_f1": 0.6724715333308007, "eval_runtime": 2.6889, "eval_samples_per_second": 375.253, "step": 2265 }, { "epoch": 84.44, "eval_loss": 0.3565642833709717, "eval_micro_f1": 0.6909331563545306, "eval_runtime": 2.5598, "eval_samples_per_second": 394.17, "step": 2280 }, { "epoch": 85.0, "eval_loss": 0.35410866141319275, "eval_micro_f1": 0.700520832836341, "eval_runtime": 2.6358, "eval_samples_per_second": 382.812, "step": 2295 }, { "epoch": 85.56, "eval_loss": 0.3323992192745209, "eval_micro_f1": 0.7078294075215347, "eval_runtime": 2.608, "eval_samples_per_second": 386.892, "step": 2310 }, { "epoch": 86.11, "eval_loss": 0.33769142627716064, "eval_micro_f1": 0.7076135631611551, "eval_runtime": 2.6496, "eval_samples_per_second": 380.818, "step": 2325 }, { "epoch": 86.67, "eval_loss": 0.36460915207862854, "eval_micro_f1": 0.6943346503606211, "eval_runtime": 2.5209, "eval_samples_per_second": 400.249, "step": 2340 }, { "epoch": 87.22, "eval_loss": 0.34131544828414917, "eval_micro_f1": 0.703115066252517, "eval_runtime": 2.532, "eval_samples_per_second": 398.495, "step": 2355 }, { "epoch": 87.78, "eval_loss": 0.3585151731967926, "eval_micro_f1": 0.6979166661696778, "eval_runtime": 2.75, "eval_samples_per_second": 366.913, "step": 2370 }, { "epoch": 88.33, "eval_loss": 0.36730679869651794, "eval_micro_f1": 0.6918990698902822, "eval_runtime": 2.546, "eval_samples_per_second": 396.3, "step": 2385 }, { "epoch": 88.89, "eval_loss": 0.35094428062438965, "eval_micro_f1": 0.6981865279999412, "eval_runtime": 2.6454, "eval_samples_per_second": 381.411, "step": 2400 }, { "epoch": 89.44, "eval_loss": 0.33933812379837036, "eval_micro_f1": 0.7078294075215347, "eval_runtime": 2.6062, "eval_samples_per_second": 387.156, "step": 2415 }, { "epoch": 90.0, "eval_loss": 0.3515303134918213, "eval_micro_f1": 0.707632599761138, "eval_runtime": 2.8781, "eval_samples_per_second": 350.584, "step": 2430 }, { "epoch": 90.56, "eval_loss": 0.36421099305152893, "eval_micro_f1": 0.6978275176081696, "eval_runtime": 3.0424, "eval_samples_per_second": 331.644, "step": 2445 }, { "epoch": 91.11, "eval_loss": 0.35457924008369446, "eval_micro_f1": 0.7031249995030042, "eval_runtime": 2.6081, "eval_samples_per_second": 386.868, "step": 2460 }, { "epoch": 91.67, "eval_loss": 0.35205426812171936, "eval_micro_f1": 0.7064935059962625, "eval_runtime": 2.7132, "eval_samples_per_second": 371.887, "step": 2475 }, { "epoch": 92.22, "eval_loss": 0.3589094579219818, "eval_micro_f1": 0.7048114429359089, "eval_runtime": 2.5454, "eval_samples_per_second": 396.399, "step": 2490 }, { "epoch": 92.59, "learning_rate": 6.913580246913581e-06, "loss": 0.0011, "step": 2500 }, { "epoch": 92.78, "eval_loss": 0.3579725921154022, "eval_micro_f1": 0.7061118330529422, "eval_runtime": 2.6758, "eval_samples_per_second": 377.078, "step": 2505 }, { "epoch": 93.33, "eval_loss": 0.3536120355129242, "eval_micro_f1": 0.7043534757861197, "eval_runtime": 3.0043, "eval_samples_per_second": 335.847, "step": 2520 }, { "epoch": 93.89, "eval_loss": 0.3673434853553772, "eval_micro_f1": 0.693741677268464, "eval_runtime": 2.5556, "eval_samples_per_second": 394.817, "step": 2535 }, { "epoch": 94.44, "eval_loss": 0.3752725422382355, "eval_micro_f1": 0.6976127316004791, "eval_runtime": 2.5309, "eval_samples_per_second": 398.666, "step": 2550 }, { "epoch": 95.0, "eval_loss": 0.354266494512558, "eval_micro_f1": 0.7054263560914441, "eval_runtime": 2.5903, "eval_samples_per_second": 389.525, "step": 2565 }, { "epoch": 95.56, "eval_loss": 0.35904696583747864, "eval_micro_f1": 0.7007772015750674, "eval_runtime": 2.5331, "eval_samples_per_second": 398.323, "step": 2580 }, { "epoch": 96.11, "eval_loss": 0.36157509684562683, "eval_micro_f1": 0.6964980539773585, "eval_runtime": 2.5911, "eval_samples_per_second": 389.412, "step": 2595 }, { "epoch": 96.67, "eval_loss": 0.35322824120521545, "eval_micro_f1": 0.7054263560914441, "eval_runtime": 5.6615, "eval_samples_per_second": 178.222, "step": 2610 }, { "epoch": 97.22, "eval_loss": 0.3600855767726898, "eval_micro_f1": 0.7000650613116647, "eval_runtime": 2.8586, "eval_samples_per_second": 352.973, "step": 2625 }, { "epoch": 97.78, "eval_loss": 0.37259265780448914, "eval_micro_f1": 0.7028795806553532, "eval_runtime": 2.9678, "eval_samples_per_second": 339.986, "step": 2640 }, { "epoch": 98.33, "eval_loss": 0.3627021312713623, "eval_micro_f1": 0.7015706801317946, "eval_runtime": 2.6863, "eval_samples_per_second": 375.609, "step": 2655 }, { "epoch": 98.89, "eval_loss": 0.3574976325035095, "eval_micro_f1": 0.7025275432485336, "eval_runtime": 2.6249, "eval_samples_per_second": 384.392, "step": 2670 }, { "epoch": 99.44, "eval_loss": 0.3473261296749115, "eval_micro_f1": 0.7041719337611578, "eval_runtime": 2.5453, "eval_samples_per_second": 396.414, "step": 2685 }, { "epoch": 100.0, "eval_loss": 0.36624401807785034, "eval_micro_f1": 0.7032385983149028, "eval_runtime": 3.124, "eval_samples_per_second": 322.981, "step": 2700 }, { "epoch": 100.56, "eval_loss": 0.3743077218532562, "eval_micro_f1": 0.6912257195330528, "eval_runtime": 2.8949, "eval_samples_per_second": 348.541, "step": 2715 }, { "epoch": 101.11, "eval_loss": 0.3670189380645752, "eval_micro_f1": 0.6978891815624212, "eval_runtime": 2.5808, "eval_samples_per_second": 390.969, "step": 2730 }, { "epoch": 101.67, "eval_loss": 0.34900036454200745, "eval_micro_f1": 0.6976744181069581, "eval_runtime": 2.556, "eval_samples_per_second": 394.765, "step": 2745 }, { "epoch": 102.22, "eval_loss": 0.34599569439888, "eval_micro_f1": 0.7028753988624614, "eval_runtime": 2.6258, "eval_samples_per_second": 384.259, "step": 2760 }, { "epoch": 102.78, "eval_loss": 0.3519628942012787, "eval_micro_f1": 0.7081462470963303, "eval_runtime": 2.5357, "eval_samples_per_second": 397.918, "step": 2775 }, { "epoch": 103.33, "eval_loss": 0.37963739037513733, "eval_micro_f1": 0.6860927147366344, "eval_runtime": 2.5541, "eval_samples_per_second": 395.051, "step": 2790 }, { "epoch": 103.89, "eval_loss": 0.36691129207611084, "eval_micro_f1": 0.6967910931512711, "eval_runtime": 2.6114, "eval_samples_per_second": 386.377, "step": 2805 }, { "epoch": 104.44, "eval_loss": 0.37201792001724243, "eval_micro_f1": 0.6961690880117913, "eval_runtime": 2.5474, "eval_samples_per_second": 396.091, "step": 2820 }, { "epoch": 105.0, "eval_loss": 0.3851890563964844, "eval_micro_f1": 0.6873315358952383, "eval_runtime": 2.593, "eval_samples_per_second": 389.125, "step": 2835 }, { "epoch": 105.56, "eval_loss": 0.3663199543952942, "eval_micro_f1": 0.7005948441840406, "eval_runtime": 2.5241, "eval_samples_per_second": 399.745, "step": 2850 }, { "epoch": 106.11, "eval_loss": 0.3643597364425659, "eval_micro_f1": 0.7067276285039708, "eval_runtime": 2.6003, "eval_samples_per_second": 388.04, "step": 2865 }, { "epoch": 106.67, "eval_loss": 0.3705441355705261, "eval_micro_f1": 0.7012475372582969, "eval_runtime": 2.5794, "eval_samples_per_second": 391.172, "step": 2880 }, { "epoch": 107.22, "eval_loss": 0.3567045032978058, "eval_micro_f1": 0.7062621040858431, "eval_runtime": 2.6966, "eval_samples_per_second": 374.179, "step": 2895 }, { "epoch": 107.78, "eval_loss": 0.3563016355037689, "eval_micro_f1": 0.7089743584760272, "eval_runtime": 2.5086, "eval_samples_per_second": 402.218, "step": 2910 }, { "epoch": 108.33, "eval_loss": 0.3776358366012573, "eval_micro_f1": 0.6988896141342881, "eval_runtime": 2.6311, "eval_samples_per_second": 383.487, "step": 2925 }, { "epoch": 108.89, "eval_loss": 0.38929614424705505, "eval_micro_f1": 0.6904290424087486, "eval_runtime": 2.5339, "eval_samples_per_second": 398.194, "step": 2940 }, { "epoch": 109.44, "eval_loss": 0.35840705037117004, "eval_micro_f1": 0.7121699930628685, "eval_runtime": 3.2318, "eval_samples_per_second": 312.209, "step": 2955 }, { "epoch": 110.0, "eval_loss": 0.3539954423904419, "eval_micro_f1": 0.7126288654814522, "eval_runtime": 2.6432, "eval_samples_per_second": 381.734, "step": 2970 }, { "epoch": 110.56, "eval_loss": 0.3581095039844513, "eval_micro_f1": 0.7109677414376641, "eval_runtime": 2.6187, "eval_samples_per_second": 385.312, "step": 2985 }, { "epoch": 111.11, "learning_rate": 6.296296296296297e-06, "loss": 0.0009, "step": 3000 }, { "epoch": 111.11, "eval_loss": 0.3580523729324341, "eval_micro_f1": 0.7151125396948369, "eval_runtime": 2.6726, "eval_samples_per_second": 377.536, "step": 3000 }, { "epoch": 111.67, "eval_loss": 0.3438720107078552, "eval_micro_f1": 0.7202531640577455, "eval_runtime": 2.6312, "eval_samples_per_second": 383.471, "step": 3015 } ], "max_steps": 8100, "num_train_epochs": 300, "total_flos": 16700749152595560, "trial_name": null, "trial_params": null }