{ "best_metric": 0.6952624834964678, "best_model_checkpoint": "/shared/data/jatin2/sec-ner/multirun/wnut/span-qa/run-142/checkpoints/checkpoint-4875", "epoch": 180.55555555555554, "global_step": 4875, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.56, "eval_loss": 0.313260018825531, "eval_micro_f1": 0.0, "eval_runtime": 3.2766, "eval_samples_per_second": 307.944, "step": 15 }, { "epoch": 1.11, "eval_loss": 0.239724263548851, "eval_micro_f1": 0.0, "eval_runtime": 3.3945, "eval_samples_per_second": 297.248, "step": 30 }, { "epoch": 1.67, "eval_loss": 0.2000923752784729, "eval_micro_f1": 0.0, "eval_runtime": 3.1571, "eval_samples_per_second": 319.595, "step": 45 }, { "epoch": 2.22, "eval_loss": 0.17800624668598175, "eval_micro_f1": 0.06694560647488665, "eval_runtime": 3.2999, "eval_samples_per_second": 305.767, "step": 60 }, { "epoch": 2.78, "eval_loss": 0.1711592972278595, "eval_micro_f1": 0.15723873410148653, "eval_runtime": 3.2869, "eval_samples_per_second": 306.974, "step": 75 }, { "epoch": 3.33, "eval_loss": 0.16085116565227509, "eval_micro_f1": 0.3108320246660489, "eval_runtime": 3.4788, "eval_samples_per_second": 290.043, "step": 90 }, { "epoch": 3.89, "eval_loss": 0.15053889155387878, "eval_micro_f1": 0.4086956516957068, "eval_runtime": 3.1716, "eval_samples_per_second": 318.131, "step": 105 }, { "epoch": 4.44, "eval_loss": 0.14953985810279846, "eval_micro_f1": 0.4923891457657794, "eval_runtime": 3.2585, "eval_samples_per_second": 309.65, "step": 120 }, { "epoch": 5.0, "eval_loss": 0.14207378029823303, "eval_micro_f1": 0.5330606675390301, "eval_runtime": 3.3137, "eval_samples_per_second": 304.498, "step": 135 }, { "epoch": 5.56, "eval_loss": 0.13747094571590424, "eval_micro_f1": 0.581486309803158, "eval_runtime": 2.9352, "eval_samples_per_second": 343.761, "step": 150 }, { "epoch": 6.11, "eval_loss": 0.1413855254650116, "eval_micro_f1": 0.5915119358446518, "eval_runtime": 3.1713, "eval_samples_per_second": 318.171, "step": 165 }, { "epoch": 6.67, "eval_loss": 0.15051181614398956, "eval_micro_f1": 0.5846153841216111, "eval_runtime": 3.3376, "eval_samples_per_second": 302.31, "step": 180 }, { "epoch": 7.22, "eval_loss": 0.15090800821781158, "eval_micro_f1": 0.6091644199923787, "eval_runtime": 3.1795, "eval_samples_per_second": 317.347, "step": 195 }, { "epoch": 7.78, "eval_loss": 0.1604917347431183, "eval_micro_f1": 0.6052454601659701, "eval_runtime": 3.1881, "eval_samples_per_second": 316.493, "step": 210 }, { "epoch": 8.33, "eval_loss": 0.15166428685188293, "eval_micro_f1": 0.6207809392798385, "eval_runtime": 3.3057, "eval_samples_per_second": 305.235, "step": 225 }, { "epoch": 8.89, "eval_loss": 0.154179647564888, "eval_micro_f1": 0.6202365303844619, "eval_runtime": 3.2187, "eval_samples_per_second": 313.478, "step": 240 }, { "epoch": 9.44, "eval_loss": 0.15733785927295685, "eval_micro_f1": 0.6295336782590976, "eval_runtime": 3.305, "eval_samples_per_second": 305.296, "step": 255 }, { "epoch": 10.0, "eval_loss": 0.16918115317821503, "eval_micro_f1": 0.6156914888671221, "eval_runtime": 3.3124, "eval_samples_per_second": 304.61, "step": 270 }, { "epoch": 10.56, "eval_loss": 0.17472217977046967, "eval_micro_f1": 0.6121902205378472, "eval_runtime": 3.5035, "eval_samples_per_second": 287.997, "step": 285 }, { "epoch": 11.11, "eval_loss": 0.1879921555519104, "eval_micro_f1": 0.5995864915852039, "eval_runtime": 2.959, "eval_samples_per_second": 340.998, "step": 300 }, { "epoch": 11.67, "eval_loss": 0.18798305094242096, "eval_micro_f1": 0.6079779912573084, "eval_runtime": 3.2377, "eval_samples_per_second": 311.642, "step": 315 }, { "epoch": 12.22, "eval_loss": 0.18920889496803284, "eval_micro_f1": 0.6128590966367006, "eval_runtime": 3.2849, "eval_samples_per_second": 307.162, "step": 330 }, { "epoch": 12.78, "eval_loss": 0.1883956789970398, "eval_micro_f1": 0.6178861783697681, "eval_runtime": 3.1007, "eval_samples_per_second": 325.414, "step": 345 }, { "epoch": 13.33, "eval_loss": 0.1765897125005722, "eval_micro_f1": 0.6243315503082247, "eval_runtime": 3.1283, "eval_samples_per_second": 322.538, "step": 360 }, { "epoch": 13.89, "eval_loss": 0.18092800676822662, "eval_micro_f1": 0.6134228182985829, "eval_runtime": 3.0944, "eval_samples_per_second": 326.074, "step": 375 }, { "epoch": 14.44, "eval_loss": 0.1933341771364212, "eval_micro_f1": 0.6097060828996644, "eval_runtime": 3.2136, "eval_samples_per_second": 313.979, "step": 390 }, { "epoch": 15.0, "eval_loss": 0.19052603840827942, "eval_micro_f1": 0.6233062325703027, "eval_runtime": 3.3749, "eval_samples_per_second": 298.97, "step": 405 }, { "epoch": 15.56, "eval_loss": 0.1840684860944748, "eval_micro_f1": 0.6379310339878262, "eval_runtime": 3.7148, "eval_samples_per_second": 271.618, "step": 420 }, { "epoch": 16.11, "eval_loss": 0.19174893200397491, "eval_micro_f1": 0.6242383204286553, "eval_runtime": 3.2335, "eval_samples_per_second": 312.048, "step": 435 }, { "epoch": 16.67, "eval_loss": 0.19104619324207306, "eval_micro_f1": 0.6321381137150628, "eval_runtime": 3.1405, "eval_samples_per_second": 321.286, "step": 450 }, { "epoch": 17.22, "eval_loss": 0.18311673402786255, "eval_micro_f1": 0.6444007853582813, "eval_runtime": 3.3749, "eval_samples_per_second": 298.973, "step": 465 }, { "epoch": 17.78, "eval_loss": 0.18750086426734924, "eval_micro_f1": 0.6412113227432015, "eval_runtime": 3.2169, "eval_samples_per_second": 313.651, "step": 480 }, { "epoch": 18.33, "eval_loss": 0.19314248859882355, "eval_micro_f1": 0.640583553881722, "eval_runtime": 3.056, "eval_samples_per_second": 330.175, "step": 495 }, { "epoch": 18.52, "learning_rate": 9.382716049382717e-06, "loss": 0.05, "step": 500 }, { "epoch": 18.89, "eval_loss": 0.18314436078071594, "eval_micro_f1": 0.6568877546034025, "eval_runtime": 3.3023, "eval_samples_per_second": 305.546, "step": 510 }, { "epoch": 19.44, "eval_loss": 0.2075609415769577, "eval_micro_f1": 0.6364883397019424, "eval_runtime": 3.7174, "eval_samples_per_second": 271.425, "step": 525 }, { "epoch": 20.0, "eval_loss": 0.19432280957698822, "eval_micro_f1": 0.6412113227432015, "eval_runtime": 3.087, "eval_samples_per_second": 326.851, "step": 540 }, { "epoch": 20.56, "eval_loss": 0.20314611494541168, "eval_micro_f1": 0.6397306392377068, "eval_runtime": 3.413, "eval_samples_per_second": 295.636, "step": 555 }, { "epoch": 21.11, "eval_loss": 0.18867215514183044, "eval_micro_f1": 0.6597537260094446, "eval_runtime": 3.1951, "eval_samples_per_second": 315.793, "step": 570 }, { "epoch": 21.67, "eval_loss": 0.20620323717594147, "eval_micro_f1": 0.6419919241368484, "eval_runtime": 3.223, "eval_samples_per_second": 313.063, "step": 585 }, { "epoch": 22.22, "eval_loss": 0.19779162108898163, "eval_micro_f1": 0.6582781452002473, "eval_runtime": 3.3538, "eval_samples_per_second": 300.854, "step": 600 }, { "epoch": 22.78, "eval_loss": 0.19607913494110107, "eval_micro_f1": 0.6507936502983889, "eval_runtime": 3.3096, "eval_samples_per_second": 304.873, "step": 615 }, { "epoch": 23.33, "eval_loss": 0.19137068092823029, "eval_micro_f1": 0.6501628659526472, "eval_runtime": 3.7145, "eval_samples_per_second": 271.637, "step": 630 }, { "epoch": 23.89, "eval_loss": 0.19038259983062744, "eval_micro_f1": 0.6622778138557477, "eval_runtime": 3.1867, "eval_samples_per_second": 316.631, "step": 645 }, { "epoch": 24.44, "eval_loss": 0.19278232753276825, "eval_micro_f1": 0.6657929221773609, "eval_runtime": 3.3124, "eval_samples_per_second": 304.611, "step": 660 }, { "epoch": 25.0, "eval_loss": 0.20714706182479858, "eval_micro_f1": 0.654594231565511, "eval_runtime": 3.3702, "eval_samples_per_second": 299.39, "step": 675 }, { "epoch": 25.56, "eval_loss": 0.20970705151557922, "eval_micro_f1": 0.6559356131885811, "eval_runtime": 2.9672, "eval_samples_per_second": 340.048, "step": 690 }, { "epoch": 26.11, "eval_loss": 0.21200864017009735, "eval_micro_f1": 0.6499999995075365, "eval_runtime": 3.3032, "eval_samples_per_second": 305.462, "step": 705 }, { "epoch": 26.67, "eval_loss": 0.20903028547763824, "eval_micro_f1": 0.6559356131885811, "eval_runtime": 3.4126, "eval_samples_per_second": 295.667, "step": 720 }, { "epoch": 27.22, "eval_loss": 0.2181977480649948, "eval_micro_f1": 0.6495263865172078, "eval_runtime": 3.4048, "eval_samples_per_second": 296.345, "step": 735 }, { "epoch": 27.78, "eval_loss": 0.22025255858898163, "eval_micro_f1": 0.645380434290962, "eval_runtime": 3.3577, "eval_samples_per_second": 300.502, "step": 750 }, { "epoch": 28.33, "eval_loss": 0.20384617149829865, "eval_micro_f1": 0.6644993493078728, "eval_runtime": 3.2671, "eval_samples_per_second": 308.832, "step": 765 }, { "epoch": 28.89, "eval_loss": 0.19968371093273163, "eval_micro_f1": 0.6710012998930399, "eval_runtime": 3.135, "eval_samples_per_second": 321.849, "step": 780 }, { "epoch": 29.44, "eval_loss": 0.22431273758411407, "eval_micro_f1": 0.6430034124783879, "eval_runtime": 3.2288, "eval_samples_per_second": 312.5, "step": 795 }, { "epoch": 30.0, "eval_loss": 0.22801224887371063, "eval_micro_f1": 0.6591060702195894, "eval_runtime": 3.267, "eval_samples_per_second": 308.85, "step": 810 }, { "epoch": 30.56, "eval_loss": 0.20350828766822815, "eval_micro_f1": 0.6753078413691133, "eval_runtime": 3.2304, "eval_samples_per_second": 312.342, "step": 825 }, { "epoch": 31.11, "eval_loss": 0.23686587810516357, "eval_micro_f1": 0.653171389520832, "eval_runtime": 2.9693, "eval_samples_per_second": 339.81, "step": 840 }, { "epoch": 31.67, "eval_loss": 0.2201978713274002, "eval_micro_f1": 0.664897146154083, "eval_runtime": 3.319, "eval_samples_per_second": 304.01, "step": 855 }, { "epoch": 32.22, "eval_loss": 0.2157113403081894, "eval_micro_f1": 0.6617548555009423, "eval_runtime": 3.3911, "eval_samples_per_second": 297.541, "step": 870 }, { "epoch": 32.78, "eval_loss": 0.22680847346782684, "eval_micro_f1": 0.6543967275252315, "eval_runtime": 3.2036, "eval_samples_per_second": 314.959, "step": 885 }, { "epoch": 33.33, "eval_loss": 0.22924786806106567, "eval_micro_f1": 0.6635388735010259, "eval_runtime": 3.3227, "eval_samples_per_second": 303.669, "step": 900 }, { "epoch": 33.89, "eval_loss": 0.20929349958896637, "eval_micro_f1": 0.6705805604947557, "eval_runtime": 3.2037, "eval_samples_per_second": 314.95, "step": 915 }, { "epoch": 34.44, "eval_loss": 0.2289011925458908, "eval_micro_f1": 0.6581081076156337, "eval_runtime": 3.1744, "eval_samples_per_second": 317.854, "step": 930 }, { "epoch": 35.0, "eval_loss": 0.2096581757068634, "eval_micro_f1": 0.6696832574209506, "eval_runtime": 3.2222, "eval_samples_per_second": 313.138, "step": 945 }, { "epoch": 35.56, "eval_loss": 0.22394207119941711, "eval_micro_f1": 0.6626425213039309, "eval_runtime": 3.321, "eval_samples_per_second": 303.823, "step": 960 }, { "epoch": 36.11, "eval_loss": 0.2278466522693634, "eval_micro_f1": 0.6626506019158491, "eval_runtime": 3.3124, "eval_samples_per_second": 304.611, "step": 975 }, { "epoch": 36.67, "eval_loss": 0.22448717057704926, "eval_micro_f1": 0.6662251650677864, "eval_runtime": 3.7159, "eval_samples_per_second": 271.538, "step": 990 }, { "epoch": 37.04, "learning_rate": 8.765432098765432e-06, "loss": 0.0035, "step": 1000 }, { "epoch": 37.22, "eval_loss": 0.22992148995399475, "eval_micro_f1": 0.66355762775344, "eval_runtime": 3.1737, "eval_samples_per_second": 317.93, "step": 1005 }, { "epoch": 37.78, "eval_loss": 0.2327638566493988, "eval_micro_f1": 0.6617647053883886, "eval_runtime": 3.2078, "eval_samples_per_second": 314.543, "step": 1020 }, { "epoch": 38.33, "eval_loss": 0.23346643149852753, "eval_micro_f1": 0.6586826342359839, "eval_runtime": 2.9531, "eval_samples_per_second": 341.68, "step": 1035 }, { "epoch": 38.89, "eval_loss": 0.23170535266399384, "eval_micro_f1": 0.666666666173416, "eval_runtime": 3.2597, "eval_samples_per_second": 309.537, "step": 1050 }, { "epoch": 39.44, "eval_loss": 0.22116872668266296, "eval_micro_f1": 0.6806557372086711, "eval_runtime": 3.1141, "eval_samples_per_second": 324.015, "step": 1065 }, { "epoch": 40.0, "eval_loss": 0.2202962338924408, "eval_micro_f1": 0.6753415739987495, "eval_runtime": 3.06, "eval_samples_per_second": 329.734, "step": 1080 }, { "epoch": 40.56, "eval_loss": 0.22711782157421112, "eval_micro_f1": 0.6729222515170992, "eval_runtime": 3.6825, "eval_samples_per_second": 274.0, "step": 1095 }, { "epoch": 41.11, "eval_loss": 0.21959638595581055, "eval_micro_f1": 0.6771241825099577, "eval_runtime": 3.3006, "eval_samples_per_second": 305.705, "step": 1110 }, { "epoch": 41.67, "eval_loss": 0.24371322989463806, "eval_micro_f1": 0.650652024218299, "eval_runtime": 3.1256, "eval_samples_per_second": 322.821, "step": 1125 }, { "epoch": 42.22, "eval_loss": 0.22645647823810577, "eval_micro_f1": 0.6609385322211055, "eval_runtime": 3.2675, "eval_samples_per_second": 308.803, "step": 1140 }, { "epoch": 42.78, "eval_loss": 0.2363562136888504, "eval_micro_f1": 0.6626098710424392, "eval_runtime": 3.294, "eval_samples_per_second": 306.314, "step": 1155 }, { "epoch": 43.33, "eval_loss": 0.22681334614753723, "eval_micro_f1": 0.6688874079000019, "eval_runtime": 3.1305, "eval_samples_per_second": 322.309, "step": 1170 }, { "epoch": 43.89, "eval_loss": 0.2312544882297516, "eval_micro_f1": 0.6639784941304089, "eval_runtime": 3.5375, "eval_samples_per_second": 285.231, "step": 1185 }, { "epoch": 44.44, "eval_loss": 0.21217389404773712, "eval_micro_f1": 0.6718547336142258, "eval_runtime": 3.3786, "eval_samples_per_second": 298.644, "step": 1200 }, { "epoch": 45.0, "eval_loss": 0.2182062864303589, "eval_micro_f1": 0.6684245215873973, "eval_runtime": 3.3272, "eval_samples_per_second": 303.254, "step": 1215 }, { "epoch": 45.56, "eval_loss": 0.23220355808734894, "eval_micro_f1": 0.6594594589669831, "eval_runtime": 3.021, "eval_samples_per_second": 334.0, "step": 1230 }, { "epoch": 46.11, "eval_loss": 0.213891863822937, "eval_micro_f1": 0.6744487673366608, "eval_runtime": 3.2729, "eval_samples_per_second": 308.29, "step": 1245 }, { "epoch": 46.67, "eval_loss": 0.2503702640533447, "eval_micro_f1": 0.6491349476083265, "eval_runtime": 3.3031, "eval_samples_per_second": 305.473, "step": 1260 }, { "epoch": 47.22, "eval_loss": 0.2412945032119751, "eval_micro_f1": 0.6648721394800209, "eval_runtime": 3.141, "eval_samples_per_second": 321.235, "step": 1275 }, { "epoch": 47.78, "eval_loss": 0.23627111315727234, "eval_micro_f1": 0.6702412863696497, "eval_runtime": 3.7885, "eval_samples_per_second": 266.332, "step": 1290 }, { "epoch": 48.33, "eval_loss": 0.2444019466638565, "eval_micro_f1": 0.6630211888462765, "eval_runtime": 5.9788, "eval_samples_per_second": 168.764, "step": 1305 }, { "epoch": 48.89, "eval_loss": 0.2294379621744156, "eval_micro_f1": 0.6693494294192807, "eval_runtime": 3.0553, "eval_samples_per_second": 330.248, "step": 1320 }, { "epoch": 49.44, "eval_loss": 0.23858784139156342, "eval_micro_f1": 0.6675675670750802, "eval_runtime": 3.3408, "eval_samples_per_second": 302.019, "step": 1335 }, { "epoch": 50.0, "eval_loss": 0.23860998451709747, "eval_micro_f1": 0.6680107521949196, "eval_runtime": 3.3983, "eval_samples_per_second": 296.911, "step": 1350 }, { "epoch": 50.56, "eval_loss": 0.2395690381526947, "eval_micro_f1": 0.6634877379283701, "eval_runtime": 3.293, "eval_samples_per_second": 306.406, "step": 1365 }, { "epoch": 51.11, "eval_loss": 0.21817098557949066, "eval_micro_f1": 0.6884389283080443, "eval_runtime": 3.3714, "eval_samples_per_second": 299.284, "step": 1380 }, { "epoch": 51.67, "eval_loss": 0.23507370054721832, "eval_micro_f1": 0.6730115562725264, "eval_runtime": 3.1901, "eval_samples_per_second": 316.289, "step": 1395 }, { "epoch": 52.22, "eval_loss": 0.23345457017421722, "eval_micro_f1": 0.6693440423442203, "eval_runtime": 3.2441, "eval_samples_per_second": 311.03, "step": 1410 }, { "epoch": 52.78, "eval_loss": 0.24302314221858978, "eval_micro_f1": 0.667574931388855, "eval_runtime": 3.1029, "eval_samples_per_second": 325.179, "step": 1425 }, { "epoch": 53.33, "eval_loss": 0.2245866358280182, "eval_micro_f1": 0.6713645094312003, "eval_runtime": 3.4183, "eval_samples_per_second": 295.172, "step": 1440 }, { "epoch": 53.89, "eval_loss": 0.23183463513851166, "eval_micro_f1": 0.6772697145480112, "eval_runtime": 3.4115, "eval_samples_per_second": 295.764, "step": 1455 }, { "epoch": 54.44, "eval_loss": 0.2349890023469925, "eval_micro_f1": 0.6799468786552383, "eval_runtime": 3.0939, "eval_samples_per_second": 326.125, "step": 1470 }, { "epoch": 55.0, "eval_loss": 0.256824254989624, "eval_micro_f1": 0.6643646403950256, "eval_runtime": 3.1773, "eval_samples_per_second": 317.569, "step": 1485 }, { "epoch": 55.56, "learning_rate": 8.148148148148148e-06, "loss": 0.0017, "step": 1500 }, { "epoch": 55.56, "eval_loss": 0.23744350671768188, "eval_micro_f1": 0.6837944659074071, "eval_runtime": 3.3632, "eval_samples_per_second": 300.016, "step": 1500 }, { "epoch": 56.11, "eval_loss": 0.24361883103847504, "eval_micro_f1": 0.6751677847414531, "eval_runtime": 3.2637, "eval_samples_per_second": 309.156, "step": 1515 }, { "epoch": 56.67, "eval_loss": 0.2461172193288803, "eval_micro_f1": 0.6698113202618388, "eval_runtime": 3.3105, "eval_samples_per_second": 304.788, "step": 1530 }, { "epoch": 57.22, "eval_loss": 0.2412833869457245, "eval_micro_f1": 0.6750830559836647, "eval_runtime": 3.342, "eval_samples_per_second": 301.918, "step": 1545 }, { "epoch": 57.78, "eval_loss": 0.24493151903152466, "eval_micro_f1": 0.6715522979732826, "eval_runtime": 3.3232, "eval_samples_per_second": 303.62, "step": 1560 }, { "epoch": 58.33, "eval_loss": 0.24852925539016724, "eval_micro_f1": 0.6693017122842377, "eval_runtime": 2.9994, "eval_samples_per_second": 336.396, "step": 1575 }, { "epoch": 58.89, "eval_loss": 0.24091537296772003, "eval_micro_f1": 0.673726008770172, "eval_runtime": 3.8292, "eval_samples_per_second": 263.504, "step": 1590 }, { "epoch": 59.44, "eval_loss": 0.23166577517986298, "eval_micro_f1": 0.6870129865157683, "eval_runtime": 3.2351, "eval_samples_per_second": 311.896, "step": 1605 }, { "epoch": 60.0, "eval_loss": 0.26394179463386536, "eval_micro_f1": 0.6574585630469689, "eval_runtime": 3.0635, "eval_samples_per_second": 329.363, "step": 1620 }, { "epoch": 60.56, "eval_loss": 0.23707003891468048, "eval_micro_f1": 0.6848602983982308, "eval_runtime": 3.2621, "eval_samples_per_second": 309.305, "step": 1635 }, { "epoch": 61.11, "eval_loss": 0.24877381324768066, "eval_micro_f1": 0.6697736346586424, "eval_runtime": 3.3159, "eval_samples_per_second": 304.288, "step": 1650 }, { "epoch": 61.67, "eval_loss": 0.2669653296470642, "eval_micro_f1": 0.6639231819515619, "eval_runtime": 3.3787, "eval_samples_per_second": 298.633, "step": 1665 }, { "epoch": 62.22, "eval_loss": 0.2299225628376007, "eval_micro_f1": 0.690231361969758, "eval_runtime": 3.3542, "eval_samples_per_second": 300.815, "step": 1680 }, { "epoch": 62.78, "eval_loss": 0.24627685546875, "eval_micro_f1": 0.673811118059533, "eval_runtime": 3.3115, "eval_samples_per_second": 304.698, "step": 1695 }, { "epoch": 63.33, "eval_loss": 0.2406027615070343, "eval_micro_f1": 0.6882430642337304, "eval_runtime": 3.2952, "eval_samples_per_second": 306.2, "step": 1710 }, { "epoch": 63.89, "eval_loss": 0.24287304282188416, "eval_micro_f1": 0.6817275742560811, "eval_runtime": 3.116, "eval_samples_per_second": 323.817, "step": 1725 }, { "epoch": 64.44, "eval_loss": 0.24628755450248718, "eval_micro_f1": 0.6750830559836647, "eval_runtime": 3.2034, "eval_samples_per_second": 314.98, "step": 1740 }, { "epoch": 65.0, "eval_loss": 0.25697484612464905, "eval_micro_f1": 0.6711229941584296, "eval_runtime": 3.5154, "eval_samples_per_second": 287.023, "step": 1755 }, { "epoch": 65.56, "eval_loss": 0.2543223798274994, "eval_micro_f1": 0.6759999995056729, "eval_runtime": 3.4333, "eval_samples_per_second": 293.886, "step": 1770 }, { "epoch": 66.11, "eval_loss": 0.2576121687889099, "eval_micro_f1": 0.6716115976191505, "eval_runtime": 3.2514, "eval_samples_per_second": 310.329, "step": 1785 }, { "epoch": 66.67, "eval_loss": 0.25401005148887634, "eval_micro_f1": 0.6755674227368187, "eval_runtime": 3.3419, "eval_samples_per_second": 301.928, "step": 1800 }, { "epoch": 67.22, "eval_loss": 0.24238573014736176, "eval_micro_f1": 0.6797385615949215, "eval_runtime": 3.1665, "eval_samples_per_second": 318.651, "step": 1815 }, { "epoch": 67.78, "eval_loss": 0.26420968770980835, "eval_micro_f1": 0.6698499312961348, "eval_runtime": 3.3558, "eval_samples_per_second": 300.676, "step": 1830 }, { "epoch": 68.33, "eval_loss": 0.25281643867492676, "eval_micro_f1": 0.6697798527412564, "eval_runtime": 3.3326, "eval_samples_per_second": 302.766, "step": 1845 }, { "epoch": 68.89, "eval_loss": 0.23178596794605255, "eval_micro_f1": 0.6932989685742608, "eval_runtime": 3.6315, "eval_samples_per_second": 277.849, "step": 1860 }, { "epoch": 69.44, "eval_loss": 0.24594207108020782, "eval_micro_f1": 0.6777408632926311, "eval_runtime": 3.3536, "eval_samples_per_second": 300.874, "step": 1875 }, { "epoch": 70.0, "eval_loss": 0.23652920126914978, "eval_micro_f1": 0.6860090259367169, "eval_runtime": 3.3497, "eval_samples_per_second": 301.221, "step": 1890 }, { "epoch": 70.56, "eval_loss": 0.2536377012729645, "eval_micro_f1": 0.6799468786552383, "eval_runtime": 3.2534, "eval_samples_per_second": 310.136, "step": 1905 }, { "epoch": 71.11, "eval_loss": 0.24122793972492218, "eval_micro_f1": 0.6873385007943098, "eval_runtime": 3.0762, "eval_samples_per_second": 328.0, "step": 1920 }, { "epoch": 71.67, "eval_loss": 0.2583581507205963, "eval_micro_f1": 0.6756939737799736, "eval_runtime": 3.2134, "eval_samples_per_second": 313.998, "step": 1935 }, { "epoch": 72.22, "eval_loss": 0.24001431465148926, "eval_micro_f1": 0.6754098355693339, "eval_runtime": 3.7877, "eval_samples_per_second": 266.391, "step": 1950 }, { "epoch": 72.78, "eval_loss": 0.2463134527206421, "eval_micro_f1": 0.6764119596381479, "eval_runtime": 3.1246, "eval_samples_per_second": 322.922, "step": 1965 }, { "epoch": 73.33, "eval_loss": 0.2513221800327301, "eval_micro_f1": 0.678191488867039, "eval_runtime": 3.2233, "eval_samples_per_second": 313.034, "step": 1980 }, { "epoch": 73.89, "eval_loss": 0.2567177414894104, "eval_micro_f1": 0.6794195245703611, "eval_runtime": 3.2807, "eval_samples_per_second": 307.554, "step": 1995 }, { "epoch": 74.07, "learning_rate": 7.530864197530865e-06, "loss": 0.001, "step": 2000 }, { "epoch": 74.44, "eval_loss": 0.2649242877960205, "eval_micro_f1": 0.6805090417031945, "eval_runtime": 3.1209, "eval_samples_per_second": 323.305, "step": 2010 }, { "epoch": 75.0, "eval_loss": 0.24954895675182343, "eval_micro_f1": 0.6744944548196039, "eval_runtime": 3.3073, "eval_samples_per_second": 305.087, "step": 2025 }, { "epoch": 75.56, "eval_loss": 0.2602313458919525, "eval_micro_f1": 0.6755319143989574, "eval_runtime": 3.1583, "eval_samples_per_second": 319.471, "step": 2040 }, { "epoch": 76.11, "eval_loss": 0.26400741934776306, "eval_micro_f1": 0.672934855114439, "eval_runtime": 3.6317, "eval_samples_per_second": 277.832, "step": 2055 }, { "epoch": 76.67, "eval_loss": 0.255902498960495, "eval_micro_f1": 0.6763925724493136, "eval_runtime": 3.0637, "eval_samples_per_second": 329.337, "step": 2070 }, { "epoch": 77.22, "eval_loss": 0.2723275423049927, "eval_micro_f1": 0.6784982930244144, "eval_runtime": 3.1909, "eval_samples_per_second": 316.214, "step": 2085 }, { "epoch": 77.78, "eval_loss": 0.26411429047584534, "eval_micro_f1": 0.6791694569744622, "eval_runtime": 3.2613, "eval_samples_per_second": 309.384, "step": 2100 }, { "epoch": 78.33, "eval_loss": 0.25438201427459717, "eval_micro_f1": 0.6814044208293073, "eval_runtime": 3.0051, "eval_samples_per_second": 335.765, "step": 2115 }, { "epoch": 78.89, "eval_loss": 0.25605905055999756, "eval_micro_f1": 0.6771860613054839, "eval_runtime": 3.3276, "eval_samples_per_second": 303.223, "step": 2130 }, { "epoch": 79.44, "eval_loss": 0.27040109038352966, "eval_micro_f1": 0.6756939737799736, "eval_runtime": 3.8992, "eval_samples_per_second": 258.772, "step": 2145 }, { "epoch": 80.0, "eval_loss": 0.2668462097644806, "eval_micro_f1": 0.6747149559115605, "eval_runtime": 3.2493, "eval_samples_per_second": 310.53, "step": 2160 }, { "epoch": 80.56, "eval_loss": 0.26718130707740784, "eval_micro_f1": 0.6755674227368187, "eval_runtime": 3.2827, "eval_samples_per_second": 307.368, "step": 2175 }, { "epoch": 81.11, "eval_loss": 0.254520058631897, "eval_micro_f1": 0.6788511744380151, "eval_runtime": 3.3701, "eval_samples_per_second": 299.398, "step": 2190 }, { "epoch": 81.67, "eval_loss": 0.2634600102901459, "eval_micro_f1": 0.6719999995056782, "eval_runtime": 3.3517, "eval_samples_per_second": 301.04, "step": 2205 }, { "epoch": 82.22, "eval_loss": 0.26370516419410706, "eval_micro_f1": 0.6702269687982411, "eval_runtime": 3.187, "eval_samples_per_second": 316.603, "step": 2220 }, { "epoch": 82.78, "eval_loss": 0.260775625705719, "eval_micro_f1": 0.6684491973669893, "eval_runtime": 3.3054, "eval_samples_per_second": 305.255, "step": 2235 }, { "epoch": 83.33, "eval_loss": 0.2722975015640259, "eval_micro_f1": 0.6729729724804784, "eval_runtime": 3.7005, "eval_samples_per_second": 272.664, "step": 2250 }, { "epoch": 83.89, "eval_loss": 0.277715265750885, "eval_micro_f1": 0.6738255028622603, "eval_runtime": 2.9392, "eval_samples_per_second": 343.296, "step": 2265 }, { "epoch": 84.44, "eval_loss": 0.26530721783638, "eval_micro_f1": 0.6746347936618855, "eval_runtime": 3.3465, "eval_samples_per_second": 301.512, "step": 2280 }, { "epoch": 85.0, "eval_loss": 0.25357839465141296, "eval_micro_f1": 0.680961662920653, "eval_runtime": 3.2444, "eval_samples_per_second": 310.994, "step": 2295 }, { "epoch": 85.56, "eval_loss": 0.2706127166748047, "eval_micro_f1": 0.6680161938393006, "eval_runtime": 3.3395, "eval_samples_per_second": 302.14, "step": 2310 }, { "epoch": 86.11, "eval_loss": 0.2748332619667053, "eval_micro_f1": 0.669830507982587, "eval_runtime": 3.4579, "eval_samples_per_second": 291.797, "step": 2325 }, { "epoch": 86.67, "eval_loss": 0.2617930471897125, "eval_micro_f1": 0.6728971957675298, "eval_runtime": 3.3379, "eval_samples_per_second": 302.289, "step": 2340 }, { "epoch": 87.22, "eval_loss": 0.2724812626838684, "eval_micro_f1": 0.6680161938393006, "eval_runtime": 3.2017, "eval_samples_per_second": 315.144, "step": 2355 }, { "epoch": 87.78, "eval_loss": 0.277841717004776, "eval_micro_f1": 0.6738690069348201, "eval_runtime": 2.9088, "eval_samples_per_second": 346.882, "step": 2370 }, { "epoch": 88.33, "eval_loss": 0.27283158898353577, "eval_micro_f1": 0.6747149559115605, "eval_runtime": 3.1975, "eval_samples_per_second": 315.562, "step": 2385 }, { "epoch": 88.89, "eval_loss": 0.2772813141345978, "eval_micro_f1": 0.6707152491699312, "eval_runtime": 3.4943, "eval_samples_per_second": 288.756, "step": 2400 }, { "epoch": 89.44, "eval_loss": 0.2589503228664398, "eval_micro_f1": 0.6801040307122739, "eval_runtime": 2.9536, "eval_samples_per_second": 341.62, "step": 2415 }, { "epoch": 90.0, "eval_loss": 0.2761433720588684, "eval_micro_f1": 0.6747311823024373, "eval_runtime": 3.2921, "eval_samples_per_second": 306.491, "step": 2430 }, { "epoch": 90.56, "eval_loss": 0.2721210718154907, "eval_micro_f1": 0.6751167440020899, "eval_runtime": 3.2268, "eval_samples_per_second": 312.697, "step": 2445 }, { "epoch": 91.11, "eval_loss": 0.25849735736846924, "eval_micro_f1": 0.6800778710147358, "eval_runtime": 3.2352, "eval_samples_per_second": 311.879, "step": 2460 }, { "epoch": 91.67, "eval_loss": 0.2677701711654663, "eval_micro_f1": 0.6684280047885783, "eval_runtime": 3.1682, "eval_samples_per_second": 318.477, "step": 2475 }, { "epoch": 92.22, "eval_loss": 0.2669242024421692, "eval_micro_f1": 0.6693121688168828, "eval_runtime": 3.256, "eval_samples_per_second": 309.892, "step": 2490 }, { "epoch": 92.59, "learning_rate": 6.913580246913581e-06, "loss": 0.0008, "step": 2500 }, { "epoch": 92.78, "eval_loss": 0.2702229619026184, "eval_micro_f1": 0.6688963205763478, "eval_runtime": 3.3742, "eval_samples_per_second": 299.032, "step": 2505 }, { "epoch": 93.33, "eval_loss": 0.27320611476898193, "eval_micro_f1": 0.6684599860569409, "eval_runtime": 3.2656, "eval_samples_per_second": 308.982, "step": 2520 }, { "epoch": 93.89, "eval_loss": 0.27507099509239197, "eval_micro_f1": 0.6689143622853713, "eval_runtime": 3.7216, "eval_samples_per_second": 271.119, "step": 2535 }, { "epoch": 94.44, "eval_loss": 0.28559377789497375, "eval_micro_f1": 0.6720430102594304, "eval_runtime": 3.2154, "eval_samples_per_second": 313.805, "step": 2550 }, { "epoch": 95.0, "eval_loss": 0.2634270191192627, "eval_micro_f1": 0.6801302926627057, "eval_runtime": 3.2567, "eval_samples_per_second": 309.824, "step": 2565 }, { "epoch": 95.56, "eval_loss": 0.266507089138031, "eval_micro_f1": 0.6763540285666392, "eval_runtime": 3.2866, "eval_samples_per_second": 307.001, "step": 2580 }, { "epoch": 96.11, "eval_loss": 0.2588798701763153, "eval_micro_f1": 0.6843467006667308, "eval_runtime": 3.3684, "eval_samples_per_second": 299.546, "step": 2595 }, { "epoch": 96.67, "eval_loss": 0.26734620332717896, "eval_micro_f1": 0.676781002142924, "eval_runtime": 3.0794, "eval_samples_per_second": 327.657, "step": 2610 }, { "epoch": 97.22, "eval_loss": 0.27607834339141846, "eval_micro_f1": 0.667115902472085, "eval_runtime": 3.2519, "eval_samples_per_second": 310.285, "step": 2625 }, { "epoch": 97.78, "eval_loss": 0.2546567916870117, "eval_micro_f1": 0.685567009811384, "eval_runtime": 3.3111, "eval_samples_per_second": 304.733, "step": 2640 }, { "epoch": 98.33, "eval_loss": 0.26265883445739746, "eval_micro_f1": 0.6823222434693, "eval_runtime": 3.2124, "eval_samples_per_second": 314.098, "step": 2655 }, { "epoch": 98.89, "eval_loss": 0.26411789655685425, "eval_micro_f1": 0.6789231774421738, "eval_runtime": 3.2986, "eval_samples_per_second": 305.889, "step": 2670 }, { "epoch": 99.44, "eval_loss": 0.2734825313091278, "eval_micro_f1": 0.6689008037959249, "eval_runtime": 3.5806, "eval_samples_per_second": 281.793, "step": 2685 }, { "epoch": 100.0, "eval_loss": 0.2630027234554291, "eval_micro_f1": 0.6749347253518583, "eval_runtime": 3.2697, "eval_samples_per_second": 308.589, "step": 2700 }, { "epoch": 100.56, "eval_loss": 0.2879752218723297, "eval_micro_f1": 0.6657552968435386, "eval_runtime": 3.8385, "eval_samples_per_second": 262.865, "step": 2715 }, { "epoch": 101.11, "eval_loss": 0.27415788173675537, "eval_micro_f1": 0.6697986572246817, "eval_runtime": 3.269, "eval_samples_per_second": 308.662, "step": 2730 }, { "epoch": 101.67, "eval_loss": 0.2747006118297577, "eval_micro_f1": 0.6697736346586424, "eval_runtime": 3.3815, "eval_samples_per_second": 298.39, "step": 2745 }, { "epoch": 102.22, "eval_loss": 0.2726960778236389, "eval_micro_f1": 0.6688741716902995, "eval_runtime": 3.0898, "eval_samples_per_second": 326.557, "step": 2760 }, { "epoch": 102.78, "eval_loss": 0.27309107780456543, "eval_micro_f1": 0.6728476816240692, "eval_runtime": 3.4485, "eval_samples_per_second": 292.588, "step": 2775 }, { "epoch": 103.33, "eval_loss": 0.273813933134079, "eval_micro_f1": 0.6733067724135472, "eval_runtime": 3.2965, "eval_samples_per_second": 306.085, "step": 2790 }, { "epoch": 103.89, "eval_loss": 0.2631343603134155, "eval_micro_f1": 0.6697612727145744, "eval_runtime": 3.0848, "eval_samples_per_second": 327.09, "step": 2805 }, { "epoch": 104.44, "eval_loss": 0.28801384568214417, "eval_micro_f1": 0.6551724133039201, "eval_runtime": 3.305, "eval_samples_per_second": 305.295, "step": 2820 }, { "epoch": 105.0, "eval_loss": 0.2717512547969818, "eval_micro_f1": 0.6716016145809538, "eval_runtime": 3.3677, "eval_samples_per_second": 299.612, "step": 2835 }, { "epoch": 105.56, "eval_loss": 0.2725674510002136, "eval_micro_f1": 0.6688963205763478, "eval_runtime": 3.2528, "eval_samples_per_second": 310.198, "step": 2850 }, { "epoch": 106.11, "eval_loss": 0.2687923312187195, "eval_micro_f1": 0.6750330246036289, "eval_runtime": 3.1928, "eval_samples_per_second": 316.028, "step": 2865 }, { "epoch": 106.67, "eval_loss": 0.2731798589229584, "eval_micro_f1": 0.6773977191577005, "eval_runtime": 3.3421, "eval_samples_per_second": 301.906, "step": 2880 }, { "epoch": 107.22, "eval_loss": 0.2674797475337982, "eval_micro_f1": 0.6786427140762769, "eval_runtime": 3.1177, "eval_samples_per_second": 323.639, "step": 2895 }, { "epoch": 107.78, "eval_loss": 0.274063378572464, "eval_micro_f1": 0.6801075263884517, "eval_runtime": 3.7997, "eval_samples_per_second": 265.547, "step": 2910 }, { "epoch": 108.33, "eval_loss": 0.2688889503479004, "eval_micro_f1": 0.6781229340717106, "eval_runtime": 3.3112, "eval_samples_per_second": 304.728, "step": 2925 }, { "epoch": 108.89, "eval_loss": 0.27587273716926575, "eval_micro_f1": 0.6720647768352465, "eval_runtime": 3.3441, "eval_samples_per_second": 301.73, "step": 2940 }, { "epoch": 109.44, "eval_loss": 0.27611032128334045, "eval_micro_f1": 0.6747802564379601, "eval_runtime": 3.0277, "eval_samples_per_second": 333.259, "step": 2955 }, { "epoch": 110.0, "eval_loss": 0.2734404504299164, "eval_micro_f1": 0.67871485894394, "eval_runtime": 3.4543, "eval_samples_per_second": 292.099, "step": 2970 }, { "epoch": 110.56, "eval_loss": 0.28242024779319763, "eval_micro_f1": 0.6707234613061197, "eval_runtime": 3.3568, "eval_samples_per_second": 300.58, "step": 2985 }, { "epoch": 111.11, "learning_rate": 6.296296296296297e-06, "loss": 0.0007, "step": 3000 }, { "epoch": 111.11, "eval_loss": 0.2871030569076538, "eval_micro_f1": 0.6716723544578709, "eval_runtime": 2.997, "eval_samples_per_second": 336.666, "step": 3000 }, { "epoch": 111.67, "eval_loss": 0.2515370845794678, "eval_micro_f1": 0.6846846841866864, "eval_runtime": 3.6588, "eval_samples_per_second": 275.775, "step": 3015 }, { "epoch": 112.22, "eval_loss": 0.27821993827819824, "eval_micro_f1": 0.6797829031716004, "eval_runtime": 3.3674, "eval_samples_per_second": 299.64, "step": 3030 }, { "epoch": 112.78, "eval_loss": 0.2683226466178894, "eval_micro_f1": 0.679495686300049, "eval_runtime": 3.1218, "eval_samples_per_second": 323.207, "step": 3045 }, { "epoch": 113.33, "eval_loss": 0.27346110343933105, "eval_micro_f1": 0.6747149559115605, "eval_runtime": 3.3226, "eval_samples_per_second": 303.682, "step": 3060 }, { "epoch": 113.89, "eval_loss": 0.27526649832725525, "eval_micro_f1": 0.6764705877413102, "eval_runtime": 3.2706, "eval_samples_per_second": 308.504, "step": 3075 }, { "epoch": 114.44, "eval_loss": 0.2687821686267853, "eval_micro_f1": 0.6819973713830667, "eval_runtime": 3.3332, "eval_samples_per_second": 302.709, "step": 3090 }, { "epoch": 115.0, "eval_loss": 0.2773393392562866, "eval_micro_f1": 0.6879574180017468, "eval_runtime": 3.6686, "eval_samples_per_second": 275.04, "step": 3105 }, { "epoch": 115.56, "eval_loss": 0.2769867181777954, "eval_micro_f1": 0.6874999995053245, "eval_runtime": 3.3965, "eval_samples_per_second": 297.067, "step": 3120 }, { "epoch": 116.11, "eval_loss": 0.27015331387519836, "eval_micro_f1": 0.6794448111371418, "eval_runtime": 3.4447, "eval_samples_per_second": 292.916, "step": 3135 }, { "epoch": 116.67, "eval_loss": 0.2707282304763794, "eval_micro_f1": 0.6803170404556697, "eval_runtime": 3.0808, "eval_samples_per_second": 327.513, "step": 3150 }, { "epoch": 117.22, "eval_loss": 0.27926602959632874, "eval_micro_f1": 0.6783783778858765, "eval_runtime": 3.268, "eval_samples_per_second": 308.752, "step": 3165 }, { "epoch": 117.78, "eval_loss": 0.2774791121482849, "eval_micro_f1": 0.6778975736311001, "eval_runtime": 3.2659, "eval_samples_per_second": 308.948, "step": 3180 }, { "epoch": 118.33, "eval_loss": 0.26499879360198975, "eval_micro_f1": 0.6815495727146588, "eval_runtime": 3.8707, "eval_samples_per_second": 260.679, "step": 3195 }, { "epoch": 118.89, "eval_loss": 0.2590312063694, "eval_micro_f1": 0.6750663125023657, "eval_runtime": 3.1552, "eval_samples_per_second": 319.785, "step": 3210 }, { "epoch": 119.44, "eval_loss": 0.27744701504707336, "eval_micro_f1": 0.6639400131421238, "eval_runtime": 3.1784, "eval_samples_per_second": 317.451, "step": 3225 }, { "epoch": 120.0, "eval_loss": 0.25695252418518066, "eval_micro_f1": 0.6772697145480112, "eval_runtime": 3.2156, "eval_samples_per_second": 313.779, "step": 3240 }, { "epoch": 120.56, "eval_loss": 0.25546836853027344, "eval_micro_f1": 0.67857142807613, "eval_runtime": 3.2866, "eval_samples_per_second": 307.007, "step": 3255 }, { "epoch": 121.11, "eval_loss": 0.2665998041629791, "eval_micro_f1": 0.6742934046213271, "eval_runtime": 3.3167, "eval_samples_per_second": 304.222, "step": 3270 }, { "epoch": 121.67, "eval_loss": 0.27430012822151184, "eval_micro_f1": 0.6689189184264299, "eval_runtime": 3.3408, "eval_samples_per_second": 302.021, "step": 3285 }, { "epoch": 122.22, "eval_loss": 0.26803842186927795, "eval_micro_f1": 0.6755319143989574, "eval_runtime": 2.9719, "eval_samples_per_second": 339.511, "step": 3300 }, { "epoch": 122.78, "eval_loss": 0.26295071840286255, "eval_micro_f1": 0.6816084372103199, "eval_runtime": 3.2046, "eval_samples_per_second": 314.856, "step": 3315 }, { "epoch": 123.33, "eval_loss": 0.2659909129142761, "eval_micro_f1": 0.679495686300049, "eval_runtime": 3.3393, "eval_samples_per_second": 302.159, "step": 3330 }, { "epoch": 123.89, "eval_loss": 0.27014198899269104, "eval_micro_f1": 0.6773333328390044, "eval_runtime": 2.9776, "eval_samples_per_second": 338.861, "step": 3345 }, { "epoch": 124.44, "eval_loss": 0.2772098779678345, "eval_micro_f1": 0.6756939737799736, "eval_runtime": 3.3167, "eval_samples_per_second": 304.22, "step": 3360 }, { "epoch": 125.0, "eval_loss": 0.2742120623588562, "eval_micro_f1": 0.6819098851826793, "eval_runtime": 3.2798, "eval_samples_per_second": 307.638, "step": 3375 }, { "epoch": 125.56, "eval_loss": 0.2720271348953247, "eval_micro_f1": 0.675099866349714, "eval_runtime": 3.4191, "eval_samples_per_second": 295.104, "step": 3390 }, { "epoch": 126.11, "eval_loss": 0.27625030279159546, "eval_micro_f1": 0.6777851896325067, "eval_runtime": 3.2757, "eval_samples_per_second": 308.024, "step": 3405 }, { "epoch": 126.67, "eval_loss": 0.281401664018631, "eval_micro_f1": 0.6769644051480131, "eval_runtime": 3.3766, "eval_samples_per_second": 298.826, "step": 3420 }, { "epoch": 127.22, "eval_loss": 0.2825535535812378, "eval_micro_f1": 0.6801075263884517, "eval_runtime": 3.4547, "eval_samples_per_second": 292.07, "step": 3435 }, { "epoch": 127.78, "eval_loss": 0.2795237600803375, "eval_micro_f1": 0.6831882111606591, "eval_runtime": 3.0353, "eval_samples_per_second": 332.426, "step": 3450 }, { "epoch": 128.33, "eval_loss": 0.2932030260562897, "eval_micro_f1": 0.6693877546105715, "eval_runtime": 3.2633, "eval_samples_per_second": 309.192, "step": 3465 }, { "epoch": 128.89, "eval_loss": 0.280192494392395, "eval_micro_f1": 0.6769436992382735, "eval_runtime": 3.3717, "eval_samples_per_second": 299.257, "step": 3480 }, { "epoch": 129.44, "eval_loss": 0.2666414976119995, "eval_micro_f1": 0.6718954243400298, "eval_runtime": 3.1007, "eval_samples_per_second": 325.415, "step": 3495 }, { "epoch": 129.63, "learning_rate": 5.6790123456790125e-06, "loss": 0.0007, "step": 3500 }, { "epoch": 130.0, "eval_loss": 0.2777402698993683, "eval_micro_f1": 0.6790945401180175, "eval_runtime": 3.4284, "eval_samples_per_second": 294.31, "step": 3510 }, { "epoch": 130.56, "eval_loss": 0.28603941202163696, "eval_micro_f1": 0.6796769847020735, "eval_runtime": 3.1932, "eval_samples_per_second": 315.988, "step": 3525 }, { "epoch": 131.11, "eval_loss": 0.2765958905220032, "eval_micro_f1": 0.6759259254306308, "eval_runtime": 3.2899, "eval_samples_per_second": 306.701, "step": 3540 }, { "epoch": 131.67, "eval_loss": 0.2686510384082794, "eval_micro_f1": 0.6762589923092442, "eval_runtime": 3.4301, "eval_samples_per_second": 294.16, "step": 3555 }, { "epoch": 132.22, "eval_loss": 0.27484676241874695, "eval_micro_f1": 0.6776750325296493, "eval_runtime": 3.2845, "eval_samples_per_second": 307.198, "step": 3570 }, { "epoch": 132.78, "eval_loss": 0.28453192114830017, "eval_micro_f1": 0.6734006729076951, "eval_runtime": 3.1269, "eval_samples_per_second": 322.68, "step": 3585 }, { "epoch": 133.33, "eval_loss": 0.27955520153045654, "eval_micro_f1": 0.6759628149102236, "eval_runtime": 3.0997, "eval_samples_per_second": 325.516, "step": 3600 }, { "epoch": 133.89, "eval_loss": 0.27887868881225586, "eval_micro_f1": 0.6768414062735097, "eval_runtime": 3.317, "eval_samples_per_second": 304.191, "step": 3615 }, { "epoch": 134.44, "eval_loss": 0.28850284218788147, "eval_micro_f1": 0.6783310896818869, "eval_runtime": 3.2487, "eval_samples_per_second": 310.588, "step": 3630 }, { "epoch": 135.0, "eval_loss": 0.29666292667388916, "eval_micro_f1": 0.6662125335686935, "eval_runtime": 3.0525, "eval_samples_per_second": 330.552, "step": 3645 }, { "epoch": 135.56, "eval_loss": 0.2978519797325134, "eval_micro_f1": 0.6702923176593418, "eval_runtime": 3.0947, "eval_samples_per_second": 326.045, "step": 3660 }, { "epoch": 136.11, "eval_loss": 0.28511765599250793, "eval_micro_f1": 0.6801075263884517, "eval_runtime": 3.6692, "eval_samples_per_second": 274.994, "step": 3675 }, { "epoch": 136.67, "eval_loss": 0.27218666672706604, "eval_micro_f1": 0.6906946259781146, "eval_runtime": 3.0085, "eval_samples_per_second": 335.383, "step": 3690 }, { "epoch": 137.22, "eval_loss": 0.27759185433387756, "eval_micro_f1": 0.6865473818773562, "eval_runtime": 3.3387, "eval_samples_per_second": 302.215, "step": 3705 }, { "epoch": 137.78, "eval_loss": 0.2860076427459717, "eval_micro_f1": 0.6784021660616218, "eval_runtime": 3.4011, "eval_samples_per_second": 296.67, "step": 3720 }, { "epoch": 138.33, "eval_loss": 0.2889839708805084, "eval_micro_f1": 0.6752368060029645, "eval_runtime": 3.306, "eval_samples_per_second": 305.198, "step": 3735 }, { "epoch": 138.89, "eval_loss": 0.29422426223754883, "eval_micro_f1": 0.6730245226695016, "eval_runtime": 5.9617, "eval_samples_per_second": 169.246, "step": 3750 }, { "epoch": 139.44, "eval_loss": 0.2894725799560547, "eval_micro_f1": 0.676075268323941, "eval_runtime": 3.2848, "eval_samples_per_second": 307.172, "step": 3765 }, { "epoch": 140.0, "eval_loss": 0.2853448688983917, "eval_micro_f1": 0.6799468786552383, "eval_runtime": 3.2961, "eval_samples_per_second": 306.115, "step": 3780 }, { "epoch": 140.56, "eval_loss": 0.28764671087265015, "eval_micro_f1": 0.6795727631907519, "eval_runtime": 3.1226, "eval_samples_per_second": 323.128, "step": 3795 }, { "epoch": 141.11, "eval_loss": 0.29320037364959717, "eval_micro_f1": 0.6814218640269104, "eval_runtime": 3.3683, "eval_samples_per_second": 299.561, "step": 3810 }, { "epoch": 141.67, "eval_loss": 0.2962234616279602, "eval_micro_f1": 0.6778975736311001, "eval_runtime": 3.3421, "eval_samples_per_second": 301.909, "step": 3825 }, { "epoch": 142.22, "eval_loss": 0.2861312925815582, "eval_micro_f1": 0.6829913959309803, "eval_runtime": 3.1894, "eval_samples_per_second": 316.358, "step": 3840 }, { "epoch": 142.78, "eval_loss": 0.28403353691101074, "eval_micro_f1": 0.6843150226682386, "eval_runtime": 3.145, "eval_samples_per_second": 320.825, "step": 3855 }, { "epoch": 143.33, "eval_loss": 0.2790556252002716, "eval_micro_f1": 0.6799204766421098, "eval_runtime": 3.2381, "eval_samples_per_second": 311.605, "step": 3870 }, { "epoch": 143.89, "eval_loss": 0.28053832054138184, "eval_micro_f1": 0.6808794132297661, "eval_runtime": 3.3961, "eval_samples_per_second": 297.107, "step": 3885 }, { "epoch": 144.44, "eval_loss": 0.28680509328842163, "eval_micro_f1": 0.6840696112866369, "eval_runtime": 3.2622, "eval_samples_per_second": 309.299, "step": 3900 }, { "epoch": 145.0, "eval_loss": 0.2873613238334656, "eval_micro_f1": 0.6814218640269104, "eval_runtime": 3.2975, "eval_samples_per_second": 305.986, "step": 3915 }, { "epoch": 145.56, "eval_loss": 0.27997052669525146, "eval_micro_f1": 0.6808228263133186, "eval_runtime": 3.2047, "eval_samples_per_second": 314.851, "step": 3930 }, { "epoch": 146.11, "eval_loss": 0.2757081389427185, "eval_micro_f1": 0.6846254922766243, "eval_runtime": 3.458, "eval_samples_per_second": 291.784, "step": 3945 }, { "epoch": 146.67, "eval_loss": 0.2803451716899872, "eval_micro_f1": 0.6856386494054971, "eval_runtime": 3.1839, "eval_samples_per_second": 316.911, "step": 3960 }, { "epoch": 147.22, "eval_loss": 0.2859652042388916, "eval_micro_f1": 0.684949832282012, "eval_runtime": 3.3946, "eval_samples_per_second": 297.235, "step": 3975 }, { "epoch": 147.78, "eval_loss": 0.28873342275619507, "eval_micro_f1": 0.684599865007827, "eval_runtime": 2.9929, "eval_samples_per_second": 337.131, "step": 3990 }, { "epoch": 148.15, "learning_rate": 5.061728395061729e-06, "loss": 0.0006, "step": 4000 }, { "epoch": 148.33, "eval_loss": 0.2890225052833557, "eval_micro_f1": 0.6863270772543467, "eval_runtime": 3.2653, "eval_samples_per_second": 309.003, "step": 4005 }, { "epoch": 148.89, "eval_loss": 0.28727051615715027, "eval_micro_f1": 0.6853333328389937, "eval_runtime": 3.1802, "eval_samples_per_second": 317.275, "step": 4020 }, { "epoch": 149.44, "eval_loss": 0.2768540382385254, "eval_micro_f1": 0.6841072591503066, "eval_runtime": 3.482, "eval_samples_per_second": 289.777, "step": 4035 }, { "epoch": 150.0, "eval_loss": 0.28233131766319275, "eval_micro_f1": 0.6827309232009627, "eval_runtime": 3.0948, "eval_samples_per_second": 326.03, "step": 4050 }, { "epoch": 150.56, "eval_loss": 0.2783200144767761, "eval_micro_f1": 0.6816677691937221, "eval_runtime": 3.6142, "eval_samples_per_second": 279.177, "step": 4065 }, { "epoch": 151.11, "eval_loss": 0.27945590019226074, "eval_micro_f1": 0.6865869848969294, "eval_runtime": 3.1951, "eval_samples_per_second": 315.801, "step": 4080 }, { "epoch": 151.67, "eval_loss": 0.2943606376647949, "eval_micro_f1": 0.6789366048258115, "eval_runtime": 2.9033, "eval_samples_per_second": 347.536, "step": 4095 }, { "epoch": 152.22, "eval_loss": 0.273691326379776, "eval_micro_f1": 0.6896095296172722, "eval_runtime": 3.1602, "eval_samples_per_second": 319.288, "step": 4110 }, { "epoch": 152.78, "eval_loss": 0.2735225558280945, "eval_micro_f1": 0.6899736142801098, "eval_runtime": 3.4434, "eval_samples_per_second": 293.026, "step": 4125 }, { "epoch": 153.33, "eval_loss": 0.2847544550895691, "eval_micro_f1": 0.6815114704924538, "eval_runtime": 3.054, "eval_samples_per_second": 330.389, "step": 4140 }, { "epoch": 153.89, "eval_loss": 0.2941019833087921, "eval_micro_f1": 0.6793737231301343, "eval_runtime": 3.2786, "eval_samples_per_second": 307.751, "step": 4155 }, { "epoch": 154.44, "eval_loss": 0.287584125995636, "eval_micro_f1": 0.682926828776184, "eval_runtime": 3.3757, "eval_samples_per_second": 298.9, "step": 4170 }, { "epoch": 155.0, "eval_loss": 0.3007400929927826, "eval_micro_f1": 0.6795048138156695, "eval_runtime": 3.0875, "eval_samples_per_second": 326.806, "step": 4185 }, { "epoch": 155.56, "eval_loss": 0.3044671416282654, "eval_micro_f1": 0.6818181813287211, "eval_runtime": 3.3596, "eval_samples_per_second": 300.337, "step": 4200 }, { "epoch": 156.11, "eval_loss": 0.2945421636104584, "eval_micro_f1": 0.6816021719454034, "eval_runtime": 3.23, "eval_samples_per_second": 312.388, "step": 4215 }, { "epoch": 156.67, "eval_loss": 0.27415814995765686, "eval_micro_f1": 0.6873760735297288, "eval_runtime": 3.1409, "eval_samples_per_second": 321.25, "step": 4230 }, { "epoch": 157.22, "eval_loss": 0.26975783705711365, "eval_micro_f1": 0.6911475404873461, "eval_runtime": 3.0325, "eval_samples_per_second": 332.731, "step": 4245 }, { "epoch": 157.78, "eval_loss": 0.2933550179004669, "eval_micro_f1": 0.6890080424017961, "eval_runtime": 3.728, "eval_samples_per_second": 270.654, "step": 4260 }, { "epoch": 158.33, "eval_loss": 0.282321959733963, "eval_micro_f1": 0.6878306873353769, "eval_runtime": 3.1989, "eval_samples_per_second": 315.424, "step": 4275 }, { "epoch": 158.89, "eval_loss": 0.2888675630092621, "eval_micro_f1": 0.6898395716985115, "eval_runtime": 3.1479, "eval_samples_per_second": 320.532, "step": 4290 }, { "epoch": 159.44, "eval_loss": 0.320819228887558, "eval_micro_f1": 0.6699096589979316, "eval_runtime": 3.2941, "eval_samples_per_second": 306.305, "step": 4305 }, { "epoch": 160.0, "eval_loss": 0.2891315519809723, "eval_micro_f1": 0.6816084372103199, "eval_runtime": 3.2507, "eval_samples_per_second": 310.392, "step": 4320 }, { "epoch": 160.56, "eval_loss": 0.286070317029953, "eval_micro_f1": 0.6856010563077101, "eval_runtime": 3.2847, "eval_samples_per_second": 307.179, "step": 4335 }, { "epoch": 161.11, "eval_loss": 0.29509714245796204, "eval_micro_f1": 0.6854082993723113, "eval_runtime": 3.3237, "eval_samples_per_second": 303.58, "step": 4350 }, { "epoch": 161.67, "eval_loss": 0.28768065571784973, "eval_micro_f1": 0.6825082503295511, "eval_runtime": 3.8306, "eval_samples_per_second": 263.404, "step": 4365 }, { "epoch": 162.22, "eval_loss": 0.28543537855148315, "eval_micro_f1": 0.6812748999035766, "eval_runtime": 3.219, "eval_samples_per_second": 313.449, "step": 4380 }, { "epoch": 162.78, "eval_loss": 0.2906276285648346, "eval_micro_f1": 0.6823687747424468, "eval_runtime": 3.1486, "eval_samples_per_second": 320.458, "step": 4395 }, { "epoch": 163.33, "eval_loss": 0.2783077359199524, "eval_micro_f1": 0.6819072496666421, "eval_runtime": 3.3548, "eval_samples_per_second": 300.767, "step": 4410 }, { "epoch": 163.89, "eval_loss": 0.29111939668655396, "eval_micro_f1": 0.6813040580549825, "eval_runtime": 3.3858, "eval_samples_per_second": 298.011, "step": 4425 }, { "epoch": 164.44, "eval_loss": 0.3081754446029663, "eval_micro_f1": 0.6716723544578709, "eval_runtime": 2.96, "eval_samples_per_second": 340.876, "step": 4440 }, { "epoch": 165.0, "eval_loss": 0.2761428952217102, "eval_micro_f1": 0.6883963489164475, "eval_runtime": 3.3298, "eval_samples_per_second": 303.017, "step": 4455 }, { "epoch": 165.56, "eval_loss": 0.282929390668869, "eval_micro_f1": 0.6804812829284707, "eval_runtime": 3.6399, "eval_samples_per_second": 277.203, "step": 4470 }, { "epoch": 166.11, "eval_loss": 0.295106440782547, "eval_micro_f1": 0.6693933192089193, "eval_runtime": 3.1438, "eval_samples_per_second": 320.952, "step": 4485 }, { "epoch": 166.67, "learning_rate": 4.444444444444444e-06, "loss": 0.0006, "step": 4500 }, { "epoch": 166.67, "eval_loss": 0.2782757580280304, "eval_micro_f1": 0.6816677691937221, "eval_runtime": 3.3159, "eval_samples_per_second": 304.295, "step": 4500 }, { "epoch": 167.22, "eval_loss": 0.28455284237861633, "eval_micro_f1": 0.6786907142687851, "eval_runtime": 3.2582, "eval_samples_per_second": 309.682, "step": 4515 }, { "epoch": 167.78, "eval_loss": 0.2949024736881256, "eval_micro_f1": 0.6766304342909195, "eval_runtime": 3.1862, "eval_samples_per_second": 316.676, "step": 4530 }, { "epoch": 168.33, "eval_loss": 0.2916998565196991, "eval_micro_f1": 0.676529925532384, "eval_runtime": 3.2297, "eval_samples_per_second": 312.415, "step": 4545 }, { "epoch": 168.89, "eval_loss": 0.2928021550178528, "eval_micro_f1": 0.6756756751831774, "eval_runtime": 3.749, "eval_samples_per_second": 269.139, "step": 4560 }, { "epoch": 169.44, "eval_loss": 0.283044695854187, "eval_micro_f1": 0.6853707409888831, "eval_runtime": 3.1394, "eval_samples_per_second": 321.4, "step": 4575 }, { "epoch": 170.0, "eval_loss": 0.2869914770126343, "eval_micro_f1": 0.6813922351152883, "eval_runtime": 2.9452, "eval_samples_per_second": 342.591, "step": 4590 }, { "epoch": 170.56, "eval_loss": 0.2976450026035309, "eval_micro_f1": 0.6761710789379428, "eval_runtime": 3.2828, "eval_samples_per_second": 307.357, "step": 4605 }, { "epoch": 171.11, "eval_loss": 0.2959316074848175, "eval_micro_f1": 0.6787878782948932, "eval_runtime": 3.3658, "eval_samples_per_second": 299.78, "step": 4620 }, { "epoch": 171.67, "eval_loss": 0.2901392877101898, "eval_micro_f1": 0.6818181813241907, "eval_runtime": 3.0826, "eval_samples_per_second": 327.32, "step": 4635 }, { "epoch": 172.22, "eval_loss": 0.30766862630844116, "eval_micro_f1": 0.6726395584355512, "eval_runtime": 3.2229, "eval_samples_per_second": 313.075, "step": 4650 }, { "epoch": 172.78, "eval_loss": 0.3069627285003662, "eval_micro_f1": 0.6698762030866594, "eval_runtime": 3.6746, "eval_samples_per_second": 274.587, "step": 4665 }, { "epoch": 173.33, "eval_loss": 0.2952832579612732, "eval_micro_f1": 0.6836803218706367, "eval_runtime": 3.0452, "eval_samples_per_second": 331.338, "step": 4680 }, { "epoch": 173.89, "eval_loss": 0.32065072655677795, "eval_micro_f1": 0.6662030593175984, "eval_runtime": 3.2966, "eval_samples_per_second": 306.069, "step": 4695 }, { "epoch": 174.44, "eval_loss": 0.3003557622432709, "eval_micro_f1": 0.6775510199166828, "eval_runtime": 3.2003, "eval_samples_per_second": 315.281, "step": 4710 }, { "epoch": 175.0, "eval_loss": 0.2909533679485321, "eval_micro_f1": 0.6796246643857229, "eval_runtime": 3.4002, "eval_samples_per_second": 296.746, "step": 4725 }, { "epoch": 175.56, "eval_loss": 0.2972177267074585, "eval_micro_f1": 0.683322079183288, "eval_runtime": 3.3296, "eval_samples_per_second": 303.036, "step": 4740 }, { "epoch": 176.11, "eval_loss": 0.28323253989219666, "eval_micro_f1": 0.6870026520248964, "eval_runtime": 3.4014, "eval_samples_per_second": 296.639, "step": 4755 }, { "epoch": 176.67, "eval_loss": 0.28320595622062683, "eval_micro_f1": 0.6865079360126273, "eval_runtime": 3.6536, "eval_samples_per_second": 276.169, "step": 4770 }, { "epoch": 177.22, "eval_loss": 0.29028043150901794, "eval_micro_f1": 0.6827309232009627, "eval_runtime": 3.062, "eval_samples_per_second": 329.519, "step": 4785 }, { "epoch": 177.78, "eval_loss": 0.2875451147556305, "eval_micro_f1": 0.6839999995056621, "eval_runtime": 3.3379, "eval_samples_per_second": 302.287, "step": 4800 }, { "epoch": 178.33, "eval_loss": 0.2926649749279022, "eval_micro_f1": 0.6836803218706367, "eval_runtime": 3.4196, "eval_samples_per_second": 295.064, "step": 4815 }, { "epoch": 178.89, "eval_loss": 0.3026709258556366, "eval_micro_f1": 0.6780821912904353, "eval_runtime": 3.2438, "eval_samples_per_second": 311.054, "step": 4830 }, { "epoch": 179.44, "eval_loss": 0.30206215381622314, "eval_micro_f1": 0.6806779656096911, "eval_runtime": 3.3673, "eval_samples_per_second": 299.643, "step": 4845 }, { "epoch": 180.0, "eval_loss": 0.29232800006866455, "eval_micro_f1": 0.6795727631907519, "eval_runtime": 3.2996, "eval_samples_per_second": 305.792, "step": 4860 }, { "epoch": 180.56, "eval_loss": 0.27291807532310486, "eval_micro_f1": 0.6952624834964678, "eval_runtime": 3.6525, "eval_samples_per_second": 276.247, "step": 4875 } ], "max_steps": 8100, "num_train_epochs": 300, "total_flos": 31288282920987120, "trial_name": null, "trial_params": null }