| { |
| "best_global_step": 2100, |
| "best_metric": 0.9776543362648145, |
| "best_model_checkpoint": "taskA-unixcoder-focal/checkpoint-2100", |
| "epoch": 0.2814144133121253, |
| "eval_steps": 100, |
| "global_step": 2300, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.001223540927444023, |
| "grad_norm": 0.1898110806941986, |
| "learning_rate": 3.6734693877551025e-07, |
| "loss": 0.4422, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.002447081854888046, |
| "grad_norm": 0.3350900411605835, |
| "learning_rate": 7.346938775510205e-07, |
| "loss": 0.4323, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.003670622782332069, |
| "grad_norm": 0.3723449110984802, |
| "learning_rate": 1.142857142857143e-06, |
| "loss": 0.4362, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.004894163709776092, |
| "grad_norm": 0.3299769461154938, |
| "learning_rate": 1.5510204081632654e-06, |
| "loss": 0.4191, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.006117704637220115, |
| "grad_norm": 0.26681044697761536, |
| "learning_rate": 1.9591836734693877e-06, |
| "loss": 0.4289, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.007341245564664138, |
| "grad_norm": 0.30233338475227356, |
| "learning_rate": 2.3673469387755103e-06, |
| "loss": 0.4083, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.008564786492108161, |
| "grad_norm": 0.31031334400177, |
| "learning_rate": 2.775510204081633e-06, |
| "loss": 0.404, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.009788327419552184, |
| "grad_norm": 0.2552475035190582, |
| "learning_rate": 3.183673469387755e-06, |
| "loss": 0.3889, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.011011868346996207, |
| "grad_norm": 0.3131052553653717, |
| "learning_rate": 3.5918367346938777e-06, |
| "loss": 0.3813, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.01223540927444023, |
| "grad_norm": 0.3377229571342468, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.3727, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.01223540927444023, |
| "eval_accuracy": 0.6961, |
| "eval_f1_weighted": 0.6955947095331424, |
| "eval_loss": 0.15026023983955383, |
| "eval_macro_f1": 0.6959280508399847, |
| "eval_precision": 0.7019396279846728, |
| "eval_recall": 0.6961, |
| "eval_runtime": 789.7648, |
| "eval_samples_per_second": 126.62, |
| "eval_steps_per_second": 0.99, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.013458950201884253, |
| "grad_norm": 0.3366774618625641, |
| "learning_rate": 4.408163265306123e-06, |
| "loss": 0.3671, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.014682491129328276, |
| "grad_norm": 0.33491575717926025, |
| "learning_rate": 4.816326530612245e-06, |
| "loss": 0.3498, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.0159060320567723, |
| "grad_norm": 0.4119006097316742, |
| "learning_rate": 5.2244897959183684e-06, |
| "loss": 0.3409, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.017129572984216322, |
| "grad_norm": 0.2964725196361542, |
| "learning_rate": 5.63265306122449e-06, |
| "loss": 0.3433, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.018353113911660345, |
| "grad_norm": 0.3075334429740906, |
| "learning_rate": 6.040816326530613e-06, |
| "loss": 0.3298, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.019576654839104368, |
| "grad_norm": 0.33718687295913696, |
| "learning_rate": 6.4489795918367345e-06, |
| "loss": 0.3297, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.02080019576654839, |
| "grad_norm": 0.2809618413448334, |
| "learning_rate": 6.857142857142858e-06, |
| "loss": 0.3275, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.022023736693992414, |
| "grad_norm": 0.37805014848709106, |
| "learning_rate": 7.2653061224489805e-06, |
| "loss": 0.3201, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.023247277621436437, |
| "grad_norm": 0.2940429151058197, |
| "learning_rate": 7.673469387755102e-06, |
| "loss": 0.3042, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.02447081854888046, |
| "grad_norm": 0.3286060690879822, |
| "learning_rate": 8.081632653061225e-06, |
| "loss": 0.3071, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.02447081854888046, |
| "eval_accuracy": 0.77807, |
| "eval_f1_weighted": 0.7781129395311969, |
| "eval_loss": 0.12153773754835129, |
| "eval_macro_f1": 0.7780651598452646, |
| "eval_precision": 0.7808306361972198, |
| "eval_recall": 0.77807, |
| "eval_runtime": 792.7157, |
| "eval_samples_per_second": 126.149, |
| "eval_steps_per_second": 0.986, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.025694359476324483, |
| "grad_norm": 0.33857154846191406, |
| "learning_rate": 8.489795918367347e-06, |
| "loss": 0.2964, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.026917900403768506, |
| "grad_norm": 0.2752092182636261, |
| "learning_rate": 8.89795918367347e-06, |
| "loss": 0.3, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.02814144133121253, |
| "grad_norm": 0.4952544569969177, |
| "learning_rate": 9.306122448979593e-06, |
| "loss": 0.294, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.029364982258656552, |
| "grad_norm": 0.37926042079925537, |
| "learning_rate": 9.714285714285715e-06, |
| "loss": 0.2964, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.030588523186100575, |
| "grad_norm": 0.3222455680370331, |
| "learning_rate": 1.0122448979591836e-05, |
| "loss": 0.283, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.0318120641135446, |
| "grad_norm": 0.2930658459663391, |
| "learning_rate": 1.053061224489796e-05, |
| "loss": 0.2793, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.03303560504098862, |
| "grad_norm": 0.4313414692878723, |
| "learning_rate": 1.0938775510204083e-05, |
| "loss": 0.2728, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.034259145968432644, |
| "grad_norm": 0.37351569533348083, |
| "learning_rate": 1.1346938775510206e-05, |
| "loss": 0.2752, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.035482686895876664, |
| "grad_norm": 0.22772285342216492, |
| "learning_rate": 1.1755102040816328e-05, |
| "loss": 0.274, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.03670622782332069, |
| "grad_norm": 0.15888753533363342, |
| "learning_rate": 1.2163265306122449e-05, |
| "loss": 0.264, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.03670622782332069, |
| "eval_accuracy": 0.82326, |
| "eval_f1_weighted": 0.8227034206790359, |
| "eval_loss": 0.10234300792217255, |
| "eval_macro_f1": 0.8230100448030374, |
| "eval_precision": 0.8338333810964687, |
| "eval_recall": 0.82326, |
| "eval_runtime": 789.0168, |
| "eval_samples_per_second": 126.74, |
| "eval_steps_per_second": 0.991, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.03792976875076471, |
| "grad_norm": 0.23560188710689545, |
| "learning_rate": 1.2571428571428572e-05, |
| "loss": 0.2753, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.039153309678208736, |
| "grad_norm": 0.18699614703655243, |
| "learning_rate": 1.2979591836734696e-05, |
| "loss": 0.2565, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.040376850605652756, |
| "grad_norm": 0.24035991728305817, |
| "learning_rate": 1.3387755102040818e-05, |
| "loss": 0.2716, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.04160039153309678, |
| "grad_norm": 0.15309660136699677, |
| "learning_rate": 1.3795918367346941e-05, |
| "loss": 0.2515, |
| "step": 340 |
| }, |
| { |
| "epoch": 0.0428239324605408, |
| "grad_norm": 0.3382055461406708, |
| "learning_rate": 1.4204081632653062e-05, |
| "loss": 0.2597, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.04404747338798483, |
| "grad_norm": 0.24439455568790436, |
| "learning_rate": 1.4612244897959185e-05, |
| "loss": 0.247, |
| "step": 360 |
| }, |
| { |
| "epoch": 0.04527101431542885, |
| "grad_norm": 0.26233720779418945, |
| "learning_rate": 1.5020408163265307e-05, |
| "loss": 0.2431, |
| "step": 370 |
| }, |
| { |
| "epoch": 0.046494555242872875, |
| "grad_norm": 0.20477451384067535, |
| "learning_rate": 1.5387755102040818e-05, |
| "loss": 0.2538, |
| "step": 380 |
| }, |
| { |
| "epoch": 0.047718096170316894, |
| "grad_norm": 0.2765439748764038, |
| "learning_rate": 1.5795918367346942e-05, |
| "loss": 0.2404, |
| "step": 390 |
| }, |
| { |
| "epoch": 0.04894163709776092, |
| "grad_norm": 0.13196279108524323, |
| "learning_rate": 1.6204081632653063e-05, |
| "loss": 0.2393, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.04894163709776092, |
| "eval_accuracy": 0.84563, |
| "eval_f1_weighted": 0.8448128964509274, |
| "eval_loss": 0.09028046578168869, |
| "eval_macro_f1": 0.8451923512067675, |
| "eval_precision": 0.861024732271907, |
| "eval_recall": 0.84563, |
| "eval_runtime": 787.6067, |
| "eval_samples_per_second": 126.967, |
| "eval_steps_per_second": 0.993, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.05016517802520494, |
| "grad_norm": 0.0924634337425232, |
| "learning_rate": 1.6612244897959184e-05, |
| "loss": 0.2331, |
| "step": 410 |
| }, |
| { |
| "epoch": 0.05138871895264897, |
| "grad_norm": 0.277784138917923, |
| "learning_rate": 1.7020408163265308e-05, |
| "loss": 0.2301, |
| "step": 420 |
| }, |
| { |
| "epoch": 0.052612259880092986, |
| "grad_norm": 0.32299959659576416, |
| "learning_rate": 1.742857142857143e-05, |
| "loss": 0.2218, |
| "step": 430 |
| }, |
| { |
| "epoch": 0.05383580080753701, |
| "grad_norm": 0.18170586228370667, |
| "learning_rate": 1.7836734693877553e-05, |
| "loss": 0.2318, |
| "step": 440 |
| }, |
| { |
| "epoch": 0.05505934173498103, |
| "grad_norm": 0.1520216166973114, |
| "learning_rate": 1.8244897959183674e-05, |
| "loss": 0.2136, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.05628288266242506, |
| "grad_norm": 0.23452645540237427, |
| "learning_rate": 1.8653061224489795e-05, |
| "loss": 0.2219, |
| "step": 460 |
| }, |
| { |
| "epoch": 0.05750642358986908, |
| "grad_norm": 0.10036301612854004, |
| "learning_rate": 1.906122448979592e-05, |
| "loss": 0.2213, |
| "step": 470 |
| }, |
| { |
| "epoch": 0.058729964517313105, |
| "grad_norm": 0.24100220203399658, |
| "learning_rate": 1.9469387755102044e-05, |
| "loss": 0.2079, |
| "step": 480 |
| }, |
| { |
| "epoch": 0.059953505444757124, |
| "grad_norm": 0.28893032670021057, |
| "learning_rate": 1.9877551020408165e-05, |
| "loss": 0.1978, |
| "step": 490 |
| }, |
| { |
| "epoch": 0.06117704637220115, |
| "grad_norm": 0.22918537259101868, |
| "learning_rate": 1.9999836143766126e-05, |
| "loss": 0.202, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.06117704637220115, |
| "eval_accuracy": 0.91628, |
| "eval_f1_weighted": 0.9163231793856368, |
| "eval_loss": 0.055908624082803726, |
| "eval_macro_f1": 0.9162187423616152, |
| "eval_precision": 0.9170320825159874, |
| "eval_recall": 0.91628, |
| "eval_runtime": 760.1138, |
| "eval_samples_per_second": 131.559, |
| "eval_steps_per_second": 1.029, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.06240058729964517, |
| "grad_norm": 0.2930404841899872, |
| "learning_rate": 1.999903359554741e-05, |
| "loss": 0.1979, |
| "step": 510 |
| }, |
| { |
| "epoch": 0.0636241282270892, |
| "grad_norm": 0.0889664739370346, |
| "learning_rate": 1.9997562312908153e-05, |
| "loss": 0.1953, |
| "step": 520 |
| }, |
| { |
| "epoch": 0.06484766915453322, |
| "grad_norm": 0.1687588095664978, |
| "learning_rate": 1.9995422394247598e-05, |
| "loss": 0.1935, |
| "step": 530 |
| }, |
| { |
| "epoch": 0.06607121008197724, |
| "grad_norm": 0.2399725466966629, |
| "learning_rate": 1.9992613982683296e-05, |
| "loss": 0.1818, |
| "step": 540 |
| }, |
| { |
| "epoch": 0.06729475100942127, |
| "grad_norm": 0.2016785889863968, |
| "learning_rate": 1.9989137266041552e-05, |
| "loss": 0.1893, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.06851829193686529, |
| "grad_norm": 0.17420713603496552, |
| "learning_rate": 1.9984992476844845e-05, |
| "loss": 0.1895, |
| "step": 560 |
| }, |
| { |
| "epoch": 0.06974183286430931, |
| "grad_norm": 0.2180609554052353, |
| "learning_rate": 1.998017989229629e-05, |
| "loss": 0.1836, |
| "step": 570 |
| }, |
| { |
| "epoch": 0.07096537379175333, |
| "grad_norm": 0.15563039481639862, |
| "learning_rate": 1.9974699834261074e-05, |
| "loss": 0.182, |
| "step": 580 |
| }, |
| { |
| "epoch": 0.07218891471919736, |
| "grad_norm": 0.25410088896751404, |
| "learning_rate": 1.996855266924497e-05, |
| "loss": 0.1862, |
| "step": 590 |
| }, |
| { |
| "epoch": 0.07341245564664138, |
| "grad_norm": 0.24206259846687317, |
| "learning_rate": 1.996173880836979e-05, |
| "loss": 0.1818, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.07341245564664138, |
| "eval_accuracy": 0.91633, |
| "eval_f1_weighted": 0.9162437523349878, |
| "eval_loss": 0.05625538155436516, |
| "eval_macro_f1": 0.9163072974421806, |
| "eval_precision": 0.9233764457540103, |
| "eval_recall": 0.91633, |
| "eval_runtime": 759.6815, |
| "eval_samples_per_second": 131.634, |
| "eval_steps_per_second": 1.029, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.0746359965740854, |
| "grad_norm": 0.27251410484313965, |
| "learning_rate": 1.9954258707345903e-05, |
| "loss": 0.1845, |
| "step": 610 |
| }, |
| { |
| "epoch": 0.07585953750152942, |
| "grad_norm": 0.1545839011669159, |
| "learning_rate": 1.9946112866441757e-05, |
| "loss": 0.1861, |
| "step": 620 |
| }, |
| { |
| "epoch": 0.07708307842897345, |
| "grad_norm": 0.2535873055458069, |
| "learning_rate": 1.9937301830450423e-05, |
| "loss": 0.1772, |
| "step": 630 |
| }, |
| { |
| "epoch": 0.07830661935641747, |
| "grad_norm": 0.2617948651313782, |
| "learning_rate": 1.992782618865315e-05, |
| "loss": 0.1711, |
| "step": 640 |
| }, |
| { |
| "epoch": 0.07953016028386149, |
| "grad_norm": 0.38676971197128296, |
| "learning_rate": 1.9917686574779972e-05, |
| "loss": 0.1748, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.08075370121130551, |
| "grad_norm": 0.1511957049369812, |
| "learning_rate": 1.9906883666967296e-05, |
| "loss": 0.1825, |
| "step": 660 |
| }, |
| { |
| "epoch": 0.08197724213874955, |
| "grad_norm": 0.2525976002216339, |
| "learning_rate": 1.989541818771258e-05, |
| "loss": 0.1651, |
| "step": 670 |
| }, |
| { |
| "epoch": 0.08320078306619356, |
| "grad_norm": 0.25827622413635254, |
| "learning_rate": 1.9883290903825994e-05, |
| "loss": 0.1763, |
| "step": 680 |
| }, |
| { |
| "epoch": 0.08442432399363758, |
| "grad_norm": 0.24877820909023285, |
| "learning_rate": 1.9870502626379127e-05, |
| "loss": 0.1652, |
| "step": 690 |
| }, |
| { |
| "epoch": 0.0856478649210816, |
| "grad_norm": 0.278772234916687, |
| "learning_rate": 1.9857054210650776e-05, |
| "loss": 0.1651, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.0856478649210816, |
| "eval_accuracy": 0.94905, |
| "eval_f1_weighted": 0.9490731118481598, |
| "eval_loss": 0.03884471580386162, |
| "eval_macro_f1": 0.9489981325237288, |
| "eval_precision": 0.9494795831024372, |
| "eval_recall": 0.94905, |
| "eval_runtime": 759.9337, |
| "eval_samples_per_second": 131.59, |
| "eval_steps_per_second": 1.029, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.08687140584852564, |
| "grad_norm": 0.1895805150270462, |
| "learning_rate": 1.9842946556069705e-05, |
| "loss": 0.1628, |
| "step": 710 |
| }, |
| { |
| "epoch": 0.08809494677596966, |
| "grad_norm": 0.1171497106552124, |
| "learning_rate": 1.982818060615452e-05, |
| "loss": 0.1715, |
| "step": 720 |
| }, |
| { |
| "epoch": 0.08931848770341368, |
| "grad_norm": 0.22032728791236877, |
| "learning_rate": 1.9812757348450547e-05, |
| "loss": 0.1712, |
| "step": 730 |
| }, |
| { |
| "epoch": 0.0905420286308577, |
| "grad_norm": 0.20700488984584808, |
| "learning_rate": 1.9796677814463812e-05, |
| "loss": 0.1638, |
| "step": 740 |
| }, |
| { |
| "epoch": 0.09176556955830173, |
| "grad_norm": 0.24688613414764404, |
| "learning_rate": 1.977994307959202e-05, |
| "loss": 0.1647, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.09298911048574575, |
| "grad_norm": 0.1886432021856308, |
| "learning_rate": 1.9762554263052655e-05, |
| "loss": 0.1734, |
| "step": 760 |
| }, |
| { |
| "epoch": 0.09421265141318977, |
| "grad_norm": 0.08407370001077652, |
| "learning_rate": 1.9744512527808127e-05, |
| "loss": 0.1755, |
| "step": 770 |
| }, |
| { |
| "epoch": 0.09543619234063379, |
| "grad_norm": 0.14160771667957306, |
| "learning_rate": 1.9725819080487976e-05, |
| "loss": 0.1749, |
| "step": 780 |
| }, |
| { |
| "epoch": 0.09665973326807782, |
| "grad_norm": 0.17038081586360931, |
| "learning_rate": 1.970647517130819e-05, |
| "loss": 0.1795, |
| "step": 790 |
| }, |
| { |
| "epoch": 0.09788327419552184, |
| "grad_norm": 0.24339532852172852, |
| "learning_rate": 1.968648209398759e-05, |
| "loss": 0.161, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.09788327419552184, |
| "eval_accuracy": 0.95721, |
| "eval_f1_weighted": 0.9572295598206603, |
| "eval_loss": 0.03337462991476059, |
| "eval_macro_f1": 0.9571669846830866, |
| "eval_precision": 0.9576467364395861, |
| "eval_recall": 0.95721, |
| "eval_runtime": 759.9975, |
| "eval_samples_per_second": 131.579, |
| "eval_steps_per_second": 1.029, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.09910681512296586, |
| "grad_norm": 0.16346058249473572, |
| "learning_rate": 1.9665841185661283e-05, |
| "loss": 0.1596, |
| "step": 810 |
| }, |
| { |
| "epoch": 0.10033035605040988, |
| "grad_norm": 0.25031423568725586, |
| "learning_rate": 1.964455382679128e-05, |
| "loss": 0.1662, |
| "step": 820 |
| }, |
| { |
| "epoch": 0.10155389697785391, |
| "grad_norm": 0.36678382754325867, |
| "learning_rate": 1.9622621441074113e-05, |
| "loss": 0.1552, |
| "step": 830 |
| }, |
| { |
| "epoch": 0.10277743790529793, |
| "grad_norm": 0.34810611605644226, |
| "learning_rate": 1.960004549534567e-05, |
| "loss": 0.1663, |
| "step": 840 |
| }, |
| { |
| "epoch": 0.10400097883274195, |
| "grad_norm": 0.15511688590049744, |
| "learning_rate": 1.957682749948307e-05, |
| "loss": 0.1571, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.10522451976018597, |
| "grad_norm": 0.2082190364599228, |
| "learning_rate": 1.9552969006303666e-05, |
| "loss": 0.1497, |
| "step": 860 |
| }, |
| { |
| "epoch": 0.10644806068763, |
| "grad_norm": 0.14936988055706024, |
| "learning_rate": 1.9528471611461235e-05, |
| "loss": 0.1435, |
| "step": 870 |
| }, |
| { |
| "epoch": 0.10767160161507403, |
| "grad_norm": 0.252530574798584, |
| "learning_rate": 1.9503336953339223e-05, |
| "loss": 0.1536, |
| "step": 880 |
| }, |
| { |
| "epoch": 0.10889514254251804, |
| "grad_norm": 0.07253506034612656, |
| "learning_rate": 1.947756671294118e-05, |
| "loss": 0.1605, |
| "step": 890 |
| }, |
| { |
| "epoch": 0.11011868346996206, |
| "grad_norm": 0.09060605615377426, |
| "learning_rate": 1.9451162613778353e-05, |
| "loss": 0.1581, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.11011868346996206, |
| "eval_accuracy": 0.95459, |
| "eval_f1_weighted": 0.9546135918699761, |
| "eval_loss": 0.03526490181684494, |
| "eval_macro_f1": 0.9545725664001194, |
| "eval_precision": 0.9559789658562307, |
| "eval_recall": 0.95459, |
| "eval_runtime": 759.7202, |
| "eval_samples_per_second": 131.627, |
| "eval_steps_per_second": 1.029, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.1113422243974061, |
| "grad_norm": 0.21080073714256287, |
| "learning_rate": 1.942412642175439e-05, |
| "loss": 0.164, |
| "step": 910 |
| }, |
| { |
| "epoch": 0.11256576532485012, |
| "grad_norm": 0.22832269966602325, |
| "learning_rate": 1.939645994504726e-05, |
| "loss": 0.1595, |
| "step": 920 |
| }, |
| { |
| "epoch": 0.11378930625229414, |
| "grad_norm": 0.19044892489910126, |
| "learning_rate": 1.93681650339883e-05, |
| "loss": 0.1648, |
| "step": 930 |
| }, |
| { |
| "epoch": 0.11501284717973816, |
| "grad_norm": 0.2413518726825714, |
| "learning_rate": 1.9339243580938493e-05, |
| "loss": 0.155, |
| "step": 940 |
| }, |
| { |
| "epoch": 0.11623638810718219, |
| "grad_norm": 0.13218896090984344, |
| "learning_rate": 1.930969752016187e-05, |
| "loss": 0.1499, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.11745992903462621, |
| "grad_norm": 0.23770441114902496, |
| "learning_rate": 1.927952882769619e-05, |
| "loss": 0.1555, |
| "step": 960 |
| }, |
| { |
| "epoch": 0.11868346996207023, |
| "grad_norm": 0.2193710207939148, |
| "learning_rate": 1.924873952122074e-05, |
| "loss": 0.1505, |
| "step": 970 |
| }, |
| { |
| "epoch": 0.11990701088951425, |
| "grad_norm": 0.1577174812555313, |
| "learning_rate": 1.9217331659921432e-05, |
| "loss": 0.1551, |
| "step": 980 |
| }, |
| { |
| "epoch": 0.12113055181695828, |
| "grad_norm": 0.1814967393875122, |
| "learning_rate": 1.9185307344353052e-05, |
| "loss": 0.1607, |
| "step": 990 |
| }, |
| { |
| "epoch": 0.1223540927444023, |
| "grad_norm": 0.27239707112312317, |
| "learning_rate": 1.91526687162988e-05, |
| "loss": 0.1506, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.1223540927444023, |
| "eval_accuracy": 0.96454, |
| "eval_f1_weighted": 0.9645510150201642, |
| "eval_loss": 0.028770776465535164, |
| "eval_macro_f1": 0.9644889377060355, |
| "eval_precision": 0.9646912114769961, |
| "eval_recall": 0.96454, |
| "eval_runtime": 759.5962, |
| "eval_samples_per_second": 131.649, |
| "eval_steps_per_second": 1.029, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.12357763367184632, |
| "grad_norm": 0.20511822402477264, |
| "learning_rate": 1.9119417958627022e-05, |
| "loss": 0.1503, |
| "step": 1010 |
| }, |
| { |
| "epoch": 0.12480117459929034, |
| "grad_norm": 0.2324151247739792, |
| "learning_rate": 1.9085557295145254e-05, |
| "loss": 0.1581, |
| "step": 1020 |
| }, |
| { |
| "epoch": 0.12602471552673436, |
| "grad_norm": 0.11019974201917648, |
| "learning_rate": 1.905108899045146e-05, |
| "loss": 0.1556, |
| "step": 1030 |
| }, |
| { |
| "epoch": 0.1272482564541784, |
| "grad_norm": 0.13370558619499207, |
| "learning_rate": 1.9016015349782594e-05, |
| "loss": 0.1469, |
| "step": 1040 |
| }, |
| { |
| "epoch": 0.12847179738162243, |
| "grad_norm": 0.11238931119441986, |
| "learning_rate": 1.8980338718860426e-05, |
| "loss": 0.155, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.12969533830906643, |
| "grad_norm": 0.2959650158882141, |
| "learning_rate": 1.894406148373466e-05, |
| "loss": 0.1478, |
| "step": 1060 |
| }, |
| { |
| "epoch": 0.13091887923651047, |
| "grad_norm": 0.14401015639305115, |
| "learning_rate": 1.890718607062334e-05, |
| "loss": 0.1558, |
| "step": 1070 |
| }, |
| { |
| "epoch": 0.13214242016395447, |
| "grad_norm": 0.2187667042016983, |
| "learning_rate": 1.8869714945750614e-05, |
| "loss": 0.1618, |
| "step": 1080 |
| }, |
| { |
| "epoch": 0.1333659610913985, |
| "grad_norm": 0.17045481503009796, |
| "learning_rate": 1.883165061518176e-05, |
| "loss": 0.1487, |
| "step": 1090 |
| }, |
| { |
| "epoch": 0.13458950201884254, |
| "grad_norm": 0.09508351981639862, |
| "learning_rate": 1.8792995624655605e-05, |
| "loss": 0.1461, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.13458950201884254, |
| "eval_accuracy": 0.95198, |
| "eval_f1_weighted": 0.9520023284947491, |
| "eval_loss": 0.04088817164301872, |
| "eval_macro_f1": 0.9519693367124435, |
| "eval_precision": 0.9538785423213092, |
| "eval_recall": 0.95198, |
| "eval_runtime": 759.8551, |
| "eval_samples_per_second": 131.604, |
| "eval_steps_per_second": 1.029, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.13581304294628654, |
| "grad_norm": 0.1880544275045395, |
| "learning_rate": 1.875375255941426e-05, |
| "loss": 0.1442, |
| "step": 1110 |
| }, |
| { |
| "epoch": 0.13703658387373058, |
| "grad_norm": 0.1614997684955597, |
| "learning_rate": 1.8713924044030212e-05, |
| "loss": 0.1622, |
| "step": 1120 |
| }, |
| { |
| "epoch": 0.1382601248011746, |
| "grad_norm": 0.10545000433921814, |
| "learning_rate": 1.86735127422308e-05, |
| "loss": 0.1531, |
| "step": 1130 |
| }, |
| { |
| "epoch": 0.13948366572861862, |
| "grad_norm": 0.2203921526670456, |
| "learning_rate": 1.8632521356720064e-05, |
| "loss": 0.1471, |
| "step": 1140 |
| }, |
| { |
| "epoch": 0.14070720665606265, |
| "grad_norm": 0.16150350868701935, |
| "learning_rate": 1.8590952628997994e-05, |
| "loss": 0.1436, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.14193074758350666, |
| "grad_norm": 0.1466459184885025, |
| "learning_rate": 1.8548809339177155e-05, |
| "loss": 0.1486, |
| "step": 1160 |
| }, |
| { |
| "epoch": 0.1431542885109507, |
| "grad_norm": 0.1858566850423813, |
| "learning_rate": 1.8506094305796786e-05, |
| "loss": 0.1485, |
| "step": 1170 |
| }, |
| { |
| "epoch": 0.14437782943839472, |
| "grad_norm": 0.21629975736141205, |
| "learning_rate": 1.846281038563428e-05, |
| "loss": 0.1558, |
| "step": 1180 |
| }, |
| { |
| "epoch": 0.14560137036583873, |
| "grad_norm": 0.12939126789569855, |
| "learning_rate": 1.841896047351412e-05, |
| "loss": 0.1388, |
| "step": 1190 |
| }, |
| { |
| "epoch": 0.14682491129328276, |
| "grad_norm": 0.12447889149188995, |
| "learning_rate": 1.8374547502114277e-05, |
| "loss": 0.1683, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.14682491129328276, |
| "eval_accuracy": 0.96627, |
| "eval_f1_weighted": 0.9662808443914441, |
| "eval_loss": 0.027206970378756523, |
| "eval_macro_f1": 0.9662223734621376, |
| "eval_precision": 0.966433068847901, |
| "eval_recall": 0.96627, |
| "eval_runtime": 661.8465, |
| "eval_samples_per_second": 151.092, |
| "eval_steps_per_second": 1.182, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.1480484522207268, |
| "grad_norm": 0.07575482875108719, |
| "learning_rate": 1.832957444177007e-05, |
| "loss": 0.152, |
| "step": 1210 |
| }, |
| { |
| "epoch": 0.1492719931481708, |
| "grad_norm": 0.22879591584205627, |
| "learning_rate": 1.828404430027553e-05, |
| "loss": 0.15, |
| "step": 1220 |
| }, |
| { |
| "epoch": 0.15049553407561483, |
| "grad_norm": 0.25837475061416626, |
| "learning_rate": 1.8237960122682207e-05, |
| "loss": 0.1557, |
| "step": 1230 |
| }, |
| { |
| "epoch": 0.15171907500305884, |
| "grad_norm": 0.1440538763999939, |
| "learning_rate": 1.8191324991095527e-05, |
| "loss": 0.154, |
| "step": 1240 |
| }, |
| { |
| "epoch": 0.15294261593050287, |
| "grad_norm": 0.21304763853549957, |
| "learning_rate": 1.814414202446869e-05, |
| "loss": 0.1428, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.1541661568579469, |
| "grad_norm": 0.2292693555355072, |
| "learning_rate": 1.809641437839403e-05, |
| "loss": 0.1441, |
| "step": 1260 |
| }, |
| { |
| "epoch": 0.1553896977853909, |
| "grad_norm": 0.0891769602894783, |
| "learning_rate": 1.8048145244892e-05, |
| "loss": 0.1563, |
| "step": 1270 |
| }, |
| { |
| "epoch": 0.15661323871283495, |
| "grad_norm": 0.13292840123176575, |
| "learning_rate": 1.799933785219769e-05, |
| "loss": 0.1418, |
| "step": 1280 |
| }, |
| { |
| "epoch": 0.15783677964027898, |
| "grad_norm": 0.30031099915504456, |
| "learning_rate": 1.7949995464544892e-05, |
| "loss": 0.1543, |
| "step": 1290 |
| }, |
| { |
| "epoch": 0.15906032056772298, |
| "grad_norm": 0.08812980353832245, |
| "learning_rate": 1.790012138194783e-05, |
| "loss": 0.1473, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.15906032056772298, |
| "eval_accuracy": 0.96636, |
| "eval_f1_weighted": 0.9663763998373325, |
| "eval_loss": 0.02714269980788231, |
| "eval_macro_f1": 0.9663303002945869, |
| "eval_precision": 0.9669126928794434, |
| "eval_recall": 0.96636, |
| "eval_runtime": 661.9303, |
| "eval_samples_per_second": 151.073, |
| "eval_steps_per_second": 1.181, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.16028386149516702, |
| "grad_norm": 0.1380453258752823, |
| "learning_rate": 1.7849718939980426e-05, |
| "loss": 0.1594, |
| "step": 1310 |
| }, |
| { |
| "epoch": 0.16150740242261102, |
| "grad_norm": 0.08388533443212509, |
| "learning_rate": 1.7798791509553224e-05, |
| "loss": 0.1411, |
| "step": 1320 |
| }, |
| { |
| "epoch": 0.16273094335005506, |
| "grad_norm": 0.2659275531768799, |
| "learning_rate": 1.7747342496687957e-05, |
| "loss": 0.1495, |
| "step": 1330 |
| }, |
| { |
| "epoch": 0.1639544842774991, |
| "grad_norm": 0.275398313999176, |
| "learning_rate": 1.7695375342289732e-05, |
| "loss": 0.134, |
| "step": 1340 |
| }, |
| { |
| "epoch": 0.1651780252049431, |
| "grad_norm": 0.15272289514541626, |
| "learning_rate": 1.7642893521916926e-05, |
| "loss": 0.1427, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.16640156613238713, |
| "grad_norm": 0.21478359401226044, |
| "learning_rate": 1.7589900545548706e-05, |
| "loss": 0.1465, |
| "step": 1360 |
| }, |
| { |
| "epoch": 0.16762510705983116, |
| "grad_norm": 0.2184278517961502, |
| "learning_rate": 1.7536399957350326e-05, |
| "loss": 0.1452, |
| "step": 1370 |
| }, |
| { |
| "epoch": 0.16884864798727517, |
| "grad_norm": 0.23272652924060822, |
| "learning_rate": 1.7482395335436052e-05, |
| "loss": 0.142, |
| "step": 1380 |
| }, |
| { |
| "epoch": 0.1700721889147192, |
| "grad_norm": 0.14892522990703583, |
| "learning_rate": 1.7427890291629895e-05, |
| "loss": 0.1465, |
| "step": 1390 |
| }, |
| { |
| "epoch": 0.1712957298421632, |
| "grad_norm": 0.2066282033920288, |
| "learning_rate": 1.737288847122402e-05, |
| "loss": 0.1444, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.1712957298421632, |
| "eval_accuracy": 0.95302, |
| "eval_f1_weighted": 0.9530351521706546, |
| "eval_loss": 0.03864819556474686, |
| "eval_macro_f1": 0.9530165251021966, |
| "eval_precision": 0.9557329367218795, |
| "eval_recall": 0.95302, |
| "eval_runtime": 661.7384, |
| "eval_samples_per_second": 151.117, |
| "eval_steps_per_second": 1.182, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.17251927076960724, |
| "grad_norm": 0.2941270172595978, |
| "learning_rate": 1.7317393552734977e-05, |
| "loss": 0.136, |
| "step": 1410 |
| }, |
| { |
| "epoch": 0.17374281169705127, |
| "grad_norm": 0.11988822370767593, |
| "learning_rate": 1.7261409247657656e-05, |
| "loss": 0.1551, |
| "step": 1420 |
| }, |
| { |
| "epoch": 0.17496635262449528, |
| "grad_norm": 0.346236914396286, |
| "learning_rate": 1.7204939300217084e-05, |
| "loss": 0.1453, |
| "step": 1430 |
| }, |
| { |
| "epoch": 0.17618989355193931, |
| "grad_norm": 0.15973429381847382, |
| "learning_rate": 1.7147987487118006e-05, |
| "loss": 0.1341, |
| "step": 1440 |
| }, |
| { |
| "epoch": 0.17741343447938335, |
| "grad_norm": 0.2531983554363251, |
| "learning_rate": 1.7090557617292287e-05, |
| "loss": 0.1479, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.17863697540682735, |
| "grad_norm": 0.10105066746473312, |
| "learning_rate": 1.703265353164419e-05, |
| "loss": 0.1459, |
| "step": 1460 |
| }, |
| { |
| "epoch": 0.1798605163342714, |
| "grad_norm": 0.10651528090238571, |
| "learning_rate": 1.6974279102793473e-05, |
| "loss": 0.152, |
| "step": 1470 |
| }, |
| { |
| "epoch": 0.1810840572617154, |
| "grad_norm": 0.2675159275531769, |
| "learning_rate": 1.6915438234816423e-05, |
| "loss": 0.1467, |
| "step": 1480 |
| }, |
| { |
| "epoch": 0.18230759818915943, |
| "grad_norm": 0.09507659822702408, |
| "learning_rate": 1.6856134862984718e-05, |
| "loss": 0.1504, |
| "step": 1490 |
| }, |
| { |
| "epoch": 0.18353113911660346, |
| "grad_norm": 0.13831426203250885, |
| "learning_rate": 1.6796372953502252e-05, |
| "loss": 0.151, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.18353113911660346, |
| "eval_accuracy": 0.96716, |
| "eval_f1_weighted": 0.9671757267424962, |
| "eval_loss": 0.02643330581486225, |
| "eval_macro_f1": 0.9671297823300075, |
| "eval_precision": 0.9676731949933907, |
| "eval_recall": 0.96716, |
| "eval_runtime": 662.2285, |
| "eval_samples_per_second": 151.005, |
| "eval_steps_per_second": 1.181, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.18475468004404746, |
| "grad_norm": 0.20989136397838593, |
| "learning_rate": 1.673615650323988e-05, |
| "loss": 0.1424, |
| "step": 1510 |
| }, |
| { |
| "epoch": 0.1859782209714915, |
| "grad_norm": 0.13308484852313995, |
| "learning_rate": 1.6675489539468094e-05, |
| "loss": 0.1541, |
| "step": 1520 |
| }, |
| { |
| "epoch": 0.18720176189893553, |
| "grad_norm": 0.3802664577960968, |
| "learning_rate": 1.6614376119587685e-05, |
| "loss": 0.1426, |
| "step": 1530 |
| }, |
| { |
| "epoch": 0.18842530282637954, |
| "grad_norm": 0.254869282245636, |
| "learning_rate": 1.6552820330858398e-05, |
| "loss": 0.1407, |
| "step": 1540 |
| }, |
| { |
| "epoch": 0.18964884375382357, |
| "grad_norm": 0.22702300548553467, |
| "learning_rate": 1.6490826290125555e-05, |
| "loss": 0.1404, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.19087238468126758, |
| "grad_norm": 0.18147043883800507, |
| "learning_rate": 1.6428398143544727e-05, |
| "loss": 0.1398, |
| "step": 1560 |
| }, |
| { |
| "epoch": 0.1920959256087116, |
| "grad_norm": 0.2697111964225769, |
| "learning_rate": 1.636554006630446e-05, |
| "loss": 0.1465, |
| "step": 1570 |
| }, |
| { |
| "epoch": 0.19331946653615564, |
| "grad_norm": 0.22285781800746918, |
| "learning_rate": 1.6302256262347e-05, |
| "loss": 0.1398, |
| "step": 1580 |
| }, |
| { |
| "epoch": 0.19454300746359965, |
| "grad_norm": 0.2551407814025879, |
| "learning_rate": 1.6238550964087175e-05, |
| "loss": 0.1347, |
| "step": 1590 |
| }, |
| { |
| "epoch": 0.19576654839104368, |
| "grad_norm": 0.25052276253700256, |
| "learning_rate": 1.61744284321293e-05, |
| "loss": 0.1461, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.19576654839104368, |
| "eval_accuracy": 0.96526, |
| "eval_f1_weighted": 0.9652784309636304, |
| "eval_loss": 0.02899531088769436, |
| "eval_macro_f1": 0.9652431164406312, |
| "eval_precision": 0.9664143950990177, |
| "eval_recall": 0.96526, |
| "eval_runtime": 662.3587, |
| "eval_samples_per_second": 150.976, |
| "eval_steps_per_second": 1.181, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.19699008931848772, |
| "grad_norm": 0.09207922220230103, |
| "learning_rate": 1.6109892954982242e-05, |
| "loss": 0.1382, |
| "step": 1610 |
| }, |
| { |
| "epoch": 0.19821363024593172, |
| "grad_norm": 0.2670917809009552, |
| "learning_rate": 1.6044948848772605e-05, |
| "loss": 0.142, |
| "step": 1620 |
| }, |
| { |
| "epoch": 0.19943717117337575, |
| "grad_norm": 0.28024110198020935, |
| "learning_rate": 1.597960045695607e-05, |
| "loss": 0.1385, |
| "step": 1630 |
| }, |
| { |
| "epoch": 0.20066071210081976, |
| "grad_norm": 0.15802879631519318, |
| "learning_rate": 1.5913852150026895e-05, |
| "loss": 0.1328, |
| "step": 1640 |
| }, |
| { |
| "epoch": 0.2018842530282638, |
| "grad_norm": 0.12178096175193787, |
| "learning_rate": 1.5847708325225618e-05, |
| "loss": 0.1446, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.20310779395570783, |
| "grad_norm": 0.22587499022483826, |
| "learning_rate": 1.578117340624499e-05, |
| "loss": 0.1406, |
| "step": 1660 |
| }, |
| { |
| "epoch": 0.20433133488315183, |
| "grad_norm": 0.18149550259113312, |
| "learning_rate": 1.5714251842934096e-05, |
| "loss": 0.1459, |
| "step": 1670 |
| }, |
| { |
| "epoch": 0.20555487581059587, |
| "grad_norm": 0.15662655234336853, |
| "learning_rate": 1.5646948111000756e-05, |
| "loss": 0.1344, |
| "step": 1680 |
| }, |
| { |
| "epoch": 0.2067784167380399, |
| "grad_norm": 0.1990954577922821, |
| "learning_rate": 1.5579266711712185e-05, |
| "loss": 0.1384, |
| "step": 1690 |
| }, |
| { |
| "epoch": 0.2080019576654839, |
| "grad_norm": 0.14277924597263336, |
| "learning_rate": 1.551121217159397e-05, |
| "loss": 0.1251, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.2080019576654839, |
| "eval_accuracy": 0.97199, |
| "eval_f1_weighted": 0.9719965673787706, |
| "eval_loss": 0.025022055953741074, |
| "eval_macro_f1": 0.9719444578845672, |
| "eval_precision": 0.9720688283360513, |
| "eval_recall": 0.97199, |
| "eval_runtime": 661.2104, |
| "eval_samples_per_second": 151.238, |
| "eval_steps_per_second": 1.183, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.20922549859292794, |
| "grad_norm": 0.13305141031742096, |
| "learning_rate": 1.5442789042127306e-05, |
| "loss": 0.1465, |
| "step": 1710 |
| }, |
| { |
| "epoch": 0.21044903952037194, |
| "grad_norm": 0.2761312425136566, |
| "learning_rate": 1.5374001899444624e-05, |
| "loss": 0.1413, |
| "step": 1720 |
| }, |
| { |
| "epoch": 0.21167258044781598, |
| "grad_norm": 0.11722280085086823, |
| "learning_rate": 1.530485534402351e-05, |
| "loss": 0.1337, |
| "step": 1730 |
| }, |
| { |
| "epoch": 0.21289612137526, |
| "grad_norm": 0.0893188863992691, |
| "learning_rate": 1.523535400037905e-05, |
| "loss": 0.1458, |
| "step": 1740 |
| }, |
| { |
| "epoch": 0.21411966230270402, |
| "grad_norm": 0.14586731791496277, |
| "learning_rate": 1.5165502516754526e-05, |
| "loss": 0.1389, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.21534320323014805, |
| "grad_norm": 0.23379822075366974, |
| "learning_rate": 1.509530556481056e-05, |
| "loss": 0.1467, |
| "step": 1760 |
| }, |
| { |
| "epoch": 0.21656674415759208, |
| "grad_norm": 0.12035554647445679, |
| "learning_rate": 1.5024767839312642e-05, |
| "loss": 0.1386, |
| "step": 1770 |
| }, |
| { |
| "epoch": 0.2177902850850361, |
| "grad_norm": 0.1451006382703781, |
| "learning_rate": 1.495389405781719e-05, |
| "loss": 0.1435, |
| "step": 1780 |
| }, |
| { |
| "epoch": 0.21901382601248012, |
| "grad_norm": 0.08014333248138428, |
| "learning_rate": 1.4882688960355994e-05, |
| "loss": 0.1491, |
| "step": 1790 |
| }, |
| { |
| "epoch": 0.22023736693992413, |
| "grad_norm": 0.17279869318008423, |
| "learning_rate": 1.4811157309119235e-05, |
| "loss": 0.151, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.22023736693992413, |
| "eval_accuracy": 0.96674, |
| "eval_f1_weighted": 0.9667576374640046, |
| "eval_loss": 0.02695448324084282, |
| "eval_macro_f1": 0.9667205101995933, |
| "eval_precision": 0.9677025757044254, |
| "eval_recall": 0.96674, |
| "eval_runtime": 661.5931, |
| "eval_samples_per_second": 151.15, |
| "eval_steps_per_second": 1.182, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.22146090786736816, |
| "grad_norm": 0.32028236985206604, |
| "learning_rate": 1.473930388813698e-05, |
| "loss": 0.1342, |
| "step": 1810 |
| }, |
| { |
| "epoch": 0.2226844487948122, |
| "grad_norm": 0.2838447690010071, |
| "learning_rate": 1.466713350295922e-05, |
| "loss": 0.1346, |
| "step": 1820 |
| }, |
| { |
| "epoch": 0.2239079897222562, |
| "grad_norm": 0.2165336161851883, |
| "learning_rate": 1.4594650980334492e-05, |
| "loss": 0.1447, |
| "step": 1830 |
| }, |
| { |
| "epoch": 0.22513153064970023, |
| "grad_norm": 0.1966007500886917, |
| "learning_rate": 1.4521861167887043e-05, |
| "loss": 0.1405, |
| "step": 1840 |
| }, |
| { |
| "epoch": 0.22635507157714427, |
| "grad_norm": 0.16725124418735504, |
| "learning_rate": 1.4448768933792644e-05, |
| "loss": 0.1272, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.22757861250458827, |
| "grad_norm": 0.22608086466789246, |
| "learning_rate": 1.4375379166452991e-05, |
| "loss": 0.1305, |
| "step": 1860 |
| }, |
| { |
| "epoch": 0.2288021534320323, |
| "grad_norm": 0.24929635226726532, |
| "learning_rate": 1.4301696774168782e-05, |
| "loss": 0.1276, |
| "step": 1870 |
| }, |
| { |
| "epoch": 0.2300256943594763, |
| "grad_norm": 0.0894479975104332, |
| "learning_rate": 1.4227726684811439e-05, |
| "loss": 0.1515, |
| "step": 1880 |
| }, |
| { |
| "epoch": 0.23124923528692035, |
| "grad_norm": 0.31293338537216187, |
| "learning_rate": 1.4153473845493531e-05, |
| "loss": 0.1262, |
| "step": 1890 |
| }, |
| { |
| "epoch": 0.23247277621436438, |
| "grad_norm": 0.34327465295791626, |
| "learning_rate": 1.4078943222237933e-05, |
| "loss": 0.1371, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.23247277621436438, |
| "eval_accuracy": 0.97149, |
| "eval_f1_weighted": 0.9715031773882226, |
| "eval_loss": 0.02571570873260498, |
| "eval_macro_f1": 0.9714618804747581, |
| "eval_precision": 0.9719368831197501, |
| "eval_recall": 0.97149, |
| "eval_runtime": 660.9647, |
| "eval_samples_per_second": 151.294, |
| "eval_steps_per_second": 1.183, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.23369631714180839, |
| "grad_norm": 0.07504434138536453, |
| "learning_rate": 1.4004139799645669e-05, |
| "loss": 0.1506, |
| "step": 1910 |
| }, |
| { |
| "epoch": 0.23491985806925242, |
| "grad_norm": 0.2954120934009552, |
| "learning_rate": 1.3929068580562561e-05, |
| "loss": 0.1329, |
| "step": 1920 |
| }, |
| { |
| "epoch": 0.23614339899669645, |
| "grad_norm": 0.17359323799610138, |
| "learning_rate": 1.3853734585744642e-05, |
| "loss": 0.1347, |
| "step": 1930 |
| }, |
| { |
| "epoch": 0.23736693992414046, |
| "grad_norm": 0.15386463701725006, |
| "learning_rate": 1.3778142853522352e-05, |
| "loss": 0.1429, |
| "step": 1940 |
| }, |
| { |
| "epoch": 0.2385904808515845, |
| "grad_norm": 0.2623615264892578, |
| "learning_rate": 1.3702298439463589e-05, |
| "loss": 0.1296, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.2398140217790285, |
| "grad_norm": 0.12422071397304535, |
| "learning_rate": 1.3626206416035589e-05, |
| "loss": 0.1441, |
| "step": 1960 |
| }, |
| { |
| "epoch": 0.24103756270647253, |
| "grad_norm": 0.14957550168037415, |
| "learning_rate": 1.3549871872265672e-05, |
| "loss": 0.1406, |
| "step": 1970 |
| }, |
| { |
| "epoch": 0.24226110363391656, |
| "grad_norm": 0.11441356688737869, |
| "learning_rate": 1.3473299913400905e-05, |
| "loss": 0.1294, |
| "step": 1980 |
| }, |
| { |
| "epoch": 0.24348464456136057, |
| "grad_norm": 0.19187535345554352, |
| "learning_rate": 1.3396495660566651e-05, |
| "loss": 0.1427, |
| "step": 1990 |
| }, |
| { |
| "epoch": 0.2447081854888046, |
| "grad_norm": 0.10940376669168472, |
| "learning_rate": 1.3319464250424068e-05, |
| "loss": 0.1439, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.2447081854888046, |
| "eval_accuracy": 0.97729, |
| "eval_f1_weighted": 0.9772907740157332, |
| "eval_loss": 0.01969166286289692, |
| "eval_macro_f1": 0.9772431978486675, |
| "eval_precision": 0.9772926495694174, |
| "eval_recall": 0.97729, |
| "eval_runtime": 660.9031, |
| "eval_samples_per_second": 151.308, |
| "eval_steps_per_second": 1.183, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.24593172641624864, |
| "grad_norm": 0.07293081283569336, |
| "learning_rate": 1.3242210834826575e-05, |
| "loss": 0.1322, |
| "step": 2010 |
| }, |
| { |
| "epoch": 0.24715526734369264, |
| "grad_norm": 0.1582045555114746, |
| "learning_rate": 1.31647405804753e-05, |
| "loss": 0.1273, |
| "step": 2020 |
| }, |
| { |
| "epoch": 0.24837880827113668, |
| "grad_norm": 0.29221460223197937, |
| "learning_rate": 1.3087058668573521e-05, |
| "loss": 0.1303, |
| "step": 2030 |
| }, |
| { |
| "epoch": 0.24960234919858068, |
| "grad_norm": 0.17140211164951324, |
| "learning_rate": 1.3009170294480149e-05, |
| "loss": 0.1394, |
| "step": 2040 |
| }, |
| { |
| "epoch": 0.25082589012602474, |
| "grad_norm": 0.3539097011089325, |
| "learning_rate": 1.2931080667362276e-05, |
| "loss": 0.1331, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.2520494310534687, |
| "grad_norm": 0.23371531069278717, |
| "learning_rate": 1.2852795009846775e-05, |
| "loss": 0.1238, |
| "step": 2060 |
| }, |
| { |
| "epoch": 0.25327297198091275, |
| "grad_norm": 0.21888205409049988, |
| "learning_rate": 1.2774318557671009e-05, |
| "loss": 0.1509, |
| "step": 2070 |
| }, |
| { |
| "epoch": 0.2544965129083568, |
| "grad_norm": 0.4899176359176636, |
| "learning_rate": 1.2695656559332671e-05, |
| "loss": 0.1461, |
| "step": 2080 |
| }, |
| { |
| "epoch": 0.2557200538358008, |
| "grad_norm": 0.1515502780675888, |
| "learning_rate": 1.261681427573877e-05, |
| "loss": 0.1331, |
| "step": 2090 |
| }, |
| { |
| "epoch": 0.25694359476324485, |
| "grad_norm": 0.13595114648342133, |
| "learning_rate": 1.2537796979853764e-05, |
| "loss": 0.1484, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.25694359476324485, |
| "eval_accuracy": 0.97769, |
| "eval_f1_weighted": 0.9776954901619872, |
| "eval_loss": 0.019225435331463814, |
| "eval_macro_f1": 0.9776543362648145, |
| "eval_precision": 0.9777750172865488, |
| "eval_recall": 0.97769, |
| "eval_runtime": 660.729, |
| "eval_samples_per_second": 151.348, |
| "eval_steps_per_second": 1.184, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.25816713569068883, |
| "grad_norm": 0.14403671026229858, |
| "learning_rate": 1.2458609956346927e-05, |
| "loss": 0.1386, |
| "step": 2110 |
| }, |
| { |
| "epoch": 0.25939067661813286, |
| "grad_norm": 0.28055140376091003, |
| "learning_rate": 1.23792585012389e-05, |
| "loss": 0.1331, |
| "step": 2120 |
| }, |
| { |
| "epoch": 0.2606142175455769, |
| "grad_norm": 0.15281730890274048, |
| "learning_rate": 1.2299747921547485e-05, |
| "loss": 0.1428, |
| "step": 2130 |
| }, |
| { |
| "epoch": 0.26183775847302093, |
| "grad_norm": 0.2775639593601227, |
| "learning_rate": 1.2220083534932731e-05, |
| "loss": 0.1292, |
| "step": 2140 |
| }, |
| { |
| "epoch": 0.26306129940046497, |
| "grad_norm": 0.23231762647628784, |
| "learning_rate": 1.2140270669341272e-05, |
| "loss": 0.1278, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.26428484032790894, |
| "grad_norm": 0.15349626541137695, |
| "learning_rate": 1.2060314662650008e-05, |
| "loss": 0.1289, |
| "step": 2160 |
| }, |
| { |
| "epoch": 0.265508381255353, |
| "grad_norm": 0.270783394575119, |
| "learning_rate": 1.1980220862309097e-05, |
| "loss": 0.1353, |
| "step": 2170 |
| }, |
| { |
| "epoch": 0.266731922182797, |
| "grad_norm": 0.25189876556396484, |
| "learning_rate": 1.1899994624984324e-05, |
| "loss": 0.128, |
| "step": 2180 |
| }, |
| { |
| "epoch": 0.26795546311024104, |
| "grad_norm": 0.3517930805683136, |
| "learning_rate": 1.1819641316198856e-05, |
| "loss": 0.1368, |
| "step": 2190 |
| }, |
| { |
| "epoch": 0.2691790040376851, |
| "grad_norm": 0.1853000968694687, |
| "learning_rate": 1.173916630997437e-05, |
| "loss": 0.1261, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.2691790040376851, |
| "eval_accuracy": 0.96989, |
| "eval_f1_weighted": 0.9699058894297731, |
| "eval_loss": 0.027551453560590744, |
| "eval_macro_f1": 0.9698711242322156, |
| "eval_precision": 0.97078292839073, |
| "eval_recall": 0.96989, |
| "eval_runtime": 660.4203, |
| "eval_samples_per_second": 151.419, |
| "eval_steps_per_second": 1.184, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.2704025449651291, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1658574988471674e-05, |
| "loss": 0.1637, |
| "step": 2210 |
| }, |
| { |
| "epoch": 0.2716260858925731, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.157787274163072e-05, |
| "loss": 0.1536, |
| "step": 2220 |
| }, |
| { |
| "epoch": 0.2728496268200171, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.1497064966810137e-05, |
| "loss": 0.1539, |
| "step": 2230 |
| }, |
| { |
| "epoch": 0.27407316774746115, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1416157068426259e-05, |
| "loss": 0.1476, |
| "step": 2240 |
| }, |
| { |
| "epoch": 0.2752967086749052, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1335154457591673e-05, |
| "loss": 0.1608, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.2765202496023492, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1254062551753324e-05, |
| "loss": 0.1648, |
| "step": 2260 |
| }, |
| { |
| "epoch": 0.2777437905297932, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1172886774330198e-05, |
| "loss": 0.1491, |
| "step": 2270 |
| }, |
| { |
| "epoch": 0.27896733145723723, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.1091632554350612e-05, |
| "loss": 0.1357, |
| "step": 2280 |
| }, |
| { |
| "epoch": 0.28019087238468127, |
| "grad_norm": 1.0, |
| "learning_rate": 1.1010305326089106e-05, |
| "loss": 0.1556, |
| "step": 2290 |
| }, |
| { |
| "epoch": 0.2814144133121253, |
| "grad_norm": 0.9999999403953552, |
| "learning_rate": 1.0928910528703007e-05, |
| "loss": 0.1448, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.2814144133121253, |
| "eval_accuracy": 0.97262, |
| "eval_f1_weighted": 0.9726184157943225, |
| "eval_loss": 0.022996049374341965, |
| "eval_macro_f1": 0.972558553596182, |
| "eval_precision": 0.9726197333502502, |
| "eval_recall": 0.97262, |
| "eval_runtime": 1557.6213, |
| "eval_samples_per_second": 64.2, |
| "eval_steps_per_second": 0.251, |
| "step": 2300 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 8173, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "EarlyStoppingCallback": { |
| "args": { |
| "early_stopping_patience": 3, |
| "early_stopping_threshold": 0.0 |
| }, |
| "attributes": { |
| "early_stopping_patience_counter": 1 |
| } |
| }, |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3.904095929041229e+16, |
| "train_batch_size": 64, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
