| { |
| "best_global_step": 2464, |
| "best_metric": 0.7966146756469337, |
| "best_model_checkpoint": "Obstacle/dinov2/checkpoint-2464", |
| "epoch": 22.0, |
| "eval_steps": 500, |
| "global_step": 2464, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.0894854586129754, |
| "grad_norm": 68.26221466064453, |
| "learning_rate": 3.214285714285714e-07, |
| "loss": 0.9281, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.1789709172259508, |
| "grad_norm": 49.921424865722656, |
| "learning_rate": 6.785714285714286e-07, |
| "loss": 0.8782, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.2684563758389262, |
| "grad_norm": 63.9870491027832, |
| "learning_rate": 1.0357142857142859e-06, |
| "loss": 0.769, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.3579418344519016, |
| "grad_norm": 27.94622230529785, |
| "learning_rate": 1.392857142857143e-06, |
| "loss": 0.7484, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.44742729306487694, |
| "grad_norm": 31.261272430419922, |
| "learning_rate": 1.75e-06, |
| "loss": 0.7224, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5369127516778524, |
| "grad_norm": 30.373384475708008, |
| "learning_rate": 2.1071428571428572e-06, |
| "loss": 0.6935, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.6263982102908278, |
| "grad_norm": 25.922801971435547, |
| "learning_rate": 2.4642857142857147e-06, |
| "loss": 0.656, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.7158836689038032, |
| "grad_norm": 21.445323944091797, |
| "learning_rate": 2.8214285714285718e-06, |
| "loss": 0.6086, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.8053691275167785, |
| "grad_norm": 47.42407989501953, |
| "learning_rate": 3.178571428571429e-06, |
| "loss": 0.7216, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.8948545861297539, |
| "grad_norm": 23.003158569335938, |
| "learning_rate": 3.5357142857142863e-06, |
| "loss": 0.6132, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.9843400447427293, |
| "grad_norm": 31.152210235595703, |
| "learning_rate": 3.892857142857143e-06, |
| "loss": 0.6263, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 0.572486162185669, |
| "eval_macro_f1": 0.6811600432857552, |
| "eval_runtime": 118.5033, |
| "eval_samples_per_second": 6.456, |
| "eval_steps_per_second": 0.81, |
| "step": 112 |
| }, |
| { |
| "epoch": 1.0715883668903803, |
| "grad_norm": 19.629968643188477, |
| "learning_rate": 4.25e-06, |
| "loss": 0.5971, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.1610738255033557, |
| "grad_norm": 38.47784423828125, |
| "learning_rate": 4.6071428571428574e-06, |
| "loss": 0.5379, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.250559284116331, |
| "grad_norm": 24.479284286499023, |
| "learning_rate": 4.964285714285715e-06, |
| "loss": 0.529, |
| "step": 140 |
| }, |
| { |
| "epoch": 1.3400447427293065, |
| "grad_norm": 20.997512817382812, |
| "learning_rate": 5.3214285714285715e-06, |
| "loss": 0.6006, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.429530201342282, |
| "grad_norm": 52.60095977783203, |
| "learning_rate": 5.678571428571429e-06, |
| "loss": 0.7468, |
| "step": 160 |
| }, |
| { |
| "epoch": 1.5190156599552571, |
| "grad_norm": 15.642265319824219, |
| "learning_rate": 6.035714285714286e-06, |
| "loss": 0.559, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.6085011185682325, |
| "grad_norm": 70.16302490234375, |
| "learning_rate": 6.392857142857143e-06, |
| "loss": 0.6043, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.697986577181208, |
| "grad_norm": 26.643476486206055, |
| "learning_rate": 6.750000000000001e-06, |
| "loss": 0.5636, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.7874720357941833, |
| "grad_norm": 177.88034057617188, |
| "learning_rate": 7.107142857142858e-06, |
| "loss": 0.5427, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.8769574944071588, |
| "grad_norm": 38.7111701965332, |
| "learning_rate": 7.464285714285715e-06, |
| "loss": 0.5486, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.9664429530201342, |
| "grad_norm": 21.803434371948242, |
| "learning_rate": 7.821428571428571e-06, |
| "loss": 0.609, |
| "step": 220 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.5907321572303772, |
| "eval_macro_f1": 0.7001507404932478, |
| "eval_runtime": 121.4035, |
| "eval_samples_per_second": 6.301, |
| "eval_steps_per_second": 0.791, |
| "step": 224 |
| }, |
| { |
| "epoch": 2.053691275167785, |
| "grad_norm": 23.68389320373535, |
| "learning_rate": 8.17857142857143e-06, |
| "loss": 0.4989, |
| "step": 230 |
| }, |
| { |
| "epoch": 2.1431767337807606, |
| "grad_norm": 26.48926544189453, |
| "learning_rate": 8.535714285714286e-06, |
| "loss": 0.5119, |
| "step": 240 |
| }, |
| { |
| "epoch": 2.232662192393736, |
| "grad_norm": 25.900455474853516, |
| "learning_rate": 8.892857142857143e-06, |
| "loss": 0.5046, |
| "step": 250 |
| }, |
| { |
| "epoch": 2.3221476510067114, |
| "grad_norm": 26.200103759765625, |
| "learning_rate": 9.250000000000001e-06, |
| "loss": 0.4793, |
| "step": 260 |
| }, |
| { |
| "epoch": 2.411633109619687, |
| "grad_norm": 36.33053970336914, |
| "learning_rate": 9.607142857142858e-06, |
| "loss": 0.5127, |
| "step": 270 |
| }, |
| { |
| "epoch": 2.501118568232662, |
| "grad_norm": 51.3528938293457, |
| "learning_rate": 9.964285714285714e-06, |
| "loss": 0.5188, |
| "step": 280 |
| }, |
| { |
| "epoch": 2.5906040268456376, |
| "grad_norm": 28.10676383972168, |
| "learning_rate": 9.964285714285714e-06, |
| "loss": 0.4858, |
| "step": 290 |
| }, |
| { |
| "epoch": 2.680089485458613, |
| "grad_norm": 25.275537490844727, |
| "learning_rate": 9.924603174603175e-06, |
| "loss": 0.497, |
| "step": 300 |
| }, |
| { |
| "epoch": 2.7695749440715884, |
| "grad_norm": 23.899168014526367, |
| "learning_rate": 9.884920634920636e-06, |
| "loss": 0.4843, |
| "step": 310 |
| }, |
| { |
| "epoch": 2.859060402684564, |
| "grad_norm": 21.87393569946289, |
| "learning_rate": 9.845238095238097e-06, |
| "loss": 0.5006, |
| "step": 320 |
| }, |
| { |
| "epoch": 2.9485458612975393, |
| "grad_norm": 27.74087905883789, |
| "learning_rate": 9.805555555555556e-06, |
| "loss": 0.4471, |
| "step": 330 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.5459941029548645, |
| "eval_macro_f1": 0.726109493936894, |
| "eval_runtime": 121.5217, |
| "eval_samples_per_second": 6.295, |
| "eval_steps_per_second": 0.79, |
| "step": 336 |
| }, |
| { |
| "epoch": 3.0357941834451903, |
| "grad_norm": 41.323997497558594, |
| "learning_rate": 9.765873015873017e-06, |
| "loss": 0.5304, |
| "step": 340 |
| }, |
| { |
| "epoch": 3.1252796420581657, |
| "grad_norm": 31.197467803955078, |
| "learning_rate": 9.726190476190477e-06, |
| "loss": 0.4863, |
| "step": 350 |
| }, |
| { |
| "epoch": 3.214765100671141, |
| "grad_norm": 15.407756805419922, |
| "learning_rate": 9.686507936507938e-06, |
| "loss": 0.4116, |
| "step": 360 |
| }, |
| { |
| "epoch": 3.3042505592841165, |
| "grad_norm": 19.091278076171875, |
| "learning_rate": 9.646825396825397e-06, |
| "loss": 0.4092, |
| "step": 370 |
| }, |
| { |
| "epoch": 3.393736017897092, |
| "grad_norm": 42.068511962890625, |
| "learning_rate": 9.607142857142858e-06, |
| "loss": 0.4627, |
| "step": 380 |
| }, |
| { |
| "epoch": 3.4832214765100673, |
| "grad_norm": 26.687232971191406, |
| "learning_rate": 9.567460317460319e-06, |
| "loss": 0.4487, |
| "step": 390 |
| }, |
| { |
| "epoch": 3.5727069351230423, |
| "grad_norm": 22.164098739624023, |
| "learning_rate": 9.527777777777778e-06, |
| "loss": 0.48, |
| "step": 400 |
| }, |
| { |
| "epoch": 3.662192393736018, |
| "grad_norm": 22.220373153686523, |
| "learning_rate": 9.488095238095238e-06, |
| "loss": 0.53, |
| "step": 410 |
| }, |
| { |
| "epoch": 3.751677852348993, |
| "grad_norm": 8.822561264038086, |
| "learning_rate": 9.4484126984127e-06, |
| "loss": 0.4999, |
| "step": 420 |
| }, |
| { |
| "epoch": 3.841163310961969, |
| "grad_norm": 11.927675247192383, |
| "learning_rate": 9.40873015873016e-06, |
| "loss": 0.4642, |
| "step": 430 |
| }, |
| { |
| "epoch": 3.930648769574944, |
| "grad_norm": 14.933186531066895, |
| "learning_rate": 9.36904761904762e-06, |
| "loss": 0.4145, |
| "step": 440 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.5586118102073669, |
| "eval_macro_f1": 0.741893986276926, |
| "eval_runtime": 120.2217, |
| "eval_samples_per_second": 6.363, |
| "eval_steps_per_second": 0.799, |
| "step": 448 |
| }, |
| { |
| "epoch": 4.017897091722595, |
| "grad_norm": 23.335527420043945, |
| "learning_rate": 9.32936507936508e-06, |
| "loss": 0.4222, |
| "step": 450 |
| }, |
| { |
| "epoch": 4.10738255033557, |
| "grad_norm": 28.71408462524414, |
| "learning_rate": 9.28968253968254e-06, |
| "loss": 0.3959, |
| "step": 460 |
| }, |
| { |
| "epoch": 4.196868008948546, |
| "grad_norm": 20.4088077545166, |
| "learning_rate": 9.250000000000001e-06, |
| "loss": 0.3423, |
| "step": 470 |
| }, |
| { |
| "epoch": 4.286353467561521, |
| "grad_norm": 39.36516189575195, |
| "learning_rate": 9.21031746031746e-06, |
| "loss": 0.3851, |
| "step": 480 |
| }, |
| { |
| "epoch": 4.375838926174497, |
| "grad_norm": 32.29376983642578, |
| "learning_rate": 9.170634920634921e-06, |
| "loss": 0.3766, |
| "step": 490 |
| }, |
| { |
| "epoch": 4.465324384787472, |
| "grad_norm": 13.637434959411621, |
| "learning_rate": 9.130952380952382e-06, |
| "loss": 0.3328, |
| "step": 500 |
| }, |
| { |
| "epoch": 4.554809843400448, |
| "grad_norm": 23.359638214111328, |
| "learning_rate": 9.091269841269843e-06, |
| "loss": 0.3988, |
| "step": 510 |
| }, |
| { |
| "epoch": 4.644295302013423, |
| "grad_norm": 25.244564056396484, |
| "learning_rate": 9.051587301587302e-06, |
| "loss": 0.3149, |
| "step": 520 |
| }, |
| { |
| "epoch": 4.733780760626399, |
| "grad_norm": 273.609619140625, |
| "learning_rate": 9.011904761904762e-06, |
| "loss": 0.3685, |
| "step": 530 |
| }, |
| { |
| "epoch": 4.823266219239374, |
| "grad_norm": 18.818504333496094, |
| "learning_rate": 8.972222222222223e-06, |
| "loss": 0.2867, |
| "step": 540 |
| }, |
| { |
| "epoch": 4.912751677852349, |
| "grad_norm": 19.458040237426758, |
| "learning_rate": 8.932539682539684e-06, |
| "loss": 0.3952, |
| "step": 550 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 11.257533073425293, |
| "learning_rate": 8.892857142857143e-06, |
| "loss": 0.3553, |
| "step": 560 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.5237393379211426, |
| "eval_macro_f1": 0.7685140098500236, |
| "eval_runtime": 124.8114, |
| "eval_samples_per_second": 6.129, |
| "eval_steps_per_second": 0.769, |
| "step": 560 |
| }, |
| { |
| "epoch": 5.089485458612975, |
| "grad_norm": 16.261404037475586, |
| "learning_rate": 8.853174603174604e-06, |
| "loss": 0.3108, |
| "step": 570 |
| }, |
| { |
| "epoch": 5.178970917225951, |
| "grad_norm": 16.059083938598633, |
| "learning_rate": 8.813492063492064e-06, |
| "loss": 0.2986, |
| "step": 580 |
| }, |
| { |
| "epoch": 5.268456375838926, |
| "grad_norm": 22.006534576416016, |
| "learning_rate": 8.773809523809525e-06, |
| "loss": 0.2952, |
| "step": 590 |
| }, |
| { |
| "epoch": 5.357941834451902, |
| "grad_norm": 16.75338363647461, |
| "learning_rate": 8.734126984126984e-06, |
| "loss": 0.2512, |
| "step": 600 |
| }, |
| { |
| "epoch": 5.447427293064877, |
| "grad_norm": 36.52522659301758, |
| "learning_rate": 8.694444444444445e-06, |
| "loss": 0.2308, |
| "step": 610 |
| }, |
| { |
| "epoch": 5.5369127516778525, |
| "grad_norm": 14.535757064819336, |
| "learning_rate": 8.654761904761906e-06, |
| "loss": 0.3012, |
| "step": 620 |
| }, |
| { |
| "epoch": 5.626398210290827, |
| "grad_norm": 22.867900848388672, |
| "learning_rate": 8.615079365079366e-06, |
| "loss": 0.3232, |
| "step": 630 |
| }, |
| { |
| "epoch": 5.715883668903803, |
| "grad_norm": 19.417451858520508, |
| "learning_rate": 8.575396825396826e-06, |
| "loss": 0.3173, |
| "step": 640 |
| }, |
| { |
| "epoch": 5.805369127516778, |
| "grad_norm": 21.25806427001953, |
| "learning_rate": 8.535714285714286e-06, |
| "loss": 0.3376, |
| "step": 650 |
| }, |
| { |
| "epoch": 5.894854586129754, |
| "grad_norm": 11.842672348022461, |
| "learning_rate": 8.496031746031747e-06, |
| "loss": 0.3756, |
| "step": 660 |
| }, |
| { |
| "epoch": 5.984340044742729, |
| "grad_norm": 16.4525203704834, |
| "learning_rate": 8.456349206349208e-06, |
| "loss": 0.2923, |
| "step": 670 |
| }, |
| { |
| "epoch": 6.0, |
| "eval_loss": 0.5606415271759033, |
| "eval_macro_f1": 0.7435031036046287, |
| "eval_runtime": 115.5398, |
| "eval_samples_per_second": 6.621, |
| "eval_steps_per_second": 0.831, |
| "step": 672 |
| }, |
| { |
| "epoch": 6.0715883668903805, |
| "grad_norm": 20.93574333190918, |
| "learning_rate": 8.416666666666667e-06, |
| "loss": 0.2473, |
| "step": 680 |
| }, |
| { |
| "epoch": 6.1610738255033555, |
| "grad_norm": 26.189205169677734, |
| "learning_rate": 8.376984126984128e-06, |
| "loss": 0.2403, |
| "step": 690 |
| }, |
| { |
| "epoch": 6.250559284116331, |
| "grad_norm": 13.84333610534668, |
| "learning_rate": 8.337301587301588e-06, |
| "loss": 0.231, |
| "step": 700 |
| }, |
| { |
| "epoch": 6.340044742729306, |
| "grad_norm": 22.295377731323242, |
| "learning_rate": 8.297619047619049e-06, |
| "loss": 0.2416, |
| "step": 710 |
| }, |
| { |
| "epoch": 6.429530201342282, |
| "grad_norm": 14.893708229064941, |
| "learning_rate": 8.257936507936508e-06, |
| "loss": 0.2409, |
| "step": 720 |
| }, |
| { |
| "epoch": 6.519015659955257, |
| "grad_norm": 14.828768730163574, |
| "learning_rate": 8.218253968253969e-06, |
| "loss": 0.1927, |
| "step": 730 |
| }, |
| { |
| "epoch": 6.608501118568233, |
| "grad_norm": 23.54037094116211, |
| "learning_rate": 8.17857142857143e-06, |
| "loss": 0.2373, |
| "step": 740 |
| }, |
| { |
| "epoch": 6.697986577181208, |
| "grad_norm": 20.361324310302734, |
| "learning_rate": 8.138888888888889e-06, |
| "loss": 0.2266, |
| "step": 750 |
| }, |
| { |
| "epoch": 6.787472035794184, |
| "grad_norm": 32.86820602416992, |
| "learning_rate": 8.09920634920635e-06, |
| "loss": 0.3065, |
| "step": 760 |
| }, |
| { |
| "epoch": 6.876957494407159, |
| "grad_norm": 25.08152198791504, |
| "learning_rate": 8.05952380952381e-06, |
| "loss": 0.307, |
| "step": 770 |
| }, |
| { |
| "epoch": 6.966442953020135, |
| "grad_norm": 21.257457733154297, |
| "learning_rate": 8.019841269841271e-06, |
| "loss": 0.2943, |
| "step": 780 |
| }, |
| { |
| "epoch": 7.0, |
| "eval_loss": 0.5504983067512512, |
| "eval_macro_f1": 0.7728941735285386, |
| "eval_runtime": 119.5498, |
| "eval_samples_per_second": 6.399, |
| "eval_steps_per_second": 0.803, |
| "step": 784 |
| }, |
| { |
| "epoch": 7.053691275167785, |
| "grad_norm": 13.639359474182129, |
| "learning_rate": 7.980158730158732e-06, |
| "loss": 0.2103, |
| "step": 790 |
| }, |
| { |
| "epoch": 7.143176733780761, |
| "grad_norm": 27.568639755249023, |
| "learning_rate": 7.94047619047619e-06, |
| "loss": 0.1676, |
| "step": 800 |
| }, |
| { |
| "epoch": 7.232662192393736, |
| "grad_norm": 17.152692794799805, |
| "learning_rate": 7.900793650793652e-06, |
| "loss": 0.1818, |
| "step": 810 |
| }, |
| { |
| "epoch": 7.322147651006711, |
| "grad_norm": 16.47798728942871, |
| "learning_rate": 7.861111111111112e-06, |
| "loss": 0.2058, |
| "step": 820 |
| }, |
| { |
| "epoch": 7.411633109619687, |
| "grad_norm": 17.176942825317383, |
| "learning_rate": 7.821428571428571e-06, |
| "loss": 0.1508, |
| "step": 830 |
| }, |
| { |
| "epoch": 7.501118568232663, |
| "grad_norm": 29.886573791503906, |
| "learning_rate": 7.781746031746032e-06, |
| "loss": 0.2434, |
| "step": 840 |
| }, |
| { |
| "epoch": 7.590604026845638, |
| "grad_norm": 22.851221084594727, |
| "learning_rate": 7.742063492063493e-06, |
| "loss": 0.2431, |
| "step": 850 |
| }, |
| { |
| "epoch": 7.680089485458613, |
| "grad_norm": 9.74971866607666, |
| "learning_rate": 7.702380952380954e-06, |
| "loss": 0.1905, |
| "step": 860 |
| }, |
| { |
| "epoch": 7.769574944071588, |
| "grad_norm": 22.99750328063965, |
| "learning_rate": 7.662698412698414e-06, |
| "loss": 0.2215, |
| "step": 870 |
| }, |
| { |
| "epoch": 7.859060402684563, |
| "grad_norm": 29.295093536376953, |
| "learning_rate": 7.623015873015873e-06, |
| "loss": 0.2222, |
| "step": 880 |
| }, |
| { |
| "epoch": 7.948545861297539, |
| "grad_norm": 13.15281867980957, |
| "learning_rate": 7.583333333333333e-06, |
| "loss": 0.2172, |
| "step": 890 |
| }, |
| { |
| "epoch": 8.0, |
| "eval_loss": 0.5693853497505188, |
| "eval_macro_f1": 0.7617472396955967, |
| "eval_runtime": 71.7674, |
| "eval_samples_per_second": 10.659, |
| "eval_steps_per_second": 1.338, |
| "step": 896 |
| }, |
| { |
| "epoch": 8.03579418344519, |
| "grad_norm": 17.01239585876465, |
| "learning_rate": 7.543650793650794e-06, |
| "loss": 0.2183, |
| "step": 900 |
| }, |
| { |
| "epoch": 8.125279642058166, |
| "grad_norm": 16.31254768371582, |
| "learning_rate": 7.503968253968255e-06, |
| "loss": 0.1393, |
| "step": 910 |
| }, |
| { |
| "epoch": 8.21476510067114, |
| "grad_norm": 21.926393508911133, |
| "learning_rate": 7.464285714285715e-06, |
| "loss": 0.2104, |
| "step": 920 |
| }, |
| { |
| "epoch": 8.304250559284116, |
| "grad_norm": 16.77183723449707, |
| "learning_rate": 7.4246031746031754e-06, |
| "loss": 0.1808, |
| "step": 930 |
| }, |
| { |
| "epoch": 8.393736017897092, |
| "grad_norm": 10.125628471374512, |
| "learning_rate": 7.384920634920636e-06, |
| "loss": 0.142, |
| "step": 940 |
| }, |
| { |
| "epoch": 8.483221476510067, |
| "grad_norm": 8.853920936584473, |
| "learning_rate": 7.345238095238096e-06, |
| "loss": 0.1674, |
| "step": 950 |
| }, |
| { |
| "epoch": 8.572706935123042, |
| "grad_norm": 16.407033920288086, |
| "learning_rate": 7.305555555555556e-06, |
| "loss": 0.1684, |
| "step": 960 |
| }, |
| { |
| "epoch": 8.662192393736017, |
| "grad_norm": 19.892669677734375, |
| "learning_rate": 7.265873015873016e-06, |
| "loss": 0.1673, |
| "step": 970 |
| }, |
| { |
| "epoch": 8.751677852348994, |
| "grad_norm": 5.113985061645508, |
| "learning_rate": 7.226190476190477e-06, |
| "loss": 0.2087, |
| "step": 980 |
| }, |
| { |
| "epoch": 8.841163310961969, |
| "grad_norm": 10.283279418945312, |
| "learning_rate": 7.186507936507937e-06, |
| "loss": 0.1728, |
| "step": 990 |
| }, |
| { |
| "epoch": 8.930648769574944, |
| "grad_norm": 11.258045196533203, |
| "learning_rate": 7.146825396825397e-06, |
| "loss": 0.2067, |
| "step": 1000 |
| }, |
| { |
| "epoch": 9.0, |
| "eval_loss": 0.6666957139968872, |
| "eval_macro_f1": 0.7585227272727273, |
| "eval_runtime": 75.2405, |
| "eval_samples_per_second": 10.167, |
| "eval_steps_per_second": 1.276, |
| "step": 1008 |
| }, |
| { |
| "epoch": 9.017897091722595, |
| "grad_norm": 31.886018753051758, |
| "learning_rate": 7.107142857142858e-06, |
| "loss": 0.1853, |
| "step": 1010 |
| }, |
| { |
| "epoch": 9.10738255033557, |
| "grad_norm": 21.961132049560547, |
| "learning_rate": 7.067460317460319e-06, |
| "loss": 0.1823, |
| "step": 1020 |
| }, |
| { |
| "epoch": 9.196868008948545, |
| "grad_norm": 9.536689758300781, |
| "learning_rate": 7.027777777777778e-06, |
| "loss": 0.1289, |
| "step": 1030 |
| }, |
| { |
| "epoch": 9.286353467561522, |
| "grad_norm": 17.52619171142578, |
| "learning_rate": 6.988095238095239e-06, |
| "loss": 0.1421, |
| "step": 1040 |
| }, |
| { |
| "epoch": 9.375838926174497, |
| "grad_norm": 5.5908379554748535, |
| "learning_rate": 6.9484126984126985e-06, |
| "loss": 0.1024, |
| "step": 1050 |
| }, |
| { |
| "epoch": 9.465324384787472, |
| "grad_norm": 15.923222541809082, |
| "learning_rate": 6.908730158730159e-06, |
| "loss": 0.1363, |
| "step": 1060 |
| }, |
| { |
| "epoch": 9.554809843400447, |
| "grad_norm": 7.426005840301514, |
| "learning_rate": 6.86904761904762e-06, |
| "loss": 0.1851, |
| "step": 1070 |
| }, |
| { |
| "epoch": 9.644295302013422, |
| "grad_norm": 2.362064838409424, |
| "learning_rate": 6.82936507936508e-06, |
| "loss": 0.1177, |
| "step": 1080 |
| }, |
| { |
| "epoch": 9.733780760626399, |
| "grad_norm": 16.235544204711914, |
| "learning_rate": 6.789682539682541e-06, |
| "loss": 0.0991, |
| "step": 1090 |
| }, |
| { |
| "epoch": 9.823266219239374, |
| "grad_norm": 8.337503433227539, |
| "learning_rate": 6.750000000000001e-06, |
| "loss": 0.13, |
| "step": 1100 |
| }, |
| { |
| "epoch": 9.912751677852349, |
| "grad_norm": 34.09331130981445, |
| "learning_rate": 6.7103174603174605e-06, |
| "loss": 0.1171, |
| "step": 1110 |
| }, |
| { |
| "epoch": 10.0, |
| "grad_norm": 25.452791213989258, |
| "learning_rate": 6.67063492063492e-06, |
| "loss": 0.1817, |
| "step": 1120 |
| }, |
| { |
| "epoch": 10.0, |
| "eval_loss": 0.8301987051963806, |
| "eval_macro_f1": 0.7432961635470596, |
| "eval_runtime": 71.6774, |
| "eval_samples_per_second": 10.673, |
| "eval_steps_per_second": 1.339, |
| "step": 1120 |
| }, |
| { |
| "epoch": 10.089485458612975, |
| "grad_norm": 19.931293487548828, |
| "learning_rate": 6.630952380952381e-06, |
| "loss": 0.1405, |
| "step": 1130 |
| }, |
| { |
| "epoch": 10.17897091722595, |
| "grad_norm": 20.297443389892578, |
| "learning_rate": 6.591269841269842e-06, |
| "loss": 0.1359, |
| "step": 1140 |
| }, |
| { |
| "epoch": 10.268456375838927, |
| "grad_norm": 11.013289451599121, |
| "learning_rate": 6.551587301587302e-06, |
| "loss": 0.0918, |
| "step": 1150 |
| }, |
| { |
| "epoch": 10.357941834451902, |
| "grad_norm": 19.394319534301758, |
| "learning_rate": 6.5119047619047626e-06, |
| "loss": 0.1392, |
| "step": 1160 |
| }, |
| { |
| "epoch": 10.447427293064877, |
| "grad_norm": 28.343791961669922, |
| "learning_rate": 6.472222222222223e-06, |
| "loss": 0.1866, |
| "step": 1170 |
| }, |
| { |
| "epoch": 10.536912751677852, |
| "grad_norm": 14.38354778289795, |
| "learning_rate": 6.432539682539683e-06, |
| "loss": 0.1381, |
| "step": 1180 |
| }, |
| { |
| "epoch": 10.626398210290828, |
| "grad_norm": 24.752470016479492, |
| "learning_rate": 6.392857142857143e-06, |
| "loss": 0.202, |
| "step": 1190 |
| }, |
| { |
| "epoch": 10.715883668903803, |
| "grad_norm": 19.56192970275879, |
| "learning_rate": 6.353174603174603e-06, |
| "loss": 0.1566, |
| "step": 1200 |
| }, |
| { |
| "epoch": 10.805369127516778, |
| "grad_norm": 20.234485626220703, |
| "learning_rate": 6.313492063492064e-06, |
| "loss": 0.1061, |
| "step": 1210 |
| }, |
| { |
| "epoch": 10.894854586129753, |
| "grad_norm": 19.531757354736328, |
| "learning_rate": 6.2738095238095245e-06, |
| "loss": 0.1873, |
| "step": 1220 |
| }, |
| { |
| "epoch": 10.98434004474273, |
| "grad_norm": 16.655208587646484, |
| "learning_rate": 6.2341269841269844e-06, |
| "loss": 0.1102, |
| "step": 1230 |
| }, |
| { |
| "epoch": 11.0, |
| "eval_loss": 0.6939279437065125, |
| "eval_macro_f1": 0.769257323981233, |
| "eval_runtime": 73.198, |
| "eval_samples_per_second": 10.451, |
| "eval_steps_per_second": 1.312, |
| "step": 1232 |
| }, |
| { |
| "epoch": 11.07158836689038, |
| "grad_norm": 5.695398330688477, |
| "learning_rate": 6.194444444444445e-06, |
| "loss": 0.1283, |
| "step": 1240 |
| }, |
| { |
| "epoch": 11.161073825503356, |
| "grad_norm": 9.851438522338867, |
| "learning_rate": 6.154761904761906e-06, |
| "loss": 0.1065, |
| "step": 1250 |
| }, |
| { |
| "epoch": 11.250559284116331, |
| "grad_norm": 29.838871002197266, |
| "learning_rate": 6.115079365079366e-06, |
| "loss": 0.1426, |
| "step": 1260 |
| }, |
| { |
| "epoch": 11.340044742729306, |
| "grad_norm": 7.144505500793457, |
| "learning_rate": 6.075396825396826e-06, |
| "loss": 0.093, |
| "step": 1270 |
| }, |
| { |
| "epoch": 11.429530201342281, |
| "grad_norm": 15.980908393859863, |
| "learning_rate": 6.035714285714286e-06, |
| "loss": 0.1508, |
| "step": 1280 |
| }, |
| { |
| "epoch": 11.519015659955258, |
| "grad_norm": 23.028108596801758, |
| "learning_rate": 5.996031746031746e-06, |
| "loss": 0.1719, |
| "step": 1290 |
| }, |
| { |
| "epoch": 11.608501118568233, |
| "grad_norm": 14.000625610351562, |
| "learning_rate": 5.956349206349207e-06, |
| "loss": 0.1063, |
| "step": 1300 |
| }, |
| { |
| "epoch": 11.697986577181208, |
| "grad_norm": 13.606029510498047, |
| "learning_rate": 5.916666666666667e-06, |
| "loss": 0.1194, |
| "step": 1310 |
| }, |
| { |
| "epoch": 11.787472035794183, |
| "grad_norm": 13.779529571533203, |
| "learning_rate": 5.876984126984128e-06, |
| "loss": 0.1728, |
| "step": 1320 |
| }, |
| { |
| "epoch": 11.87695749440716, |
| "grad_norm": 10.599024772644043, |
| "learning_rate": 5.8373015873015886e-06, |
| "loss": 0.0797, |
| "step": 1330 |
| }, |
| { |
| "epoch": 11.966442953020135, |
| "grad_norm": 11.666370391845703, |
| "learning_rate": 5.7976190476190485e-06, |
| "loss": 0.1175, |
| "step": 1340 |
| }, |
| { |
| "epoch": 12.0, |
| "eval_loss": 0.6560544967651367, |
| "eval_macro_f1": 0.7722084367245657, |
| "eval_runtime": 65.1441, |
| "eval_samples_per_second": 11.743, |
| "eval_steps_per_second": 1.474, |
| "step": 1344 |
| }, |
| { |
| "epoch": 12.053691275167786, |
| "grad_norm": 12.950461387634277, |
| "learning_rate": 5.7579365079365075e-06, |
| "loss": 0.1042, |
| "step": 1350 |
| }, |
| { |
| "epoch": 12.143176733780761, |
| "grad_norm": 9.609066009521484, |
| "learning_rate": 5.718253968253968e-06, |
| "loss": 0.12, |
| "step": 1360 |
| }, |
| { |
| "epoch": 12.232662192393736, |
| "grad_norm": 23.64732551574707, |
| "learning_rate": 5.678571428571429e-06, |
| "loss": 0.1145, |
| "step": 1370 |
| }, |
| { |
| "epoch": 12.322147651006711, |
| "grad_norm": 32.57529067993164, |
| "learning_rate": 5.638888888888889e-06, |
| "loss": 0.0992, |
| "step": 1380 |
| }, |
| { |
| "epoch": 12.411633109619686, |
| "grad_norm": 7.419304370880127, |
| "learning_rate": 5.59920634920635e-06, |
| "loss": 0.0988, |
| "step": 1390 |
| }, |
| { |
| "epoch": 12.501118568232663, |
| "grad_norm": 6.912314414978027, |
| "learning_rate": 5.5595238095238104e-06, |
| "loss": 0.1157, |
| "step": 1400 |
| }, |
| { |
| "epoch": 12.590604026845638, |
| "grad_norm": 19.71913719177246, |
| "learning_rate": 5.51984126984127e-06, |
| "loss": 0.1478, |
| "step": 1410 |
| }, |
| { |
| "epoch": 12.680089485458613, |
| "grad_norm": 20.64476203918457, |
| "learning_rate": 5.480158730158731e-06, |
| "loss": 0.1196, |
| "step": 1420 |
| }, |
| { |
| "epoch": 12.769574944071588, |
| "grad_norm": 15.437020301818848, |
| "learning_rate": 5.44047619047619e-06, |
| "loss": 0.0766, |
| "step": 1430 |
| }, |
| { |
| "epoch": 12.859060402684564, |
| "grad_norm": 9.825302124023438, |
| "learning_rate": 5.400793650793651e-06, |
| "loss": 0.1254, |
| "step": 1440 |
| }, |
| { |
| "epoch": 12.94854586129754, |
| "grad_norm": 26.381696701049805, |
| "learning_rate": 5.361111111111112e-06, |
| "loss": 0.1025, |
| "step": 1450 |
| }, |
| { |
| "epoch": 13.0, |
| "eval_loss": 0.7549577951431274, |
| "eval_macro_f1": 0.7658037701779237, |
| "eval_runtime": 75.4344, |
| "eval_samples_per_second": 10.141, |
| "eval_steps_per_second": 1.273, |
| "step": 1456 |
| }, |
| { |
| "epoch": 13.03579418344519, |
| "grad_norm": 25.113908767700195, |
| "learning_rate": 5.3214285714285715e-06, |
| "loss": 0.1438, |
| "step": 1460 |
| }, |
| { |
| "epoch": 13.125279642058166, |
| "grad_norm": 10.833968162536621, |
| "learning_rate": 5.281746031746032e-06, |
| "loss": 0.1749, |
| "step": 1470 |
| }, |
| { |
| "epoch": 13.21476510067114, |
| "grad_norm": 22.27955436706543, |
| "learning_rate": 5.242063492063493e-06, |
| "loss": 0.1608, |
| "step": 1480 |
| }, |
| { |
| "epoch": 13.304250559284116, |
| "grad_norm": 15.125386238098145, |
| "learning_rate": 5.202380952380953e-06, |
| "loss": 0.1503, |
| "step": 1490 |
| }, |
| { |
| "epoch": 13.393736017897092, |
| "grad_norm": 3.4376182556152344, |
| "learning_rate": 5.162698412698414e-06, |
| "loss": 0.0819, |
| "step": 1500 |
| }, |
| { |
| "epoch": 13.483221476510067, |
| "grad_norm": 15.98349380493164, |
| "learning_rate": 5.123015873015873e-06, |
| "loss": 0.0837, |
| "step": 1510 |
| }, |
| { |
| "epoch": 13.572706935123042, |
| "grad_norm": 11.065319061279297, |
| "learning_rate": 5.0833333333333335e-06, |
| "loss": 0.1035, |
| "step": 1520 |
| }, |
| { |
| "epoch": 13.662192393736017, |
| "grad_norm": 10.306619644165039, |
| "learning_rate": 5.043650793650794e-06, |
| "loss": 0.1075, |
| "step": 1530 |
| }, |
| { |
| "epoch": 13.751677852348994, |
| "grad_norm": 15.42297077178955, |
| "learning_rate": 5.003968253968254e-06, |
| "loss": 0.1208, |
| "step": 1540 |
| }, |
| { |
| "epoch": 13.841163310961969, |
| "grad_norm": 20.406225204467773, |
| "learning_rate": 4.964285714285715e-06, |
| "loss": 0.1014, |
| "step": 1550 |
| }, |
| { |
| "epoch": 13.930648769574944, |
| "grad_norm": 16.1427059173584, |
| "learning_rate": 4.924603174603176e-06, |
| "loss": 0.1593, |
| "step": 1560 |
| }, |
| { |
| "epoch": 14.0, |
| "eval_loss": 0.7316491007804871, |
| "eval_macro_f1": 0.7694998475634216, |
| "eval_runtime": 69.4982, |
| "eval_samples_per_second": 11.007, |
| "eval_steps_per_second": 1.381, |
| "step": 1568 |
| }, |
| { |
| "epoch": 14.017897091722595, |
| "grad_norm": 9.524744987487793, |
| "learning_rate": 4.8849206349206356e-06, |
| "loss": 0.1199, |
| "step": 1570 |
| }, |
| { |
| "epoch": 14.10738255033557, |
| "grad_norm": 14.937419891357422, |
| "learning_rate": 4.8452380952380955e-06, |
| "loss": 0.1189, |
| "step": 1580 |
| }, |
| { |
| "epoch": 14.196868008948545, |
| "grad_norm": 19.528654098510742, |
| "learning_rate": 4.805555555555556e-06, |
| "loss": 0.1114, |
| "step": 1590 |
| }, |
| { |
| "epoch": 14.286353467561522, |
| "grad_norm": 2.1810483932495117, |
| "learning_rate": 4.765873015873016e-06, |
| "loss": 0.0805, |
| "step": 1600 |
| }, |
| { |
| "epoch": 14.375838926174497, |
| "grad_norm": 5.020853042602539, |
| "learning_rate": 4.726190476190476e-06, |
| "loss": 0.1097, |
| "step": 1610 |
| }, |
| { |
| "epoch": 14.465324384787472, |
| "grad_norm": 12.4754638671875, |
| "learning_rate": 4.686507936507937e-06, |
| "loss": 0.1231, |
| "step": 1620 |
| }, |
| { |
| "epoch": 14.554809843400447, |
| "grad_norm": 25.44110679626465, |
| "learning_rate": 4.6468253968253975e-06, |
| "loss": 0.0903, |
| "step": 1630 |
| }, |
| { |
| "epoch": 14.644295302013422, |
| "grad_norm": 27.849111557006836, |
| "learning_rate": 4.6071428571428574e-06, |
| "loss": 0.0905, |
| "step": 1640 |
| }, |
| { |
| "epoch": 14.733780760626399, |
| "grad_norm": 18.283781051635742, |
| "learning_rate": 4.567460317460317e-06, |
| "loss": 0.0617, |
| "step": 1650 |
| }, |
| { |
| "epoch": 14.823266219239374, |
| "grad_norm": 17.507619857788086, |
| "learning_rate": 4.527777777777778e-06, |
| "loss": 0.13, |
| "step": 1660 |
| }, |
| { |
| "epoch": 14.912751677852349, |
| "grad_norm": 21.756675720214844, |
| "learning_rate": 4.488095238095239e-06, |
| "loss": 0.0926, |
| "step": 1670 |
| }, |
| { |
| "epoch": 15.0, |
| "grad_norm": 19.568700790405273, |
| "learning_rate": 4.448412698412699e-06, |
| "loss": 0.0954, |
| "step": 1680 |
| }, |
| { |
| "epoch": 15.0, |
| "eval_loss": 0.6716505885124207, |
| "eval_macro_f1": 0.7774340887550624, |
| "eval_runtime": 72.4554, |
| "eval_samples_per_second": 10.558, |
| "eval_steps_per_second": 1.325, |
| "step": 1680 |
| }, |
| { |
| "epoch": 15.089485458612975, |
| "grad_norm": 18.1299991607666, |
| "learning_rate": 4.408730158730159e-06, |
| "loss": 0.0678, |
| "step": 1690 |
| }, |
| { |
| "epoch": 15.17897091722595, |
| "grad_norm": 4.439563751220703, |
| "learning_rate": 4.369047619047619e-06, |
| "loss": 0.0767, |
| "step": 1700 |
| }, |
| { |
| "epoch": 15.268456375838927, |
| "grad_norm": 14.997693061828613, |
| "learning_rate": 4.32936507936508e-06, |
| "loss": 0.0664, |
| "step": 1710 |
| }, |
| { |
| "epoch": 15.357941834451902, |
| "grad_norm": 7.552863597869873, |
| "learning_rate": 4.28968253968254e-06, |
| "loss": 0.0842, |
| "step": 1720 |
| }, |
| { |
| "epoch": 15.447427293064877, |
| "grad_norm": 8.728134155273438, |
| "learning_rate": 4.25e-06, |
| "loss": 0.1015, |
| "step": 1730 |
| }, |
| { |
| "epoch": 15.536912751677852, |
| "grad_norm": 11.534658432006836, |
| "learning_rate": 4.210317460317461e-06, |
| "loss": 0.1085, |
| "step": 1740 |
| }, |
| { |
| "epoch": 15.626398210290828, |
| "grad_norm": 22.487648010253906, |
| "learning_rate": 4.1706349206349215e-06, |
| "loss": 0.0993, |
| "step": 1750 |
| }, |
| { |
| "epoch": 15.715883668903803, |
| "grad_norm": 4.885320663452148, |
| "learning_rate": 4.130952380952381e-06, |
| "loss": 0.093, |
| "step": 1760 |
| }, |
| { |
| "epoch": 15.805369127516778, |
| "grad_norm": 16.688884735107422, |
| "learning_rate": 4.091269841269841e-06, |
| "loss": 0.0732, |
| "step": 1770 |
| }, |
| { |
| "epoch": 15.894854586129753, |
| "grad_norm": 30.58871841430664, |
| "learning_rate": 4.051587301587302e-06, |
| "loss": 0.0867, |
| "step": 1780 |
| }, |
| { |
| "epoch": 15.98434004474273, |
| "grad_norm": 17.19178009033203, |
| "learning_rate": 4.011904761904763e-06, |
| "loss": 0.0676, |
| "step": 1790 |
| }, |
| { |
| "epoch": 16.0, |
| "eval_loss": 0.7994140386581421, |
| "eval_macro_f1": 0.7741348066298342, |
| "eval_runtime": 75.3551, |
| "eval_samples_per_second": 10.152, |
| "eval_steps_per_second": 1.274, |
| "step": 1792 |
| }, |
| { |
| "epoch": 16.07158836689038, |
| "grad_norm": 10.005722999572754, |
| "learning_rate": 3.972222222222223e-06, |
| "loss": 0.0858, |
| "step": 1800 |
| }, |
| { |
| "epoch": 16.161073825503355, |
| "grad_norm": 20.64703369140625, |
| "learning_rate": 3.932539682539683e-06, |
| "loss": 0.0836, |
| "step": 1810 |
| }, |
| { |
| "epoch": 16.25055928411633, |
| "grad_norm": 8.218932151794434, |
| "learning_rate": 3.892857142857143e-06, |
| "loss": 0.0969, |
| "step": 1820 |
| }, |
| { |
| "epoch": 16.340044742729308, |
| "grad_norm": 0.8766313195228577, |
| "learning_rate": 3.853174603174604e-06, |
| "loss": 0.0432, |
| "step": 1830 |
| }, |
| { |
| "epoch": 16.42953020134228, |
| "grad_norm": 12.166719436645508, |
| "learning_rate": 3.8134920634920636e-06, |
| "loss": 0.0844, |
| "step": 1840 |
| }, |
| { |
| "epoch": 16.519015659955258, |
| "grad_norm": 8.594962120056152, |
| "learning_rate": 3.773809523809524e-06, |
| "loss": 0.1276, |
| "step": 1850 |
| }, |
| { |
| "epoch": 16.60850111856823, |
| "grad_norm": 2.2263548374176025, |
| "learning_rate": 3.7341269841269846e-06, |
| "loss": 0.0661, |
| "step": 1860 |
| }, |
| { |
| "epoch": 16.697986577181208, |
| "grad_norm": 6.170251846313477, |
| "learning_rate": 3.694444444444445e-06, |
| "loss": 0.1007, |
| "step": 1870 |
| }, |
| { |
| "epoch": 16.787472035794185, |
| "grad_norm": 8.359641075134277, |
| "learning_rate": 3.654761904761905e-06, |
| "loss": 0.0993, |
| "step": 1880 |
| }, |
| { |
| "epoch": 16.876957494407158, |
| "grad_norm": 12.583647727966309, |
| "learning_rate": 3.615079365079365e-06, |
| "loss": 0.0826, |
| "step": 1890 |
| }, |
| { |
| "epoch": 16.966442953020135, |
| "grad_norm": 6.046731948852539, |
| "learning_rate": 3.575396825396826e-06, |
| "loss": 0.0444, |
| "step": 1900 |
| }, |
| { |
| "epoch": 17.0, |
| "eval_loss": 0.747003436088562, |
| "eval_macro_f1": 0.7839196689592837, |
| "eval_runtime": 75.1906, |
| "eval_samples_per_second": 10.174, |
| "eval_steps_per_second": 1.277, |
| "step": 1904 |
| }, |
| { |
| "epoch": 17.053691275167786, |
| "grad_norm": 20.228485107421875, |
| "learning_rate": 3.5357142857142863e-06, |
| "loss": 0.0961, |
| "step": 1910 |
| }, |
| { |
| "epoch": 17.14317673378076, |
| "grad_norm": 26.031396865844727, |
| "learning_rate": 3.496031746031746e-06, |
| "loss": 0.0873, |
| "step": 1920 |
| }, |
| { |
| "epoch": 17.232662192393736, |
| "grad_norm": 12.642768859863281, |
| "learning_rate": 3.4563492063492065e-06, |
| "loss": 0.1064, |
| "step": 1930 |
| }, |
| { |
| "epoch": 17.322147651006713, |
| "grad_norm": 18.097814559936523, |
| "learning_rate": 3.416666666666667e-06, |
| "loss": 0.0768, |
| "step": 1940 |
| }, |
| { |
| "epoch": 17.411633109619686, |
| "grad_norm": 10.280755043029785, |
| "learning_rate": 3.3769841269841276e-06, |
| "loss": 0.1336, |
| "step": 1950 |
| }, |
| { |
| "epoch": 17.501118568232663, |
| "grad_norm": 11.690203666687012, |
| "learning_rate": 3.3373015873015875e-06, |
| "loss": 0.0707, |
| "step": 1960 |
| }, |
| { |
| "epoch": 17.59060402684564, |
| "grad_norm": 22.514507293701172, |
| "learning_rate": 3.297619047619048e-06, |
| "loss": 0.1073, |
| "step": 1970 |
| }, |
| { |
| "epoch": 17.680089485458613, |
| "grad_norm": 10.396025657653809, |
| "learning_rate": 3.257936507936508e-06, |
| "loss": 0.0543, |
| "step": 1980 |
| }, |
| { |
| "epoch": 17.76957494407159, |
| "grad_norm": 12.947179794311523, |
| "learning_rate": 3.218253968253969e-06, |
| "loss": 0.0768, |
| "step": 1990 |
| }, |
| { |
| "epoch": 17.859060402684563, |
| "grad_norm": 2.5873477458953857, |
| "learning_rate": 3.178571428571429e-06, |
| "loss": 0.0766, |
| "step": 2000 |
| }, |
| { |
| "epoch": 17.94854586129754, |
| "grad_norm": 6.163917064666748, |
| "learning_rate": 3.138888888888889e-06, |
| "loss": 0.0455, |
| "step": 2010 |
| }, |
| { |
| "epoch": 18.0, |
| "eval_loss": 0.8047569990158081, |
| "eval_macro_f1": 0.7781014378358804, |
| "eval_runtime": 66.3878, |
| "eval_samples_per_second": 11.523, |
| "eval_steps_per_second": 1.446, |
| "step": 2016 |
| }, |
| { |
| "epoch": 18.03579418344519, |
| "grad_norm": 4.654578685760498, |
| "learning_rate": 3.0992063492063495e-06, |
| "loss": 0.0684, |
| "step": 2020 |
| }, |
| { |
| "epoch": 18.125279642058164, |
| "grad_norm": 1.1822065114974976, |
| "learning_rate": 3.05952380952381e-06, |
| "loss": 0.0961, |
| "step": 2030 |
| }, |
| { |
| "epoch": 18.21476510067114, |
| "grad_norm": 21.223234176635742, |
| "learning_rate": 3.0198412698412697e-06, |
| "loss": 0.1265, |
| "step": 2040 |
| }, |
| { |
| "epoch": 18.304250559284117, |
| "grad_norm": 12.335346221923828, |
| "learning_rate": 2.9801587301587305e-06, |
| "loss": 0.1095, |
| "step": 2050 |
| }, |
| { |
| "epoch": 18.39373601789709, |
| "grad_norm": 4.7988715171813965, |
| "learning_rate": 2.9404761904761908e-06, |
| "loss": 0.0944, |
| "step": 2060 |
| }, |
| { |
| "epoch": 18.483221476510067, |
| "grad_norm": 28.275365829467773, |
| "learning_rate": 2.900793650793651e-06, |
| "loss": 0.0549, |
| "step": 2070 |
| }, |
| { |
| "epoch": 18.572706935123044, |
| "grad_norm": 7.988637447357178, |
| "learning_rate": 2.861111111111111e-06, |
| "loss": 0.0881, |
| "step": 2080 |
| }, |
| { |
| "epoch": 18.662192393736017, |
| "grad_norm": 9.342594146728516, |
| "learning_rate": 2.8214285714285718e-06, |
| "loss": 0.0528, |
| "step": 2090 |
| }, |
| { |
| "epoch": 18.751677852348994, |
| "grad_norm": 12.687505722045898, |
| "learning_rate": 2.781746031746032e-06, |
| "loss": 0.0711, |
| "step": 2100 |
| }, |
| { |
| "epoch": 18.841163310961967, |
| "grad_norm": 7.692240238189697, |
| "learning_rate": 2.7420634920634924e-06, |
| "loss": 0.072, |
| "step": 2110 |
| }, |
| { |
| "epoch": 18.930648769574944, |
| "grad_norm": 14.148133277893066, |
| "learning_rate": 2.7023809523809523e-06, |
| "loss": 0.0677, |
| "step": 2120 |
| }, |
| { |
| "epoch": 19.0, |
| "eval_loss": 0.8003770709037781, |
| "eval_macro_f1": 0.766772035108551, |
| "eval_runtime": 25.3025, |
| "eval_samples_per_second": 30.234, |
| "eval_steps_per_second": 3.794, |
| "step": 2128 |
| }, |
| { |
| "epoch": 19.017897091722595, |
| "grad_norm": 17.935680389404297, |
| "learning_rate": 2.662698412698413e-06, |
| "loss": 0.0416, |
| "step": 2130 |
| }, |
| { |
| "epoch": 19.107382550335572, |
| "grad_norm": 7.1221537590026855, |
| "learning_rate": 2.6230158730158734e-06, |
| "loss": 0.1003, |
| "step": 2140 |
| }, |
| { |
| "epoch": 19.196868008948545, |
| "grad_norm": 17.375965118408203, |
| "learning_rate": 2.5833333333333337e-06, |
| "loss": 0.0854, |
| "step": 2150 |
| }, |
| { |
| "epoch": 19.286353467561522, |
| "grad_norm": 13.114810943603516, |
| "learning_rate": 2.5436507936507936e-06, |
| "loss": 0.0759, |
| "step": 2160 |
| }, |
| { |
| "epoch": 19.375838926174495, |
| "grad_norm": 20.650806427001953, |
| "learning_rate": 2.503968253968254e-06, |
| "loss": 0.0576, |
| "step": 2170 |
| }, |
| { |
| "epoch": 19.465324384787472, |
| "grad_norm": 1.7908034324645996, |
| "learning_rate": 2.4642857142857147e-06, |
| "loss": 0.0314, |
| "step": 2180 |
| }, |
| { |
| "epoch": 19.55480984340045, |
| "grad_norm": 15.814742088317871, |
| "learning_rate": 2.4246031746031746e-06, |
| "loss": 0.0754, |
| "step": 2190 |
| }, |
| { |
| "epoch": 19.644295302013422, |
| "grad_norm": 18.996606826782227, |
| "learning_rate": 2.3849206349206354e-06, |
| "loss": 0.0502, |
| "step": 2200 |
| }, |
| { |
| "epoch": 19.7337807606264, |
| "grad_norm": 24.4049015045166, |
| "learning_rate": 2.3452380952380953e-06, |
| "loss": 0.0502, |
| "step": 2210 |
| }, |
| { |
| "epoch": 19.823266219239372, |
| "grad_norm": 6.1143879890441895, |
| "learning_rate": 2.305555555555556e-06, |
| "loss": 0.054, |
| "step": 2220 |
| }, |
| { |
| "epoch": 19.91275167785235, |
| "grad_norm": 12.98304557800293, |
| "learning_rate": 2.265873015873016e-06, |
| "loss": 0.0737, |
| "step": 2230 |
| }, |
| { |
| "epoch": 20.0, |
| "grad_norm": 0.3279534876346588, |
| "learning_rate": 2.2261904761904763e-06, |
| "loss": 0.0353, |
| "step": 2240 |
| }, |
| { |
| "epoch": 20.0, |
| "eval_loss": 0.8695369958877563, |
| "eval_macro_f1": 0.7699478748997595, |
| "eval_runtime": 25.1606, |
| "eval_samples_per_second": 30.405, |
| "eval_steps_per_second": 3.815, |
| "step": 2240 |
| }, |
| { |
| "epoch": 20.089485458612977, |
| "grad_norm": 5.161200523376465, |
| "learning_rate": 2.1865079365079366e-06, |
| "loss": 0.0489, |
| "step": 2250 |
| }, |
| { |
| "epoch": 20.17897091722595, |
| "grad_norm": 24.046892166137695, |
| "learning_rate": 2.146825396825397e-06, |
| "loss": 0.0887, |
| "step": 2260 |
| }, |
| { |
| "epoch": 20.268456375838927, |
| "grad_norm": 3.9411873817443848, |
| "learning_rate": 2.1071428571428572e-06, |
| "loss": 0.0804, |
| "step": 2270 |
| }, |
| { |
| "epoch": 20.3579418344519, |
| "grad_norm": 12.20919418334961, |
| "learning_rate": 2.0674603174603176e-06, |
| "loss": 0.0318, |
| "step": 2280 |
| }, |
| { |
| "epoch": 20.447427293064877, |
| "grad_norm": 5.021272659301758, |
| "learning_rate": 2.027777777777778e-06, |
| "loss": 0.0983, |
| "step": 2290 |
| }, |
| { |
| "epoch": 20.536912751677853, |
| "grad_norm": 15.741971969604492, |
| "learning_rate": 1.9880952380952382e-06, |
| "loss": 0.0335, |
| "step": 2300 |
| }, |
| { |
| "epoch": 20.626398210290827, |
| "grad_norm": 16.82331085205078, |
| "learning_rate": 1.9484126984126985e-06, |
| "loss": 0.0744, |
| "step": 2310 |
| }, |
| { |
| "epoch": 20.715883668903803, |
| "grad_norm": 0.5343822240829468, |
| "learning_rate": 1.908730158730159e-06, |
| "loss": 0.0432, |
| "step": 2320 |
| }, |
| { |
| "epoch": 20.80536912751678, |
| "grad_norm": 18.707128524780273, |
| "learning_rate": 1.8690476190476192e-06, |
| "loss": 0.0517, |
| "step": 2330 |
| }, |
| { |
| "epoch": 20.894854586129753, |
| "grad_norm": 10.502820014953613, |
| "learning_rate": 1.8293650793650793e-06, |
| "loss": 0.0596, |
| "step": 2340 |
| }, |
| { |
| "epoch": 20.98434004474273, |
| "grad_norm": 3.260993242263794, |
| "learning_rate": 1.7896825396825399e-06, |
| "loss": 0.0262, |
| "step": 2350 |
| }, |
| { |
| "epoch": 21.0, |
| "eval_loss": 0.8509567975997925, |
| "eval_macro_f1": 0.7710241615578796, |
| "eval_runtime": 21.2423, |
| "eval_samples_per_second": 36.013, |
| "eval_steps_per_second": 4.519, |
| "step": 2352 |
| }, |
| { |
| "epoch": 21.07158836689038, |
| "grad_norm": 21.054967880249023, |
| "learning_rate": 1.75e-06, |
| "loss": 0.0623, |
| "step": 2360 |
| }, |
| { |
| "epoch": 21.161073825503355, |
| "grad_norm": 7.076012134552002, |
| "learning_rate": 1.7103174603174605e-06, |
| "loss": 0.0567, |
| "step": 2370 |
| }, |
| { |
| "epoch": 21.25055928411633, |
| "grad_norm": 9.261219024658203, |
| "learning_rate": 1.6706349206349206e-06, |
| "loss": 0.0805, |
| "step": 2380 |
| }, |
| { |
| "epoch": 21.340044742729308, |
| "grad_norm": 21.940967559814453, |
| "learning_rate": 1.6309523809523812e-06, |
| "loss": 0.062, |
| "step": 2390 |
| }, |
| { |
| "epoch": 21.42953020134228, |
| "grad_norm": 0.5533654093742371, |
| "learning_rate": 1.5912698412698413e-06, |
| "loss": 0.0443, |
| "step": 2400 |
| }, |
| { |
| "epoch": 21.519015659955258, |
| "grad_norm": 1.7748634815216064, |
| "learning_rate": 1.5515873015873018e-06, |
| "loss": 0.0465, |
| "step": 2410 |
| }, |
| { |
| "epoch": 21.60850111856823, |
| "grad_norm": 14.389286994934082, |
| "learning_rate": 1.511904761904762e-06, |
| "loss": 0.0426, |
| "step": 2420 |
| }, |
| { |
| "epoch": 21.697986577181208, |
| "grad_norm": 0.1624564379453659, |
| "learning_rate": 1.4722222222222225e-06, |
| "loss": 0.0399, |
| "step": 2430 |
| }, |
| { |
| "epoch": 21.787472035794185, |
| "grad_norm": 16.362260818481445, |
| "learning_rate": 1.4325396825396826e-06, |
| "loss": 0.0737, |
| "step": 2440 |
| }, |
| { |
| "epoch": 21.876957494407158, |
| "grad_norm": 9.44295883178711, |
| "learning_rate": 1.392857142857143e-06, |
| "loss": 0.1062, |
| "step": 2450 |
| }, |
| { |
| "epoch": 21.966442953020135, |
| "grad_norm": 12.541874885559082, |
| "learning_rate": 1.3531746031746033e-06, |
| "loss": 0.0628, |
| "step": 2460 |
| }, |
| { |
| "epoch": 22.0, |
| "eval_loss": 0.8052472472190857, |
| "eval_macro_f1": 0.7966146756469337, |
| "eval_runtime": 25.2623, |
| "eval_samples_per_second": 30.282, |
| "eval_steps_per_second": 3.8, |
| "step": 2464 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 2800, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 25, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.8247393356405015e+19, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
