|
{ |
|
"best_metric": 0.9892592592592593, |
|
"best_model_checkpoint": "swinv2-small-patch4-window16-256-finetuned-eurosat/checkpoint-1265", |
|
"epoch": 4.9990128331688055, |
|
"global_step": 1265, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 3.952569169960475e-06, |
|
"loss": 2.3985, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 7.90513833992095e-06, |
|
"loss": 2.3159, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 1.1857707509881423e-05, |
|
"loss": 2.1587, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 1.58102766798419e-05, |
|
"loss": 1.8862, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 1.9762845849802372e-05, |
|
"loss": 1.4084, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 2.3715415019762845e-05, |
|
"loss": 0.8373, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.28, |
|
"learning_rate": 2.766798418972332e-05, |
|
"loss": 0.5612, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 3.16205533596838e-05, |
|
"loss": 0.483, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.557312252964427e-05, |
|
"loss": 0.361, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.39, |
|
"learning_rate": 3.9525691699604744e-05, |
|
"loss": 0.3518, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.347826086956522e-05, |
|
"loss": 0.3125, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.47, |
|
"learning_rate": 4.743083003952569e-05, |
|
"loss": 0.3053, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.51, |
|
"learning_rate": 5.138339920948617e-05, |
|
"loss": 0.291, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.55, |
|
"learning_rate": 5.533596837944664e-05, |
|
"loss": 0.2977, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.59, |
|
"learning_rate": 5.928853754940712e-05, |
|
"loss": 0.3152, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 6.32411067193676e-05, |
|
"loss": 0.3344, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 6.719367588932807e-05, |
|
"loss": 0.304, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 7.114624505928854e-05, |
|
"loss": 0.2897, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 7.509881422924901e-05, |
|
"loss": 0.2128, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 7.905138339920949e-05, |
|
"loss": 0.2161, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 8.300395256916996e-05, |
|
"loss": 0.2273, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.87, |
|
"learning_rate": 8.695652173913044e-05, |
|
"loss": 0.2824, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.91, |
|
"learning_rate": 9.090909090909092e-05, |
|
"loss": 0.2307, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.95, |
|
"learning_rate": 9.486166007905138e-05, |
|
"loss": 0.2615, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 9.881422924901186e-05, |
|
"loss": 0.2326, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.9714814814814815, |
|
"eval_f1": 0.9715764538635164, |
|
"eval_loss": 0.08702292293310165, |
|
"eval_precision": 0.9719745362775079, |
|
"eval_recall": 0.9714814814814815, |
|
"eval_runtime": 47.1052, |
|
"eval_samples_per_second": 57.319, |
|
"eval_steps_per_second": 2.399, |
|
"step": 253 |
|
}, |
|
{ |
|
"epoch": 1.03, |
|
"learning_rate": 9.930830039525692e-05, |
|
"loss": 0.2224, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 9.832015810276681e-05, |
|
"loss": 0.2211, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 1.11, |
|
"learning_rate": 9.73320158102767e-05, |
|
"loss": 0.2459, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 1.15, |
|
"learning_rate": 9.634387351778657e-05, |
|
"loss": 0.2155, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 1.19, |
|
"learning_rate": 9.535573122529646e-05, |
|
"loss": 0.2328, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.23, |
|
"learning_rate": 9.436758893280633e-05, |
|
"loss": 0.2663, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 1.26, |
|
"learning_rate": 9.337944664031622e-05, |
|
"loss": 0.1832, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 1.3, |
|
"learning_rate": 9.239130434782609e-05, |
|
"loss": 0.2021, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 1.34, |
|
"learning_rate": 9.140316205533598e-05, |
|
"loss": 0.1731, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 1.38, |
|
"learning_rate": 9.041501976284585e-05, |
|
"loss": 0.1652, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 8.942687747035574e-05, |
|
"loss": 0.1945, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 1.46, |
|
"learning_rate": 8.843873517786562e-05, |
|
"loss": 0.1779, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 1.5, |
|
"learning_rate": 8.745059288537549e-05, |
|
"loss": 0.2328, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 1.54, |
|
"learning_rate": 8.646245059288538e-05, |
|
"loss": 0.134, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 1.58, |
|
"learning_rate": 8.547430830039525e-05, |
|
"loss": 0.2235, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 1.62, |
|
"learning_rate": 8.448616600790514e-05, |
|
"loss": 0.1912, |
|
"step": 410 |
|
}, |
|
{ |
|
"epoch": 1.66, |
|
"learning_rate": 8.349802371541501e-05, |
|
"loss": 0.1949, |
|
"step": 420 |
|
}, |
|
{ |
|
"epoch": 1.7, |
|
"learning_rate": 8.25098814229249e-05, |
|
"loss": 0.2259, |
|
"step": 430 |
|
}, |
|
{ |
|
"epoch": 1.74, |
|
"learning_rate": 8.152173913043478e-05, |
|
"loss": 0.1537, |
|
"step": 440 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"learning_rate": 8.053359683794466e-05, |
|
"loss": 0.1948, |
|
"step": 450 |
|
}, |
|
{ |
|
"epoch": 1.82, |
|
"learning_rate": 7.954545454545455e-05, |
|
"loss": 0.1639, |
|
"step": 460 |
|
}, |
|
{ |
|
"epoch": 1.86, |
|
"learning_rate": 7.855731225296444e-05, |
|
"loss": 0.1703, |
|
"step": 470 |
|
}, |
|
{ |
|
"epoch": 1.9, |
|
"learning_rate": 7.756916996047431e-05, |
|
"loss": 0.2037, |
|
"step": 480 |
|
}, |
|
{ |
|
"epoch": 1.94, |
|
"learning_rate": 7.65810276679842e-05, |
|
"loss": 0.1894, |
|
"step": 490 |
|
}, |
|
{ |
|
"epoch": 1.98, |
|
"learning_rate": 7.559288537549407e-05, |
|
"loss": 0.1955, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.9788888888888889, |
|
"eval_f1": 0.9788325259364008, |
|
"eval_loss": 0.05759148672223091, |
|
"eval_precision": 0.9794411747058277, |
|
"eval_recall": 0.9788888888888889, |
|
"eval_runtime": 47.0432, |
|
"eval_samples_per_second": 57.394, |
|
"eval_steps_per_second": 2.402, |
|
"step": 506 |
|
}, |
|
{ |
|
"epoch": 2.02, |
|
"learning_rate": 7.460474308300396e-05, |
|
"loss": 0.1479, |
|
"step": 510 |
|
}, |
|
{ |
|
"epoch": 2.06, |
|
"learning_rate": 7.361660079051384e-05, |
|
"loss": 0.1269, |
|
"step": 520 |
|
}, |
|
{ |
|
"epoch": 2.09, |
|
"learning_rate": 7.262845849802372e-05, |
|
"loss": 0.1617, |
|
"step": 530 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 7.16403162055336e-05, |
|
"loss": 0.1737, |
|
"step": 540 |
|
}, |
|
{ |
|
"epoch": 2.17, |
|
"learning_rate": 7.065217391304349e-05, |
|
"loss": 0.1311, |
|
"step": 550 |
|
}, |
|
{ |
|
"epoch": 2.21, |
|
"learning_rate": 6.966403162055336e-05, |
|
"loss": 0.1814, |
|
"step": 560 |
|
}, |
|
{ |
|
"epoch": 2.25, |
|
"learning_rate": 6.867588932806325e-05, |
|
"loss": 0.1353, |
|
"step": 570 |
|
}, |
|
{ |
|
"epoch": 2.29, |
|
"learning_rate": 6.768774703557312e-05, |
|
"loss": 0.155, |
|
"step": 580 |
|
}, |
|
{ |
|
"epoch": 2.33, |
|
"learning_rate": 6.669960474308301e-05, |
|
"loss": 0.1355, |
|
"step": 590 |
|
}, |
|
{ |
|
"epoch": 2.37, |
|
"learning_rate": 6.571146245059288e-05, |
|
"loss": 0.1412, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 2.41, |
|
"learning_rate": 6.472332015810277e-05, |
|
"loss": 0.0878, |
|
"step": 610 |
|
}, |
|
{ |
|
"epoch": 2.45, |
|
"learning_rate": 6.373517786561265e-05, |
|
"loss": 0.1964, |
|
"step": 620 |
|
}, |
|
{ |
|
"epoch": 2.49, |
|
"learning_rate": 6.274703557312253e-05, |
|
"loss": 0.1532, |
|
"step": 630 |
|
}, |
|
{ |
|
"epoch": 2.53, |
|
"learning_rate": 6.175889328063241e-05, |
|
"loss": 0.1535, |
|
"step": 640 |
|
}, |
|
{ |
|
"epoch": 2.57, |
|
"learning_rate": 6.07707509881423e-05, |
|
"loss": 0.1217, |
|
"step": 650 |
|
}, |
|
{ |
|
"epoch": 2.61, |
|
"learning_rate": 5.9782608695652175e-05, |
|
"loss": 0.1091, |
|
"step": 660 |
|
}, |
|
{ |
|
"epoch": 2.65, |
|
"learning_rate": 5.879446640316206e-05, |
|
"loss": 0.1395, |
|
"step": 670 |
|
}, |
|
{ |
|
"epoch": 2.69, |
|
"learning_rate": 5.780632411067194e-05, |
|
"loss": 0.1109, |
|
"step": 680 |
|
}, |
|
{ |
|
"epoch": 2.73, |
|
"learning_rate": 5.6818181818181825e-05, |
|
"loss": 0.1431, |
|
"step": 690 |
|
}, |
|
{ |
|
"epoch": 2.77, |
|
"learning_rate": 5.58300395256917e-05, |
|
"loss": 0.1237, |
|
"step": 700 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 5.484189723320159e-05, |
|
"loss": 0.1467, |
|
"step": 710 |
|
}, |
|
{ |
|
"epoch": 2.85, |
|
"learning_rate": 5.385375494071147e-05, |
|
"loss": 0.1581, |
|
"step": 720 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 5.286561264822134e-05, |
|
"loss": 0.1511, |
|
"step": 730 |
|
}, |
|
{ |
|
"epoch": 2.92, |
|
"learning_rate": 5.187747035573123e-05, |
|
"loss": 0.1526, |
|
"step": 740 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 5.0889328063241103e-05, |
|
"loss": 0.1229, |
|
"step": 750 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.9837037037037037, |
|
"eval_f1": 0.9837109627392333, |
|
"eval_loss": 0.04496677964925766, |
|
"eval_precision": 0.983912783675654, |
|
"eval_recall": 0.9837037037037037, |
|
"eval_runtime": 46.9155, |
|
"eval_samples_per_second": 57.55, |
|
"eval_steps_per_second": 2.409, |
|
"step": 759 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 4.990118577075099e-05, |
|
"loss": 0.1399, |
|
"step": 760 |
|
}, |
|
{ |
|
"epoch": 3.04, |
|
"learning_rate": 4.891304347826087e-05, |
|
"loss": 0.168, |
|
"step": 770 |
|
}, |
|
{ |
|
"epoch": 3.08, |
|
"learning_rate": 4.792490118577075e-05, |
|
"loss": 0.081, |
|
"step": 780 |
|
}, |
|
{ |
|
"epoch": 3.12, |
|
"learning_rate": 4.6936758893280634e-05, |
|
"loss": 0.1218, |
|
"step": 790 |
|
}, |
|
{ |
|
"epoch": 3.16, |
|
"learning_rate": 4.5948616600790515e-05, |
|
"loss": 0.1144, |
|
"step": 800 |
|
}, |
|
{ |
|
"epoch": 3.2, |
|
"learning_rate": 4.4960474308300396e-05, |
|
"loss": 0.1295, |
|
"step": 810 |
|
}, |
|
{ |
|
"epoch": 3.24, |
|
"learning_rate": 4.397233201581028e-05, |
|
"loss": 0.0932, |
|
"step": 820 |
|
}, |
|
{ |
|
"epoch": 3.28, |
|
"learning_rate": 4.2984189723320164e-05, |
|
"loss": 0.0997, |
|
"step": 830 |
|
}, |
|
{ |
|
"epoch": 3.32, |
|
"learning_rate": 4.1996047430830045e-05, |
|
"loss": 0.0813, |
|
"step": 840 |
|
}, |
|
{ |
|
"epoch": 3.36, |
|
"learning_rate": 4.1007905138339926e-05, |
|
"loss": 0.0852, |
|
"step": 850 |
|
}, |
|
{ |
|
"epoch": 3.4, |
|
"learning_rate": 4.001976284584981e-05, |
|
"loss": 0.1327, |
|
"step": 860 |
|
}, |
|
{ |
|
"epoch": 3.44, |
|
"learning_rate": 3.903162055335969e-05, |
|
"loss": 0.1208, |
|
"step": 870 |
|
}, |
|
{ |
|
"epoch": 3.48, |
|
"learning_rate": 3.804347826086957e-05, |
|
"loss": 0.1348, |
|
"step": 880 |
|
}, |
|
{ |
|
"epoch": 3.52, |
|
"learning_rate": 3.705533596837945e-05, |
|
"loss": 0.0916, |
|
"step": 890 |
|
}, |
|
{ |
|
"epoch": 3.56, |
|
"learning_rate": 3.606719367588933e-05, |
|
"loss": 0.1281, |
|
"step": 900 |
|
}, |
|
{ |
|
"epoch": 3.6, |
|
"learning_rate": 3.507905138339921e-05, |
|
"loss": 0.1211, |
|
"step": 910 |
|
}, |
|
{ |
|
"epoch": 3.64, |
|
"learning_rate": 3.409090909090909e-05, |
|
"loss": 0.1056, |
|
"step": 920 |
|
}, |
|
{ |
|
"epoch": 3.68, |
|
"learning_rate": 3.310276679841897e-05, |
|
"loss": 0.114, |
|
"step": 930 |
|
}, |
|
{ |
|
"epoch": 3.71, |
|
"learning_rate": 3.2114624505928854e-05, |
|
"loss": 0.1107, |
|
"step": 940 |
|
}, |
|
{ |
|
"epoch": 3.75, |
|
"learning_rate": 3.1126482213438735e-05, |
|
"loss": 0.1094, |
|
"step": 950 |
|
}, |
|
{ |
|
"epoch": 3.79, |
|
"learning_rate": 3.0138339920948616e-05, |
|
"loss": 0.1125, |
|
"step": 960 |
|
}, |
|
{ |
|
"epoch": 3.83, |
|
"learning_rate": 2.9150197628458497e-05, |
|
"loss": 0.0943, |
|
"step": 970 |
|
}, |
|
{ |
|
"epoch": 3.87, |
|
"learning_rate": 2.8162055335968378e-05, |
|
"loss": 0.0849, |
|
"step": 980 |
|
}, |
|
{ |
|
"epoch": 3.91, |
|
"learning_rate": 2.7173913043478262e-05, |
|
"loss": 0.0829, |
|
"step": 990 |
|
}, |
|
{ |
|
"epoch": 3.95, |
|
"learning_rate": 2.6185770750988143e-05, |
|
"loss": 0.1144, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 3.99, |
|
"learning_rate": 2.5197628458498024e-05, |
|
"loss": 0.0797, |
|
"step": 1010 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_accuracy": 0.9888888888888889, |
|
"eval_f1": 0.9888916751728891, |
|
"eval_loss": 0.03322984650731087, |
|
"eval_precision": 0.988925059432856, |
|
"eval_recall": 0.9888888888888889, |
|
"eval_runtime": 47.2107, |
|
"eval_samples_per_second": 57.19, |
|
"eval_steps_per_second": 2.394, |
|
"step": 1012 |
|
}, |
|
{ |
|
"epoch": 4.03, |
|
"learning_rate": 2.4209486166007905e-05, |
|
"loss": 0.1276, |
|
"step": 1020 |
|
}, |
|
{ |
|
"epoch": 4.07, |
|
"learning_rate": 2.3221343873517785e-05, |
|
"loss": 0.1045, |
|
"step": 1030 |
|
}, |
|
{ |
|
"epoch": 4.11, |
|
"learning_rate": 2.223320158102767e-05, |
|
"loss": 0.1008, |
|
"step": 1040 |
|
}, |
|
{ |
|
"epoch": 4.15, |
|
"learning_rate": 2.124505928853755e-05, |
|
"loss": 0.0893, |
|
"step": 1050 |
|
}, |
|
{ |
|
"epoch": 4.19, |
|
"learning_rate": 2.025691699604743e-05, |
|
"loss": 0.0833, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 4.23, |
|
"learning_rate": 1.9268774703557312e-05, |
|
"loss": 0.0982, |
|
"step": 1070 |
|
}, |
|
{ |
|
"epoch": 4.27, |
|
"learning_rate": 1.8280632411067193e-05, |
|
"loss": 0.1158, |
|
"step": 1080 |
|
}, |
|
{ |
|
"epoch": 4.31, |
|
"learning_rate": 1.7292490118577078e-05, |
|
"loss": 0.1044, |
|
"step": 1090 |
|
}, |
|
{ |
|
"epoch": 4.35, |
|
"learning_rate": 1.630434782608696e-05, |
|
"loss": 0.0834, |
|
"step": 1100 |
|
}, |
|
{ |
|
"epoch": 4.39, |
|
"learning_rate": 1.531620553359684e-05, |
|
"loss": 0.0667, |
|
"step": 1110 |
|
}, |
|
{ |
|
"epoch": 4.43, |
|
"learning_rate": 1.432806324110672e-05, |
|
"loss": 0.0621, |
|
"step": 1120 |
|
}, |
|
{ |
|
"epoch": 4.47, |
|
"learning_rate": 1.3339920948616603e-05, |
|
"loss": 0.078, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 4.51, |
|
"learning_rate": 1.2351778656126482e-05, |
|
"loss": 0.0808, |
|
"step": 1140 |
|
}, |
|
{ |
|
"epoch": 4.54, |
|
"learning_rate": 1.1363636363636365e-05, |
|
"loss": 0.0669, |
|
"step": 1150 |
|
}, |
|
{ |
|
"epoch": 4.58, |
|
"learning_rate": 1.0375494071146246e-05, |
|
"loss": 0.0804, |
|
"step": 1160 |
|
}, |
|
{ |
|
"epoch": 4.62, |
|
"learning_rate": 9.387351778656126e-06, |
|
"loss": 0.0764, |
|
"step": 1170 |
|
}, |
|
{ |
|
"epoch": 4.66, |
|
"learning_rate": 8.399209486166009e-06, |
|
"loss": 0.0862, |
|
"step": 1180 |
|
}, |
|
{ |
|
"epoch": 4.7, |
|
"learning_rate": 7.41106719367589e-06, |
|
"loss": 0.107, |
|
"step": 1190 |
|
}, |
|
{ |
|
"epoch": 4.74, |
|
"learning_rate": 6.422924901185772e-06, |
|
"loss": 0.1063, |
|
"step": 1200 |
|
}, |
|
{ |
|
"epoch": 4.78, |
|
"learning_rate": 5.4347826086956525e-06, |
|
"loss": 0.1053, |
|
"step": 1210 |
|
}, |
|
{ |
|
"epoch": 4.82, |
|
"learning_rate": 4.4466403162055334e-06, |
|
"loss": 0.079, |
|
"step": 1220 |
|
}, |
|
{ |
|
"epoch": 4.86, |
|
"learning_rate": 3.458498023715415e-06, |
|
"loss": 0.0722, |
|
"step": 1230 |
|
}, |
|
{ |
|
"epoch": 4.9, |
|
"learning_rate": 2.4703557312252965e-06, |
|
"loss": 0.1076, |
|
"step": 1240 |
|
}, |
|
{ |
|
"epoch": 4.94, |
|
"learning_rate": 1.4822134387351778e-06, |
|
"loss": 0.1046, |
|
"step": 1250 |
|
}, |
|
{ |
|
"epoch": 4.98, |
|
"learning_rate": 4.940711462450593e-07, |
|
"loss": 0.0826, |
|
"step": 1260 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_accuracy": 0.9892592592592593, |
|
"eval_f1": 0.9892542163878574, |
|
"eval_loss": 0.032755617052316666, |
|
"eval_precision": 0.9892896521886161, |
|
"eval_recall": 0.9892592592592593, |
|
"eval_runtime": 46.8779, |
|
"eval_samples_per_second": 57.596, |
|
"eval_steps_per_second": 2.411, |
|
"step": 1265 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"step": 1265, |
|
"total_flos": 7.01762688127284e+18, |
|
"train_loss": 0.24173720938414925, |
|
"train_runtime": 5910.6077, |
|
"train_samples_per_second": 20.556, |
|
"train_steps_per_second": 0.214 |
|
} |
|
], |
|
"max_steps": 1265, |
|
"num_train_epochs": 5, |
|
"total_flos": 7.01762688127284e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|