{ "best_metric": 0.4911738417994935, "best_model_checkpoint": "convnext-tiny-224_album_vit/checkpoint-2832", "epoch": 3.0, "global_step": 2832, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.7605633802816904e-06, "loss": 5.9445, "step": 10 }, { "epoch": 0.02, "learning_rate": 3.521126760563381e-06, "loss": 5.9461, "step": 20 }, { "epoch": 0.03, "learning_rate": 5.28169014084507e-06, "loss": 5.9367, "step": 30 }, { "epoch": 0.04, "learning_rate": 7.042253521126762e-06, "loss": 5.9287, "step": 40 }, { "epoch": 0.05, "learning_rate": 8.802816901408451e-06, "loss": 5.9162, "step": 50 }, { "epoch": 0.06, "learning_rate": 1.056338028169014e-05, "loss": 5.9084, "step": 60 }, { "epoch": 0.07, "learning_rate": 1.2323943661971832e-05, "loss": 5.8957, "step": 70 }, { "epoch": 0.08, "learning_rate": 1.4084507042253523e-05, "loss": 5.8748, "step": 80 }, { "epoch": 0.1, "learning_rate": 1.5845070422535213e-05, "loss": 5.8597, "step": 90 }, { "epoch": 0.11, "learning_rate": 1.7605633802816902e-05, "loss": 5.8312, "step": 100 }, { "epoch": 0.12, "learning_rate": 1.9366197183098592e-05, "loss": 5.7844, "step": 110 }, { "epoch": 0.13, "learning_rate": 2.112676056338028e-05, "loss": 5.7469, "step": 120 }, { "epoch": 0.14, "learning_rate": 2.2887323943661974e-05, "loss": 5.6846, "step": 130 }, { "epoch": 0.15, "learning_rate": 2.4647887323943664e-05, "loss": 5.6204, "step": 140 }, { "epoch": 0.16, "learning_rate": 2.640845070422535e-05, "loss": 5.5601, "step": 150 }, { "epoch": 0.17, "learning_rate": 2.8169014084507046e-05, "loss": 5.5053, "step": 160 }, { "epoch": 0.18, "learning_rate": 2.9929577464788733e-05, "loss": 5.4203, "step": 170 }, { "epoch": 0.19, "learning_rate": 3.1690140845070426e-05, "loss": 5.3959, "step": 180 }, { "epoch": 0.2, "learning_rate": 3.345070422535211e-05, "loss": 5.369, "step": 190 }, { "epoch": 0.21, "learning_rate": 3.5211267605633805e-05, "loss": 5.319, "step": 200 }, { "epoch": 0.22, "learning_rate": 3.69718309859155e-05, "loss": 5.363, "step": 210 }, { "epoch": 0.23, "learning_rate": 3.8732394366197184e-05, "loss": 5.2891, "step": 220 }, { "epoch": 0.24, "learning_rate": 4.049295774647888e-05, "loss": 5.2756, "step": 230 }, { "epoch": 0.25, "learning_rate": 4.225352112676056e-05, "loss": 5.2821, "step": 240 }, { "epoch": 0.26, "learning_rate": 4.4014084507042256e-05, "loss": 5.2228, "step": 250 }, { "epoch": 0.28, "learning_rate": 4.577464788732395e-05, "loss": 5.2485, "step": 260 }, { "epoch": 0.29, "learning_rate": 4.7535211267605635e-05, "loss": 5.2134, "step": 270 }, { "epoch": 0.3, "learning_rate": 4.929577464788733e-05, "loss": 5.1768, "step": 280 }, { "epoch": 0.31, "learning_rate": 4.988226059654632e-05, "loss": 5.153, "step": 290 }, { "epoch": 0.32, "learning_rate": 4.968602825745683e-05, "loss": 5.1334, "step": 300 }, { "epoch": 0.33, "learning_rate": 4.9489795918367346e-05, "loss": 5.0489, "step": 310 }, { "epoch": 0.34, "learning_rate": 4.929356357927787e-05, "loss": 5.0801, "step": 320 }, { "epoch": 0.35, "learning_rate": 4.909733124018839e-05, "loss": 4.9967, "step": 330 }, { "epoch": 0.36, "learning_rate": 4.8901098901098904e-05, "loss": 4.9866, "step": 340 }, { "epoch": 0.37, "learning_rate": 4.870486656200942e-05, "loss": 4.897, "step": 350 }, { "epoch": 0.38, "learning_rate": 4.850863422291994e-05, "loss": 4.9258, "step": 360 }, { "epoch": 0.39, "learning_rate": 4.8312401883830455e-05, "loss": 4.843, "step": 370 }, { "epoch": 0.4, "learning_rate": 4.811616954474098e-05, "loss": 4.8081, "step": 380 }, { "epoch": 0.41, "learning_rate": 4.791993720565149e-05, "loss": 4.7773, "step": 390 }, { "epoch": 0.42, "learning_rate": 4.772370486656201e-05, "loss": 4.772, "step": 400 }, { "epoch": 0.43, "learning_rate": 4.752747252747253e-05, "loss": 4.7747, "step": 410 }, { "epoch": 0.44, "learning_rate": 4.733124018838305e-05, "loss": 4.6581, "step": 420 }, { "epoch": 0.46, "learning_rate": 4.7135007849293564e-05, "loss": 4.733, "step": 430 }, { "epoch": 0.47, "learning_rate": 4.6938775510204086e-05, "loss": 4.6203, "step": 440 }, { "epoch": 0.48, "learning_rate": 4.67425431711146e-05, "loss": 4.6023, "step": 450 }, { "epoch": 0.49, "learning_rate": 4.654631083202512e-05, "loss": 4.5723, "step": 460 }, { "epoch": 0.5, "learning_rate": 4.6350078492935637e-05, "loss": 4.5551, "step": 470 }, { "epoch": 0.51, "learning_rate": 4.615384615384616e-05, "loss": 4.5284, "step": 480 }, { "epoch": 0.52, "learning_rate": 4.595761381475667e-05, "loss": 4.5553, "step": 490 }, { "epoch": 0.53, "learning_rate": 4.5761381475667194e-05, "loss": 4.4564, "step": 500 }, { "epoch": 0.54, "learning_rate": 4.556514913657771e-05, "loss": 4.442, "step": 510 }, { "epoch": 0.55, "learning_rate": 4.5368916797488224e-05, "loss": 4.4394, "step": 520 }, { "epoch": 0.56, "learning_rate": 4.5172684458398746e-05, "loss": 4.4142, "step": 530 }, { "epoch": 0.57, "learning_rate": 4.497645211930927e-05, "loss": 4.3796, "step": 540 }, { "epoch": 0.58, "learning_rate": 4.478021978021978e-05, "loss": 4.406, "step": 550 }, { "epoch": 0.59, "learning_rate": 4.4583987441130297e-05, "loss": 4.3724, "step": 560 }, { "epoch": 0.6, "learning_rate": 4.438775510204082e-05, "loss": 4.3546, "step": 570 }, { "epoch": 0.61, "learning_rate": 4.419152276295134e-05, "loss": 4.2688, "step": 580 }, { "epoch": 0.62, "learning_rate": 4.3995290423861854e-05, "loss": 4.2699, "step": 590 }, { "epoch": 0.64, "learning_rate": 4.379905808477237e-05, "loss": 4.2794, "step": 600 }, { "epoch": 0.65, "learning_rate": 4.360282574568289e-05, "loss": 4.2094, "step": 610 }, { "epoch": 0.66, "learning_rate": 4.340659340659341e-05, "loss": 4.2296, "step": 620 }, { "epoch": 0.67, "learning_rate": 4.321036106750393e-05, "loss": 4.1843, "step": 630 }, { "epoch": 0.68, "learning_rate": 4.301412872841444e-05, "loss": 4.1559, "step": 640 }, { "epoch": 0.69, "learning_rate": 4.281789638932496e-05, "loss": 4.1437, "step": 650 }, { "epoch": 0.7, "learning_rate": 4.2621664050235485e-05, "loss": 4.0615, "step": 660 }, { "epoch": 0.71, "learning_rate": 4.2425431711146e-05, "loss": 4.0465, "step": 670 }, { "epoch": 0.72, "learning_rate": 4.2229199372056514e-05, "loss": 4.0517, "step": 680 }, { "epoch": 0.73, "learning_rate": 4.2032967032967036e-05, "loss": 4.0597, "step": 690 }, { "epoch": 0.74, "learning_rate": 4.183673469387756e-05, "loss": 4.1122, "step": 700 }, { "epoch": 0.75, "learning_rate": 4.164050235478807e-05, "loss": 4.0793, "step": 710 }, { "epoch": 0.76, "learning_rate": 4.144427001569859e-05, "loss": 4.0427, "step": 720 }, { "epoch": 0.77, "learning_rate": 4.124803767660911e-05, "loss": 3.971, "step": 730 }, { "epoch": 0.78, "learning_rate": 4.105180533751963e-05, "loss": 3.9802, "step": 740 }, { "epoch": 0.79, "learning_rate": 4.0855572998430145e-05, "loss": 3.917, "step": 750 }, { "epoch": 0.81, "learning_rate": 4.065934065934066e-05, "loss": 3.946, "step": 760 }, { "epoch": 0.82, "learning_rate": 4.046310832025118e-05, "loss": 3.9967, "step": 770 }, { "epoch": 0.83, "learning_rate": 4.0266875981161696e-05, "loss": 3.9373, "step": 780 }, { "epoch": 0.84, "learning_rate": 4.007064364207222e-05, "loss": 3.9479, "step": 790 }, { "epoch": 0.85, "learning_rate": 3.987441130298273e-05, "loss": 3.8503, "step": 800 }, { "epoch": 0.86, "learning_rate": 3.9678178963893254e-05, "loss": 3.9053, "step": 810 }, { "epoch": 0.87, "learning_rate": 3.948194662480377e-05, "loss": 3.8367, "step": 820 }, { "epoch": 0.88, "learning_rate": 3.928571428571429e-05, "loss": 3.8379, "step": 830 }, { "epoch": 0.89, "learning_rate": 3.9089481946624805e-05, "loss": 3.8315, "step": 840 }, { "epoch": 0.9, "learning_rate": 3.8893249607535326e-05, "loss": 3.8069, "step": 850 }, { "epoch": 0.91, "learning_rate": 3.869701726844584e-05, "loss": 3.7994, "step": 860 }, { "epoch": 0.92, "learning_rate": 3.850078492935636e-05, "loss": 3.7922, "step": 870 }, { "epoch": 0.93, "learning_rate": 3.830455259026688e-05, "loss": 3.7675, "step": 880 }, { "epoch": 0.94, "learning_rate": 3.81083202511774e-05, "loss": 3.7423, "step": 890 }, { "epoch": 0.95, "learning_rate": 3.7912087912087914e-05, "loss": 3.7161, "step": 900 }, { "epoch": 0.96, "learning_rate": 3.7715855572998435e-05, "loss": 3.716, "step": 910 }, { "epoch": 0.97, "learning_rate": 3.751962323390895e-05, "loss": 3.727, "step": 920 }, { "epoch": 0.99, "learning_rate": 3.7323390894819465e-05, "loss": 3.6528, "step": 930 }, { "epoch": 1.0, "learning_rate": 3.7127158555729986e-05, "loss": 3.6659, "step": 940 }, { "epoch": 1.0, "eval_accuracy": 0.2606509757187547, "eval_loss": 3.533505916595459, "eval_runtime": 97.4862, "eval_samples_per_second": 275.444, "eval_steps_per_second": 4.308, "step": 944 }, { "epoch": 1.01, "learning_rate": 3.693092621664051e-05, "loss": 3.6428, "step": 950 }, { "epoch": 1.02, "learning_rate": 3.673469387755102e-05, "loss": 3.6448, "step": 960 }, { "epoch": 1.03, "learning_rate": 3.653846153846154e-05, "loss": 3.6328, "step": 970 }, { "epoch": 1.04, "learning_rate": 3.634222919937206e-05, "loss": 3.5496, "step": 980 }, { "epoch": 1.05, "learning_rate": 3.614599686028258e-05, "loss": 3.5896, "step": 990 }, { "epoch": 1.06, "learning_rate": 3.5949764521193095e-05, "loss": 3.6441, "step": 1000 }, { "epoch": 1.07, "learning_rate": 3.575353218210361e-05, "loss": 3.539, "step": 1010 }, { "epoch": 1.08, "learning_rate": 3.555729984301413e-05, "loss": 3.5687, "step": 1020 }, { "epoch": 1.09, "learning_rate": 3.536106750392465e-05, "loss": 3.5421, "step": 1030 }, { "epoch": 1.1, "learning_rate": 3.516483516483517e-05, "loss": 3.4795, "step": 1040 }, { "epoch": 1.11, "learning_rate": 3.496860282574568e-05, "loss": 3.5074, "step": 1050 }, { "epoch": 1.12, "learning_rate": 3.4772370486656204e-05, "loss": 3.5137, "step": 1060 }, { "epoch": 1.13, "learning_rate": 3.4576138147566726e-05, "loss": 3.5203, "step": 1070 }, { "epoch": 1.14, "learning_rate": 3.4379905808477234e-05, "loss": 3.4245, "step": 1080 }, { "epoch": 1.15, "learning_rate": 3.4183673469387755e-05, "loss": 3.5115, "step": 1090 }, { "epoch": 1.17, "learning_rate": 3.398744113029828e-05, "loss": 3.4804, "step": 1100 }, { "epoch": 1.18, "learning_rate": 3.37912087912088e-05, "loss": 3.4304, "step": 1110 }, { "epoch": 1.19, "learning_rate": 3.3594976452119306e-05, "loss": 3.4354, "step": 1120 }, { "epoch": 1.2, "learning_rate": 3.339874411302983e-05, "loss": 3.3765, "step": 1130 }, { "epoch": 1.21, "learning_rate": 3.320251177394035e-05, "loss": 3.4077, "step": 1140 }, { "epoch": 1.22, "learning_rate": 3.300627943485087e-05, "loss": 3.4707, "step": 1150 }, { "epoch": 1.23, "learning_rate": 3.281004709576138e-05, "loss": 3.3938, "step": 1160 }, { "epoch": 1.24, "learning_rate": 3.26138147566719e-05, "loss": 3.3528, "step": 1170 }, { "epoch": 1.25, "learning_rate": 3.241758241758242e-05, "loss": 3.3962, "step": 1180 }, { "epoch": 1.26, "learning_rate": 3.222135007849294e-05, "loss": 3.3941, "step": 1190 }, { "epoch": 1.27, "learning_rate": 3.202511773940345e-05, "loss": 3.4488, "step": 1200 }, { "epoch": 1.28, "learning_rate": 3.182888540031397e-05, "loss": 3.3212, "step": 1210 }, { "epoch": 1.29, "learning_rate": 3.1632653061224494e-05, "loss": 3.3005, "step": 1220 }, { "epoch": 1.3, "learning_rate": 3.143642072213501e-05, "loss": 3.3064, "step": 1230 }, { "epoch": 1.31, "learning_rate": 3.1240188383045524e-05, "loss": 3.3063, "step": 1240 }, { "epoch": 1.32, "learning_rate": 3.1043956043956046e-05, "loss": 3.2612, "step": 1250 }, { "epoch": 1.33, "learning_rate": 3.084772370486657e-05, "loss": 3.2411, "step": 1260 }, { "epoch": 1.35, "learning_rate": 3.065149136577708e-05, "loss": 3.309, "step": 1270 }, { "epoch": 1.36, "learning_rate": 3.04552590266876e-05, "loss": 3.2564, "step": 1280 }, { "epoch": 1.37, "learning_rate": 3.0259026687598118e-05, "loss": 3.2723, "step": 1290 }, { "epoch": 1.38, "learning_rate": 3.006279434850864e-05, "loss": 3.3098, "step": 1300 }, { "epoch": 1.39, "learning_rate": 2.986656200941915e-05, "loss": 3.2508, "step": 1310 }, { "epoch": 1.4, "learning_rate": 2.9670329670329673e-05, "loss": 3.1985, "step": 1320 }, { "epoch": 1.41, "learning_rate": 2.947409733124019e-05, "loss": 3.2328, "step": 1330 }, { "epoch": 1.42, "learning_rate": 2.9277864992150706e-05, "loss": 3.1489, "step": 1340 }, { "epoch": 1.43, "learning_rate": 2.9081632653061224e-05, "loss": 3.1567, "step": 1350 }, { "epoch": 1.44, "learning_rate": 2.8885400313971745e-05, "loss": 3.1081, "step": 1360 }, { "epoch": 1.45, "learning_rate": 2.8689167974882263e-05, "loss": 3.142, "step": 1370 }, { "epoch": 1.46, "learning_rate": 2.8492935635792778e-05, "loss": 3.1408, "step": 1380 }, { "epoch": 1.47, "learning_rate": 2.8296703296703296e-05, "loss": 3.1543, "step": 1390 }, { "epoch": 1.48, "learning_rate": 2.8100470957613818e-05, "loss": 3.1944, "step": 1400 }, { "epoch": 1.49, "learning_rate": 2.7904238618524336e-05, "loss": 3.1483, "step": 1410 }, { "epoch": 1.5, "learning_rate": 2.770800627943485e-05, "loss": 3.1497, "step": 1420 }, { "epoch": 1.51, "learning_rate": 2.751177394034537e-05, "loss": 3.1025, "step": 1430 }, { "epoch": 1.53, "learning_rate": 2.731554160125589e-05, "loss": 3.0822, "step": 1440 }, { "epoch": 1.54, "learning_rate": 2.7119309262166405e-05, "loss": 3.1437, "step": 1450 }, { "epoch": 1.55, "learning_rate": 2.6923076923076923e-05, "loss": 3.0663, "step": 1460 }, { "epoch": 1.56, "learning_rate": 2.672684458398744e-05, "loss": 3.1177, "step": 1470 }, { "epoch": 1.57, "learning_rate": 2.6530612244897963e-05, "loss": 3.0665, "step": 1480 }, { "epoch": 1.58, "learning_rate": 2.6334379905808478e-05, "loss": 3.091, "step": 1490 }, { "epoch": 1.59, "learning_rate": 2.6138147566718996e-05, "loss": 3.0334, "step": 1500 }, { "epoch": 1.6, "learning_rate": 2.5941915227629514e-05, "loss": 3.0471, "step": 1510 }, { "epoch": 1.61, "learning_rate": 2.5745682888540036e-05, "loss": 3.0843, "step": 1520 }, { "epoch": 1.62, "learning_rate": 2.554945054945055e-05, "loss": 3.0209, "step": 1530 }, { "epoch": 1.63, "learning_rate": 2.535321821036107e-05, "loss": 3.0012, "step": 1540 }, { "epoch": 1.64, "learning_rate": 2.5156985871271587e-05, "loss": 3.046, "step": 1550 }, { "epoch": 1.65, "learning_rate": 2.4960753532182105e-05, "loss": 3.0183, "step": 1560 }, { "epoch": 1.66, "learning_rate": 2.4764521193092623e-05, "loss": 3.0526, "step": 1570 }, { "epoch": 1.67, "learning_rate": 2.456828885400314e-05, "loss": 3.0337, "step": 1580 }, { "epoch": 1.68, "learning_rate": 2.437205651491366e-05, "loss": 3.0085, "step": 1590 }, { "epoch": 1.69, "learning_rate": 2.4175824175824177e-05, "loss": 2.9889, "step": 1600 }, { "epoch": 1.71, "learning_rate": 2.3979591836734696e-05, "loss": 3.0547, "step": 1610 }, { "epoch": 1.72, "learning_rate": 2.3783359497645214e-05, "loss": 2.9625, "step": 1620 }, { "epoch": 1.73, "learning_rate": 2.3587127158555732e-05, "loss": 2.9162, "step": 1630 }, { "epoch": 1.74, "learning_rate": 2.339089481946625e-05, "loss": 2.995, "step": 1640 }, { "epoch": 1.75, "learning_rate": 2.3194662480376765e-05, "loss": 2.9096, "step": 1650 }, { "epoch": 1.76, "learning_rate": 2.2998430141287286e-05, "loss": 2.9733, "step": 1660 }, { "epoch": 1.77, "learning_rate": 2.28021978021978e-05, "loss": 2.9812, "step": 1670 }, { "epoch": 1.78, "learning_rate": 2.2605965463108323e-05, "loss": 2.9212, "step": 1680 }, { "epoch": 1.79, "learning_rate": 2.2409733124018837e-05, "loss": 2.9416, "step": 1690 }, { "epoch": 1.8, "learning_rate": 2.221350078492936e-05, "loss": 2.9251, "step": 1700 }, { "epoch": 1.81, "learning_rate": 2.2017268445839874e-05, "loss": 2.8985, "step": 1710 }, { "epoch": 1.82, "learning_rate": 2.1821036106750395e-05, "loss": 2.9358, "step": 1720 }, { "epoch": 1.83, "learning_rate": 2.162480376766091e-05, "loss": 2.9233, "step": 1730 }, { "epoch": 1.84, "learning_rate": 2.1428571428571428e-05, "loss": 2.893, "step": 1740 }, { "epoch": 1.85, "learning_rate": 2.1232339089481946e-05, "loss": 2.899, "step": 1750 }, { "epoch": 1.86, "learning_rate": 2.1036106750392464e-05, "loss": 2.8488, "step": 1760 }, { "epoch": 1.88, "learning_rate": 2.0839874411302983e-05, "loss": 2.868, "step": 1770 }, { "epoch": 1.89, "learning_rate": 2.06436420722135e-05, "loss": 2.8552, "step": 1780 }, { "epoch": 1.9, "learning_rate": 2.044740973312402e-05, "loss": 2.9662, "step": 1790 }, { "epoch": 1.91, "learning_rate": 2.0251177394034537e-05, "loss": 2.9119, "step": 1800 }, { "epoch": 1.92, "learning_rate": 2.0054945054945055e-05, "loss": 2.8802, "step": 1810 }, { "epoch": 1.93, "learning_rate": 1.9858712715855573e-05, "loss": 2.8677, "step": 1820 }, { "epoch": 1.94, "learning_rate": 1.966248037676609e-05, "loss": 2.8699, "step": 1830 }, { "epoch": 1.95, "learning_rate": 1.946624803767661e-05, "loss": 2.8098, "step": 1840 }, { "epoch": 1.96, "learning_rate": 1.9270015698587128e-05, "loss": 2.8563, "step": 1850 }, { "epoch": 1.97, "learning_rate": 1.9073783359497646e-05, "loss": 2.7886, "step": 1860 }, { "epoch": 1.98, "learning_rate": 1.8877551020408164e-05, "loss": 2.8598, "step": 1870 }, { "epoch": 1.99, "learning_rate": 1.8681318681318682e-05, "loss": 2.8174, "step": 1880 }, { "epoch": 2.0, "eval_accuracy": 0.4418292864591092, "eval_loss": 2.6391382217407227, "eval_runtime": 97.3952, "eval_samples_per_second": 275.702, "eval_steps_per_second": 4.312, "step": 1888 }, { "epoch": 2.0, "learning_rate": 1.84850863422292e-05, "loss": 2.7918, "step": 1890 }, { "epoch": 2.01, "learning_rate": 1.828885400313972e-05, "loss": 2.7957, "step": 1900 }, { "epoch": 2.02, "learning_rate": 1.8092621664050237e-05, "loss": 2.7601, "step": 1910 }, { "epoch": 2.03, "learning_rate": 1.7896389324960755e-05, "loss": 2.7688, "step": 1920 }, { "epoch": 2.04, "learning_rate": 1.7700156985871273e-05, "loss": 2.7594, "step": 1930 }, { "epoch": 2.06, "learning_rate": 1.750392464678179e-05, "loss": 2.7886, "step": 1940 }, { "epoch": 2.07, "learning_rate": 1.730769230769231e-05, "loss": 2.735, "step": 1950 }, { "epoch": 2.08, "learning_rate": 1.7111459968602827e-05, "loss": 2.7681, "step": 1960 }, { "epoch": 2.09, "learning_rate": 1.6915227629513346e-05, "loss": 2.7326, "step": 1970 }, { "epoch": 2.1, "learning_rate": 1.6718995290423864e-05, "loss": 2.7596, "step": 1980 }, { "epoch": 2.11, "learning_rate": 1.6522762951334382e-05, "loss": 2.7674, "step": 1990 }, { "epoch": 2.12, "learning_rate": 1.6326530612244897e-05, "loss": 2.7678, "step": 2000 }, { "epoch": 2.13, "learning_rate": 1.6130298273155418e-05, "loss": 2.7441, "step": 2010 }, { "epoch": 2.14, "learning_rate": 1.5934065934065933e-05, "loss": 2.7109, "step": 2020 }, { "epoch": 2.15, "learning_rate": 1.5737833594976455e-05, "loss": 2.6763, "step": 2030 }, { "epoch": 2.16, "learning_rate": 1.554160125588697e-05, "loss": 2.6663, "step": 2040 }, { "epoch": 2.17, "learning_rate": 1.534536891679749e-05, "loss": 2.7026, "step": 2050 }, { "epoch": 2.18, "learning_rate": 1.5149136577708006e-05, "loss": 2.691, "step": 2060 }, { "epoch": 2.19, "learning_rate": 1.4952904238618525e-05, "loss": 2.7213, "step": 2070 }, { "epoch": 2.2, "learning_rate": 1.4756671899529042e-05, "loss": 2.7104, "step": 2080 }, { "epoch": 2.21, "learning_rate": 1.4560439560439562e-05, "loss": 2.7264, "step": 2090 }, { "epoch": 2.22, "learning_rate": 1.4364207221350078e-05, "loss": 2.6866, "step": 2100 }, { "epoch": 2.24, "learning_rate": 1.4167974882260598e-05, "loss": 2.7339, "step": 2110 }, { "epoch": 2.25, "learning_rate": 1.3971742543171114e-05, "loss": 2.7038, "step": 2120 }, { "epoch": 2.26, "learning_rate": 1.3775510204081633e-05, "loss": 2.7007, "step": 2130 }, { "epoch": 2.27, "learning_rate": 1.357927786499215e-05, "loss": 2.6325, "step": 2140 }, { "epoch": 2.28, "learning_rate": 1.3383045525902669e-05, "loss": 2.6068, "step": 2150 }, { "epoch": 2.29, "learning_rate": 1.3186813186813187e-05, "loss": 2.63, "step": 2160 }, { "epoch": 2.3, "learning_rate": 1.2990580847723705e-05, "loss": 2.6954, "step": 2170 }, { "epoch": 2.31, "learning_rate": 1.2794348508634223e-05, "loss": 2.6464, "step": 2180 }, { "epoch": 2.32, "learning_rate": 1.2598116169544742e-05, "loss": 2.6512, "step": 2190 }, { "epoch": 2.33, "learning_rate": 1.240188383045526e-05, "loss": 2.6591, "step": 2200 }, { "epoch": 2.34, "learning_rate": 1.2205651491365778e-05, "loss": 2.6929, "step": 2210 }, { "epoch": 2.35, "learning_rate": 1.2009419152276296e-05, "loss": 2.6971, "step": 2220 }, { "epoch": 2.36, "learning_rate": 1.1813186813186814e-05, "loss": 2.653, "step": 2230 }, { "epoch": 2.37, "learning_rate": 1.1616954474097332e-05, "loss": 2.6934, "step": 2240 }, { "epoch": 2.38, "learning_rate": 1.142072213500785e-05, "loss": 2.6721, "step": 2250 }, { "epoch": 2.39, "learning_rate": 1.1224489795918369e-05, "loss": 2.6251, "step": 2260 }, { "epoch": 2.4, "learning_rate": 1.1028257456828887e-05, "loss": 2.6544, "step": 2270 }, { "epoch": 2.42, "learning_rate": 1.0832025117739405e-05, "loss": 2.6079, "step": 2280 }, { "epoch": 2.43, "learning_rate": 1.0635792778649923e-05, "loss": 2.6739, "step": 2290 }, { "epoch": 2.44, "learning_rate": 1.0439560439560441e-05, "loss": 2.6701, "step": 2300 }, { "epoch": 2.45, "learning_rate": 1.024332810047096e-05, "loss": 2.5559, "step": 2310 }, { "epoch": 2.46, "learning_rate": 1.0047095761381477e-05, "loss": 2.595, "step": 2320 }, { "epoch": 2.47, "learning_rate": 9.850863422291996e-06, "loss": 2.6354, "step": 2330 }, { "epoch": 2.48, "learning_rate": 9.654631083202512e-06, "loss": 2.5995, "step": 2340 }, { "epoch": 2.49, "learning_rate": 9.45839874411303e-06, "loss": 2.578, "step": 2350 }, { "epoch": 2.5, "learning_rate": 9.262166405023548e-06, "loss": 2.6291, "step": 2360 }, { "epoch": 2.51, "learning_rate": 9.065934065934067e-06, "loss": 2.6349, "step": 2370 }, { "epoch": 2.52, "learning_rate": 8.869701726844585e-06, "loss": 2.6519, "step": 2380 }, { "epoch": 2.53, "learning_rate": 8.673469387755103e-06, "loss": 2.6348, "step": 2390 }, { "epoch": 2.54, "learning_rate": 8.477237048665621e-06, "loss": 2.6099, "step": 2400 }, { "epoch": 2.55, "learning_rate": 8.281004709576139e-06, "loss": 2.5538, "step": 2410 }, { "epoch": 2.56, "learning_rate": 8.084772370486657e-06, "loss": 2.6195, "step": 2420 }, { "epoch": 2.57, "learning_rate": 7.888540031397175e-06, "loss": 2.6005, "step": 2430 }, { "epoch": 2.58, "learning_rate": 7.692307692307694e-06, "loss": 2.5735, "step": 2440 }, { "epoch": 2.6, "learning_rate": 7.496075353218211e-06, "loss": 2.607, "step": 2450 }, { "epoch": 2.61, "learning_rate": 7.299843014128729e-06, "loss": 2.644, "step": 2460 }, { "epoch": 2.62, "learning_rate": 7.103610675039246e-06, "loss": 2.5924, "step": 2470 }, { "epoch": 2.63, "learning_rate": 6.9073783359497645e-06, "loss": 2.5596, "step": 2480 }, { "epoch": 2.64, "learning_rate": 6.711145996860283e-06, "loss": 2.5408, "step": 2490 }, { "epoch": 2.65, "learning_rate": 6.514913657770801e-06, "loss": 2.6228, "step": 2500 }, { "epoch": 2.66, "learning_rate": 6.318681318681319e-06, "loss": 2.5923, "step": 2510 }, { "epoch": 2.67, "learning_rate": 6.122448979591837e-06, "loss": 2.5873, "step": 2520 }, { "epoch": 2.68, "learning_rate": 5.926216640502355e-06, "loss": 2.5732, "step": 2530 }, { "epoch": 2.69, "learning_rate": 5.729984301412873e-06, "loss": 2.6217, "step": 2540 }, { "epoch": 2.7, "learning_rate": 5.5337519623233915e-06, "loss": 2.5432, "step": 2550 }, { "epoch": 2.71, "learning_rate": 5.33751962323391e-06, "loss": 2.5638, "step": 2560 }, { "epoch": 2.72, "learning_rate": 5.141287284144427e-06, "loss": 2.5396, "step": 2570 }, { "epoch": 2.73, "learning_rate": 4.945054945054945e-06, "loss": 2.5384, "step": 2580 }, { "epoch": 2.74, "learning_rate": 4.748822605965463e-06, "loss": 2.6231, "step": 2590 }, { "epoch": 2.75, "learning_rate": 4.5525902668759815e-06, "loss": 2.6124, "step": 2600 }, { "epoch": 2.76, "learning_rate": 4.3563579277865e-06, "loss": 2.5478, "step": 2610 }, { "epoch": 2.78, "learning_rate": 4.160125588697018e-06, "loss": 2.6101, "step": 2620 }, { "epoch": 2.79, "learning_rate": 3.963893249607536e-06, "loss": 2.5558, "step": 2630 }, { "epoch": 2.8, "learning_rate": 3.767660910518053e-06, "loss": 2.5715, "step": 2640 }, { "epoch": 2.81, "learning_rate": 3.5714285714285714e-06, "loss": 2.5204, "step": 2650 }, { "epoch": 2.82, "learning_rate": 3.3751962323390895e-06, "loss": 2.6461, "step": 2660 }, { "epoch": 2.83, "learning_rate": 3.1789638932496077e-06, "loss": 2.6198, "step": 2670 }, { "epoch": 2.84, "learning_rate": 2.982731554160126e-06, "loss": 2.6099, "step": 2680 }, { "epoch": 2.85, "learning_rate": 2.7864992150706435e-06, "loss": 2.5261, "step": 2690 }, { "epoch": 2.86, "learning_rate": 2.5902668759811617e-06, "loss": 2.5378, "step": 2700 }, { "epoch": 2.87, "learning_rate": 2.39403453689168e-06, "loss": 2.4815, "step": 2710 }, { "epoch": 2.88, "learning_rate": 2.197802197802198e-06, "loss": 2.5685, "step": 2720 }, { "epoch": 2.89, "learning_rate": 2.0015698587127157e-06, "loss": 2.5881, "step": 2730 }, { "epoch": 2.9, "learning_rate": 1.805337519623234e-06, "loss": 2.5615, "step": 2740 }, { "epoch": 2.91, "learning_rate": 1.6091051805337522e-06, "loss": 2.5608, "step": 2750 }, { "epoch": 2.92, "learning_rate": 1.4128728414442702e-06, "loss": 2.5123, "step": 2760 }, { "epoch": 2.93, "learning_rate": 1.216640502354788e-06, "loss": 2.5326, "step": 2770 }, { "epoch": 2.94, "learning_rate": 1.020408163265306e-06, "loss": 2.6042, "step": 2780 }, { "epoch": 2.96, "learning_rate": 8.241758241758242e-07, "loss": 2.6328, "step": 2790 }, { "epoch": 2.97, "learning_rate": 6.279434850863423e-07, "loss": 2.5443, "step": 2800 }, { "epoch": 2.98, "learning_rate": 4.317111459968603e-07, "loss": 2.5534, "step": 2810 }, { "epoch": 2.99, "learning_rate": 2.3547880690737833e-07, "loss": 2.5537, "step": 2820 }, { "epoch": 3.0, "learning_rate": 3.9246467817896396e-08, "loss": 2.4959, "step": 2830 }, { "epoch": 3.0, "eval_accuracy": 0.4911738417994935, "eval_loss": 2.389798164367676, "eval_runtime": 98.4092, "eval_samples_per_second": 272.861, "eval_steps_per_second": 4.268, "step": 2832 }, { "epoch": 3.0, "step": 2832, "total_flos": 1.84051547235869e+19, "train_loss": 3.4896271976373963, "train_runtime": 4580.4169, "train_samples_per_second": 158.281, "train_steps_per_second": 0.618 }, { "epoch": 3.0, "eval_accuracy": 0.4911738417994935, "eval_loss": 2.389798164367676, "eval_runtime": 100.4578, "eval_samples_per_second": 267.296, "eval_steps_per_second": 4.181, "step": 2832 }, { "epoch": 3.0, "eval_accuracy": 0.4911738417994935, "eval_loss": 2.389798164367676, "eval_runtime": 100.2695, "eval_samples_per_second": 267.798, "eval_steps_per_second": 4.189, "step": 2832 } ], "max_steps": 2832, "num_train_epochs": 3, "total_flos": 1.84051547235869e+19, "trial_name": null, "trial_params": null }