diff --git "a/tmp-checkpoint-53956/trainer_state.json" "b/tmp-checkpoint-53956/trainer_state.json" new file mode 100644--- /dev/null +++ "b/tmp-checkpoint-53956/trainer_state.json" @@ -0,0 +1,32951 @@ +{ + "best_metric": 1.9404698610305786, + "best_model_checkpoint": "pvt-small-224-ConcreteClassifier-PVT\\checkpoint-34686", + "epoch": 28.0, + "eval_steps": 500, + "global_step": 53956, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.01, + "learning_rate": 0.001, + "loss": 2.7631, + "step": 10 + }, + { + "epoch": 0.01, + "learning_rate": 0.001, + "loss": 2.0945, + "step": 20 + }, + { + "epoch": 0.02, + "learning_rate": 0.001, + "loss": 1.9938, + "step": 30 + }, + { + "epoch": 0.02, + "learning_rate": 0.001, + "loss": 1.9829, + "step": 40 + }, + { + "epoch": 0.03, + "learning_rate": 0.001, + "loss": 2.0147, + "step": 50 + }, + { + "epoch": 0.03, + "learning_rate": 0.001, + "loss": 2.096, + "step": 60 + }, + { + "epoch": 0.04, + "learning_rate": 0.001, + "loss": 2.006, + "step": 70 + }, + { + "epoch": 0.04, + "learning_rate": 0.001, + "loss": 1.9784, + "step": 80 + }, + { + "epoch": 0.05, + "learning_rate": 0.001, + "loss": 1.9937, + "step": 90 + }, + { + "epoch": 0.05, + "learning_rate": 0.001, + "loss": 1.9689, + "step": 100 + }, + { + "epoch": 0.06, + "learning_rate": 0.001, + "loss": 2.0182, + "step": 110 + }, + { + "epoch": 0.06, + "learning_rate": 0.001, + "loss": 1.9828, + "step": 120 + }, + { + "epoch": 0.07, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 130 + }, + { + "epoch": 0.07, + "learning_rate": 0.001, + "loss": 1.9696, + "step": 140 + }, + { + "epoch": 0.08, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 150 + }, + { + "epoch": 0.08, + "learning_rate": 0.001, + "loss": 1.9834, + "step": 160 + }, + { + "epoch": 0.09, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 170 + }, + { + "epoch": 0.09, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 180 + }, + { + "epoch": 0.1, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 190 + }, + { + "epoch": 0.1, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 200 + }, + { + "epoch": 0.11, + "learning_rate": 0.001, + "loss": 1.9978, + "step": 210 + }, + { + "epoch": 0.11, + "learning_rate": 0.001, + "loss": 1.9604, + "step": 220 + }, + { + "epoch": 0.12, + "learning_rate": 0.001, + "loss": 1.971, + "step": 230 + }, + { + "epoch": 0.12, + "learning_rate": 0.001, + "loss": 1.9705, + "step": 240 + }, + { + "epoch": 0.13, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 250 + }, + { + "epoch": 0.13, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 260 + }, + { + "epoch": 0.14, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 270 + }, + { + "epoch": 0.15, + "learning_rate": 0.001, + "loss": 1.9695, + "step": 280 + }, + { + "epoch": 0.15, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 290 + }, + { + "epoch": 0.16, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 300 + }, + { + "epoch": 0.16, + "learning_rate": 0.001, + "loss": 1.9976, + "step": 310 + }, + { + "epoch": 0.17, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 320 + }, + { + "epoch": 0.17, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 330 + }, + { + "epoch": 0.18, + "learning_rate": 0.001, + "loss": 1.9623, + "step": 340 + }, + { + "epoch": 0.18, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 350 + }, + { + "epoch": 0.19, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 360 + }, + { + "epoch": 0.19, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 370 + }, + { + "epoch": 0.2, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 380 + }, + { + "epoch": 0.2, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 390 + }, + { + "epoch": 0.21, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 400 + }, + { + "epoch": 0.21, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 410 + }, + { + "epoch": 0.22, + "learning_rate": 0.001, + "loss": 1.928, + "step": 420 + }, + { + "epoch": 0.22, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 430 + }, + { + "epoch": 0.23, + "learning_rate": 0.001, + "loss": 1.8994, + "step": 440 + }, + { + "epoch": 0.23, + "learning_rate": 0.001, + "loss": 2.029, + "step": 450 + }, + { + "epoch": 0.24, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 460 + }, + { + "epoch": 0.24, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 470 + }, + { + "epoch": 0.25, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 480 + }, + { + "epoch": 0.25, + "learning_rate": 0.001, + "loss": 1.956, + "step": 490 + }, + { + "epoch": 0.26, + "learning_rate": 0.001, + "loss": 1.9707, + "step": 500 + }, + { + "epoch": 0.26, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 510 + }, + { + "epoch": 0.27, + "learning_rate": 0.001, + "loss": 1.9656, + "step": 520 + }, + { + "epoch": 0.28, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 530 + }, + { + "epoch": 0.28, + "learning_rate": 0.001, + "loss": 1.955, + "step": 540 + }, + { + "epoch": 0.29, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 550 + }, + { + "epoch": 0.29, + "learning_rate": 0.001, + "loss": 1.9574, + "step": 560 + }, + { + "epoch": 0.3, + "learning_rate": 0.001, + "loss": 1.956, + "step": 570 + }, + { + "epoch": 0.3, + "learning_rate": 0.001, + "loss": 1.9587, + "step": 580 + }, + { + "epoch": 0.31, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 590 + }, + { + "epoch": 0.31, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 600 + }, + { + "epoch": 0.32, + "learning_rate": 0.001, + "loss": 1.9648, + "step": 610 + }, + { + "epoch": 0.32, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 620 + }, + { + "epoch": 0.33, + "learning_rate": 0.001, + "loss": 1.961, + "step": 630 + }, + { + "epoch": 0.33, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 640 + }, + { + "epoch": 0.34, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 650 + }, + { + "epoch": 0.34, + "learning_rate": 0.001, + "loss": 1.967, + "step": 660 + }, + { + "epoch": 0.35, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 670 + }, + { + "epoch": 0.35, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 680 + }, + { + "epoch": 0.36, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 690 + }, + { + "epoch": 0.36, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 700 + }, + { + "epoch": 0.37, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 710 + }, + { + "epoch": 0.37, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 720 + }, + { + "epoch": 0.38, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 730 + }, + { + "epoch": 0.38, + "learning_rate": 0.001, + "loss": 1.9188, + "step": 740 + }, + { + "epoch": 0.39, + "learning_rate": 0.001, + "loss": 2.0077, + "step": 750 + }, + { + "epoch": 0.39, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 760 + }, + { + "epoch": 0.4, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 770 + }, + { + "epoch": 0.4, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 780 + }, + { + "epoch": 0.41, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 790 + }, + { + "epoch": 0.42, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 800 + }, + { + "epoch": 0.42, + "learning_rate": 0.001, + "loss": 1.9656, + "step": 810 + }, + { + "epoch": 0.43, + "learning_rate": 0.001, + "loss": 1.948, + "step": 820 + }, + { + "epoch": 0.43, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 830 + }, + { + "epoch": 0.44, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 840 + }, + { + "epoch": 0.44, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 850 + }, + { + "epoch": 0.45, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 860 + }, + { + "epoch": 0.45, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 870 + }, + { + "epoch": 0.46, + "learning_rate": 0.001, + "loss": 1.9621, + "step": 880 + }, + { + "epoch": 0.46, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 890 + }, + { + "epoch": 0.47, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 900 + }, + { + "epoch": 0.47, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 910 + }, + { + "epoch": 0.48, + "learning_rate": 0.001, + "loss": 1.948, + "step": 920 + }, + { + "epoch": 0.48, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 930 + }, + { + "epoch": 0.49, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 940 + }, + { + "epoch": 0.49, + "learning_rate": 0.001, + "loss": 1.9588, + "step": 950 + }, + { + "epoch": 0.5, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 960 + }, + { + "epoch": 0.5, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 970 + }, + { + "epoch": 0.51, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 980 + }, + { + "epoch": 0.51, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 990 + }, + { + "epoch": 0.52, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 1000 + }, + { + "epoch": 0.52, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 1010 + }, + { + "epoch": 0.53, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 1020 + }, + { + "epoch": 0.53, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 1030 + }, + { + "epoch": 0.54, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 1040 + }, + { + "epoch": 0.54, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 1050 + }, + { + "epoch": 0.55, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 1060 + }, + { + "epoch": 0.56, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 1070 + }, + { + "epoch": 0.56, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 1080 + }, + { + "epoch": 0.57, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 1090 + }, + { + "epoch": 0.57, + "learning_rate": 0.001, + "loss": 1.9666, + "step": 1100 + }, + { + "epoch": 0.58, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 1110 + }, + { + "epoch": 0.58, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 1120 + }, + { + "epoch": 0.59, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 1130 + }, + { + "epoch": 0.59, + "learning_rate": 0.001, + "loss": 1.9252, + "step": 1140 + }, + { + "epoch": 0.6, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 1150 + }, + { + "epoch": 0.6, + "learning_rate": 0.001, + "loss": 1.9619, + "step": 1160 + }, + { + "epoch": 0.61, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 1170 + }, + { + "epoch": 0.61, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 1180 + }, + { + "epoch": 0.62, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 1190 + }, + { + "epoch": 0.62, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 1200 + }, + { + "epoch": 0.63, + "learning_rate": 0.001, + "loss": 1.9166, + "step": 1210 + }, + { + "epoch": 0.63, + "learning_rate": 0.001, + "loss": 2.0, + "step": 1220 + }, + { + "epoch": 0.64, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 1230 + }, + { + "epoch": 0.64, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 1240 + }, + { + "epoch": 0.65, + "learning_rate": 0.001, + "loss": 1.9722, + "step": 1250 + }, + { + "epoch": 0.65, + "learning_rate": 0.001, + "loss": 1.9704, + "step": 1260 + }, + { + "epoch": 0.66, + "learning_rate": 0.001, + "loss": 1.957, + "step": 1270 + }, + { + "epoch": 0.66, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 1280 + }, + { + "epoch": 0.67, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 1290 + }, + { + "epoch": 0.67, + "learning_rate": 0.001, + "loss": 1.9718, + "step": 1300 + }, + { + "epoch": 0.68, + "learning_rate": 0.001, + "loss": 1.9597, + "step": 1310 + }, + { + "epoch": 0.69, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 1320 + }, + { + "epoch": 0.69, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 1330 + }, + { + "epoch": 0.7, + "learning_rate": 0.001, + "loss": 1.9636, + "step": 1340 + }, + { + "epoch": 0.7, + "learning_rate": 0.001, + "loss": 1.95, + "step": 1350 + }, + { + "epoch": 0.71, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 1360 + }, + { + "epoch": 0.71, + "learning_rate": 0.001, + "loss": 2.0172, + "step": 1370 + }, + { + "epoch": 0.72, + "learning_rate": 0.001, + "loss": 1.943, + "step": 1380 + }, + { + "epoch": 0.72, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 1390 + }, + { + "epoch": 0.73, + "learning_rate": 0.001, + "loss": 1.9877, + "step": 1400 + }, + { + "epoch": 0.73, + "learning_rate": 0.001, + "loss": 1.976, + "step": 1410 + }, + { + "epoch": 0.74, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 1420 + }, + { + "epoch": 0.74, + "learning_rate": 0.001, + "loss": 1.9797, + "step": 1430 + }, + { + "epoch": 0.75, + "learning_rate": 0.001, + "loss": 1.9719, + "step": 1440 + }, + { + "epoch": 0.75, + "learning_rate": 0.001, + "loss": 1.925, + "step": 1450 + }, + { + "epoch": 0.76, + "learning_rate": 0.001, + "loss": 1.9756, + "step": 1460 + }, + { + "epoch": 0.76, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 1470 + }, + { + "epoch": 0.77, + "learning_rate": 0.001, + "loss": 1.949, + "step": 1480 + }, + { + "epoch": 0.77, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 1490 + }, + { + "epoch": 0.78, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 1500 + }, + { + "epoch": 0.78, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 1510 + }, + { + "epoch": 0.79, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 1520 + }, + { + "epoch": 0.79, + "learning_rate": 0.001, + "loss": 1.9762, + "step": 1530 + }, + { + "epoch": 0.8, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 1540 + }, + { + "epoch": 0.8, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 1550 + }, + { + "epoch": 0.81, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 1560 + }, + { + "epoch": 0.81, + "learning_rate": 0.001, + "loss": 1.9875, + "step": 1570 + }, + { + "epoch": 0.82, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 1580 + }, + { + "epoch": 0.83, + "learning_rate": 0.001, + "loss": 1.9231, + "step": 1590 + }, + { + "epoch": 0.83, + "learning_rate": 0.001, + "loss": 1.9163, + "step": 1600 + }, + { + "epoch": 0.84, + "learning_rate": 0.001, + "loss": 1.9894, + "step": 1610 + }, + { + "epoch": 0.84, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 1620 + }, + { + "epoch": 0.85, + "learning_rate": 0.001, + "loss": 1.9237, + "step": 1630 + }, + { + "epoch": 0.85, + "learning_rate": 0.001, + "loss": 2.1552, + "step": 1640 + }, + { + "epoch": 0.86, + "learning_rate": 0.001, + "loss": 2.0399, + "step": 1650 + }, + { + "epoch": 0.86, + "learning_rate": 0.001, + "loss": 1.971, + "step": 1660 + }, + { + "epoch": 0.87, + "learning_rate": 0.001, + "loss": 2.0006, + "step": 1670 + }, + { + "epoch": 0.87, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 1680 + }, + { + "epoch": 0.88, + "learning_rate": 0.001, + "loss": 1.993, + "step": 1690 + }, + { + "epoch": 0.88, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 1700 + }, + { + "epoch": 0.89, + "learning_rate": 0.001, + "loss": 1.963, + "step": 1710 + }, + { + "epoch": 0.89, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 1720 + }, + { + "epoch": 0.9, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 1730 + }, + { + "epoch": 0.9, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 1740 + }, + { + "epoch": 0.91, + "learning_rate": 0.001, + "loss": 1.934, + "step": 1750 + }, + { + "epoch": 0.91, + "learning_rate": 0.001, + "loss": 2.0062, + "step": 1760 + }, + { + "epoch": 0.92, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 1770 + }, + { + "epoch": 0.92, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 1780 + }, + { + "epoch": 0.93, + "learning_rate": 0.001, + "loss": 1.9135, + "step": 1790 + }, + { + "epoch": 0.93, + "learning_rate": 0.001, + "loss": 1.9756, + "step": 1800 + }, + { + "epoch": 0.94, + "learning_rate": 0.001, + "loss": 1.9628, + "step": 1810 + }, + { + "epoch": 0.94, + "learning_rate": 0.001, + "loss": 1.952, + "step": 1820 + }, + { + "epoch": 0.95, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 1830 + }, + { + "epoch": 0.95, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 1840 + }, + { + "epoch": 0.96, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 1850 + }, + { + "epoch": 0.97, + "learning_rate": 0.001, + "loss": 1.938, + "step": 1860 + }, + { + "epoch": 0.97, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 1870 + }, + { + "epoch": 0.98, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 1880 + }, + { + "epoch": 0.98, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 1890 + }, + { + "epoch": 0.99, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 1900 + }, + { + "epoch": 0.99, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 1910 + }, + { + "epoch": 1.0, + "learning_rate": 0.001, + "loss": 1.981, + "step": 1920 + }, + { + "epoch": 1.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9584157466888428, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 201.5846, + "eval_samples_per_second": 19.123, + "eval_steps_per_second": 9.564, + "step": 1927 + }, + { + "epoch": 1.0, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 1930 + }, + { + "epoch": 1.01, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 1940 + }, + { + "epoch": 1.01, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 1950 + }, + { + "epoch": 1.02, + "learning_rate": 0.001, + "loss": 1.9192, + "step": 1960 + }, + { + "epoch": 1.02, + "learning_rate": 0.001, + "loss": 1.9903, + "step": 1970 + }, + { + "epoch": 1.03, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 1980 + }, + { + "epoch": 1.03, + "learning_rate": 0.001, + "loss": 1.9753, + "step": 1990 + }, + { + "epoch": 1.04, + "learning_rate": 0.001, + "loss": 1.9178, + "step": 2000 + }, + { + "epoch": 1.04, + "learning_rate": 0.001, + "loss": 1.925, + "step": 2010 + }, + { + "epoch": 1.05, + "learning_rate": 0.001, + "loss": 1.955, + "step": 2020 + }, + { + "epoch": 1.05, + "learning_rate": 0.001, + "loss": 1.9774, + "step": 2030 + }, + { + "epoch": 1.06, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 2040 + }, + { + "epoch": 1.06, + "learning_rate": 0.001, + "loss": 1.9794, + "step": 2050 + }, + { + "epoch": 1.07, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 2060 + }, + { + "epoch": 1.07, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 2070 + }, + { + "epoch": 1.08, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 2080 + }, + { + "epoch": 1.08, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 2090 + }, + { + "epoch": 1.09, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 2100 + }, + { + "epoch": 1.09, + "learning_rate": 0.001, + "loss": 1.936, + "step": 2110 + }, + { + "epoch": 1.1, + "learning_rate": 0.001, + "loss": 1.9811, + "step": 2120 + }, + { + "epoch": 1.11, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 2130 + }, + { + "epoch": 1.11, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 2140 + }, + { + "epoch": 1.12, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 2150 + }, + { + "epoch": 1.12, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 2160 + }, + { + "epoch": 1.13, + "learning_rate": 0.001, + "loss": 1.944, + "step": 2170 + }, + { + "epoch": 1.13, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 2180 + }, + { + "epoch": 1.14, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 2190 + }, + { + "epoch": 1.14, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 2200 + }, + { + "epoch": 1.15, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 2210 + }, + { + "epoch": 1.15, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 2220 + }, + { + "epoch": 1.16, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 2230 + }, + { + "epoch": 1.16, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 2240 + }, + { + "epoch": 1.17, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 2250 + }, + { + "epoch": 1.17, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 2260 + }, + { + "epoch": 1.18, + "learning_rate": 0.001, + "loss": 1.9719, + "step": 2270 + }, + { + "epoch": 1.18, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 2280 + }, + { + "epoch": 1.19, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 2290 + }, + { + "epoch": 1.19, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 2300 + }, + { + "epoch": 1.2, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 2310 + }, + { + "epoch": 1.2, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 2320 + }, + { + "epoch": 1.21, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 2330 + }, + { + "epoch": 1.21, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 2340 + }, + { + "epoch": 1.22, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 2350 + }, + { + "epoch": 1.22, + "learning_rate": 0.001, + "loss": 1.9686, + "step": 2360 + }, + { + "epoch": 1.23, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 2370 + }, + { + "epoch": 1.24, + "learning_rate": 0.001, + "loss": 1.955, + "step": 2380 + }, + { + "epoch": 1.24, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 2390 + }, + { + "epoch": 1.25, + "learning_rate": 0.001, + "loss": 1.947, + "step": 2400 + }, + { + "epoch": 1.25, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 2410 + }, + { + "epoch": 1.26, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 2420 + }, + { + "epoch": 1.26, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 2430 + }, + { + "epoch": 1.27, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 2440 + }, + { + "epoch": 1.27, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 2450 + }, + { + "epoch": 1.28, + "learning_rate": 0.001, + "loss": 1.939, + "step": 2460 + }, + { + "epoch": 1.28, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 2470 + }, + { + "epoch": 1.29, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 2480 + }, + { + "epoch": 1.29, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 2490 + }, + { + "epoch": 1.3, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 2500 + }, + { + "epoch": 1.3, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 2510 + }, + { + "epoch": 1.31, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 2520 + }, + { + "epoch": 1.31, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 2530 + }, + { + "epoch": 1.32, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 2540 + }, + { + "epoch": 1.32, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 2550 + }, + { + "epoch": 1.33, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 2560 + }, + { + "epoch": 1.33, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 2570 + }, + { + "epoch": 1.34, + "learning_rate": 0.001, + "loss": 1.9223, + "step": 2580 + }, + { + "epoch": 1.34, + "learning_rate": 0.001, + "loss": 1.9679, + "step": 2590 + }, + { + "epoch": 1.35, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 2600 + }, + { + "epoch": 1.35, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 2610 + }, + { + "epoch": 1.36, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 2620 + }, + { + "epoch": 1.36, + "learning_rate": 0.001, + "loss": 1.951, + "step": 2630 + }, + { + "epoch": 1.37, + "learning_rate": 0.001, + "loss": 1.9154, + "step": 2640 + }, + { + "epoch": 1.38, + "learning_rate": 0.001, + "loss": 1.965, + "step": 2650 + }, + { + "epoch": 1.38, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 2660 + }, + { + "epoch": 1.39, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 2670 + }, + { + "epoch": 1.39, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 2680 + }, + { + "epoch": 1.4, + "learning_rate": 0.001, + "loss": 1.9597, + "step": 2690 + }, + { + "epoch": 1.4, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 2700 + }, + { + "epoch": 1.41, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 2710 + }, + { + "epoch": 1.41, + "learning_rate": 0.001, + "loss": 1.934, + "step": 2720 + }, + { + "epoch": 1.42, + "learning_rate": 0.001, + "loss": 1.921, + "step": 2730 + }, + { + "epoch": 1.42, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 2740 + }, + { + "epoch": 1.43, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 2750 + }, + { + "epoch": 1.43, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 2760 + }, + { + "epoch": 1.44, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 2770 + }, + { + "epoch": 1.44, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 2780 + }, + { + "epoch": 1.45, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 2790 + }, + { + "epoch": 1.45, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 2800 + }, + { + "epoch": 1.46, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 2810 + }, + { + "epoch": 1.46, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 2820 + }, + { + "epoch": 1.47, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 2830 + }, + { + "epoch": 1.47, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 2840 + }, + { + "epoch": 1.48, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 2850 + }, + { + "epoch": 1.48, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 2860 + }, + { + "epoch": 1.49, + "learning_rate": 0.001, + "loss": 1.948, + "step": 2870 + }, + { + "epoch": 1.49, + "learning_rate": 0.001, + "loss": 1.9619, + "step": 2880 + }, + { + "epoch": 1.5, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 2890 + }, + { + "epoch": 1.5, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 2900 + }, + { + "epoch": 1.51, + "learning_rate": 0.001, + "loss": 1.9226, + "step": 2910 + }, + { + "epoch": 1.52, + "learning_rate": 0.001, + "loss": 1.9836, + "step": 2920 + }, + { + "epoch": 1.52, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 2930 + }, + { + "epoch": 1.53, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 2940 + }, + { + "epoch": 1.53, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 2950 + }, + { + "epoch": 1.54, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 2960 + }, + { + "epoch": 1.54, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 2970 + }, + { + "epoch": 1.55, + "learning_rate": 0.001, + "loss": 1.942, + "step": 2980 + }, + { + "epoch": 1.55, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 2990 + }, + { + "epoch": 1.56, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 3000 + }, + { + "epoch": 1.56, + "learning_rate": 0.001, + "loss": 1.9591, + "step": 3010 + }, + { + "epoch": 1.57, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 3020 + }, + { + "epoch": 1.57, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 3030 + }, + { + "epoch": 1.58, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 3040 + }, + { + "epoch": 1.58, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 3050 + }, + { + "epoch": 1.59, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 3060 + }, + { + "epoch": 1.59, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 3070 + }, + { + "epoch": 1.6, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 3080 + }, + { + "epoch": 1.6, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 3090 + }, + { + "epoch": 1.61, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 3100 + }, + { + "epoch": 1.61, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 3110 + }, + { + "epoch": 1.62, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 3120 + }, + { + "epoch": 1.62, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 3130 + }, + { + "epoch": 1.63, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 3140 + }, + { + "epoch": 1.63, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 3150 + }, + { + "epoch": 1.64, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 3160 + }, + { + "epoch": 1.65, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 3170 + }, + { + "epoch": 1.65, + "learning_rate": 0.001, + "loss": 1.9731, + "step": 3180 + }, + { + "epoch": 1.66, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 3190 + }, + { + "epoch": 1.66, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 3200 + }, + { + "epoch": 1.67, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 3210 + }, + { + "epoch": 1.67, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 3220 + }, + { + "epoch": 1.68, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 3230 + }, + { + "epoch": 1.68, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 3240 + }, + { + "epoch": 1.69, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 3250 + }, + { + "epoch": 1.69, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 3260 + }, + { + "epoch": 1.7, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 3270 + }, + { + "epoch": 1.7, + "learning_rate": 0.001, + "loss": 1.953, + "step": 3280 + }, + { + "epoch": 1.71, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 3290 + }, + { + "epoch": 1.71, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 3300 + }, + { + "epoch": 1.72, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 3310 + }, + { + "epoch": 1.72, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 3320 + }, + { + "epoch": 1.73, + "learning_rate": 0.001, + "loss": 1.9654, + "step": 3330 + }, + { + "epoch": 1.73, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 3340 + }, + { + "epoch": 1.74, + "learning_rate": 0.001, + "loss": 1.956, + "step": 3350 + }, + { + "epoch": 1.74, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 3360 + }, + { + "epoch": 1.75, + "learning_rate": 0.001, + "loss": 1.9138, + "step": 3370 + }, + { + "epoch": 1.75, + "learning_rate": 0.001, + "loss": 1.928, + "step": 3380 + }, + { + "epoch": 1.76, + "learning_rate": 0.001, + "loss": 1.9845, + "step": 3390 + }, + { + "epoch": 1.76, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 3400 + }, + { + "epoch": 1.77, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 3410 + }, + { + "epoch": 1.77, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 3420 + }, + { + "epoch": 1.78, + "learning_rate": 0.001, + "loss": 1.935, + "step": 3430 + }, + { + "epoch": 1.79, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 3440 + }, + { + "epoch": 1.79, + "learning_rate": 0.001, + "loss": 1.931, + "step": 3450 + }, + { + "epoch": 1.8, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 3460 + }, + { + "epoch": 1.8, + "learning_rate": 0.001, + "loss": 1.949, + "step": 3470 + }, + { + "epoch": 1.81, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 3480 + }, + { + "epoch": 1.81, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 3490 + }, + { + "epoch": 1.82, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 3500 + }, + { + "epoch": 1.82, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 3510 + }, + { + "epoch": 1.83, + "learning_rate": 0.001, + "loss": 1.9056, + "step": 3520 + }, + { + "epoch": 1.83, + "learning_rate": 0.001, + "loss": 1.9871, + "step": 3530 + }, + { + "epoch": 1.84, + "learning_rate": 0.001, + "loss": 1.9884, + "step": 3540 + }, + { + "epoch": 1.84, + "learning_rate": 0.001, + "loss": 1.944, + "step": 3550 + }, + { + "epoch": 1.85, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 3560 + }, + { + "epoch": 1.85, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 3570 + }, + { + "epoch": 1.86, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 3580 + }, + { + "epoch": 1.86, + "learning_rate": 0.001, + "loss": 1.9259, + "step": 3590 + }, + { + "epoch": 1.87, + "learning_rate": 0.001, + "loss": 1.9648, + "step": 3600 + }, + { + "epoch": 1.87, + "learning_rate": 0.001, + "loss": 1.9642, + "step": 3610 + }, + { + "epoch": 1.88, + "learning_rate": 0.001, + "loss": 1.9677, + "step": 3620 + }, + { + "epoch": 1.88, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 3630 + }, + { + "epoch": 1.89, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 3640 + }, + { + "epoch": 1.89, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 3650 + }, + { + "epoch": 1.9, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 3660 + }, + { + "epoch": 1.9, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 3670 + }, + { + "epoch": 1.91, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 3680 + }, + { + "epoch": 1.91, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 3690 + }, + { + "epoch": 1.92, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 3700 + }, + { + "epoch": 1.93, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 3710 + }, + { + "epoch": 1.93, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 3720 + }, + { + "epoch": 1.94, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 3730 + }, + { + "epoch": 1.94, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 3740 + }, + { + "epoch": 1.95, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 3750 + }, + { + "epoch": 1.95, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 3760 + }, + { + "epoch": 1.96, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 3770 + }, + { + "epoch": 1.96, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 3780 + }, + { + "epoch": 1.97, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 3790 + }, + { + "epoch": 1.97, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 3800 + }, + { + "epoch": 1.98, + "learning_rate": 0.001, + "loss": 1.943, + "step": 3810 + }, + { + "epoch": 1.98, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 3820 + }, + { + "epoch": 1.99, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 3830 + }, + { + "epoch": 1.99, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 3840 + }, + { + "epoch": 2.0, + "learning_rate": 0.001, + "loss": 1.951, + "step": 3850 + }, + { + "epoch": 2.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9446961879730225, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 78.0133, + "eval_samples_per_second": 49.415, + "eval_steps_per_second": 24.714, + "step": 3854 + }, + { + "epoch": 2.0, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 3860 + }, + { + "epoch": 2.01, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 3870 + }, + { + "epoch": 2.01, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 3880 + }, + { + "epoch": 2.02, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 3890 + }, + { + "epoch": 2.02, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 3900 + }, + { + "epoch": 2.03, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 3910 + }, + { + "epoch": 2.03, + "learning_rate": 0.001, + "loss": 1.9283, + "step": 3920 + }, + { + "epoch": 2.04, + "learning_rate": 0.001, + "loss": 1.9559, + "step": 3930 + }, + { + "epoch": 2.04, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 3940 + }, + { + "epoch": 2.05, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 3950 + }, + { + "epoch": 2.06, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 3960 + }, + { + "epoch": 2.06, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 3970 + }, + { + "epoch": 2.07, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 3980 + }, + { + "epoch": 2.07, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 3990 + }, + { + "epoch": 2.08, + "learning_rate": 0.001, + "loss": 1.949, + "step": 4000 + }, + { + "epoch": 2.08, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 4010 + }, + { + "epoch": 2.09, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 4020 + }, + { + "epoch": 2.09, + "learning_rate": 0.001, + "loss": 1.935, + "step": 4030 + }, + { + "epoch": 2.1, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 4040 + }, + { + "epoch": 2.1, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 4050 + }, + { + "epoch": 2.11, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 4060 + }, + { + "epoch": 2.11, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 4070 + }, + { + "epoch": 2.12, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 4080 + }, + { + "epoch": 2.12, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 4090 + }, + { + "epoch": 2.13, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 4100 + }, + { + "epoch": 2.13, + "learning_rate": 0.001, + "loss": 1.942, + "step": 4110 + }, + { + "epoch": 2.14, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 4120 + }, + { + "epoch": 2.14, + "learning_rate": 0.001, + "loss": 1.94, + "step": 4130 + }, + { + "epoch": 2.15, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 4140 + }, + { + "epoch": 2.15, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 4150 + }, + { + "epoch": 2.16, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 4160 + }, + { + "epoch": 2.16, + "learning_rate": 0.001, + "loss": 1.9266, + "step": 4170 + }, + { + "epoch": 2.17, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 4180 + }, + { + "epoch": 2.17, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 4190 + }, + { + "epoch": 2.18, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 4200 + }, + { + "epoch": 2.18, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 4210 + }, + { + "epoch": 2.19, + "learning_rate": 0.001, + "loss": 1.952, + "step": 4220 + }, + { + "epoch": 2.2, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 4230 + }, + { + "epoch": 2.2, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 4240 + }, + { + "epoch": 2.21, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 4250 + }, + { + "epoch": 2.21, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 4260 + }, + { + "epoch": 2.22, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 4270 + }, + { + "epoch": 2.22, + "learning_rate": 0.001, + "loss": 1.944, + "step": 4280 + }, + { + "epoch": 2.23, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 4290 + }, + { + "epoch": 2.23, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 4300 + }, + { + "epoch": 2.24, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 4310 + }, + { + "epoch": 2.24, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 4320 + }, + { + "epoch": 2.25, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 4330 + }, + { + "epoch": 2.25, + "learning_rate": 0.001, + "loss": 1.9253, + "step": 4340 + }, + { + "epoch": 2.26, + "learning_rate": 0.001, + "loss": 1.9697, + "step": 4350 + }, + { + "epoch": 2.26, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 4360 + }, + { + "epoch": 2.27, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 4370 + }, + { + "epoch": 2.27, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 4380 + }, + { + "epoch": 2.28, + "learning_rate": 0.001, + "loss": 1.95, + "step": 4390 + }, + { + "epoch": 2.28, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 4400 + }, + { + "epoch": 2.29, + "learning_rate": 0.001, + "loss": 1.958, + "step": 4410 + }, + { + "epoch": 2.29, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 4420 + }, + { + "epoch": 2.3, + "learning_rate": 0.001, + "loss": 1.9225, + "step": 4430 + }, + { + "epoch": 2.3, + "learning_rate": 0.001, + "loss": 1.9194, + "step": 4440 + }, + { + "epoch": 2.31, + "learning_rate": 0.001, + "loss": 1.9816, + "step": 4450 + }, + { + "epoch": 2.31, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 4460 + }, + { + "epoch": 2.32, + "learning_rate": 0.001, + "loss": 1.939, + "step": 4470 + }, + { + "epoch": 2.32, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 4480 + }, + { + "epoch": 2.33, + "learning_rate": 0.001, + "loss": 1.955, + "step": 4490 + }, + { + "epoch": 2.34, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 4500 + }, + { + "epoch": 2.34, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 4510 + }, + { + "epoch": 2.35, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 4520 + }, + { + "epoch": 2.35, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 4530 + }, + { + "epoch": 2.36, + "learning_rate": 0.001, + "loss": 1.9262, + "step": 4540 + }, + { + "epoch": 2.36, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 4550 + }, + { + "epoch": 2.37, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 4560 + }, + { + "epoch": 2.37, + "learning_rate": 0.001, + "loss": 1.9701, + "step": 4570 + }, + { + "epoch": 2.38, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 4580 + }, + { + "epoch": 2.38, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 4590 + }, + { + "epoch": 2.39, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 4600 + }, + { + "epoch": 2.39, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 4610 + }, + { + "epoch": 2.4, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 4620 + }, + { + "epoch": 2.4, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 4630 + }, + { + "epoch": 2.41, + "learning_rate": 0.001, + "loss": 1.9659, + "step": 4640 + }, + { + "epoch": 2.41, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 4650 + }, + { + "epoch": 2.42, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 4660 + }, + { + "epoch": 2.42, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 4670 + }, + { + "epoch": 2.43, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 4680 + }, + { + "epoch": 2.43, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 4690 + }, + { + "epoch": 2.44, + "learning_rate": 0.001, + "loss": 1.9659, + "step": 4700 + }, + { + "epoch": 2.44, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 4710 + }, + { + "epoch": 2.45, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 4720 + }, + { + "epoch": 2.45, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 4730 + }, + { + "epoch": 2.46, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 4740 + }, + { + "epoch": 2.46, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 4750 + }, + { + "epoch": 2.47, + "learning_rate": 0.001, + "loss": 1.94, + "step": 4760 + }, + { + "epoch": 2.48, + "learning_rate": 0.001, + "loss": 1.9248, + "step": 4770 + }, + { + "epoch": 2.48, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 4780 + }, + { + "epoch": 2.49, + "learning_rate": 0.001, + "loss": 1.9833, + "step": 4790 + }, + { + "epoch": 2.49, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 4800 + }, + { + "epoch": 2.5, + "learning_rate": 0.001, + "loss": 1.939, + "step": 4810 + }, + { + "epoch": 2.5, + "learning_rate": 0.001, + "loss": 1.9267, + "step": 4820 + }, + { + "epoch": 2.51, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 4830 + }, + { + "epoch": 2.51, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 4840 + }, + { + "epoch": 2.52, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 4850 + }, + { + "epoch": 2.52, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 4860 + }, + { + "epoch": 2.53, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 4870 + }, + { + "epoch": 2.53, + "learning_rate": 0.001, + "loss": 1.92, + "step": 4880 + }, + { + "epoch": 2.54, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 4890 + }, + { + "epoch": 2.54, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 4900 + }, + { + "epoch": 2.55, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 4910 + }, + { + "epoch": 2.55, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 4920 + }, + { + "epoch": 2.56, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 4930 + }, + { + "epoch": 2.56, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 4940 + }, + { + "epoch": 2.57, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 4950 + }, + { + "epoch": 2.57, + "learning_rate": 0.001, + "loss": 1.951, + "step": 4960 + }, + { + "epoch": 2.58, + "learning_rate": 0.001, + "loss": 1.8918, + "step": 4970 + }, + { + "epoch": 2.58, + "learning_rate": 0.001, + "loss": 1.94, + "step": 4980 + }, + { + "epoch": 2.59, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 4990 + }, + { + "epoch": 2.59, + "learning_rate": 0.001, + "loss": 1.9679, + "step": 5000 + }, + { + "epoch": 2.6, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 5010 + }, + { + "epoch": 2.61, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 5020 + }, + { + "epoch": 2.61, + "learning_rate": 0.001, + "loss": 1.929, + "step": 5030 + }, + { + "epoch": 2.62, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 5040 + }, + { + "epoch": 2.62, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 5050 + }, + { + "epoch": 2.63, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 5060 + }, + { + "epoch": 2.63, + "learning_rate": 0.001, + "loss": 1.9235, + "step": 5070 + }, + { + "epoch": 2.64, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 5080 + }, + { + "epoch": 2.64, + "learning_rate": 0.001, + "loss": 1.9806, + "step": 5090 + }, + { + "epoch": 2.65, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 5100 + }, + { + "epoch": 2.65, + "learning_rate": 0.001, + "loss": 1.9781, + "step": 5110 + }, + { + "epoch": 2.66, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 5120 + }, + { + "epoch": 2.66, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 5130 + }, + { + "epoch": 2.67, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 5140 + }, + { + "epoch": 2.67, + "learning_rate": 0.001, + "loss": 1.967, + "step": 5150 + }, + { + "epoch": 2.68, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 5160 + }, + { + "epoch": 2.68, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 5170 + }, + { + "epoch": 2.69, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 5180 + }, + { + "epoch": 2.69, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 5190 + }, + { + "epoch": 2.7, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 5200 + }, + { + "epoch": 2.7, + "learning_rate": 0.001, + "loss": 1.96, + "step": 5210 + }, + { + "epoch": 2.71, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 5220 + }, + { + "epoch": 2.71, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 5230 + }, + { + "epoch": 2.72, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 5240 + }, + { + "epoch": 2.72, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 5250 + }, + { + "epoch": 2.73, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 5260 + }, + { + "epoch": 2.73, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 5270 + }, + { + "epoch": 2.74, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 5280 + }, + { + "epoch": 2.75, + "learning_rate": 0.001, + "loss": 1.9624, + "step": 5290 + }, + { + "epoch": 2.75, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 5300 + }, + { + "epoch": 2.76, + "learning_rate": 0.001, + "loss": 1.9217, + "step": 5310 + }, + { + "epoch": 2.76, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 5320 + }, + { + "epoch": 2.77, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 5330 + }, + { + "epoch": 2.77, + "learning_rate": 0.001, + "loss": 1.99, + "step": 5340 + }, + { + "epoch": 2.78, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 5350 + }, + { + "epoch": 2.78, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 5360 + }, + { + "epoch": 2.79, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 5370 + }, + { + "epoch": 2.79, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 5380 + }, + { + "epoch": 2.8, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 5390 + }, + { + "epoch": 2.8, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 5400 + }, + { + "epoch": 2.81, + "learning_rate": 0.001, + "loss": 1.9821, + "step": 5410 + }, + { + "epoch": 2.81, + "learning_rate": 0.001, + "loss": 1.934, + "step": 5420 + }, + { + "epoch": 2.82, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 5430 + }, + { + "epoch": 2.82, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 5440 + }, + { + "epoch": 2.83, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 5450 + }, + { + "epoch": 2.83, + "learning_rate": 0.001, + "loss": 1.9197, + "step": 5460 + }, + { + "epoch": 2.84, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 5470 + }, + { + "epoch": 2.84, + "learning_rate": 0.001, + "loss": 1.9653, + "step": 5480 + }, + { + "epoch": 2.85, + "learning_rate": 0.001, + "loss": 1.947, + "step": 5490 + }, + { + "epoch": 2.85, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 5500 + }, + { + "epoch": 2.86, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 5510 + }, + { + "epoch": 2.86, + "learning_rate": 0.001, + "loss": 1.9582, + "step": 5520 + }, + { + "epoch": 2.87, + "learning_rate": 0.001, + "loss": 1.9202, + "step": 5530 + }, + { + "epoch": 2.87, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 5540 + }, + { + "epoch": 2.88, + "learning_rate": 0.001, + "loss": 1.939, + "step": 5550 + }, + { + "epoch": 2.89, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 5560 + }, + { + "epoch": 2.89, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 5570 + }, + { + "epoch": 2.9, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 5580 + }, + { + "epoch": 2.9, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 5590 + }, + { + "epoch": 2.91, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 5600 + }, + { + "epoch": 2.91, + "learning_rate": 0.001, + "loss": 1.959, + "step": 5610 + }, + { + "epoch": 2.92, + "learning_rate": 0.001, + "loss": 1.9649, + "step": 5620 + }, + { + "epoch": 2.92, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 5630 + }, + { + "epoch": 2.93, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 5640 + }, + { + "epoch": 2.93, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 5650 + }, + { + "epoch": 2.94, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 5660 + }, + { + "epoch": 2.94, + "learning_rate": 0.001, + "loss": 1.949, + "step": 5670 + }, + { + "epoch": 2.95, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 5680 + }, + { + "epoch": 2.95, + "learning_rate": 0.001, + "loss": 1.95, + "step": 5690 + }, + { + "epoch": 2.96, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 5700 + }, + { + "epoch": 2.96, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 5710 + }, + { + "epoch": 2.97, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 5720 + }, + { + "epoch": 2.97, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 5730 + }, + { + "epoch": 2.98, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 5740 + }, + { + "epoch": 2.98, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 5750 + }, + { + "epoch": 2.99, + "learning_rate": 0.001, + "loss": 1.9192, + "step": 5760 + }, + { + "epoch": 2.99, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 5770 + }, + { + "epoch": 3.0, + "learning_rate": 0.001, + "loss": 1.9799, + "step": 5780 + }, + { + "epoch": 3.0, + "eval_accuracy": { + "accuracy": 0.13618677042801555 + }, + "eval_f1": { + "f1": 0.03424657534246575 + }, + "eval_loss": 1.9497852325439453, + "eval_precision": { + "precision": 0.019455252918287935 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.5559, + "eval_samples_per_second": 49.706, + "eval_steps_per_second": 24.859, + "step": 5781 + }, + { + "epoch": 3.0, + "learning_rate": 0.001, + "loss": 1.9658, + "step": 5790 + }, + { + "epoch": 3.01, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 5800 + }, + { + "epoch": 3.02, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 5810 + }, + { + "epoch": 3.02, + "learning_rate": 0.001, + "loss": 1.957, + "step": 5820 + }, + { + "epoch": 3.03, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 5830 + }, + { + "epoch": 3.03, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 5840 + }, + { + "epoch": 3.04, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 5850 + }, + { + "epoch": 3.04, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 5860 + }, + { + "epoch": 3.05, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 5870 + }, + { + "epoch": 3.05, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 5880 + }, + { + "epoch": 3.06, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 5890 + }, + { + "epoch": 3.06, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 5900 + }, + { + "epoch": 3.07, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 5910 + }, + { + "epoch": 3.07, + "learning_rate": 0.001, + "loss": 1.944, + "step": 5920 + }, + { + "epoch": 3.08, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 5930 + }, + { + "epoch": 3.08, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 5940 + }, + { + "epoch": 3.09, + "learning_rate": 0.001, + "loss": 1.9169, + "step": 5950 + }, + { + "epoch": 3.09, + "learning_rate": 0.001, + "loss": 1.9782, + "step": 5960 + }, + { + "epoch": 3.1, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 5970 + }, + { + "epoch": 3.1, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 5980 + }, + { + "epoch": 3.11, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 5990 + }, + { + "epoch": 3.11, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 6000 + }, + { + "epoch": 3.12, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 6010 + }, + { + "epoch": 3.12, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 6020 + }, + { + "epoch": 3.13, + "learning_rate": 0.001, + "loss": 1.9587, + "step": 6030 + }, + { + "epoch": 3.13, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 6040 + }, + { + "epoch": 3.14, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 6050 + }, + { + "epoch": 3.14, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 6060 + }, + { + "epoch": 3.15, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 6070 + }, + { + "epoch": 3.16, + "learning_rate": 0.001, + "loss": 1.9602, + "step": 6080 + }, + { + "epoch": 3.16, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 6090 + }, + { + "epoch": 3.17, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 6100 + }, + { + "epoch": 3.17, + "learning_rate": 0.001, + "loss": 1.935, + "step": 6110 + }, + { + "epoch": 3.18, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 6120 + }, + { + "epoch": 3.18, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 6130 + }, + { + "epoch": 3.19, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 6140 + }, + { + "epoch": 3.19, + "learning_rate": 0.001, + "loss": 1.943, + "step": 6150 + }, + { + "epoch": 3.2, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 6160 + }, + { + "epoch": 3.2, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 6170 + }, + { + "epoch": 3.21, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 6180 + }, + { + "epoch": 3.21, + "learning_rate": 0.001, + "loss": 1.946, + "step": 6190 + }, + { + "epoch": 3.22, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 6200 + }, + { + "epoch": 3.22, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 6210 + }, + { + "epoch": 3.23, + "learning_rate": 0.001, + "loss": 1.943, + "step": 6220 + }, + { + "epoch": 3.23, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 6230 + }, + { + "epoch": 3.24, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 6240 + }, + { + "epoch": 3.24, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 6250 + }, + { + "epoch": 3.25, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 6260 + }, + { + "epoch": 3.25, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 6270 + }, + { + "epoch": 3.26, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 6280 + }, + { + "epoch": 3.26, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 6290 + }, + { + "epoch": 3.27, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 6300 + }, + { + "epoch": 3.27, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 6310 + }, + { + "epoch": 3.28, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 6320 + }, + { + "epoch": 3.28, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 6330 + }, + { + "epoch": 3.29, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 6340 + }, + { + "epoch": 3.3, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 6350 + }, + { + "epoch": 3.3, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 6360 + }, + { + "epoch": 3.31, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 6370 + }, + { + "epoch": 3.31, + "learning_rate": 0.001, + "loss": 1.9617, + "step": 6380 + }, + { + "epoch": 3.32, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 6390 + }, + { + "epoch": 3.32, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 6400 + }, + { + "epoch": 3.33, + "learning_rate": 0.001, + "loss": 1.9657, + "step": 6410 + }, + { + "epoch": 3.33, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 6420 + }, + { + "epoch": 3.34, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 6430 + }, + { + "epoch": 3.34, + "learning_rate": 0.001, + "loss": 1.941, + "step": 6440 + }, + { + "epoch": 3.35, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 6450 + }, + { + "epoch": 3.35, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 6460 + }, + { + "epoch": 3.36, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 6470 + }, + { + "epoch": 3.36, + "learning_rate": 0.001, + "loss": 1.9664, + "step": 6480 + }, + { + "epoch": 3.37, + "learning_rate": 0.001, + "loss": 1.9279, + "step": 6490 + }, + { + "epoch": 3.37, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 6500 + }, + { + "epoch": 3.38, + "learning_rate": 0.001, + "loss": 1.9162, + "step": 6510 + }, + { + "epoch": 3.38, + "learning_rate": 0.001, + "loss": 1.9218, + "step": 6520 + }, + { + "epoch": 3.39, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 6530 + }, + { + "epoch": 3.39, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 6540 + }, + { + "epoch": 3.4, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 6550 + }, + { + "epoch": 3.4, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 6560 + }, + { + "epoch": 3.41, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 6570 + }, + { + "epoch": 3.41, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 6580 + }, + { + "epoch": 3.42, + "learning_rate": 0.001, + "loss": 1.944, + "step": 6590 + }, + { + "epoch": 3.43, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 6600 + }, + { + "epoch": 3.43, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 6610 + }, + { + "epoch": 3.44, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 6620 + }, + { + "epoch": 3.44, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 6630 + }, + { + "epoch": 3.45, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 6640 + }, + { + "epoch": 3.45, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 6650 + }, + { + "epoch": 3.46, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 6660 + }, + { + "epoch": 3.46, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 6670 + }, + { + "epoch": 3.47, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 6680 + }, + { + "epoch": 3.47, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 6690 + }, + { + "epoch": 3.48, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 6700 + }, + { + "epoch": 3.48, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 6710 + }, + { + "epoch": 3.49, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 6720 + }, + { + "epoch": 3.49, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 6730 + }, + { + "epoch": 3.5, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 6740 + }, + { + "epoch": 3.5, + "learning_rate": 0.001, + "loss": 1.9642, + "step": 6750 + }, + { + "epoch": 3.51, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 6760 + }, + { + "epoch": 3.51, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 6770 + }, + { + "epoch": 3.52, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 6780 + }, + { + "epoch": 3.52, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 6790 + }, + { + "epoch": 3.53, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 6800 + }, + { + "epoch": 3.53, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 6810 + }, + { + "epoch": 3.54, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 6820 + }, + { + "epoch": 3.54, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 6830 + }, + { + "epoch": 3.55, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 6840 + }, + { + "epoch": 3.55, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 6850 + }, + { + "epoch": 3.56, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 6860 + }, + { + "epoch": 3.57, + "learning_rate": 0.001, + "loss": 1.9679, + "step": 6870 + }, + { + "epoch": 3.57, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 6880 + }, + { + "epoch": 3.58, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 6890 + }, + { + "epoch": 3.58, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 6900 + }, + { + "epoch": 3.59, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 6910 + }, + { + "epoch": 3.59, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 6920 + }, + { + "epoch": 3.6, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 6930 + }, + { + "epoch": 3.6, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 6940 + }, + { + "epoch": 3.61, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 6950 + }, + { + "epoch": 3.61, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 6960 + }, + { + "epoch": 3.62, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 6970 + }, + { + "epoch": 3.62, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 6980 + }, + { + "epoch": 3.63, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 6990 + }, + { + "epoch": 3.63, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 7000 + }, + { + "epoch": 3.64, + "learning_rate": 0.001, + "loss": 1.933, + "step": 7010 + }, + { + "epoch": 3.64, + "learning_rate": 0.001, + "loss": 1.9064, + "step": 7020 + }, + { + "epoch": 3.65, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 7030 + }, + { + "epoch": 3.65, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 7040 + }, + { + "epoch": 3.66, + "learning_rate": 0.001, + "loss": 1.946, + "step": 7050 + }, + { + "epoch": 3.66, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 7060 + }, + { + "epoch": 3.67, + "learning_rate": 0.001, + "loss": 1.8934, + "step": 7070 + }, + { + "epoch": 3.67, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 7080 + }, + { + "epoch": 3.68, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 7090 + }, + { + "epoch": 3.68, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 7100 + }, + { + "epoch": 3.69, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 7110 + }, + { + "epoch": 3.69, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 7120 + }, + { + "epoch": 3.7, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 7130 + }, + { + "epoch": 3.71, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 7140 + }, + { + "epoch": 3.71, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 7150 + }, + { + "epoch": 3.72, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 7160 + }, + { + "epoch": 3.72, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 7170 + }, + { + "epoch": 3.73, + "learning_rate": 0.001, + "loss": 1.9574, + "step": 7180 + }, + { + "epoch": 3.73, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 7190 + }, + { + "epoch": 3.74, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 7200 + }, + { + "epoch": 3.74, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 7210 + }, + { + "epoch": 3.75, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 7220 + }, + { + "epoch": 3.75, + "learning_rate": 0.001, + "loss": 1.9731, + "step": 7230 + }, + { + "epoch": 3.76, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 7240 + }, + { + "epoch": 3.76, + "learning_rate": 0.001, + "loss": 1.949, + "step": 7250 + }, + { + "epoch": 3.77, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 7260 + }, + { + "epoch": 3.77, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 7270 + }, + { + "epoch": 3.78, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 7280 + }, + { + "epoch": 3.78, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 7290 + }, + { + "epoch": 3.79, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 7300 + }, + { + "epoch": 3.79, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 7310 + }, + { + "epoch": 3.8, + "learning_rate": 0.001, + "loss": 1.931, + "step": 7320 + }, + { + "epoch": 3.8, + "learning_rate": 0.001, + "loss": 1.9003, + "step": 7330 + }, + { + "epoch": 3.81, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 7340 + }, + { + "epoch": 3.81, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 7350 + }, + { + "epoch": 3.82, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 7360 + }, + { + "epoch": 3.82, + "learning_rate": 0.001, + "loss": 1.946, + "step": 7370 + }, + { + "epoch": 3.83, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 7380 + }, + { + "epoch": 3.83, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 7390 + }, + { + "epoch": 3.84, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 7400 + }, + { + "epoch": 3.85, + "learning_rate": 0.001, + "loss": 1.967, + "step": 7410 + }, + { + "epoch": 3.85, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 7420 + }, + { + "epoch": 3.86, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 7430 + }, + { + "epoch": 3.86, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 7440 + }, + { + "epoch": 3.87, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 7450 + }, + { + "epoch": 3.87, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 7460 + }, + { + "epoch": 3.88, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 7470 + }, + { + "epoch": 3.88, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 7480 + }, + { + "epoch": 3.89, + "learning_rate": 0.001, + "loss": 1.9622, + "step": 7490 + }, + { + "epoch": 3.89, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 7500 + }, + { + "epoch": 3.9, + "learning_rate": 0.001, + "loss": 1.9044, + "step": 7510 + }, + { + "epoch": 3.9, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 7520 + }, + { + "epoch": 3.91, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 7530 + }, + { + "epoch": 3.91, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 7540 + }, + { + "epoch": 3.92, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 7550 + }, + { + "epoch": 3.92, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 7560 + }, + { + "epoch": 3.93, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 7570 + }, + { + "epoch": 3.93, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 7580 + }, + { + "epoch": 3.94, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 7590 + }, + { + "epoch": 3.94, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 7600 + }, + { + "epoch": 3.95, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 7610 + }, + { + "epoch": 3.95, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 7620 + }, + { + "epoch": 3.96, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 7630 + }, + { + "epoch": 3.96, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 7640 + }, + { + "epoch": 3.97, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 7650 + }, + { + "epoch": 3.98, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 7660 + }, + { + "epoch": 3.98, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 7670 + }, + { + "epoch": 3.99, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 7680 + }, + { + "epoch": 3.99, + "learning_rate": 0.001, + "loss": 1.9615, + "step": 7690 + }, + { + "epoch": 4.0, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 7700 + }, + { + "epoch": 4.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9412175416946411, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.9759, + "eval_samples_per_second": 49.438, + "eval_steps_per_second": 24.726, + "step": 7708 + }, + { + "epoch": 4.0, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 7710 + }, + { + "epoch": 4.01, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 7720 + }, + { + "epoch": 4.01, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 7730 + }, + { + "epoch": 4.02, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 7740 + }, + { + "epoch": 4.02, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 7750 + }, + { + "epoch": 4.03, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 7760 + }, + { + "epoch": 4.03, + "learning_rate": 0.001, + "loss": 1.939, + "step": 7770 + }, + { + "epoch": 4.04, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 7780 + }, + { + "epoch": 4.04, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 7790 + }, + { + "epoch": 4.05, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 7800 + }, + { + "epoch": 4.05, + "learning_rate": 0.001, + "loss": 1.9636, + "step": 7810 + }, + { + "epoch": 4.06, + "learning_rate": 0.001, + "loss": 1.9634, + "step": 7820 + }, + { + "epoch": 4.06, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 7830 + }, + { + "epoch": 4.07, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 7840 + }, + { + "epoch": 4.07, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 7850 + }, + { + "epoch": 4.08, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 7860 + }, + { + "epoch": 4.08, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 7870 + }, + { + "epoch": 4.09, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 7880 + }, + { + "epoch": 4.09, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 7890 + }, + { + "epoch": 4.1, + "learning_rate": 0.001, + "loss": 1.929, + "step": 7900 + }, + { + "epoch": 4.1, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 7910 + }, + { + "epoch": 4.11, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 7920 + }, + { + "epoch": 4.12, + "learning_rate": 0.001, + "loss": 1.9622, + "step": 7930 + }, + { + "epoch": 4.12, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 7940 + }, + { + "epoch": 4.13, + "learning_rate": 0.001, + "loss": 1.9243, + "step": 7950 + }, + { + "epoch": 4.13, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 7960 + }, + { + "epoch": 4.14, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 7970 + }, + { + "epoch": 4.14, + "learning_rate": 0.001, + "loss": 1.9191, + "step": 7980 + }, + { + "epoch": 4.15, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 7990 + }, + { + "epoch": 4.15, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 8000 + }, + { + "epoch": 4.16, + "learning_rate": 0.001, + "loss": 1.9774, + "step": 8010 + }, + { + "epoch": 4.16, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 8020 + }, + { + "epoch": 4.17, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 8030 + }, + { + "epoch": 4.17, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 8040 + }, + { + "epoch": 4.18, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 8050 + }, + { + "epoch": 4.18, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 8060 + }, + { + "epoch": 4.19, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 8070 + }, + { + "epoch": 4.19, + "learning_rate": 0.001, + "loss": 1.9786, + "step": 8080 + }, + { + "epoch": 4.2, + "learning_rate": 0.001, + "loss": 1.9257, + "step": 8090 + }, + { + "epoch": 4.2, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 8100 + }, + { + "epoch": 4.21, + "learning_rate": 0.001, + "loss": 1.9279, + "step": 8110 + }, + { + "epoch": 4.21, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 8120 + }, + { + "epoch": 4.22, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 8130 + }, + { + "epoch": 4.22, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 8140 + }, + { + "epoch": 4.23, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 8150 + }, + { + "epoch": 4.23, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 8160 + }, + { + "epoch": 4.24, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 8170 + }, + { + "epoch": 4.24, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 8180 + }, + { + "epoch": 4.25, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 8190 + }, + { + "epoch": 4.26, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 8200 + }, + { + "epoch": 4.26, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 8210 + }, + { + "epoch": 4.27, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 8220 + }, + { + "epoch": 4.27, + "learning_rate": 0.001, + "loss": 1.9633, + "step": 8230 + }, + { + "epoch": 4.28, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 8240 + }, + { + "epoch": 4.28, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 8250 + }, + { + "epoch": 4.29, + "learning_rate": 0.001, + "loss": 1.954, + "step": 8260 + }, + { + "epoch": 4.29, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 8270 + }, + { + "epoch": 4.3, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 8280 + }, + { + "epoch": 4.3, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 8290 + }, + { + "epoch": 4.31, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 8300 + }, + { + "epoch": 4.31, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 8310 + }, + { + "epoch": 4.32, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 8320 + }, + { + "epoch": 4.32, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 8330 + }, + { + "epoch": 4.33, + "learning_rate": 0.001, + "loss": 1.9559, + "step": 8340 + }, + { + "epoch": 4.33, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 8350 + }, + { + "epoch": 4.34, + "learning_rate": 0.001, + "loss": 1.9615, + "step": 8360 + }, + { + "epoch": 4.34, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 8370 + }, + { + "epoch": 4.35, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 8380 + }, + { + "epoch": 4.35, + "learning_rate": 0.001, + "loss": 1.947, + "step": 8390 + }, + { + "epoch": 4.36, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 8400 + }, + { + "epoch": 4.36, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 8410 + }, + { + "epoch": 4.37, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 8420 + }, + { + "epoch": 4.37, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 8430 + }, + { + "epoch": 4.38, + "learning_rate": 0.001, + "loss": 1.93, + "step": 8440 + }, + { + "epoch": 4.39, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 8450 + }, + { + "epoch": 4.39, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 8460 + }, + { + "epoch": 4.4, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 8470 + }, + { + "epoch": 4.4, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 8480 + }, + { + "epoch": 4.41, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 8490 + }, + { + "epoch": 4.41, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 8500 + }, + { + "epoch": 4.42, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 8510 + }, + { + "epoch": 4.42, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 8520 + }, + { + "epoch": 4.43, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 8530 + }, + { + "epoch": 4.43, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 8540 + }, + { + "epoch": 4.44, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 8550 + }, + { + "epoch": 4.44, + "learning_rate": 0.001, + "loss": 1.9077, + "step": 8560 + }, + { + "epoch": 4.45, + "learning_rate": 0.001, + "loss": 1.9779, + "step": 8570 + }, + { + "epoch": 4.45, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 8580 + }, + { + "epoch": 4.46, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 8590 + }, + { + "epoch": 4.46, + "learning_rate": 0.001, + "loss": 1.9254, + "step": 8600 + }, + { + "epoch": 4.47, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 8610 + }, + { + "epoch": 4.47, + "learning_rate": 0.001, + "loss": 1.946, + "step": 8620 + }, + { + "epoch": 4.48, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 8630 + }, + { + "epoch": 4.48, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 8640 + }, + { + "epoch": 4.49, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 8650 + }, + { + "epoch": 4.49, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 8660 + }, + { + "epoch": 4.5, + "learning_rate": 0.001, + "loss": 1.962, + "step": 8670 + }, + { + "epoch": 4.5, + "learning_rate": 0.001, + "loss": 1.958, + "step": 8680 + }, + { + "epoch": 4.51, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 8690 + }, + { + "epoch": 4.51, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 8700 + }, + { + "epoch": 4.52, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 8710 + }, + { + "epoch": 4.53, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 8720 + }, + { + "epoch": 4.53, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 8730 + }, + { + "epoch": 4.54, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 8740 + }, + { + "epoch": 4.54, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 8750 + }, + { + "epoch": 4.55, + "learning_rate": 0.001, + "loss": 1.9292, + "step": 8760 + }, + { + "epoch": 4.55, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 8770 + }, + { + "epoch": 4.56, + "learning_rate": 0.001, + "loss": 1.9686, + "step": 8780 + }, + { + "epoch": 4.56, + "learning_rate": 0.001, + "loss": 1.9181, + "step": 8790 + }, + { + "epoch": 4.57, + "learning_rate": 0.001, + "loss": 1.9606, + "step": 8800 + }, + { + "epoch": 4.57, + "learning_rate": 0.001, + "loss": 1.937, + "step": 8810 + }, + { + "epoch": 4.58, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 8820 + }, + { + "epoch": 4.58, + "learning_rate": 0.001, + "loss": 1.9756, + "step": 8830 + }, + { + "epoch": 4.59, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 8840 + }, + { + "epoch": 4.59, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 8850 + }, + { + "epoch": 4.6, + "learning_rate": 0.001, + "loss": 1.962, + "step": 8860 + }, + { + "epoch": 4.6, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 8870 + }, + { + "epoch": 4.61, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 8880 + }, + { + "epoch": 4.61, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 8890 + }, + { + "epoch": 4.62, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 8900 + }, + { + "epoch": 4.62, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 8910 + }, + { + "epoch": 4.63, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 8920 + }, + { + "epoch": 4.63, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 8930 + }, + { + "epoch": 4.64, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 8940 + }, + { + "epoch": 4.64, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 8950 + }, + { + "epoch": 4.65, + "learning_rate": 0.001, + "loss": 1.908, + "step": 8960 + }, + { + "epoch": 4.65, + "learning_rate": 0.001, + "loss": 1.9273, + "step": 8970 + }, + { + "epoch": 4.66, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 8980 + }, + { + "epoch": 4.67, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 8990 + }, + { + "epoch": 4.67, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 9000 + }, + { + "epoch": 4.68, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 9010 + }, + { + "epoch": 4.68, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 9020 + }, + { + "epoch": 4.69, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 9030 + }, + { + "epoch": 4.69, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 9040 + }, + { + "epoch": 4.7, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 9050 + }, + { + "epoch": 4.7, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 9060 + }, + { + "epoch": 4.71, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 9070 + }, + { + "epoch": 4.71, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 9080 + }, + { + "epoch": 4.72, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 9090 + }, + { + "epoch": 4.72, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 9100 + }, + { + "epoch": 4.73, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 9110 + }, + { + "epoch": 4.73, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 9120 + }, + { + "epoch": 4.74, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 9130 + }, + { + "epoch": 4.74, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 9140 + }, + { + "epoch": 4.75, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 9150 + }, + { + "epoch": 4.75, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 9160 + }, + { + "epoch": 4.76, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 9170 + }, + { + "epoch": 4.76, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 9180 + }, + { + "epoch": 4.77, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 9190 + }, + { + "epoch": 4.77, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 9200 + }, + { + "epoch": 4.78, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 9210 + }, + { + "epoch": 4.78, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 9220 + }, + { + "epoch": 4.79, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 9230 + }, + { + "epoch": 4.8, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 9240 + }, + { + "epoch": 4.8, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 9250 + }, + { + "epoch": 4.81, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 9260 + }, + { + "epoch": 4.81, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 9270 + }, + { + "epoch": 4.82, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 9280 + }, + { + "epoch": 4.82, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 9290 + }, + { + "epoch": 4.83, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 9300 + }, + { + "epoch": 4.83, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 9310 + }, + { + "epoch": 4.84, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 9320 + }, + { + "epoch": 4.84, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 9330 + }, + { + "epoch": 4.85, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 9340 + }, + { + "epoch": 4.85, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 9350 + }, + { + "epoch": 4.86, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 9360 + }, + { + "epoch": 4.86, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 9370 + }, + { + "epoch": 4.87, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 9380 + }, + { + "epoch": 4.87, + "learning_rate": 0.001, + "loss": 1.9125, + "step": 9390 + }, + { + "epoch": 4.88, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 9400 + }, + { + "epoch": 4.88, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 9410 + }, + { + "epoch": 4.89, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 9420 + }, + { + "epoch": 4.89, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 9430 + }, + { + "epoch": 4.9, + "learning_rate": 0.001, + "loss": 1.9634, + "step": 9440 + }, + { + "epoch": 4.9, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 9450 + }, + { + "epoch": 4.91, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 9460 + }, + { + "epoch": 4.91, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 9470 + }, + { + "epoch": 4.92, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 9480 + }, + { + "epoch": 4.92, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 9490 + }, + { + "epoch": 4.93, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 9500 + }, + { + "epoch": 4.94, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 9510 + }, + { + "epoch": 4.94, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 9520 + }, + { + "epoch": 4.95, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 9530 + }, + { + "epoch": 4.95, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 9540 + }, + { + "epoch": 4.96, + "learning_rate": 0.001, + "loss": 1.966, + "step": 9550 + }, + { + "epoch": 4.96, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 9560 + }, + { + "epoch": 4.97, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 9570 + }, + { + "epoch": 4.97, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 9580 + }, + { + "epoch": 4.98, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 9590 + }, + { + "epoch": 4.98, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 9600 + }, + { + "epoch": 4.99, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 9610 + }, + { + "epoch": 4.99, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 9620 + }, + { + "epoch": 5.0, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 9630 + }, + { + "epoch": 5.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9407862424850464, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.9258, + "eval_samples_per_second": 50.113, + "eval_steps_per_second": 25.063, + "step": 9635 + }, + { + "epoch": 5.0, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 9640 + }, + { + "epoch": 5.01, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 9650 + }, + { + "epoch": 5.01, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 9660 + }, + { + "epoch": 5.02, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 9670 + }, + { + "epoch": 5.02, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 9680 + }, + { + "epoch": 5.03, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 9690 + }, + { + "epoch": 5.03, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 9700 + }, + { + "epoch": 5.04, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 9710 + }, + { + "epoch": 5.04, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 9720 + }, + { + "epoch": 5.05, + "learning_rate": 0.001, + "loss": 1.9598, + "step": 9730 + }, + { + "epoch": 5.05, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 9740 + }, + { + "epoch": 5.06, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 9750 + }, + { + "epoch": 5.06, + "learning_rate": 0.001, + "loss": 1.936, + "step": 9760 + }, + { + "epoch": 5.07, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 9770 + }, + { + "epoch": 5.08, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 9780 + }, + { + "epoch": 5.08, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 9790 + }, + { + "epoch": 5.09, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 9800 + }, + { + "epoch": 5.09, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 9810 + }, + { + "epoch": 5.1, + "learning_rate": 0.001, + "loss": 1.9248, + "step": 9820 + }, + { + "epoch": 5.1, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 9830 + }, + { + "epoch": 5.11, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 9840 + }, + { + "epoch": 5.11, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 9850 + }, + { + "epoch": 5.12, + "learning_rate": 0.001, + "loss": 1.9049, + "step": 9860 + }, + { + "epoch": 5.12, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 9870 + }, + { + "epoch": 5.13, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 9880 + }, + { + "epoch": 5.13, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 9890 + }, + { + "epoch": 5.14, + "learning_rate": 0.001, + "loss": 1.9756, + "step": 9900 + }, + { + "epoch": 5.14, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 9910 + }, + { + "epoch": 5.15, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 9920 + }, + { + "epoch": 5.15, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 9930 + }, + { + "epoch": 5.16, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 9940 + }, + { + "epoch": 5.16, + "learning_rate": 0.001, + "loss": 1.9657, + "step": 9950 + }, + { + "epoch": 5.17, + "learning_rate": 0.001, + "loss": 1.945, + "step": 9960 + }, + { + "epoch": 5.17, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 9970 + }, + { + "epoch": 5.18, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 9980 + }, + { + "epoch": 5.18, + "learning_rate": 0.001, + "loss": 1.952, + "step": 9990 + }, + { + "epoch": 5.19, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 10000 + }, + { + "epoch": 5.19, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 10010 + }, + { + "epoch": 5.2, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 10020 + }, + { + "epoch": 5.2, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 10030 + }, + { + "epoch": 5.21, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 10040 + }, + { + "epoch": 5.22, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 10050 + }, + { + "epoch": 5.22, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 10060 + }, + { + "epoch": 5.23, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 10070 + }, + { + "epoch": 5.23, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 10080 + }, + { + "epoch": 5.24, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 10090 + }, + { + "epoch": 5.24, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 10100 + }, + { + "epoch": 5.25, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 10110 + }, + { + "epoch": 5.25, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 10120 + }, + { + "epoch": 5.26, + "learning_rate": 0.001, + "loss": 1.94, + "step": 10130 + }, + { + "epoch": 5.26, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 10140 + }, + { + "epoch": 5.27, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 10150 + }, + { + "epoch": 5.27, + "learning_rate": 0.001, + "loss": 1.918, + "step": 10160 + }, + { + "epoch": 5.28, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 10170 + }, + { + "epoch": 5.28, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 10180 + }, + { + "epoch": 5.29, + "learning_rate": 0.001, + "loss": 1.9636, + "step": 10190 + }, + { + "epoch": 5.29, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 10200 + }, + { + "epoch": 5.3, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 10210 + }, + { + "epoch": 5.3, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 10220 + }, + { + "epoch": 5.31, + "learning_rate": 0.001, + "loss": 1.9801, + "step": 10230 + }, + { + "epoch": 5.31, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 10240 + }, + { + "epoch": 5.32, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 10250 + }, + { + "epoch": 5.32, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 10260 + }, + { + "epoch": 5.33, + "learning_rate": 0.001, + "loss": 1.9295, + "step": 10270 + }, + { + "epoch": 5.33, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 10280 + }, + { + "epoch": 5.34, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 10290 + }, + { + "epoch": 5.35, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 10300 + }, + { + "epoch": 5.35, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 10310 + }, + { + "epoch": 5.36, + "learning_rate": 0.001, + "loss": 1.925, + "step": 10320 + }, + { + "epoch": 5.36, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 10330 + }, + { + "epoch": 5.37, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 10340 + }, + { + "epoch": 5.37, + "learning_rate": 0.001, + "loss": 1.951, + "step": 10350 + }, + { + "epoch": 5.38, + "learning_rate": 0.001, + "loss": 1.955, + "step": 10360 + }, + { + "epoch": 5.38, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 10370 + }, + { + "epoch": 5.39, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 10380 + }, + { + "epoch": 5.39, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 10390 + }, + { + "epoch": 5.4, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 10400 + }, + { + "epoch": 5.4, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 10410 + }, + { + "epoch": 5.41, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 10420 + }, + { + "epoch": 5.41, + "learning_rate": 0.001, + "loss": 1.9221, + "step": 10430 + }, + { + "epoch": 5.42, + "learning_rate": 0.001, + "loss": 1.95, + "step": 10440 + }, + { + "epoch": 5.42, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 10450 + }, + { + "epoch": 5.43, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 10460 + }, + { + "epoch": 5.43, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 10470 + }, + { + "epoch": 5.44, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 10480 + }, + { + "epoch": 5.44, + "learning_rate": 0.001, + "loss": 1.948, + "step": 10490 + }, + { + "epoch": 5.45, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 10500 + }, + { + "epoch": 5.45, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 10510 + }, + { + "epoch": 5.46, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 10520 + }, + { + "epoch": 5.46, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 10530 + }, + { + "epoch": 5.47, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 10540 + }, + { + "epoch": 5.47, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 10550 + }, + { + "epoch": 5.48, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 10560 + }, + { + "epoch": 5.49, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 10570 + }, + { + "epoch": 5.49, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 10580 + }, + { + "epoch": 5.5, + "learning_rate": 0.001, + "loss": 1.9682, + "step": 10590 + }, + { + "epoch": 5.5, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 10600 + }, + { + "epoch": 5.51, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 10610 + }, + { + "epoch": 5.51, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 10620 + }, + { + "epoch": 5.52, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 10630 + }, + { + "epoch": 5.52, + "learning_rate": 0.001, + "loss": 1.9715, + "step": 10640 + }, + { + "epoch": 5.53, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 10650 + }, + { + "epoch": 5.53, + "learning_rate": 0.001, + "loss": 1.9623, + "step": 10660 + }, + { + "epoch": 5.54, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 10670 + }, + { + "epoch": 5.54, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 10680 + }, + { + "epoch": 5.55, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 10690 + }, + { + "epoch": 5.55, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 10700 + }, + { + "epoch": 5.56, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 10710 + }, + { + "epoch": 5.56, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 10720 + }, + { + "epoch": 5.57, + "learning_rate": 0.001, + "loss": 1.9674, + "step": 10730 + }, + { + "epoch": 5.57, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 10740 + }, + { + "epoch": 5.58, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 10750 + }, + { + "epoch": 5.58, + "learning_rate": 0.001, + "loss": 1.9223, + "step": 10760 + }, + { + "epoch": 5.59, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 10770 + }, + { + "epoch": 5.59, + "learning_rate": 0.001, + "loss": 1.9707, + "step": 10780 + }, + { + "epoch": 5.6, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 10790 + }, + { + "epoch": 5.6, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 10800 + }, + { + "epoch": 5.61, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 10810 + }, + { + "epoch": 5.61, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 10820 + }, + { + "epoch": 5.62, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 10830 + }, + { + "epoch": 5.63, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 10840 + }, + { + "epoch": 5.63, + "learning_rate": 0.001, + "loss": 1.9244, + "step": 10850 + }, + { + "epoch": 5.64, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 10860 + }, + { + "epoch": 5.64, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 10870 + }, + { + "epoch": 5.65, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 10880 + }, + { + "epoch": 5.65, + "learning_rate": 0.001, + "loss": 1.9679, + "step": 10890 + }, + { + "epoch": 5.66, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 10900 + }, + { + "epoch": 5.66, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 10910 + }, + { + "epoch": 5.67, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 10920 + }, + { + "epoch": 5.67, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 10930 + }, + { + "epoch": 5.68, + "learning_rate": 0.001, + "loss": 1.9587, + "step": 10940 + }, + { + "epoch": 5.68, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 10950 + }, + { + "epoch": 5.69, + "learning_rate": 0.001, + "loss": 1.959, + "step": 10960 + }, + { + "epoch": 5.69, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 10970 + }, + { + "epoch": 5.7, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 10980 + }, + { + "epoch": 5.7, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 10990 + }, + { + "epoch": 5.71, + "learning_rate": 0.001, + "loss": 1.94, + "step": 11000 + }, + { + "epoch": 5.71, + "learning_rate": 0.001, + "loss": 1.9562, + "step": 11010 + }, + { + "epoch": 5.72, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 11020 + }, + { + "epoch": 5.72, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 11030 + }, + { + "epoch": 5.73, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 11040 + }, + { + "epoch": 5.73, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 11050 + }, + { + "epoch": 5.74, + "learning_rate": 0.001, + "loss": 1.951, + "step": 11060 + }, + { + "epoch": 5.74, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 11070 + }, + { + "epoch": 5.75, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 11080 + }, + { + "epoch": 5.76, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 11090 + }, + { + "epoch": 5.76, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 11100 + }, + { + "epoch": 5.77, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 11110 + }, + { + "epoch": 5.77, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 11120 + }, + { + "epoch": 5.78, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 11130 + }, + { + "epoch": 5.78, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 11140 + }, + { + "epoch": 5.79, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 11150 + }, + { + "epoch": 5.79, + "learning_rate": 0.001, + "loss": 1.948, + "step": 11160 + }, + { + "epoch": 5.8, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 11170 + }, + { + "epoch": 5.8, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 11180 + }, + { + "epoch": 5.81, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 11190 + }, + { + "epoch": 5.81, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 11200 + }, + { + "epoch": 5.82, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 11210 + }, + { + "epoch": 5.82, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 11220 + }, + { + "epoch": 5.83, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 11230 + }, + { + "epoch": 5.83, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 11240 + }, + { + "epoch": 5.84, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 11250 + }, + { + "epoch": 5.84, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 11260 + }, + { + "epoch": 5.85, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 11270 + }, + { + "epoch": 5.85, + "learning_rate": 0.001, + "loss": 1.9193, + "step": 11280 + }, + { + "epoch": 5.86, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 11290 + }, + { + "epoch": 5.86, + "learning_rate": 0.001, + "loss": 1.9644, + "step": 11300 + }, + { + "epoch": 5.87, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 11310 + }, + { + "epoch": 5.87, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 11320 + }, + { + "epoch": 5.88, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 11330 + }, + { + "epoch": 5.88, + "learning_rate": 0.001, + "loss": 1.9213, + "step": 11340 + }, + { + "epoch": 5.89, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 11350 + }, + { + "epoch": 5.9, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 11360 + }, + { + "epoch": 5.9, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 11370 + }, + { + "epoch": 5.91, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 11380 + }, + { + "epoch": 5.91, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 11390 + }, + { + "epoch": 5.92, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 11400 + }, + { + "epoch": 5.92, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 11410 + }, + { + "epoch": 5.93, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 11420 + }, + { + "epoch": 5.93, + "learning_rate": 0.001, + "loss": 1.945, + "step": 11430 + }, + { + "epoch": 5.94, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 11440 + }, + { + "epoch": 5.94, + "learning_rate": 0.001, + "loss": 1.9599, + "step": 11450 + }, + { + "epoch": 5.95, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 11460 + }, + { + "epoch": 5.95, + "learning_rate": 0.001, + "loss": 1.94, + "step": 11470 + }, + { + "epoch": 5.96, + "learning_rate": 0.001, + "loss": 1.943, + "step": 11480 + }, + { + "epoch": 5.96, + "learning_rate": 0.001, + "loss": 1.9242, + "step": 11490 + }, + { + "epoch": 5.97, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 11500 + }, + { + "epoch": 5.97, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 11510 + }, + { + "epoch": 5.98, + "learning_rate": 0.001, + "loss": 1.9703, + "step": 11520 + }, + { + "epoch": 5.98, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 11530 + }, + { + "epoch": 5.99, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 11540 + }, + { + "epoch": 5.99, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 11550 + }, + { + "epoch": 6.0, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 11560 + }, + { + "epoch": 6.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9427300691604614, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.3874, + "eval_samples_per_second": 49.814, + "eval_steps_per_second": 24.914, + "step": 11562 + }, + { + "epoch": 6.0, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 11570 + }, + { + "epoch": 6.01, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 11580 + }, + { + "epoch": 6.01, + "learning_rate": 0.001, + "loss": 1.9266, + "step": 11590 + }, + { + "epoch": 6.02, + "learning_rate": 0.001, + "loss": 1.937, + "step": 11600 + }, + { + "epoch": 6.02, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 11610 + }, + { + "epoch": 6.03, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 11620 + }, + { + "epoch": 6.04, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 11630 + }, + { + "epoch": 6.04, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 11640 + }, + { + "epoch": 6.05, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 11650 + }, + { + "epoch": 6.05, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 11660 + }, + { + "epoch": 6.06, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 11670 + }, + { + "epoch": 6.06, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 11680 + }, + { + "epoch": 6.07, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 11690 + }, + { + "epoch": 6.07, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 11700 + }, + { + "epoch": 6.08, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 11710 + }, + { + "epoch": 6.08, + "learning_rate": 0.001, + "loss": 1.9233, + "step": 11720 + }, + { + "epoch": 6.09, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 11730 + }, + { + "epoch": 6.09, + "learning_rate": 0.001, + "loss": 1.9187, + "step": 11740 + }, + { + "epoch": 6.1, + "learning_rate": 0.001, + "loss": 1.9728, + "step": 11750 + }, + { + "epoch": 6.1, + "learning_rate": 0.001, + "loss": 1.943, + "step": 11760 + }, + { + "epoch": 6.11, + "learning_rate": 0.001, + "loss": 1.9603, + "step": 11770 + }, + { + "epoch": 6.11, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 11780 + }, + { + "epoch": 6.12, + "learning_rate": 0.001, + "loss": 1.9679, + "step": 11790 + }, + { + "epoch": 6.12, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 11800 + }, + { + "epoch": 6.13, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 11810 + }, + { + "epoch": 6.13, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 11820 + }, + { + "epoch": 6.14, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 11830 + }, + { + "epoch": 6.14, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 11840 + }, + { + "epoch": 6.15, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 11850 + }, + { + "epoch": 6.15, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 11860 + }, + { + "epoch": 6.16, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 11870 + }, + { + "epoch": 6.17, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 11880 + }, + { + "epoch": 6.17, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 11890 + }, + { + "epoch": 6.18, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 11900 + }, + { + "epoch": 6.18, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 11910 + }, + { + "epoch": 6.19, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 11920 + }, + { + "epoch": 6.19, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 11930 + }, + { + "epoch": 6.2, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 11940 + }, + { + "epoch": 6.2, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 11950 + }, + { + "epoch": 6.21, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 11960 + }, + { + "epoch": 6.21, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 11970 + }, + { + "epoch": 6.22, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 11980 + }, + { + "epoch": 6.22, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 11990 + }, + { + "epoch": 6.23, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 12000 + }, + { + "epoch": 6.23, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 12010 + }, + { + "epoch": 6.24, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 12020 + }, + { + "epoch": 6.24, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 12030 + }, + { + "epoch": 6.25, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 12040 + }, + { + "epoch": 6.25, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 12050 + }, + { + "epoch": 6.26, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 12060 + }, + { + "epoch": 6.26, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 12070 + }, + { + "epoch": 6.27, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 12080 + }, + { + "epoch": 6.27, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 12090 + }, + { + "epoch": 6.28, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 12100 + }, + { + "epoch": 6.28, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 12110 + }, + { + "epoch": 6.29, + "learning_rate": 0.001, + "loss": 1.919, + "step": 12120 + }, + { + "epoch": 6.29, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 12130 + }, + { + "epoch": 6.3, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 12140 + }, + { + "epoch": 6.31, + "learning_rate": 0.001, + "loss": 1.9628, + "step": 12150 + }, + { + "epoch": 6.31, + "learning_rate": 0.001, + "loss": 1.933, + "step": 12160 + }, + { + "epoch": 6.32, + "learning_rate": 0.001, + "loss": 1.9667, + "step": 12170 + }, + { + "epoch": 6.32, + "learning_rate": 0.001, + "loss": 1.919, + "step": 12180 + }, + { + "epoch": 6.33, + "learning_rate": 0.001, + "loss": 1.9281, + "step": 12190 + }, + { + "epoch": 6.33, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 12200 + }, + { + "epoch": 6.34, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 12210 + }, + { + "epoch": 6.34, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 12220 + }, + { + "epoch": 6.35, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 12230 + }, + { + "epoch": 6.35, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 12240 + }, + { + "epoch": 6.36, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 12250 + }, + { + "epoch": 6.36, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 12260 + }, + { + "epoch": 6.37, + "learning_rate": 0.001, + "loss": 1.9727, + "step": 12270 + }, + { + "epoch": 6.37, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 12280 + }, + { + "epoch": 6.38, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 12290 + }, + { + "epoch": 6.38, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 12300 + }, + { + "epoch": 6.39, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 12310 + }, + { + "epoch": 6.39, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 12320 + }, + { + "epoch": 6.4, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 12330 + }, + { + "epoch": 6.4, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 12340 + }, + { + "epoch": 6.41, + "learning_rate": 0.001, + "loss": 1.946, + "step": 12350 + }, + { + "epoch": 6.41, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 12360 + }, + { + "epoch": 6.42, + "learning_rate": 0.001, + "loss": 1.94, + "step": 12370 + }, + { + "epoch": 6.42, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 12380 + }, + { + "epoch": 6.43, + "learning_rate": 0.001, + "loss": 1.95, + "step": 12390 + }, + { + "epoch": 6.43, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 12400 + }, + { + "epoch": 6.44, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 12410 + }, + { + "epoch": 6.45, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 12420 + }, + { + "epoch": 6.45, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 12430 + }, + { + "epoch": 6.46, + "learning_rate": 0.001, + "loss": 1.929, + "step": 12440 + }, + { + "epoch": 6.46, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 12450 + }, + { + "epoch": 6.47, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 12460 + }, + { + "epoch": 6.47, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 12470 + }, + { + "epoch": 6.48, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 12480 + }, + { + "epoch": 6.48, + "learning_rate": 0.001, + "loss": 1.9259, + "step": 12490 + }, + { + "epoch": 6.49, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 12500 + }, + { + "epoch": 6.49, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 12510 + }, + { + "epoch": 6.5, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 12520 + }, + { + "epoch": 6.5, + "learning_rate": 0.001, + "loss": 1.938, + "step": 12530 + }, + { + "epoch": 6.51, + "learning_rate": 0.001, + "loss": 1.9261, + "step": 12540 + }, + { + "epoch": 6.51, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 12550 + }, + { + "epoch": 6.52, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 12560 + }, + { + "epoch": 6.52, + "learning_rate": 0.001, + "loss": 1.9199, + "step": 12570 + }, + { + "epoch": 6.53, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 12580 + }, + { + "epoch": 6.53, + "learning_rate": 0.001, + "loss": 1.953, + "step": 12590 + }, + { + "epoch": 6.54, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 12600 + }, + { + "epoch": 6.54, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 12610 + }, + { + "epoch": 6.55, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 12620 + }, + { + "epoch": 6.55, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 12630 + }, + { + "epoch": 6.56, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 12640 + }, + { + "epoch": 6.56, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 12650 + }, + { + "epoch": 6.57, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 12660 + }, + { + "epoch": 6.57, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 12670 + }, + { + "epoch": 6.58, + "learning_rate": 0.001, + "loss": 1.9177, + "step": 12680 + }, + { + "epoch": 6.59, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 12690 + }, + { + "epoch": 6.59, + "learning_rate": 0.001, + "loss": 1.938, + "step": 12700 + }, + { + "epoch": 6.6, + "learning_rate": 0.001, + "loss": 1.964, + "step": 12710 + }, + { + "epoch": 6.6, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 12720 + }, + { + "epoch": 6.61, + "learning_rate": 0.001, + "loss": 1.948, + "step": 12730 + }, + { + "epoch": 6.61, + "learning_rate": 0.001, + "loss": 1.9659, + "step": 12740 + }, + { + "epoch": 6.62, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 12750 + }, + { + "epoch": 6.62, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 12760 + }, + { + "epoch": 6.63, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 12770 + }, + { + "epoch": 6.63, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 12780 + }, + { + "epoch": 6.64, + "learning_rate": 0.001, + "loss": 1.9627, + "step": 12790 + }, + { + "epoch": 6.64, + "learning_rate": 0.001, + "loss": 1.92, + "step": 12800 + }, + { + "epoch": 6.65, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 12810 + }, + { + "epoch": 6.65, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 12820 + }, + { + "epoch": 6.66, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 12830 + }, + { + "epoch": 6.66, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 12840 + }, + { + "epoch": 6.67, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 12850 + }, + { + "epoch": 6.67, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 12860 + }, + { + "epoch": 6.68, + "learning_rate": 0.001, + "loss": 1.956, + "step": 12870 + }, + { + "epoch": 6.68, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 12880 + }, + { + "epoch": 6.69, + "learning_rate": 0.001, + "loss": 1.9196, + "step": 12890 + }, + { + "epoch": 6.69, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 12900 + }, + { + "epoch": 6.7, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 12910 + }, + { + "epoch": 6.7, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 12920 + }, + { + "epoch": 6.71, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 12930 + }, + { + "epoch": 6.72, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 12940 + }, + { + "epoch": 6.72, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 12950 + }, + { + "epoch": 6.73, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 12960 + }, + { + "epoch": 6.73, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 12970 + }, + { + "epoch": 6.74, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 12980 + }, + { + "epoch": 6.74, + "learning_rate": 0.001, + "loss": 1.923, + "step": 12990 + }, + { + "epoch": 6.75, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 13000 + }, + { + "epoch": 6.75, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 13010 + }, + { + "epoch": 6.76, + "learning_rate": 0.001, + "loss": 1.957, + "step": 13020 + }, + { + "epoch": 6.76, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 13030 + }, + { + "epoch": 6.77, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 13040 + }, + { + "epoch": 6.77, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 13050 + }, + { + "epoch": 6.78, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 13060 + }, + { + "epoch": 6.78, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 13070 + }, + { + "epoch": 6.79, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 13080 + }, + { + "epoch": 6.79, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 13090 + }, + { + "epoch": 6.8, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 13100 + }, + { + "epoch": 6.8, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 13110 + }, + { + "epoch": 6.81, + "learning_rate": 0.001, + "loss": 1.9254, + "step": 13120 + }, + { + "epoch": 6.81, + "learning_rate": 0.001, + "loss": 1.9722, + "step": 13130 + }, + { + "epoch": 6.82, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 13140 + }, + { + "epoch": 6.82, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 13150 + }, + { + "epoch": 6.83, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 13160 + }, + { + "epoch": 6.83, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 13170 + }, + { + "epoch": 6.84, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 13180 + }, + { + "epoch": 6.84, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 13190 + }, + { + "epoch": 6.85, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 13200 + }, + { + "epoch": 6.86, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 13210 + }, + { + "epoch": 6.86, + "learning_rate": 0.001, + "loss": 1.947, + "step": 13220 + }, + { + "epoch": 6.87, + "learning_rate": 0.001, + "loss": 1.9168, + "step": 13230 + }, + { + "epoch": 6.87, + "learning_rate": 0.001, + "loss": 1.9118, + "step": 13240 + }, + { + "epoch": 6.88, + "learning_rate": 0.001, + "loss": 1.9839, + "step": 13250 + }, + { + "epoch": 6.88, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 13260 + }, + { + "epoch": 6.89, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 13270 + }, + { + "epoch": 6.89, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 13280 + }, + { + "epoch": 6.9, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 13290 + }, + { + "epoch": 6.9, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 13300 + }, + { + "epoch": 6.91, + "learning_rate": 0.001, + "loss": 1.9662, + "step": 13310 + }, + { + "epoch": 6.91, + "learning_rate": 0.001, + "loss": 1.937, + "step": 13320 + }, + { + "epoch": 6.92, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 13330 + }, + { + "epoch": 6.92, + "learning_rate": 0.001, + "loss": 1.9661, + "step": 13340 + }, + { + "epoch": 6.93, + "learning_rate": 0.001, + "loss": 1.9593, + "step": 13350 + }, + { + "epoch": 6.93, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 13360 + }, + { + "epoch": 6.94, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 13370 + }, + { + "epoch": 6.94, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 13380 + }, + { + "epoch": 6.95, + "learning_rate": 0.001, + "loss": 1.9245, + "step": 13390 + }, + { + "epoch": 6.95, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 13400 + }, + { + "epoch": 6.96, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 13410 + }, + { + "epoch": 6.96, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 13420 + }, + { + "epoch": 6.97, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 13430 + }, + { + "epoch": 6.97, + "learning_rate": 0.001, + "loss": 1.963, + "step": 13440 + }, + { + "epoch": 6.98, + "learning_rate": 0.001, + "loss": 1.957, + "step": 13450 + }, + { + "epoch": 6.98, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 13460 + }, + { + "epoch": 6.99, + "learning_rate": 0.001, + "loss": 1.9837, + "step": 13470 + }, + { + "epoch": 7.0, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 13480 + }, + { + "epoch": 7.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9433287382125854, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.8252, + "eval_samples_per_second": 49.534, + "eval_steps_per_second": 24.773, + "step": 13489 + }, + { + "epoch": 7.0, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 13490 + }, + { + "epoch": 7.01, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 13500 + }, + { + "epoch": 7.01, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 13510 + }, + { + "epoch": 7.02, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 13520 + }, + { + "epoch": 7.02, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 13530 + }, + { + "epoch": 7.03, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 13540 + }, + { + "epoch": 7.03, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 13550 + }, + { + "epoch": 7.04, + "learning_rate": 0.001, + "loss": 1.947, + "step": 13560 + }, + { + "epoch": 7.04, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 13570 + }, + { + "epoch": 7.05, + "learning_rate": 0.001, + "loss": 1.942, + "step": 13580 + }, + { + "epoch": 7.05, + "learning_rate": 0.001, + "loss": 1.949, + "step": 13590 + }, + { + "epoch": 7.06, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 13600 + }, + { + "epoch": 7.06, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 13610 + }, + { + "epoch": 7.07, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 13620 + }, + { + "epoch": 7.07, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 13630 + }, + { + "epoch": 7.08, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 13640 + }, + { + "epoch": 7.08, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 13650 + }, + { + "epoch": 7.09, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 13660 + }, + { + "epoch": 7.09, + "learning_rate": 0.001, + "loss": 1.9638, + "step": 13670 + }, + { + "epoch": 7.1, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 13680 + }, + { + "epoch": 7.1, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 13690 + }, + { + "epoch": 7.11, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 13700 + }, + { + "epoch": 7.11, + "learning_rate": 0.001, + "loss": 1.95, + "step": 13710 + }, + { + "epoch": 7.12, + "learning_rate": 0.001, + "loss": 1.9668, + "step": 13720 + }, + { + "epoch": 7.13, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 13730 + }, + { + "epoch": 7.13, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 13740 + }, + { + "epoch": 7.14, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 13750 + }, + { + "epoch": 7.14, + "learning_rate": 0.001, + "loss": 1.9664, + "step": 13760 + }, + { + "epoch": 7.15, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 13770 + }, + { + "epoch": 7.15, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 13780 + }, + { + "epoch": 7.16, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 13790 + }, + { + "epoch": 7.16, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 13800 + }, + { + "epoch": 7.17, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 13810 + }, + { + "epoch": 7.17, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 13820 + }, + { + "epoch": 7.18, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 13830 + }, + { + "epoch": 7.18, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 13840 + }, + { + "epoch": 7.19, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 13850 + }, + { + "epoch": 7.19, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 13860 + }, + { + "epoch": 7.2, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 13870 + }, + { + "epoch": 7.2, + "learning_rate": 0.001, + "loss": 1.9733, + "step": 13880 + }, + { + "epoch": 7.21, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 13890 + }, + { + "epoch": 7.21, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 13900 + }, + { + "epoch": 7.22, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 13910 + }, + { + "epoch": 7.22, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 13920 + }, + { + "epoch": 7.23, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 13930 + }, + { + "epoch": 7.23, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 13940 + }, + { + "epoch": 7.24, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 13950 + }, + { + "epoch": 7.24, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 13960 + }, + { + "epoch": 7.25, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 13970 + }, + { + "epoch": 7.25, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 13980 + }, + { + "epoch": 7.26, + "learning_rate": 0.001, + "loss": 1.931, + "step": 13990 + }, + { + "epoch": 7.27, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 14000 + }, + { + "epoch": 7.27, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 14010 + }, + { + "epoch": 7.28, + "learning_rate": 0.001, + "loss": 1.951, + "step": 14020 + }, + { + "epoch": 7.28, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 14030 + }, + { + "epoch": 7.29, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 14040 + }, + { + "epoch": 7.29, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 14050 + }, + { + "epoch": 7.3, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 14060 + }, + { + "epoch": 7.3, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 14070 + }, + { + "epoch": 7.31, + "learning_rate": 0.001, + "loss": 1.9215, + "step": 14080 + }, + { + "epoch": 7.31, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 14090 + }, + { + "epoch": 7.32, + "learning_rate": 0.001, + "loss": 1.935, + "step": 14100 + }, + { + "epoch": 7.32, + "learning_rate": 0.001, + "loss": 1.9188, + "step": 14110 + }, + { + "epoch": 7.33, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 14120 + }, + { + "epoch": 7.33, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 14130 + }, + { + "epoch": 7.34, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 14140 + }, + { + "epoch": 7.34, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 14150 + }, + { + "epoch": 7.35, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 14160 + }, + { + "epoch": 7.35, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 14170 + }, + { + "epoch": 7.36, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 14180 + }, + { + "epoch": 7.36, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 14190 + }, + { + "epoch": 7.37, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 14200 + }, + { + "epoch": 7.37, + "learning_rate": 0.001, + "loss": 1.933, + "step": 14210 + }, + { + "epoch": 7.38, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 14220 + }, + { + "epoch": 7.38, + "learning_rate": 0.001, + "loss": 1.941, + "step": 14230 + }, + { + "epoch": 7.39, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 14240 + }, + { + "epoch": 7.39, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 14250 + }, + { + "epoch": 7.4, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 14260 + }, + { + "epoch": 7.41, + "learning_rate": 0.001, + "loss": 1.94, + "step": 14270 + }, + { + "epoch": 7.41, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 14280 + }, + { + "epoch": 7.42, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 14290 + }, + { + "epoch": 7.42, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 14300 + }, + { + "epoch": 7.43, + "learning_rate": 0.001, + "loss": 1.9244, + "step": 14310 + }, + { + "epoch": 7.43, + "learning_rate": 0.001, + "loss": 1.938, + "step": 14320 + }, + { + "epoch": 7.44, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 14330 + }, + { + "epoch": 7.44, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 14340 + }, + { + "epoch": 7.45, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 14350 + }, + { + "epoch": 7.45, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 14360 + }, + { + "epoch": 7.46, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 14370 + }, + { + "epoch": 7.46, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 14380 + }, + { + "epoch": 7.47, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 14390 + }, + { + "epoch": 7.47, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 14400 + }, + { + "epoch": 7.48, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 14410 + }, + { + "epoch": 7.48, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 14420 + }, + { + "epoch": 7.49, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 14430 + }, + { + "epoch": 7.49, + "learning_rate": 0.001, + "loss": 1.94, + "step": 14440 + }, + { + "epoch": 7.5, + "learning_rate": 0.001, + "loss": 1.9268, + "step": 14450 + }, + { + "epoch": 7.5, + "learning_rate": 0.001, + "loss": 1.936, + "step": 14460 + }, + { + "epoch": 7.51, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 14470 + }, + { + "epoch": 7.51, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 14480 + }, + { + "epoch": 7.52, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 14490 + }, + { + "epoch": 7.52, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 14500 + }, + { + "epoch": 7.53, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 14510 + }, + { + "epoch": 7.54, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 14520 + }, + { + "epoch": 7.54, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 14530 + }, + { + "epoch": 7.55, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 14540 + }, + { + "epoch": 7.55, + "learning_rate": 0.001, + "loss": 1.948, + "step": 14550 + }, + { + "epoch": 7.56, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 14560 + }, + { + "epoch": 7.56, + "learning_rate": 0.001, + "loss": 1.9606, + "step": 14570 + }, + { + "epoch": 7.57, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 14580 + }, + { + "epoch": 7.57, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 14590 + }, + { + "epoch": 7.58, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 14600 + }, + { + "epoch": 7.58, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 14610 + }, + { + "epoch": 7.59, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 14620 + }, + { + "epoch": 7.59, + "learning_rate": 0.001, + "loss": 1.9599, + "step": 14630 + }, + { + "epoch": 7.6, + "learning_rate": 0.001, + "loss": 1.933, + "step": 14640 + }, + { + "epoch": 7.6, + "learning_rate": 0.001, + "loss": 1.9622, + "step": 14650 + }, + { + "epoch": 7.61, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 14660 + }, + { + "epoch": 7.61, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 14670 + }, + { + "epoch": 7.62, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 14680 + }, + { + "epoch": 7.62, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 14690 + }, + { + "epoch": 7.63, + "learning_rate": 0.001, + "loss": 1.936, + "step": 14700 + }, + { + "epoch": 7.63, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 14710 + }, + { + "epoch": 7.64, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 14720 + }, + { + "epoch": 7.64, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 14730 + }, + { + "epoch": 7.65, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 14740 + }, + { + "epoch": 7.65, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 14750 + }, + { + "epoch": 7.66, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 14760 + }, + { + "epoch": 7.66, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 14770 + }, + { + "epoch": 7.67, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 14780 + }, + { + "epoch": 7.68, + "learning_rate": 0.001, + "loss": 1.93, + "step": 14790 + }, + { + "epoch": 7.68, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 14800 + }, + { + "epoch": 7.69, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 14810 + }, + { + "epoch": 7.69, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 14820 + }, + { + "epoch": 7.7, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 14830 + }, + { + "epoch": 7.7, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 14840 + }, + { + "epoch": 7.71, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 14850 + }, + { + "epoch": 7.71, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 14860 + }, + { + "epoch": 7.72, + "learning_rate": 0.001, + "loss": 1.931, + "step": 14870 + }, + { + "epoch": 7.72, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 14880 + }, + { + "epoch": 7.73, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 14890 + }, + { + "epoch": 7.73, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 14900 + }, + { + "epoch": 7.74, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 14910 + }, + { + "epoch": 7.74, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 14920 + }, + { + "epoch": 7.75, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 14930 + }, + { + "epoch": 7.75, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 14940 + }, + { + "epoch": 7.76, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 14950 + }, + { + "epoch": 7.76, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 14960 + }, + { + "epoch": 7.77, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 14970 + }, + { + "epoch": 7.77, + "learning_rate": 0.001, + "loss": 1.956, + "step": 14980 + }, + { + "epoch": 7.78, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 14990 + }, + { + "epoch": 7.78, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 15000 + }, + { + "epoch": 7.79, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 15010 + }, + { + "epoch": 7.79, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 15020 + }, + { + "epoch": 7.8, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 15030 + }, + { + "epoch": 7.8, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 15040 + }, + { + "epoch": 7.81, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 15050 + }, + { + "epoch": 7.82, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 15060 + }, + { + "epoch": 7.82, + "learning_rate": 0.001, + "loss": 1.9295, + "step": 15070 + }, + { + "epoch": 7.83, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 15080 + }, + { + "epoch": 7.83, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 15090 + }, + { + "epoch": 7.84, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 15100 + }, + { + "epoch": 7.84, + "learning_rate": 0.001, + "loss": 1.9103, + "step": 15110 + }, + { + "epoch": 7.85, + "learning_rate": 0.001, + "loss": 1.9173, + "step": 15120 + }, + { + "epoch": 7.85, + "learning_rate": 0.001, + "loss": 1.9138, + "step": 15130 + }, + { + "epoch": 7.86, + "learning_rate": 0.001, + "loss": 1.9622, + "step": 15140 + }, + { + "epoch": 7.86, + "learning_rate": 0.001, + "loss": 1.9637, + "step": 15150 + }, + { + "epoch": 7.87, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 15160 + }, + { + "epoch": 7.87, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 15170 + }, + { + "epoch": 7.88, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 15180 + }, + { + "epoch": 7.88, + "learning_rate": 0.001, + "loss": 1.9209, + "step": 15190 + }, + { + "epoch": 7.89, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 15200 + }, + { + "epoch": 7.89, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 15210 + }, + { + "epoch": 7.9, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 15220 + }, + { + "epoch": 7.9, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 15230 + }, + { + "epoch": 7.91, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 15240 + }, + { + "epoch": 7.91, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 15250 + }, + { + "epoch": 7.92, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 15260 + }, + { + "epoch": 7.92, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 15270 + }, + { + "epoch": 7.93, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 15280 + }, + { + "epoch": 7.93, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 15290 + }, + { + "epoch": 7.94, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 15300 + }, + { + "epoch": 7.94, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 15310 + }, + { + "epoch": 7.95, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 15320 + }, + { + "epoch": 7.96, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 15330 + }, + { + "epoch": 7.96, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 15340 + }, + { + "epoch": 7.97, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 15350 + }, + { + "epoch": 7.97, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 15360 + }, + { + "epoch": 7.98, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 15370 + }, + { + "epoch": 7.98, + "learning_rate": 0.001, + "loss": 1.9279, + "step": 15380 + }, + { + "epoch": 7.99, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 15390 + }, + { + "epoch": 7.99, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 15400 + }, + { + "epoch": 8.0, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 15410 + }, + { + "epoch": 8.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9431941509246826, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.9544, + "eval_samples_per_second": 50.095, + "eval_steps_per_second": 25.054, + "step": 15416 + }, + { + "epoch": 8.0, + "learning_rate": 0.001, + "loss": 1.949, + "step": 15420 + }, + { + "epoch": 8.01, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 15430 + }, + { + "epoch": 8.01, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 15440 + }, + { + "epoch": 8.02, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 15450 + }, + { + "epoch": 8.02, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 15460 + }, + { + "epoch": 8.03, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 15470 + }, + { + "epoch": 8.03, + "learning_rate": 0.001, + "loss": 1.9699, + "step": 15480 + }, + { + "epoch": 8.04, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 15490 + }, + { + "epoch": 8.04, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 15500 + }, + { + "epoch": 8.05, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 15510 + }, + { + "epoch": 8.05, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 15520 + }, + { + "epoch": 8.06, + "learning_rate": 0.001, + "loss": 1.923, + "step": 15530 + }, + { + "epoch": 8.06, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 15540 + }, + { + "epoch": 8.07, + "learning_rate": 0.001, + "loss": 1.9206, + "step": 15550 + }, + { + "epoch": 8.07, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 15560 + }, + { + "epoch": 8.08, + "learning_rate": 0.001, + "loss": 1.957, + "step": 15570 + }, + { + "epoch": 8.09, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 15580 + }, + { + "epoch": 8.09, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 15590 + }, + { + "epoch": 8.1, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 15600 + }, + { + "epoch": 8.1, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 15610 + }, + { + "epoch": 8.11, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 15620 + }, + { + "epoch": 8.11, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 15630 + }, + { + "epoch": 8.12, + "learning_rate": 0.001, + "loss": 1.9625, + "step": 15640 + }, + { + "epoch": 8.12, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 15650 + }, + { + "epoch": 8.13, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 15660 + }, + { + "epoch": 8.13, + "learning_rate": 0.001, + "loss": 1.926, + "step": 15670 + }, + { + "epoch": 8.14, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 15680 + }, + { + "epoch": 8.14, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 15690 + }, + { + "epoch": 8.15, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 15700 + }, + { + "epoch": 8.15, + "learning_rate": 0.001, + "loss": 1.9233, + "step": 15710 + }, + { + "epoch": 8.16, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 15720 + }, + { + "epoch": 8.16, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 15730 + }, + { + "epoch": 8.17, + "learning_rate": 0.001, + "loss": 1.9172, + "step": 15740 + }, + { + "epoch": 8.17, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 15750 + }, + { + "epoch": 8.18, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 15760 + }, + { + "epoch": 8.18, + "learning_rate": 0.001, + "loss": 1.9267, + "step": 15770 + }, + { + "epoch": 8.19, + "learning_rate": 0.001, + "loss": 1.9593, + "step": 15780 + }, + { + "epoch": 8.19, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 15790 + }, + { + "epoch": 8.2, + "learning_rate": 0.001, + "loss": 1.948, + "step": 15800 + }, + { + "epoch": 8.2, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 15810 + }, + { + "epoch": 8.21, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 15820 + }, + { + "epoch": 8.21, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 15830 + }, + { + "epoch": 8.22, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 15840 + }, + { + "epoch": 8.23, + "learning_rate": 0.001, + "loss": 1.979, + "step": 15850 + }, + { + "epoch": 8.23, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 15860 + }, + { + "epoch": 8.24, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 15870 + }, + { + "epoch": 8.24, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 15880 + }, + { + "epoch": 8.25, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 15890 + }, + { + "epoch": 8.25, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 15900 + }, + { + "epoch": 8.26, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 15910 + }, + { + "epoch": 8.26, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 15920 + }, + { + "epoch": 8.27, + "learning_rate": 0.001, + "loss": 1.9215, + "step": 15930 + }, + { + "epoch": 8.27, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 15940 + }, + { + "epoch": 8.28, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 15950 + }, + { + "epoch": 8.28, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 15960 + }, + { + "epoch": 8.29, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 15970 + }, + { + "epoch": 8.29, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 15980 + }, + { + "epoch": 8.3, + "learning_rate": 0.001, + "loss": 1.939, + "step": 15990 + }, + { + "epoch": 8.3, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 16000 + }, + { + "epoch": 8.31, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 16010 + }, + { + "epoch": 8.31, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 16020 + }, + { + "epoch": 8.32, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 16030 + }, + { + "epoch": 8.32, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 16040 + }, + { + "epoch": 8.33, + "learning_rate": 0.001, + "loss": 1.9806, + "step": 16050 + }, + { + "epoch": 8.33, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 16060 + }, + { + "epoch": 8.34, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 16070 + }, + { + "epoch": 8.34, + "learning_rate": 0.001, + "loss": 1.945, + "step": 16080 + }, + { + "epoch": 8.35, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 16090 + }, + { + "epoch": 8.35, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 16100 + }, + { + "epoch": 8.36, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 16110 + }, + { + "epoch": 8.37, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 16120 + }, + { + "epoch": 8.37, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 16130 + }, + { + "epoch": 8.38, + "learning_rate": 0.001, + "loss": 1.938, + "step": 16140 + }, + { + "epoch": 8.38, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 16150 + }, + { + "epoch": 8.39, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 16160 + }, + { + "epoch": 8.39, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 16170 + }, + { + "epoch": 8.4, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 16180 + }, + { + "epoch": 8.4, + "learning_rate": 0.001, + "loss": 1.9281, + "step": 16190 + }, + { + "epoch": 8.41, + "learning_rate": 0.001, + "loss": 1.9154, + "step": 16200 + }, + { + "epoch": 8.41, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 16210 + }, + { + "epoch": 8.42, + "learning_rate": 0.001, + "loss": 1.9602, + "step": 16220 + }, + { + "epoch": 8.42, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 16230 + }, + { + "epoch": 8.43, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 16240 + }, + { + "epoch": 8.43, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 16250 + }, + { + "epoch": 8.44, + "learning_rate": 0.001, + "loss": 1.943, + "step": 16260 + }, + { + "epoch": 8.44, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 16270 + }, + { + "epoch": 8.45, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 16280 + }, + { + "epoch": 8.45, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 16290 + }, + { + "epoch": 8.46, + "learning_rate": 0.001, + "loss": 1.9716, + "step": 16300 + }, + { + "epoch": 8.46, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 16310 + }, + { + "epoch": 8.47, + "learning_rate": 0.001, + "loss": 1.938, + "step": 16320 + }, + { + "epoch": 8.47, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 16330 + }, + { + "epoch": 8.48, + "learning_rate": 0.001, + "loss": 1.959, + "step": 16340 + }, + { + "epoch": 8.48, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 16350 + }, + { + "epoch": 8.49, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 16360 + }, + { + "epoch": 8.5, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 16370 + }, + { + "epoch": 8.5, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 16380 + }, + { + "epoch": 8.51, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 16390 + }, + { + "epoch": 8.51, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 16400 + }, + { + "epoch": 8.52, + "learning_rate": 0.001, + "loss": 1.935, + "step": 16410 + }, + { + "epoch": 8.52, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 16420 + }, + { + "epoch": 8.53, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 16430 + }, + { + "epoch": 8.53, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 16440 + }, + { + "epoch": 8.54, + "learning_rate": 0.001, + "loss": 1.9623, + "step": 16450 + }, + { + "epoch": 8.54, + "learning_rate": 0.001, + "loss": 1.954, + "step": 16460 + }, + { + "epoch": 8.55, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 16470 + }, + { + "epoch": 8.55, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 16480 + }, + { + "epoch": 8.56, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 16490 + }, + { + "epoch": 8.56, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 16500 + }, + { + "epoch": 8.57, + "learning_rate": 0.001, + "loss": 1.936, + "step": 16510 + }, + { + "epoch": 8.57, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 16520 + }, + { + "epoch": 8.58, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 16530 + }, + { + "epoch": 8.58, + "learning_rate": 0.001, + "loss": 1.9245, + "step": 16540 + }, + { + "epoch": 8.59, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 16550 + }, + { + "epoch": 8.59, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 16560 + }, + { + "epoch": 8.6, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 16570 + }, + { + "epoch": 8.6, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 16580 + }, + { + "epoch": 8.61, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 16590 + }, + { + "epoch": 8.61, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 16600 + }, + { + "epoch": 8.62, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 16610 + }, + { + "epoch": 8.62, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 16620 + }, + { + "epoch": 8.63, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 16630 + }, + { + "epoch": 8.64, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 16640 + }, + { + "epoch": 8.64, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 16650 + }, + { + "epoch": 8.65, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 16660 + }, + { + "epoch": 8.65, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 16670 + }, + { + "epoch": 8.66, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 16680 + }, + { + "epoch": 8.66, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 16690 + }, + { + "epoch": 8.67, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 16700 + }, + { + "epoch": 8.67, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 16710 + }, + { + "epoch": 8.68, + "learning_rate": 0.001, + "loss": 1.941, + "step": 16720 + }, + { + "epoch": 8.68, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 16730 + }, + { + "epoch": 8.69, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 16740 + }, + { + "epoch": 8.69, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 16750 + }, + { + "epoch": 8.7, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 16760 + }, + { + "epoch": 8.7, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 16770 + }, + { + "epoch": 8.71, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 16780 + }, + { + "epoch": 8.71, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 16790 + }, + { + "epoch": 8.72, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 16800 + }, + { + "epoch": 8.72, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 16810 + }, + { + "epoch": 8.73, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 16820 + }, + { + "epoch": 8.73, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 16830 + }, + { + "epoch": 8.74, + "learning_rate": 0.001, + "loss": 1.9775, + "step": 16840 + }, + { + "epoch": 8.74, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 16850 + }, + { + "epoch": 8.75, + "learning_rate": 0.001, + "loss": 1.9621, + "step": 16860 + }, + { + "epoch": 8.75, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 16870 + }, + { + "epoch": 8.76, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 16880 + }, + { + "epoch": 8.76, + "learning_rate": 0.001, + "loss": 1.945, + "step": 16890 + }, + { + "epoch": 8.77, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 16900 + }, + { + "epoch": 8.78, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 16910 + }, + { + "epoch": 8.78, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 16920 + }, + { + "epoch": 8.79, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 16930 + }, + { + "epoch": 8.79, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 16940 + }, + { + "epoch": 8.8, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 16950 + }, + { + "epoch": 8.8, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 16960 + }, + { + "epoch": 8.81, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 16970 + }, + { + "epoch": 8.81, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 16980 + }, + { + "epoch": 8.82, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 16990 + }, + { + "epoch": 8.82, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 17000 + }, + { + "epoch": 8.83, + "learning_rate": 0.001, + "loss": 1.96, + "step": 17010 + }, + { + "epoch": 8.83, + "learning_rate": 0.001, + "loss": 1.9827, + "step": 17020 + }, + { + "epoch": 8.84, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 17030 + }, + { + "epoch": 8.84, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 17040 + }, + { + "epoch": 8.85, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 17050 + }, + { + "epoch": 8.85, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 17060 + }, + { + "epoch": 8.86, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 17070 + }, + { + "epoch": 8.86, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 17080 + }, + { + "epoch": 8.87, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 17090 + }, + { + "epoch": 8.87, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 17100 + }, + { + "epoch": 8.88, + "learning_rate": 0.001, + "loss": 1.9242, + "step": 17110 + }, + { + "epoch": 8.88, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 17120 + }, + { + "epoch": 8.89, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 17130 + }, + { + "epoch": 8.89, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 17140 + }, + { + "epoch": 8.9, + "learning_rate": 0.001, + "loss": 1.9175, + "step": 17150 + }, + { + "epoch": 8.91, + "learning_rate": 0.001, + "loss": 1.9588, + "step": 17160 + }, + { + "epoch": 8.91, + "learning_rate": 0.001, + "loss": 1.9634, + "step": 17170 + }, + { + "epoch": 8.92, + "learning_rate": 0.001, + "loss": 1.941, + "step": 17180 + }, + { + "epoch": 8.92, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 17190 + }, + { + "epoch": 8.93, + "learning_rate": 0.001, + "loss": 1.956, + "step": 17200 + }, + { + "epoch": 8.93, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 17210 + }, + { + "epoch": 8.94, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 17220 + }, + { + "epoch": 8.94, + "learning_rate": 0.001, + "loss": 1.9628, + "step": 17230 + }, + { + "epoch": 8.95, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 17240 + }, + { + "epoch": 8.95, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 17250 + }, + { + "epoch": 8.96, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 17260 + }, + { + "epoch": 8.96, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 17270 + }, + { + "epoch": 8.97, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 17280 + }, + { + "epoch": 8.97, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 17290 + }, + { + "epoch": 8.98, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 17300 + }, + { + "epoch": 8.98, + "learning_rate": 0.001, + "loss": 1.9135, + "step": 17310 + }, + { + "epoch": 8.99, + "learning_rate": 0.001, + "loss": 1.975, + "step": 17320 + }, + { + "epoch": 8.99, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 17330 + }, + { + "epoch": 9.0, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 17340 + }, + { + "epoch": 9.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9463131427764893, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.7556, + "eval_samples_per_second": 50.224, + "eval_steps_per_second": 25.119, + "step": 17343 + }, + { + "epoch": 9.0, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 17350 + }, + { + "epoch": 9.01, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 17360 + }, + { + "epoch": 9.01, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 17370 + }, + { + "epoch": 9.02, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 17380 + }, + { + "epoch": 9.02, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 17390 + }, + { + "epoch": 9.03, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 17400 + }, + { + "epoch": 9.03, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 17410 + }, + { + "epoch": 9.04, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 17420 + }, + { + "epoch": 9.05, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 17430 + }, + { + "epoch": 9.05, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 17440 + }, + { + "epoch": 9.06, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 17450 + }, + { + "epoch": 9.06, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 17460 + }, + { + "epoch": 9.07, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 17470 + }, + { + "epoch": 9.07, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 17480 + }, + { + "epoch": 9.08, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 17490 + }, + { + "epoch": 9.08, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 17500 + }, + { + "epoch": 9.09, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 17510 + }, + { + "epoch": 9.09, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 17520 + }, + { + "epoch": 9.1, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 17530 + }, + { + "epoch": 9.1, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 17540 + }, + { + "epoch": 9.11, + "learning_rate": 0.001, + "loss": 1.924, + "step": 17550 + }, + { + "epoch": 9.11, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 17560 + }, + { + "epoch": 9.12, + "learning_rate": 0.001, + "loss": 1.9226, + "step": 17570 + }, + { + "epoch": 9.12, + "learning_rate": 0.001, + "loss": 1.9669, + "step": 17580 + }, + { + "epoch": 9.13, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 17590 + }, + { + "epoch": 9.13, + "learning_rate": 0.001, + "loss": 1.95, + "step": 17600 + }, + { + "epoch": 9.14, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 17610 + }, + { + "epoch": 9.14, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 17620 + }, + { + "epoch": 9.15, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 17630 + }, + { + "epoch": 9.15, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 17640 + }, + { + "epoch": 9.16, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 17650 + }, + { + "epoch": 9.16, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 17660 + }, + { + "epoch": 9.17, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 17670 + }, + { + "epoch": 9.17, + "learning_rate": 0.001, + "loss": 1.941, + "step": 17680 + }, + { + "epoch": 9.18, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 17690 + }, + { + "epoch": 9.19, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 17700 + }, + { + "epoch": 9.19, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 17710 + }, + { + "epoch": 9.2, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 17720 + }, + { + "epoch": 9.2, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 17730 + }, + { + "epoch": 9.21, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 17740 + }, + { + "epoch": 9.21, + "learning_rate": 0.001, + "loss": 1.9659, + "step": 17750 + }, + { + "epoch": 9.22, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 17760 + }, + { + "epoch": 9.22, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 17770 + }, + { + "epoch": 9.23, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 17780 + }, + { + "epoch": 9.23, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 17790 + }, + { + "epoch": 9.24, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 17800 + }, + { + "epoch": 9.24, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 17810 + }, + { + "epoch": 9.25, + "learning_rate": 0.001, + "loss": 1.9702, + "step": 17820 + }, + { + "epoch": 9.25, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 17830 + }, + { + "epoch": 9.26, + "learning_rate": 0.001, + "loss": 1.95, + "step": 17840 + }, + { + "epoch": 9.26, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 17850 + }, + { + "epoch": 9.27, + "learning_rate": 0.001, + "loss": 1.9196, + "step": 17860 + }, + { + "epoch": 9.27, + "learning_rate": 0.001, + "loss": 1.942, + "step": 17870 + }, + { + "epoch": 9.28, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 17880 + }, + { + "epoch": 9.28, + "learning_rate": 0.001, + "loss": 1.9203, + "step": 17890 + }, + { + "epoch": 9.29, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 17900 + }, + { + "epoch": 9.29, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 17910 + }, + { + "epoch": 9.3, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 17920 + }, + { + "epoch": 9.3, + "learning_rate": 0.001, + "loss": 1.961, + "step": 17930 + }, + { + "epoch": 9.31, + "learning_rate": 0.001, + "loss": 1.9179, + "step": 17940 + }, + { + "epoch": 9.31, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 17950 + }, + { + "epoch": 9.32, + "learning_rate": 0.001, + "loss": 1.954, + "step": 17960 + }, + { + "epoch": 9.33, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 17970 + }, + { + "epoch": 9.33, + "learning_rate": 0.001, + "loss": 1.94, + "step": 17980 + }, + { + "epoch": 9.34, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 17990 + }, + { + "epoch": 9.34, + "learning_rate": 0.001, + "loss": 1.938, + "step": 18000 + }, + { + "epoch": 9.35, + "learning_rate": 0.001, + "loss": 1.9236, + "step": 18010 + }, + { + "epoch": 9.35, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 18020 + }, + { + "epoch": 9.36, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 18030 + }, + { + "epoch": 9.36, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 18040 + }, + { + "epoch": 9.37, + "learning_rate": 0.001, + "loss": 1.9638, + "step": 18050 + }, + { + "epoch": 9.37, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 18060 + }, + { + "epoch": 9.38, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 18070 + }, + { + "epoch": 9.38, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 18080 + }, + { + "epoch": 9.39, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 18090 + }, + { + "epoch": 9.39, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 18100 + }, + { + "epoch": 9.4, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 18110 + }, + { + "epoch": 9.4, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 18120 + }, + { + "epoch": 9.41, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 18130 + }, + { + "epoch": 9.41, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 18140 + }, + { + "epoch": 9.42, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 18150 + }, + { + "epoch": 9.42, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 18160 + }, + { + "epoch": 9.43, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 18170 + }, + { + "epoch": 9.43, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 18180 + }, + { + "epoch": 9.44, + "learning_rate": 0.001, + "loss": 1.945, + "step": 18190 + }, + { + "epoch": 9.44, + "learning_rate": 0.001, + "loss": 1.943, + "step": 18200 + }, + { + "epoch": 9.45, + "learning_rate": 0.001, + "loss": 1.928, + "step": 18210 + }, + { + "epoch": 9.46, + "learning_rate": 0.001, + "loss": 1.931, + "step": 18220 + }, + { + "epoch": 9.46, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 18230 + }, + { + "epoch": 9.47, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 18240 + }, + { + "epoch": 9.47, + "learning_rate": 0.001, + "loss": 1.9231, + "step": 18250 + }, + { + "epoch": 9.48, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 18260 + }, + { + "epoch": 9.48, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 18270 + }, + { + "epoch": 9.49, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 18280 + }, + { + "epoch": 9.49, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 18290 + }, + { + "epoch": 9.5, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 18300 + }, + { + "epoch": 9.5, + "learning_rate": 0.001, + "loss": 1.9559, + "step": 18310 + }, + { + "epoch": 9.51, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 18320 + }, + { + "epoch": 9.51, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 18330 + }, + { + "epoch": 9.52, + "learning_rate": 0.001, + "loss": 1.9259, + "step": 18340 + }, + { + "epoch": 9.52, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 18350 + }, + { + "epoch": 9.53, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 18360 + }, + { + "epoch": 9.53, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 18370 + }, + { + "epoch": 9.54, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 18380 + }, + { + "epoch": 9.54, + "learning_rate": 0.001, + "loss": 1.948, + "step": 18390 + }, + { + "epoch": 9.55, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 18400 + }, + { + "epoch": 9.55, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 18410 + }, + { + "epoch": 9.56, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 18420 + }, + { + "epoch": 9.56, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 18430 + }, + { + "epoch": 9.57, + "learning_rate": 0.001, + "loss": 1.945, + "step": 18440 + }, + { + "epoch": 9.57, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 18450 + }, + { + "epoch": 9.58, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 18460 + }, + { + "epoch": 9.58, + "learning_rate": 0.001, + "loss": 1.9273, + "step": 18470 + }, + { + "epoch": 9.59, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 18480 + }, + { + "epoch": 9.6, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 18490 + }, + { + "epoch": 9.6, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 18500 + }, + { + "epoch": 9.61, + "learning_rate": 0.001, + "loss": 1.9709, + "step": 18510 + }, + { + "epoch": 9.61, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 18520 + }, + { + "epoch": 9.62, + "learning_rate": 0.001, + "loss": 1.94, + "step": 18530 + }, + { + "epoch": 9.62, + "learning_rate": 0.001, + "loss": 1.9665, + "step": 18540 + }, + { + "epoch": 9.63, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 18550 + }, + { + "epoch": 9.63, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 18560 + }, + { + "epoch": 9.64, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 18570 + }, + { + "epoch": 9.64, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 18580 + }, + { + "epoch": 9.65, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 18590 + }, + { + "epoch": 9.65, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 18600 + }, + { + "epoch": 9.66, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 18610 + }, + { + "epoch": 9.66, + "learning_rate": 0.001, + "loss": 1.943, + "step": 18620 + }, + { + "epoch": 9.67, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 18630 + }, + { + "epoch": 9.67, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 18640 + }, + { + "epoch": 9.68, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 18650 + }, + { + "epoch": 9.68, + "learning_rate": 0.001, + "loss": 1.944, + "step": 18660 + }, + { + "epoch": 9.69, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 18670 + }, + { + "epoch": 9.69, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 18680 + }, + { + "epoch": 9.7, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 18690 + }, + { + "epoch": 9.7, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 18700 + }, + { + "epoch": 9.71, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 18710 + }, + { + "epoch": 9.71, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 18720 + }, + { + "epoch": 9.72, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 18730 + }, + { + "epoch": 9.72, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 18740 + }, + { + "epoch": 9.73, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 18750 + }, + { + "epoch": 9.74, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 18760 + }, + { + "epoch": 9.74, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 18770 + }, + { + "epoch": 9.75, + "learning_rate": 0.001, + "loss": 1.939, + "step": 18780 + }, + { + "epoch": 9.75, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 18790 + }, + { + "epoch": 9.76, + "learning_rate": 0.001, + "loss": 1.938, + "step": 18800 + }, + { + "epoch": 9.76, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 18810 + }, + { + "epoch": 9.77, + "learning_rate": 0.001, + "loss": 1.955, + "step": 18820 + }, + { + "epoch": 9.77, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 18830 + }, + { + "epoch": 9.78, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 18840 + }, + { + "epoch": 9.78, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 18850 + }, + { + "epoch": 9.79, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 18860 + }, + { + "epoch": 9.79, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 18870 + }, + { + "epoch": 9.8, + "learning_rate": 0.001, + "loss": 1.9007, + "step": 18880 + }, + { + "epoch": 9.8, + "learning_rate": 0.001, + "loss": 1.9883, + "step": 18890 + }, + { + "epoch": 9.81, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 18900 + }, + { + "epoch": 9.81, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 18910 + }, + { + "epoch": 9.82, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 18920 + }, + { + "epoch": 9.82, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 18930 + }, + { + "epoch": 9.83, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 18940 + }, + { + "epoch": 9.83, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 18950 + }, + { + "epoch": 9.84, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 18960 + }, + { + "epoch": 9.84, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 18970 + }, + { + "epoch": 9.85, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 18980 + }, + { + "epoch": 9.85, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 18990 + }, + { + "epoch": 9.86, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 19000 + }, + { + "epoch": 9.87, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 19010 + }, + { + "epoch": 9.87, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 19020 + }, + { + "epoch": 9.88, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 19030 + }, + { + "epoch": 9.88, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 19040 + }, + { + "epoch": 9.89, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 19050 + }, + { + "epoch": 9.89, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 19060 + }, + { + "epoch": 9.9, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 19070 + }, + { + "epoch": 9.9, + "learning_rate": 0.001, + "loss": 1.9652, + "step": 19080 + }, + { + "epoch": 9.91, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 19090 + }, + { + "epoch": 9.91, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 19100 + }, + { + "epoch": 9.92, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 19110 + }, + { + "epoch": 9.92, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 19120 + }, + { + "epoch": 9.93, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 19130 + }, + { + "epoch": 9.93, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 19140 + }, + { + "epoch": 9.94, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 19150 + }, + { + "epoch": 9.94, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 19160 + }, + { + "epoch": 9.95, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 19170 + }, + { + "epoch": 9.95, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 19180 + }, + { + "epoch": 9.96, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 19190 + }, + { + "epoch": 9.96, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 19200 + }, + { + "epoch": 9.97, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 19210 + }, + { + "epoch": 9.97, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 19220 + }, + { + "epoch": 9.98, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 19230 + }, + { + "epoch": 9.98, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 19240 + }, + { + "epoch": 9.99, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 19250 + }, + { + "epoch": 9.99, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 19260 + }, + { + "epoch": 10.0, + "learning_rate": 0.001, + "loss": 1.94, + "step": 19270 + }, + { + "epoch": 10.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9412217140197754, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.9999, + "eval_samples_per_second": 50.724, + "eval_steps_per_second": 25.368, + "step": 19270 + }, + { + "epoch": 10.01, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 19280 + }, + { + "epoch": 10.01, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 19290 + }, + { + "epoch": 10.02, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 19300 + }, + { + "epoch": 10.02, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 19310 + }, + { + "epoch": 10.03, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 19320 + }, + { + "epoch": 10.03, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 19330 + }, + { + "epoch": 10.04, + "learning_rate": 0.001, + "loss": 1.9209, + "step": 19340 + }, + { + "epoch": 10.04, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 19350 + }, + { + "epoch": 10.05, + "learning_rate": 0.001, + "loss": 1.9599, + "step": 19360 + }, + { + "epoch": 10.05, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 19370 + }, + { + "epoch": 10.06, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 19380 + }, + { + "epoch": 10.06, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 19390 + }, + { + "epoch": 10.07, + "learning_rate": 0.001, + "loss": 1.942, + "step": 19400 + }, + { + "epoch": 10.07, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 19410 + }, + { + "epoch": 10.08, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 19420 + }, + { + "epoch": 10.08, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 19430 + }, + { + "epoch": 10.09, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 19440 + }, + { + "epoch": 10.09, + "learning_rate": 0.001, + "loss": 1.9599, + "step": 19450 + }, + { + "epoch": 10.1, + "learning_rate": 0.001, + "loss": 1.934, + "step": 19460 + }, + { + "epoch": 10.1, + "learning_rate": 0.001, + "loss": 1.9107, + "step": 19470 + }, + { + "epoch": 10.11, + "learning_rate": 0.001, + "loss": 1.9662, + "step": 19480 + }, + { + "epoch": 10.11, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 19490 + }, + { + "epoch": 10.12, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 19500 + }, + { + "epoch": 10.12, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 19510 + }, + { + "epoch": 10.13, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 19520 + }, + { + "epoch": 10.13, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 19530 + }, + { + "epoch": 10.14, + "learning_rate": 0.001, + "loss": 1.9132, + "step": 19540 + }, + { + "epoch": 10.15, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 19550 + }, + { + "epoch": 10.15, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 19560 + }, + { + "epoch": 10.16, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 19570 + }, + { + "epoch": 10.16, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 19580 + }, + { + "epoch": 10.17, + "learning_rate": 0.001, + "loss": 1.957, + "step": 19590 + }, + { + "epoch": 10.17, + "learning_rate": 0.001, + "loss": 1.9637, + "step": 19600 + }, + { + "epoch": 10.18, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 19610 + }, + { + "epoch": 10.18, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 19620 + }, + { + "epoch": 10.19, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 19630 + }, + { + "epoch": 10.19, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 19640 + }, + { + "epoch": 10.2, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 19650 + }, + { + "epoch": 10.2, + "learning_rate": 0.001, + "loss": 1.9171, + "step": 19660 + }, + { + "epoch": 10.21, + "learning_rate": 0.001, + "loss": 1.9613, + "step": 19670 + }, + { + "epoch": 10.21, + "learning_rate": 0.001, + "loss": 1.948, + "step": 19680 + }, + { + "epoch": 10.22, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 19690 + }, + { + "epoch": 10.22, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 19700 + }, + { + "epoch": 10.23, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 19710 + }, + { + "epoch": 10.23, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 19720 + }, + { + "epoch": 10.24, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 19730 + }, + { + "epoch": 10.24, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 19740 + }, + { + "epoch": 10.25, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 19750 + }, + { + "epoch": 10.25, + "learning_rate": 0.001, + "loss": 1.9257, + "step": 19760 + }, + { + "epoch": 10.26, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 19770 + }, + { + "epoch": 10.26, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 19780 + }, + { + "epoch": 10.27, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 19790 + }, + { + "epoch": 10.28, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 19800 + }, + { + "epoch": 10.28, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 19810 + }, + { + "epoch": 10.29, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 19820 + }, + { + "epoch": 10.29, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 19830 + }, + { + "epoch": 10.3, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 19840 + }, + { + "epoch": 10.3, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 19850 + }, + { + "epoch": 10.31, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 19860 + }, + { + "epoch": 10.31, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 19870 + }, + { + "epoch": 10.32, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 19880 + }, + { + "epoch": 10.32, + "learning_rate": 0.001, + "loss": 1.9609, + "step": 19890 + }, + { + "epoch": 10.33, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 19900 + }, + { + "epoch": 10.33, + "learning_rate": 0.001, + "loss": 1.941, + "step": 19910 + }, + { + "epoch": 10.34, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 19920 + }, + { + "epoch": 10.34, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 19930 + }, + { + "epoch": 10.35, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 19940 + }, + { + "epoch": 10.35, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 19950 + }, + { + "epoch": 10.36, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 19960 + }, + { + "epoch": 10.36, + "learning_rate": 0.001, + "loss": 1.9281, + "step": 19970 + }, + { + "epoch": 10.37, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 19980 + }, + { + "epoch": 10.37, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 19990 + }, + { + "epoch": 10.38, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 20000 + }, + { + "epoch": 10.38, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 20010 + }, + { + "epoch": 10.39, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 20020 + }, + { + "epoch": 10.39, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 20030 + }, + { + "epoch": 10.4, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 20040 + }, + { + "epoch": 10.4, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 20050 + }, + { + "epoch": 10.41, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 20060 + }, + { + "epoch": 10.42, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 20070 + }, + { + "epoch": 10.42, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 20080 + }, + { + "epoch": 10.43, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 20090 + }, + { + "epoch": 10.43, + "learning_rate": 0.001, + "loss": 1.962, + "step": 20100 + }, + { + "epoch": 10.44, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 20110 + }, + { + "epoch": 10.44, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 20120 + }, + { + "epoch": 10.45, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 20130 + }, + { + "epoch": 10.45, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 20140 + }, + { + "epoch": 10.46, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 20150 + }, + { + "epoch": 10.46, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 20160 + }, + { + "epoch": 10.47, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 20170 + }, + { + "epoch": 10.47, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 20180 + }, + { + "epoch": 10.48, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 20190 + }, + { + "epoch": 10.48, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 20200 + }, + { + "epoch": 10.49, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 20210 + }, + { + "epoch": 10.49, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 20220 + }, + { + "epoch": 10.5, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 20230 + }, + { + "epoch": 10.5, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 20240 + }, + { + "epoch": 10.51, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 20250 + }, + { + "epoch": 10.51, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 20260 + }, + { + "epoch": 10.52, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 20270 + }, + { + "epoch": 10.52, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 20280 + }, + { + "epoch": 10.53, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 20290 + }, + { + "epoch": 10.53, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 20300 + }, + { + "epoch": 10.54, + "learning_rate": 0.001, + "loss": 1.9583, + "step": 20310 + }, + { + "epoch": 10.54, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 20320 + }, + { + "epoch": 10.55, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 20330 + }, + { + "epoch": 10.56, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 20340 + }, + { + "epoch": 10.56, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 20350 + }, + { + "epoch": 10.57, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 20360 + }, + { + "epoch": 10.57, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 20370 + }, + { + "epoch": 10.58, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 20380 + }, + { + "epoch": 10.58, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 20390 + }, + { + "epoch": 10.59, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 20400 + }, + { + "epoch": 10.59, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 20410 + }, + { + "epoch": 10.6, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 20420 + }, + { + "epoch": 10.6, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 20430 + }, + { + "epoch": 10.61, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 20440 + }, + { + "epoch": 10.61, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 20450 + }, + { + "epoch": 10.62, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 20460 + }, + { + "epoch": 10.62, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 20470 + }, + { + "epoch": 10.63, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 20480 + }, + { + "epoch": 10.63, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 20490 + }, + { + "epoch": 10.64, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 20500 + }, + { + "epoch": 10.64, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 20510 + }, + { + "epoch": 10.65, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 20520 + }, + { + "epoch": 10.65, + "learning_rate": 0.001, + "loss": 1.9248, + "step": 20530 + }, + { + "epoch": 10.66, + "learning_rate": 0.001, + "loss": 1.9628, + "step": 20540 + }, + { + "epoch": 10.66, + "learning_rate": 0.001, + "loss": 1.936, + "step": 20550 + }, + { + "epoch": 10.67, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 20560 + }, + { + "epoch": 10.67, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 20570 + }, + { + "epoch": 10.68, + "learning_rate": 0.001, + "loss": 1.939, + "step": 20580 + }, + { + "epoch": 10.69, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 20590 + }, + { + "epoch": 10.69, + "learning_rate": 0.001, + "loss": 1.9257, + "step": 20600 + }, + { + "epoch": 10.7, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 20610 + }, + { + "epoch": 10.7, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 20620 + }, + { + "epoch": 10.71, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 20630 + }, + { + "epoch": 10.71, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 20640 + }, + { + "epoch": 10.72, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 20650 + }, + { + "epoch": 10.72, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 20660 + }, + { + "epoch": 10.73, + "learning_rate": 0.001, + "loss": 1.929, + "step": 20670 + }, + { + "epoch": 10.73, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 20680 + }, + { + "epoch": 10.74, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 20690 + }, + { + "epoch": 10.74, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 20700 + }, + { + "epoch": 10.75, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 20710 + }, + { + "epoch": 10.75, + "learning_rate": 0.001, + "loss": 1.949, + "step": 20720 + }, + { + "epoch": 10.76, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 20730 + }, + { + "epoch": 10.76, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 20740 + }, + { + "epoch": 10.77, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 20750 + }, + { + "epoch": 10.77, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 20760 + }, + { + "epoch": 10.78, + "learning_rate": 0.001, + "loss": 1.949, + "step": 20770 + }, + { + "epoch": 10.78, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 20780 + }, + { + "epoch": 10.79, + "learning_rate": 0.001, + "loss": 1.9598, + "step": 20790 + }, + { + "epoch": 10.79, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 20800 + }, + { + "epoch": 10.8, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 20810 + }, + { + "epoch": 10.8, + "learning_rate": 0.001, + "loss": 1.9621, + "step": 20820 + }, + { + "epoch": 10.81, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 20830 + }, + { + "epoch": 10.81, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 20840 + }, + { + "epoch": 10.82, + "learning_rate": 0.001, + "loss": 1.951, + "step": 20850 + }, + { + "epoch": 10.83, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 20860 + }, + { + "epoch": 10.83, + "learning_rate": 0.001, + "loss": 1.947, + "step": 20870 + }, + { + "epoch": 10.84, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 20880 + }, + { + "epoch": 10.84, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 20890 + }, + { + "epoch": 10.85, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 20900 + }, + { + "epoch": 10.85, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 20910 + }, + { + "epoch": 10.86, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 20920 + }, + { + "epoch": 10.86, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 20930 + }, + { + "epoch": 10.87, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 20940 + }, + { + "epoch": 10.87, + "learning_rate": 0.001, + "loss": 1.942, + "step": 20950 + }, + { + "epoch": 10.88, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 20960 + }, + { + "epoch": 10.88, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 20970 + }, + { + "epoch": 10.89, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 20980 + }, + { + "epoch": 10.89, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 20990 + }, + { + "epoch": 10.9, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 21000 + }, + { + "epoch": 10.9, + "learning_rate": 0.001, + "loss": 1.94, + "step": 21010 + }, + { + "epoch": 10.91, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 21020 + }, + { + "epoch": 10.91, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 21030 + }, + { + "epoch": 10.92, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 21040 + }, + { + "epoch": 10.92, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 21050 + }, + { + "epoch": 10.93, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 21060 + }, + { + "epoch": 10.93, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 21070 + }, + { + "epoch": 10.94, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 21080 + }, + { + "epoch": 10.94, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 21090 + }, + { + "epoch": 10.95, + "learning_rate": 0.001, + "loss": 1.9281, + "step": 21100 + }, + { + "epoch": 10.95, + "learning_rate": 0.001, + "loss": 1.9646, + "step": 21110 + }, + { + "epoch": 10.96, + "learning_rate": 0.001, + "loss": 1.9283, + "step": 21120 + }, + { + "epoch": 10.97, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 21130 + }, + { + "epoch": 10.97, + "learning_rate": 0.001, + "loss": 1.9648, + "step": 21140 + }, + { + "epoch": 10.98, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 21150 + }, + { + "epoch": 10.98, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 21160 + }, + { + "epoch": 10.99, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 21170 + }, + { + "epoch": 10.99, + "learning_rate": 0.001, + "loss": 1.934, + "step": 21180 + }, + { + "epoch": 11.0, + "learning_rate": 0.001, + "loss": 1.945, + "step": 21190 + }, + { + "epoch": 11.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.943160057067871, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.9934, + "eval_samples_per_second": 50.728, + "eval_steps_per_second": 25.371, + "step": 21197 + }, + { + "epoch": 11.0, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 21200 + }, + { + "epoch": 11.01, + "learning_rate": 0.001, + "loss": 1.941, + "step": 21210 + }, + { + "epoch": 11.01, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 21220 + }, + { + "epoch": 11.02, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 21230 + }, + { + "epoch": 11.02, + "learning_rate": 0.001, + "loss": 1.958, + "step": 21240 + }, + { + "epoch": 11.03, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 21250 + }, + { + "epoch": 11.03, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 21260 + }, + { + "epoch": 11.04, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 21270 + }, + { + "epoch": 11.04, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 21280 + }, + { + "epoch": 11.05, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 21290 + }, + { + "epoch": 11.05, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 21300 + }, + { + "epoch": 11.06, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 21310 + }, + { + "epoch": 11.06, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 21320 + }, + { + "epoch": 11.07, + "learning_rate": 0.001, + "loss": 1.946, + "step": 21330 + }, + { + "epoch": 11.07, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 21340 + }, + { + "epoch": 11.08, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 21350 + }, + { + "epoch": 11.08, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 21360 + }, + { + "epoch": 11.09, + "learning_rate": 0.001, + "loss": 1.9242, + "step": 21370 + }, + { + "epoch": 11.09, + "learning_rate": 0.001, + "loss": 1.9265, + "step": 21380 + }, + { + "epoch": 11.1, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 21390 + }, + { + "epoch": 11.11, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 21400 + }, + { + "epoch": 11.11, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 21410 + }, + { + "epoch": 11.12, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 21420 + }, + { + "epoch": 11.12, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 21430 + }, + { + "epoch": 11.13, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 21440 + }, + { + "epoch": 11.13, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 21450 + }, + { + "epoch": 11.14, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 21460 + }, + { + "epoch": 11.14, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 21470 + }, + { + "epoch": 11.15, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 21480 + }, + { + "epoch": 11.15, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 21490 + }, + { + "epoch": 11.16, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 21500 + }, + { + "epoch": 11.16, + "learning_rate": 0.001, + "loss": 1.943, + "step": 21510 + }, + { + "epoch": 11.17, + "learning_rate": 0.001, + "loss": 1.9259, + "step": 21520 + }, + { + "epoch": 11.17, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 21530 + }, + { + "epoch": 11.18, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 21540 + }, + { + "epoch": 11.18, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 21550 + }, + { + "epoch": 11.19, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 21560 + }, + { + "epoch": 11.19, + "learning_rate": 0.001, + "loss": 1.9226, + "step": 21570 + }, + { + "epoch": 11.2, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 21580 + }, + { + "epoch": 11.2, + "learning_rate": 0.001, + "loss": 1.9678, + "step": 21590 + }, + { + "epoch": 11.21, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 21600 + }, + { + "epoch": 11.21, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 21610 + }, + { + "epoch": 11.22, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 21620 + }, + { + "epoch": 11.22, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 21630 + }, + { + "epoch": 11.23, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 21640 + }, + { + "epoch": 11.24, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 21650 + }, + { + "epoch": 11.24, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 21660 + }, + { + "epoch": 11.25, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 21670 + }, + { + "epoch": 11.25, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 21680 + }, + { + "epoch": 11.26, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 21690 + }, + { + "epoch": 11.26, + "learning_rate": 0.001, + "loss": 1.9262, + "step": 21700 + }, + { + "epoch": 11.27, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 21710 + }, + { + "epoch": 11.27, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 21720 + }, + { + "epoch": 11.28, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 21730 + }, + { + "epoch": 11.28, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 21740 + }, + { + "epoch": 11.29, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 21750 + }, + { + "epoch": 11.29, + "learning_rate": 0.001, + "loss": 1.9173, + "step": 21760 + }, + { + "epoch": 11.3, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 21770 + }, + { + "epoch": 11.3, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 21780 + }, + { + "epoch": 11.31, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 21790 + }, + { + "epoch": 11.31, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 21800 + }, + { + "epoch": 11.32, + "learning_rate": 0.001, + "loss": 1.955, + "step": 21810 + }, + { + "epoch": 11.32, + "learning_rate": 0.001, + "loss": 1.9216, + "step": 21820 + }, + { + "epoch": 11.33, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 21830 + }, + { + "epoch": 11.33, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 21840 + }, + { + "epoch": 11.34, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 21850 + }, + { + "epoch": 11.34, + "learning_rate": 0.001, + "loss": 1.9633, + "step": 21860 + }, + { + "epoch": 11.35, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 21870 + }, + { + "epoch": 11.35, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 21880 + }, + { + "epoch": 11.36, + "learning_rate": 0.001, + "loss": 1.96, + "step": 21890 + }, + { + "epoch": 11.36, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 21900 + }, + { + "epoch": 11.37, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 21910 + }, + { + "epoch": 11.38, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 21920 + }, + { + "epoch": 11.38, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 21930 + }, + { + "epoch": 11.39, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 21940 + }, + { + "epoch": 11.39, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 21950 + }, + { + "epoch": 11.4, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 21960 + }, + { + "epoch": 11.4, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 21970 + }, + { + "epoch": 11.41, + "learning_rate": 0.001, + "loss": 1.925, + "step": 21980 + }, + { + "epoch": 11.41, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 21990 + }, + { + "epoch": 11.42, + "learning_rate": 0.001, + "loss": 1.9748, + "step": 22000 + }, + { + "epoch": 11.42, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 22010 + }, + { + "epoch": 11.43, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 22020 + }, + { + "epoch": 11.43, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 22030 + }, + { + "epoch": 11.44, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 22040 + }, + { + "epoch": 11.44, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 22050 + }, + { + "epoch": 11.45, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 22060 + }, + { + "epoch": 11.45, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 22070 + }, + { + "epoch": 11.46, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 22080 + }, + { + "epoch": 11.46, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 22090 + }, + { + "epoch": 11.47, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 22100 + }, + { + "epoch": 11.47, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 22110 + }, + { + "epoch": 11.48, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 22120 + }, + { + "epoch": 11.48, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 22130 + }, + { + "epoch": 11.49, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 22140 + }, + { + "epoch": 11.49, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 22150 + }, + { + "epoch": 11.5, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 22160 + }, + { + "epoch": 11.5, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 22170 + }, + { + "epoch": 11.51, + "learning_rate": 0.001, + "loss": 1.942, + "step": 22180 + }, + { + "epoch": 11.52, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 22190 + }, + { + "epoch": 11.52, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 22200 + }, + { + "epoch": 11.53, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 22210 + }, + { + "epoch": 11.53, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 22220 + }, + { + "epoch": 11.54, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 22230 + }, + { + "epoch": 11.54, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 22240 + }, + { + "epoch": 11.55, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 22250 + }, + { + "epoch": 11.55, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 22260 + }, + { + "epoch": 11.56, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 22270 + }, + { + "epoch": 11.56, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 22280 + }, + { + "epoch": 11.57, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 22290 + }, + { + "epoch": 11.57, + "learning_rate": 0.001, + "loss": 1.936, + "step": 22300 + }, + { + "epoch": 11.58, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 22310 + }, + { + "epoch": 11.58, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 22320 + }, + { + "epoch": 11.59, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 22330 + }, + { + "epoch": 11.59, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 22340 + }, + { + "epoch": 11.6, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 22350 + }, + { + "epoch": 11.6, + "learning_rate": 0.001, + "loss": 1.9649, + "step": 22360 + }, + { + "epoch": 11.61, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 22370 + }, + { + "epoch": 11.61, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 22380 + }, + { + "epoch": 11.62, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 22390 + }, + { + "epoch": 11.62, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 22400 + }, + { + "epoch": 11.63, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 22410 + }, + { + "epoch": 11.63, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 22420 + }, + { + "epoch": 11.64, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 22430 + }, + { + "epoch": 11.65, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 22440 + }, + { + "epoch": 11.65, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 22450 + }, + { + "epoch": 11.66, + "learning_rate": 0.001, + "loss": 1.951, + "step": 22460 + }, + { + "epoch": 11.66, + "learning_rate": 0.001, + "loss": 1.94, + "step": 22470 + }, + { + "epoch": 11.67, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 22480 + }, + { + "epoch": 11.67, + "learning_rate": 0.001, + "loss": 1.9604, + "step": 22490 + }, + { + "epoch": 11.68, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 22500 + }, + { + "epoch": 11.68, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 22510 + }, + { + "epoch": 11.69, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 22520 + }, + { + "epoch": 11.69, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 22530 + }, + { + "epoch": 11.7, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 22540 + }, + { + "epoch": 11.7, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 22550 + }, + { + "epoch": 11.71, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 22560 + }, + { + "epoch": 11.71, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 22570 + }, + { + "epoch": 11.72, + "learning_rate": 0.001, + "loss": 1.948, + "step": 22580 + }, + { + "epoch": 11.72, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 22590 + }, + { + "epoch": 11.73, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 22600 + }, + { + "epoch": 11.73, + "learning_rate": 0.001, + "loss": 1.9208, + "step": 22610 + }, + { + "epoch": 11.74, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 22620 + }, + { + "epoch": 11.74, + "learning_rate": 0.001, + "loss": 1.9602, + "step": 22630 + }, + { + "epoch": 11.75, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 22640 + }, + { + "epoch": 11.75, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 22650 + }, + { + "epoch": 11.76, + "learning_rate": 0.001, + "loss": 1.9648, + "step": 22660 + }, + { + "epoch": 11.76, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 22670 + }, + { + "epoch": 11.77, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 22680 + }, + { + "epoch": 11.77, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 22690 + }, + { + "epoch": 11.78, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 22700 + }, + { + "epoch": 11.79, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 22710 + }, + { + "epoch": 11.79, + "learning_rate": 0.001, + "loss": 1.9712, + "step": 22720 + }, + { + "epoch": 11.8, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 22730 + }, + { + "epoch": 11.8, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 22740 + }, + { + "epoch": 11.81, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 22750 + }, + { + "epoch": 11.81, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 22760 + }, + { + "epoch": 11.82, + "learning_rate": 0.001, + "loss": 1.944, + "step": 22770 + }, + { + "epoch": 11.82, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 22780 + }, + { + "epoch": 11.83, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 22790 + }, + { + "epoch": 11.83, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 22800 + }, + { + "epoch": 11.84, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 22810 + }, + { + "epoch": 11.84, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 22820 + }, + { + "epoch": 11.85, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 22830 + }, + { + "epoch": 11.85, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 22840 + }, + { + "epoch": 11.86, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 22850 + }, + { + "epoch": 11.86, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 22860 + }, + { + "epoch": 11.87, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 22870 + }, + { + "epoch": 11.87, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 22880 + }, + { + "epoch": 11.88, + "learning_rate": 0.001, + "loss": 1.953, + "step": 22890 + }, + { + "epoch": 11.88, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 22900 + }, + { + "epoch": 11.89, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 22910 + }, + { + "epoch": 11.89, + "learning_rate": 0.001, + "loss": 1.9562, + "step": 22920 + }, + { + "epoch": 11.9, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 22930 + }, + { + "epoch": 11.9, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 22940 + }, + { + "epoch": 11.91, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 22950 + }, + { + "epoch": 11.91, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 22960 + }, + { + "epoch": 11.92, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 22970 + }, + { + "epoch": 11.93, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 22980 + }, + { + "epoch": 11.93, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 22990 + }, + { + "epoch": 11.94, + "learning_rate": 0.001, + "loss": 1.957, + "step": 23000 + }, + { + "epoch": 11.94, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 23010 + }, + { + "epoch": 11.95, + "learning_rate": 0.001, + "loss": 1.953, + "step": 23020 + }, + { + "epoch": 11.95, + "learning_rate": 0.001, + "loss": 1.9213, + "step": 23030 + }, + { + "epoch": 11.96, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 23040 + }, + { + "epoch": 11.96, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 23050 + }, + { + "epoch": 11.97, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 23060 + }, + { + "epoch": 11.97, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 23070 + }, + { + "epoch": 11.98, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 23080 + }, + { + "epoch": 11.98, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 23090 + }, + { + "epoch": 11.99, + "learning_rate": 0.001, + "loss": 1.9192, + "step": 23100 + }, + { + "epoch": 11.99, + "learning_rate": 0.001, + "loss": 1.9279, + "step": 23110 + }, + { + "epoch": 12.0, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 23120 + }, + { + "epoch": 12.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9443979263305664, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.177, + "eval_samples_per_second": 50.606, + "eval_steps_per_second": 25.309, + "step": 23124 + }, + { + "epoch": 12.0, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 23130 + }, + { + "epoch": 12.01, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 23140 + }, + { + "epoch": 12.01, + "learning_rate": 0.001, + "loss": 1.9845, + "step": 23150 + }, + { + "epoch": 12.02, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 23160 + }, + { + "epoch": 12.02, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 23170 + }, + { + "epoch": 12.03, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 23180 + }, + { + "epoch": 12.03, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 23190 + }, + { + "epoch": 12.04, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 23200 + }, + { + "epoch": 12.04, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 23210 + }, + { + "epoch": 12.05, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 23220 + }, + { + "epoch": 12.06, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 23230 + }, + { + "epoch": 12.06, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 23240 + }, + { + "epoch": 12.07, + "learning_rate": 0.001, + "loss": 1.9694, + "step": 23250 + }, + { + "epoch": 12.07, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 23260 + }, + { + "epoch": 12.08, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 23270 + }, + { + "epoch": 12.08, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 23280 + }, + { + "epoch": 12.09, + "learning_rate": 0.001, + "loss": 1.9236, + "step": 23290 + }, + { + "epoch": 12.09, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 23300 + }, + { + "epoch": 12.1, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 23310 + }, + { + "epoch": 12.1, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 23320 + }, + { + "epoch": 12.11, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 23330 + }, + { + "epoch": 12.11, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 23340 + }, + { + "epoch": 12.12, + "learning_rate": 0.001, + "loss": 1.9216, + "step": 23350 + }, + { + "epoch": 12.12, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 23360 + }, + { + "epoch": 12.13, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 23370 + }, + { + "epoch": 12.13, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 23380 + }, + { + "epoch": 12.14, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 23390 + }, + { + "epoch": 12.14, + "learning_rate": 0.001, + "loss": 1.9225, + "step": 23400 + }, + { + "epoch": 12.15, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 23410 + }, + { + "epoch": 12.15, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 23420 + }, + { + "epoch": 12.16, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 23430 + }, + { + "epoch": 12.16, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 23440 + }, + { + "epoch": 12.17, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 23450 + }, + { + "epoch": 12.17, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 23460 + }, + { + "epoch": 12.18, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 23470 + }, + { + "epoch": 12.18, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 23480 + }, + { + "epoch": 12.19, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 23490 + }, + { + "epoch": 12.2, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 23500 + }, + { + "epoch": 12.2, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 23510 + }, + { + "epoch": 12.21, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 23520 + }, + { + "epoch": 12.21, + "learning_rate": 0.001, + "loss": 1.948, + "step": 23530 + }, + { + "epoch": 12.22, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 23540 + }, + { + "epoch": 12.22, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 23550 + }, + { + "epoch": 12.23, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 23560 + }, + { + "epoch": 12.23, + "learning_rate": 0.001, + "loss": 1.9629, + "step": 23570 + }, + { + "epoch": 12.24, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 23580 + }, + { + "epoch": 12.24, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 23590 + }, + { + "epoch": 12.25, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 23600 + }, + { + "epoch": 12.25, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 23610 + }, + { + "epoch": 12.26, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 23620 + }, + { + "epoch": 12.26, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 23630 + }, + { + "epoch": 12.27, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 23640 + }, + { + "epoch": 12.27, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 23650 + }, + { + "epoch": 12.28, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 23660 + }, + { + "epoch": 12.28, + "learning_rate": 0.001, + "loss": 1.9183, + "step": 23670 + }, + { + "epoch": 12.29, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 23680 + }, + { + "epoch": 12.29, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 23690 + }, + { + "epoch": 12.3, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 23700 + }, + { + "epoch": 12.3, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 23710 + }, + { + "epoch": 12.31, + "learning_rate": 0.001, + "loss": 1.946, + "step": 23720 + }, + { + "epoch": 12.31, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 23730 + }, + { + "epoch": 12.32, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 23740 + }, + { + "epoch": 12.32, + "learning_rate": 0.001, + "loss": 1.932, + "step": 23750 + }, + { + "epoch": 12.33, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 23760 + }, + { + "epoch": 12.34, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 23770 + }, + { + "epoch": 12.34, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 23780 + }, + { + "epoch": 12.35, + "learning_rate": 0.001, + "loss": 1.9631, + "step": 23790 + }, + { + "epoch": 12.35, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 23800 + }, + { + "epoch": 12.36, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 23810 + }, + { + "epoch": 12.36, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 23820 + }, + { + "epoch": 12.37, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 23830 + }, + { + "epoch": 12.37, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 23840 + }, + { + "epoch": 12.38, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 23850 + }, + { + "epoch": 12.38, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 23860 + }, + { + "epoch": 12.39, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 23870 + }, + { + "epoch": 12.39, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 23880 + }, + { + "epoch": 12.4, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 23890 + }, + { + "epoch": 12.4, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 23900 + }, + { + "epoch": 12.41, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 23910 + }, + { + "epoch": 12.41, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 23920 + }, + { + "epoch": 12.42, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 23930 + }, + { + "epoch": 12.42, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 23940 + }, + { + "epoch": 12.43, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 23950 + }, + { + "epoch": 12.43, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 23960 + }, + { + "epoch": 12.44, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 23970 + }, + { + "epoch": 12.44, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 23980 + }, + { + "epoch": 12.45, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 23990 + }, + { + "epoch": 12.45, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 24000 + }, + { + "epoch": 12.46, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 24010 + }, + { + "epoch": 12.46, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 24020 + }, + { + "epoch": 12.47, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 24030 + }, + { + "epoch": 12.48, + "learning_rate": 0.001, + "loss": 1.943, + "step": 24040 + }, + { + "epoch": 12.48, + "learning_rate": 0.001, + "loss": 1.9769, + "step": 24050 + }, + { + "epoch": 12.49, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 24060 + }, + { + "epoch": 12.49, + "learning_rate": 0.001, + "loss": 1.9664, + "step": 24070 + }, + { + "epoch": 12.5, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 24080 + }, + { + "epoch": 12.5, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 24090 + }, + { + "epoch": 12.51, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 24100 + }, + { + "epoch": 12.51, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 24110 + }, + { + "epoch": 12.52, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 24120 + }, + { + "epoch": 12.52, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 24130 + }, + { + "epoch": 12.53, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 24140 + }, + { + "epoch": 12.53, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 24150 + }, + { + "epoch": 12.54, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 24160 + }, + { + "epoch": 12.54, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 24170 + }, + { + "epoch": 12.55, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 24180 + }, + { + "epoch": 12.55, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 24190 + }, + { + "epoch": 12.56, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 24200 + }, + { + "epoch": 12.56, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 24210 + }, + { + "epoch": 12.57, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 24220 + }, + { + "epoch": 12.57, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 24230 + }, + { + "epoch": 12.58, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 24240 + }, + { + "epoch": 12.58, + "learning_rate": 0.001, + "loss": 1.9631, + "step": 24250 + }, + { + "epoch": 12.59, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 24260 + }, + { + "epoch": 12.59, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 24270 + }, + { + "epoch": 12.6, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 24280 + }, + { + "epoch": 12.61, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 24290 + }, + { + "epoch": 12.61, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 24300 + }, + { + "epoch": 12.62, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 24310 + }, + { + "epoch": 12.62, + "learning_rate": 0.001, + "loss": 1.9254, + "step": 24320 + }, + { + "epoch": 12.63, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 24330 + }, + { + "epoch": 12.63, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 24340 + }, + { + "epoch": 12.64, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 24350 + }, + { + "epoch": 12.64, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 24360 + }, + { + "epoch": 12.65, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 24370 + }, + { + "epoch": 12.65, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 24380 + }, + { + "epoch": 12.66, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 24390 + }, + { + "epoch": 12.66, + "learning_rate": 0.001, + "loss": 1.9257, + "step": 24400 + }, + { + "epoch": 12.67, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 24410 + }, + { + "epoch": 12.67, + "learning_rate": 0.001, + "loss": 1.9208, + "step": 24420 + }, + { + "epoch": 12.68, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 24430 + }, + { + "epoch": 12.68, + "learning_rate": 0.001, + "loss": 1.9591, + "step": 24440 + }, + { + "epoch": 12.69, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 24450 + }, + { + "epoch": 12.69, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 24460 + }, + { + "epoch": 12.7, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 24470 + }, + { + "epoch": 12.7, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 24480 + }, + { + "epoch": 12.71, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 24490 + }, + { + "epoch": 12.71, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 24500 + }, + { + "epoch": 12.72, + "learning_rate": 0.001, + "loss": 1.928, + "step": 24510 + }, + { + "epoch": 12.72, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 24520 + }, + { + "epoch": 12.73, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 24530 + }, + { + "epoch": 12.73, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 24540 + }, + { + "epoch": 12.74, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 24550 + }, + { + "epoch": 12.75, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 24560 + }, + { + "epoch": 12.75, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 24570 + }, + { + "epoch": 12.76, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 24580 + }, + { + "epoch": 12.76, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 24590 + }, + { + "epoch": 12.77, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 24600 + }, + { + "epoch": 12.77, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 24610 + }, + { + "epoch": 12.78, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 24620 + }, + { + "epoch": 12.78, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 24630 + }, + { + "epoch": 12.79, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 24640 + }, + { + "epoch": 12.79, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 24650 + }, + { + "epoch": 12.8, + "learning_rate": 0.001, + "loss": 1.96, + "step": 24660 + }, + { + "epoch": 12.8, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 24670 + }, + { + "epoch": 12.81, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 24680 + }, + { + "epoch": 12.81, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 24690 + }, + { + "epoch": 12.82, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 24700 + }, + { + "epoch": 12.82, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 24710 + }, + { + "epoch": 12.83, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 24720 + }, + { + "epoch": 12.83, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 24730 + }, + { + "epoch": 12.84, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 24740 + }, + { + "epoch": 12.84, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 24750 + }, + { + "epoch": 12.85, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 24760 + }, + { + "epoch": 12.85, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 24770 + }, + { + "epoch": 12.86, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 24780 + }, + { + "epoch": 12.86, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 24790 + }, + { + "epoch": 12.87, + "learning_rate": 0.001, + "loss": 1.9637, + "step": 24800 + }, + { + "epoch": 12.87, + "learning_rate": 0.001, + "loss": 1.9556, + "step": 24810 + }, + { + "epoch": 12.88, + "learning_rate": 0.001, + "loss": 1.9612, + "step": 24820 + }, + { + "epoch": 12.89, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 24830 + }, + { + "epoch": 12.89, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 24840 + }, + { + "epoch": 12.9, + "learning_rate": 0.001, + "loss": 1.946, + "step": 24850 + }, + { + "epoch": 12.9, + "learning_rate": 0.001, + "loss": 1.9248, + "step": 24860 + }, + { + "epoch": 12.91, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 24870 + }, + { + "epoch": 12.91, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 24880 + }, + { + "epoch": 12.92, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 24890 + }, + { + "epoch": 12.92, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 24900 + }, + { + "epoch": 12.93, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 24910 + }, + { + "epoch": 12.93, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 24920 + }, + { + "epoch": 12.94, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 24930 + }, + { + "epoch": 12.94, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 24940 + }, + { + "epoch": 12.95, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 24950 + }, + { + "epoch": 12.95, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 24960 + }, + { + "epoch": 12.96, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 24970 + }, + { + "epoch": 12.96, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 24980 + }, + { + "epoch": 12.97, + "learning_rate": 0.001, + "loss": 1.955, + "step": 24990 + }, + { + "epoch": 12.97, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 25000 + }, + { + "epoch": 12.98, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 25010 + }, + { + "epoch": 12.98, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 25020 + }, + { + "epoch": 12.99, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 25030 + }, + { + "epoch": 12.99, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 25040 + }, + { + "epoch": 13.0, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 25050 + }, + { + "epoch": 13.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9415048360824585, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.0997, + "eval_samples_per_second": 50.0, + "eval_steps_per_second": 25.007, + "step": 25051 + }, + { + "epoch": 13.0, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 25060 + }, + { + "epoch": 13.01, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 25070 + }, + { + "epoch": 13.02, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 25080 + }, + { + "epoch": 13.02, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 25090 + }, + { + "epoch": 13.03, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 25100 + }, + { + "epoch": 13.03, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 25110 + }, + { + "epoch": 13.04, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 25120 + }, + { + "epoch": 13.04, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 25130 + }, + { + "epoch": 13.05, + "learning_rate": 0.001, + "loss": 1.937, + "step": 25140 + }, + { + "epoch": 13.05, + "learning_rate": 0.001, + "loss": 1.921, + "step": 25150 + }, + { + "epoch": 13.06, + "learning_rate": 0.001, + "loss": 1.944, + "step": 25160 + }, + { + "epoch": 13.06, + "learning_rate": 0.001, + "loss": 1.9649, + "step": 25170 + }, + { + "epoch": 13.07, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 25180 + }, + { + "epoch": 13.07, + "learning_rate": 0.001, + "loss": 1.941, + "step": 25190 + }, + { + "epoch": 13.08, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 25200 + }, + { + "epoch": 13.08, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 25210 + }, + { + "epoch": 13.09, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 25220 + }, + { + "epoch": 13.09, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 25230 + }, + { + "epoch": 13.1, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 25240 + }, + { + "epoch": 13.1, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 25250 + }, + { + "epoch": 13.11, + "learning_rate": 0.001, + "loss": 1.9175, + "step": 25260 + }, + { + "epoch": 13.11, + "learning_rate": 0.001, + "loss": 1.9066, + "step": 25270 + }, + { + "epoch": 13.12, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 25280 + }, + { + "epoch": 13.12, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 25290 + }, + { + "epoch": 13.13, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 25300 + }, + { + "epoch": 13.13, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 25310 + }, + { + "epoch": 13.14, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 25320 + }, + { + "epoch": 13.14, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 25330 + }, + { + "epoch": 13.15, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 25340 + }, + { + "epoch": 13.16, + "learning_rate": 0.001, + "loss": 1.9268, + "step": 25350 + }, + { + "epoch": 13.16, + "learning_rate": 0.001, + "loss": 1.928, + "step": 25360 + }, + { + "epoch": 13.17, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 25370 + }, + { + "epoch": 13.17, + "learning_rate": 0.001, + "loss": 1.9675, + "step": 25380 + }, + { + "epoch": 13.18, + "learning_rate": 0.001, + "loss": 1.9682, + "step": 25390 + }, + { + "epoch": 13.18, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 25400 + }, + { + "epoch": 13.19, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 25410 + }, + { + "epoch": 13.19, + "learning_rate": 0.001, + "loss": 1.956, + "step": 25420 + }, + { + "epoch": 13.2, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 25430 + }, + { + "epoch": 13.2, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 25440 + }, + { + "epoch": 13.21, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 25450 + }, + { + "epoch": 13.21, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 25460 + }, + { + "epoch": 13.22, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 25470 + }, + { + "epoch": 13.22, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 25480 + }, + { + "epoch": 13.23, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 25490 + }, + { + "epoch": 13.23, + "learning_rate": 0.001, + "loss": 1.957, + "step": 25500 + }, + { + "epoch": 13.24, + "learning_rate": 0.001, + "loss": 1.942, + "step": 25510 + }, + { + "epoch": 13.24, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 25520 + }, + { + "epoch": 13.25, + "learning_rate": 0.001, + "loss": 1.9695, + "step": 25530 + }, + { + "epoch": 13.25, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 25540 + }, + { + "epoch": 13.26, + "learning_rate": 0.001, + "loss": 1.9634, + "step": 25550 + }, + { + "epoch": 13.26, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 25560 + }, + { + "epoch": 13.27, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 25570 + }, + { + "epoch": 13.27, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 25580 + }, + { + "epoch": 13.28, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 25590 + }, + { + "epoch": 13.28, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 25600 + }, + { + "epoch": 13.29, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 25610 + }, + { + "epoch": 13.3, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 25620 + }, + { + "epoch": 13.3, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 25630 + }, + { + "epoch": 13.31, + "learning_rate": 0.001, + "loss": 1.9191, + "step": 25640 + }, + { + "epoch": 13.31, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 25650 + }, + { + "epoch": 13.32, + "learning_rate": 0.001, + "loss": 1.9609, + "step": 25660 + }, + { + "epoch": 13.32, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 25670 + }, + { + "epoch": 13.33, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 25680 + }, + { + "epoch": 13.33, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 25690 + }, + { + "epoch": 13.34, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 25700 + }, + { + "epoch": 13.34, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 25710 + }, + { + "epoch": 13.35, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 25720 + }, + { + "epoch": 13.35, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 25730 + }, + { + "epoch": 13.36, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 25740 + }, + { + "epoch": 13.36, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 25750 + }, + { + "epoch": 13.37, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 25760 + }, + { + "epoch": 13.37, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 25770 + }, + { + "epoch": 13.38, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 25780 + }, + { + "epoch": 13.38, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 25790 + }, + { + "epoch": 13.39, + "learning_rate": 0.001, + "loss": 1.947, + "step": 25800 + }, + { + "epoch": 13.39, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 25810 + }, + { + "epoch": 13.4, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 25820 + }, + { + "epoch": 13.4, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 25830 + }, + { + "epoch": 13.41, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 25840 + }, + { + "epoch": 13.41, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 25850 + }, + { + "epoch": 13.42, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 25860 + }, + { + "epoch": 13.43, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 25870 + }, + { + "epoch": 13.43, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 25880 + }, + { + "epoch": 13.44, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 25890 + }, + { + "epoch": 13.44, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 25900 + }, + { + "epoch": 13.45, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 25910 + }, + { + "epoch": 13.45, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 25920 + }, + { + "epoch": 13.46, + "learning_rate": 0.001, + "loss": 1.928, + "step": 25930 + }, + { + "epoch": 13.46, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 25940 + }, + { + "epoch": 13.47, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 25950 + }, + { + "epoch": 13.47, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 25960 + }, + { + "epoch": 13.48, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 25970 + }, + { + "epoch": 13.48, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 25980 + }, + { + "epoch": 13.49, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 25990 + }, + { + "epoch": 13.49, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 26000 + }, + { + "epoch": 13.5, + "learning_rate": 0.001, + "loss": 1.9261, + "step": 26010 + }, + { + "epoch": 13.5, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 26020 + }, + { + "epoch": 13.51, + "learning_rate": 0.001, + "loss": 1.9633, + "step": 26030 + }, + { + "epoch": 13.51, + "learning_rate": 0.001, + "loss": 1.944, + "step": 26040 + }, + { + "epoch": 13.52, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 26050 + }, + { + "epoch": 13.52, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 26060 + }, + { + "epoch": 13.53, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 26070 + }, + { + "epoch": 13.53, + "learning_rate": 0.001, + "loss": 1.9248, + "step": 26080 + }, + { + "epoch": 13.54, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 26090 + }, + { + "epoch": 13.54, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 26100 + }, + { + "epoch": 13.55, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 26110 + }, + { + "epoch": 13.55, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 26120 + }, + { + "epoch": 13.56, + "learning_rate": 0.001, + "loss": 1.957, + "step": 26130 + }, + { + "epoch": 13.57, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 26140 + }, + { + "epoch": 13.57, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 26150 + }, + { + "epoch": 13.58, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 26160 + }, + { + "epoch": 13.58, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 26170 + }, + { + "epoch": 13.59, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 26180 + }, + { + "epoch": 13.59, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 26190 + }, + { + "epoch": 13.6, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 26200 + }, + { + "epoch": 13.6, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 26210 + }, + { + "epoch": 13.61, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 26220 + }, + { + "epoch": 13.61, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 26230 + }, + { + "epoch": 13.62, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 26240 + }, + { + "epoch": 13.62, + "learning_rate": 0.001, + "loss": 1.9254, + "step": 26250 + }, + { + "epoch": 13.63, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 26260 + }, + { + "epoch": 13.63, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 26270 + }, + { + "epoch": 13.64, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 26280 + }, + { + "epoch": 13.64, + "learning_rate": 0.001, + "loss": 1.94, + "step": 26290 + }, + { + "epoch": 13.65, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 26300 + }, + { + "epoch": 13.65, + "learning_rate": 0.001, + "loss": 1.937, + "step": 26310 + }, + { + "epoch": 13.66, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 26320 + }, + { + "epoch": 13.66, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 26330 + }, + { + "epoch": 13.67, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 26340 + }, + { + "epoch": 13.67, + "learning_rate": 0.001, + "loss": 1.9667, + "step": 26350 + }, + { + "epoch": 13.68, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 26360 + }, + { + "epoch": 13.68, + "learning_rate": 0.001, + "loss": 1.947, + "step": 26370 + }, + { + "epoch": 13.69, + "learning_rate": 0.001, + "loss": 1.951, + "step": 26380 + }, + { + "epoch": 13.69, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 26390 + }, + { + "epoch": 13.7, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 26400 + }, + { + "epoch": 13.71, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 26410 + }, + { + "epoch": 13.71, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 26420 + }, + { + "epoch": 13.72, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 26430 + }, + { + "epoch": 13.72, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 26440 + }, + { + "epoch": 13.73, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 26450 + }, + { + "epoch": 13.73, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 26460 + }, + { + "epoch": 13.74, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 26470 + }, + { + "epoch": 13.74, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 26480 + }, + { + "epoch": 13.75, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 26490 + }, + { + "epoch": 13.75, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 26500 + }, + { + "epoch": 13.76, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 26510 + }, + { + "epoch": 13.76, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 26520 + }, + { + "epoch": 13.77, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 26530 + }, + { + "epoch": 13.77, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 26540 + }, + { + "epoch": 13.78, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 26550 + }, + { + "epoch": 13.78, + "learning_rate": 0.001, + "loss": 1.9643, + "step": 26560 + }, + { + "epoch": 13.79, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 26570 + }, + { + "epoch": 13.79, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 26580 + }, + { + "epoch": 13.8, + "learning_rate": 0.001, + "loss": 1.9657, + "step": 26590 + }, + { + "epoch": 13.8, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 26600 + }, + { + "epoch": 13.81, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 26610 + }, + { + "epoch": 13.81, + "learning_rate": 0.001, + "loss": 1.9279, + "step": 26620 + }, + { + "epoch": 13.82, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 26630 + }, + { + "epoch": 13.82, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 26640 + }, + { + "epoch": 13.83, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 26650 + }, + { + "epoch": 13.83, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 26660 + }, + { + "epoch": 13.84, + "learning_rate": 0.001, + "loss": 1.9245, + "step": 26670 + }, + { + "epoch": 13.85, + "learning_rate": 0.001, + "loss": 1.956, + "step": 26680 + }, + { + "epoch": 13.85, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 26690 + }, + { + "epoch": 13.86, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 26700 + }, + { + "epoch": 13.86, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 26710 + }, + { + "epoch": 13.87, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 26720 + }, + { + "epoch": 13.87, + "learning_rate": 0.001, + "loss": 1.9629, + "step": 26730 + }, + { + "epoch": 13.88, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 26740 + }, + { + "epoch": 13.88, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 26750 + }, + { + "epoch": 13.89, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 26760 + }, + { + "epoch": 13.89, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 26770 + }, + { + "epoch": 13.9, + "learning_rate": 0.001, + "loss": 1.96, + "step": 26780 + }, + { + "epoch": 13.9, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 26790 + }, + { + "epoch": 13.91, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 26800 + }, + { + "epoch": 13.91, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 26810 + }, + { + "epoch": 13.92, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 26820 + }, + { + "epoch": 13.92, + "learning_rate": 0.001, + "loss": 1.932, + "step": 26830 + }, + { + "epoch": 13.93, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 26840 + }, + { + "epoch": 13.93, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 26850 + }, + { + "epoch": 13.94, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 26860 + }, + { + "epoch": 13.94, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 26870 + }, + { + "epoch": 13.95, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 26880 + }, + { + "epoch": 13.95, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 26890 + }, + { + "epoch": 13.96, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 26900 + }, + { + "epoch": 13.96, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 26910 + }, + { + "epoch": 13.97, + "learning_rate": 0.001, + "loss": 1.94, + "step": 26920 + }, + { + "epoch": 13.98, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 26930 + }, + { + "epoch": 13.98, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 26940 + }, + { + "epoch": 13.99, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 26950 + }, + { + "epoch": 13.99, + "learning_rate": 0.001, + "loss": 1.943, + "step": 26960 + }, + { + "epoch": 14.0, + "learning_rate": 0.001, + "loss": 1.934, + "step": 26970 + }, + { + "epoch": 14.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9407793283462524, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.3935, + "eval_samples_per_second": 50.462, + "eval_steps_per_second": 25.238, + "step": 26978 + }, + { + "epoch": 14.0, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 26980 + }, + { + "epoch": 14.01, + "learning_rate": 0.001, + "loss": 1.9699, + "step": 26990 + }, + { + "epoch": 14.01, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 27000 + }, + { + "epoch": 14.02, + "learning_rate": 0.001, + "loss": 1.9283, + "step": 27010 + }, + { + "epoch": 14.02, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 27020 + }, + { + "epoch": 14.03, + "learning_rate": 0.001, + "loss": 1.9273, + "step": 27030 + }, + { + "epoch": 14.03, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 27040 + }, + { + "epoch": 14.04, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 27050 + }, + { + "epoch": 14.04, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 27060 + }, + { + "epoch": 14.05, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 27070 + }, + { + "epoch": 14.05, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 27080 + }, + { + "epoch": 14.06, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 27090 + }, + { + "epoch": 14.06, + "learning_rate": 0.001, + "loss": 1.93, + "step": 27100 + }, + { + "epoch": 14.07, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 27110 + }, + { + "epoch": 14.07, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 27120 + }, + { + "epoch": 14.08, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 27130 + }, + { + "epoch": 14.08, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 27140 + }, + { + "epoch": 14.09, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 27150 + }, + { + "epoch": 14.09, + "learning_rate": 0.001, + "loss": 1.944, + "step": 27160 + }, + { + "epoch": 14.1, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 27170 + }, + { + "epoch": 14.1, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 27180 + }, + { + "epoch": 14.11, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 27190 + }, + { + "epoch": 14.12, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 27200 + }, + { + "epoch": 14.12, + "learning_rate": 0.001, + "loss": 1.9559, + "step": 27210 + }, + { + "epoch": 14.13, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 27220 + }, + { + "epoch": 14.13, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 27230 + }, + { + "epoch": 14.14, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 27240 + }, + { + "epoch": 14.14, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 27250 + }, + { + "epoch": 14.15, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 27260 + }, + { + "epoch": 14.15, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 27270 + }, + { + "epoch": 14.16, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 27280 + }, + { + "epoch": 14.16, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 27290 + }, + { + "epoch": 14.17, + "learning_rate": 0.001, + "loss": 1.948, + "step": 27300 + }, + { + "epoch": 14.17, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 27310 + }, + { + "epoch": 14.18, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 27320 + }, + { + "epoch": 14.18, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 27330 + }, + { + "epoch": 14.19, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 27340 + }, + { + "epoch": 14.19, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 27350 + }, + { + "epoch": 14.2, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 27360 + }, + { + "epoch": 14.2, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 27370 + }, + { + "epoch": 14.21, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 27380 + }, + { + "epoch": 14.21, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 27390 + }, + { + "epoch": 14.22, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 27400 + }, + { + "epoch": 14.22, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 27410 + }, + { + "epoch": 14.23, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 27420 + }, + { + "epoch": 14.23, + "learning_rate": 0.001, + "loss": 1.941, + "step": 27430 + }, + { + "epoch": 14.24, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 27440 + }, + { + "epoch": 14.24, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 27450 + }, + { + "epoch": 14.25, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 27460 + }, + { + "epoch": 14.26, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 27470 + }, + { + "epoch": 14.26, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 27480 + }, + { + "epoch": 14.27, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 27490 + }, + { + "epoch": 14.27, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 27500 + }, + { + "epoch": 14.28, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 27510 + }, + { + "epoch": 14.28, + "learning_rate": 0.001, + "loss": 1.9709, + "step": 27520 + }, + { + "epoch": 14.29, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 27530 + }, + { + "epoch": 14.29, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 27540 + }, + { + "epoch": 14.3, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 27550 + }, + { + "epoch": 14.3, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 27560 + }, + { + "epoch": 14.31, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 27570 + }, + { + "epoch": 14.31, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 27580 + }, + { + "epoch": 14.32, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 27590 + }, + { + "epoch": 14.32, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 27600 + }, + { + "epoch": 14.33, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 27610 + }, + { + "epoch": 14.33, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 27620 + }, + { + "epoch": 14.34, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 27630 + }, + { + "epoch": 14.34, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 27640 + }, + { + "epoch": 14.35, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 27650 + }, + { + "epoch": 14.35, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 27660 + }, + { + "epoch": 14.36, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 27670 + }, + { + "epoch": 14.36, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 27680 + }, + { + "epoch": 14.37, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 27690 + }, + { + "epoch": 14.37, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 27700 + }, + { + "epoch": 14.38, + "learning_rate": 0.001, + "loss": 1.936, + "step": 27710 + }, + { + "epoch": 14.39, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 27720 + }, + { + "epoch": 14.39, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 27730 + }, + { + "epoch": 14.4, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 27740 + }, + { + "epoch": 14.4, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 27750 + }, + { + "epoch": 14.41, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 27760 + }, + { + "epoch": 14.41, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 27770 + }, + { + "epoch": 14.42, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 27780 + }, + { + "epoch": 14.42, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 27790 + }, + { + "epoch": 14.43, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 27800 + }, + { + "epoch": 14.43, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 27810 + }, + { + "epoch": 14.44, + "learning_rate": 0.001, + "loss": 1.927, + "step": 27820 + }, + { + "epoch": 14.44, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 27830 + }, + { + "epoch": 14.45, + "learning_rate": 0.001, + "loss": 1.946, + "step": 27840 + }, + { + "epoch": 14.45, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 27850 + }, + { + "epoch": 14.46, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 27860 + }, + { + "epoch": 14.46, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 27870 + }, + { + "epoch": 14.47, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 27880 + }, + { + "epoch": 14.47, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 27890 + }, + { + "epoch": 14.48, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 27900 + }, + { + "epoch": 14.48, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 27910 + }, + { + "epoch": 14.49, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 27920 + }, + { + "epoch": 14.49, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 27930 + }, + { + "epoch": 14.5, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 27940 + }, + { + "epoch": 14.5, + "learning_rate": 0.001, + "loss": 1.943, + "step": 27950 + }, + { + "epoch": 14.51, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 27960 + }, + { + "epoch": 14.51, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 27970 + }, + { + "epoch": 14.52, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 27980 + }, + { + "epoch": 14.53, + "learning_rate": 0.001, + "loss": 1.9559, + "step": 27990 + }, + { + "epoch": 14.53, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 28000 + }, + { + "epoch": 14.54, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 28010 + }, + { + "epoch": 14.54, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 28020 + }, + { + "epoch": 14.55, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 28030 + }, + { + "epoch": 14.55, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 28040 + }, + { + "epoch": 14.56, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 28050 + }, + { + "epoch": 14.56, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 28060 + }, + { + "epoch": 14.57, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 28070 + }, + { + "epoch": 14.57, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 28080 + }, + { + "epoch": 14.58, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 28090 + }, + { + "epoch": 14.58, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 28100 + }, + { + "epoch": 14.59, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 28110 + }, + { + "epoch": 14.59, + "learning_rate": 0.001, + "loss": 1.943, + "step": 28120 + }, + { + "epoch": 14.6, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 28130 + }, + { + "epoch": 14.6, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 28140 + }, + { + "epoch": 14.61, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 28150 + }, + { + "epoch": 14.61, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 28160 + }, + { + "epoch": 14.62, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 28170 + }, + { + "epoch": 14.62, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 28180 + }, + { + "epoch": 14.63, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 28190 + }, + { + "epoch": 14.63, + "learning_rate": 0.001, + "loss": 1.9142, + "step": 28200 + }, + { + "epoch": 14.64, + "learning_rate": 0.001, + "loss": 1.931, + "step": 28210 + }, + { + "epoch": 14.64, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 28220 + }, + { + "epoch": 14.65, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 28230 + }, + { + "epoch": 14.65, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 28240 + }, + { + "epoch": 14.66, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 28250 + }, + { + "epoch": 14.67, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 28260 + }, + { + "epoch": 14.67, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 28270 + }, + { + "epoch": 14.68, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 28280 + }, + { + "epoch": 14.68, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 28290 + }, + { + "epoch": 14.69, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 28300 + }, + { + "epoch": 14.69, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 28310 + }, + { + "epoch": 14.7, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 28320 + }, + { + "epoch": 14.7, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 28330 + }, + { + "epoch": 14.71, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 28340 + }, + { + "epoch": 14.71, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 28350 + }, + { + "epoch": 14.72, + "learning_rate": 0.001, + "loss": 1.945, + "step": 28360 + }, + { + "epoch": 14.72, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 28370 + }, + { + "epoch": 14.73, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 28380 + }, + { + "epoch": 14.73, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 28390 + }, + { + "epoch": 14.74, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 28400 + }, + { + "epoch": 14.74, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 28410 + }, + { + "epoch": 14.75, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 28420 + }, + { + "epoch": 14.75, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 28430 + }, + { + "epoch": 14.76, + "learning_rate": 0.001, + "loss": 1.945, + "step": 28440 + }, + { + "epoch": 14.76, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 28450 + }, + { + "epoch": 14.77, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 28460 + }, + { + "epoch": 14.77, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 28470 + }, + { + "epoch": 14.78, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 28480 + }, + { + "epoch": 14.78, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 28490 + }, + { + "epoch": 14.79, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 28500 + }, + { + "epoch": 14.8, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 28510 + }, + { + "epoch": 14.8, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 28520 + }, + { + "epoch": 14.81, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 28530 + }, + { + "epoch": 14.81, + "learning_rate": 0.001, + "loss": 1.952, + "step": 28540 + }, + { + "epoch": 14.82, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 28550 + }, + { + "epoch": 14.82, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 28560 + }, + { + "epoch": 14.83, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 28570 + }, + { + "epoch": 14.83, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 28580 + }, + { + "epoch": 14.84, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 28590 + }, + { + "epoch": 14.84, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 28600 + }, + { + "epoch": 14.85, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 28610 + }, + { + "epoch": 14.85, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 28620 + }, + { + "epoch": 14.86, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 28630 + }, + { + "epoch": 14.86, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 28640 + }, + { + "epoch": 14.87, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 28650 + }, + { + "epoch": 14.87, + "learning_rate": 0.001, + "loss": 1.9644, + "step": 28660 + }, + { + "epoch": 14.88, + "learning_rate": 0.001, + "loss": 1.938, + "step": 28670 + }, + { + "epoch": 14.88, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 28680 + }, + { + "epoch": 14.89, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 28690 + }, + { + "epoch": 14.89, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 28700 + }, + { + "epoch": 14.9, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 28710 + }, + { + "epoch": 14.9, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 28720 + }, + { + "epoch": 14.91, + "learning_rate": 0.001, + "loss": 1.921, + "step": 28730 + }, + { + "epoch": 14.91, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 28740 + }, + { + "epoch": 14.92, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 28750 + }, + { + "epoch": 14.92, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 28760 + }, + { + "epoch": 14.93, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 28770 + }, + { + "epoch": 14.94, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 28780 + }, + { + "epoch": 14.94, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 28790 + }, + { + "epoch": 14.95, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 28800 + }, + { + "epoch": 14.95, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 28810 + }, + { + "epoch": 14.96, + "learning_rate": 0.001, + "loss": 1.9733, + "step": 28820 + }, + { + "epoch": 14.96, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 28830 + }, + { + "epoch": 14.97, + "learning_rate": 0.001, + "loss": 1.939, + "step": 28840 + }, + { + "epoch": 14.97, + "learning_rate": 0.001, + "loss": 1.9267, + "step": 28850 + }, + { + "epoch": 14.98, + "learning_rate": 0.001, + "loss": 1.9655, + "step": 28860 + }, + { + "epoch": 14.98, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 28870 + }, + { + "epoch": 14.99, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 28880 + }, + { + "epoch": 14.99, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 28890 + }, + { + "epoch": 15.0, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 28900 + }, + { + "epoch": 15.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9423017501831055, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.7437, + "eval_samples_per_second": 50.232, + "eval_steps_per_second": 25.123, + "step": 28905 + }, + { + "epoch": 15.0, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 28910 + }, + { + "epoch": 15.01, + "learning_rate": 0.001, + "loss": 1.939, + "step": 28920 + }, + { + "epoch": 15.01, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 28930 + }, + { + "epoch": 15.02, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 28940 + }, + { + "epoch": 15.02, + "learning_rate": 0.001, + "loss": 1.9639, + "step": 28950 + }, + { + "epoch": 15.03, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 28960 + }, + { + "epoch": 15.03, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 28970 + }, + { + "epoch": 15.04, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 28980 + }, + { + "epoch": 15.04, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 28990 + }, + { + "epoch": 15.05, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 29000 + }, + { + "epoch": 15.05, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 29010 + }, + { + "epoch": 15.06, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 29020 + }, + { + "epoch": 15.06, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 29030 + }, + { + "epoch": 15.07, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 29040 + }, + { + "epoch": 15.08, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 29050 + }, + { + "epoch": 15.08, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 29060 + }, + { + "epoch": 15.09, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 29070 + }, + { + "epoch": 15.09, + "learning_rate": 0.001, + "loss": 1.949, + "step": 29080 + }, + { + "epoch": 15.1, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 29090 + }, + { + "epoch": 15.1, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 29100 + }, + { + "epoch": 15.11, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 29110 + }, + { + "epoch": 15.11, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 29120 + }, + { + "epoch": 15.12, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 29130 + }, + { + "epoch": 15.12, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 29140 + }, + { + "epoch": 15.13, + "learning_rate": 0.001, + "loss": 1.944, + "step": 29150 + }, + { + "epoch": 15.13, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 29160 + }, + { + "epoch": 15.14, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 29170 + }, + { + "epoch": 15.14, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 29180 + }, + { + "epoch": 15.15, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 29190 + }, + { + "epoch": 15.15, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 29200 + }, + { + "epoch": 15.16, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 29210 + }, + { + "epoch": 15.16, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 29220 + }, + { + "epoch": 15.17, + "learning_rate": 0.001, + "loss": 1.9199, + "step": 29230 + }, + { + "epoch": 15.17, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 29240 + }, + { + "epoch": 15.18, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 29250 + }, + { + "epoch": 15.18, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 29260 + }, + { + "epoch": 15.19, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 29270 + }, + { + "epoch": 15.19, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 29280 + }, + { + "epoch": 15.2, + "learning_rate": 0.001, + "loss": 1.95, + "step": 29290 + }, + { + "epoch": 15.2, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 29300 + }, + { + "epoch": 15.21, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 29310 + }, + { + "epoch": 15.22, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 29320 + }, + { + "epoch": 15.22, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 29330 + }, + { + "epoch": 15.23, + "learning_rate": 0.001, + "loss": 1.929, + "step": 29340 + }, + { + "epoch": 15.23, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 29350 + }, + { + "epoch": 15.24, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 29360 + }, + { + "epoch": 15.24, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 29370 + }, + { + "epoch": 15.25, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 29380 + }, + { + "epoch": 15.25, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 29390 + }, + { + "epoch": 15.26, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 29400 + }, + { + "epoch": 15.26, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 29410 + }, + { + "epoch": 15.27, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 29420 + }, + { + "epoch": 15.27, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 29430 + }, + { + "epoch": 15.28, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 29440 + }, + { + "epoch": 15.28, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 29450 + }, + { + "epoch": 15.29, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 29460 + }, + { + "epoch": 15.29, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 29470 + }, + { + "epoch": 15.3, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 29480 + }, + { + "epoch": 15.3, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 29490 + }, + { + "epoch": 15.31, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 29500 + }, + { + "epoch": 15.31, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 29510 + }, + { + "epoch": 15.32, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 29520 + }, + { + "epoch": 15.32, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 29530 + }, + { + "epoch": 15.33, + "learning_rate": 0.001, + "loss": 1.94, + "step": 29540 + }, + { + "epoch": 15.33, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 29550 + }, + { + "epoch": 15.34, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 29560 + }, + { + "epoch": 15.35, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 29570 + }, + { + "epoch": 15.35, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 29580 + }, + { + "epoch": 15.36, + "learning_rate": 0.001, + "loss": 1.953, + "step": 29590 + }, + { + "epoch": 15.36, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 29600 + }, + { + "epoch": 15.37, + "learning_rate": 0.001, + "loss": 1.9243, + "step": 29610 + }, + { + "epoch": 15.37, + "learning_rate": 0.001, + "loss": 1.9701, + "step": 29620 + }, + { + "epoch": 15.38, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 29630 + }, + { + "epoch": 15.38, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 29640 + }, + { + "epoch": 15.39, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 29650 + }, + { + "epoch": 15.39, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 29660 + }, + { + "epoch": 15.4, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 29670 + }, + { + "epoch": 15.4, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 29680 + }, + { + "epoch": 15.41, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 29690 + }, + { + "epoch": 15.41, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 29700 + }, + { + "epoch": 15.42, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 29710 + }, + { + "epoch": 15.42, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 29720 + }, + { + "epoch": 15.43, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 29730 + }, + { + "epoch": 15.43, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 29740 + }, + { + "epoch": 15.44, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 29750 + }, + { + "epoch": 15.44, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 29760 + }, + { + "epoch": 15.45, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 29770 + }, + { + "epoch": 15.45, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 29780 + }, + { + "epoch": 15.46, + "learning_rate": 0.001, + "loss": 1.94, + "step": 29790 + }, + { + "epoch": 15.46, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 29800 + }, + { + "epoch": 15.47, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 29810 + }, + { + "epoch": 15.47, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 29820 + }, + { + "epoch": 15.48, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 29830 + }, + { + "epoch": 15.49, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 29840 + }, + { + "epoch": 15.49, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 29850 + }, + { + "epoch": 15.5, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 29860 + }, + { + "epoch": 15.5, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 29870 + }, + { + "epoch": 15.51, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 29880 + }, + { + "epoch": 15.51, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 29890 + }, + { + "epoch": 15.52, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 29900 + }, + { + "epoch": 15.52, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 29910 + }, + { + "epoch": 15.53, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 29920 + }, + { + "epoch": 15.53, + "learning_rate": 0.001, + "loss": 1.9217, + "step": 29930 + }, + { + "epoch": 15.54, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 29940 + }, + { + "epoch": 15.54, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 29950 + }, + { + "epoch": 15.55, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 29960 + }, + { + "epoch": 15.55, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 29970 + }, + { + "epoch": 15.56, + "learning_rate": 0.001, + "loss": 1.9266, + "step": 29980 + }, + { + "epoch": 15.56, + "learning_rate": 0.001, + "loss": 1.945, + "step": 29990 + }, + { + "epoch": 15.57, + "learning_rate": 0.001, + "loss": 1.9206, + "step": 30000 + }, + { + "epoch": 15.57, + "learning_rate": 0.001, + "loss": 1.9139, + "step": 30010 + }, + { + "epoch": 15.58, + "learning_rate": 0.001, + "loss": 1.9187, + "step": 30020 + }, + { + "epoch": 15.58, + "learning_rate": 0.001, + "loss": 1.9912, + "step": 30030 + }, + { + "epoch": 15.59, + "learning_rate": 0.001, + "loss": 1.9261, + "step": 30040 + }, + { + "epoch": 15.59, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 30050 + }, + { + "epoch": 15.6, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 30060 + }, + { + "epoch": 15.6, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 30070 + }, + { + "epoch": 15.61, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 30080 + }, + { + "epoch": 15.61, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 30090 + }, + { + "epoch": 15.62, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 30100 + }, + { + "epoch": 15.63, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 30110 + }, + { + "epoch": 15.63, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 30120 + }, + { + "epoch": 15.64, + "learning_rate": 0.001, + "loss": 1.9224, + "step": 30130 + }, + { + "epoch": 15.64, + "learning_rate": 0.001, + "loss": 1.9574, + "step": 30140 + }, + { + "epoch": 15.65, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 30150 + }, + { + "epoch": 15.65, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 30160 + }, + { + "epoch": 15.66, + "learning_rate": 0.001, + "loss": 1.918, + "step": 30170 + }, + { + "epoch": 15.66, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 30180 + }, + { + "epoch": 15.67, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 30190 + }, + { + "epoch": 15.67, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 30200 + }, + { + "epoch": 15.68, + "learning_rate": 0.001, + "loss": 1.9672, + "step": 30210 + }, + { + "epoch": 15.68, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 30220 + }, + { + "epoch": 15.69, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 30230 + }, + { + "epoch": 15.69, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 30240 + }, + { + "epoch": 15.7, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 30250 + }, + { + "epoch": 15.7, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 30260 + }, + { + "epoch": 15.71, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 30270 + }, + { + "epoch": 15.71, + "learning_rate": 0.001, + "loss": 1.9249, + "step": 30280 + }, + { + "epoch": 15.72, + "learning_rate": 0.001, + "loss": 1.9638, + "step": 30290 + }, + { + "epoch": 15.72, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 30300 + }, + { + "epoch": 15.73, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 30310 + }, + { + "epoch": 15.73, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 30320 + }, + { + "epoch": 15.74, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 30330 + }, + { + "epoch": 15.74, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 30340 + }, + { + "epoch": 15.75, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 30350 + }, + { + "epoch": 15.76, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 30360 + }, + { + "epoch": 15.76, + "learning_rate": 0.001, + "loss": 1.953, + "step": 30370 + }, + { + "epoch": 15.77, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 30380 + }, + { + "epoch": 15.77, + "learning_rate": 0.001, + "loss": 1.946, + "step": 30390 + }, + { + "epoch": 15.78, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 30400 + }, + { + "epoch": 15.78, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 30410 + }, + { + "epoch": 15.79, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 30420 + }, + { + "epoch": 15.79, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 30430 + }, + { + "epoch": 15.8, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 30440 + }, + { + "epoch": 15.8, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 30450 + }, + { + "epoch": 15.81, + "learning_rate": 0.001, + "loss": 1.9266, + "step": 30460 + }, + { + "epoch": 15.81, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 30470 + }, + { + "epoch": 15.82, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 30480 + }, + { + "epoch": 15.82, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 30490 + }, + { + "epoch": 15.83, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 30500 + }, + { + "epoch": 15.83, + "learning_rate": 0.001, + "loss": 1.94, + "step": 30510 + }, + { + "epoch": 15.84, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 30520 + }, + { + "epoch": 15.84, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 30530 + }, + { + "epoch": 15.85, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 30540 + }, + { + "epoch": 15.85, + "learning_rate": 0.001, + "loss": 1.9666, + "step": 30550 + }, + { + "epoch": 15.86, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 30560 + }, + { + "epoch": 15.86, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 30570 + }, + { + "epoch": 15.87, + "learning_rate": 0.001, + "loss": 1.956, + "step": 30580 + }, + { + "epoch": 15.87, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 30590 + }, + { + "epoch": 15.88, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 30600 + }, + { + "epoch": 15.88, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 30610 + }, + { + "epoch": 15.89, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 30620 + }, + { + "epoch": 15.9, + "learning_rate": 0.001, + "loss": 1.954, + "step": 30630 + }, + { + "epoch": 15.9, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 30640 + }, + { + "epoch": 15.91, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 30650 + }, + { + "epoch": 15.91, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 30660 + }, + { + "epoch": 15.92, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 30670 + }, + { + "epoch": 15.92, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 30680 + }, + { + "epoch": 15.93, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 30690 + }, + { + "epoch": 15.93, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 30700 + }, + { + "epoch": 15.94, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 30710 + }, + { + "epoch": 15.94, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 30720 + }, + { + "epoch": 15.95, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 30730 + }, + { + "epoch": 15.95, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 30740 + }, + { + "epoch": 15.96, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 30750 + }, + { + "epoch": 15.96, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 30760 + }, + { + "epoch": 15.97, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 30770 + }, + { + "epoch": 15.97, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 30780 + }, + { + "epoch": 15.98, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 30790 + }, + { + "epoch": 15.98, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 30800 + }, + { + "epoch": 15.99, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 30810 + }, + { + "epoch": 15.99, + "learning_rate": 0.001, + "loss": 1.931, + "step": 30820 + }, + { + "epoch": 16.0, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 30830 + }, + { + "epoch": 16.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9440184831619263, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.38, + "eval_samples_per_second": 51.141, + "eval_steps_per_second": 25.577, + "step": 30832 + }, + { + "epoch": 16.0, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 30840 + }, + { + "epoch": 16.01, + "learning_rate": 0.001, + "loss": 1.9022, + "step": 30850 + }, + { + "epoch": 16.01, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 30860 + }, + { + "epoch": 16.02, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 30870 + }, + { + "epoch": 16.02, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 30880 + }, + { + "epoch": 16.03, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 30890 + }, + { + "epoch": 16.04, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 30900 + }, + { + "epoch": 16.04, + "learning_rate": 0.001, + "loss": 1.9598, + "step": 30910 + }, + { + "epoch": 16.05, + "learning_rate": 0.001, + "loss": 1.924, + "step": 30920 + }, + { + "epoch": 16.05, + "learning_rate": 0.001, + "loss": 1.942, + "step": 30930 + }, + { + "epoch": 16.06, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 30940 + }, + { + "epoch": 16.06, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 30950 + }, + { + "epoch": 16.07, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 30960 + }, + { + "epoch": 16.07, + "learning_rate": 0.001, + "loss": 1.94, + "step": 30970 + }, + { + "epoch": 16.08, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 30980 + }, + { + "epoch": 16.08, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 30990 + }, + { + "epoch": 16.09, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 31000 + }, + { + "epoch": 16.09, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 31010 + }, + { + "epoch": 16.1, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 31020 + }, + { + "epoch": 16.1, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 31030 + }, + { + "epoch": 16.11, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 31040 + }, + { + "epoch": 16.11, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 31050 + }, + { + "epoch": 16.12, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 31060 + }, + { + "epoch": 16.12, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 31070 + }, + { + "epoch": 16.13, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 31080 + }, + { + "epoch": 16.13, + "learning_rate": 0.001, + "loss": 1.9649, + "step": 31090 + }, + { + "epoch": 16.14, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 31100 + }, + { + "epoch": 16.14, + "learning_rate": 0.001, + "loss": 1.9644, + "step": 31110 + }, + { + "epoch": 16.15, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 31120 + }, + { + "epoch": 16.15, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 31130 + }, + { + "epoch": 16.16, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 31140 + }, + { + "epoch": 16.17, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 31150 + }, + { + "epoch": 16.17, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 31160 + }, + { + "epoch": 16.18, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 31170 + }, + { + "epoch": 16.18, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 31180 + }, + { + "epoch": 16.19, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 31190 + }, + { + "epoch": 16.19, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 31200 + }, + { + "epoch": 16.2, + "learning_rate": 0.001, + "loss": 1.921, + "step": 31210 + }, + { + "epoch": 16.2, + "learning_rate": 0.001, + "loss": 1.9123, + "step": 31220 + }, + { + "epoch": 16.21, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 31230 + }, + { + "epoch": 16.21, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 31240 + }, + { + "epoch": 16.22, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 31250 + }, + { + "epoch": 16.22, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 31260 + }, + { + "epoch": 16.23, + "learning_rate": 0.001, + "loss": 1.9237, + "step": 31270 + }, + { + "epoch": 16.23, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 31280 + }, + { + "epoch": 16.24, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 31290 + }, + { + "epoch": 16.24, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 31300 + }, + { + "epoch": 16.25, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 31310 + }, + { + "epoch": 16.25, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 31320 + }, + { + "epoch": 16.26, + "learning_rate": 0.001, + "loss": 1.949, + "step": 31330 + }, + { + "epoch": 16.26, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 31340 + }, + { + "epoch": 16.27, + "learning_rate": 0.001, + "loss": 1.9661, + "step": 31350 + }, + { + "epoch": 16.27, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 31360 + }, + { + "epoch": 16.28, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 31370 + }, + { + "epoch": 16.28, + "learning_rate": 0.001, + "loss": 1.9585, + "step": 31380 + }, + { + "epoch": 16.29, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 31390 + }, + { + "epoch": 16.29, + "learning_rate": 0.001, + "loss": 1.939, + "step": 31400 + }, + { + "epoch": 16.3, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 31410 + }, + { + "epoch": 16.31, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 31420 + }, + { + "epoch": 16.31, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 31430 + }, + { + "epoch": 16.32, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 31440 + }, + { + "epoch": 16.32, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 31450 + }, + { + "epoch": 16.33, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 31460 + }, + { + "epoch": 16.33, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 31470 + }, + { + "epoch": 16.34, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 31480 + }, + { + "epoch": 16.34, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 31490 + }, + { + "epoch": 16.35, + "learning_rate": 0.001, + "loss": 1.933, + "step": 31500 + }, + { + "epoch": 16.35, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 31510 + }, + { + "epoch": 16.36, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 31520 + }, + { + "epoch": 16.36, + "learning_rate": 0.001, + "loss": 1.9246, + "step": 31530 + }, + { + "epoch": 16.37, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 31540 + }, + { + "epoch": 16.37, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 31550 + }, + { + "epoch": 16.38, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 31560 + }, + { + "epoch": 16.38, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 31570 + }, + { + "epoch": 16.39, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 31580 + }, + { + "epoch": 16.39, + "learning_rate": 0.001, + "loss": 1.956, + "step": 31590 + }, + { + "epoch": 16.4, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 31600 + }, + { + "epoch": 16.4, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 31610 + }, + { + "epoch": 16.41, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 31620 + }, + { + "epoch": 16.41, + "learning_rate": 0.001, + "loss": 1.9249, + "step": 31630 + }, + { + "epoch": 16.42, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 31640 + }, + { + "epoch": 16.42, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 31650 + }, + { + "epoch": 16.43, + "learning_rate": 0.001, + "loss": 1.942, + "step": 31660 + }, + { + "epoch": 16.43, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 31670 + }, + { + "epoch": 16.44, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 31680 + }, + { + "epoch": 16.45, + "learning_rate": 0.001, + "loss": 1.948, + "step": 31690 + }, + { + "epoch": 16.45, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 31700 + }, + { + "epoch": 16.46, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 31710 + }, + { + "epoch": 16.46, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 31720 + }, + { + "epoch": 16.47, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 31730 + }, + { + "epoch": 16.47, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 31740 + }, + { + "epoch": 16.48, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 31750 + }, + { + "epoch": 16.48, + "learning_rate": 0.001, + "loss": 1.94, + "step": 31760 + }, + { + "epoch": 16.49, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 31770 + }, + { + "epoch": 16.49, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 31780 + }, + { + "epoch": 16.5, + "learning_rate": 0.001, + "loss": 1.9597, + "step": 31790 + }, + { + "epoch": 16.5, + "learning_rate": 0.001, + "loss": 1.947, + "step": 31800 + }, + { + "epoch": 16.51, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 31810 + }, + { + "epoch": 16.51, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 31820 + }, + { + "epoch": 16.52, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 31830 + }, + { + "epoch": 16.52, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 31840 + }, + { + "epoch": 16.53, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 31850 + }, + { + "epoch": 16.53, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 31860 + }, + { + "epoch": 16.54, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 31870 + }, + { + "epoch": 16.54, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 31880 + }, + { + "epoch": 16.55, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 31890 + }, + { + "epoch": 16.55, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 31900 + }, + { + "epoch": 16.56, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 31910 + }, + { + "epoch": 16.56, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 31920 + }, + { + "epoch": 16.57, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 31930 + }, + { + "epoch": 16.57, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 31940 + }, + { + "epoch": 16.58, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 31950 + }, + { + "epoch": 16.59, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 31960 + }, + { + "epoch": 16.59, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 31970 + }, + { + "epoch": 16.6, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 31980 + }, + { + "epoch": 16.6, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 31990 + }, + { + "epoch": 16.61, + "learning_rate": 0.001, + "loss": 1.9267, + "step": 32000 + }, + { + "epoch": 16.61, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 32010 + }, + { + "epoch": 16.62, + "learning_rate": 0.001, + "loss": 1.9216, + "step": 32020 + }, + { + "epoch": 16.62, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 32030 + }, + { + "epoch": 16.63, + "learning_rate": 0.001, + "loss": 1.963, + "step": 32040 + }, + { + "epoch": 16.63, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 32050 + }, + { + "epoch": 16.64, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 32060 + }, + { + "epoch": 16.64, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 32070 + }, + { + "epoch": 16.65, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 32080 + }, + { + "epoch": 16.65, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 32090 + }, + { + "epoch": 16.66, + "learning_rate": 0.001, + "loss": 1.954, + "step": 32100 + }, + { + "epoch": 16.66, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 32110 + }, + { + "epoch": 16.67, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 32120 + }, + { + "epoch": 16.67, + "learning_rate": 0.001, + "loss": 1.9657, + "step": 32130 + }, + { + "epoch": 16.68, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 32140 + }, + { + "epoch": 16.68, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 32150 + }, + { + "epoch": 16.69, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 32160 + }, + { + "epoch": 16.69, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 32170 + }, + { + "epoch": 16.7, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 32180 + }, + { + "epoch": 16.7, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 32190 + }, + { + "epoch": 16.71, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 32200 + }, + { + "epoch": 16.72, + "learning_rate": 0.001, + "loss": 1.9642, + "step": 32210 + }, + { + "epoch": 16.72, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 32220 + }, + { + "epoch": 16.73, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 32230 + }, + { + "epoch": 16.73, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 32240 + }, + { + "epoch": 16.74, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 32250 + }, + { + "epoch": 16.74, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 32260 + }, + { + "epoch": 16.75, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 32270 + }, + { + "epoch": 16.75, + "learning_rate": 0.001, + "loss": 1.9635, + "step": 32280 + }, + { + "epoch": 16.76, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 32290 + }, + { + "epoch": 16.76, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 32300 + }, + { + "epoch": 16.77, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 32310 + }, + { + "epoch": 16.77, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 32320 + }, + { + "epoch": 16.78, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 32330 + }, + { + "epoch": 16.78, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 32340 + }, + { + "epoch": 16.79, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 32350 + }, + { + "epoch": 16.79, + "learning_rate": 0.001, + "loss": 1.9601, + "step": 32360 + }, + { + "epoch": 16.8, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 32370 + }, + { + "epoch": 16.8, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 32380 + }, + { + "epoch": 16.81, + "learning_rate": 0.001, + "loss": 1.936, + "step": 32390 + }, + { + "epoch": 16.81, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 32400 + }, + { + "epoch": 16.82, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 32410 + }, + { + "epoch": 16.82, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 32420 + }, + { + "epoch": 16.83, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 32430 + }, + { + "epoch": 16.83, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 32440 + }, + { + "epoch": 16.84, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 32450 + }, + { + "epoch": 16.84, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 32460 + }, + { + "epoch": 16.85, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 32470 + }, + { + "epoch": 16.86, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 32480 + }, + { + "epoch": 16.86, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 32490 + }, + { + "epoch": 16.87, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 32500 + }, + { + "epoch": 16.87, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 32510 + }, + { + "epoch": 16.88, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 32520 + }, + { + "epoch": 16.88, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 32530 + }, + { + "epoch": 16.89, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 32540 + }, + { + "epoch": 16.89, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 32550 + }, + { + "epoch": 16.9, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 32560 + }, + { + "epoch": 16.9, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 32570 + }, + { + "epoch": 16.91, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 32580 + }, + { + "epoch": 16.91, + "learning_rate": 0.001, + "loss": 1.9633, + "step": 32590 + }, + { + "epoch": 16.92, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 32600 + }, + { + "epoch": 16.92, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 32610 + }, + { + "epoch": 16.93, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 32620 + }, + { + "epoch": 16.93, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 32630 + }, + { + "epoch": 16.94, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 32640 + }, + { + "epoch": 16.94, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 32650 + }, + { + "epoch": 16.95, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 32660 + }, + { + "epoch": 16.95, + "learning_rate": 0.001, + "loss": 1.947, + "step": 32670 + }, + { + "epoch": 16.96, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 32680 + }, + { + "epoch": 16.96, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 32690 + }, + { + "epoch": 16.97, + "learning_rate": 0.001, + "loss": 1.924, + "step": 32700 + }, + { + "epoch": 16.97, + "learning_rate": 0.001, + "loss": 1.957, + "step": 32710 + }, + { + "epoch": 16.98, + "learning_rate": 0.001, + "loss": 1.9699, + "step": 32720 + }, + { + "epoch": 16.98, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 32730 + }, + { + "epoch": 16.99, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 32740 + }, + { + "epoch": 17.0, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 32750 + }, + { + "epoch": 17.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9412354230880737, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.9869, + "eval_samples_per_second": 50.732, + "eval_steps_per_second": 25.373, + "step": 32759 + }, + { + "epoch": 17.0, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 32760 + }, + { + "epoch": 17.01, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 32770 + }, + { + "epoch": 17.01, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 32780 + }, + { + "epoch": 17.02, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 32790 + }, + { + "epoch": 17.02, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 32800 + }, + { + "epoch": 17.03, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 32810 + }, + { + "epoch": 17.03, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 32820 + }, + { + "epoch": 17.04, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 32830 + }, + { + "epoch": 17.04, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 32840 + }, + { + "epoch": 17.05, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 32850 + }, + { + "epoch": 17.05, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 32860 + }, + { + "epoch": 17.06, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 32870 + }, + { + "epoch": 17.06, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 32880 + }, + { + "epoch": 17.07, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 32890 + }, + { + "epoch": 17.07, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 32900 + }, + { + "epoch": 17.08, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 32910 + }, + { + "epoch": 17.08, + "learning_rate": 0.001, + "loss": 1.9261, + "step": 32920 + }, + { + "epoch": 17.09, + "learning_rate": 0.001, + "loss": 1.9185, + "step": 32930 + }, + { + "epoch": 17.09, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 32940 + }, + { + "epoch": 17.1, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 32950 + }, + { + "epoch": 17.1, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 32960 + }, + { + "epoch": 17.11, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 32970 + }, + { + "epoch": 17.11, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 32980 + }, + { + "epoch": 17.12, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 32990 + }, + { + "epoch": 17.13, + "learning_rate": 0.001, + "loss": 1.945, + "step": 33000 + }, + { + "epoch": 17.13, + "learning_rate": 0.001, + "loss": 1.933, + "step": 33010 + }, + { + "epoch": 17.14, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 33020 + }, + { + "epoch": 17.14, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 33030 + }, + { + "epoch": 17.15, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 33040 + }, + { + "epoch": 17.15, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 33050 + }, + { + "epoch": 17.16, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 33060 + }, + { + "epoch": 17.16, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 33070 + }, + { + "epoch": 17.17, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 33080 + }, + { + "epoch": 17.17, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 33090 + }, + { + "epoch": 17.18, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 33100 + }, + { + "epoch": 17.18, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 33110 + }, + { + "epoch": 17.19, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 33120 + }, + { + "epoch": 17.19, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 33130 + }, + { + "epoch": 17.2, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 33140 + }, + { + "epoch": 17.2, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 33150 + }, + { + "epoch": 17.21, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 33160 + }, + { + "epoch": 17.21, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 33170 + }, + { + "epoch": 17.22, + "learning_rate": 0.001, + "loss": 1.9295, + "step": 33180 + }, + { + "epoch": 17.22, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 33190 + }, + { + "epoch": 17.23, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 33200 + }, + { + "epoch": 17.23, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 33210 + }, + { + "epoch": 17.24, + "learning_rate": 0.001, + "loss": 1.9262, + "step": 33220 + }, + { + "epoch": 17.24, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 33230 + }, + { + "epoch": 17.25, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 33240 + }, + { + "epoch": 17.25, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 33250 + }, + { + "epoch": 17.26, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 33260 + }, + { + "epoch": 17.27, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 33270 + }, + { + "epoch": 17.27, + "learning_rate": 0.001, + "loss": 1.954, + "step": 33280 + }, + { + "epoch": 17.28, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 33290 + }, + { + "epoch": 17.28, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 33300 + }, + { + "epoch": 17.29, + "learning_rate": 0.001, + "loss": 1.9224, + "step": 33310 + }, + { + "epoch": 17.29, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 33320 + }, + { + "epoch": 17.3, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 33330 + }, + { + "epoch": 17.3, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 33340 + }, + { + "epoch": 17.31, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 33350 + }, + { + "epoch": 17.31, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 33360 + }, + { + "epoch": 17.32, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 33370 + }, + { + "epoch": 17.32, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 33380 + }, + { + "epoch": 17.33, + "learning_rate": 0.001, + "loss": 1.944, + "step": 33390 + }, + { + "epoch": 17.33, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 33400 + }, + { + "epoch": 17.34, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 33410 + }, + { + "epoch": 17.34, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 33420 + }, + { + "epoch": 17.35, + "learning_rate": 0.001, + "loss": 1.945, + "step": 33430 + }, + { + "epoch": 17.35, + "learning_rate": 0.001, + "loss": 1.946, + "step": 33440 + }, + { + "epoch": 17.36, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 33450 + }, + { + "epoch": 17.36, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 33460 + }, + { + "epoch": 17.37, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 33470 + }, + { + "epoch": 17.37, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 33480 + }, + { + "epoch": 17.38, + "learning_rate": 0.001, + "loss": 1.948, + "step": 33490 + }, + { + "epoch": 17.38, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 33500 + }, + { + "epoch": 17.39, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 33510 + }, + { + "epoch": 17.39, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 33520 + }, + { + "epoch": 17.4, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 33530 + }, + { + "epoch": 17.41, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 33540 + }, + { + "epoch": 17.41, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 33550 + }, + { + "epoch": 17.42, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 33560 + }, + { + "epoch": 17.42, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 33570 + }, + { + "epoch": 17.43, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 33580 + }, + { + "epoch": 17.43, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 33590 + }, + { + "epoch": 17.44, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 33600 + }, + { + "epoch": 17.44, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 33610 + }, + { + "epoch": 17.45, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 33620 + }, + { + "epoch": 17.45, + "learning_rate": 0.001, + "loss": 1.936, + "step": 33630 + }, + { + "epoch": 17.46, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 33640 + }, + { + "epoch": 17.46, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 33650 + }, + { + "epoch": 17.47, + "learning_rate": 0.001, + "loss": 1.9665, + "step": 33660 + }, + { + "epoch": 17.47, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 33670 + }, + { + "epoch": 17.48, + "learning_rate": 0.001, + "loss": 1.9268, + "step": 33680 + }, + { + "epoch": 17.48, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 33690 + }, + { + "epoch": 17.49, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 33700 + }, + { + "epoch": 17.49, + "learning_rate": 0.001, + "loss": 1.921, + "step": 33710 + }, + { + "epoch": 17.5, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 33720 + }, + { + "epoch": 17.5, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 33730 + }, + { + "epoch": 17.51, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 33740 + }, + { + "epoch": 17.51, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 33750 + }, + { + "epoch": 17.52, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 33760 + }, + { + "epoch": 17.52, + "learning_rate": 0.001, + "loss": 1.9268, + "step": 33770 + }, + { + "epoch": 17.53, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 33780 + }, + { + "epoch": 17.54, + "learning_rate": 0.001, + "loss": 1.947, + "step": 33790 + }, + { + "epoch": 17.54, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 33800 + }, + { + "epoch": 17.55, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 33810 + }, + { + "epoch": 17.55, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 33820 + }, + { + "epoch": 17.56, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 33830 + }, + { + "epoch": 17.56, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 33840 + }, + { + "epoch": 17.57, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 33850 + }, + { + "epoch": 17.57, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 33860 + }, + { + "epoch": 17.58, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 33870 + }, + { + "epoch": 17.58, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 33880 + }, + { + "epoch": 17.59, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 33890 + }, + { + "epoch": 17.59, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 33900 + }, + { + "epoch": 17.6, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 33910 + }, + { + "epoch": 17.6, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 33920 + }, + { + "epoch": 17.61, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 33930 + }, + { + "epoch": 17.61, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 33940 + }, + { + "epoch": 17.62, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 33950 + }, + { + "epoch": 17.62, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 33960 + }, + { + "epoch": 17.63, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 33970 + }, + { + "epoch": 17.63, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 33980 + }, + { + "epoch": 17.64, + "learning_rate": 0.001, + "loss": 1.943, + "step": 33990 + }, + { + "epoch": 17.64, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 34000 + }, + { + "epoch": 17.65, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 34010 + }, + { + "epoch": 17.65, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 34020 + }, + { + "epoch": 17.66, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 34030 + }, + { + "epoch": 17.66, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 34040 + }, + { + "epoch": 17.67, + "learning_rate": 0.001, + "loss": 1.9237, + "step": 34050 + }, + { + "epoch": 17.68, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 34060 + }, + { + "epoch": 17.68, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 34070 + }, + { + "epoch": 17.69, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 34080 + }, + { + "epoch": 17.69, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 34090 + }, + { + "epoch": 17.7, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 34100 + }, + { + "epoch": 17.7, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 34110 + }, + { + "epoch": 17.71, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 34120 + }, + { + "epoch": 17.71, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 34130 + }, + { + "epoch": 17.72, + "learning_rate": 0.001, + "loss": 1.9081, + "step": 34140 + }, + { + "epoch": 17.72, + "learning_rate": 0.001, + "loss": 1.9666, + "step": 34150 + }, + { + "epoch": 17.73, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 34160 + }, + { + "epoch": 17.73, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 34170 + }, + { + "epoch": 17.74, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 34180 + }, + { + "epoch": 17.74, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 34190 + }, + { + "epoch": 17.75, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 34200 + }, + { + "epoch": 17.75, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 34210 + }, + { + "epoch": 17.76, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 34220 + }, + { + "epoch": 17.76, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 34230 + }, + { + "epoch": 17.77, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 34240 + }, + { + "epoch": 17.77, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 34250 + }, + { + "epoch": 17.78, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 34260 + }, + { + "epoch": 17.78, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 34270 + }, + { + "epoch": 17.79, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 34280 + }, + { + "epoch": 17.79, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 34290 + }, + { + "epoch": 17.8, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 34300 + }, + { + "epoch": 17.8, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 34310 + }, + { + "epoch": 17.81, + "learning_rate": 0.001, + "loss": 1.932, + "step": 34320 + }, + { + "epoch": 17.82, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 34330 + }, + { + "epoch": 17.82, + "learning_rate": 0.001, + "loss": 1.952, + "step": 34340 + }, + { + "epoch": 17.83, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 34350 + }, + { + "epoch": 17.83, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 34360 + }, + { + "epoch": 17.84, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 34370 + }, + { + "epoch": 17.84, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 34380 + }, + { + "epoch": 17.85, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 34390 + }, + { + "epoch": 17.85, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 34400 + }, + { + "epoch": 17.86, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 34410 + }, + { + "epoch": 17.86, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 34420 + }, + { + "epoch": 17.87, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 34430 + }, + { + "epoch": 17.87, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 34440 + }, + { + "epoch": 17.88, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 34450 + }, + { + "epoch": 17.88, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 34460 + }, + { + "epoch": 17.89, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 34470 + }, + { + "epoch": 17.89, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 34480 + }, + { + "epoch": 17.9, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 34490 + }, + { + "epoch": 17.9, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 34500 + }, + { + "epoch": 17.91, + "learning_rate": 0.001, + "loss": 1.933, + "step": 34510 + }, + { + "epoch": 17.91, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 34520 + }, + { + "epoch": 17.92, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 34530 + }, + { + "epoch": 17.92, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 34540 + }, + { + "epoch": 17.93, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 34550 + }, + { + "epoch": 17.93, + "learning_rate": 0.001, + "loss": 1.9601, + "step": 34560 + }, + { + "epoch": 17.94, + "learning_rate": 0.001, + "loss": 1.9639, + "step": 34570 + }, + { + "epoch": 17.94, + "learning_rate": 0.001, + "loss": 1.9131, + "step": 34580 + }, + { + "epoch": 17.95, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 34590 + }, + { + "epoch": 17.96, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 34600 + }, + { + "epoch": 17.96, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 34610 + }, + { + "epoch": 17.97, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 34620 + }, + { + "epoch": 17.97, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 34630 + }, + { + "epoch": 17.98, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 34640 + }, + { + "epoch": 17.98, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 34650 + }, + { + "epoch": 17.99, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 34660 + }, + { + "epoch": 17.99, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 34670 + }, + { + "epoch": 18.0, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 34680 + }, + { + "epoch": 18.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9404698610305786, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.6412, + "eval_samples_per_second": 49.652, + "eval_steps_per_second": 24.832, + "step": 34686 + }, + { + "epoch": 18.0, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 34690 + }, + { + "epoch": 18.01, + "learning_rate": 0.001, + "loss": 1.9689, + "step": 34700 + }, + { + "epoch": 18.01, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 34710 + }, + { + "epoch": 18.02, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 34720 + }, + { + "epoch": 18.02, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 34730 + }, + { + "epoch": 18.03, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 34740 + }, + { + "epoch": 18.03, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 34750 + }, + { + "epoch": 18.04, + "learning_rate": 0.001, + "loss": 1.9565, + "step": 34760 + }, + { + "epoch": 18.04, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 34770 + }, + { + "epoch": 18.05, + "learning_rate": 0.001, + "loss": 1.939, + "step": 34780 + }, + { + "epoch": 18.05, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 34790 + }, + { + "epoch": 18.06, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 34800 + }, + { + "epoch": 18.06, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 34810 + }, + { + "epoch": 18.07, + "learning_rate": 0.001, + "loss": 1.9231, + "step": 34820 + }, + { + "epoch": 18.07, + "learning_rate": 0.001, + "loss": 1.9041, + "step": 34830 + }, + { + "epoch": 18.08, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 34840 + }, + { + "epoch": 18.09, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 34850 + }, + { + "epoch": 18.09, + "learning_rate": 0.001, + "loss": 1.926, + "step": 34860 + }, + { + "epoch": 18.1, + "learning_rate": 0.001, + "loss": 1.9562, + "step": 34870 + }, + { + "epoch": 18.1, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 34880 + }, + { + "epoch": 18.11, + "learning_rate": 0.001, + "loss": 1.9704, + "step": 34890 + }, + { + "epoch": 18.11, + "learning_rate": 0.001, + "loss": 1.965, + "step": 34900 + }, + { + "epoch": 18.12, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 34910 + }, + { + "epoch": 18.12, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 34920 + }, + { + "epoch": 18.13, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 34930 + }, + { + "epoch": 18.13, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 34940 + }, + { + "epoch": 18.14, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 34950 + }, + { + "epoch": 18.14, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 34960 + }, + { + "epoch": 18.15, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 34970 + }, + { + "epoch": 18.15, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 34980 + }, + { + "epoch": 18.16, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 34990 + }, + { + "epoch": 18.16, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 35000 + }, + { + "epoch": 18.17, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 35010 + }, + { + "epoch": 18.17, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 35020 + }, + { + "epoch": 18.18, + "learning_rate": 0.001, + "loss": 1.946, + "step": 35030 + }, + { + "epoch": 18.18, + "learning_rate": 0.001, + "loss": 1.9226, + "step": 35040 + }, + { + "epoch": 18.19, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 35050 + }, + { + "epoch": 18.19, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 35060 + }, + { + "epoch": 18.2, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 35070 + }, + { + "epoch": 18.2, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 35080 + }, + { + "epoch": 18.21, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 35090 + }, + { + "epoch": 18.21, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 35100 + }, + { + "epoch": 18.22, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 35110 + }, + { + "epoch": 18.23, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 35120 + }, + { + "epoch": 18.23, + "learning_rate": 0.001, + "loss": 1.938, + "step": 35130 + }, + { + "epoch": 18.24, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 35140 + }, + { + "epoch": 18.24, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 35150 + }, + { + "epoch": 18.25, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 35160 + }, + { + "epoch": 18.25, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 35170 + }, + { + "epoch": 18.26, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 35180 + }, + { + "epoch": 18.26, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 35190 + }, + { + "epoch": 18.27, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 35200 + }, + { + "epoch": 18.27, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 35210 + }, + { + "epoch": 18.28, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 35220 + }, + { + "epoch": 18.28, + "learning_rate": 0.001, + "loss": 1.9305, + "step": 35230 + }, + { + "epoch": 18.29, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 35240 + }, + { + "epoch": 18.29, + "learning_rate": 0.001, + "loss": 1.9252, + "step": 35250 + }, + { + "epoch": 18.3, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 35260 + }, + { + "epoch": 18.3, + "learning_rate": 0.001, + "loss": 1.954, + "step": 35270 + }, + { + "epoch": 18.31, + "learning_rate": 0.001, + "loss": 1.9683, + "step": 35280 + }, + { + "epoch": 18.31, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 35290 + }, + { + "epoch": 18.32, + "learning_rate": 0.001, + "loss": 1.9255, + "step": 35300 + }, + { + "epoch": 18.32, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 35310 + }, + { + "epoch": 18.33, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 35320 + }, + { + "epoch": 18.33, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 35330 + }, + { + "epoch": 18.34, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 35340 + }, + { + "epoch": 18.34, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 35350 + }, + { + "epoch": 18.35, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 35360 + }, + { + "epoch": 18.35, + "learning_rate": 0.001, + "loss": 1.956, + "step": 35370 + }, + { + "epoch": 18.36, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 35380 + }, + { + "epoch": 18.37, + "learning_rate": 0.001, + "loss": 1.957, + "step": 35390 + }, + { + "epoch": 18.37, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 35400 + }, + { + "epoch": 18.38, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 35410 + }, + { + "epoch": 18.38, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 35420 + }, + { + "epoch": 18.39, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 35430 + }, + { + "epoch": 18.39, + "learning_rate": 0.001, + "loss": 1.957, + "step": 35440 + }, + { + "epoch": 18.4, + "learning_rate": 0.001, + "loss": 1.9621, + "step": 35450 + }, + { + "epoch": 18.4, + "learning_rate": 0.001, + "loss": 1.936, + "step": 35460 + }, + { + "epoch": 18.41, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 35470 + }, + { + "epoch": 18.41, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 35480 + }, + { + "epoch": 18.42, + "learning_rate": 0.001, + "loss": 1.9246, + "step": 35490 + }, + { + "epoch": 18.42, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 35500 + }, + { + "epoch": 18.43, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 35510 + }, + { + "epoch": 18.43, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 35520 + }, + { + "epoch": 18.44, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 35530 + }, + { + "epoch": 18.44, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 35540 + }, + { + "epoch": 18.45, + "learning_rate": 0.001, + "loss": 1.9566, + "step": 35550 + }, + { + "epoch": 18.45, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 35560 + }, + { + "epoch": 18.46, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 35570 + }, + { + "epoch": 18.46, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 35580 + }, + { + "epoch": 18.47, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 35590 + }, + { + "epoch": 18.47, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 35600 + }, + { + "epoch": 18.48, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 35610 + }, + { + "epoch": 18.48, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 35620 + }, + { + "epoch": 18.49, + "learning_rate": 0.001, + "loss": 1.95, + "step": 35630 + }, + { + "epoch": 18.5, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 35640 + }, + { + "epoch": 18.5, + "learning_rate": 0.001, + "loss": 1.9583, + "step": 35650 + }, + { + "epoch": 18.51, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 35660 + }, + { + "epoch": 18.51, + "learning_rate": 0.001, + "loss": 1.936, + "step": 35670 + }, + { + "epoch": 18.52, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 35680 + }, + { + "epoch": 18.52, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 35690 + }, + { + "epoch": 18.53, + "learning_rate": 0.001, + "loss": 1.9711, + "step": 35700 + }, + { + "epoch": 18.53, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 35710 + }, + { + "epoch": 18.54, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 35720 + }, + { + "epoch": 18.54, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 35730 + }, + { + "epoch": 18.55, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 35740 + }, + { + "epoch": 18.55, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 35750 + }, + { + "epoch": 18.56, + "learning_rate": 0.001, + "loss": 1.928, + "step": 35760 + }, + { + "epoch": 18.56, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 35770 + }, + { + "epoch": 18.57, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 35780 + }, + { + "epoch": 18.57, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 35790 + }, + { + "epoch": 18.58, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 35800 + }, + { + "epoch": 18.58, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 35810 + }, + { + "epoch": 18.59, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 35820 + }, + { + "epoch": 18.59, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 35830 + }, + { + "epoch": 18.6, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 35840 + }, + { + "epoch": 18.6, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 35850 + }, + { + "epoch": 18.61, + "learning_rate": 0.001, + "loss": 1.9213, + "step": 35860 + }, + { + "epoch": 18.61, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 35870 + }, + { + "epoch": 18.62, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 35880 + }, + { + "epoch": 18.62, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 35890 + }, + { + "epoch": 18.63, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 35900 + }, + { + "epoch": 18.64, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 35910 + }, + { + "epoch": 18.64, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 35920 + }, + { + "epoch": 18.65, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 35930 + }, + { + "epoch": 18.65, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 35940 + }, + { + "epoch": 18.66, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 35950 + }, + { + "epoch": 18.66, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 35960 + }, + { + "epoch": 18.67, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 35970 + }, + { + "epoch": 18.67, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 35980 + }, + { + "epoch": 18.68, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 35990 + }, + { + "epoch": 18.68, + "learning_rate": 0.001, + "loss": 1.9645, + "step": 36000 + }, + { + "epoch": 18.69, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 36010 + }, + { + "epoch": 18.69, + "learning_rate": 0.001, + "loss": 1.948, + "step": 36020 + }, + { + "epoch": 18.7, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 36030 + }, + { + "epoch": 18.7, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 36040 + }, + { + "epoch": 18.71, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 36050 + }, + { + "epoch": 18.71, + "learning_rate": 0.001, + "loss": 1.9631, + "step": 36060 + }, + { + "epoch": 18.72, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 36070 + }, + { + "epoch": 18.72, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 36080 + }, + { + "epoch": 18.73, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 36090 + }, + { + "epoch": 18.73, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 36100 + }, + { + "epoch": 18.74, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 36110 + }, + { + "epoch": 18.74, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 36120 + }, + { + "epoch": 18.75, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 36130 + }, + { + "epoch": 18.75, + "learning_rate": 0.001, + "loss": 1.933, + "step": 36140 + }, + { + "epoch": 18.76, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 36150 + }, + { + "epoch": 18.76, + "learning_rate": 0.001, + "loss": 1.954, + "step": 36160 + }, + { + "epoch": 18.77, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 36170 + }, + { + "epoch": 18.78, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 36180 + }, + { + "epoch": 18.78, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 36190 + }, + { + "epoch": 18.79, + "learning_rate": 0.001, + "loss": 1.945, + "step": 36200 + }, + { + "epoch": 18.79, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 36210 + }, + { + "epoch": 18.8, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 36220 + }, + { + "epoch": 18.8, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 36230 + }, + { + "epoch": 18.81, + "learning_rate": 0.001, + "loss": 1.951, + "step": 36240 + }, + { + "epoch": 18.81, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 36250 + }, + { + "epoch": 18.82, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 36260 + }, + { + "epoch": 18.82, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 36270 + }, + { + "epoch": 18.83, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 36280 + }, + { + "epoch": 18.83, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 36290 + }, + { + "epoch": 18.84, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 36300 + }, + { + "epoch": 18.84, + "learning_rate": 0.001, + "loss": 1.936, + "step": 36310 + }, + { + "epoch": 18.85, + "learning_rate": 0.001, + "loss": 1.935, + "step": 36320 + }, + { + "epoch": 18.85, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 36330 + }, + { + "epoch": 18.86, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 36340 + }, + { + "epoch": 18.86, + "learning_rate": 0.001, + "loss": 1.9604, + "step": 36350 + }, + { + "epoch": 18.87, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 36360 + }, + { + "epoch": 18.87, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 36370 + }, + { + "epoch": 18.88, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 36380 + }, + { + "epoch": 18.88, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 36390 + }, + { + "epoch": 18.89, + "learning_rate": 0.001, + "loss": 1.9253, + "step": 36400 + }, + { + "epoch": 18.89, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 36410 + }, + { + "epoch": 18.9, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 36420 + }, + { + "epoch": 18.91, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 36430 + }, + { + "epoch": 18.91, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 36440 + }, + { + "epoch": 18.92, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 36450 + }, + { + "epoch": 18.92, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 36460 + }, + { + "epoch": 18.93, + "learning_rate": 0.001, + "loss": 1.9607, + "step": 36470 + }, + { + "epoch": 18.93, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 36480 + }, + { + "epoch": 18.94, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 36490 + }, + { + "epoch": 18.94, + "learning_rate": 0.001, + "loss": 1.944, + "step": 36500 + }, + { + "epoch": 18.95, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 36510 + }, + { + "epoch": 18.95, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 36520 + }, + { + "epoch": 18.96, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 36530 + }, + { + "epoch": 18.96, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 36540 + }, + { + "epoch": 18.97, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 36550 + }, + { + "epoch": 18.97, + "learning_rate": 0.001, + "loss": 1.9322, + "step": 36560 + }, + { + "epoch": 18.98, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 36570 + }, + { + "epoch": 18.98, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 36580 + }, + { + "epoch": 18.99, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 36590 + }, + { + "epoch": 18.99, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 36600 + }, + { + "epoch": 19.0, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 36610 + }, + { + "epoch": 19.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.94051992893219, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 78.5408, + "eval_samples_per_second": 49.083, + "eval_steps_per_second": 24.548, + "step": 36613 + }, + { + "epoch": 19.0, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 36620 + }, + { + "epoch": 19.01, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 36630 + }, + { + "epoch": 19.01, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 36640 + }, + { + "epoch": 19.02, + "learning_rate": 0.001, + "loss": 1.956, + "step": 36650 + }, + { + "epoch": 19.02, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 36660 + }, + { + "epoch": 19.03, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 36670 + }, + { + "epoch": 19.03, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 36680 + }, + { + "epoch": 19.04, + "learning_rate": 0.001, + "loss": 1.9221, + "step": 36690 + }, + { + "epoch": 19.05, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 36700 + }, + { + "epoch": 19.05, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 36710 + }, + { + "epoch": 19.06, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 36720 + }, + { + "epoch": 19.06, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 36730 + }, + { + "epoch": 19.07, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 36740 + }, + { + "epoch": 19.07, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 36750 + }, + { + "epoch": 19.08, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 36760 + }, + { + "epoch": 19.08, + "learning_rate": 0.001, + "loss": 1.9622, + "step": 36770 + }, + { + "epoch": 19.09, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 36780 + }, + { + "epoch": 19.09, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 36790 + }, + { + "epoch": 19.1, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 36800 + }, + { + "epoch": 19.1, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 36810 + }, + { + "epoch": 19.11, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 36820 + }, + { + "epoch": 19.11, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 36830 + }, + { + "epoch": 19.12, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 36840 + }, + { + "epoch": 19.12, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 36850 + }, + { + "epoch": 19.13, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 36860 + }, + { + "epoch": 19.13, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 36870 + }, + { + "epoch": 19.14, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 36880 + }, + { + "epoch": 19.14, + "learning_rate": 0.001, + "loss": 1.938, + "step": 36890 + }, + { + "epoch": 19.15, + "learning_rate": 0.001, + "loss": 1.959, + "step": 36900 + }, + { + "epoch": 19.15, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 36910 + }, + { + "epoch": 19.16, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 36920 + }, + { + "epoch": 19.16, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 36930 + }, + { + "epoch": 19.17, + "learning_rate": 0.001, + "loss": 1.95, + "step": 36940 + }, + { + "epoch": 19.17, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 36950 + }, + { + "epoch": 19.18, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 36960 + }, + { + "epoch": 19.19, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 36970 + }, + { + "epoch": 19.19, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 36980 + }, + { + "epoch": 19.2, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 36990 + }, + { + "epoch": 19.2, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 37000 + }, + { + "epoch": 19.21, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 37010 + }, + { + "epoch": 19.21, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 37020 + }, + { + "epoch": 19.22, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 37030 + }, + { + "epoch": 19.22, + "learning_rate": 0.001, + "loss": 1.9662, + "step": 37040 + }, + { + "epoch": 19.23, + "learning_rate": 0.001, + "loss": 1.944, + "step": 37050 + }, + { + "epoch": 19.23, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 37060 + }, + { + "epoch": 19.24, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 37070 + }, + { + "epoch": 19.24, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 37080 + }, + { + "epoch": 19.25, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 37090 + }, + { + "epoch": 19.25, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 37100 + }, + { + "epoch": 19.26, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 37110 + }, + { + "epoch": 19.26, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 37120 + }, + { + "epoch": 19.27, + "learning_rate": 0.001, + "loss": 1.9198, + "step": 37130 + }, + { + "epoch": 19.27, + "learning_rate": 0.001, + "loss": 1.9597, + "step": 37140 + }, + { + "epoch": 19.28, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 37150 + }, + { + "epoch": 19.28, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 37160 + }, + { + "epoch": 19.29, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 37170 + }, + { + "epoch": 19.29, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 37180 + }, + { + "epoch": 19.3, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 37190 + }, + { + "epoch": 19.3, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 37200 + }, + { + "epoch": 19.31, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 37210 + }, + { + "epoch": 19.31, + "learning_rate": 0.001, + "loss": 1.942, + "step": 37220 + }, + { + "epoch": 19.32, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 37230 + }, + { + "epoch": 19.33, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 37240 + }, + { + "epoch": 19.33, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 37250 + }, + { + "epoch": 19.34, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 37260 + }, + { + "epoch": 19.34, + "learning_rate": 0.001, + "loss": 1.923, + "step": 37270 + }, + { + "epoch": 19.35, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 37280 + }, + { + "epoch": 19.35, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 37290 + }, + { + "epoch": 19.36, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 37300 + }, + { + "epoch": 19.36, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 37310 + }, + { + "epoch": 19.37, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 37320 + }, + { + "epoch": 19.37, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 37330 + }, + { + "epoch": 19.38, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 37340 + }, + { + "epoch": 19.38, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 37350 + }, + { + "epoch": 19.39, + "learning_rate": 0.001, + "loss": 1.94, + "step": 37360 + }, + { + "epoch": 19.39, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 37370 + }, + { + "epoch": 19.4, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 37380 + }, + { + "epoch": 19.4, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 37390 + }, + { + "epoch": 19.41, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 37400 + }, + { + "epoch": 19.41, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 37410 + }, + { + "epoch": 19.42, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 37420 + }, + { + "epoch": 19.42, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 37430 + }, + { + "epoch": 19.43, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 37440 + }, + { + "epoch": 19.43, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 37450 + }, + { + "epoch": 19.44, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 37460 + }, + { + "epoch": 19.44, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 37470 + }, + { + "epoch": 19.45, + "learning_rate": 0.001, + "loss": 1.9211, + "step": 37480 + }, + { + "epoch": 19.46, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 37490 + }, + { + "epoch": 19.46, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 37500 + }, + { + "epoch": 19.47, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 37510 + }, + { + "epoch": 19.47, + "learning_rate": 0.001, + "loss": 1.946, + "step": 37520 + }, + { + "epoch": 19.48, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 37530 + }, + { + "epoch": 19.48, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 37540 + }, + { + "epoch": 19.49, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 37550 + }, + { + "epoch": 19.49, + "learning_rate": 0.001, + "loss": 1.952, + "step": 37560 + }, + { + "epoch": 19.5, + "learning_rate": 0.001, + "loss": 1.945, + "step": 37570 + }, + { + "epoch": 19.5, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 37580 + }, + { + "epoch": 19.51, + "learning_rate": 0.001, + "loss": 1.9594, + "step": 37590 + }, + { + "epoch": 19.51, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 37600 + }, + { + "epoch": 19.52, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 37610 + }, + { + "epoch": 19.52, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 37620 + }, + { + "epoch": 19.53, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 37630 + }, + { + "epoch": 19.53, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 37640 + }, + { + "epoch": 19.54, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 37650 + }, + { + "epoch": 19.54, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 37660 + }, + { + "epoch": 19.55, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 37670 + }, + { + "epoch": 19.55, + "learning_rate": 0.001, + "loss": 1.952, + "step": 37680 + }, + { + "epoch": 19.56, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 37690 + }, + { + "epoch": 19.56, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 37700 + }, + { + "epoch": 19.57, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 37710 + }, + { + "epoch": 19.57, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 37720 + }, + { + "epoch": 19.58, + "learning_rate": 0.001, + "loss": 1.934, + "step": 37730 + }, + { + "epoch": 19.58, + "learning_rate": 0.001, + "loss": 1.931, + "step": 37740 + }, + { + "epoch": 19.59, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 37750 + }, + { + "epoch": 19.6, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 37760 + }, + { + "epoch": 19.6, + "learning_rate": 0.001, + "loss": 1.9074, + "step": 37770 + }, + { + "epoch": 19.61, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 37780 + }, + { + "epoch": 19.61, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 37790 + }, + { + "epoch": 19.62, + "learning_rate": 0.001, + "loss": 1.9189, + "step": 37800 + }, + { + "epoch": 19.62, + "learning_rate": 0.001, + "loss": 1.9673, + "step": 37810 + }, + { + "epoch": 19.63, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 37820 + }, + { + "epoch": 19.63, + "learning_rate": 0.001, + "loss": 1.9637, + "step": 37830 + }, + { + "epoch": 19.64, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 37840 + }, + { + "epoch": 19.64, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 37850 + }, + { + "epoch": 19.65, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 37860 + }, + { + "epoch": 19.65, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 37870 + }, + { + "epoch": 19.66, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 37880 + }, + { + "epoch": 19.66, + "learning_rate": 0.001, + "loss": 1.939, + "step": 37890 + }, + { + "epoch": 19.67, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 37900 + }, + { + "epoch": 19.67, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 37910 + }, + { + "epoch": 19.68, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 37920 + }, + { + "epoch": 19.68, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 37930 + }, + { + "epoch": 19.69, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 37940 + }, + { + "epoch": 19.69, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 37950 + }, + { + "epoch": 19.7, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 37960 + }, + { + "epoch": 19.7, + "learning_rate": 0.001, + "loss": 1.929, + "step": 37970 + }, + { + "epoch": 19.71, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 37980 + }, + { + "epoch": 19.71, + "learning_rate": 0.001, + "loss": 1.9262, + "step": 37990 + }, + { + "epoch": 19.72, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 38000 + }, + { + "epoch": 19.72, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 38010 + }, + { + "epoch": 19.73, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 38020 + }, + { + "epoch": 19.74, + "learning_rate": 0.001, + "loss": 1.912, + "step": 38030 + }, + { + "epoch": 19.74, + "learning_rate": 0.001, + "loss": 1.9769, + "step": 38040 + }, + { + "epoch": 19.75, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 38050 + }, + { + "epoch": 19.75, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 38060 + }, + { + "epoch": 19.76, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 38070 + }, + { + "epoch": 19.76, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 38080 + }, + { + "epoch": 19.77, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 38090 + }, + { + "epoch": 19.77, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 38100 + }, + { + "epoch": 19.78, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 38110 + }, + { + "epoch": 19.78, + "learning_rate": 0.001, + "loss": 1.9262, + "step": 38120 + }, + { + "epoch": 19.79, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 38130 + }, + { + "epoch": 19.79, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 38140 + }, + { + "epoch": 19.8, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 38150 + }, + { + "epoch": 19.8, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 38160 + }, + { + "epoch": 19.81, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 38170 + }, + { + "epoch": 19.81, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 38180 + }, + { + "epoch": 19.82, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 38190 + }, + { + "epoch": 19.82, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 38200 + }, + { + "epoch": 19.83, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 38210 + }, + { + "epoch": 19.83, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 38220 + }, + { + "epoch": 19.84, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 38230 + }, + { + "epoch": 19.84, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 38240 + }, + { + "epoch": 19.85, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 38250 + }, + { + "epoch": 19.85, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 38260 + }, + { + "epoch": 19.86, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 38270 + }, + { + "epoch": 19.87, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 38280 + }, + { + "epoch": 19.87, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 38290 + }, + { + "epoch": 19.88, + "learning_rate": 0.001, + "loss": 1.937, + "step": 38300 + }, + { + "epoch": 19.88, + "learning_rate": 0.001, + "loss": 1.939, + "step": 38310 + }, + { + "epoch": 19.89, + "learning_rate": 0.001, + "loss": 1.955, + "step": 38320 + }, + { + "epoch": 19.89, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 38330 + }, + { + "epoch": 19.9, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 38340 + }, + { + "epoch": 19.9, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 38350 + }, + { + "epoch": 19.91, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 38360 + }, + { + "epoch": 19.91, + "learning_rate": 0.001, + "loss": 1.935, + "step": 38370 + }, + { + "epoch": 19.92, + "learning_rate": 0.001, + "loss": 1.9111, + "step": 38380 + }, + { + "epoch": 19.92, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 38390 + }, + { + "epoch": 19.93, + "learning_rate": 0.001, + "loss": 1.9748, + "step": 38400 + }, + { + "epoch": 19.93, + "learning_rate": 0.001, + "loss": 1.9595, + "step": 38410 + }, + { + "epoch": 19.94, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 38420 + }, + { + "epoch": 19.94, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 38430 + }, + { + "epoch": 19.95, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 38440 + }, + { + "epoch": 19.95, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 38450 + }, + { + "epoch": 19.96, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 38460 + }, + { + "epoch": 19.96, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 38470 + }, + { + "epoch": 19.97, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 38480 + }, + { + "epoch": 19.97, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 38490 + }, + { + "epoch": 19.98, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 38500 + }, + { + "epoch": 19.98, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 38510 + }, + { + "epoch": 19.99, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 38520 + }, + { + "epoch": 19.99, + "learning_rate": 0.001, + "loss": 1.942, + "step": 38530 + }, + { + "epoch": 20.0, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 38540 + }, + { + "epoch": 20.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.941011667251587, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.0441, + "eval_samples_per_second": 50.036, + "eval_steps_per_second": 25.025, + "step": 38540 + }, + { + "epoch": 20.01, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 38550 + }, + { + "epoch": 20.01, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 38560 + }, + { + "epoch": 20.02, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 38570 + }, + { + "epoch": 20.02, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 38580 + }, + { + "epoch": 20.03, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 38590 + }, + { + "epoch": 20.03, + "learning_rate": 0.001, + "loss": 1.932, + "step": 38600 + }, + { + "epoch": 20.04, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 38610 + }, + { + "epoch": 20.04, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 38620 + }, + { + "epoch": 20.05, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 38630 + }, + { + "epoch": 20.05, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 38640 + }, + { + "epoch": 20.06, + "learning_rate": 0.001, + "loss": 1.9677, + "step": 38650 + }, + { + "epoch": 20.06, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 38660 + }, + { + "epoch": 20.07, + "learning_rate": 0.001, + "loss": 1.942, + "step": 38670 + }, + { + "epoch": 20.07, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 38680 + }, + { + "epoch": 20.08, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 38690 + }, + { + "epoch": 20.08, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 38700 + }, + { + "epoch": 20.09, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 38710 + }, + { + "epoch": 20.09, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 38720 + }, + { + "epoch": 20.1, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 38730 + }, + { + "epoch": 20.1, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 38740 + }, + { + "epoch": 20.11, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 38750 + }, + { + "epoch": 20.11, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 38760 + }, + { + "epoch": 20.12, + "learning_rate": 0.001, + "loss": 1.95, + "step": 38770 + }, + { + "epoch": 20.12, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 38780 + }, + { + "epoch": 20.13, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 38790 + }, + { + "epoch": 20.13, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 38800 + }, + { + "epoch": 20.14, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 38810 + }, + { + "epoch": 20.15, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 38820 + }, + { + "epoch": 20.15, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 38830 + }, + { + "epoch": 20.16, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 38840 + }, + { + "epoch": 20.16, + "learning_rate": 0.001, + "loss": 1.944, + "step": 38850 + }, + { + "epoch": 20.17, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 38860 + }, + { + "epoch": 20.17, + "learning_rate": 0.001, + "loss": 1.948, + "step": 38870 + }, + { + "epoch": 20.18, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 38880 + }, + { + "epoch": 20.18, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 38890 + }, + { + "epoch": 20.19, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 38900 + }, + { + "epoch": 20.19, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 38910 + }, + { + "epoch": 20.2, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 38920 + }, + { + "epoch": 20.2, + "learning_rate": 0.001, + "loss": 1.9624, + "step": 38930 + }, + { + "epoch": 20.21, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 38940 + }, + { + "epoch": 20.21, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 38950 + }, + { + "epoch": 20.22, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 38960 + }, + { + "epoch": 20.22, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 38970 + }, + { + "epoch": 20.23, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 38980 + }, + { + "epoch": 20.23, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 38990 + }, + { + "epoch": 20.24, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 39000 + }, + { + "epoch": 20.24, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 39010 + }, + { + "epoch": 20.25, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 39020 + }, + { + "epoch": 20.25, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 39030 + }, + { + "epoch": 20.26, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 39040 + }, + { + "epoch": 20.26, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 39050 + }, + { + "epoch": 20.27, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 39060 + }, + { + "epoch": 20.28, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 39070 + }, + { + "epoch": 20.28, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 39080 + }, + { + "epoch": 20.29, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 39090 + }, + { + "epoch": 20.29, + "learning_rate": 0.001, + "loss": 1.944, + "step": 39100 + }, + { + "epoch": 20.3, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 39110 + }, + { + "epoch": 20.3, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 39120 + }, + { + "epoch": 20.31, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 39130 + }, + { + "epoch": 20.31, + "learning_rate": 0.001, + "loss": 1.948, + "step": 39140 + }, + { + "epoch": 20.32, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 39150 + }, + { + "epoch": 20.32, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 39160 + }, + { + "epoch": 20.33, + "learning_rate": 0.001, + "loss": 1.9531, + "step": 39170 + }, + { + "epoch": 20.33, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 39180 + }, + { + "epoch": 20.34, + "learning_rate": 0.001, + "loss": 1.937, + "step": 39190 + }, + { + "epoch": 20.34, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 39200 + }, + { + "epoch": 20.35, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 39210 + }, + { + "epoch": 20.35, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 39220 + }, + { + "epoch": 20.36, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 39230 + }, + { + "epoch": 20.36, + "learning_rate": 0.001, + "loss": 1.9627, + "step": 39240 + }, + { + "epoch": 20.37, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 39250 + }, + { + "epoch": 20.37, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 39260 + }, + { + "epoch": 20.38, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 39270 + }, + { + "epoch": 20.38, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 39280 + }, + { + "epoch": 20.39, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 39290 + }, + { + "epoch": 20.39, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 39300 + }, + { + "epoch": 20.4, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 39310 + }, + { + "epoch": 20.4, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 39320 + }, + { + "epoch": 20.41, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 39330 + }, + { + "epoch": 20.42, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 39340 + }, + { + "epoch": 20.42, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 39350 + }, + { + "epoch": 20.43, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 39360 + }, + { + "epoch": 20.43, + "learning_rate": 0.001, + "loss": 1.935, + "step": 39370 + }, + { + "epoch": 20.44, + "learning_rate": 0.001, + "loss": 1.9263, + "step": 39380 + }, + { + "epoch": 20.44, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 39390 + }, + { + "epoch": 20.45, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 39400 + }, + { + "epoch": 20.45, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 39410 + }, + { + "epoch": 20.46, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 39420 + }, + { + "epoch": 20.46, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 39430 + }, + { + "epoch": 20.47, + "learning_rate": 0.001, + "loss": 1.9228, + "step": 39440 + }, + { + "epoch": 20.47, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 39450 + }, + { + "epoch": 20.48, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 39460 + }, + { + "epoch": 20.48, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 39470 + }, + { + "epoch": 20.49, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 39480 + }, + { + "epoch": 20.49, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 39490 + }, + { + "epoch": 20.5, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 39500 + }, + { + "epoch": 20.5, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 39510 + }, + { + "epoch": 20.51, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 39520 + }, + { + "epoch": 20.51, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 39530 + }, + { + "epoch": 20.52, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 39540 + }, + { + "epoch": 20.52, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 39550 + }, + { + "epoch": 20.53, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 39560 + }, + { + "epoch": 20.53, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 39570 + }, + { + "epoch": 20.54, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 39580 + }, + { + "epoch": 20.54, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 39590 + }, + { + "epoch": 20.55, + "learning_rate": 0.001, + "loss": 1.9764, + "step": 39600 + }, + { + "epoch": 20.56, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 39610 + }, + { + "epoch": 20.56, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 39620 + }, + { + "epoch": 20.57, + "learning_rate": 0.001, + "loss": 1.9325, + "step": 39630 + }, + { + "epoch": 20.57, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 39640 + }, + { + "epoch": 20.58, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 39650 + }, + { + "epoch": 20.58, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 39660 + }, + { + "epoch": 20.59, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 39670 + }, + { + "epoch": 20.59, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 39680 + }, + { + "epoch": 20.6, + "learning_rate": 0.001, + "loss": 1.9194, + "step": 39690 + }, + { + "epoch": 20.6, + "learning_rate": 0.001, + "loss": 1.946, + "step": 39700 + }, + { + "epoch": 20.61, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 39710 + }, + { + "epoch": 20.61, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 39720 + }, + { + "epoch": 20.62, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 39730 + }, + { + "epoch": 20.62, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 39740 + }, + { + "epoch": 20.63, + "learning_rate": 0.001, + "loss": 1.9265, + "step": 39750 + }, + { + "epoch": 20.63, + "learning_rate": 0.001, + "loss": 1.934, + "step": 39760 + }, + { + "epoch": 20.64, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 39770 + }, + { + "epoch": 20.64, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 39780 + }, + { + "epoch": 20.65, + "learning_rate": 0.001, + "loss": 1.9197, + "step": 39790 + }, + { + "epoch": 20.65, + "learning_rate": 0.001, + "loss": 1.9632, + "step": 39800 + }, + { + "epoch": 20.66, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 39810 + }, + { + "epoch": 20.66, + "learning_rate": 0.001, + "loss": 1.9214, + "step": 39820 + }, + { + "epoch": 20.67, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 39830 + }, + { + "epoch": 20.67, + "learning_rate": 0.001, + "loss": 1.9664, + "step": 39840 + }, + { + "epoch": 20.68, + "learning_rate": 0.001, + "loss": 1.9688, + "step": 39850 + }, + { + "epoch": 20.69, + "learning_rate": 0.001, + "loss": 1.959, + "step": 39860 + }, + { + "epoch": 20.69, + "learning_rate": 0.001, + "loss": 1.929, + "step": 39870 + }, + { + "epoch": 20.7, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 39880 + }, + { + "epoch": 20.7, + "learning_rate": 0.001, + "loss": 1.9257, + "step": 39890 + }, + { + "epoch": 20.71, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 39900 + }, + { + "epoch": 20.71, + "learning_rate": 0.001, + "loss": 1.936, + "step": 39910 + }, + { + "epoch": 20.72, + "learning_rate": 0.001, + "loss": 1.9593, + "step": 39920 + }, + { + "epoch": 20.72, + "learning_rate": 0.001, + "loss": 1.9637, + "step": 39930 + }, + { + "epoch": 20.73, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 39940 + }, + { + "epoch": 20.73, + "learning_rate": 0.001, + "loss": 1.9298, + "step": 39950 + }, + { + "epoch": 20.74, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 39960 + }, + { + "epoch": 20.74, + "learning_rate": 0.001, + "loss": 1.9286, + "step": 39970 + }, + { + "epoch": 20.75, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 39980 + }, + { + "epoch": 20.75, + "learning_rate": 0.001, + "loss": 1.9612, + "step": 39990 + }, + { + "epoch": 20.76, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 40000 + }, + { + "epoch": 20.76, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 40010 + }, + { + "epoch": 20.77, + "learning_rate": 0.001, + "loss": 1.9231, + "step": 40020 + }, + { + "epoch": 20.77, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 40030 + }, + { + "epoch": 20.78, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 40040 + }, + { + "epoch": 20.78, + "learning_rate": 0.001, + "loss": 1.949, + "step": 40050 + }, + { + "epoch": 20.79, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 40060 + }, + { + "epoch": 20.79, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 40070 + }, + { + "epoch": 20.8, + "learning_rate": 0.001, + "loss": 1.9718, + "step": 40080 + }, + { + "epoch": 20.8, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 40090 + }, + { + "epoch": 20.81, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 40100 + }, + { + "epoch": 20.81, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 40110 + }, + { + "epoch": 20.82, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 40120 + }, + { + "epoch": 20.83, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 40130 + }, + { + "epoch": 20.83, + "learning_rate": 0.001, + "loss": 1.9258, + "step": 40140 + }, + { + "epoch": 20.84, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 40150 + }, + { + "epoch": 20.84, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 40160 + }, + { + "epoch": 20.85, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 40170 + }, + { + "epoch": 20.85, + "learning_rate": 0.001, + "loss": 1.926, + "step": 40180 + }, + { + "epoch": 20.86, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 40190 + }, + { + "epoch": 20.86, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 40200 + }, + { + "epoch": 20.87, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 40210 + }, + { + "epoch": 20.87, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 40220 + }, + { + "epoch": 20.88, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 40230 + }, + { + "epoch": 20.88, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 40240 + }, + { + "epoch": 20.89, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 40250 + }, + { + "epoch": 20.89, + "learning_rate": 0.001, + "loss": 1.949, + "step": 40260 + }, + { + "epoch": 20.9, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 40270 + }, + { + "epoch": 20.9, + "learning_rate": 0.001, + "loss": 1.95, + "step": 40280 + }, + { + "epoch": 20.91, + "learning_rate": 0.001, + "loss": 1.9634, + "step": 40290 + }, + { + "epoch": 20.91, + "learning_rate": 0.001, + "loss": 1.949, + "step": 40300 + }, + { + "epoch": 20.92, + "learning_rate": 0.001, + "loss": 1.936, + "step": 40310 + }, + { + "epoch": 20.92, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 40320 + }, + { + "epoch": 20.93, + "learning_rate": 0.001, + "loss": 1.931, + "step": 40330 + }, + { + "epoch": 20.93, + "learning_rate": 0.001, + "loss": 1.972, + "step": 40340 + }, + { + "epoch": 20.94, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 40350 + }, + { + "epoch": 20.94, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 40360 + }, + { + "epoch": 20.95, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 40370 + }, + { + "epoch": 20.95, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 40380 + }, + { + "epoch": 20.96, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 40390 + }, + { + "epoch": 20.97, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 40400 + }, + { + "epoch": 20.97, + "learning_rate": 0.001, + "loss": 1.9218, + "step": 40410 + }, + { + "epoch": 20.98, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 40420 + }, + { + "epoch": 20.98, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 40430 + }, + { + "epoch": 20.99, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 40440 + }, + { + "epoch": 20.99, + "learning_rate": 0.001, + "loss": 1.945, + "step": 40450 + }, + { + "epoch": 21.0, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 40460 + }, + { + "epoch": 21.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.941245436668396, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.9699, + "eval_samples_per_second": 50.084, + "eval_steps_per_second": 25.049, + "step": 40467 + }, + { + "epoch": 21.0, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 40470 + }, + { + "epoch": 21.01, + "learning_rate": 0.001, + "loss": 1.9208, + "step": 40480 + }, + { + "epoch": 21.01, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 40490 + }, + { + "epoch": 21.02, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 40500 + }, + { + "epoch": 21.02, + "learning_rate": 0.001, + "loss": 1.9245, + "step": 40510 + }, + { + "epoch": 21.03, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 40520 + }, + { + "epoch": 21.03, + "learning_rate": 0.001, + "loss": 1.9256, + "step": 40530 + }, + { + "epoch": 21.04, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 40540 + }, + { + "epoch": 21.04, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 40550 + }, + { + "epoch": 21.05, + "learning_rate": 0.001, + "loss": 1.9681, + "step": 40560 + }, + { + "epoch": 21.05, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 40570 + }, + { + "epoch": 21.06, + "learning_rate": 0.001, + "loss": 1.935, + "step": 40580 + }, + { + "epoch": 21.06, + "learning_rate": 0.001, + "loss": 1.932, + "step": 40590 + }, + { + "epoch": 21.07, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 40600 + }, + { + "epoch": 21.07, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 40610 + }, + { + "epoch": 21.08, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 40620 + }, + { + "epoch": 21.08, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 40630 + }, + { + "epoch": 21.09, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 40640 + }, + { + "epoch": 21.09, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 40650 + }, + { + "epoch": 21.1, + "learning_rate": 0.001, + "loss": 1.936, + "step": 40660 + }, + { + "epoch": 21.11, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 40670 + }, + { + "epoch": 21.11, + "learning_rate": 0.001, + "loss": 1.9236, + "step": 40680 + }, + { + "epoch": 21.12, + "learning_rate": 0.001, + "loss": 1.936, + "step": 40690 + }, + { + "epoch": 21.12, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 40700 + }, + { + "epoch": 21.13, + "learning_rate": 0.001, + "loss": 1.924, + "step": 40710 + }, + { + "epoch": 21.13, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 40720 + }, + { + "epoch": 21.14, + "learning_rate": 0.001, + "loss": 1.9609, + "step": 40730 + }, + { + "epoch": 21.14, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 40740 + }, + { + "epoch": 21.15, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 40750 + }, + { + "epoch": 21.15, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 40760 + }, + { + "epoch": 21.16, + "learning_rate": 0.001, + "loss": 1.9627, + "step": 40770 + }, + { + "epoch": 21.16, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 40780 + }, + { + "epoch": 21.17, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 40790 + }, + { + "epoch": 21.17, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 40800 + }, + { + "epoch": 21.18, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 40810 + }, + { + "epoch": 21.18, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 40820 + }, + { + "epoch": 21.19, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 40830 + }, + { + "epoch": 21.19, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 40840 + }, + { + "epoch": 21.2, + "learning_rate": 0.001, + "loss": 1.943, + "step": 40850 + }, + { + "epoch": 21.2, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 40860 + }, + { + "epoch": 21.21, + "learning_rate": 0.001, + "loss": 1.93, + "step": 40870 + }, + { + "epoch": 21.21, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 40880 + }, + { + "epoch": 21.22, + "learning_rate": 0.001, + "loss": 1.9144, + "step": 40890 + }, + { + "epoch": 21.22, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 40900 + }, + { + "epoch": 21.23, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 40910 + }, + { + "epoch": 21.24, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 40920 + }, + { + "epoch": 21.24, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 40930 + }, + { + "epoch": 21.25, + "learning_rate": 0.001, + "loss": 1.9191, + "step": 40940 + }, + { + "epoch": 21.25, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 40950 + }, + { + "epoch": 21.26, + "learning_rate": 0.001, + "loss": 1.95, + "step": 40960 + }, + { + "epoch": 21.26, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 40970 + }, + { + "epoch": 21.27, + "learning_rate": 0.001, + "loss": 1.9667, + "step": 40980 + }, + { + "epoch": 21.27, + "learning_rate": 0.001, + "loss": 1.9638, + "step": 40990 + }, + { + "epoch": 21.28, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 41000 + }, + { + "epoch": 21.28, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 41010 + }, + { + "epoch": 21.29, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 41020 + }, + { + "epoch": 21.29, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 41030 + }, + { + "epoch": 21.3, + "learning_rate": 0.001, + "loss": 1.946, + "step": 41040 + }, + { + "epoch": 21.3, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 41050 + }, + { + "epoch": 21.31, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 41060 + }, + { + "epoch": 21.31, + "learning_rate": 0.001, + "loss": 1.948, + "step": 41070 + }, + { + "epoch": 21.32, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 41080 + }, + { + "epoch": 21.32, + "learning_rate": 0.001, + "loss": 1.9542, + "step": 41090 + }, + { + "epoch": 21.33, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 41100 + }, + { + "epoch": 21.33, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 41110 + }, + { + "epoch": 21.34, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 41120 + }, + { + "epoch": 21.34, + "learning_rate": 0.001, + "loss": 1.932, + "step": 41130 + }, + { + "epoch": 21.35, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 41140 + }, + { + "epoch": 21.35, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 41150 + }, + { + "epoch": 21.36, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 41160 + }, + { + "epoch": 21.36, + "learning_rate": 0.001, + "loss": 1.952, + "step": 41170 + }, + { + "epoch": 21.37, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 41180 + }, + { + "epoch": 21.38, + "learning_rate": 0.001, + "loss": 1.9606, + "step": 41190 + }, + { + "epoch": 21.38, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 41200 + }, + { + "epoch": 21.39, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 41210 + }, + { + "epoch": 21.39, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 41220 + }, + { + "epoch": 21.4, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 41230 + }, + { + "epoch": 21.4, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 41240 + }, + { + "epoch": 21.41, + "learning_rate": 0.001, + "loss": 1.9662, + "step": 41250 + }, + { + "epoch": 21.41, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 41260 + }, + { + "epoch": 21.42, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 41270 + }, + { + "epoch": 21.42, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 41280 + }, + { + "epoch": 21.43, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 41290 + }, + { + "epoch": 21.43, + "learning_rate": 0.001, + "loss": 1.937, + "step": 41300 + }, + { + "epoch": 21.44, + "learning_rate": 0.001, + "loss": 1.9686, + "step": 41310 + }, + { + "epoch": 21.44, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 41320 + }, + { + "epoch": 21.45, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 41330 + }, + { + "epoch": 21.45, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 41340 + }, + { + "epoch": 21.46, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 41350 + }, + { + "epoch": 21.46, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 41360 + }, + { + "epoch": 21.47, + "learning_rate": 0.001, + "loss": 1.9613, + "step": 41370 + }, + { + "epoch": 21.47, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 41380 + }, + { + "epoch": 21.48, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 41390 + }, + { + "epoch": 21.48, + "learning_rate": 0.001, + "loss": 1.9022, + "step": 41400 + }, + { + "epoch": 21.49, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 41410 + }, + { + "epoch": 21.49, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 41420 + }, + { + "epoch": 21.5, + "learning_rate": 0.001, + "loss": 1.9672, + "step": 41430 + }, + { + "epoch": 21.5, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 41440 + }, + { + "epoch": 21.51, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 41450 + }, + { + "epoch": 21.52, + "learning_rate": 0.001, + "loss": 1.9602, + "step": 41460 + }, + { + "epoch": 21.52, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 41470 + }, + { + "epoch": 21.53, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 41480 + }, + { + "epoch": 21.53, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 41490 + }, + { + "epoch": 21.54, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 41500 + }, + { + "epoch": 21.54, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 41510 + }, + { + "epoch": 21.55, + "learning_rate": 0.001, + "loss": 1.9676, + "step": 41520 + }, + { + "epoch": 21.55, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 41530 + }, + { + "epoch": 21.56, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 41540 + }, + { + "epoch": 21.56, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 41550 + }, + { + "epoch": 21.57, + "learning_rate": 0.001, + "loss": 1.944, + "step": 41560 + }, + { + "epoch": 21.57, + "learning_rate": 0.001, + "loss": 1.9669, + "step": 41570 + }, + { + "epoch": 21.58, + "learning_rate": 0.001, + "loss": 1.9582, + "step": 41580 + }, + { + "epoch": 21.58, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 41590 + }, + { + "epoch": 21.59, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 41600 + }, + { + "epoch": 21.59, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 41610 + }, + { + "epoch": 21.6, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 41620 + }, + { + "epoch": 21.6, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 41630 + }, + { + "epoch": 21.61, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 41640 + }, + { + "epoch": 21.61, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 41650 + }, + { + "epoch": 21.62, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 41660 + }, + { + "epoch": 21.62, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 41670 + }, + { + "epoch": 21.63, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 41680 + }, + { + "epoch": 21.63, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 41690 + }, + { + "epoch": 21.64, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 41700 + }, + { + "epoch": 21.65, + "learning_rate": 0.001, + "loss": 1.9249, + "step": 41710 + }, + { + "epoch": 21.65, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 41720 + }, + { + "epoch": 21.66, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 41730 + }, + { + "epoch": 21.66, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 41740 + }, + { + "epoch": 21.67, + "learning_rate": 0.001, + "loss": 1.9369, + "step": 41750 + }, + { + "epoch": 21.67, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 41760 + }, + { + "epoch": 21.68, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 41770 + }, + { + "epoch": 21.68, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 41780 + }, + { + "epoch": 21.69, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 41790 + }, + { + "epoch": 21.69, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 41800 + }, + { + "epoch": 21.7, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 41810 + }, + { + "epoch": 21.7, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 41820 + }, + { + "epoch": 21.71, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 41830 + }, + { + "epoch": 21.71, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 41840 + }, + { + "epoch": 21.72, + "learning_rate": 0.001, + "loss": 1.9192, + "step": 41850 + }, + { + "epoch": 21.72, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 41860 + }, + { + "epoch": 21.73, + "learning_rate": 0.001, + "loss": 1.9597, + "step": 41870 + }, + { + "epoch": 21.73, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 41880 + }, + { + "epoch": 21.74, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 41890 + }, + { + "epoch": 21.74, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 41900 + }, + { + "epoch": 21.75, + "learning_rate": 0.001, + "loss": 1.9265, + "step": 41910 + }, + { + "epoch": 21.75, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 41920 + }, + { + "epoch": 21.76, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 41930 + }, + { + "epoch": 21.76, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 41940 + }, + { + "epoch": 21.77, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 41950 + }, + { + "epoch": 21.77, + "learning_rate": 0.001, + "loss": 1.9606, + "step": 41960 + }, + { + "epoch": 21.78, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 41970 + }, + { + "epoch": 21.79, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 41980 + }, + { + "epoch": 21.79, + "learning_rate": 0.001, + "loss": 1.948, + "step": 41990 + }, + { + "epoch": 21.8, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 42000 + }, + { + "epoch": 21.8, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 42010 + }, + { + "epoch": 21.81, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 42020 + }, + { + "epoch": 21.81, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 42030 + }, + { + "epoch": 21.82, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 42040 + }, + { + "epoch": 21.82, + "learning_rate": 0.001, + "loss": 1.946, + "step": 42050 + }, + { + "epoch": 21.83, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 42060 + }, + { + "epoch": 21.83, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 42070 + }, + { + "epoch": 21.84, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 42080 + }, + { + "epoch": 21.84, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 42090 + }, + { + "epoch": 21.85, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 42100 + }, + { + "epoch": 21.85, + "learning_rate": 0.001, + "loss": 1.9217, + "step": 42110 + }, + { + "epoch": 21.86, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 42120 + }, + { + "epoch": 21.86, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 42130 + }, + { + "epoch": 21.87, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 42140 + }, + { + "epoch": 21.87, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 42150 + }, + { + "epoch": 21.88, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 42160 + }, + { + "epoch": 21.88, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 42170 + }, + { + "epoch": 21.89, + "learning_rate": 0.001, + "loss": 1.9572, + "step": 42180 + }, + { + "epoch": 21.89, + "learning_rate": 0.001, + "loss": 1.9567, + "step": 42190 + }, + { + "epoch": 21.9, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 42200 + }, + { + "epoch": 21.9, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 42210 + }, + { + "epoch": 21.91, + "learning_rate": 0.001, + "loss": 1.9394, + "step": 42220 + }, + { + "epoch": 21.91, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 42230 + }, + { + "epoch": 21.92, + "learning_rate": 0.001, + "loss": 1.9154, + "step": 42240 + }, + { + "epoch": 21.93, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 42250 + }, + { + "epoch": 21.93, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 42260 + }, + { + "epoch": 21.94, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 42270 + }, + { + "epoch": 21.94, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 42280 + }, + { + "epoch": 21.95, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 42290 + }, + { + "epoch": 21.95, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 42300 + }, + { + "epoch": 21.96, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 42310 + }, + { + "epoch": 21.96, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 42320 + }, + { + "epoch": 21.97, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 42330 + }, + { + "epoch": 21.97, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 42340 + }, + { + "epoch": 21.98, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 42350 + }, + { + "epoch": 21.98, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 42360 + }, + { + "epoch": 21.99, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 42370 + }, + { + "epoch": 21.99, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 42380 + }, + { + "epoch": 22.0, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 42390 + }, + { + "epoch": 22.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.941336989402771, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 78.0898, + "eval_samples_per_second": 49.366, + "eval_steps_per_second": 24.69, + "step": 42394 + }, + { + "epoch": 22.0, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 42400 + }, + { + "epoch": 22.01, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 42410 + }, + { + "epoch": 22.01, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 42420 + }, + { + "epoch": 22.02, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 42430 + }, + { + "epoch": 22.02, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 42440 + }, + { + "epoch": 22.03, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 42450 + }, + { + "epoch": 22.03, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 42460 + }, + { + "epoch": 22.04, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 42470 + }, + { + "epoch": 22.04, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 42480 + }, + { + "epoch": 22.05, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 42490 + }, + { + "epoch": 22.06, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 42500 + }, + { + "epoch": 22.06, + "learning_rate": 0.001, + "loss": 1.951, + "step": 42510 + }, + { + "epoch": 22.07, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 42520 + }, + { + "epoch": 22.07, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 42530 + }, + { + "epoch": 22.08, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 42540 + }, + { + "epoch": 22.08, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 42550 + }, + { + "epoch": 22.09, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 42560 + }, + { + "epoch": 22.09, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 42570 + }, + { + "epoch": 22.1, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 42580 + }, + { + "epoch": 22.1, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 42590 + }, + { + "epoch": 22.11, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 42600 + }, + { + "epoch": 22.11, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 42610 + }, + { + "epoch": 22.12, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 42620 + }, + { + "epoch": 22.12, + "learning_rate": 0.001, + "loss": 1.9551, + "step": 42630 + }, + { + "epoch": 22.13, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 42640 + }, + { + "epoch": 22.13, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 42650 + }, + { + "epoch": 22.14, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 42660 + }, + { + "epoch": 22.14, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 42670 + }, + { + "epoch": 22.15, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 42680 + }, + { + "epoch": 22.15, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 42690 + }, + { + "epoch": 22.16, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 42700 + }, + { + "epoch": 22.16, + "learning_rate": 0.001, + "loss": 1.9223, + "step": 42710 + }, + { + "epoch": 22.17, + "learning_rate": 0.001, + "loss": 1.94, + "step": 42720 + }, + { + "epoch": 22.17, + "learning_rate": 0.001, + "loss": 1.9266, + "step": 42730 + }, + { + "epoch": 22.18, + "learning_rate": 0.001, + "loss": 1.944, + "step": 42740 + }, + { + "epoch": 22.18, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 42750 + }, + { + "epoch": 22.19, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 42760 + }, + { + "epoch": 22.2, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 42770 + }, + { + "epoch": 22.2, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 42780 + }, + { + "epoch": 22.21, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 42790 + }, + { + "epoch": 22.21, + "learning_rate": 0.001, + "loss": 1.933, + "step": 42800 + }, + { + "epoch": 22.22, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 42810 + }, + { + "epoch": 22.22, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 42820 + }, + { + "epoch": 22.23, + "learning_rate": 0.001, + "loss": 1.948, + "step": 42830 + }, + { + "epoch": 22.23, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 42840 + }, + { + "epoch": 22.24, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 42850 + }, + { + "epoch": 22.24, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 42860 + }, + { + "epoch": 22.25, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 42870 + }, + { + "epoch": 22.25, + "learning_rate": 0.001, + "loss": 1.9715, + "step": 42880 + }, + { + "epoch": 22.26, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 42890 + }, + { + "epoch": 22.26, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 42900 + }, + { + "epoch": 22.27, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 42910 + }, + { + "epoch": 22.27, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 42920 + }, + { + "epoch": 22.28, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 42930 + }, + { + "epoch": 22.28, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 42940 + }, + { + "epoch": 22.29, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 42950 + }, + { + "epoch": 22.29, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 42960 + }, + { + "epoch": 22.3, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 42970 + }, + { + "epoch": 22.3, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 42980 + }, + { + "epoch": 22.31, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 42990 + }, + { + "epoch": 22.31, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 43000 + }, + { + "epoch": 22.32, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 43010 + }, + { + "epoch": 22.32, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 43020 + }, + { + "epoch": 22.33, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 43030 + }, + { + "epoch": 22.34, + "learning_rate": 0.001, + "loss": 1.9614, + "step": 43040 + }, + { + "epoch": 22.34, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 43050 + }, + { + "epoch": 22.35, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 43060 + }, + { + "epoch": 22.35, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 43070 + }, + { + "epoch": 22.36, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 43080 + }, + { + "epoch": 22.36, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 43090 + }, + { + "epoch": 22.37, + "learning_rate": 0.001, + "loss": 1.948, + "step": 43100 + }, + { + "epoch": 22.37, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 43110 + }, + { + "epoch": 22.38, + "learning_rate": 0.001, + "loss": 1.954, + "step": 43120 + }, + { + "epoch": 22.38, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 43130 + }, + { + "epoch": 22.39, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 43140 + }, + { + "epoch": 22.39, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 43150 + }, + { + "epoch": 22.4, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 43160 + }, + { + "epoch": 22.4, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 43170 + }, + { + "epoch": 22.41, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 43180 + }, + { + "epoch": 22.41, + "learning_rate": 0.001, + "loss": 1.939, + "step": 43190 + }, + { + "epoch": 22.42, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 43200 + }, + { + "epoch": 22.42, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 43210 + }, + { + "epoch": 22.43, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 43220 + }, + { + "epoch": 22.43, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 43230 + }, + { + "epoch": 22.44, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 43240 + }, + { + "epoch": 22.44, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 43250 + }, + { + "epoch": 22.45, + "learning_rate": 0.001, + "loss": 1.9327, + "step": 43260 + }, + { + "epoch": 22.45, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 43270 + }, + { + "epoch": 22.46, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 43280 + }, + { + "epoch": 22.46, + "learning_rate": 0.001, + "loss": 1.9267, + "step": 43290 + }, + { + "epoch": 22.47, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 43300 + }, + { + "epoch": 22.48, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 43310 + }, + { + "epoch": 22.48, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 43320 + }, + { + "epoch": 22.49, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 43330 + }, + { + "epoch": 22.49, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 43340 + }, + { + "epoch": 22.5, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 43350 + }, + { + "epoch": 22.5, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 43360 + }, + { + "epoch": 22.51, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 43370 + }, + { + "epoch": 22.51, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 43380 + }, + { + "epoch": 22.52, + "learning_rate": 0.001, + "loss": 1.9181, + "step": 43390 + }, + { + "epoch": 22.52, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 43400 + }, + { + "epoch": 22.53, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 43410 + }, + { + "epoch": 22.53, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 43420 + }, + { + "epoch": 22.54, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 43430 + }, + { + "epoch": 22.54, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 43440 + }, + { + "epoch": 22.55, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 43450 + }, + { + "epoch": 22.55, + "learning_rate": 0.001, + "loss": 1.9272, + "step": 43460 + }, + { + "epoch": 22.56, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 43470 + }, + { + "epoch": 22.56, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 43480 + }, + { + "epoch": 22.57, + "learning_rate": 0.001, + "loss": 1.9249, + "step": 43490 + }, + { + "epoch": 22.57, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 43500 + }, + { + "epoch": 22.58, + "learning_rate": 0.001, + "loss": 1.948, + "step": 43510 + }, + { + "epoch": 22.58, + "learning_rate": 0.001, + "loss": 1.9457, + "step": 43520 + }, + { + "epoch": 22.59, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 43530 + }, + { + "epoch": 22.59, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 43540 + }, + { + "epoch": 22.6, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 43550 + }, + { + "epoch": 22.61, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 43560 + }, + { + "epoch": 22.61, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 43570 + }, + { + "epoch": 22.62, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 43580 + }, + { + "epoch": 22.62, + "learning_rate": 0.001, + "loss": 1.943, + "step": 43590 + }, + { + "epoch": 22.63, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 43600 + }, + { + "epoch": 22.63, + "learning_rate": 0.001, + "loss": 1.9591, + "step": 43610 + }, + { + "epoch": 22.64, + "learning_rate": 0.001, + "loss": 1.922, + "step": 43620 + }, + { + "epoch": 22.64, + "learning_rate": 0.001, + "loss": 1.9687, + "step": 43630 + }, + { + "epoch": 22.65, + "learning_rate": 0.001, + "loss": 1.922, + "step": 43640 + }, + { + "epoch": 22.65, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 43650 + }, + { + "epoch": 22.66, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 43660 + }, + { + "epoch": 22.66, + "learning_rate": 0.001, + "loss": 1.954, + "step": 43670 + }, + { + "epoch": 22.67, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 43680 + }, + { + "epoch": 22.67, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 43690 + }, + { + "epoch": 22.68, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 43700 + }, + { + "epoch": 22.68, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 43710 + }, + { + "epoch": 22.69, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 43720 + }, + { + "epoch": 22.69, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 43730 + }, + { + "epoch": 22.7, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 43740 + }, + { + "epoch": 22.7, + "learning_rate": 0.001, + "loss": 1.923, + "step": 43750 + }, + { + "epoch": 22.71, + "learning_rate": 0.001, + "loss": 1.9603, + "step": 43760 + }, + { + "epoch": 22.71, + "learning_rate": 0.001, + "loss": 1.956, + "step": 43770 + }, + { + "epoch": 22.72, + "learning_rate": 0.001, + "loss": 1.946, + "step": 43780 + }, + { + "epoch": 22.72, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 43790 + }, + { + "epoch": 22.73, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 43800 + }, + { + "epoch": 22.73, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 43810 + }, + { + "epoch": 22.74, + "learning_rate": 0.001, + "loss": 1.9525, + "step": 43820 + }, + { + "epoch": 22.75, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 43830 + }, + { + "epoch": 22.75, + "learning_rate": 0.001, + "loss": 1.937, + "step": 43840 + }, + { + "epoch": 22.76, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 43850 + }, + { + "epoch": 22.76, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 43860 + }, + { + "epoch": 22.77, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 43870 + }, + { + "epoch": 22.77, + "learning_rate": 0.001, + "loss": 1.9378, + "step": 43880 + }, + { + "epoch": 22.78, + "learning_rate": 0.001, + "loss": 1.9623, + "step": 43890 + }, + { + "epoch": 22.78, + "learning_rate": 0.001, + "loss": 1.9544, + "step": 43900 + }, + { + "epoch": 22.79, + "learning_rate": 0.001, + "loss": 1.9536, + "step": 43910 + }, + { + "epoch": 22.79, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 43920 + }, + { + "epoch": 22.8, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 43930 + }, + { + "epoch": 22.8, + "learning_rate": 0.001, + "loss": 1.9642, + "step": 43940 + }, + { + "epoch": 22.81, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 43950 + }, + { + "epoch": 22.81, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 43960 + }, + { + "epoch": 22.82, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 43970 + }, + { + "epoch": 22.82, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 43980 + }, + { + "epoch": 22.83, + "learning_rate": 0.001, + "loss": 1.947, + "step": 43990 + }, + { + "epoch": 22.83, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 44000 + }, + { + "epoch": 22.84, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 44010 + }, + { + "epoch": 22.84, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 44020 + }, + { + "epoch": 22.85, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 44030 + }, + { + "epoch": 22.85, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 44040 + }, + { + "epoch": 22.86, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 44050 + }, + { + "epoch": 22.86, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 44060 + }, + { + "epoch": 22.87, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 44070 + }, + { + "epoch": 22.87, + "learning_rate": 0.001, + "loss": 1.93, + "step": 44080 + }, + { + "epoch": 22.88, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 44090 + }, + { + "epoch": 22.89, + "learning_rate": 0.001, + "loss": 1.9295, + "step": 44100 + }, + { + "epoch": 22.89, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 44110 + }, + { + "epoch": 22.9, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 44120 + }, + { + "epoch": 22.9, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 44130 + }, + { + "epoch": 22.91, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 44140 + }, + { + "epoch": 22.91, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 44150 + }, + { + "epoch": 22.92, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 44160 + }, + { + "epoch": 22.92, + "learning_rate": 0.001, + "loss": 1.966, + "step": 44170 + }, + { + "epoch": 22.93, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 44180 + }, + { + "epoch": 22.93, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 44190 + }, + { + "epoch": 22.94, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 44200 + }, + { + "epoch": 22.94, + "learning_rate": 0.001, + "loss": 1.947, + "step": 44210 + }, + { + "epoch": 22.95, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 44220 + }, + { + "epoch": 22.95, + "learning_rate": 0.001, + "loss": 1.9292, + "step": 44230 + }, + { + "epoch": 22.96, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 44240 + }, + { + "epoch": 22.96, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 44250 + }, + { + "epoch": 22.97, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 44260 + }, + { + "epoch": 22.97, + "learning_rate": 0.001, + "loss": 1.939, + "step": 44270 + }, + { + "epoch": 22.98, + "learning_rate": 0.001, + "loss": 1.9265, + "step": 44280 + }, + { + "epoch": 22.98, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 44290 + }, + { + "epoch": 22.99, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 44300 + }, + { + "epoch": 22.99, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 44310 + }, + { + "epoch": 23.0, + "learning_rate": 0.001, + "loss": 1.9258, + "step": 44320 + }, + { + "epoch": 23.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9413355588912964, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 77.8457, + "eval_samples_per_second": 49.521, + "eval_steps_per_second": 24.767, + "step": 44321 + }, + { + "epoch": 23.0, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 44330 + }, + { + "epoch": 23.01, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 44340 + }, + { + "epoch": 23.02, + "learning_rate": 0.001, + "loss": 1.94, + "step": 44350 + }, + { + "epoch": 23.02, + "learning_rate": 0.001, + "loss": 1.9221, + "step": 44360 + }, + { + "epoch": 23.03, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 44370 + }, + { + "epoch": 23.03, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 44380 + }, + { + "epoch": 23.04, + "learning_rate": 0.001, + "loss": 1.943, + "step": 44390 + }, + { + "epoch": 23.04, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 44400 + }, + { + "epoch": 23.05, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 44410 + }, + { + "epoch": 23.05, + "learning_rate": 0.001, + "loss": 1.947, + "step": 44420 + }, + { + "epoch": 23.06, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 44430 + }, + { + "epoch": 23.06, + "learning_rate": 0.001, + "loss": 1.963, + "step": 44440 + }, + { + "epoch": 23.07, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 44450 + }, + { + "epoch": 23.07, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 44460 + }, + { + "epoch": 23.08, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 44470 + }, + { + "epoch": 23.08, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 44480 + }, + { + "epoch": 23.09, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 44490 + }, + { + "epoch": 23.09, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 44500 + }, + { + "epoch": 23.1, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 44510 + }, + { + "epoch": 23.1, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 44520 + }, + { + "epoch": 23.11, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 44530 + }, + { + "epoch": 23.11, + "learning_rate": 0.001, + "loss": 1.9579, + "step": 44540 + }, + { + "epoch": 23.12, + "learning_rate": 0.001, + "loss": 1.9644, + "step": 44550 + }, + { + "epoch": 23.12, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 44560 + }, + { + "epoch": 23.13, + "learning_rate": 0.001, + "loss": 1.9478, + "step": 44570 + }, + { + "epoch": 23.13, + "learning_rate": 0.001, + "loss": 1.9288, + "step": 44580 + }, + { + "epoch": 23.14, + "learning_rate": 0.001, + "loss": 1.9318, + "step": 44590 + }, + { + "epoch": 23.14, + "learning_rate": 0.001, + "loss": 1.9355, + "step": 44600 + }, + { + "epoch": 23.15, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 44610 + }, + { + "epoch": 23.16, + "learning_rate": 0.001, + "loss": 1.94, + "step": 44620 + }, + { + "epoch": 23.16, + "learning_rate": 0.001, + "loss": 1.9309, + "step": 44630 + }, + { + "epoch": 23.17, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 44640 + }, + { + "epoch": 23.17, + "learning_rate": 0.001, + "loss": 1.9583, + "step": 44650 + }, + { + "epoch": 23.18, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 44660 + }, + { + "epoch": 23.18, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 44670 + }, + { + "epoch": 23.19, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 44680 + }, + { + "epoch": 23.19, + "learning_rate": 0.001, + "loss": 1.9523, + "step": 44690 + }, + { + "epoch": 23.2, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 44700 + }, + { + "epoch": 23.2, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 44710 + }, + { + "epoch": 23.21, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 44720 + }, + { + "epoch": 23.21, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 44730 + }, + { + "epoch": 23.22, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 44740 + }, + { + "epoch": 23.22, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 44750 + }, + { + "epoch": 23.23, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 44760 + }, + { + "epoch": 23.23, + "learning_rate": 0.001, + "loss": 1.961, + "step": 44770 + }, + { + "epoch": 23.24, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 44780 + }, + { + "epoch": 23.24, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 44790 + }, + { + "epoch": 23.25, + "learning_rate": 0.001, + "loss": 1.9644, + "step": 44800 + }, + { + "epoch": 23.25, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 44810 + }, + { + "epoch": 23.26, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 44820 + }, + { + "epoch": 23.26, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 44830 + }, + { + "epoch": 23.27, + "learning_rate": 0.001, + "loss": 1.942, + "step": 44840 + }, + { + "epoch": 23.27, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 44850 + }, + { + "epoch": 23.28, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 44860 + }, + { + "epoch": 23.28, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 44870 + }, + { + "epoch": 23.29, + "learning_rate": 0.001, + "loss": 1.953, + "step": 44880 + }, + { + "epoch": 23.3, + "learning_rate": 0.001, + "loss": 1.947, + "step": 44890 + }, + { + "epoch": 23.3, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 44900 + }, + { + "epoch": 23.31, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 44910 + }, + { + "epoch": 23.31, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 44920 + }, + { + "epoch": 23.32, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 44930 + }, + { + "epoch": 23.32, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 44940 + }, + { + "epoch": 23.33, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 44950 + }, + { + "epoch": 23.33, + "learning_rate": 0.001, + "loss": 1.9592, + "step": 44960 + }, + { + "epoch": 23.34, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 44970 + }, + { + "epoch": 23.34, + "learning_rate": 0.001, + "loss": 1.9588, + "step": 44980 + }, + { + "epoch": 23.35, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 44990 + }, + { + "epoch": 23.35, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 45000 + }, + { + "epoch": 23.36, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 45010 + }, + { + "epoch": 23.36, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 45020 + }, + { + "epoch": 23.37, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 45030 + }, + { + "epoch": 23.37, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 45040 + }, + { + "epoch": 23.38, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 45050 + }, + { + "epoch": 23.38, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 45060 + }, + { + "epoch": 23.39, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 45070 + }, + { + "epoch": 23.39, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 45080 + }, + { + "epoch": 23.4, + "learning_rate": 0.001, + "loss": 1.9669, + "step": 45090 + }, + { + "epoch": 23.4, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 45100 + }, + { + "epoch": 23.41, + "learning_rate": 0.001, + "loss": 1.952, + "step": 45110 + }, + { + "epoch": 23.41, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 45120 + }, + { + "epoch": 23.42, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 45130 + }, + { + "epoch": 23.43, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 45140 + }, + { + "epoch": 23.43, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 45150 + }, + { + "epoch": 23.44, + "learning_rate": 0.001, + "loss": 1.9311, + "step": 45160 + }, + { + "epoch": 23.44, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 45170 + }, + { + "epoch": 23.45, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 45180 + }, + { + "epoch": 23.45, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 45190 + }, + { + "epoch": 23.46, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 45200 + }, + { + "epoch": 23.46, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 45210 + }, + { + "epoch": 23.47, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 45220 + }, + { + "epoch": 23.47, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 45230 + }, + { + "epoch": 23.48, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 45240 + }, + { + "epoch": 23.48, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 45250 + }, + { + "epoch": 23.49, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 45260 + }, + { + "epoch": 23.49, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 45270 + }, + { + "epoch": 23.5, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 45280 + }, + { + "epoch": 23.5, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 45290 + }, + { + "epoch": 23.51, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 45300 + }, + { + "epoch": 23.51, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 45310 + }, + { + "epoch": 23.52, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 45320 + }, + { + "epoch": 23.52, + "learning_rate": 0.001, + "loss": 1.942, + "step": 45330 + }, + { + "epoch": 23.53, + "learning_rate": 0.001, + "loss": 1.938, + "step": 45340 + }, + { + "epoch": 23.53, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 45350 + }, + { + "epoch": 23.54, + "learning_rate": 0.001, + "loss": 1.9669, + "step": 45360 + }, + { + "epoch": 23.54, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 45370 + }, + { + "epoch": 23.55, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 45380 + }, + { + "epoch": 23.55, + "learning_rate": 0.001, + "loss": 1.93, + "step": 45390 + }, + { + "epoch": 23.56, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 45400 + }, + { + "epoch": 23.57, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 45410 + }, + { + "epoch": 23.57, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 45420 + }, + { + "epoch": 23.58, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 45430 + }, + { + "epoch": 23.58, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 45440 + }, + { + "epoch": 23.59, + "learning_rate": 0.001, + "loss": 1.9534, + "step": 45450 + }, + { + "epoch": 23.59, + "learning_rate": 0.001, + "loss": 1.937, + "step": 45460 + }, + { + "epoch": 23.6, + "learning_rate": 0.001, + "loss": 1.94, + "step": 45470 + }, + { + "epoch": 23.6, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 45480 + }, + { + "epoch": 23.61, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 45490 + }, + { + "epoch": 23.61, + "learning_rate": 0.001, + "loss": 1.9707, + "step": 45500 + }, + { + "epoch": 23.62, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 45510 + }, + { + "epoch": 23.62, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 45520 + }, + { + "epoch": 23.63, + "learning_rate": 0.001, + "loss": 1.9208, + "step": 45530 + }, + { + "epoch": 23.63, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 45540 + }, + { + "epoch": 23.64, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 45550 + }, + { + "epoch": 23.64, + "learning_rate": 0.001, + "loss": 1.936, + "step": 45560 + }, + { + "epoch": 23.65, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 45570 + }, + { + "epoch": 23.65, + "learning_rate": 0.001, + "loss": 1.927, + "step": 45580 + }, + { + "epoch": 23.66, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 45590 + }, + { + "epoch": 23.66, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 45600 + }, + { + "epoch": 23.67, + "learning_rate": 0.001, + "loss": 1.9574, + "step": 45610 + }, + { + "epoch": 23.67, + "learning_rate": 0.001, + "loss": 1.925, + "step": 45620 + }, + { + "epoch": 23.68, + "learning_rate": 0.001, + "loss": 1.9284, + "step": 45630 + }, + { + "epoch": 23.68, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 45640 + }, + { + "epoch": 23.69, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 45650 + }, + { + "epoch": 23.69, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 45660 + }, + { + "epoch": 23.7, + "learning_rate": 0.001, + "loss": 1.9181, + "step": 45670 + }, + { + "epoch": 23.71, + "learning_rate": 0.001, + "loss": 1.9674, + "step": 45680 + }, + { + "epoch": 23.71, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 45690 + }, + { + "epoch": 23.72, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 45700 + }, + { + "epoch": 23.72, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 45710 + }, + { + "epoch": 23.73, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 45720 + }, + { + "epoch": 23.73, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 45730 + }, + { + "epoch": 23.74, + "learning_rate": 0.001, + "loss": 1.9227, + "step": 45740 + }, + { + "epoch": 23.74, + "learning_rate": 0.001, + "loss": 1.9088, + "step": 45750 + }, + { + "epoch": 23.75, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 45760 + }, + { + "epoch": 23.75, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 45770 + }, + { + "epoch": 23.76, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 45780 + }, + { + "epoch": 23.76, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 45790 + }, + { + "epoch": 23.77, + "learning_rate": 0.001, + "loss": 1.9665, + "step": 45800 + }, + { + "epoch": 23.77, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 45810 + }, + { + "epoch": 23.78, + "learning_rate": 0.001, + "loss": 1.9212, + "step": 45820 + }, + { + "epoch": 23.78, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 45830 + }, + { + "epoch": 23.79, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 45840 + }, + { + "epoch": 23.79, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 45850 + }, + { + "epoch": 23.8, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 45860 + }, + { + "epoch": 23.8, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 45870 + }, + { + "epoch": 23.81, + "learning_rate": 0.001, + "loss": 1.9695, + "step": 45880 + }, + { + "epoch": 23.81, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 45890 + }, + { + "epoch": 23.82, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 45900 + }, + { + "epoch": 23.82, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 45910 + }, + { + "epoch": 23.83, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 45920 + }, + { + "epoch": 23.83, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 45930 + }, + { + "epoch": 23.84, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 45940 + }, + { + "epoch": 23.85, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 45950 + }, + { + "epoch": 23.85, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 45960 + }, + { + "epoch": 23.86, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 45970 + }, + { + "epoch": 23.86, + "learning_rate": 0.001, + "loss": 1.9546, + "step": 45980 + }, + { + "epoch": 23.87, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 45990 + }, + { + "epoch": 23.87, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 46000 + }, + { + "epoch": 23.88, + "learning_rate": 0.001, + "loss": 1.9097, + "step": 46010 + }, + { + "epoch": 23.88, + "learning_rate": 0.001, + "loss": 1.9586, + "step": 46020 + }, + { + "epoch": 23.89, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 46030 + }, + { + "epoch": 23.89, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 46040 + }, + { + "epoch": 23.9, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 46050 + }, + { + "epoch": 23.9, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 46060 + }, + { + "epoch": 23.91, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 46070 + }, + { + "epoch": 23.91, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 46080 + }, + { + "epoch": 23.92, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 46090 + }, + { + "epoch": 23.92, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 46100 + }, + { + "epoch": 23.93, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 46110 + }, + { + "epoch": 23.93, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 46120 + }, + { + "epoch": 23.94, + "learning_rate": 0.001, + "loss": 1.946, + "step": 46130 + }, + { + "epoch": 23.94, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 46140 + }, + { + "epoch": 23.95, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 46150 + }, + { + "epoch": 23.95, + "learning_rate": 0.001, + "loss": 1.9197, + "step": 46160 + }, + { + "epoch": 23.96, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 46170 + }, + { + "epoch": 23.96, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 46180 + }, + { + "epoch": 23.97, + "learning_rate": 0.001, + "loss": 1.9727, + "step": 46190 + }, + { + "epoch": 23.98, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 46200 + }, + { + "epoch": 23.98, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 46210 + }, + { + "epoch": 23.99, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 46220 + }, + { + "epoch": 23.99, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 46230 + }, + { + "epoch": 24.0, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 46240 + }, + { + "epoch": 24.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9421918392181396, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 78.2846, + "eval_samples_per_second": 49.243, + "eval_steps_per_second": 24.628, + "step": 46248 + }, + { + "epoch": 24.0, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 46250 + }, + { + "epoch": 24.01, + "learning_rate": 0.001, + "loss": 1.942, + "step": 46260 + }, + { + "epoch": 24.01, + "learning_rate": 0.001, + "loss": 1.9655, + "step": 46270 + }, + { + "epoch": 24.02, + "learning_rate": 0.001, + "loss": 1.934, + "step": 46280 + }, + { + "epoch": 24.02, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 46290 + }, + { + "epoch": 24.03, + "learning_rate": 0.001, + "loss": 1.9287, + "step": 46300 + }, + { + "epoch": 24.03, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 46310 + }, + { + "epoch": 24.04, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 46320 + }, + { + "epoch": 24.04, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 46330 + }, + { + "epoch": 24.05, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 46340 + }, + { + "epoch": 24.05, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 46350 + }, + { + "epoch": 24.06, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 46360 + }, + { + "epoch": 24.06, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 46370 + }, + { + "epoch": 24.07, + "learning_rate": 0.001, + "loss": 1.9582, + "step": 46380 + }, + { + "epoch": 24.07, + "learning_rate": 0.001, + "loss": 1.946, + "step": 46390 + }, + { + "epoch": 24.08, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 46400 + }, + { + "epoch": 24.08, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 46410 + }, + { + "epoch": 24.09, + "learning_rate": 0.001, + "loss": 1.9423, + "step": 46420 + }, + { + "epoch": 24.09, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 46430 + }, + { + "epoch": 24.1, + "learning_rate": 0.001, + "loss": 1.947, + "step": 46440 + }, + { + "epoch": 24.1, + "learning_rate": 0.001, + "loss": 1.9282, + "step": 46450 + }, + { + "epoch": 24.11, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 46460 + }, + { + "epoch": 24.12, + "learning_rate": 0.001, + "loss": 1.937, + "step": 46470 + }, + { + "epoch": 24.12, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 46480 + }, + { + "epoch": 24.13, + "learning_rate": 0.001, + "loss": 1.9373, + "step": 46490 + }, + { + "epoch": 24.13, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 46500 + }, + { + "epoch": 24.14, + "learning_rate": 0.001, + "loss": 1.9472, + "step": 46510 + }, + { + "epoch": 24.14, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 46520 + }, + { + "epoch": 24.15, + "learning_rate": 0.001, + "loss": 1.9253, + "step": 46530 + }, + { + "epoch": 24.15, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 46540 + }, + { + "epoch": 24.16, + "learning_rate": 0.001, + "loss": 1.9552, + "step": 46550 + }, + { + "epoch": 24.16, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 46560 + }, + { + "epoch": 24.17, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 46570 + }, + { + "epoch": 24.17, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 46580 + }, + { + "epoch": 24.18, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 46590 + }, + { + "epoch": 24.18, + "learning_rate": 0.001, + "loss": 1.9353, + "step": 46600 + }, + { + "epoch": 24.19, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 46610 + }, + { + "epoch": 24.19, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 46620 + }, + { + "epoch": 24.2, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 46630 + }, + { + "epoch": 24.2, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 46640 + }, + { + "epoch": 24.21, + "learning_rate": 0.001, + "loss": 1.9627, + "step": 46650 + }, + { + "epoch": 24.21, + "learning_rate": 0.001, + "loss": 1.9254, + "step": 46660 + }, + { + "epoch": 24.22, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 46670 + }, + { + "epoch": 24.22, + "learning_rate": 0.001, + "loss": 1.9329, + "step": 46680 + }, + { + "epoch": 24.23, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 46690 + }, + { + "epoch": 24.23, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 46700 + }, + { + "epoch": 24.24, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 46710 + }, + { + "epoch": 24.24, + "learning_rate": 0.001, + "loss": 1.9642, + "step": 46720 + }, + { + "epoch": 24.25, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 46730 + }, + { + "epoch": 24.26, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 46740 + }, + { + "epoch": 24.26, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 46750 + }, + { + "epoch": 24.27, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 46760 + }, + { + "epoch": 24.27, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 46770 + }, + { + "epoch": 24.28, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 46780 + }, + { + "epoch": 24.28, + "learning_rate": 0.001, + "loss": 1.955, + "step": 46790 + }, + { + "epoch": 24.29, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 46800 + }, + { + "epoch": 24.29, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 46810 + }, + { + "epoch": 24.3, + "learning_rate": 0.001, + "loss": 1.9227, + "step": 46820 + }, + { + "epoch": 24.3, + "learning_rate": 0.001, + "loss": 1.9152, + "step": 46830 + }, + { + "epoch": 24.31, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 46840 + }, + { + "epoch": 24.31, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 46850 + }, + { + "epoch": 24.32, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 46860 + }, + { + "epoch": 24.32, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 46870 + }, + { + "epoch": 24.33, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 46880 + }, + { + "epoch": 24.33, + "learning_rate": 0.001, + "loss": 1.951, + "step": 46890 + }, + { + "epoch": 24.34, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 46900 + }, + { + "epoch": 24.34, + "learning_rate": 0.001, + "loss": 1.953, + "step": 46910 + }, + { + "epoch": 24.35, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 46920 + }, + { + "epoch": 24.35, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 46930 + }, + { + "epoch": 24.36, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 46940 + }, + { + "epoch": 24.36, + "learning_rate": 0.001, + "loss": 1.9588, + "step": 46950 + }, + { + "epoch": 24.37, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 46960 + }, + { + "epoch": 24.37, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 46970 + }, + { + "epoch": 24.38, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 46980 + }, + { + "epoch": 24.39, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 46990 + }, + { + "epoch": 24.39, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 47000 + }, + { + "epoch": 24.4, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 47010 + }, + { + "epoch": 24.4, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 47020 + }, + { + "epoch": 24.41, + "learning_rate": 0.001, + "loss": 1.9695, + "step": 47030 + }, + { + "epoch": 24.41, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 47040 + }, + { + "epoch": 24.42, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 47050 + }, + { + "epoch": 24.42, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 47060 + }, + { + "epoch": 24.43, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 47070 + }, + { + "epoch": 24.43, + "learning_rate": 0.001, + "loss": 1.9611, + "step": 47080 + }, + { + "epoch": 24.44, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 47090 + }, + { + "epoch": 24.44, + "learning_rate": 0.001, + "loss": 1.927, + "step": 47100 + }, + { + "epoch": 24.45, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 47110 + }, + { + "epoch": 24.45, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 47120 + }, + { + "epoch": 24.46, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 47130 + }, + { + "epoch": 24.46, + "learning_rate": 0.001, + "loss": 1.9545, + "step": 47140 + }, + { + "epoch": 24.47, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 47150 + }, + { + "epoch": 24.47, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 47160 + }, + { + "epoch": 24.48, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 47170 + }, + { + "epoch": 24.48, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 47180 + }, + { + "epoch": 24.49, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 47190 + }, + { + "epoch": 24.49, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 47200 + }, + { + "epoch": 24.5, + "learning_rate": 0.001, + "loss": 1.9511, + "step": 47210 + }, + { + "epoch": 24.5, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 47220 + }, + { + "epoch": 24.51, + "learning_rate": 0.001, + "loss": 1.9518, + "step": 47230 + }, + { + "epoch": 24.51, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 47240 + }, + { + "epoch": 24.52, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 47250 + }, + { + "epoch": 24.53, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 47260 + }, + { + "epoch": 24.53, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 47270 + }, + { + "epoch": 24.54, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 47280 + }, + { + "epoch": 24.54, + "learning_rate": 0.001, + "loss": 1.9097, + "step": 47290 + }, + { + "epoch": 24.55, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 47300 + }, + { + "epoch": 24.55, + "learning_rate": 0.001, + "loss": 1.9605, + "step": 47310 + }, + { + "epoch": 24.56, + "learning_rate": 0.001, + "loss": 1.9664, + "step": 47320 + }, + { + "epoch": 24.56, + "learning_rate": 0.001, + "loss": 1.9291, + "step": 47330 + }, + { + "epoch": 24.57, + "learning_rate": 0.001, + "loss": 1.935, + "step": 47340 + }, + { + "epoch": 24.57, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 47350 + }, + { + "epoch": 24.58, + "learning_rate": 0.001, + "loss": 1.957, + "step": 47360 + }, + { + "epoch": 24.58, + "learning_rate": 0.001, + "loss": 1.9084, + "step": 47370 + }, + { + "epoch": 24.59, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 47380 + }, + { + "epoch": 24.59, + "learning_rate": 0.001, + "loss": 1.928, + "step": 47390 + }, + { + "epoch": 24.6, + "learning_rate": 0.001, + "loss": 1.911, + "step": 47400 + }, + { + "epoch": 24.6, + "learning_rate": 0.001, + "loss": 1.9681, + "step": 47410 + }, + { + "epoch": 24.61, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 47420 + }, + { + "epoch": 24.61, + "learning_rate": 0.001, + "loss": 1.964, + "step": 47430 + }, + { + "epoch": 24.62, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 47440 + }, + { + "epoch": 24.62, + "learning_rate": 0.001, + "loss": 1.9145, + "step": 47450 + }, + { + "epoch": 24.63, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 47460 + }, + { + "epoch": 24.63, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 47470 + }, + { + "epoch": 24.64, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 47480 + }, + { + "epoch": 24.64, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 47490 + }, + { + "epoch": 24.65, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 47500 + }, + { + "epoch": 24.65, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 47510 + }, + { + "epoch": 24.66, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 47520 + }, + { + "epoch": 24.67, + "learning_rate": 0.001, + "loss": 1.9543, + "step": 47530 + }, + { + "epoch": 24.67, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 47540 + }, + { + "epoch": 24.68, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 47550 + }, + { + "epoch": 24.68, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 47560 + }, + { + "epoch": 24.69, + "learning_rate": 0.001, + "loss": 1.9689, + "step": 47570 + }, + { + "epoch": 24.69, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 47580 + }, + { + "epoch": 24.7, + "learning_rate": 0.001, + "loss": 1.9293, + "step": 47590 + }, + { + "epoch": 24.7, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 47600 + }, + { + "epoch": 24.71, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 47610 + }, + { + "epoch": 24.71, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 47620 + }, + { + "epoch": 24.72, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 47630 + }, + { + "epoch": 24.72, + "learning_rate": 0.001, + "loss": 1.9379, + "step": 47640 + }, + { + "epoch": 24.73, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 47650 + }, + { + "epoch": 24.73, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 47660 + }, + { + "epoch": 24.74, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 47670 + }, + { + "epoch": 24.74, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 47680 + }, + { + "epoch": 24.75, + "learning_rate": 0.001, + "loss": 1.9308, + "step": 47690 + }, + { + "epoch": 24.75, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 47700 + }, + { + "epoch": 24.76, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 47710 + }, + { + "epoch": 24.76, + "learning_rate": 0.001, + "loss": 1.945, + "step": 47720 + }, + { + "epoch": 24.77, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 47730 + }, + { + "epoch": 24.77, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 47740 + }, + { + "epoch": 24.78, + "learning_rate": 0.001, + "loss": 1.9685, + "step": 47750 + }, + { + "epoch": 24.78, + "learning_rate": 0.001, + "loss": 1.9606, + "step": 47760 + }, + { + "epoch": 24.79, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 47770 + }, + { + "epoch": 24.8, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 47780 + }, + { + "epoch": 24.8, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 47790 + }, + { + "epoch": 24.81, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 47800 + }, + { + "epoch": 24.81, + "learning_rate": 0.001, + "loss": 1.944, + "step": 47810 + }, + { + "epoch": 24.82, + "learning_rate": 0.001, + "loss": 1.926, + "step": 47820 + }, + { + "epoch": 24.82, + "learning_rate": 0.001, + "loss": 1.9495, + "step": 47830 + }, + { + "epoch": 24.83, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 47840 + }, + { + "epoch": 24.83, + "learning_rate": 0.001, + "loss": 1.9464, + "step": 47850 + }, + { + "epoch": 24.84, + "learning_rate": 0.001, + "loss": 1.938, + "step": 47860 + }, + { + "epoch": 24.84, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 47870 + }, + { + "epoch": 24.85, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 47880 + }, + { + "epoch": 24.85, + "learning_rate": 0.001, + "loss": 1.9514, + "step": 47890 + }, + { + "epoch": 24.86, + "learning_rate": 0.001, + "loss": 1.9563, + "step": 47900 + }, + { + "epoch": 24.86, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 47910 + }, + { + "epoch": 24.87, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 47920 + }, + { + "epoch": 24.87, + "learning_rate": 0.001, + "loss": 1.947, + "step": 47930 + }, + { + "epoch": 24.88, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 47940 + }, + { + "epoch": 24.88, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 47950 + }, + { + "epoch": 24.89, + "learning_rate": 0.001, + "loss": 1.9346, + "step": 47960 + }, + { + "epoch": 24.89, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 47970 + }, + { + "epoch": 24.9, + "learning_rate": 0.001, + "loss": 1.935, + "step": 47980 + }, + { + "epoch": 24.9, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 47990 + }, + { + "epoch": 24.91, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 48000 + }, + { + "epoch": 24.91, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 48010 + }, + { + "epoch": 24.92, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 48020 + }, + { + "epoch": 24.92, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 48030 + }, + { + "epoch": 24.93, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 48040 + }, + { + "epoch": 24.94, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 48050 + }, + { + "epoch": 24.94, + "learning_rate": 0.001, + "loss": 1.9481, + "step": 48060 + }, + { + "epoch": 24.95, + "learning_rate": 0.001, + "loss": 1.9422, + "step": 48070 + }, + { + "epoch": 24.95, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 48080 + }, + { + "epoch": 24.96, + "learning_rate": 0.001, + "loss": 1.9488, + "step": 48090 + }, + { + "epoch": 24.96, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 48100 + }, + { + "epoch": 24.97, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 48110 + }, + { + "epoch": 24.97, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 48120 + }, + { + "epoch": 24.98, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 48130 + }, + { + "epoch": 24.98, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 48140 + }, + { + "epoch": 24.99, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 48150 + }, + { + "epoch": 24.99, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 48160 + }, + { + "epoch": 25.0, + "learning_rate": 0.001, + "loss": 1.948, + "step": 48170 + }, + { + "epoch": 25.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9422612190246582, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 76.5041, + "eval_samples_per_second": 50.389, + "eval_steps_per_second": 25.201, + "step": 48175 + }, + { + "epoch": 25.0, + "learning_rate": 0.001, + "loss": 1.9519, + "step": 48180 + }, + { + "epoch": 25.01, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 48190 + }, + { + "epoch": 25.01, + "learning_rate": 0.001, + "loss": 1.9273, + "step": 48200 + }, + { + "epoch": 25.02, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 48210 + }, + { + "epoch": 25.02, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 48220 + }, + { + "epoch": 25.03, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 48230 + }, + { + "epoch": 25.03, + "learning_rate": 0.001, + "loss": 1.9252, + "step": 48240 + }, + { + "epoch": 25.04, + "learning_rate": 0.001, + "loss": 1.9717, + "step": 48250 + }, + { + "epoch": 25.04, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 48260 + }, + { + "epoch": 25.05, + "learning_rate": 0.001, + "loss": 1.9236, + "step": 48270 + }, + { + "epoch": 25.05, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 48280 + }, + { + "epoch": 25.06, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 48290 + }, + { + "epoch": 25.06, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 48300 + }, + { + "epoch": 25.07, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 48310 + }, + { + "epoch": 25.08, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 48320 + }, + { + "epoch": 25.08, + "learning_rate": 0.001, + "loss": 1.94, + "step": 48330 + }, + { + "epoch": 25.09, + "learning_rate": 0.001, + "loss": 1.9304, + "step": 48340 + }, + { + "epoch": 25.09, + "learning_rate": 0.001, + "loss": 1.9168, + "step": 48350 + }, + { + "epoch": 25.1, + "learning_rate": 0.001, + "loss": 1.9347, + "step": 48360 + }, + { + "epoch": 25.1, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 48370 + }, + { + "epoch": 25.11, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 48380 + }, + { + "epoch": 25.11, + "learning_rate": 0.001, + "loss": 1.9584, + "step": 48390 + }, + { + "epoch": 25.12, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 48400 + }, + { + "epoch": 25.12, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 48410 + }, + { + "epoch": 25.13, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 48420 + }, + { + "epoch": 25.13, + "learning_rate": 0.001, + "loss": 1.9504, + "step": 48430 + }, + { + "epoch": 25.14, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 48440 + }, + { + "epoch": 25.14, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 48450 + }, + { + "epoch": 25.15, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 48460 + }, + { + "epoch": 25.15, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 48470 + }, + { + "epoch": 25.16, + "learning_rate": 0.001, + "loss": 1.9302, + "step": 48480 + }, + { + "epoch": 25.16, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 48490 + }, + { + "epoch": 25.17, + "learning_rate": 0.001, + "loss": 1.958, + "step": 48500 + }, + { + "epoch": 25.17, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 48510 + }, + { + "epoch": 25.18, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 48520 + }, + { + "epoch": 25.18, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 48530 + }, + { + "epoch": 25.19, + "learning_rate": 0.001, + "loss": 1.9473, + "step": 48540 + }, + { + "epoch": 25.19, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 48550 + }, + { + "epoch": 25.2, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 48560 + }, + { + "epoch": 25.2, + "learning_rate": 0.001, + "loss": 1.947, + "step": 48570 + }, + { + "epoch": 25.21, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 48580 + }, + { + "epoch": 25.22, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 48590 + }, + { + "epoch": 25.22, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 48600 + }, + { + "epoch": 25.23, + "learning_rate": 0.001, + "loss": 1.944, + "step": 48610 + }, + { + "epoch": 25.23, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 48620 + }, + { + "epoch": 25.24, + "learning_rate": 0.001, + "loss": 1.917, + "step": 48630 + }, + { + "epoch": 25.24, + "learning_rate": 0.001, + "loss": 1.9363, + "step": 48640 + }, + { + "epoch": 25.25, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 48650 + }, + { + "epoch": 25.25, + "learning_rate": 0.001, + "loss": 1.9357, + "step": 48660 + }, + { + "epoch": 25.26, + "learning_rate": 0.001, + "loss": 1.9516, + "step": 48670 + }, + { + "epoch": 25.26, + "learning_rate": 0.001, + "loss": 1.9313, + "step": 48680 + }, + { + "epoch": 25.27, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 48690 + }, + { + "epoch": 25.27, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 48700 + }, + { + "epoch": 25.28, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 48710 + }, + { + "epoch": 25.28, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 48720 + }, + { + "epoch": 25.29, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 48730 + }, + { + "epoch": 25.29, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 48740 + }, + { + "epoch": 25.3, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 48750 + }, + { + "epoch": 25.3, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 48760 + }, + { + "epoch": 25.31, + "learning_rate": 0.001, + "loss": 1.951, + "step": 48770 + }, + { + "epoch": 25.31, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 48780 + }, + { + "epoch": 25.32, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 48790 + }, + { + "epoch": 25.32, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 48800 + }, + { + "epoch": 25.33, + "learning_rate": 0.001, + "loss": 1.9409, + "step": 48810 + }, + { + "epoch": 25.33, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 48820 + }, + { + "epoch": 25.34, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 48830 + }, + { + "epoch": 25.35, + "learning_rate": 0.001, + "loss": 1.933, + "step": 48840 + }, + { + "epoch": 25.35, + "learning_rate": 0.001, + "loss": 1.9489, + "step": 48850 + }, + { + "epoch": 25.36, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 48860 + }, + { + "epoch": 25.36, + "learning_rate": 0.001, + "loss": 1.9319, + "step": 48870 + }, + { + "epoch": 25.37, + "learning_rate": 0.001, + "loss": 1.955, + "step": 48880 + }, + { + "epoch": 25.37, + "learning_rate": 0.001, + "loss": 1.9463, + "step": 48890 + }, + { + "epoch": 25.38, + "learning_rate": 0.001, + "loss": 1.943, + "step": 48900 + }, + { + "epoch": 25.38, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 48910 + }, + { + "epoch": 25.39, + "learning_rate": 0.001, + "loss": 1.929, + "step": 48920 + }, + { + "epoch": 25.39, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 48930 + }, + { + "epoch": 25.4, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 48940 + }, + { + "epoch": 25.4, + "learning_rate": 0.001, + "loss": 1.9562, + "step": 48950 + }, + { + "epoch": 25.41, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 48960 + }, + { + "epoch": 25.41, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 48970 + }, + { + "epoch": 25.42, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 48980 + }, + { + "epoch": 25.42, + "learning_rate": 0.001, + "loss": 1.943, + "step": 48990 + }, + { + "epoch": 25.43, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 49000 + }, + { + "epoch": 25.43, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 49010 + }, + { + "epoch": 25.44, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 49020 + }, + { + "epoch": 25.44, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 49030 + }, + { + "epoch": 25.45, + "learning_rate": 0.001, + "loss": 1.9157, + "step": 49040 + }, + { + "epoch": 25.45, + "learning_rate": 0.001, + "loss": 1.9717, + "step": 49050 + }, + { + "epoch": 25.46, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 49060 + }, + { + "epoch": 25.46, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 49070 + }, + { + "epoch": 25.47, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 49080 + }, + { + "epoch": 25.47, + "learning_rate": 0.001, + "loss": 1.9125, + "step": 49090 + }, + { + "epoch": 25.48, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 49100 + }, + { + "epoch": 25.49, + "learning_rate": 0.001, + "loss": 1.9486, + "step": 49110 + }, + { + "epoch": 25.49, + "learning_rate": 0.001, + "loss": 1.9658, + "step": 49120 + }, + { + "epoch": 25.5, + "learning_rate": 0.001, + "loss": 1.9234, + "step": 49130 + }, + { + "epoch": 25.5, + "learning_rate": 0.001, + "loss": 1.9501, + "step": 49140 + }, + { + "epoch": 25.51, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 49150 + }, + { + "epoch": 25.51, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 49160 + }, + { + "epoch": 25.52, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 49170 + }, + { + "epoch": 25.52, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 49180 + }, + { + "epoch": 25.53, + "learning_rate": 0.001, + "loss": 1.9198, + "step": 49190 + }, + { + "epoch": 25.53, + "learning_rate": 0.001, + "loss": 1.9265, + "step": 49200 + }, + { + "epoch": 25.54, + "learning_rate": 0.001, + "loss": 1.947, + "step": 49210 + }, + { + "epoch": 25.54, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 49220 + }, + { + "epoch": 25.55, + "learning_rate": 0.001, + "loss": 1.9581, + "step": 49230 + }, + { + "epoch": 25.55, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 49240 + }, + { + "epoch": 25.56, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 49250 + }, + { + "epoch": 25.56, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 49260 + }, + { + "epoch": 25.57, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 49270 + }, + { + "epoch": 25.57, + "learning_rate": 0.001, + "loss": 1.951, + "step": 49280 + }, + { + "epoch": 25.58, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 49290 + }, + { + "epoch": 25.58, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 49300 + }, + { + "epoch": 25.59, + "learning_rate": 0.001, + "loss": 1.94, + "step": 49310 + }, + { + "epoch": 25.59, + "learning_rate": 0.001, + "loss": 1.9301, + "step": 49320 + }, + { + "epoch": 25.6, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 49330 + }, + { + "epoch": 25.6, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 49340 + }, + { + "epoch": 25.61, + "learning_rate": 0.001, + "loss": 1.9393, + "step": 49350 + }, + { + "epoch": 25.61, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 49360 + }, + { + "epoch": 25.62, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 49370 + }, + { + "epoch": 25.63, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 49380 + }, + { + "epoch": 25.63, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 49390 + }, + { + "epoch": 25.64, + "learning_rate": 0.001, + "loss": 1.9467, + "step": 49400 + }, + { + "epoch": 25.64, + "learning_rate": 0.001, + "loss": 1.9497, + "step": 49410 + }, + { + "epoch": 25.65, + "learning_rate": 0.001, + "loss": 1.9777, + "step": 49420 + }, + { + "epoch": 25.65, + "learning_rate": 0.001, + "loss": 1.97, + "step": 49430 + }, + { + "epoch": 25.66, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 49440 + }, + { + "epoch": 25.66, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 49450 + }, + { + "epoch": 25.67, + "learning_rate": 0.001, + "loss": 1.9438, + "step": 49460 + }, + { + "epoch": 25.67, + "learning_rate": 0.001, + "loss": 1.9277, + "step": 49470 + }, + { + "epoch": 25.68, + "learning_rate": 0.001, + "loss": 1.9521, + "step": 49480 + }, + { + "epoch": 25.68, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 49490 + }, + { + "epoch": 25.69, + "learning_rate": 0.001, + "loss": 1.9485, + "step": 49500 + }, + { + "epoch": 25.69, + "learning_rate": 0.001, + "loss": 1.95, + "step": 49510 + }, + { + "epoch": 25.7, + "learning_rate": 0.001, + "loss": 1.927, + "step": 49520 + }, + { + "epoch": 25.7, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 49530 + }, + { + "epoch": 25.71, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 49540 + }, + { + "epoch": 25.71, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 49550 + }, + { + "epoch": 25.72, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 49560 + }, + { + "epoch": 25.72, + "learning_rate": 0.001, + "loss": 1.9285, + "step": 49570 + }, + { + "epoch": 25.73, + "learning_rate": 0.001, + "loss": 1.9433, + "step": 49580 + }, + { + "epoch": 25.73, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 49590 + }, + { + "epoch": 25.74, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 49600 + }, + { + "epoch": 25.74, + "learning_rate": 0.001, + "loss": 1.9596, + "step": 49610 + }, + { + "epoch": 25.75, + "learning_rate": 0.001, + "loss": 1.9631, + "step": 49620 + }, + { + "epoch": 25.76, + "learning_rate": 0.001, + "loss": 1.9388, + "step": 49630 + }, + { + "epoch": 25.76, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 49640 + }, + { + "epoch": 25.77, + "learning_rate": 0.001, + "loss": 1.9332, + "step": 49650 + }, + { + "epoch": 25.77, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 49660 + }, + { + "epoch": 25.78, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 49670 + }, + { + "epoch": 25.78, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 49680 + }, + { + "epoch": 25.79, + "learning_rate": 0.001, + "loss": 1.9576, + "step": 49690 + }, + { + "epoch": 25.79, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 49700 + }, + { + "epoch": 25.8, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 49710 + }, + { + "epoch": 25.8, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 49720 + }, + { + "epoch": 25.81, + "learning_rate": 0.001, + "loss": 1.951, + "step": 49730 + }, + { + "epoch": 25.81, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 49740 + }, + { + "epoch": 25.82, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 49750 + }, + { + "epoch": 25.82, + "learning_rate": 0.001, + "loss": 1.9494, + "step": 49760 + }, + { + "epoch": 25.83, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 49770 + }, + { + "epoch": 25.83, + "learning_rate": 0.001, + "loss": 1.9303, + "step": 49780 + }, + { + "epoch": 25.84, + "learning_rate": 0.001, + "loss": 1.9582, + "step": 49790 + }, + { + "epoch": 25.84, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 49800 + }, + { + "epoch": 25.85, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 49810 + }, + { + "epoch": 25.85, + "learning_rate": 0.001, + "loss": 1.949, + "step": 49820 + }, + { + "epoch": 25.86, + "learning_rate": 0.001, + "loss": 1.9626, + "step": 49830 + }, + { + "epoch": 25.86, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 49840 + }, + { + "epoch": 25.87, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 49850 + }, + { + "epoch": 25.87, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 49860 + }, + { + "epoch": 25.88, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 49870 + }, + { + "epoch": 25.88, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 49880 + }, + { + "epoch": 25.89, + "learning_rate": 0.001, + "loss": 1.9375, + "step": 49890 + }, + { + "epoch": 25.9, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 49900 + }, + { + "epoch": 25.9, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 49910 + }, + { + "epoch": 25.91, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 49920 + }, + { + "epoch": 25.91, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 49930 + }, + { + "epoch": 25.92, + "learning_rate": 0.001, + "loss": 1.9657, + "step": 49940 + }, + { + "epoch": 25.92, + "learning_rate": 0.001, + "loss": 1.9307, + "step": 49950 + }, + { + "epoch": 25.93, + "learning_rate": 0.001, + "loss": 1.9336, + "step": 49960 + }, + { + "epoch": 25.93, + "learning_rate": 0.001, + "loss": 1.941, + "step": 49970 + }, + { + "epoch": 25.94, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 49980 + }, + { + "epoch": 25.94, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 49990 + }, + { + "epoch": 25.95, + "learning_rate": 0.001, + "loss": 1.9216, + "step": 50000 + }, + { + "epoch": 25.95, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 50010 + }, + { + "epoch": 25.96, + "learning_rate": 0.001, + "loss": 1.9561, + "step": 50020 + }, + { + "epoch": 25.96, + "learning_rate": 0.001, + "loss": 1.9466, + "step": 50030 + }, + { + "epoch": 25.97, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 50040 + }, + { + "epoch": 25.97, + "learning_rate": 0.001, + "loss": 1.9296, + "step": 50050 + }, + { + "epoch": 25.98, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 50060 + }, + { + "epoch": 25.98, + "learning_rate": 0.001, + "loss": 1.9245, + "step": 50070 + }, + { + "epoch": 25.99, + "learning_rate": 0.001, + "loss": 1.9628, + "step": 50080 + }, + { + "epoch": 25.99, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 50090 + }, + { + "epoch": 26.0, + "learning_rate": 0.001, + "loss": 1.918, + "step": 50100 + }, + { + "epoch": 26.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9415614604949951, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 101.3825, + "eval_samples_per_second": 38.024, + "eval_steps_per_second": 19.017, + "step": 50102 + }, + { + "epoch": 26.0, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 50110 + }, + { + "epoch": 26.01, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 50120 + }, + { + "epoch": 26.01, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 50130 + }, + { + "epoch": 26.02, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 50140 + }, + { + "epoch": 26.02, + "learning_rate": 0.001, + "loss": 1.957, + "step": 50150 + }, + { + "epoch": 26.03, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 50160 + }, + { + "epoch": 26.04, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 50170 + }, + { + "epoch": 26.04, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 50180 + }, + { + "epoch": 26.05, + "learning_rate": 0.001, + "loss": 1.9387, + "step": 50190 + }, + { + "epoch": 26.05, + "learning_rate": 0.001, + "loss": 1.9439, + "step": 50200 + }, + { + "epoch": 26.06, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 50210 + }, + { + "epoch": 26.06, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 50220 + }, + { + "epoch": 26.07, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 50230 + }, + { + "epoch": 26.07, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 50240 + }, + { + "epoch": 26.08, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 50250 + }, + { + "epoch": 26.08, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 50260 + }, + { + "epoch": 26.09, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 50270 + }, + { + "epoch": 26.09, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 50280 + }, + { + "epoch": 26.1, + "learning_rate": 0.001, + "loss": 1.9922, + "step": 50290 + }, + { + "epoch": 26.1, + "learning_rate": 0.001, + "loss": 1.9509, + "step": 50300 + }, + { + "epoch": 26.11, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 50310 + }, + { + "epoch": 26.11, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 50320 + }, + { + "epoch": 26.12, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 50330 + }, + { + "epoch": 26.12, + "learning_rate": 0.001, + "loss": 1.954, + "step": 50340 + }, + { + "epoch": 26.13, + "learning_rate": 0.001, + "loss": 1.9539, + "step": 50350 + }, + { + "epoch": 26.13, + "learning_rate": 0.001, + "loss": 1.9292, + "step": 50360 + }, + { + "epoch": 26.14, + "learning_rate": 0.001, + "loss": 1.9461, + "step": 50370 + }, + { + "epoch": 26.14, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 50380 + }, + { + "epoch": 26.15, + "learning_rate": 0.001, + "loss": 1.9492, + "step": 50390 + }, + { + "epoch": 26.15, + "learning_rate": 0.001, + "loss": 1.9608, + "step": 50400 + }, + { + "epoch": 26.16, + "learning_rate": 0.001, + "loss": 1.9359, + "step": 50410 + }, + { + "epoch": 26.17, + "learning_rate": 0.001, + "loss": 1.9386, + "step": 50420 + }, + { + "epoch": 26.17, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 50430 + }, + { + "epoch": 26.18, + "learning_rate": 0.001, + "loss": 1.9506, + "step": 50440 + }, + { + "epoch": 26.18, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 50450 + }, + { + "epoch": 26.19, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 50460 + }, + { + "epoch": 26.19, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 50470 + }, + { + "epoch": 26.2, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 50480 + }, + { + "epoch": 26.2, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 50490 + }, + { + "epoch": 26.21, + "learning_rate": 0.001, + "loss": 1.9326, + "step": 50500 + }, + { + "epoch": 26.21, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 50510 + }, + { + "epoch": 26.22, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 50520 + }, + { + "epoch": 26.22, + "learning_rate": 0.001, + "loss": 1.9789, + "step": 50530 + }, + { + "epoch": 26.23, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 50540 + }, + { + "epoch": 26.23, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 50550 + }, + { + "epoch": 26.24, + "learning_rate": 0.001, + "loss": 1.938, + "step": 50560 + }, + { + "epoch": 26.24, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 50570 + }, + { + "epoch": 26.25, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 50580 + }, + { + "epoch": 26.25, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 50590 + }, + { + "epoch": 26.26, + "learning_rate": 0.001, + "loss": 1.9361, + "step": 50600 + }, + { + "epoch": 26.26, + "learning_rate": 0.001, + "loss": 1.9498, + "step": 50610 + }, + { + "epoch": 26.27, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 50620 + }, + { + "epoch": 26.27, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 50630 + }, + { + "epoch": 26.28, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 50640 + }, + { + "epoch": 26.28, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 50650 + }, + { + "epoch": 26.29, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 50660 + }, + { + "epoch": 26.29, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 50670 + }, + { + "epoch": 26.3, + "learning_rate": 0.001, + "loss": 1.9406, + "step": 50680 + }, + { + "epoch": 26.31, + "learning_rate": 0.001, + "loss": 1.9235, + "step": 50690 + }, + { + "epoch": 26.31, + "learning_rate": 0.001, + "loss": 1.9372, + "step": 50700 + }, + { + "epoch": 26.32, + "learning_rate": 0.001, + "loss": 1.9578, + "step": 50710 + }, + { + "epoch": 26.32, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 50720 + }, + { + "epoch": 26.33, + "learning_rate": 0.001, + "loss": 1.955, + "step": 50730 + }, + { + "epoch": 26.33, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 50740 + }, + { + "epoch": 26.34, + "learning_rate": 0.001, + "loss": 1.9343, + "step": 50750 + }, + { + "epoch": 26.34, + "learning_rate": 0.001, + "loss": 1.9383, + "step": 50760 + }, + { + "epoch": 26.35, + "learning_rate": 0.001, + "loss": 1.9537, + "step": 50770 + }, + { + "epoch": 26.35, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 50780 + }, + { + "epoch": 26.36, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 50790 + }, + { + "epoch": 26.36, + "learning_rate": 0.001, + "loss": 1.9389, + "step": 50800 + }, + { + "epoch": 26.37, + "learning_rate": 0.001, + "loss": 1.9264, + "step": 50810 + }, + { + "epoch": 26.37, + "learning_rate": 0.001, + "loss": 1.94, + "step": 50820 + }, + { + "epoch": 26.38, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 50830 + }, + { + "epoch": 26.38, + "learning_rate": 0.001, + "loss": 1.9515, + "step": 50840 + }, + { + "epoch": 26.39, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 50850 + }, + { + "epoch": 26.39, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 50860 + }, + { + "epoch": 26.4, + "learning_rate": 0.001, + "loss": 1.9615, + "step": 50870 + }, + { + "epoch": 26.4, + "learning_rate": 0.001, + "loss": 1.9555, + "step": 50880 + }, + { + "epoch": 26.41, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 50890 + }, + { + "epoch": 26.41, + "learning_rate": 0.001, + "loss": 1.943, + "step": 50900 + }, + { + "epoch": 26.42, + "learning_rate": 0.001, + "loss": 1.946, + "step": 50910 + }, + { + "epoch": 26.42, + "learning_rate": 0.001, + "loss": 1.947, + "step": 50920 + }, + { + "epoch": 26.43, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 50930 + }, + { + "epoch": 26.43, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 50940 + }, + { + "epoch": 26.44, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 50950 + }, + { + "epoch": 26.45, + "learning_rate": 0.001, + "loss": 1.9512, + "step": 50960 + }, + { + "epoch": 26.45, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 50970 + }, + { + "epoch": 26.46, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 50980 + }, + { + "epoch": 26.46, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 50990 + }, + { + "epoch": 26.47, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 51000 + }, + { + "epoch": 26.47, + "learning_rate": 0.001, + "loss": 1.9295, + "step": 51010 + }, + { + "epoch": 26.48, + "learning_rate": 0.001, + "loss": 1.9428, + "step": 51020 + }, + { + "epoch": 26.48, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 51030 + }, + { + "epoch": 26.49, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 51040 + }, + { + "epoch": 26.49, + "learning_rate": 0.001, + "loss": 1.944, + "step": 51050 + }, + { + "epoch": 26.5, + "learning_rate": 0.001, + "loss": 1.9532, + "step": 51060 + }, + { + "epoch": 26.5, + "learning_rate": 0.001, + "loss": 1.9413, + "step": 51070 + }, + { + "epoch": 26.51, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 51080 + }, + { + "epoch": 26.51, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 51090 + }, + { + "epoch": 26.52, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 51100 + }, + { + "epoch": 26.52, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 51110 + }, + { + "epoch": 26.53, + "learning_rate": 0.001, + "loss": 1.96, + "step": 51120 + }, + { + "epoch": 26.53, + "learning_rate": 0.001, + "loss": 1.9443, + "step": 51130 + }, + { + "epoch": 26.54, + "learning_rate": 0.001, + "loss": 1.9334, + "step": 51140 + }, + { + "epoch": 26.54, + "learning_rate": 0.001, + "loss": 1.9583, + "step": 51150 + }, + { + "epoch": 26.55, + "learning_rate": 0.001, + "loss": 1.9398, + "step": 51160 + }, + { + "epoch": 26.55, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 51170 + }, + { + "epoch": 26.56, + "learning_rate": 0.001, + "loss": 1.9397, + "step": 51180 + }, + { + "epoch": 26.56, + "learning_rate": 0.001, + "loss": 1.9342, + "step": 51190 + }, + { + "epoch": 26.57, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 51200 + }, + { + "epoch": 26.57, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 51210 + }, + { + "epoch": 26.58, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 51220 + }, + { + "epoch": 26.59, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 51230 + }, + { + "epoch": 26.59, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 51240 + }, + { + "epoch": 26.6, + "learning_rate": 0.001, + "loss": 1.9425, + "step": 51250 + }, + { + "epoch": 26.6, + "learning_rate": 0.001, + "loss": 1.933, + "step": 51260 + }, + { + "epoch": 26.61, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 51270 + }, + { + "epoch": 26.61, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 51280 + }, + { + "epoch": 26.62, + "learning_rate": 0.001, + "loss": 1.9722, + "step": 51290 + }, + { + "epoch": 26.62, + "learning_rate": 0.001, + "loss": 1.9491, + "step": 51300 + }, + { + "epoch": 26.63, + "learning_rate": 0.001, + "loss": 1.947, + "step": 51310 + }, + { + "epoch": 26.63, + "learning_rate": 0.001, + "loss": 1.9273, + "step": 51320 + }, + { + "epoch": 26.64, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 51330 + }, + { + "epoch": 26.64, + "learning_rate": 0.001, + "loss": 1.9496, + "step": 51340 + }, + { + "epoch": 26.65, + "learning_rate": 0.001, + "loss": 1.9399, + "step": 51350 + }, + { + "epoch": 26.65, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 51360 + }, + { + "epoch": 26.66, + "learning_rate": 0.001, + "loss": 1.9411, + "step": 51370 + }, + { + "epoch": 26.66, + "learning_rate": 0.001, + "loss": 1.9339, + "step": 51380 + }, + { + "epoch": 26.67, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 51390 + }, + { + "epoch": 26.67, + "learning_rate": 0.001, + "loss": 1.9231, + "step": 51400 + }, + { + "epoch": 26.68, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 51410 + }, + { + "epoch": 26.68, + "learning_rate": 0.001, + "loss": 1.9623, + "step": 51420 + }, + { + "epoch": 26.69, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 51430 + }, + { + "epoch": 26.69, + "learning_rate": 0.001, + "loss": 1.9381, + "step": 51440 + }, + { + "epoch": 26.7, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 51450 + }, + { + "epoch": 26.7, + "learning_rate": 0.001, + "loss": 1.9427, + "step": 51460 + }, + { + "epoch": 26.71, + "learning_rate": 0.001, + "loss": 1.9476, + "step": 51470 + }, + { + "epoch": 26.72, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 51480 + }, + { + "epoch": 26.72, + "learning_rate": 0.001, + "loss": 1.9239, + "step": 51490 + }, + { + "epoch": 26.73, + "learning_rate": 0.001, + "loss": 1.9395, + "step": 51500 + }, + { + "epoch": 26.73, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 51510 + }, + { + "epoch": 26.74, + "learning_rate": 0.001, + "loss": 1.9465, + "step": 51520 + }, + { + "epoch": 26.74, + "learning_rate": 0.001, + "loss": 1.9274, + "step": 51530 + }, + { + "epoch": 26.75, + "learning_rate": 0.001, + "loss": 1.9403, + "step": 51540 + }, + { + "epoch": 26.75, + "learning_rate": 0.001, + "loss": 1.9338, + "step": 51550 + }, + { + "epoch": 26.76, + "learning_rate": 0.001, + "loss": 1.9616, + "step": 51560 + }, + { + "epoch": 26.76, + "learning_rate": 0.001, + "loss": 1.9588, + "step": 51570 + }, + { + "epoch": 26.77, + "learning_rate": 0.001, + "loss": 1.931, + "step": 51580 + }, + { + "epoch": 26.77, + "learning_rate": 0.001, + "loss": 1.932, + "step": 51590 + }, + { + "epoch": 26.78, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 51600 + }, + { + "epoch": 26.78, + "learning_rate": 0.001, + "loss": 1.9367, + "step": 51610 + }, + { + "epoch": 26.79, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 51620 + }, + { + "epoch": 26.79, + "learning_rate": 0.001, + "loss": 1.9452, + "step": 51630 + }, + { + "epoch": 26.8, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 51640 + }, + { + "epoch": 26.8, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 51650 + }, + { + "epoch": 26.81, + "learning_rate": 0.001, + "loss": 1.9391, + "step": 51660 + }, + { + "epoch": 26.81, + "learning_rate": 0.001, + "loss": 1.9253, + "step": 51670 + }, + { + "epoch": 26.82, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 51680 + }, + { + "epoch": 26.82, + "learning_rate": 0.001, + "loss": 1.9419, + "step": 51690 + }, + { + "epoch": 26.83, + "learning_rate": 0.001, + "loss": 1.9589, + "step": 51700 + }, + { + "epoch": 26.83, + "learning_rate": 0.001, + "loss": 1.9524, + "step": 51710 + }, + { + "epoch": 26.84, + "learning_rate": 0.001, + "loss": 1.9401, + "step": 51720 + }, + { + "epoch": 26.84, + "learning_rate": 0.001, + "loss": 1.9575, + "step": 51730 + }, + { + "epoch": 26.85, + "learning_rate": 0.001, + "loss": 1.9328, + "step": 51740 + }, + { + "epoch": 26.86, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 51750 + }, + { + "epoch": 26.86, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 51760 + }, + { + "epoch": 26.87, + "learning_rate": 0.001, + "loss": 1.9316, + "step": 51770 + }, + { + "epoch": 26.87, + "learning_rate": 0.001, + "loss": 1.9661, + "step": 51780 + }, + { + "epoch": 26.88, + "learning_rate": 0.001, + "loss": 1.9227, + "step": 51790 + }, + { + "epoch": 26.88, + "learning_rate": 0.001, + "loss": 1.948, + "step": 51800 + }, + { + "epoch": 26.89, + "learning_rate": 0.001, + "loss": 1.9299, + "step": 51810 + }, + { + "epoch": 26.89, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 51820 + }, + { + "epoch": 26.9, + "learning_rate": 0.001, + "loss": 1.9205, + "step": 51830 + }, + { + "epoch": 26.9, + "learning_rate": 0.001, + "loss": 1.9553, + "step": 51840 + }, + { + "epoch": 26.91, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 51850 + }, + { + "epoch": 26.91, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 51860 + }, + { + "epoch": 26.92, + "learning_rate": 0.001, + "loss": 1.9377, + "step": 51870 + }, + { + "epoch": 26.92, + "learning_rate": 0.001, + "loss": 1.9416, + "step": 51880 + }, + { + "epoch": 26.93, + "learning_rate": 0.001, + "loss": 1.923, + "step": 51890 + }, + { + "epoch": 26.93, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 51900 + }, + { + "epoch": 26.94, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 51910 + }, + { + "epoch": 26.94, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 51920 + }, + { + "epoch": 26.95, + "learning_rate": 0.001, + "loss": 1.9529, + "step": 51930 + }, + { + "epoch": 26.95, + "learning_rate": 0.001, + "loss": 1.9426, + "step": 51940 + }, + { + "epoch": 26.96, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 51950 + }, + { + "epoch": 26.96, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 51960 + }, + { + "epoch": 26.97, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 51970 + }, + { + "epoch": 26.97, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 51980 + }, + { + "epoch": 26.98, + "learning_rate": 0.001, + "loss": 1.9376, + "step": 51990 + }, + { + "epoch": 26.98, + "learning_rate": 0.001, + "loss": 1.9392, + "step": 52000 + }, + { + "epoch": 26.99, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 52010 + }, + { + "epoch": 27.0, + "learning_rate": 0.001, + "loss": 1.938, + "step": 52020 + }, + { + "epoch": 27.0, + "eval_accuracy": { + "accuracy": 0.17665369649805449 + }, + "eval_f1": { + "f1": 0.04289493575207861 + }, + "eval_loss": 1.9414470195770264, + "eval_precision": { + "precision": 0.025236242356864926 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.5633, + "eval_samples_per_second": 51.017, + "eval_steps_per_second": 25.515, + "step": 52029 + }, + { + "epoch": 27.0, + "learning_rate": 0.001, + "loss": 1.9458, + "step": 52030 + }, + { + "epoch": 27.01, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 52040 + }, + { + "epoch": 27.01, + "learning_rate": 0.001, + "loss": 1.9641, + "step": 52050 + }, + { + "epoch": 27.02, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 52060 + }, + { + "epoch": 27.02, + "learning_rate": 0.001, + "loss": 1.9404, + "step": 52070 + }, + { + "epoch": 27.03, + "learning_rate": 0.001, + "loss": 1.9294, + "step": 52080 + }, + { + "epoch": 27.03, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 52090 + }, + { + "epoch": 27.04, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 52100 + }, + { + "epoch": 27.04, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 52110 + }, + { + "epoch": 27.05, + "learning_rate": 0.001, + "loss": 1.9217, + "step": 52120 + }, + { + "epoch": 27.05, + "learning_rate": 0.001, + "loss": 1.9314, + "step": 52130 + }, + { + "epoch": 27.06, + "learning_rate": 0.001, + "loss": 1.941, + "step": 52140 + }, + { + "epoch": 27.06, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 52150 + }, + { + "epoch": 27.07, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 52160 + }, + { + "epoch": 27.07, + "learning_rate": 0.001, + "loss": 1.9278, + "step": 52170 + }, + { + "epoch": 27.08, + "learning_rate": 0.001, + "loss": 1.9441, + "step": 52180 + }, + { + "epoch": 27.08, + "learning_rate": 0.001, + "loss": 1.9434, + "step": 52190 + }, + { + "epoch": 27.09, + "learning_rate": 0.001, + "loss": 1.9554, + "step": 52200 + }, + { + "epoch": 27.09, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 52210 + }, + { + "epoch": 27.1, + "learning_rate": 0.001, + "loss": 1.9312, + "step": 52220 + }, + { + "epoch": 27.1, + "learning_rate": 0.001, + "loss": 1.9331, + "step": 52230 + }, + { + "epoch": 27.11, + "learning_rate": 0.001, + "loss": 1.9436, + "step": 52240 + }, + { + "epoch": 27.11, + "learning_rate": 0.001, + "loss": 1.9568, + "step": 52250 + }, + { + "epoch": 27.12, + "learning_rate": 0.001, + "loss": 1.9216, + "step": 52260 + }, + { + "epoch": 27.13, + "learning_rate": 0.001, + "loss": 1.9349, + "step": 52270 + }, + { + "epoch": 27.13, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 52280 + }, + { + "epoch": 27.14, + "learning_rate": 0.001, + "loss": 1.9569, + "step": 52290 + }, + { + "epoch": 27.14, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 52300 + }, + { + "epoch": 27.15, + "learning_rate": 0.001, + "loss": 1.9487, + "step": 52310 + }, + { + "epoch": 27.15, + "learning_rate": 0.001, + "loss": 1.9276, + "step": 52320 + }, + { + "epoch": 27.16, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 52330 + }, + { + "epoch": 27.16, + "learning_rate": 0.001, + "loss": 1.9477, + "step": 52340 + }, + { + "epoch": 27.17, + "learning_rate": 0.001, + "loss": 1.9199, + "step": 52350 + }, + { + "epoch": 27.17, + "learning_rate": 0.001, + "loss": 1.9788, + "step": 52360 + }, + { + "epoch": 27.18, + "learning_rate": 0.001, + "loss": 1.962, + "step": 52370 + }, + { + "epoch": 27.18, + "learning_rate": 0.001, + "loss": 1.9484, + "step": 52380 + }, + { + "epoch": 27.19, + "learning_rate": 0.001, + "loss": 1.9564, + "step": 52390 + }, + { + "epoch": 27.19, + "learning_rate": 0.001, + "loss": 1.934, + "step": 52400 + }, + { + "epoch": 27.2, + "learning_rate": 0.001, + "loss": 1.931, + "step": 52410 + }, + { + "epoch": 27.2, + "learning_rate": 0.001, + "loss": 1.9269, + "step": 52420 + }, + { + "epoch": 27.21, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 52430 + }, + { + "epoch": 27.21, + "learning_rate": 0.001, + "loss": 1.9448, + "step": 52440 + }, + { + "epoch": 27.22, + "learning_rate": 0.001, + "loss": 1.9371, + "step": 52450 + }, + { + "epoch": 27.22, + "learning_rate": 0.001, + "loss": 1.9344, + "step": 52460 + }, + { + "epoch": 27.23, + "learning_rate": 0.001, + "loss": 1.9547, + "step": 52470 + }, + { + "epoch": 27.23, + "learning_rate": 0.001, + "loss": 1.9289, + "step": 52480 + }, + { + "epoch": 27.24, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 52490 + }, + { + "epoch": 27.24, + "learning_rate": 0.001, + "loss": 1.9351, + "step": 52500 + }, + { + "epoch": 27.25, + "learning_rate": 0.001, + "loss": 1.9499, + "step": 52510 + }, + { + "epoch": 27.25, + "learning_rate": 0.001, + "loss": 1.9364, + "step": 52520 + }, + { + "epoch": 27.26, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 52530 + }, + { + "epoch": 27.27, + "learning_rate": 0.001, + "loss": 1.9577, + "step": 52540 + }, + { + "epoch": 27.27, + "learning_rate": 0.001, + "loss": 1.9356, + "step": 52550 + }, + { + "epoch": 27.28, + "learning_rate": 0.001, + "loss": 1.9315, + "step": 52560 + }, + { + "epoch": 27.28, + "learning_rate": 0.001, + "loss": 1.9232, + "step": 52570 + }, + { + "epoch": 27.29, + "learning_rate": 0.001, + "loss": 1.952, + "step": 52580 + }, + { + "epoch": 27.29, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 52590 + }, + { + "epoch": 27.3, + "learning_rate": 0.001, + "loss": 1.9638, + "step": 52600 + }, + { + "epoch": 27.3, + "learning_rate": 0.001, + "loss": 1.9618, + "step": 52610 + }, + { + "epoch": 27.31, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 52620 + }, + { + "epoch": 27.31, + "learning_rate": 0.001, + "loss": 1.9454, + "step": 52630 + }, + { + "epoch": 27.32, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 52640 + }, + { + "epoch": 27.32, + "learning_rate": 0.001, + "loss": 1.9337, + "step": 52650 + }, + { + "epoch": 27.33, + "learning_rate": 0.001, + "loss": 1.9297, + "step": 52660 + }, + { + "epoch": 27.33, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 52670 + }, + { + "epoch": 27.34, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 52680 + }, + { + "epoch": 27.34, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 52690 + }, + { + "epoch": 27.35, + "learning_rate": 0.001, + "loss": 1.9446, + "step": 52700 + }, + { + "epoch": 27.35, + "learning_rate": 0.001, + "loss": 1.9271, + "step": 52710 + }, + { + "epoch": 27.36, + "learning_rate": 0.001, + "loss": 1.9451, + "step": 52720 + }, + { + "epoch": 27.36, + "learning_rate": 0.001, + "loss": 1.9417, + "step": 52730 + }, + { + "epoch": 27.37, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 52740 + }, + { + "epoch": 27.37, + "learning_rate": 0.001, + "loss": 1.937, + "step": 52750 + }, + { + "epoch": 27.38, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 52760 + }, + { + "epoch": 27.38, + "learning_rate": 0.001, + "loss": 1.9323, + "step": 52770 + }, + { + "epoch": 27.39, + "learning_rate": 0.001, + "loss": 1.9444, + "step": 52780 + }, + { + "epoch": 27.39, + "learning_rate": 0.001, + "loss": 1.9169, + "step": 52790 + }, + { + "epoch": 27.4, + "learning_rate": 0.001, + "loss": 1.9358, + "step": 52800 + }, + { + "epoch": 27.41, + "learning_rate": 0.001, + "loss": 1.9692, + "step": 52810 + }, + { + "epoch": 27.41, + "learning_rate": 0.001, + "loss": 1.9533, + "step": 52820 + }, + { + "epoch": 27.42, + "learning_rate": 0.001, + "loss": 1.9102, + "step": 52830 + }, + { + "epoch": 27.42, + "learning_rate": 0.001, + "loss": 1.9247, + "step": 52840 + }, + { + "epoch": 27.43, + "learning_rate": 0.001, + "loss": 1.9241, + "step": 52850 + }, + { + "epoch": 27.43, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 52860 + }, + { + "epoch": 27.44, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 52870 + }, + { + "epoch": 27.44, + "learning_rate": 0.001, + "loss": 1.9889, + "step": 52880 + }, + { + "epoch": 27.45, + "learning_rate": 0.001, + "loss": 1.9402, + "step": 52890 + }, + { + "epoch": 27.45, + "learning_rate": 0.001, + "loss": 1.9571, + "step": 52900 + }, + { + "epoch": 27.46, + "learning_rate": 0.001, + "loss": 1.9352, + "step": 52910 + }, + { + "epoch": 27.46, + "learning_rate": 0.001, + "loss": 1.9111, + "step": 52920 + }, + { + "epoch": 27.47, + "learning_rate": 0.001, + "loss": 1.9396, + "step": 52930 + }, + { + "epoch": 27.47, + "learning_rate": 0.001, + "loss": 1.972, + "step": 52940 + }, + { + "epoch": 27.48, + "learning_rate": 0.001, + "loss": 1.9557, + "step": 52950 + }, + { + "epoch": 27.48, + "learning_rate": 0.001, + "loss": 1.9685, + "step": 52960 + }, + { + "epoch": 27.49, + "learning_rate": 0.001, + "loss": 1.9384, + "step": 52970 + }, + { + "epoch": 27.49, + "learning_rate": 0.001, + "loss": 1.9469, + "step": 52980 + }, + { + "epoch": 27.5, + "learning_rate": 0.001, + "loss": 1.954, + "step": 52990 + }, + { + "epoch": 27.5, + "learning_rate": 0.001, + "loss": 1.9421, + "step": 53000 + }, + { + "epoch": 27.51, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 53010 + }, + { + "epoch": 27.51, + "learning_rate": 0.001, + "loss": 1.9573, + "step": 53020 + }, + { + "epoch": 27.52, + "learning_rate": 0.001, + "loss": 1.9405, + "step": 53030 + }, + { + "epoch": 27.52, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 53040 + }, + { + "epoch": 27.53, + "learning_rate": 0.001, + "loss": 1.9503, + "step": 53050 + }, + { + "epoch": 27.54, + "learning_rate": 0.001, + "loss": 1.9348, + "step": 53060 + }, + { + "epoch": 27.54, + "learning_rate": 0.001, + "loss": 1.9562, + "step": 53070 + }, + { + "epoch": 27.55, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 53080 + }, + { + "epoch": 27.55, + "learning_rate": 0.001, + "loss": 1.9306, + "step": 53090 + }, + { + "epoch": 27.56, + "learning_rate": 0.001, + "loss": 1.9456, + "step": 53100 + }, + { + "epoch": 27.56, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 53110 + }, + { + "epoch": 27.57, + "learning_rate": 0.001, + "loss": 1.947, + "step": 53120 + }, + { + "epoch": 27.57, + "learning_rate": 0.001, + "loss": 1.9526, + "step": 53130 + }, + { + "epoch": 27.58, + "learning_rate": 0.001, + "loss": 1.9527, + "step": 53140 + }, + { + "epoch": 27.58, + "learning_rate": 0.001, + "loss": 1.9418, + "step": 53150 + }, + { + "epoch": 27.59, + "learning_rate": 0.001, + "loss": 1.9535, + "step": 53160 + }, + { + "epoch": 27.59, + "learning_rate": 0.001, + "loss": 1.956, + "step": 53170 + }, + { + "epoch": 27.6, + "learning_rate": 0.001, + "loss": 1.9625, + "step": 53180 + }, + { + "epoch": 27.6, + "learning_rate": 0.001, + "loss": 1.9517, + "step": 53190 + }, + { + "epoch": 27.61, + "learning_rate": 0.001, + "loss": 1.9442, + "step": 53200 + }, + { + "epoch": 27.61, + "learning_rate": 0.001, + "loss": 1.9431, + "step": 53210 + }, + { + "epoch": 27.62, + "learning_rate": 0.001, + "loss": 1.9341, + "step": 53220 + }, + { + "epoch": 27.62, + "learning_rate": 0.001, + "loss": 1.947, + "step": 53230 + }, + { + "epoch": 27.63, + "learning_rate": 0.001, + "loss": 1.9345, + "step": 53240 + }, + { + "epoch": 27.63, + "learning_rate": 0.001, + "loss": 1.9365, + "step": 53250 + }, + { + "epoch": 27.64, + "learning_rate": 0.001, + "loss": 1.963, + "step": 53260 + }, + { + "epoch": 27.64, + "learning_rate": 0.001, + "loss": 1.9317, + "step": 53270 + }, + { + "epoch": 27.65, + "learning_rate": 0.001, + "loss": 1.924, + "step": 53280 + }, + { + "epoch": 27.65, + "learning_rate": 0.001, + "loss": 1.9186, + "step": 53290 + }, + { + "epoch": 27.66, + "learning_rate": 0.001, + "loss": 1.9385, + "step": 53300 + }, + { + "epoch": 27.66, + "learning_rate": 0.001, + "loss": 1.9362, + "step": 53310 + }, + { + "epoch": 27.67, + "learning_rate": 0.001, + "loss": 1.9324, + "step": 53320 + }, + { + "epoch": 27.68, + "learning_rate": 0.001, + "loss": 1.9222, + "step": 53330 + }, + { + "epoch": 27.68, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 53340 + }, + { + "epoch": 27.69, + "learning_rate": 0.001, + "loss": 1.9415, + "step": 53350 + }, + { + "epoch": 27.69, + "learning_rate": 0.001, + "loss": 1.9505, + "step": 53360 + }, + { + "epoch": 27.7, + "learning_rate": 0.001, + "loss": 1.9408, + "step": 53370 + }, + { + "epoch": 27.7, + "learning_rate": 0.001, + "loss": 1.9243, + "step": 53380 + }, + { + "epoch": 27.71, + "learning_rate": 0.001, + "loss": 1.9471, + "step": 53390 + }, + { + "epoch": 27.71, + "learning_rate": 0.001, + "loss": 1.9548, + "step": 53400 + }, + { + "epoch": 27.72, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 53410 + }, + { + "epoch": 27.72, + "learning_rate": 0.001, + "loss": 1.9407, + "step": 53420 + }, + { + "epoch": 27.73, + "learning_rate": 0.001, + "loss": 1.9437, + "step": 53430 + }, + { + "epoch": 27.73, + "learning_rate": 0.001, + "loss": 1.9445, + "step": 53440 + }, + { + "epoch": 27.74, + "learning_rate": 0.001, + "loss": 1.9455, + "step": 53450 + }, + { + "epoch": 27.74, + "learning_rate": 0.001, + "loss": 1.9541, + "step": 53460 + }, + { + "epoch": 27.75, + "learning_rate": 0.001, + "loss": 1.9243, + "step": 53470 + }, + { + "epoch": 27.75, + "learning_rate": 0.001, + "loss": 1.9475, + "step": 53480 + }, + { + "epoch": 27.76, + "learning_rate": 0.001, + "loss": 1.9482, + "step": 53490 + }, + { + "epoch": 27.76, + "learning_rate": 0.001, + "loss": 1.952, + "step": 53500 + }, + { + "epoch": 27.77, + "learning_rate": 0.001, + "loss": 1.9522, + "step": 53510 + }, + { + "epoch": 27.77, + "learning_rate": 0.001, + "loss": 1.9424, + "step": 53520 + }, + { + "epoch": 27.78, + "learning_rate": 0.001, + "loss": 1.9412, + "step": 53530 + }, + { + "epoch": 27.78, + "learning_rate": 0.001, + "loss": 1.9513, + "step": 53540 + }, + { + "epoch": 27.79, + "learning_rate": 0.001, + "loss": 1.94, + "step": 53550 + }, + { + "epoch": 27.79, + "learning_rate": 0.001, + "loss": 1.9333, + "step": 53560 + }, + { + "epoch": 27.8, + "learning_rate": 0.001, + "loss": 1.9663, + "step": 53570 + }, + { + "epoch": 27.8, + "learning_rate": 0.001, + "loss": 1.9502, + "step": 53580 + }, + { + "epoch": 27.81, + "learning_rate": 0.001, + "loss": 1.9435, + "step": 53590 + }, + { + "epoch": 27.82, + "learning_rate": 0.001, + "loss": 1.9414, + "step": 53600 + }, + { + "epoch": 27.82, + "learning_rate": 0.001, + "loss": 1.9453, + "step": 53610 + }, + { + "epoch": 27.83, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 53620 + }, + { + "epoch": 27.83, + "learning_rate": 0.001, + "loss": 1.9549, + "step": 53630 + }, + { + "epoch": 27.84, + "learning_rate": 0.001, + "loss": 1.9366, + "step": 53640 + }, + { + "epoch": 27.84, + "learning_rate": 0.001, + "loss": 1.9275, + "step": 53650 + }, + { + "epoch": 27.85, + "learning_rate": 0.001, + "loss": 1.939, + "step": 53660 + }, + { + "epoch": 27.85, + "learning_rate": 0.001, + "loss": 1.9704, + "step": 53670 + }, + { + "epoch": 27.86, + "learning_rate": 0.001, + "loss": 1.9474, + "step": 53680 + }, + { + "epoch": 27.86, + "learning_rate": 0.001, + "loss": 1.9493, + "step": 53690 + }, + { + "epoch": 27.87, + "learning_rate": 0.001, + "loss": 1.9508, + "step": 53700 + }, + { + "epoch": 27.87, + "learning_rate": 0.001, + "loss": 1.9354, + "step": 53710 + }, + { + "epoch": 27.88, + "learning_rate": 0.001, + "loss": 1.947, + "step": 53720 + }, + { + "epoch": 27.88, + "learning_rate": 0.001, + "loss": 1.9583, + "step": 53730 + }, + { + "epoch": 27.89, + "learning_rate": 0.001, + "loss": 1.9447, + "step": 53740 + }, + { + "epoch": 27.89, + "learning_rate": 0.001, + "loss": 1.9449, + "step": 53750 + }, + { + "epoch": 27.9, + "learning_rate": 0.001, + "loss": 1.957, + "step": 53760 + }, + { + "epoch": 27.9, + "learning_rate": 0.001, + "loss": 1.9483, + "step": 53770 + }, + { + "epoch": 27.91, + "learning_rate": 0.001, + "loss": 1.951, + "step": 53780 + }, + { + "epoch": 27.91, + "learning_rate": 0.001, + "loss": 1.9538, + "step": 53790 + }, + { + "epoch": 27.92, + "learning_rate": 0.001, + "loss": 1.9374, + "step": 53800 + }, + { + "epoch": 27.92, + "learning_rate": 0.001, + "loss": 1.9462, + "step": 53810 + }, + { + "epoch": 27.93, + "learning_rate": 0.001, + "loss": 1.9558, + "step": 53820 + }, + { + "epoch": 27.93, + "learning_rate": 0.001, + "loss": 1.9368, + "step": 53830 + }, + { + "epoch": 27.94, + "learning_rate": 0.001, + "loss": 1.9468, + "step": 53840 + }, + { + "epoch": 27.94, + "learning_rate": 0.001, + "loss": 1.9528, + "step": 53850 + }, + { + "epoch": 27.95, + "learning_rate": 0.001, + "loss": 1.9429, + "step": 53860 + }, + { + "epoch": 27.96, + "learning_rate": 0.001, + "loss": 1.9507, + "step": 53870 + }, + { + "epoch": 27.96, + "learning_rate": 0.001, + "loss": 1.9432, + "step": 53880 + }, + { + "epoch": 27.97, + "learning_rate": 0.001, + "loss": 1.9335, + "step": 53890 + }, + { + "epoch": 27.97, + "learning_rate": 0.001, + "loss": 1.9479, + "step": 53900 + }, + { + "epoch": 27.98, + "learning_rate": 0.001, + "loss": 1.9459, + "step": 53910 + }, + { + "epoch": 27.98, + "learning_rate": 0.001, + "loss": 1.948, + "step": 53920 + }, + { + "epoch": 27.99, + "learning_rate": 0.001, + "loss": 1.9321, + "step": 53930 + }, + { + "epoch": 27.99, + "learning_rate": 0.001, + "loss": 1.9382, + "step": 53940 + }, + { + "epoch": 28.0, + "learning_rate": 0.001, + "loss": 1.9207, + "step": 53950 + }, + { + "epoch": 28.0, + "eval_accuracy": { + "accuracy": 0.1556420233463035 + }, + "eval_f1": { + "f1": 0.03848003848003848 + }, + "eval_loss": 1.9410392045974731, + "eval_precision": { + "precision": 0.022234574763757644 + }, + "eval_recall": { + "recall": 0.14285714285714285 + }, + "eval_runtime": 75.917, + "eval_samples_per_second": 50.779, + "eval_steps_per_second": 25.396, + "step": 53956 + } + ], + "logging_steps": 10, + "max_steps": 57810, + "num_input_tokens_seen": 0, + "num_train_epochs": 30, + "save_steps": 500, + "total_flos": 9.347236826925957e+18, + "train_batch_size": 2, + "trial_name": null, + "trial_params": null +}