diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,10357 @@ +{ + "best_metric": 0.009275409393012524, + "best_model_checkpoint": "./results/checkpoint-16000", + "epoch": 0.9725956862520739, + "eval_steps": 1000, + "global_step": 17000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 3.0000000000000004e-07, + "loss": 0.003, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 6.000000000000001e-07, + "loss": 0.0356, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 9e-07, + "loss": 0.0025, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.2000000000000002e-06, + "loss": 0.0021, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 1.5e-06, + "loss": 0.0634, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 1.8e-06, + "loss": 0.0024, + "step": 60 + }, + { + "epoch": 0.0, + "learning_rate": 2.1000000000000002e-06, + "loss": 0.0582, + "step": 70 + }, + { + "epoch": 0.0, + "learning_rate": 2.4000000000000003e-06, + "loss": 0.0403, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 2.7e-06, + "loss": 0.0018, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 3e-06, + "loss": 0.0067, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 3.3e-06, + "loss": 0.023, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 3.6e-06, + "loss": 0.0033, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 3.9e-06, + "loss": 0.0064, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 4.2000000000000004e-06, + "loss": 0.0052, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 4.5e-06, + "loss": 0.0014, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 4.800000000000001e-06, + "loss": 0.0048, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 5.1e-06, + "loss": 0.0015, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 5.4e-06, + "loss": 0.0042, + "step": 180 + }, + { + "epoch": 0.01, + "learning_rate": 5.7000000000000005e-06, + "loss": 0.0024, + "step": 190 + }, + { + "epoch": 0.01, + "learning_rate": 6e-06, + "loss": 0.0438, + "step": 200 + }, + { + "epoch": 0.01, + "learning_rate": 6.3e-06, + "loss": 0.001, + "step": 210 + }, + { + "epoch": 0.01, + "learning_rate": 6.6e-06, + "loss": 0.0077, + "step": 220 + }, + { + "epoch": 0.01, + "learning_rate": 6.900000000000001e-06, + "loss": 0.047, + "step": 230 + }, + { + "epoch": 0.01, + "learning_rate": 7.2e-06, + "loss": 0.0236, + "step": 240 + }, + { + "epoch": 0.01, + "learning_rate": 7.5e-06, + "loss": 0.0061, + "step": 250 + }, + { + "epoch": 0.01, + "learning_rate": 7.8e-06, + "loss": 0.0021, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 8.1e-06, + "loss": 0.0062, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 8.400000000000001e-06, + "loss": 0.0008, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 8.7e-06, + "loss": 0.0117, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 9e-06, + "loss": 0.0126, + "step": 300 + }, + { + "epoch": 0.02, + "learning_rate": 9.3e-06, + "loss": 0.0323, + "step": 310 + }, + { + "epoch": 0.02, + "learning_rate": 9.600000000000001e-06, + "loss": 0.0006, + "step": 320 + }, + { + "epoch": 0.02, + "learning_rate": 9.9e-06, + "loss": 0.0004, + "step": 330 + }, + { + "epoch": 0.02, + "learning_rate": 1.02e-05, + "loss": 0.0004, + "step": 340 + }, + { + "epoch": 0.02, + "learning_rate": 1.05e-05, + "loss": 0.0087, + "step": 350 + }, + { + "epoch": 0.02, + "learning_rate": 1.08e-05, + "loss": 0.0225, + "step": 360 + }, + { + "epoch": 0.02, + "learning_rate": 1.11e-05, + "loss": 0.0153, + "step": 370 + }, + { + "epoch": 0.02, + "learning_rate": 1.1400000000000001e-05, + "loss": 0.0003, + "step": 380 + }, + { + "epoch": 0.02, + "learning_rate": 1.1700000000000001e-05, + "loss": 0.0059, + "step": 390 + }, + { + "epoch": 0.02, + "learning_rate": 1.2e-05, + "loss": 0.0104, + "step": 400 + }, + { + "epoch": 0.02, + "learning_rate": 1.2299999999999999e-05, + "loss": 0.0517, + "step": 410 + }, + { + "epoch": 0.02, + "learning_rate": 1.26e-05, + "loss": 0.0192, + "step": 420 + }, + { + "epoch": 0.02, + "learning_rate": 1.29e-05, + "loss": 0.0355, + "step": 430 + }, + { + "epoch": 0.03, + "learning_rate": 1.32e-05, + "loss": 0.0303, + "step": 440 + }, + { + "epoch": 0.03, + "learning_rate": 1.3500000000000001e-05, + "loss": 0.0257, + "step": 450 + }, + { + "epoch": 0.03, + "learning_rate": 1.3800000000000002e-05, + "loss": 0.0013, + "step": 460 + }, + { + "epoch": 0.03, + "learning_rate": 1.4099999999999999e-05, + "loss": 0.0415, + "step": 470 + }, + { + "epoch": 0.03, + "learning_rate": 1.44e-05, + "loss": 0.0036, + "step": 480 + }, + { + "epoch": 0.03, + "learning_rate": 1.47e-05, + "loss": 0.0059, + "step": 490 + }, + { + "epoch": 0.03, + "learning_rate": 1.5e-05, + "loss": 0.0443, + "step": 500 + }, + { + "epoch": 0.03, + "learning_rate": 1.53e-05, + "loss": 0.0015, + "step": 510 + }, + { + "epoch": 0.03, + "learning_rate": 1.56e-05, + "loss": 0.0226, + "step": 520 + }, + { + "epoch": 0.03, + "learning_rate": 1.59e-05, + "loss": 0.0009, + "step": 530 + }, + { + "epoch": 0.03, + "learning_rate": 1.62e-05, + "loss": 0.0007, + "step": 540 + }, + { + "epoch": 0.03, + "learning_rate": 1.65e-05, + "loss": 0.0422, + "step": 550 + }, + { + "epoch": 0.03, + "learning_rate": 1.6800000000000002e-05, + "loss": 0.0004, + "step": 560 + }, + { + "epoch": 0.03, + "learning_rate": 1.71e-05, + "loss": 0.0812, + "step": 570 + }, + { + "epoch": 0.03, + "learning_rate": 1.74e-05, + "loss": 0.0012, + "step": 580 + }, + { + "epoch": 0.03, + "learning_rate": 1.77e-05, + "loss": 0.0011, + "step": 590 + }, + { + "epoch": 0.03, + "learning_rate": 1.8e-05, + "loss": 0.0324, + "step": 600 + }, + { + "epoch": 0.03, + "learning_rate": 1.83e-05, + "loss": 0.0622, + "step": 610 + }, + { + "epoch": 0.04, + "learning_rate": 1.86e-05, + "loss": 0.0249, + "step": 620 + }, + { + "epoch": 0.04, + "learning_rate": 1.8900000000000002e-05, + "loss": 0.0628, + "step": 630 + }, + { + "epoch": 0.04, + "learning_rate": 1.9200000000000003e-05, + "loss": 0.0011, + "step": 640 + }, + { + "epoch": 0.04, + "learning_rate": 1.95e-05, + "loss": 0.0224, + "step": 650 + }, + { + "epoch": 0.04, + "learning_rate": 1.98e-05, + "loss": 0.0523, + "step": 660 + }, + { + "epoch": 0.04, + "learning_rate": 2.01e-05, + "loss": 0.0008, + "step": 670 + }, + { + "epoch": 0.04, + "learning_rate": 2.04e-05, + "loss": 0.0228, + "step": 680 + }, + { + "epoch": 0.04, + "learning_rate": 2.07e-05, + "loss": 0.0106, + "step": 690 + }, + { + "epoch": 0.04, + "learning_rate": 2.1e-05, + "loss": 0.0026, + "step": 700 + }, + { + "epoch": 0.04, + "learning_rate": 2.13e-05, + "loss": 0.0047, + "step": 710 + }, + { + "epoch": 0.04, + "learning_rate": 2.16e-05, + "loss": 0.0021, + "step": 720 + }, + { + "epoch": 0.04, + "learning_rate": 2.19e-05, + "loss": 0.002, + "step": 730 + }, + { + "epoch": 0.04, + "learning_rate": 2.22e-05, + "loss": 0.0519, + "step": 740 + }, + { + "epoch": 0.04, + "learning_rate": 2.25e-05, + "loss": 0.0118, + "step": 750 + }, + { + "epoch": 0.04, + "learning_rate": 2.2800000000000002e-05, + "loss": 0.0009, + "step": 760 + }, + { + "epoch": 0.04, + "learning_rate": 2.3100000000000002e-05, + "loss": 0.001, + "step": 770 + }, + { + "epoch": 0.04, + "learning_rate": 2.3400000000000003e-05, + "loss": 0.0003, + "step": 780 + }, + { + "epoch": 0.05, + "learning_rate": 2.37e-05, + "loss": 0.002, + "step": 790 + }, + { + "epoch": 0.05, + "learning_rate": 2.4e-05, + "loss": 0.0487, + "step": 800 + }, + { + "epoch": 0.05, + "learning_rate": 2.43e-05, + "loss": 0.0002, + "step": 810 + }, + { + "epoch": 0.05, + "learning_rate": 2.4599999999999998e-05, + "loss": 0.0016, + "step": 820 + }, + { + "epoch": 0.05, + "learning_rate": 2.49e-05, + "loss": 0.0004, + "step": 830 + }, + { + "epoch": 0.05, + "learning_rate": 2.52e-05, + "loss": 0.0027, + "step": 840 + }, + { + "epoch": 0.05, + "learning_rate": 2.55e-05, + "loss": 0.0032, + "step": 850 + }, + { + "epoch": 0.05, + "learning_rate": 2.58e-05, + "loss": 0.0002, + "step": 860 + }, + { + "epoch": 0.05, + "learning_rate": 2.61e-05, + "loss": 0.0011, + "step": 870 + }, + { + "epoch": 0.05, + "learning_rate": 2.64e-05, + "loss": 0.0002, + "step": 880 + }, + { + "epoch": 0.05, + "learning_rate": 2.6700000000000002e-05, + "loss": 0.0634, + "step": 890 + }, + { + "epoch": 0.05, + "learning_rate": 2.7000000000000002e-05, + "loss": 0.0112, + "step": 900 + }, + { + "epoch": 0.05, + "learning_rate": 2.7300000000000003e-05, + "loss": 0.0185, + "step": 910 + }, + { + "epoch": 0.05, + "learning_rate": 2.7600000000000003e-05, + "loss": 0.0006, + "step": 920 + }, + { + "epoch": 0.05, + "learning_rate": 2.79e-05, + "loss": 0.0784, + "step": 930 + }, + { + "epoch": 0.05, + "learning_rate": 2.8199999999999998e-05, + "loss": 0.0126, + "step": 940 + }, + { + "epoch": 0.05, + "learning_rate": 2.8499999999999998e-05, + "loss": 0.0214, + "step": 950 + }, + { + "epoch": 0.05, + "learning_rate": 2.88e-05, + "loss": 0.0038, + "step": 960 + }, + { + "epoch": 0.06, + "learning_rate": 2.91e-05, + "loss": 0.0015, + "step": 970 + }, + { + "epoch": 0.06, + "learning_rate": 2.94e-05, + "loss": 0.0371, + "step": 980 + }, + { + "epoch": 0.06, + "learning_rate": 2.97e-05, + "loss": 0.0368, + "step": 990 + }, + { + "epoch": 0.06, + "learning_rate": 3e-05, + "loss": 0.0026, + "step": 1000 + }, + { + "epoch": 0.06, + "eval_loss": 0.017844753339886665, + "eval_runtime": 381.7901, + "eval_samples_per_second": 183.122, + "eval_steps_per_second": 11.446, + "step": 1000 + }, + { + "epoch": 0.06, + "learning_rate": 2.998179390702755e-05, + "loss": 0.0006, + "step": 1010 + }, + { + "epoch": 0.06, + "learning_rate": 2.9963587814055105e-05, + "loss": 0.0004, + "step": 1020 + }, + { + "epoch": 0.06, + "learning_rate": 2.9945381721082656e-05, + "loss": 0.0114, + "step": 1030 + }, + { + "epoch": 0.06, + "learning_rate": 2.9927175628110206e-05, + "loss": 0.0469, + "step": 1040 + }, + { + "epoch": 0.06, + "learning_rate": 2.990896953513776e-05, + "loss": 0.0142, + "step": 1050 + }, + { + "epoch": 0.06, + "learning_rate": 2.989076344216531e-05, + "loss": 0.0422, + "step": 1060 + }, + { + "epoch": 0.06, + "learning_rate": 2.987255734919286e-05, + "loss": 0.0113, + "step": 1070 + }, + { + "epoch": 0.06, + "learning_rate": 2.985435125622042e-05, + "loss": 0.001, + "step": 1080 + }, + { + "epoch": 0.06, + "learning_rate": 2.983614516324797e-05, + "loss": 0.0013, + "step": 1090 + }, + { + "epoch": 0.06, + "learning_rate": 2.981793907027552e-05, + "loss": 0.0334, + "step": 1100 + }, + { + "epoch": 0.06, + "learning_rate": 2.9799732977303073e-05, + "loss": 0.001, + "step": 1110 + }, + { + "epoch": 0.06, + "learning_rate": 2.9781526884330624e-05, + "loss": 0.0006, + "step": 1120 + }, + { + "epoch": 0.06, + "learning_rate": 2.9763320791358175e-05, + "loss": 0.0005, + "step": 1130 + }, + { + "epoch": 0.07, + "learning_rate": 2.974511469838573e-05, + "loss": 0.0005, + "step": 1140 + }, + { + "epoch": 0.07, + "learning_rate": 2.972690860541328e-05, + "loss": 0.0003, + "step": 1150 + }, + { + "epoch": 0.07, + "learning_rate": 2.970870251244083e-05, + "loss": 0.0445, + "step": 1160 + }, + { + "epoch": 0.07, + "learning_rate": 2.9690496419468383e-05, + "loss": 0.0027, + "step": 1170 + }, + { + "epoch": 0.07, + "learning_rate": 2.9672290326495934e-05, + "loss": 0.0288, + "step": 1180 + }, + { + "epoch": 0.07, + "learning_rate": 2.9654084233523484e-05, + "loss": 0.0004, + "step": 1190 + }, + { + "epoch": 0.07, + "learning_rate": 2.963587814055104e-05, + "loss": 0.0003, + "step": 1200 + }, + { + "epoch": 0.07, + "learning_rate": 2.961767204757859e-05, + "loss": 0.0114, + "step": 1210 + }, + { + "epoch": 0.07, + "learning_rate": 2.959946595460614e-05, + "loss": 0.0006, + "step": 1220 + }, + { + "epoch": 0.07, + "learning_rate": 2.9581259861633693e-05, + "loss": 0.0003, + "step": 1230 + }, + { + "epoch": 0.07, + "learning_rate": 2.9563053768661247e-05, + "loss": 0.0021, + "step": 1240 + }, + { + "epoch": 0.07, + "learning_rate": 2.9544847675688798e-05, + "loss": 0.0262, + "step": 1250 + }, + { + "epoch": 0.07, + "learning_rate": 2.952664158271635e-05, + "loss": 0.0101, + "step": 1260 + }, + { + "epoch": 0.07, + "learning_rate": 2.9508435489743902e-05, + "loss": 0.0708, + "step": 1270 + }, + { + "epoch": 0.07, + "learning_rate": 2.9490229396771453e-05, + "loss": 0.0459, + "step": 1280 + }, + { + "epoch": 0.07, + "learning_rate": 2.9472023303799007e-05, + "loss": 0.0377, + "step": 1290 + }, + { + "epoch": 0.07, + "learning_rate": 2.9453817210826557e-05, + "loss": 0.0412, + "step": 1300 + }, + { + "epoch": 0.07, + "learning_rate": 2.9435611117854108e-05, + "loss": 0.0012, + "step": 1310 + }, + { + "epoch": 0.08, + "learning_rate": 2.941740502488166e-05, + "loss": 0.022, + "step": 1320 + }, + { + "epoch": 0.08, + "learning_rate": 2.9399198931909212e-05, + "loss": 0.0025, + "step": 1330 + }, + { + "epoch": 0.08, + "learning_rate": 2.9380992838936766e-05, + "loss": 0.0095, + "step": 1340 + }, + { + "epoch": 0.08, + "learning_rate": 2.9362786745964317e-05, + "loss": 0.0109, + "step": 1350 + }, + { + "epoch": 0.08, + "learning_rate": 2.9344580652991867e-05, + "loss": 0.0004, + "step": 1360 + }, + { + "epoch": 0.08, + "learning_rate": 2.932637456001942e-05, + "loss": 0.0001, + "step": 1370 + }, + { + "epoch": 0.08, + "learning_rate": 2.930816846704697e-05, + "loss": 0.0002, + "step": 1380 + }, + { + "epoch": 0.08, + "learning_rate": 2.9289962374074525e-05, + "loss": 0.0003, + "step": 1390 + }, + { + "epoch": 0.08, + "learning_rate": 2.927175628110208e-05, + "loss": 0.0001, + "step": 1400 + }, + { + "epoch": 0.08, + "learning_rate": 2.925355018812963e-05, + "loss": 0.0188, + "step": 1410 + }, + { + "epoch": 0.08, + "learning_rate": 2.923534409515718e-05, + "loss": 0.0016, + "step": 1420 + }, + { + "epoch": 0.08, + "learning_rate": 2.9217138002184734e-05, + "loss": 0.0091, + "step": 1430 + }, + { + "epoch": 0.08, + "learning_rate": 2.9198931909212285e-05, + "loss": 0.001, + "step": 1440 + }, + { + "epoch": 0.08, + "learning_rate": 2.9180725816239835e-05, + "loss": 0.0006, + "step": 1450 + }, + { + "epoch": 0.08, + "learning_rate": 2.916251972326739e-05, + "loss": 0.0521, + "step": 1460 + }, + { + "epoch": 0.08, + "learning_rate": 2.914431363029494e-05, + "loss": 0.0002, + "step": 1470 + }, + { + "epoch": 0.08, + "learning_rate": 2.912610753732249e-05, + "loss": 0.0761, + "step": 1480 + }, + { + "epoch": 0.09, + "learning_rate": 2.9107901444350044e-05, + "loss": 0.0071, + "step": 1490 + }, + { + "epoch": 0.09, + "learning_rate": 2.9089695351377595e-05, + "loss": 0.0475, + "step": 1500 + }, + { + "epoch": 0.09, + "learning_rate": 2.9071489258405145e-05, + "loss": 0.0006, + "step": 1510 + }, + { + "epoch": 0.09, + "learning_rate": 2.90532831654327e-05, + "loss": 0.0041, + "step": 1520 + }, + { + "epoch": 0.09, + "learning_rate": 2.903507707246025e-05, + "loss": 0.0003, + "step": 1530 + }, + { + "epoch": 0.09, + "learning_rate": 2.90168709794878e-05, + "loss": 0.0129, + "step": 1540 + }, + { + "epoch": 0.09, + "learning_rate": 2.8998664886515357e-05, + "loss": 0.0481, + "step": 1550 + }, + { + "epoch": 0.09, + "learning_rate": 2.8980458793542908e-05, + "loss": 0.0007, + "step": 1560 + }, + { + "epoch": 0.09, + "learning_rate": 2.896225270057046e-05, + "loss": 0.0701, + "step": 1570 + }, + { + "epoch": 0.09, + "learning_rate": 2.8944046607598012e-05, + "loss": 0.0068, + "step": 1580 + }, + { + "epoch": 0.09, + "learning_rate": 2.8925840514625563e-05, + "loss": 0.0343, + "step": 1590 + }, + { + "epoch": 0.09, + "learning_rate": 2.8907634421653113e-05, + "loss": 0.0104, + "step": 1600 + }, + { + "epoch": 0.09, + "learning_rate": 2.8889428328680667e-05, + "loss": 0.0007, + "step": 1610 + }, + { + "epoch": 0.09, + "learning_rate": 2.8871222235708218e-05, + "loss": 0.0004, + "step": 1620 + }, + { + "epoch": 0.09, + "learning_rate": 2.885301614273577e-05, + "loss": 0.0147, + "step": 1630 + }, + { + "epoch": 0.09, + "learning_rate": 2.8834810049763322e-05, + "loss": 0.0028, + "step": 1640 + }, + { + "epoch": 0.09, + "learning_rate": 2.8816603956790873e-05, + "loss": 0.0014, + "step": 1650 + }, + { + "epoch": 0.09, + "learning_rate": 2.8798397863818423e-05, + "loss": 0.0002, + "step": 1660 + }, + { + "epoch": 0.1, + "learning_rate": 2.8780191770845977e-05, + "loss": 0.0605, + "step": 1670 + }, + { + "epoch": 0.1, + "learning_rate": 2.8761985677873528e-05, + "loss": 0.0313, + "step": 1680 + }, + { + "epoch": 0.1, + "learning_rate": 2.874377958490108e-05, + "loss": 0.0017, + "step": 1690 + }, + { + "epoch": 0.1, + "learning_rate": 2.8725573491928632e-05, + "loss": 0.0241, + "step": 1700 + }, + { + "epoch": 0.1, + "learning_rate": 2.8707367398956186e-05, + "loss": 0.001, + "step": 1710 + }, + { + "epoch": 0.1, + "learning_rate": 2.8689161305983737e-05, + "loss": 0.0003, + "step": 1720 + }, + { + "epoch": 0.1, + "learning_rate": 2.867095521301129e-05, + "loss": 0.0003, + "step": 1730 + }, + { + "epoch": 0.1, + "learning_rate": 2.865274912003884e-05, + "loss": 0.0003, + "step": 1740 + }, + { + "epoch": 0.1, + "learning_rate": 2.863454302706639e-05, + "loss": 0.013, + "step": 1750 + }, + { + "epoch": 0.1, + "learning_rate": 2.8616336934093946e-05, + "loss": 0.0005, + "step": 1760 + }, + { + "epoch": 0.1, + "learning_rate": 2.8598130841121496e-05, + "loss": 0.0002, + "step": 1770 + }, + { + "epoch": 0.1, + "learning_rate": 2.8579924748149047e-05, + "loss": 0.0377, + "step": 1780 + }, + { + "epoch": 0.1, + "learning_rate": 2.85617186551766e-05, + "loss": 0.0002, + "step": 1790 + }, + { + "epoch": 0.1, + "learning_rate": 2.854351256220415e-05, + "loss": 0.0003, + "step": 1800 + }, + { + "epoch": 0.1, + "learning_rate": 2.85253064692317e-05, + "loss": 0.0454, + "step": 1810 + }, + { + "epoch": 0.1, + "learning_rate": 2.8507100376259255e-05, + "loss": 0.0003, + "step": 1820 + }, + { + "epoch": 0.1, + "learning_rate": 2.8488894283286806e-05, + "loss": 0.0002, + "step": 1830 + }, + { + "epoch": 0.11, + "learning_rate": 2.8470688190314357e-05, + "loss": 0.0002, + "step": 1840 + }, + { + "epoch": 0.11, + "learning_rate": 2.845248209734191e-05, + "loss": 0.0005, + "step": 1850 + }, + { + "epoch": 0.11, + "learning_rate": 2.8434276004369464e-05, + "loss": 0.0004, + "step": 1860 + }, + { + "epoch": 0.11, + "learning_rate": 2.8416069911397015e-05, + "loss": 0.0506, + "step": 1870 + }, + { + "epoch": 0.11, + "learning_rate": 2.839786381842457e-05, + "loss": 0.0472, + "step": 1880 + }, + { + "epoch": 0.11, + "learning_rate": 2.837965772545212e-05, + "loss": 0.0632, + "step": 1890 + }, + { + "epoch": 0.11, + "learning_rate": 2.836145163247967e-05, + "loss": 0.0484, + "step": 1900 + }, + { + "epoch": 0.11, + "learning_rate": 2.8343245539507224e-05, + "loss": 0.053, + "step": 1910 + }, + { + "epoch": 0.11, + "learning_rate": 2.8325039446534774e-05, + "loss": 0.0032, + "step": 1920 + }, + { + "epoch": 0.11, + "learning_rate": 2.8306833353562325e-05, + "loss": 0.0481, + "step": 1930 + }, + { + "epoch": 0.11, + "learning_rate": 2.828862726058988e-05, + "loss": 0.0026, + "step": 1940 + }, + { + "epoch": 0.11, + "learning_rate": 2.827042116761743e-05, + "loss": 0.0182, + "step": 1950 + }, + { + "epoch": 0.11, + "learning_rate": 2.825221507464498e-05, + "loss": 0.0009, + "step": 1960 + }, + { + "epoch": 0.11, + "learning_rate": 2.8234008981672534e-05, + "loss": 0.0011, + "step": 1970 + }, + { + "epoch": 0.11, + "learning_rate": 2.8215802888700084e-05, + "loss": 0.0181, + "step": 1980 + }, + { + "epoch": 0.11, + "learning_rate": 2.8197596795727635e-05, + "loss": 0.0359, + "step": 1990 + }, + { + "epoch": 0.11, + "learning_rate": 2.817939070275519e-05, + "loss": 0.0027, + "step": 2000 + }, + { + "epoch": 0.11, + "eval_loss": 0.014105047099292278, + "eval_runtime": 376.6099, + "eval_samples_per_second": 185.64, + "eval_steps_per_second": 11.604, + "step": 2000 + }, + { + "epoch": 0.11, + "learning_rate": 2.816118460978274e-05, + "loss": 0.0004, + "step": 2010 + }, + { + "epoch": 0.12, + "learning_rate": 2.8142978516810296e-05, + "loss": 0.0456, + "step": 2020 + }, + { + "epoch": 0.12, + "learning_rate": 2.8124772423837847e-05, + "loss": 0.0057, + "step": 2030 + }, + { + "epoch": 0.12, + "learning_rate": 2.8106566330865397e-05, + "loss": 0.0432, + "step": 2040 + }, + { + "epoch": 0.12, + "learning_rate": 2.808836023789295e-05, + "loss": 0.0581, + "step": 2050 + }, + { + "epoch": 0.12, + "learning_rate": 2.8070154144920502e-05, + "loss": 0.0132, + "step": 2060 + }, + { + "epoch": 0.12, + "learning_rate": 2.8051948051948052e-05, + "loss": 0.0193, + "step": 2070 + }, + { + "epoch": 0.12, + "learning_rate": 2.8033741958975606e-05, + "loss": 0.001, + "step": 2080 + }, + { + "epoch": 0.12, + "learning_rate": 2.8015535866003157e-05, + "loss": 0.0462, + "step": 2090 + }, + { + "epoch": 0.12, + "learning_rate": 2.7997329773030707e-05, + "loss": 0.0289, + "step": 2100 + }, + { + "epoch": 0.12, + "learning_rate": 2.797912368005826e-05, + "loss": 0.0016, + "step": 2110 + }, + { + "epoch": 0.12, + "learning_rate": 2.7960917587085812e-05, + "loss": 0.0207, + "step": 2120 + }, + { + "epoch": 0.12, + "learning_rate": 2.7942711494113362e-05, + "loss": 0.0371, + "step": 2130 + }, + { + "epoch": 0.12, + "learning_rate": 2.7924505401140916e-05, + "loss": 0.0143, + "step": 2140 + }, + { + "epoch": 0.12, + "learning_rate": 2.7906299308168467e-05, + "loss": 0.0031, + "step": 2150 + }, + { + "epoch": 0.12, + "learning_rate": 2.7888093215196017e-05, + "loss": 0.0018, + "step": 2160 + }, + { + "epoch": 0.12, + "learning_rate": 2.7869887122223575e-05, + "loss": 0.0066, + "step": 2170 + }, + { + "epoch": 0.12, + "learning_rate": 2.7851681029251125e-05, + "loss": 0.0004, + "step": 2180 + }, + { + "epoch": 0.13, + "learning_rate": 2.7833474936278676e-05, + "loss": 0.0249, + "step": 2190 + }, + { + "epoch": 0.13, + "learning_rate": 2.781526884330623e-05, + "loss": 0.0038, + "step": 2200 + }, + { + "epoch": 0.13, + "learning_rate": 2.779706275033378e-05, + "loss": 0.0002, + "step": 2210 + }, + { + "epoch": 0.13, + "learning_rate": 2.777885665736133e-05, + "loss": 0.0378, + "step": 2220 + }, + { + "epoch": 0.13, + "learning_rate": 2.7760650564388885e-05, + "loss": 0.0374, + "step": 2230 + }, + { + "epoch": 0.13, + "learning_rate": 2.7742444471416435e-05, + "loss": 0.0585, + "step": 2240 + }, + { + "epoch": 0.13, + "learning_rate": 2.7724238378443986e-05, + "loss": 0.0174, + "step": 2250 + }, + { + "epoch": 0.13, + "learning_rate": 2.770603228547154e-05, + "loss": 0.0006, + "step": 2260 + }, + { + "epoch": 0.13, + "learning_rate": 2.768782619249909e-05, + "loss": 0.0004, + "step": 2270 + }, + { + "epoch": 0.13, + "learning_rate": 2.766962009952664e-05, + "loss": 0.0057, + "step": 2280 + }, + { + "epoch": 0.13, + "learning_rate": 2.7651414006554194e-05, + "loss": 0.0716, + "step": 2290 + }, + { + "epoch": 0.13, + "learning_rate": 2.7633207913581745e-05, + "loss": 0.0049, + "step": 2300 + }, + { + "epoch": 0.13, + "learning_rate": 2.7615001820609295e-05, + "loss": 0.004, + "step": 2310 + }, + { + "epoch": 0.13, + "learning_rate": 2.759679572763685e-05, + "loss": 0.0004, + "step": 2320 + }, + { + "epoch": 0.13, + "learning_rate": 2.7578589634664403e-05, + "loss": 0.001, + "step": 2330 + }, + { + "epoch": 0.13, + "learning_rate": 2.7560383541691954e-05, + "loss": 0.0454, + "step": 2340 + }, + { + "epoch": 0.13, + "learning_rate": 2.7542177448719508e-05, + "loss": 0.0004, + "step": 2350 + }, + { + "epoch": 0.14, + "learning_rate": 2.7523971355747058e-05, + "loss": 0.0003, + "step": 2360 + }, + { + "epoch": 0.14, + "learning_rate": 2.750576526277461e-05, + "loss": 0.0003, + "step": 2370 + }, + { + "epoch": 0.14, + "learning_rate": 2.7487559169802163e-05, + "loss": 0.0143, + "step": 2380 + }, + { + "epoch": 0.14, + "learning_rate": 2.7469353076829713e-05, + "loss": 0.0367, + "step": 2390 + }, + { + "epoch": 0.14, + "learning_rate": 2.7451146983857264e-05, + "loss": 0.0401, + "step": 2400 + }, + { + "epoch": 0.14, + "learning_rate": 2.7432940890884818e-05, + "loss": 0.0128, + "step": 2410 + }, + { + "epoch": 0.14, + "learning_rate": 2.7414734797912368e-05, + "loss": 0.0035, + "step": 2420 + }, + { + "epoch": 0.14, + "learning_rate": 2.739652870493992e-05, + "loss": 0.0016, + "step": 2430 + }, + { + "epoch": 0.14, + "learning_rate": 2.7378322611967473e-05, + "loss": 0.0003, + "step": 2440 + }, + { + "epoch": 0.14, + "learning_rate": 2.7360116518995023e-05, + "loss": 0.0002, + "step": 2450 + }, + { + "epoch": 0.14, + "learning_rate": 2.7341910426022574e-05, + "loss": 0.0011, + "step": 2460 + }, + { + "epoch": 0.14, + "learning_rate": 2.7323704333050128e-05, + "loss": 0.016, + "step": 2470 + }, + { + "epoch": 0.14, + "learning_rate": 2.730549824007768e-05, + "loss": 0.0081, + "step": 2480 + }, + { + "epoch": 0.14, + "learning_rate": 2.7287292147105232e-05, + "loss": 0.0002, + "step": 2490 + }, + { + "epoch": 0.14, + "learning_rate": 2.7269086054132786e-05, + "loss": 0.0345, + "step": 2500 + }, + { + "epoch": 0.14, + "learning_rate": 2.7250879961160336e-05, + "loss": 0.0019, + "step": 2510 + }, + { + "epoch": 0.14, + "learning_rate": 2.7232673868187887e-05, + "loss": 0.0005, + "step": 2520 + }, + { + "epoch": 0.14, + "learning_rate": 2.721446777521544e-05, + "loss": 0.0199, + "step": 2530 + }, + { + "epoch": 0.15, + "learning_rate": 2.719626168224299e-05, + "loss": 0.0003, + "step": 2540 + }, + { + "epoch": 0.15, + "learning_rate": 2.7178055589270542e-05, + "loss": 0.0003, + "step": 2550 + }, + { + "epoch": 0.15, + "learning_rate": 2.7159849496298096e-05, + "loss": 0.0223, + "step": 2560 + }, + { + "epoch": 0.15, + "learning_rate": 2.7141643403325646e-05, + "loss": 0.0004, + "step": 2570 + }, + { + "epoch": 0.15, + "learning_rate": 2.7123437310353197e-05, + "loss": 0.002, + "step": 2580 + }, + { + "epoch": 0.15, + "learning_rate": 2.710523121738075e-05, + "loss": 0.0033, + "step": 2590 + }, + { + "epoch": 0.15, + "learning_rate": 2.70870251244083e-05, + "loss": 0.0493, + "step": 2600 + }, + { + "epoch": 0.15, + "learning_rate": 2.7068819031435852e-05, + "loss": 0.0299, + "step": 2610 + }, + { + "epoch": 0.15, + "learning_rate": 2.7050612938463406e-05, + "loss": 0.0001, + "step": 2620 + }, + { + "epoch": 0.15, + "learning_rate": 2.7032406845490956e-05, + "loss": 0.0487, + "step": 2630 + }, + { + "epoch": 0.15, + "learning_rate": 2.701420075251851e-05, + "loss": 0.001, + "step": 2640 + }, + { + "epoch": 0.15, + "learning_rate": 2.6995994659546064e-05, + "loss": 0.0001, + "step": 2650 + }, + { + "epoch": 0.15, + "learning_rate": 2.6977788566573615e-05, + "loss": 0.0005, + "step": 2660 + }, + { + "epoch": 0.15, + "learning_rate": 2.6959582473601165e-05, + "loss": 0.0097, + "step": 2670 + }, + { + "epoch": 0.15, + "learning_rate": 2.694137638062872e-05, + "loss": 0.0001, + "step": 2680 + }, + { + "epoch": 0.15, + "learning_rate": 2.692317028765627e-05, + "loss": 0.0002, + "step": 2690 + }, + { + "epoch": 0.15, + "learning_rate": 2.6904964194683823e-05, + "loss": 0.0082, + "step": 2700 + }, + { + "epoch": 0.16, + "learning_rate": 2.6886758101711374e-05, + "loss": 0.0002, + "step": 2710 + }, + { + "epoch": 0.16, + "learning_rate": 2.6868552008738925e-05, + "loss": 0.023, + "step": 2720 + }, + { + "epoch": 0.16, + "learning_rate": 2.685034591576648e-05, + "loss": 0.0019, + "step": 2730 + }, + { + "epoch": 0.16, + "learning_rate": 2.683213982279403e-05, + "loss": 0.0023, + "step": 2740 + }, + { + "epoch": 0.16, + "learning_rate": 2.681393372982158e-05, + "loss": 0.0928, + "step": 2750 + }, + { + "epoch": 0.16, + "learning_rate": 2.6795727636849133e-05, + "loss": 0.0007, + "step": 2760 + }, + { + "epoch": 0.16, + "learning_rate": 2.6777521543876684e-05, + "loss": 0.0006, + "step": 2770 + }, + { + "epoch": 0.16, + "learning_rate": 2.6759315450904234e-05, + "loss": 0.0091, + "step": 2780 + }, + { + "epoch": 0.16, + "learning_rate": 2.674110935793179e-05, + "loss": 0.001, + "step": 2790 + }, + { + "epoch": 0.16, + "learning_rate": 2.6722903264959342e-05, + "loss": 0.057, + "step": 2800 + }, + { + "epoch": 0.16, + "learning_rate": 2.6704697171986893e-05, + "loss": 0.0002, + "step": 2810 + }, + { + "epoch": 0.16, + "learning_rate": 2.6686491079014447e-05, + "loss": 0.0002, + "step": 2820 + }, + { + "epoch": 0.16, + "learning_rate": 2.6668284986041997e-05, + "loss": 0.0273, + "step": 2830 + }, + { + "epoch": 0.16, + "learning_rate": 2.6650078893069548e-05, + "loss": 0.0004, + "step": 2840 + }, + { + "epoch": 0.16, + "learning_rate": 2.66318728000971e-05, + "loss": 0.0239, + "step": 2850 + }, + { + "epoch": 0.16, + "learning_rate": 2.6613666707124652e-05, + "loss": 0.0003, + "step": 2860 + }, + { + "epoch": 0.16, + "learning_rate": 2.6595460614152203e-05, + "loss": 0.0003, + "step": 2870 + }, + { + "epoch": 0.16, + "learning_rate": 2.6577254521179757e-05, + "loss": 0.0281, + "step": 2880 + }, + { + "epoch": 0.17, + "learning_rate": 2.6559048428207307e-05, + "loss": 0.0009, + "step": 2890 + }, + { + "epoch": 0.17, + "learning_rate": 2.6540842335234858e-05, + "loss": 0.0015, + "step": 2900 + }, + { + "epoch": 0.17, + "learning_rate": 2.652263624226241e-05, + "loss": 0.007, + "step": 2910 + }, + { + "epoch": 0.17, + "learning_rate": 2.6504430149289962e-05, + "loss": 0.0349, + "step": 2920 + }, + { + "epoch": 0.17, + "learning_rate": 2.6486224056317513e-05, + "loss": 0.0004, + "step": 2930 + }, + { + "epoch": 0.17, + "learning_rate": 2.6468017963345067e-05, + "loss": 0.0504, + "step": 2940 + }, + { + "epoch": 0.17, + "learning_rate": 2.644981187037262e-05, + "loss": 0.0528, + "step": 2950 + }, + { + "epoch": 0.17, + "learning_rate": 2.643160577740017e-05, + "loss": 0.0542, + "step": 2960 + }, + { + "epoch": 0.17, + "learning_rate": 2.6413399684427725e-05, + "loss": 0.0008, + "step": 2970 + }, + { + "epoch": 0.17, + "learning_rate": 2.6395193591455275e-05, + "loss": 0.039, + "step": 2980 + }, + { + "epoch": 0.17, + "learning_rate": 2.6376987498482826e-05, + "loss": 0.0007, + "step": 2990 + }, + { + "epoch": 0.17, + "learning_rate": 2.635878140551038e-05, + "loss": 0.0017, + "step": 3000 + }, + { + "epoch": 0.17, + "eval_loss": 0.01332151610404253, + "eval_runtime": 374.8224, + "eval_samples_per_second": 186.526, + "eval_steps_per_second": 11.659, + "step": 3000 + }, + { + "epoch": 0.17, + "learning_rate": 2.634057531253793e-05, + "loss": 0.0013, + "step": 3010 + }, + { + "epoch": 0.17, + "learning_rate": 2.632236921956548e-05, + "loss": 0.0133, + "step": 3020 + }, + { + "epoch": 0.17, + "learning_rate": 2.6304163126593035e-05, + "loss": 0.0003, + "step": 3030 + }, + { + "epoch": 0.17, + "learning_rate": 2.6285957033620585e-05, + "loss": 0.0154, + "step": 3040 + }, + { + "epoch": 0.17, + "learning_rate": 2.6267750940648136e-05, + "loss": 0.0004, + "step": 3050 + }, + { + "epoch": 0.18, + "learning_rate": 2.624954484767569e-05, + "loss": 0.0003, + "step": 3060 + }, + { + "epoch": 0.18, + "learning_rate": 2.623133875470324e-05, + "loss": 0.0002, + "step": 3070 + }, + { + "epoch": 0.18, + "learning_rate": 2.621313266173079e-05, + "loss": 0.0001, + "step": 3080 + }, + { + "epoch": 0.18, + "learning_rate": 2.6194926568758345e-05, + "loss": 0.0002, + "step": 3090 + }, + { + "epoch": 0.18, + "learning_rate": 2.6176720475785895e-05, + "loss": 0.0468, + "step": 3100 + }, + { + "epoch": 0.18, + "learning_rate": 2.615851438281345e-05, + "loss": 0.0026, + "step": 3110 + }, + { + "epoch": 0.18, + "learning_rate": 2.6140308289841003e-05, + "loss": 0.0003, + "step": 3120 + }, + { + "epoch": 0.18, + "learning_rate": 2.6122102196868554e-05, + "loss": 0.0706, + "step": 3130 + }, + { + "epoch": 0.18, + "learning_rate": 2.6103896103896104e-05, + "loss": 0.0005, + "step": 3140 + }, + { + "epoch": 0.18, + "learning_rate": 2.6085690010923658e-05, + "loss": 0.0018, + "step": 3150 + }, + { + "epoch": 0.18, + "learning_rate": 2.606748391795121e-05, + "loss": 0.0178, + "step": 3160 + }, + { + "epoch": 0.18, + "learning_rate": 2.604927782497876e-05, + "loss": 0.0005, + "step": 3170 + }, + { + "epoch": 0.18, + "learning_rate": 2.6031071732006313e-05, + "loss": 0.0002, + "step": 3180 + }, + { + "epoch": 0.18, + "learning_rate": 2.6012865639033864e-05, + "loss": 0.0012, + "step": 3190 + }, + { + "epoch": 0.18, + "learning_rate": 2.5994659546061414e-05, + "loss": 0.0498, + "step": 3200 + }, + { + "epoch": 0.18, + "learning_rate": 2.5976453453088968e-05, + "loss": 0.0104, + "step": 3210 + }, + { + "epoch": 0.18, + "learning_rate": 2.595824736011652e-05, + "loss": 0.0077, + "step": 3220 + }, + { + "epoch": 0.18, + "learning_rate": 2.594004126714407e-05, + "loss": 0.0129, + "step": 3230 + }, + { + "epoch": 0.19, + "learning_rate": 2.5921835174171623e-05, + "loss": 0.0016, + "step": 3240 + }, + { + "epoch": 0.19, + "learning_rate": 2.5903629081199173e-05, + "loss": 0.06, + "step": 3250 + }, + { + "epoch": 0.19, + "learning_rate": 2.5885422988226727e-05, + "loss": 0.0003, + "step": 3260 + }, + { + "epoch": 0.19, + "learning_rate": 2.586721689525428e-05, + "loss": 0.0006, + "step": 3270 + }, + { + "epoch": 0.19, + "learning_rate": 2.5849010802281832e-05, + "loss": 0.0002, + "step": 3280 + }, + { + "epoch": 0.19, + "learning_rate": 2.5830804709309382e-05, + "loss": 0.0653, + "step": 3290 + }, + { + "epoch": 0.19, + "learning_rate": 2.5812598616336936e-05, + "loss": 0.0033, + "step": 3300 + }, + { + "epoch": 0.19, + "learning_rate": 2.5794392523364487e-05, + "loss": 0.0032, + "step": 3310 + }, + { + "epoch": 0.19, + "learning_rate": 2.5776186430392037e-05, + "loss": 0.0004, + "step": 3320 + }, + { + "epoch": 0.19, + "learning_rate": 2.575798033741959e-05, + "loss": 0.0007, + "step": 3330 + }, + { + "epoch": 0.19, + "learning_rate": 2.573977424444714e-05, + "loss": 0.0064, + "step": 3340 + }, + { + "epoch": 0.19, + "learning_rate": 2.5721568151474692e-05, + "loss": 0.0479, + "step": 3350 + }, + { + "epoch": 0.19, + "learning_rate": 2.5703362058502246e-05, + "loss": 0.0003, + "step": 3360 + }, + { + "epoch": 0.19, + "learning_rate": 2.5685155965529797e-05, + "loss": 0.0278, + "step": 3370 + }, + { + "epoch": 0.19, + "learning_rate": 2.566694987255735e-05, + "loss": 0.0422, + "step": 3380 + }, + { + "epoch": 0.19, + "learning_rate": 2.56487437795849e-05, + "loss": 0.0632, + "step": 3390 + }, + { + "epoch": 0.19, + "learning_rate": 2.563053768661245e-05, + "loss": 0.0006, + "step": 3400 + }, + { + "epoch": 0.2, + "learning_rate": 2.5612331593640006e-05, + "loss": 0.0007, + "step": 3410 + }, + { + "epoch": 0.2, + "learning_rate": 2.559412550066756e-05, + "loss": 0.0012, + "step": 3420 + }, + { + "epoch": 0.2, + "learning_rate": 2.557591940769511e-05, + "loss": 0.0007, + "step": 3430 + }, + { + "epoch": 0.2, + "learning_rate": 2.5557713314722664e-05, + "loss": 0.0422, + "step": 3440 + }, + { + "epoch": 0.2, + "learning_rate": 2.5539507221750214e-05, + "loss": 0.002, + "step": 3450 + }, + { + "epoch": 0.2, + "learning_rate": 2.5521301128777765e-05, + "loss": 0.0011, + "step": 3460 + }, + { + "epoch": 0.2, + "learning_rate": 2.550309503580532e-05, + "loss": 0.0003, + "step": 3470 + }, + { + "epoch": 0.2, + "learning_rate": 2.548488894283287e-05, + "loss": 0.0002, + "step": 3480 + }, + { + "epoch": 0.2, + "learning_rate": 2.546668284986042e-05, + "loss": 0.0002, + "step": 3490 + }, + { + "epoch": 0.2, + "learning_rate": 2.5448476756887974e-05, + "loss": 0.0007, + "step": 3500 + }, + { + "epoch": 0.2, + "learning_rate": 2.5430270663915524e-05, + "loss": 0.028, + "step": 3510 + }, + { + "epoch": 0.2, + "learning_rate": 2.5412064570943075e-05, + "loss": 0.0397, + "step": 3520 + }, + { + "epoch": 0.2, + "learning_rate": 2.539385847797063e-05, + "loss": 0.0004, + "step": 3530 + }, + { + "epoch": 0.2, + "learning_rate": 2.537565238499818e-05, + "loss": 0.0162, + "step": 3540 + }, + { + "epoch": 0.2, + "learning_rate": 2.535744629202573e-05, + "loss": 0.0008, + "step": 3550 + }, + { + "epoch": 0.2, + "learning_rate": 2.5339240199053284e-05, + "loss": 0.0005, + "step": 3560 + }, + { + "epoch": 0.2, + "learning_rate": 2.5321034106080838e-05, + "loss": 0.002, + "step": 3570 + }, + { + "epoch": 0.2, + "learning_rate": 2.5302828013108388e-05, + "loss": 0.0002, + "step": 3580 + }, + { + "epoch": 0.21, + "learning_rate": 2.5284621920135942e-05, + "loss": 0.0216, + "step": 3590 + }, + { + "epoch": 0.21, + "learning_rate": 2.5266415827163493e-05, + "loss": 0.0483, + "step": 3600 + }, + { + "epoch": 0.21, + "learning_rate": 2.5248209734191043e-05, + "loss": 0.0003, + "step": 3610 + }, + { + "epoch": 0.21, + "learning_rate": 2.5230003641218597e-05, + "loss": 0.0499, + "step": 3620 + }, + { + "epoch": 0.21, + "learning_rate": 2.5211797548246148e-05, + "loss": 0.0003, + "step": 3630 + }, + { + "epoch": 0.21, + "learning_rate": 2.5193591455273698e-05, + "loss": 0.0009, + "step": 3640 + }, + { + "epoch": 0.21, + "learning_rate": 2.5175385362301252e-05, + "loss": 0.0494, + "step": 3650 + }, + { + "epoch": 0.21, + "learning_rate": 2.5157179269328802e-05, + "loss": 0.059, + "step": 3660 + }, + { + "epoch": 0.21, + "learning_rate": 2.5138973176356353e-05, + "loss": 0.0007, + "step": 3670 + }, + { + "epoch": 0.21, + "learning_rate": 2.5120767083383907e-05, + "loss": 0.001, + "step": 3680 + }, + { + "epoch": 0.21, + "learning_rate": 2.5102560990411457e-05, + "loss": 0.0843, + "step": 3690 + }, + { + "epoch": 0.21, + "learning_rate": 2.5084354897439008e-05, + "loss": 0.0006, + "step": 3700 + }, + { + "epoch": 0.21, + "learning_rate": 2.5066148804466562e-05, + "loss": 0.0022, + "step": 3710 + }, + { + "epoch": 0.21, + "learning_rate": 2.5047942711494112e-05, + "loss": 0.0005, + "step": 3720 + }, + { + "epoch": 0.21, + "learning_rate": 2.5029736618521666e-05, + "loss": 0.0002, + "step": 3730 + }, + { + "epoch": 0.21, + "learning_rate": 2.501153052554922e-05, + "loss": 0.0003, + "step": 3740 + }, + { + "epoch": 0.21, + "learning_rate": 2.499332443257677e-05, + "loss": 0.0625, + "step": 3750 + }, + { + "epoch": 0.22, + "learning_rate": 2.497511833960432e-05, + "loss": 0.0122, + "step": 3760 + }, + { + "epoch": 0.22, + "learning_rate": 2.4956912246631875e-05, + "loss": 0.0478, + "step": 3770 + }, + { + "epoch": 0.22, + "learning_rate": 2.4938706153659426e-05, + "loss": 0.0008, + "step": 3780 + }, + { + "epoch": 0.22, + "learning_rate": 2.4920500060686976e-05, + "loss": 0.0006, + "step": 3790 + }, + { + "epoch": 0.22, + "learning_rate": 2.490229396771453e-05, + "loss": 0.0013, + "step": 3800 + }, + { + "epoch": 0.22, + "learning_rate": 2.488408787474208e-05, + "loss": 0.001, + "step": 3810 + }, + { + "epoch": 0.22, + "learning_rate": 2.486588178176963e-05, + "loss": 0.047, + "step": 3820 + }, + { + "epoch": 0.22, + "learning_rate": 2.4847675688797185e-05, + "loss": 0.0007, + "step": 3830 + }, + { + "epoch": 0.22, + "learning_rate": 2.4829469595824736e-05, + "loss": 0.035, + "step": 3840 + }, + { + "epoch": 0.22, + "learning_rate": 2.4811263502852286e-05, + "loss": 0.028, + "step": 3850 + }, + { + "epoch": 0.22, + "learning_rate": 2.479305740987984e-05, + "loss": 0.0007, + "step": 3860 + }, + { + "epoch": 0.22, + "learning_rate": 2.477485131690739e-05, + "loss": 0.0011, + "step": 3870 + }, + { + "epoch": 0.22, + "learning_rate": 2.475664522393494e-05, + "loss": 0.0014, + "step": 3880 + }, + { + "epoch": 0.22, + "learning_rate": 2.47384391309625e-05, + "loss": 0.0003, + "step": 3890 + }, + { + "epoch": 0.22, + "learning_rate": 2.472023303799005e-05, + "loss": 0.0447, + "step": 3900 + }, + { + "epoch": 0.22, + "learning_rate": 2.47020269450176e-05, + "loss": 0.0008, + "step": 3910 + }, + { + "epoch": 0.22, + "learning_rate": 2.4683820852045153e-05, + "loss": 0.0009, + "step": 3920 + }, + { + "epoch": 0.22, + "learning_rate": 2.4665614759072704e-05, + "loss": 0.0007, + "step": 3930 + }, + { + "epoch": 0.23, + "learning_rate": 2.4647408666100254e-05, + "loss": 0.0004, + "step": 3940 + }, + { + "epoch": 0.23, + "learning_rate": 2.462920257312781e-05, + "loss": 0.0003, + "step": 3950 + }, + { + "epoch": 0.23, + "learning_rate": 2.461099648015536e-05, + "loss": 0.0003, + "step": 3960 + }, + { + "epoch": 0.23, + "learning_rate": 2.459279038718291e-05, + "loss": 0.0006, + "step": 3970 + }, + { + "epoch": 0.23, + "learning_rate": 2.4574584294210463e-05, + "loss": 0.0003, + "step": 3980 + }, + { + "epoch": 0.23, + "learning_rate": 2.4556378201238014e-05, + "loss": 0.0002, + "step": 3990 + }, + { + "epoch": 0.23, + "learning_rate": 2.4538172108265564e-05, + "loss": 0.0447, + "step": 4000 + }, + { + "epoch": 0.23, + "eval_loss": 0.01801093854010105, + "eval_runtime": 372.5794, + "eval_samples_per_second": 187.649, + "eval_steps_per_second": 11.729, + "step": 4000 + }, + { + "epoch": 0.23, + "learning_rate": 2.4519966015293118e-05, + "loss": 0.0004, + "step": 4010 + }, + { + "epoch": 0.23, + "learning_rate": 2.450175992232067e-05, + "loss": 0.0588, + "step": 4020 + }, + { + "epoch": 0.23, + "learning_rate": 2.448355382934822e-05, + "loss": 0.0523, + "step": 4030 + }, + { + "epoch": 0.23, + "learning_rate": 2.4465347736375777e-05, + "loss": 0.0009, + "step": 4040 + }, + { + "epoch": 0.23, + "learning_rate": 2.4447141643403327e-05, + "loss": 0.017, + "step": 4050 + }, + { + "epoch": 0.23, + "learning_rate": 2.442893555043088e-05, + "loss": 0.0244, + "step": 4060 + }, + { + "epoch": 0.23, + "learning_rate": 2.441072945745843e-05, + "loss": 0.0003, + "step": 4070 + }, + { + "epoch": 0.23, + "learning_rate": 2.4392523364485982e-05, + "loss": 0.0026, + "step": 4080 + }, + { + "epoch": 0.23, + "learning_rate": 2.4374317271513536e-05, + "loss": 0.0305, + "step": 4090 + }, + { + "epoch": 0.23, + "learning_rate": 2.4356111178541086e-05, + "loss": 0.0007, + "step": 4100 + }, + { + "epoch": 0.24, + "learning_rate": 2.4337905085568637e-05, + "loss": 0.0208, + "step": 4110 + }, + { + "epoch": 0.24, + "learning_rate": 2.431969899259619e-05, + "loss": 0.0191, + "step": 4120 + }, + { + "epoch": 0.24, + "learning_rate": 2.430149289962374e-05, + "loss": 0.0212, + "step": 4130 + }, + { + "epoch": 0.24, + "learning_rate": 2.4283286806651292e-05, + "loss": 0.0269, + "step": 4140 + }, + { + "epoch": 0.24, + "learning_rate": 2.4265080713678846e-05, + "loss": 0.0005, + "step": 4150 + }, + { + "epoch": 0.24, + "learning_rate": 2.4246874620706396e-05, + "loss": 0.0109, + "step": 4160 + }, + { + "epoch": 0.24, + "learning_rate": 2.4228668527733947e-05, + "loss": 0.0007, + "step": 4170 + }, + { + "epoch": 0.24, + "learning_rate": 2.42104624347615e-05, + "loss": 0.0021, + "step": 4180 + }, + { + "epoch": 0.24, + "learning_rate": 2.419225634178905e-05, + "loss": 0.0046, + "step": 4190 + }, + { + "epoch": 0.24, + "learning_rate": 2.4174050248816605e-05, + "loss": 0.0538, + "step": 4200 + }, + { + "epoch": 0.24, + "learning_rate": 2.415584415584416e-05, + "loss": 0.0002, + "step": 4210 + }, + { + "epoch": 0.24, + "learning_rate": 2.413763806287171e-05, + "loss": 0.0167, + "step": 4220 + }, + { + "epoch": 0.24, + "learning_rate": 2.411943196989926e-05, + "loss": 0.0004, + "step": 4230 + }, + { + "epoch": 0.24, + "learning_rate": 2.4101225876926814e-05, + "loss": 0.0002, + "step": 4240 + }, + { + "epoch": 0.24, + "learning_rate": 2.4083019783954365e-05, + "loss": 0.066, + "step": 4250 + }, + { + "epoch": 0.24, + "learning_rate": 2.4064813690981915e-05, + "loss": 0.0681, + "step": 4260 + }, + { + "epoch": 0.24, + "learning_rate": 2.404660759800947e-05, + "loss": 0.0005, + "step": 4270 + }, + { + "epoch": 0.24, + "learning_rate": 2.402840150503702e-05, + "loss": 0.0005, + "step": 4280 + }, + { + "epoch": 0.25, + "learning_rate": 2.401019541206457e-05, + "loss": 0.0531, + "step": 4290 + }, + { + "epoch": 0.25, + "learning_rate": 2.3991989319092124e-05, + "loss": 0.0346, + "step": 4300 + }, + { + "epoch": 0.25, + "learning_rate": 2.3973783226119675e-05, + "loss": 0.0023, + "step": 4310 + }, + { + "epoch": 0.25, + "learning_rate": 2.3955577133147225e-05, + "loss": 0.0017, + "step": 4320 + }, + { + "epoch": 0.25, + "learning_rate": 2.393737104017478e-05, + "loss": 0.0019, + "step": 4330 + }, + { + "epoch": 0.25, + "learning_rate": 2.391916494720233e-05, + "loss": 0.0003, + "step": 4340 + }, + { + "epoch": 0.25, + "learning_rate": 2.3900958854229883e-05, + "loss": 0.0307, + "step": 4350 + }, + { + "epoch": 0.25, + "learning_rate": 2.3882752761257437e-05, + "loss": 0.0279, + "step": 4360 + }, + { + "epoch": 0.25, + "learning_rate": 2.3864546668284988e-05, + "loss": 0.0122, + "step": 4370 + }, + { + "epoch": 0.25, + "learning_rate": 2.384634057531254e-05, + "loss": 0.1179, + "step": 4380 + }, + { + "epoch": 0.25, + "learning_rate": 2.3828134482340092e-05, + "loss": 0.0512, + "step": 4390 + }, + { + "epoch": 0.25, + "learning_rate": 2.3809928389367643e-05, + "loss": 0.0407, + "step": 4400 + }, + { + "epoch": 0.25, + "learning_rate": 2.3791722296395193e-05, + "loss": 0.0013, + "step": 4410 + }, + { + "epoch": 0.25, + "learning_rate": 2.3773516203422747e-05, + "loss": 0.0277, + "step": 4420 + }, + { + "epoch": 0.25, + "learning_rate": 2.3755310110450298e-05, + "loss": 0.001, + "step": 4430 + }, + { + "epoch": 0.25, + "learning_rate": 2.373710401747785e-05, + "loss": 0.0287, + "step": 4440 + }, + { + "epoch": 0.25, + "learning_rate": 2.3718897924505402e-05, + "loss": 0.0005, + "step": 4450 + }, + { + "epoch": 0.26, + "learning_rate": 2.3700691831532953e-05, + "loss": 0.0018, + "step": 4460 + }, + { + "epoch": 0.26, + "learning_rate": 2.3682485738560503e-05, + "loss": 0.0003, + "step": 4470 + }, + { + "epoch": 0.26, + "learning_rate": 2.3664279645588057e-05, + "loss": 0.0003, + "step": 4480 + }, + { + "epoch": 0.26, + "learning_rate": 2.3646073552615608e-05, + "loss": 0.0018, + "step": 4490 + }, + { + "epoch": 0.26, + "learning_rate": 2.3627867459643158e-05, + "loss": 0.0005, + "step": 4500 + }, + { + "epoch": 0.26, + "learning_rate": 2.3609661366670716e-05, + "loss": 0.0523, + "step": 4510 + }, + { + "epoch": 0.26, + "learning_rate": 2.3591455273698266e-05, + "loss": 0.0275, + "step": 4520 + }, + { + "epoch": 0.26, + "learning_rate": 2.3573249180725817e-05, + "loss": 0.0003, + "step": 4530 + }, + { + "epoch": 0.26, + "learning_rate": 2.355504308775337e-05, + "loss": 0.0008, + "step": 4540 + }, + { + "epoch": 0.26, + "learning_rate": 2.353683699478092e-05, + "loss": 0.0006, + "step": 4550 + }, + { + "epoch": 0.26, + "learning_rate": 2.351863090180847e-05, + "loss": 0.0002, + "step": 4560 + }, + { + "epoch": 0.26, + "learning_rate": 2.3500424808836025e-05, + "loss": 0.0281, + "step": 4570 + }, + { + "epoch": 0.26, + "learning_rate": 2.3482218715863576e-05, + "loss": 0.0004, + "step": 4580 + }, + { + "epoch": 0.26, + "learning_rate": 2.3464012622891127e-05, + "loss": 0.0215, + "step": 4590 + }, + { + "epoch": 0.26, + "learning_rate": 2.344580652991868e-05, + "loss": 0.0459, + "step": 4600 + }, + { + "epoch": 0.26, + "learning_rate": 2.342760043694623e-05, + "loss": 0.0014, + "step": 4610 + }, + { + "epoch": 0.26, + "learning_rate": 2.340939434397378e-05, + "loss": 0.0005, + "step": 4620 + }, + { + "epoch": 0.26, + "learning_rate": 2.3391188251001335e-05, + "loss": 0.0007, + "step": 4630 + }, + { + "epoch": 0.27, + "learning_rate": 2.3372982158028886e-05, + "loss": 0.0003, + "step": 4640 + }, + { + "epoch": 0.27, + "learning_rate": 2.3354776065056436e-05, + "loss": 0.0002, + "step": 4650 + }, + { + "epoch": 0.27, + "learning_rate": 2.333656997208399e-05, + "loss": 0.0002, + "step": 4660 + }, + { + "epoch": 0.27, + "learning_rate": 2.3318363879111544e-05, + "loss": 0.0002, + "step": 4670 + }, + { + "epoch": 0.27, + "learning_rate": 2.3300157786139095e-05, + "loss": 0.0376, + "step": 4680 + }, + { + "epoch": 0.27, + "learning_rate": 2.328195169316665e-05, + "loss": 0.0498, + "step": 4690 + }, + { + "epoch": 0.27, + "learning_rate": 2.32637456001942e-05, + "loss": 0.0014, + "step": 4700 + }, + { + "epoch": 0.27, + "learning_rate": 2.324553950722175e-05, + "loss": 0.0142, + "step": 4710 + }, + { + "epoch": 0.27, + "learning_rate": 2.3227333414249304e-05, + "loss": 0.0004, + "step": 4720 + }, + { + "epoch": 0.27, + "learning_rate": 2.3209127321276854e-05, + "loss": 0.0005, + "step": 4730 + }, + { + "epoch": 0.27, + "learning_rate": 2.3190921228304408e-05, + "loss": 0.058, + "step": 4740 + }, + { + "epoch": 0.27, + "learning_rate": 2.317271513533196e-05, + "loss": 0.0026, + "step": 4750 + }, + { + "epoch": 0.27, + "learning_rate": 2.315450904235951e-05, + "loss": 0.0004, + "step": 4760 + }, + { + "epoch": 0.27, + "learning_rate": 2.3136302949387063e-05, + "loss": 0.0006, + "step": 4770 + }, + { + "epoch": 0.27, + "learning_rate": 2.3118096856414614e-05, + "loss": 0.0638, + "step": 4780 + }, + { + "epoch": 0.27, + "learning_rate": 2.3099890763442164e-05, + "loss": 0.001, + "step": 4790 + }, + { + "epoch": 0.27, + "learning_rate": 2.3081684670469718e-05, + "loss": 0.0625, + "step": 4800 + }, + { + "epoch": 0.28, + "learning_rate": 2.306347857749727e-05, + "loss": 0.0013, + "step": 4810 + }, + { + "epoch": 0.28, + "learning_rate": 2.3045272484524822e-05, + "loss": 0.0017, + "step": 4820 + }, + { + "epoch": 0.28, + "learning_rate": 2.3027066391552376e-05, + "loss": 0.0005, + "step": 4830 + }, + { + "epoch": 0.28, + "learning_rate": 2.3008860298579927e-05, + "loss": 0.0005, + "step": 4840 + }, + { + "epoch": 0.28, + "learning_rate": 2.2990654205607477e-05, + "loss": 0.0003, + "step": 4850 + }, + { + "epoch": 0.28, + "learning_rate": 2.297244811263503e-05, + "loss": 0.0257, + "step": 4860 + }, + { + "epoch": 0.28, + "learning_rate": 2.2954242019662582e-05, + "loss": 0.0221, + "step": 4870 + }, + { + "epoch": 0.28, + "learning_rate": 2.2936035926690132e-05, + "loss": 0.0002, + "step": 4880 + }, + { + "epoch": 0.28, + "learning_rate": 2.2917829833717686e-05, + "loss": 0.0004, + "step": 4890 + }, + { + "epoch": 0.28, + "learning_rate": 2.2899623740745237e-05, + "loss": 0.0183, + "step": 4900 + }, + { + "epoch": 0.28, + "learning_rate": 2.2881417647772787e-05, + "loss": 0.0094, + "step": 4910 + }, + { + "epoch": 0.28, + "learning_rate": 2.286321155480034e-05, + "loss": 0.0096, + "step": 4920 + }, + { + "epoch": 0.28, + "learning_rate": 2.2845005461827892e-05, + "loss": 0.0006, + "step": 4930 + }, + { + "epoch": 0.28, + "learning_rate": 2.2826799368855442e-05, + "loss": 0.0105, + "step": 4940 + }, + { + "epoch": 0.28, + "learning_rate": 2.2808593275882996e-05, + "loss": 0.0683, + "step": 4950 + }, + { + "epoch": 0.28, + "learning_rate": 2.2790387182910547e-05, + "loss": 0.0184, + "step": 4960 + }, + { + "epoch": 0.28, + "learning_rate": 2.2772181089938097e-05, + "loss": 0.0002, + "step": 4970 + }, + { + "epoch": 0.28, + "learning_rate": 2.2753974996965655e-05, + "loss": 0.0238, + "step": 4980 + }, + { + "epoch": 0.29, + "learning_rate": 2.2735768903993205e-05, + "loss": 0.0003, + "step": 4990 + }, + { + "epoch": 0.29, + "learning_rate": 2.2717562811020756e-05, + "loss": 0.0016, + "step": 5000 + }, + { + "epoch": 0.29, + "eval_loss": 0.018033137544989586, + "eval_runtime": 373.1081, + "eval_samples_per_second": 187.383, + "eval_steps_per_second": 11.712, + "step": 5000 + }, + { + "epoch": 0.29, + "learning_rate": 2.269935671804831e-05, + "loss": 0.0217, + "step": 5010 + }, + { + "epoch": 0.29, + "learning_rate": 2.268115062507586e-05, + "loss": 0.0483, + "step": 5020 + }, + { + "epoch": 0.29, + "learning_rate": 2.266294453210341e-05, + "loss": 0.0557, + "step": 5030 + }, + { + "epoch": 0.29, + "learning_rate": 2.2644738439130964e-05, + "loss": 0.0516, + "step": 5040 + }, + { + "epoch": 0.29, + "learning_rate": 2.2626532346158515e-05, + "loss": 0.0023, + "step": 5050 + }, + { + "epoch": 0.29, + "learning_rate": 2.2608326253186065e-05, + "loss": 0.053, + "step": 5060 + }, + { + "epoch": 0.29, + "learning_rate": 2.259012016021362e-05, + "loss": 0.0259, + "step": 5070 + }, + { + "epoch": 0.29, + "learning_rate": 2.257191406724117e-05, + "loss": 0.0129, + "step": 5080 + }, + { + "epoch": 0.29, + "learning_rate": 2.255370797426872e-05, + "loss": 0.0319, + "step": 5090 + }, + { + "epoch": 0.29, + "learning_rate": 2.2535501881296274e-05, + "loss": 0.0117, + "step": 5100 + }, + { + "epoch": 0.29, + "learning_rate": 2.2517295788323825e-05, + "loss": 0.0096, + "step": 5110 + }, + { + "epoch": 0.29, + "learning_rate": 2.2499089695351375e-05, + "loss": 0.0004, + "step": 5120 + }, + { + "epoch": 0.29, + "learning_rate": 2.2480883602378933e-05, + "loss": 0.0004, + "step": 5130 + }, + { + "epoch": 0.29, + "learning_rate": 2.2462677509406483e-05, + "loss": 0.0013, + "step": 5140 + }, + { + "epoch": 0.29, + "learning_rate": 2.2444471416434034e-05, + "loss": 0.0047, + "step": 5150 + }, + { + "epoch": 0.3, + "learning_rate": 2.2426265323461588e-05, + "loss": 0.0085, + "step": 5160 + }, + { + "epoch": 0.3, + "learning_rate": 2.2408059230489138e-05, + "loss": 0.0005, + "step": 5170 + }, + { + "epoch": 0.3, + "learning_rate": 2.238985313751669e-05, + "loss": 0.0337, + "step": 5180 + }, + { + "epoch": 0.3, + "learning_rate": 2.2371647044544243e-05, + "loss": 0.0034, + "step": 5190 + }, + { + "epoch": 0.3, + "learning_rate": 2.2353440951571793e-05, + "loss": 0.0005, + "step": 5200 + }, + { + "epoch": 0.3, + "learning_rate": 2.2335234858599344e-05, + "loss": 0.0077, + "step": 5210 + }, + { + "epoch": 0.3, + "learning_rate": 2.2317028765626898e-05, + "loss": 0.0013, + "step": 5220 + }, + { + "epoch": 0.3, + "learning_rate": 2.2298822672654448e-05, + "loss": 0.0517, + "step": 5230 + }, + { + "epoch": 0.3, + "learning_rate": 2.2280616579682e-05, + "loss": 0.0003, + "step": 5240 + }, + { + "epoch": 0.3, + "learning_rate": 2.2262410486709553e-05, + "loss": 0.0071, + "step": 5250 + }, + { + "epoch": 0.3, + "learning_rate": 2.2244204393737103e-05, + "loss": 0.0529, + "step": 5260 + }, + { + "epoch": 0.3, + "learning_rate": 2.2225998300764654e-05, + "loss": 0.0515, + "step": 5270 + }, + { + "epoch": 0.3, + "learning_rate": 2.2207792207792207e-05, + "loss": 0.001, + "step": 5280 + }, + { + "epoch": 0.3, + "learning_rate": 2.218958611481976e-05, + "loss": 0.036, + "step": 5290 + }, + { + "epoch": 0.3, + "learning_rate": 2.2171380021847312e-05, + "loss": 0.0141, + "step": 5300 + }, + { + "epoch": 0.3, + "learning_rate": 2.2153173928874866e-05, + "loss": 0.0006, + "step": 5310 + }, + { + "epoch": 0.3, + "learning_rate": 2.2134967835902416e-05, + "loss": 0.0007, + "step": 5320 + }, + { + "epoch": 0.3, + "learning_rate": 2.2116761742929967e-05, + "loss": 0.0057, + "step": 5330 + }, + { + "epoch": 0.31, + "learning_rate": 2.209855564995752e-05, + "loss": 0.0075, + "step": 5340 + }, + { + "epoch": 0.31, + "learning_rate": 2.208034955698507e-05, + "loss": 0.0004, + "step": 5350 + }, + { + "epoch": 0.31, + "learning_rate": 2.2062143464012622e-05, + "loss": 0.0532, + "step": 5360 + }, + { + "epoch": 0.31, + "learning_rate": 2.2043937371040176e-05, + "loss": 0.0299, + "step": 5370 + }, + { + "epoch": 0.31, + "learning_rate": 2.2025731278067726e-05, + "loss": 0.0375, + "step": 5380 + }, + { + "epoch": 0.31, + "learning_rate": 2.200752518509528e-05, + "loss": 0.001, + "step": 5390 + }, + { + "epoch": 0.31, + "learning_rate": 2.198931909212283e-05, + "loss": 0.0007, + "step": 5400 + }, + { + "epoch": 0.31, + "learning_rate": 2.197111299915038e-05, + "loss": 0.002, + "step": 5410 + }, + { + "epoch": 0.31, + "learning_rate": 2.1952906906177935e-05, + "loss": 0.0236, + "step": 5420 + }, + { + "epoch": 0.31, + "learning_rate": 2.1934700813205486e-05, + "loss": 0.0061, + "step": 5430 + }, + { + "epoch": 0.31, + "learning_rate": 2.191649472023304e-05, + "loss": 0.0003, + "step": 5440 + }, + { + "epoch": 0.31, + "learning_rate": 2.1898288627260593e-05, + "loss": 0.0004, + "step": 5450 + }, + { + "epoch": 0.31, + "learning_rate": 2.1880082534288144e-05, + "loss": 0.0321, + "step": 5460 + }, + { + "epoch": 0.31, + "learning_rate": 2.1861876441315695e-05, + "loss": 0.0265, + "step": 5470 + }, + { + "epoch": 0.31, + "learning_rate": 2.184367034834325e-05, + "loss": 0.0075, + "step": 5480 + }, + { + "epoch": 0.31, + "learning_rate": 2.18254642553708e-05, + "loss": 0.0423, + "step": 5490 + }, + { + "epoch": 0.31, + "learning_rate": 2.180725816239835e-05, + "loss": 0.0017, + "step": 5500 + }, + { + "epoch": 0.32, + "learning_rate": 2.1789052069425903e-05, + "loss": 0.001, + "step": 5510 + }, + { + "epoch": 0.32, + "learning_rate": 2.1770845976453454e-05, + "loss": 0.0006, + "step": 5520 + }, + { + "epoch": 0.32, + "learning_rate": 2.1752639883481004e-05, + "loss": 0.0006, + "step": 5530 + }, + { + "epoch": 0.32, + "learning_rate": 2.173443379050856e-05, + "loss": 0.0166, + "step": 5540 + }, + { + "epoch": 0.32, + "learning_rate": 2.171622769753611e-05, + "loss": 0.0002, + "step": 5550 + }, + { + "epoch": 0.32, + "learning_rate": 2.169802160456366e-05, + "loss": 0.0001, + "step": 5560 + }, + { + "epoch": 0.32, + "learning_rate": 2.1679815511591213e-05, + "loss": 0.0485, + "step": 5570 + }, + { + "epoch": 0.32, + "learning_rate": 2.1661609418618764e-05, + "loss": 0.0005, + "step": 5580 + }, + { + "epoch": 0.32, + "learning_rate": 2.1643403325646314e-05, + "loss": 0.0004, + "step": 5590 + }, + { + "epoch": 0.32, + "learning_rate": 2.162519723267387e-05, + "loss": 0.0004, + "step": 5600 + }, + { + "epoch": 0.32, + "learning_rate": 2.1606991139701422e-05, + "loss": 0.0131, + "step": 5610 + }, + { + "epoch": 0.32, + "learning_rate": 2.1588785046728973e-05, + "loss": 0.0002, + "step": 5620 + }, + { + "epoch": 0.32, + "learning_rate": 2.1570578953756527e-05, + "loss": 0.0001, + "step": 5630 + }, + { + "epoch": 0.32, + "learning_rate": 2.1552372860784077e-05, + "loss": 0.0039, + "step": 5640 + }, + { + "epoch": 0.32, + "learning_rate": 2.1534166767811628e-05, + "loss": 0.0001, + "step": 5650 + }, + { + "epoch": 0.32, + "learning_rate": 2.151596067483918e-05, + "loss": 0.0001, + "step": 5660 + }, + { + "epoch": 0.32, + "learning_rate": 2.1497754581866732e-05, + "loss": 0.0027, + "step": 5670 + }, + { + "epoch": 0.32, + "learning_rate": 2.1479548488894283e-05, + "loss": 0.0047, + "step": 5680 + }, + { + "epoch": 0.33, + "learning_rate": 2.1461342395921837e-05, + "loss": 0.0283, + "step": 5690 + }, + { + "epoch": 0.33, + "learning_rate": 2.1443136302949387e-05, + "loss": 0.0001, + "step": 5700 + }, + { + "epoch": 0.33, + "learning_rate": 2.1424930209976938e-05, + "loss": 0.0455, + "step": 5710 + }, + { + "epoch": 0.33, + "learning_rate": 2.140672411700449e-05, + "loss": 0.0003, + "step": 5720 + }, + { + "epoch": 0.33, + "learning_rate": 2.1388518024032042e-05, + "loss": 0.0111, + "step": 5730 + }, + { + "epoch": 0.33, + "learning_rate": 2.1370311931059593e-05, + "loss": 0.0002, + "step": 5740 + }, + { + "epoch": 0.33, + "learning_rate": 2.1352105838087146e-05, + "loss": 0.1088, + "step": 5750 + }, + { + "epoch": 0.33, + "learning_rate": 2.13338997451147e-05, + "loss": 0.0004, + "step": 5760 + }, + { + "epoch": 0.33, + "learning_rate": 2.131569365214225e-05, + "loss": 0.0408, + "step": 5770 + }, + { + "epoch": 0.33, + "learning_rate": 2.1297487559169805e-05, + "loss": 0.0012, + "step": 5780 + }, + { + "epoch": 0.33, + "learning_rate": 2.1279281466197355e-05, + "loss": 0.0019, + "step": 5790 + }, + { + "epoch": 0.33, + "learning_rate": 2.1261075373224906e-05, + "loss": 0.0089, + "step": 5800 + }, + { + "epoch": 0.33, + "learning_rate": 2.124286928025246e-05, + "loss": 0.0017, + "step": 5810 + }, + { + "epoch": 0.33, + "learning_rate": 2.122466318728001e-05, + "loss": 0.0002, + "step": 5820 + }, + { + "epoch": 0.33, + "learning_rate": 2.120645709430756e-05, + "loss": 0.0003, + "step": 5830 + }, + { + "epoch": 0.33, + "learning_rate": 2.1188251001335115e-05, + "loss": 0.0001, + "step": 5840 + }, + { + "epoch": 0.33, + "learning_rate": 2.1170044908362665e-05, + "loss": 0.0356, + "step": 5850 + }, + { + "epoch": 0.34, + "learning_rate": 2.1151838815390216e-05, + "loss": 0.0002, + "step": 5860 + }, + { + "epoch": 0.34, + "learning_rate": 2.113363272241777e-05, + "loss": 0.0004, + "step": 5870 + }, + { + "epoch": 0.34, + "learning_rate": 2.111542662944532e-05, + "loss": 0.0292, + "step": 5880 + }, + { + "epoch": 0.34, + "learning_rate": 2.109722053647287e-05, + "loss": 0.0043, + "step": 5890 + }, + { + "epoch": 0.34, + "learning_rate": 2.1079014443500425e-05, + "loss": 0.0009, + "step": 5900 + }, + { + "epoch": 0.34, + "learning_rate": 2.106080835052798e-05, + "loss": 0.0511, + "step": 5910 + }, + { + "epoch": 0.34, + "learning_rate": 2.104260225755553e-05, + "loss": 0.0002, + "step": 5920 + }, + { + "epoch": 0.34, + "learning_rate": 2.1024396164583083e-05, + "loss": 0.0059, + "step": 5930 + }, + { + "epoch": 0.34, + "learning_rate": 2.1006190071610633e-05, + "loss": 0.0006, + "step": 5940 + }, + { + "epoch": 0.34, + "learning_rate": 2.0987983978638184e-05, + "loss": 0.0239, + "step": 5950 + }, + { + "epoch": 0.34, + "learning_rate": 2.0969777885665738e-05, + "loss": 0.013, + "step": 5960 + }, + { + "epoch": 0.34, + "learning_rate": 2.095157179269329e-05, + "loss": 0.0002, + "step": 5970 + }, + { + "epoch": 0.34, + "learning_rate": 2.093336569972084e-05, + "loss": 0.0136, + "step": 5980 + }, + { + "epoch": 0.34, + "learning_rate": 2.0915159606748393e-05, + "loss": 0.0008, + "step": 5990 + }, + { + "epoch": 0.34, + "learning_rate": 2.0896953513775943e-05, + "loss": 0.0334, + "step": 6000 + }, + { + "epoch": 0.34, + "eval_loss": 0.012497886084020138, + "eval_runtime": 387.2077, + "eval_samples_per_second": 180.559, + "eval_steps_per_second": 11.286, + "step": 6000 + }, + { + "epoch": 0.34, + "learning_rate": 2.0878747420803494e-05, + "loss": 0.0156, + "step": 6010 + }, + { + "epoch": 0.34, + "learning_rate": 2.0860541327831048e-05, + "loss": 0.0085, + "step": 6020 + }, + { + "epoch": 0.34, + "learning_rate": 2.08423352348586e-05, + "loss": 0.0012, + "step": 6030 + }, + { + "epoch": 0.35, + "learning_rate": 2.082412914188615e-05, + "loss": 0.0003, + "step": 6040 + }, + { + "epoch": 0.35, + "learning_rate": 2.0805923048913703e-05, + "loss": 0.0262, + "step": 6050 + }, + { + "epoch": 0.35, + "learning_rate": 2.0787716955941253e-05, + "loss": 0.0006, + "step": 6060 + }, + { + "epoch": 0.35, + "learning_rate": 2.076951086296881e-05, + "loss": 0.0024, + "step": 6070 + }, + { + "epoch": 0.35, + "learning_rate": 2.075130476999636e-05, + "loss": 0.0032, + "step": 6080 + }, + { + "epoch": 0.35, + "learning_rate": 2.073309867702391e-05, + "loss": 0.0354, + "step": 6090 + }, + { + "epoch": 0.35, + "learning_rate": 2.0714892584051466e-05, + "loss": 0.0007, + "step": 6100 + }, + { + "epoch": 0.35, + "learning_rate": 2.0696686491079016e-05, + "loss": 0.0002, + "step": 6110 + }, + { + "epoch": 0.35, + "learning_rate": 2.0678480398106567e-05, + "loss": 0.0003, + "step": 6120 + }, + { + "epoch": 0.35, + "learning_rate": 2.066027430513412e-05, + "loss": 0.0001, + "step": 6130 + }, + { + "epoch": 0.35, + "learning_rate": 2.064206821216167e-05, + "loss": 0.0045, + "step": 6140 + }, + { + "epoch": 0.35, + "learning_rate": 2.062386211918922e-05, + "loss": 0.0003, + "step": 6150 + }, + { + "epoch": 0.35, + "learning_rate": 2.0605656026216775e-05, + "loss": 0.0272, + "step": 6160 + }, + { + "epoch": 0.35, + "learning_rate": 2.0587449933244326e-05, + "loss": 0.0003, + "step": 6170 + }, + { + "epoch": 0.35, + "learning_rate": 2.0569243840271877e-05, + "loss": 0.0462, + "step": 6180 + }, + { + "epoch": 0.35, + "learning_rate": 2.055103774729943e-05, + "loss": 0.0002, + "step": 6190 + }, + { + "epoch": 0.35, + "learning_rate": 2.053283165432698e-05, + "loss": 0.0008, + "step": 6200 + }, + { + "epoch": 0.36, + "learning_rate": 2.051462556135453e-05, + "loss": 0.0001, + "step": 6210 + }, + { + "epoch": 0.36, + "learning_rate": 2.049641946838209e-05, + "loss": 0.0961, + "step": 6220 + }, + { + "epoch": 0.36, + "learning_rate": 2.047821337540964e-05, + "loss": 0.0006, + "step": 6230 + }, + { + "epoch": 0.36, + "learning_rate": 2.046000728243719e-05, + "loss": 0.0003, + "step": 6240 + }, + { + "epoch": 0.36, + "learning_rate": 2.0441801189464744e-05, + "loss": 0.0005, + "step": 6250 + }, + { + "epoch": 0.36, + "learning_rate": 2.0423595096492294e-05, + "loss": 0.0536, + "step": 6260 + }, + { + "epoch": 0.36, + "learning_rate": 2.0405389003519845e-05, + "loss": 0.0008, + "step": 6270 + }, + { + "epoch": 0.36, + "learning_rate": 2.03871829105474e-05, + "loss": 0.051, + "step": 6280 + }, + { + "epoch": 0.36, + "learning_rate": 2.036897681757495e-05, + "loss": 0.0252, + "step": 6290 + }, + { + "epoch": 0.36, + "learning_rate": 2.03507707246025e-05, + "loss": 0.0003, + "step": 6300 + }, + { + "epoch": 0.36, + "learning_rate": 2.0332564631630054e-05, + "loss": 0.0006, + "step": 6310 + }, + { + "epoch": 0.36, + "learning_rate": 2.0314358538657604e-05, + "loss": 0.0005, + "step": 6320 + }, + { + "epoch": 0.36, + "learning_rate": 2.0296152445685155e-05, + "loss": 0.0579, + "step": 6330 + }, + { + "epoch": 0.36, + "learning_rate": 2.027794635271271e-05, + "loss": 0.0003, + "step": 6340 + }, + { + "epoch": 0.36, + "learning_rate": 2.025974025974026e-05, + "loss": 0.0015, + "step": 6350 + }, + { + "epoch": 0.36, + "learning_rate": 2.024153416676781e-05, + "loss": 0.0356, + "step": 6360 + }, + { + "epoch": 0.36, + "learning_rate": 2.0223328073795364e-05, + "loss": 0.0008, + "step": 6370 + }, + { + "epoch": 0.37, + "learning_rate": 2.0205121980822917e-05, + "loss": 0.0008, + "step": 6380 + }, + { + "epoch": 0.37, + "learning_rate": 2.0186915887850468e-05, + "loss": 0.0015, + "step": 6390 + }, + { + "epoch": 0.37, + "learning_rate": 2.0168709794878022e-05, + "loss": 0.0019, + "step": 6400 + }, + { + "epoch": 0.37, + "learning_rate": 2.0150503701905572e-05, + "loss": 0.0189, + "step": 6410 + }, + { + "epoch": 0.37, + "learning_rate": 2.0132297608933123e-05, + "loss": 0.0002, + "step": 6420 + }, + { + "epoch": 0.37, + "learning_rate": 2.0114091515960677e-05, + "loss": 0.0005, + "step": 6430 + }, + { + "epoch": 0.37, + "learning_rate": 2.0095885422988227e-05, + "loss": 0.0003, + "step": 6440 + }, + { + "epoch": 0.37, + "learning_rate": 2.0077679330015778e-05, + "loss": 0.0163, + "step": 6450 + }, + { + "epoch": 0.37, + "learning_rate": 2.0059473237043332e-05, + "loss": 0.0002, + "step": 6460 + }, + { + "epoch": 0.37, + "learning_rate": 2.0041267144070882e-05, + "loss": 0.0004, + "step": 6470 + }, + { + "epoch": 0.37, + "learning_rate": 2.0023061051098433e-05, + "loss": 0.0511, + "step": 6480 + }, + { + "epoch": 0.37, + "learning_rate": 2.0004854958125987e-05, + "loss": 0.0006, + "step": 6490 + }, + { + "epoch": 0.37, + "learning_rate": 1.9986648865153537e-05, + "loss": 0.0003, + "step": 6500 + }, + { + "epoch": 0.37, + "learning_rate": 1.9968442772181088e-05, + "loss": 0.0002, + "step": 6510 + }, + { + "epoch": 0.37, + "learning_rate": 1.9950236679208642e-05, + "loss": 0.0398, + "step": 6520 + }, + { + "epoch": 0.37, + "learning_rate": 1.9932030586236196e-05, + "loss": 0.0138, + "step": 6530 + }, + { + "epoch": 0.37, + "learning_rate": 1.9913824493263746e-05, + "loss": 0.0012, + "step": 6540 + }, + { + "epoch": 0.37, + "learning_rate": 1.98956184002913e-05, + "loss": 0.0271, + "step": 6550 + }, + { + "epoch": 0.38, + "learning_rate": 1.987741230731885e-05, + "loss": 0.0016, + "step": 6560 + }, + { + "epoch": 0.38, + "learning_rate": 1.98592062143464e-05, + "loss": 0.0005, + "step": 6570 + }, + { + "epoch": 0.38, + "learning_rate": 1.9841000121373955e-05, + "loss": 0.0008, + "step": 6580 + }, + { + "epoch": 0.38, + "learning_rate": 1.9822794028401506e-05, + "loss": 0.0003, + "step": 6590 + }, + { + "epoch": 0.38, + "learning_rate": 1.9804587935429056e-05, + "loss": 0.0005, + "step": 6600 + }, + { + "epoch": 0.38, + "learning_rate": 1.978638184245661e-05, + "loss": 0.0194, + "step": 6610 + }, + { + "epoch": 0.38, + "learning_rate": 1.976817574948416e-05, + "loss": 0.1011, + "step": 6620 + }, + { + "epoch": 0.38, + "learning_rate": 1.974996965651171e-05, + "loss": 0.0082, + "step": 6630 + }, + { + "epoch": 0.38, + "learning_rate": 1.9731763563539265e-05, + "loss": 0.0234, + "step": 6640 + }, + { + "epoch": 0.38, + "learning_rate": 1.9713557470566816e-05, + "loss": 0.028, + "step": 6650 + }, + { + "epoch": 0.38, + "learning_rate": 1.9695351377594366e-05, + "loss": 0.0002, + "step": 6660 + }, + { + "epoch": 0.38, + "learning_rate": 1.967714528462192e-05, + "loss": 0.0005, + "step": 6670 + }, + { + "epoch": 0.38, + "learning_rate": 1.965893919164947e-05, + "loss": 0.0007, + "step": 6680 + }, + { + "epoch": 0.38, + "learning_rate": 1.9640733098677024e-05, + "loss": 0.0508, + "step": 6690 + }, + { + "epoch": 0.38, + "learning_rate": 1.9622527005704578e-05, + "loss": 0.0004, + "step": 6700 + }, + { + "epoch": 0.38, + "learning_rate": 1.960432091273213e-05, + "loss": 0.0211, + "step": 6710 + }, + { + "epoch": 0.38, + "learning_rate": 1.958611481975968e-05, + "loss": 0.0134, + "step": 6720 + }, + { + "epoch": 0.39, + "learning_rate": 1.9567908726787233e-05, + "loss": 0.0264, + "step": 6730 + }, + { + "epoch": 0.39, + "learning_rate": 1.9549702633814784e-05, + "loss": 0.0004, + "step": 6740 + }, + { + "epoch": 0.39, + "learning_rate": 1.9531496540842338e-05, + "loss": 0.0309, + "step": 6750 + }, + { + "epoch": 0.39, + "learning_rate": 1.9513290447869888e-05, + "loss": 0.0011, + "step": 6760 + }, + { + "epoch": 0.39, + "learning_rate": 1.949508435489744e-05, + "loss": 0.0005, + "step": 6770 + }, + { + "epoch": 0.39, + "learning_rate": 1.9476878261924993e-05, + "loss": 0.0059, + "step": 6780 + }, + { + "epoch": 0.39, + "learning_rate": 1.9458672168952543e-05, + "loss": 0.0161, + "step": 6790 + }, + { + "epoch": 0.39, + "learning_rate": 1.9440466075980094e-05, + "loss": 0.0209, + "step": 6800 + }, + { + "epoch": 0.39, + "learning_rate": 1.9422259983007648e-05, + "loss": 0.0002, + "step": 6810 + }, + { + "epoch": 0.39, + "learning_rate": 1.9404053890035198e-05, + "loss": 0.001, + "step": 6820 + }, + { + "epoch": 0.39, + "learning_rate": 1.938584779706275e-05, + "loss": 0.0224, + "step": 6830 + }, + { + "epoch": 0.39, + "learning_rate": 1.9367641704090303e-05, + "loss": 0.0006, + "step": 6840 + }, + { + "epoch": 0.39, + "learning_rate": 1.9349435611117856e-05, + "loss": 0.0012, + "step": 6850 + }, + { + "epoch": 0.39, + "learning_rate": 1.9331229518145407e-05, + "loss": 0.0005, + "step": 6860 + }, + { + "epoch": 0.39, + "learning_rate": 1.931302342517296e-05, + "loss": 0.0435, + "step": 6870 + }, + { + "epoch": 0.39, + "learning_rate": 1.929481733220051e-05, + "loss": 0.0461, + "step": 6880 + }, + { + "epoch": 0.39, + "learning_rate": 1.9276611239228062e-05, + "loss": 0.0175, + "step": 6890 + }, + { + "epoch": 0.39, + "learning_rate": 1.9258405146255616e-05, + "loss": 0.0461, + "step": 6900 + }, + { + "epoch": 0.4, + "learning_rate": 1.9240199053283166e-05, + "loss": 0.0011, + "step": 6910 + }, + { + "epoch": 0.4, + "learning_rate": 1.9221992960310717e-05, + "loss": 0.0017, + "step": 6920 + }, + { + "epoch": 0.4, + "learning_rate": 1.920378686733827e-05, + "loss": 0.0007, + "step": 6930 + }, + { + "epoch": 0.4, + "learning_rate": 1.918558077436582e-05, + "loss": 0.0002, + "step": 6940 + }, + { + "epoch": 0.4, + "learning_rate": 1.9167374681393372e-05, + "loss": 0.0008, + "step": 6950 + }, + { + "epoch": 0.4, + "learning_rate": 1.9149168588420926e-05, + "loss": 0.0001, + "step": 6960 + }, + { + "epoch": 0.4, + "learning_rate": 1.9130962495448476e-05, + "loss": 0.0387, + "step": 6970 + }, + { + "epoch": 0.4, + "learning_rate": 1.9112756402476027e-05, + "loss": 0.0036, + "step": 6980 + }, + { + "epoch": 0.4, + "learning_rate": 1.909455030950358e-05, + "loss": 0.0009, + "step": 6990 + }, + { + "epoch": 0.4, + "learning_rate": 1.9076344216531135e-05, + "loss": 0.0005, + "step": 7000 + }, + { + "epoch": 0.4, + "eval_loss": 0.012360856868326664, + "eval_runtime": 382.7836, + "eval_samples_per_second": 182.646, + "eval_steps_per_second": 11.416, + "step": 7000 + }, + { + "epoch": 0.4, + "learning_rate": 1.9058138123558685e-05, + "loss": 0.0233, + "step": 7010 + }, + { + "epoch": 0.4, + "learning_rate": 1.903993203058624e-05, + "loss": 0.0523, + "step": 7020 + }, + { + "epoch": 0.4, + "learning_rate": 1.902172593761379e-05, + "loss": 0.0016, + "step": 7030 + }, + { + "epoch": 0.4, + "learning_rate": 1.900351984464134e-05, + "loss": 0.0013, + "step": 7040 + }, + { + "epoch": 0.4, + "learning_rate": 1.8985313751668894e-05, + "loss": 0.0005, + "step": 7050 + }, + { + "epoch": 0.4, + "learning_rate": 1.8967107658696445e-05, + "loss": 0.1385, + "step": 7060 + }, + { + "epoch": 0.4, + "learning_rate": 1.8948901565723995e-05, + "loss": 0.0012, + "step": 7070 + }, + { + "epoch": 0.41, + "learning_rate": 1.893069547275155e-05, + "loss": 0.0343, + "step": 7080 + }, + { + "epoch": 0.41, + "learning_rate": 1.89124893797791e-05, + "loss": 0.0174, + "step": 7090 + }, + { + "epoch": 0.41, + "learning_rate": 1.889428328680665e-05, + "loss": 0.0004, + "step": 7100 + }, + { + "epoch": 0.41, + "learning_rate": 1.8876077193834204e-05, + "loss": 0.0497, + "step": 7110 + }, + { + "epoch": 0.41, + "learning_rate": 1.8857871100861754e-05, + "loss": 0.0006, + "step": 7120 + }, + { + "epoch": 0.41, + "learning_rate": 1.8839665007889305e-05, + "loss": 0.0039, + "step": 7130 + }, + { + "epoch": 0.41, + "learning_rate": 1.882145891491686e-05, + "loss": 0.0001, + "step": 7140 + }, + { + "epoch": 0.41, + "learning_rate": 1.880325282194441e-05, + "loss": 0.0008, + "step": 7150 + }, + { + "epoch": 0.41, + "learning_rate": 1.8785046728971963e-05, + "loss": 0.0002, + "step": 7160 + }, + { + "epoch": 0.41, + "learning_rate": 1.8766840635999517e-05, + "loss": 0.0027, + "step": 7170 + }, + { + "epoch": 0.41, + "learning_rate": 1.8748634543027068e-05, + "loss": 0.0172, + "step": 7180 + }, + { + "epoch": 0.41, + "learning_rate": 1.8730428450054618e-05, + "loss": 0.0003, + "step": 7190 + }, + { + "epoch": 0.41, + "learning_rate": 1.8712222357082172e-05, + "loss": 0.0208, + "step": 7200 + }, + { + "epoch": 0.41, + "learning_rate": 1.8694016264109723e-05, + "loss": 0.001, + "step": 7210 + }, + { + "epoch": 0.41, + "learning_rate": 1.8675810171137273e-05, + "loss": 0.0001, + "step": 7220 + }, + { + "epoch": 0.41, + "learning_rate": 1.8657604078164827e-05, + "loss": 0.0002, + "step": 7230 + }, + { + "epoch": 0.41, + "learning_rate": 1.8639397985192378e-05, + "loss": 0.0001, + "step": 7240 + }, + { + "epoch": 0.41, + "learning_rate": 1.8621191892219928e-05, + "loss": 0.0001, + "step": 7250 + }, + { + "epoch": 0.42, + "learning_rate": 1.8602985799247482e-05, + "loss": 0.0001, + "step": 7260 + }, + { + "epoch": 0.42, + "learning_rate": 1.8584779706275033e-05, + "loss": 0.0001, + "step": 7270 + }, + { + "epoch": 0.42, + "learning_rate": 1.8566573613302583e-05, + "loss": 0.0323, + "step": 7280 + }, + { + "epoch": 0.42, + "learning_rate": 1.8548367520330137e-05, + "loss": 0.0957, + "step": 7290 + }, + { + "epoch": 0.42, + "learning_rate": 1.8530161427357688e-05, + "loss": 0.0011, + "step": 7300 + }, + { + "epoch": 0.42, + "learning_rate": 1.851195533438524e-05, + "loss": 0.0002, + "step": 7310 + }, + { + "epoch": 0.42, + "learning_rate": 1.8493749241412795e-05, + "loss": 0.0009, + "step": 7320 + }, + { + "epoch": 0.42, + "learning_rate": 1.8475543148440346e-05, + "loss": 0.0431, + "step": 7330 + }, + { + "epoch": 0.42, + "learning_rate": 1.8457337055467896e-05, + "loss": 0.0004, + "step": 7340 + }, + { + "epoch": 0.42, + "learning_rate": 1.843913096249545e-05, + "loss": 0.0008, + "step": 7350 + }, + { + "epoch": 0.42, + "learning_rate": 1.8420924869523e-05, + "loss": 0.0005, + "step": 7360 + }, + { + "epoch": 0.42, + "learning_rate": 1.840271877655055e-05, + "loss": 0.0215, + "step": 7370 + }, + { + "epoch": 0.42, + "learning_rate": 1.8384512683578105e-05, + "loss": 0.0011, + "step": 7380 + }, + { + "epoch": 0.42, + "learning_rate": 1.8366306590605656e-05, + "loss": 0.0353, + "step": 7390 + }, + { + "epoch": 0.42, + "learning_rate": 1.8348100497633206e-05, + "loss": 0.027, + "step": 7400 + }, + { + "epoch": 0.42, + "learning_rate": 1.832989440466076e-05, + "loss": 0.0511, + "step": 7410 + }, + { + "epoch": 0.42, + "learning_rate": 1.831168831168831e-05, + "loss": 0.0027, + "step": 7420 + }, + { + "epoch": 0.43, + "learning_rate": 1.8293482218715865e-05, + "loss": 0.0005, + "step": 7430 + }, + { + "epoch": 0.43, + "learning_rate": 1.8275276125743415e-05, + "loss": 0.0011, + "step": 7440 + }, + { + "epoch": 0.43, + "learning_rate": 1.8257070032770966e-05, + "loss": 0.033, + "step": 7450 + }, + { + "epoch": 0.43, + "learning_rate": 1.823886393979852e-05, + "loss": 0.0006, + "step": 7460 + }, + { + "epoch": 0.43, + "learning_rate": 1.8220657846826074e-05, + "loss": 0.0004, + "step": 7470 + }, + { + "epoch": 0.43, + "learning_rate": 1.8202451753853624e-05, + "loss": 0.0024, + "step": 7480 + }, + { + "epoch": 0.43, + "learning_rate": 1.8184245660881178e-05, + "loss": 0.0146, + "step": 7490 + }, + { + "epoch": 0.43, + "learning_rate": 1.816603956790873e-05, + "loss": 0.0005, + "step": 7500 + }, + { + "epoch": 0.43, + "learning_rate": 1.814783347493628e-05, + "loss": 0.0008, + "step": 7510 + }, + { + "epoch": 0.43, + "learning_rate": 1.8129627381963833e-05, + "loss": 0.0006, + "step": 7520 + }, + { + "epoch": 0.43, + "learning_rate": 1.8111421288991384e-05, + "loss": 0.0001, + "step": 7530 + }, + { + "epoch": 0.43, + "learning_rate": 1.8093215196018934e-05, + "loss": 0.0001, + "step": 7540 + }, + { + "epoch": 0.43, + "learning_rate": 1.8075009103046488e-05, + "loss": 0.0001, + "step": 7550 + }, + { + "epoch": 0.43, + "learning_rate": 1.805680301007404e-05, + "loss": 0.0001, + "step": 7560 + }, + { + "epoch": 0.43, + "learning_rate": 1.803859691710159e-05, + "loss": 0.0187, + "step": 7570 + }, + { + "epoch": 0.43, + "learning_rate": 1.8020390824129143e-05, + "loss": 0.0229, + "step": 7580 + }, + { + "epoch": 0.43, + "learning_rate": 1.8002184731156693e-05, + "loss": 0.0004, + "step": 7590 + }, + { + "epoch": 0.43, + "learning_rate": 1.7983978638184244e-05, + "loss": 0.0426, + "step": 7600 + }, + { + "epoch": 0.44, + "learning_rate": 1.7965772545211798e-05, + "loss": 0.0003, + "step": 7610 + }, + { + "epoch": 0.44, + "learning_rate": 1.7947566452239352e-05, + "loss": 0.0004, + "step": 7620 + }, + { + "epoch": 0.44, + "learning_rate": 1.7929360359266902e-05, + "loss": 0.011, + "step": 7630 + }, + { + "epoch": 0.44, + "learning_rate": 1.7911154266294456e-05, + "loss": 0.0001, + "step": 7640 + }, + { + "epoch": 0.44, + "learning_rate": 1.7892948173322007e-05, + "loss": 0.0022, + "step": 7650 + }, + { + "epoch": 0.44, + "learning_rate": 1.7874742080349557e-05, + "loss": 0.0001, + "step": 7660 + }, + { + "epoch": 0.44, + "learning_rate": 1.785653598737711e-05, + "loss": 0.0001, + "step": 7670 + }, + { + "epoch": 0.44, + "learning_rate": 1.7838329894404662e-05, + "loss": 0.0001, + "step": 7680 + }, + { + "epoch": 0.44, + "learning_rate": 1.7820123801432212e-05, + "loss": 0.0006, + "step": 7690 + }, + { + "epoch": 0.44, + "learning_rate": 1.7801917708459766e-05, + "loss": 0.0002, + "step": 7700 + }, + { + "epoch": 0.44, + "learning_rate": 1.7783711615487317e-05, + "loss": 0.0001, + "step": 7710 + }, + { + "epoch": 0.44, + "learning_rate": 1.7765505522514867e-05, + "loss": 0.0001, + "step": 7720 + }, + { + "epoch": 0.44, + "learning_rate": 1.774729942954242e-05, + "loss": 0.0004, + "step": 7730 + }, + { + "epoch": 0.44, + "learning_rate": 1.772909333656997e-05, + "loss": 0.0003, + "step": 7740 + }, + { + "epoch": 0.44, + "learning_rate": 1.7710887243597522e-05, + "loss": 0.0004, + "step": 7750 + }, + { + "epoch": 0.44, + "learning_rate": 1.7692681150625076e-05, + "loss": 0.0, + "step": 7760 + }, + { + "epoch": 0.44, + "learning_rate": 1.7674475057652627e-05, + "loss": 0.0, + "step": 7770 + }, + { + "epoch": 0.45, + "learning_rate": 1.765626896468018e-05, + "loss": 0.0002, + "step": 7780 + }, + { + "epoch": 0.45, + "learning_rate": 1.7638062871707734e-05, + "loss": 0.0134, + "step": 7790 + }, + { + "epoch": 0.45, + "learning_rate": 1.7619856778735285e-05, + "loss": 0.0, + "step": 7800 + }, + { + "epoch": 0.45, + "learning_rate": 1.7601650685762835e-05, + "loss": 0.0004, + "step": 7810 + }, + { + "epoch": 0.45, + "learning_rate": 1.758344459279039e-05, + "loss": 0.0002, + "step": 7820 + }, + { + "epoch": 0.45, + "learning_rate": 1.756523849981794e-05, + "loss": 0.0, + "step": 7830 + }, + { + "epoch": 0.45, + "learning_rate": 1.754703240684549e-05, + "loss": 0.0644, + "step": 7840 + }, + { + "epoch": 0.45, + "learning_rate": 1.7528826313873044e-05, + "loss": 0.0148, + "step": 7850 + }, + { + "epoch": 0.45, + "learning_rate": 1.7510620220900595e-05, + "loss": 0.0474, + "step": 7860 + }, + { + "epoch": 0.45, + "learning_rate": 1.7492414127928145e-05, + "loss": 0.0002, + "step": 7870 + }, + { + "epoch": 0.45, + "learning_rate": 1.74742080349557e-05, + "loss": 0.0002, + "step": 7880 + }, + { + "epoch": 0.45, + "learning_rate": 1.745600194198325e-05, + "loss": 0.0003, + "step": 7890 + }, + { + "epoch": 0.45, + "learning_rate": 1.74377958490108e-05, + "loss": 0.0002, + "step": 7900 + }, + { + "epoch": 0.45, + "learning_rate": 1.7419589756038354e-05, + "loss": 0.0001, + "step": 7910 + }, + { + "epoch": 0.45, + "learning_rate": 1.7401383663065905e-05, + "loss": 0.0002, + "step": 7920 + }, + { + "epoch": 0.45, + "learning_rate": 1.738317757009346e-05, + "loss": 0.0007, + "step": 7930 + }, + { + "epoch": 0.45, + "learning_rate": 1.7364971477121013e-05, + "loss": 0.0006, + "step": 7940 + }, + { + "epoch": 0.45, + "learning_rate": 1.7346765384148563e-05, + "loss": 0.0002, + "step": 7950 + }, + { + "epoch": 0.46, + "learning_rate": 1.7328559291176114e-05, + "loss": 0.0002, + "step": 7960 + }, + { + "epoch": 0.46, + "learning_rate": 1.7310353198203668e-05, + "loss": 0.0586, + "step": 7970 + }, + { + "epoch": 0.46, + "learning_rate": 1.7292147105231218e-05, + "loss": 0.0005, + "step": 7980 + }, + { + "epoch": 0.46, + "learning_rate": 1.727394101225877e-05, + "loss": 0.0001, + "step": 7990 + }, + { + "epoch": 0.46, + "learning_rate": 1.7255734919286322e-05, + "loss": 0.0005, + "step": 8000 + }, + { + "epoch": 0.46, + "eval_loss": 0.01887901872396469, + "eval_runtime": 374.3804, + "eval_samples_per_second": 186.746, + "eval_steps_per_second": 11.673, + "step": 8000 + }, + { + "epoch": 0.46, + "learning_rate": 1.7237528826313873e-05, + "loss": 0.0001, + "step": 8010 + }, + { + "epoch": 0.46, + "learning_rate": 1.7219322733341424e-05, + "loss": 0.0466, + "step": 8020 + }, + { + "epoch": 0.46, + "learning_rate": 1.7201116640368977e-05, + "loss": 0.0232, + "step": 8030 + }, + { + "epoch": 0.46, + "learning_rate": 1.7182910547396528e-05, + "loss": 0.0493, + "step": 8040 + }, + { + "epoch": 0.46, + "learning_rate": 1.716470445442408e-05, + "loss": 0.0001, + "step": 8050 + }, + { + "epoch": 0.46, + "learning_rate": 1.7146498361451632e-05, + "loss": 0.0003, + "step": 8060 + }, + { + "epoch": 0.46, + "learning_rate": 1.7128292268479183e-05, + "loss": 0.0001, + "step": 8070 + }, + { + "epoch": 0.46, + "learning_rate": 1.7110086175506733e-05, + "loss": 0.0003, + "step": 8080 + }, + { + "epoch": 0.46, + "learning_rate": 1.709188008253429e-05, + "loss": 0.0001, + "step": 8090 + }, + { + "epoch": 0.46, + "learning_rate": 1.707367398956184e-05, + "loss": 0.0001, + "step": 8100 + }, + { + "epoch": 0.46, + "learning_rate": 1.7055467896589395e-05, + "loss": 0.0001, + "step": 8110 + }, + { + "epoch": 0.46, + "learning_rate": 1.7037261803616946e-05, + "loss": 0.0522, + "step": 8120 + }, + { + "epoch": 0.47, + "learning_rate": 1.7019055710644496e-05, + "loss": 0.0343, + "step": 8130 + }, + { + "epoch": 0.47, + "learning_rate": 1.700084961767205e-05, + "loss": 0.0009, + "step": 8140 + }, + { + "epoch": 0.47, + "learning_rate": 1.69826435246996e-05, + "loss": 0.0007, + "step": 8150 + }, + { + "epoch": 0.47, + "learning_rate": 1.696443743172715e-05, + "loss": 0.0005, + "step": 8160 + }, + { + "epoch": 0.47, + "learning_rate": 1.6946231338754705e-05, + "loss": 0.0003, + "step": 8170 + }, + { + "epoch": 0.47, + "learning_rate": 1.6928025245782256e-05, + "loss": 0.0001, + "step": 8180 + }, + { + "epoch": 0.47, + "learning_rate": 1.6909819152809806e-05, + "loss": 0.0002, + "step": 8190 + }, + { + "epoch": 0.47, + "learning_rate": 1.689161305983736e-05, + "loss": 0.0001, + "step": 8200 + }, + { + "epoch": 0.47, + "learning_rate": 1.687340696686491e-05, + "loss": 0.0004, + "step": 8210 + }, + { + "epoch": 0.47, + "learning_rate": 1.685520087389246e-05, + "loss": 0.0007, + "step": 8220 + }, + { + "epoch": 0.47, + "learning_rate": 1.6836994780920015e-05, + "loss": 0.0001, + "step": 8230 + }, + { + "epoch": 0.47, + "learning_rate": 1.6818788687947566e-05, + "loss": 0.0196, + "step": 8240 + }, + { + "epoch": 0.47, + "learning_rate": 1.680058259497512e-05, + "loss": 0.0392, + "step": 8250 + }, + { + "epoch": 0.47, + "learning_rate": 1.6782376502002673e-05, + "loss": 0.0588, + "step": 8260 + }, + { + "epoch": 0.47, + "learning_rate": 1.6764170409030224e-05, + "loss": 0.0371, + "step": 8270 + }, + { + "epoch": 0.47, + "learning_rate": 1.6745964316057774e-05, + "loss": 0.0003, + "step": 8280 + }, + { + "epoch": 0.47, + "learning_rate": 1.672775822308533e-05, + "loss": 0.0302, + "step": 8290 + }, + { + "epoch": 0.47, + "learning_rate": 1.670955213011288e-05, + "loss": 0.0133, + "step": 8300 + }, + { + "epoch": 0.48, + "learning_rate": 1.669134603714043e-05, + "loss": 0.0012, + "step": 8310 + }, + { + "epoch": 0.48, + "learning_rate": 1.6673139944167983e-05, + "loss": 0.0003, + "step": 8320 + }, + { + "epoch": 0.48, + "learning_rate": 1.6654933851195534e-05, + "loss": 0.0006, + "step": 8330 + }, + { + "epoch": 0.48, + "learning_rate": 1.6636727758223084e-05, + "loss": 0.0001, + "step": 8340 + }, + { + "epoch": 0.48, + "learning_rate": 1.6618521665250638e-05, + "loss": 0.071, + "step": 8350 + }, + { + "epoch": 0.48, + "learning_rate": 1.660031557227819e-05, + "loss": 0.0307, + "step": 8360 + }, + { + "epoch": 0.48, + "learning_rate": 1.658210947930574e-05, + "loss": 0.0246, + "step": 8370 + }, + { + "epoch": 0.48, + "learning_rate": 1.6563903386333293e-05, + "loss": 0.0259, + "step": 8380 + }, + { + "epoch": 0.48, + "learning_rate": 1.6545697293360844e-05, + "loss": 0.0253, + "step": 8390 + }, + { + "epoch": 0.48, + "learning_rate": 1.6527491200388398e-05, + "loss": 0.0019, + "step": 8400 + }, + { + "epoch": 0.48, + "learning_rate": 1.650928510741595e-05, + "loss": 0.013, + "step": 8410 + }, + { + "epoch": 0.48, + "learning_rate": 1.6491079014443502e-05, + "loss": 0.0003, + "step": 8420 + }, + { + "epoch": 0.48, + "learning_rate": 1.6472872921471053e-05, + "loss": 0.001, + "step": 8430 + }, + { + "epoch": 0.48, + "learning_rate": 1.6454666828498607e-05, + "loss": 0.013, + "step": 8440 + }, + { + "epoch": 0.48, + "learning_rate": 1.6436460735526157e-05, + "loss": 0.0008, + "step": 8450 + }, + { + "epoch": 0.48, + "learning_rate": 1.6418254642553708e-05, + "loss": 0.0027, + "step": 8460 + }, + { + "epoch": 0.48, + "learning_rate": 1.640004854958126e-05, + "loss": 0.0013, + "step": 8470 + }, + { + "epoch": 0.49, + "learning_rate": 1.6381842456608812e-05, + "loss": 0.0017, + "step": 8480 + }, + { + "epoch": 0.49, + "learning_rate": 1.6363636363636363e-05, + "loss": 0.0623, + "step": 8490 + }, + { + "epoch": 0.49, + "learning_rate": 1.6345430270663916e-05, + "loss": 0.0012, + "step": 8500 + }, + { + "epoch": 0.49, + "learning_rate": 1.6327224177691467e-05, + "loss": 0.0018, + "step": 8510 + }, + { + "epoch": 0.49, + "learning_rate": 1.6309018084719017e-05, + "loss": 0.0002, + "step": 8520 + }, + { + "epoch": 0.49, + "learning_rate": 1.629081199174657e-05, + "loss": 0.0446, + "step": 8530 + }, + { + "epoch": 0.49, + "learning_rate": 1.6272605898774122e-05, + "loss": 0.0005, + "step": 8540 + }, + { + "epoch": 0.49, + "learning_rate": 1.6254399805801672e-05, + "loss": 0.0366, + "step": 8550 + }, + { + "epoch": 0.49, + "learning_rate": 1.623619371282923e-05, + "loss": 0.0003, + "step": 8560 + }, + { + "epoch": 0.49, + "learning_rate": 1.621798761985678e-05, + "loss": 0.0003, + "step": 8570 + }, + { + "epoch": 0.49, + "learning_rate": 1.619978152688433e-05, + "loss": 0.047, + "step": 8580 + }, + { + "epoch": 0.49, + "learning_rate": 1.6181575433911885e-05, + "loss": 0.0005, + "step": 8590 + }, + { + "epoch": 0.49, + "learning_rate": 1.6163369340939435e-05, + "loss": 0.0021, + "step": 8600 + }, + { + "epoch": 0.49, + "learning_rate": 1.6145163247966986e-05, + "loss": 0.0165, + "step": 8610 + }, + { + "epoch": 0.49, + "learning_rate": 1.612695715499454e-05, + "loss": 0.0357, + "step": 8620 + }, + { + "epoch": 0.49, + "learning_rate": 1.610875106202209e-05, + "loss": 0.0217, + "step": 8630 + }, + { + "epoch": 0.49, + "learning_rate": 1.609054496904964e-05, + "loss": 0.0003, + "step": 8640 + }, + { + "epoch": 0.49, + "learning_rate": 1.6072338876077195e-05, + "loss": 0.0011, + "step": 8650 + }, + { + "epoch": 0.5, + "learning_rate": 1.6054132783104745e-05, + "loss": 0.0174, + "step": 8660 + }, + { + "epoch": 0.5, + "learning_rate": 1.6035926690132296e-05, + "loss": 0.001, + "step": 8670 + }, + { + "epoch": 0.5, + "learning_rate": 1.601772059715985e-05, + "loss": 0.0004, + "step": 8680 + }, + { + "epoch": 0.5, + "learning_rate": 1.59995145041874e-05, + "loss": 0.0014, + "step": 8690 + }, + { + "epoch": 0.5, + "learning_rate": 1.598130841121495e-05, + "loss": 0.0003, + "step": 8700 + }, + { + "epoch": 0.5, + "learning_rate": 1.5963102318242508e-05, + "loss": 0.0025, + "step": 8710 + }, + { + "epoch": 0.5, + "learning_rate": 1.594489622527006e-05, + "loss": 0.0107, + "step": 8720 + }, + { + "epoch": 0.5, + "learning_rate": 1.592669013229761e-05, + "loss": 0.0004, + "step": 8730 + }, + { + "epoch": 0.5, + "learning_rate": 1.5908484039325163e-05, + "loss": 0.014, + "step": 8740 + }, + { + "epoch": 0.5, + "learning_rate": 1.5890277946352713e-05, + "loss": 0.0245, + "step": 8750 + }, + { + "epoch": 0.5, + "learning_rate": 1.5872071853380264e-05, + "loss": 0.0001, + "step": 8760 + }, + { + "epoch": 0.5, + "learning_rate": 1.5853865760407818e-05, + "loss": 0.0001, + "step": 8770 + }, + { + "epoch": 0.5, + "learning_rate": 1.583565966743537e-05, + "loss": 0.0004, + "step": 8780 + }, + { + "epoch": 0.5, + "learning_rate": 1.5817453574462922e-05, + "loss": 0.0016, + "step": 8790 + }, + { + "epoch": 0.5, + "learning_rate": 1.5799247481490473e-05, + "loss": 0.0003, + "step": 8800 + }, + { + "epoch": 0.5, + "learning_rate": 1.5781041388518023e-05, + "loss": 0.0126, + "step": 8810 + }, + { + "epoch": 0.5, + "learning_rate": 1.5762835295545577e-05, + "loss": 0.0235, + "step": 8820 + }, + { + "epoch": 0.51, + "learning_rate": 1.5744629202573128e-05, + "loss": 0.0336, + "step": 8830 + }, + { + "epoch": 0.51, + "learning_rate": 1.5726423109600678e-05, + "loss": 0.0152, + "step": 8840 + }, + { + "epoch": 0.51, + "learning_rate": 1.5708217016628232e-05, + "loss": 0.0001, + "step": 8850 + }, + { + "epoch": 0.51, + "learning_rate": 1.5690010923655783e-05, + "loss": 0.0249, + "step": 8860 + }, + { + "epoch": 0.51, + "learning_rate": 1.5671804830683337e-05, + "loss": 0.0003, + "step": 8870 + }, + { + "epoch": 0.51, + "learning_rate": 1.565359873771089e-05, + "loss": 0.0008, + "step": 8880 + }, + { + "epoch": 0.51, + "learning_rate": 1.563539264473844e-05, + "loss": 0.0008, + "step": 8890 + }, + { + "epoch": 0.51, + "learning_rate": 1.561718655176599e-05, + "loss": 0.064, + "step": 8900 + }, + { + "epoch": 0.51, + "learning_rate": 1.5598980458793545e-05, + "loss": 0.0011, + "step": 8910 + }, + { + "epoch": 0.51, + "learning_rate": 1.5580774365821096e-05, + "loss": 0.0024, + "step": 8920 + }, + { + "epoch": 0.51, + "learning_rate": 1.5562568272848647e-05, + "loss": 0.0002, + "step": 8930 + }, + { + "epoch": 0.51, + "learning_rate": 1.55443621798762e-05, + "loss": 0.0568, + "step": 8940 + }, + { + "epoch": 0.51, + "learning_rate": 1.552615608690375e-05, + "loss": 0.015, + "step": 8950 + }, + { + "epoch": 0.51, + "learning_rate": 1.55079499939313e-05, + "loss": 0.0566, + "step": 8960 + }, + { + "epoch": 0.51, + "learning_rate": 1.5489743900958855e-05, + "loss": 0.0157, + "step": 8970 + }, + { + "epoch": 0.51, + "learning_rate": 1.5471537807986406e-05, + "loss": 0.007, + "step": 8980 + }, + { + "epoch": 0.51, + "learning_rate": 1.5453331715013956e-05, + "loss": 0.0225, + "step": 8990 + }, + { + "epoch": 0.51, + "learning_rate": 1.543512562204151e-05, + "loss": 0.0505, + "step": 9000 + }, + { + "epoch": 0.51, + "eval_loss": 0.013111772947013378, + "eval_runtime": 374.1624, + "eval_samples_per_second": 186.855, + "eval_steps_per_second": 11.679, + "step": 9000 + }, + { + "epoch": 0.52, + "learning_rate": 1.541691952906906e-05, + "loss": 0.0018, + "step": 9010 + }, + { + "epoch": 0.52, + "learning_rate": 1.539871343609661e-05, + "loss": 0.0004, + "step": 9020 + }, + { + "epoch": 0.52, + "learning_rate": 1.538050734312417e-05, + "loss": 0.0013, + "step": 9030 + }, + { + "epoch": 0.52, + "learning_rate": 1.536230125015172e-05, + "loss": 0.002, + "step": 9040 + }, + { + "epoch": 0.52, + "learning_rate": 1.534409515717927e-05, + "loss": 0.0561, + "step": 9050 + }, + { + "epoch": 0.52, + "learning_rate": 1.5325889064206824e-05, + "loss": 0.0002, + "step": 9060 + }, + { + "epoch": 0.52, + "learning_rate": 1.5307682971234374e-05, + "loss": 0.0318, + "step": 9070 + }, + { + "epoch": 0.52, + "learning_rate": 1.5289476878261925e-05, + "loss": 0.0551, + "step": 9080 + }, + { + "epoch": 0.52, + "learning_rate": 1.527127078528948e-05, + "loss": 0.016, + "step": 9090 + }, + { + "epoch": 0.52, + "learning_rate": 1.5253064692317029e-05, + "loss": 0.0474, + "step": 9100 + }, + { + "epoch": 0.52, + "learning_rate": 1.523485859934458e-05, + "loss": 0.0026, + "step": 9110 + }, + { + "epoch": 0.52, + "learning_rate": 1.5216652506372134e-05, + "loss": 0.0013, + "step": 9120 + }, + { + "epoch": 0.52, + "learning_rate": 1.5198446413399684e-05, + "loss": 0.0125, + "step": 9130 + }, + { + "epoch": 0.52, + "learning_rate": 1.5180240320427236e-05, + "loss": 0.0004, + "step": 9140 + }, + { + "epoch": 0.52, + "learning_rate": 1.516203422745479e-05, + "loss": 0.001, + "step": 9150 + }, + { + "epoch": 0.52, + "learning_rate": 1.514382813448234e-05, + "loss": 0.0015, + "step": 9160 + }, + { + "epoch": 0.52, + "learning_rate": 1.5125622041509891e-05, + "loss": 0.0058, + "step": 9170 + }, + { + "epoch": 0.53, + "learning_rate": 1.5107415948537445e-05, + "loss": 0.0509, + "step": 9180 + }, + { + "epoch": 0.53, + "learning_rate": 1.5089209855564996e-05, + "loss": 0.0003, + "step": 9190 + }, + { + "epoch": 0.53, + "learning_rate": 1.5071003762592546e-05, + "loss": 0.0007, + "step": 9200 + }, + { + "epoch": 0.53, + "learning_rate": 1.50527976696201e-05, + "loss": 0.0004, + "step": 9210 + }, + { + "epoch": 0.53, + "learning_rate": 1.5034591576647652e-05, + "loss": 0.0113, + "step": 9220 + }, + { + "epoch": 0.53, + "learning_rate": 1.5016385483675203e-05, + "loss": 0.0003, + "step": 9230 + }, + { + "epoch": 0.53, + "learning_rate": 1.4998179390702755e-05, + "loss": 0.0566, + "step": 9240 + }, + { + "epoch": 0.53, + "learning_rate": 1.4979973297730307e-05, + "loss": 0.0008, + "step": 9250 + }, + { + "epoch": 0.53, + "learning_rate": 1.496176720475786e-05, + "loss": 0.0385, + "step": 9260 + }, + { + "epoch": 0.53, + "learning_rate": 1.494356111178541e-05, + "loss": 0.0174, + "step": 9270 + }, + { + "epoch": 0.53, + "learning_rate": 1.4925355018812962e-05, + "loss": 0.0313, + "step": 9280 + }, + { + "epoch": 0.53, + "learning_rate": 1.4907148925840514e-05, + "loss": 0.1253, + "step": 9290 + }, + { + "epoch": 0.53, + "learning_rate": 1.4888942832868068e-05, + "loss": 0.0013, + "step": 9300 + }, + { + "epoch": 0.53, + "learning_rate": 1.4870736739895619e-05, + "loss": 0.0025, + "step": 9310 + }, + { + "epoch": 0.53, + "learning_rate": 1.4852530646923171e-05, + "loss": 0.0011, + "step": 9320 + }, + { + "epoch": 0.53, + "learning_rate": 1.4834324553950723e-05, + "loss": 0.0007, + "step": 9330 + }, + { + "epoch": 0.53, + "learning_rate": 1.4816118460978274e-05, + "loss": 0.0754, + "step": 9340 + }, + { + "epoch": 0.53, + "learning_rate": 1.4797912368005826e-05, + "loss": 0.0006, + "step": 9350 + }, + { + "epoch": 0.54, + "learning_rate": 1.4779706275033378e-05, + "loss": 0.0188, + "step": 9360 + }, + { + "epoch": 0.54, + "learning_rate": 1.4761500182060929e-05, + "loss": 0.0016, + "step": 9370 + }, + { + "epoch": 0.54, + "learning_rate": 1.4743294089088483e-05, + "loss": 0.001, + "step": 9380 + }, + { + "epoch": 0.54, + "learning_rate": 1.4725087996116035e-05, + "loss": 0.0125, + "step": 9390 + }, + { + "epoch": 0.54, + "learning_rate": 1.4706881903143585e-05, + "loss": 0.001, + "step": 9400 + }, + { + "epoch": 0.54, + "learning_rate": 1.4688675810171138e-05, + "loss": 0.0003, + "step": 9410 + }, + { + "epoch": 0.54, + "learning_rate": 1.467046971719869e-05, + "loss": 0.0015, + "step": 9420 + }, + { + "epoch": 0.54, + "learning_rate": 1.465226362422624e-05, + "loss": 0.0002, + "step": 9430 + }, + { + "epoch": 0.54, + "learning_rate": 1.4634057531253793e-05, + "loss": 0.0084, + "step": 9440 + }, + { + "epoch": 0.54, + "learning_rate": 1.4615851438281347e-05, + "loss": 0.0003, + "step": 9450 + }, + { + "epoch": 0.54, + "learning_rate": 1.4597645345308897e-05, + "loss": 0.0002, + "step": 9460 + }, + { + "epoch": 0.54, + "learning_rate": 1.457943925233645e-05, + "loss": 0.0002, + "step": 9470 + }, + { + "epoch": 0.54, + "learning_rate": 1.4561233159364002e-05, + "loss": 0.0008, + "step": 9480 + }, + { + "epoch": 0.54, + "learning_rate": 1.4543027066391552e-05, + "loss": 0.055, + "step": 9490 + }, + { + "epoch": 0.54, + "learning_rate": 1.4524820973419104e-05, + "loss": 0.0414, + "step": 9500 + }, + { + "epoch": 0.54, + "learning_rate": 1.4506614880446656e-05, + "loss": 0.0003, + "step": 9510 + }, + { + "epoch": 0.54, + "learning_rate": 1.4488408787474207e-05, + "loss": 0.0003, + "step": 9520 + }, + { + "epoch": 0.55, + "learning_rate": 1.4470202694501761e-05, + "loss": 0.0004, + "step": 9530 + }, + { + "epoch": 0.55, + "learning_rate": 1.4451996601529313e-05, + "loss": 0.0106, + "step": 9540 + }, + { + "epoch": 0.55, + "learning_rate": 1.4433790508556864e-05, + "loss": 0.001, + "step": 9550 + }, + { + "epoch": 0.55, + "learning_rate": 1.4415584415584416e-05, + "loss": 0.0003, + "step": 9560 + }, + { + "epoch": 0.55, + "learning_rate": 1.4397378322611968e-05, + "loss": 0.0442, + "step": 9570 + }, + { + "epoch": 0.55, + "learning_rate": 1.4379172229639519e-05, + "loss": 0.0005, + "step": 9580 + }, + { + "epoch": 0.55, + "learning_rate": 1.436096613666707e-05, + "loss": 0.0006, + "step": 9590 + }, + { + "epoch": 0.55, + "learning_rate": 1.4342760043694623e-05, + "loss": 0.0026, + "step": 9600 + }, + { + "epoch": 0.55, + "learning_rate": 1.4324553950722175e-05, + "loss": 0.0004, + "step": 9610 + }, + { + "epoch": 0.55, + "learning_rate": 1.4306347857749727e-05, + "loss": 0.0003, + "step": 9620 + }, + { + "epoch": 0.55, + "learning_rate": 1.428814176477728e-05, + "loss": 0.0004, + "step": 9630 + }, + { + "epoch": 0.55, + "learning_rate": 1.4269935671804832e-05, + "loss": 0.0003, + "step": 9640 + }, + { + "epoch": 0.55, + "learning_rate": 1.4251729578832382e-05, + "loss": 0.0003, + "step": 9650 + }, + { + "epoch": 0.55, + "learning_rate": 1.4233523485859935e-05, + "loss": 0.0009, + "step": 9660 + }, + { + "epoch": 0.55, + "learning_rate": 1.4215317392887487e-05, + "loss": 0.0004, + "step": 9670 + }, + { + "epoch": 0.55, + "learning_rate": 1.4197111299915037e-05, + "loss": 0.044, + "step": 9680 + }, + { + "epoch": 0.55, + "learning_rate": 1.4178905206942591e-05, + "loss": 0.0332, + "step": 9690 + }, + { + "epoch": 0.55, + "learning_rate": 1.4160699113970144e-05, + "loss": 0.0004, + "step": 9700 + }, + { + "epoch": 0.56, + "learning_rate": 1.4142493020997694e-05, + "loss": 0.0007, + "step": 9710 + }, + { + "epoch": 0.56, + "learning_rate": 1.4124286928025246e-05, + "loss": 0.0006, + "step": 9720 + }, + { + "epoch": 0.56, + "learning_rate": 1.4106080835052798e-05, + "loss": 0.0014, + "step": 9730 + }, + { + "epoch": 0.56, + "learning_rate": 1.4087874742080349e-05, + "loss": 0.0003, + "step": 9740 + }, + { + "epoch": 0.56, + "learning_rate": 1.4069668649107901e-05, + "loss": 0.0002, + "step": 9750 + }, + { + "epoch": 0.56, + "learning_rate": 1.4051462556135453e-05, + "loss": 0.0002, + "step": 9760 + }, + { + "epoch": 0.56, + "learning_rate": 1.4033256463163006e-05, + "loss": 0.0002, + "step": 9770 + }, + { + "epoch": 0.56, + "learning_rate": 1.4015050370190558e-05, + "loss": 0.0305, + "step": 9780 + }, + { + "epoch": 0.56, + "learning_rate": 1.399684427721811e-05, + "loss": 0.0319, + "step": 9790 + }, + { + "epoch": 0.56, + "learning_rate": 1.397863818424566e-05, + "loss": 0.0002, + "step": 9800 + }, + { + "epoch": 0.56, + "learning_rate": 1.3960432091273213e-05, + "loss": 0.0002, + "step": 9810 + }, + { + "epoch": 0.56, + "learning_rate": 1.3942225998300765e-05, + "loss": 0.0334, + "step": 9820 + }, + { + "epoch": 0.56, + "learning_rate": 1.3924019905328316e-05, + "loss": 0.0002, + "step": 9830 + }, + { + "epoch": 0.56, + "learning_rate": 1.390581381235587e-05, + "loss": 0.0001, + "step": 9840 + }, + { + "epoch": 0.56, + "learning_rate": 1.3887607719383422e-05, + "loss": 0.0001, + "step": 9850 + }, + { + "epoch": 0.56, + "learning_rate": 1.3869401626410972e-05, + "loss": 0.0002, + "step": 9860 + }, + { + "epoch": 0.56, + "learning_rate": 1.3851195533438524e-05, + "loss": 0.0002, + "step": 9870 + }, + { + "epoch": 0.57, + "learning_rate": 1.3832989440466077e-05, + "loss": 0.0243, + "step": 9880 + }, + { + "epoch": 0.57, + "learning_rate": 1.3814783347493627e-05, + "loss": 0.0362, + "step": 9890 + }, + { + "epoch": 0.57, + "learning_rate": 1.379657725452118e-05, + "loss": 0.0001, + "step": 9900 + }, + { + "epoch": 0.57, + "learning_rate": 1.3778371161548732e-05, + "loss": 0.0295, + "step": 9910 + }, + { + "epoch": 0.57, + "learning_rate": 1.3760165068576284e-05, + "loss": 0.0005, + "step": 9920 + }, + { + "epoch": 0.57, + "learning_rate": 1.3741958975603836e-05, + "loss": 0.0009, + "step": 9930 + }, + { + "epoch": 0.57, + "learning_rate": 1.3723752882631388e-05, + "loss": 0.0011, + "step": 9940 + }, + { + "epoch": 0.57, + "learning_rate": 1.370554678965894e-05, + "loss": 0.0003, + "step": 9950 + }, + { + "epoch": 0.57, + "learning_rate": 1.3687340696686491e-05, + "loss": 0.0148, + "step": 9960 + }, + { + "epoch": 0.57, + "learning_rate": 1.3669134603714043e-05, + "loss": 0.0001, + "step": 9970 + }, + { + "epoch": 0.57, + "learning_rate": 1.3650928510741595e-05, + "loss": 0.0277, + "step": 9980 + }, + { + "epoch": 0.57, + "learning_rate": 1.3632722417769146e-05, + "loss": 0.001, + "step": 9990 + }, + { + "epoch": 0.57, + "learning_rate": 1.36145163247967e-05, + "loss": 0.0006, + "step": 10000 + }, + { + "epoch": 0.57, + "eval_loss": 0.014852229505777359, + "eval_runtime": 372.761, + "eval_samples_per_second": 187.557, + "eval_steps_per_second": 11.723, + "step": 10000 + }, + { + "epoch": 0.57, + "learning_rate": 1.3596310231824252e-05, + "loss": 0.0627, + "step": 10010 + }, + { + "epoch": 0.57, + "learning_rate": 1.3578104138851803e-05, + "loss": 0.0005, + "step": 10020 + }, + { + "epoch": 0.57, + "learning_rate": 1.3559898045879355e-05, + "loss": 0.0004, + "step": 10030 + }, + { + "epoch": 0.57, + "learning_rate": 1.3541691952906907e-05, + "loss": 0.0509, + "step": 10040 + }, + { + "epoch": 0.57, + "learning_rate": 1.3523485859934458e-05, + "loss": 0.0003, + "step": 10050 + }, + { + "epoch": 0.58, + "learning_rate": 1.350527976696201e-05, + "loss": 0.0003, + "step": 10060 + }, + { + "epoch": 0.58, + "learning_rate": 1.3487073673989562e-05, + "loss": 0.0003, + "step": 10070 + }, + { + "epoch": 0.58, + "learning_rate": 1.3468867581017114e-05, + "loss": 0.0007, + "step": 10080 + }, + { + "epoch": 0.58, + "learning_rate": 1.3450661488044666e-05, + "loss": 0.0228, + "step": 10090 + }, + { + "epoch": 0.58, + "learning_rate": 1.3432455395072219e-05, + "loss": 0.0004, + "step": 10100 + }, + { + "epoch": 0.58, + "learning_rate": 1.341424930209977e-05, + "loss": 0.0004, + "step": 10110 + }, + { + "epoch": 0.58, + "learning_rate": 1.3396043209127321e-05, + "loss": 0.0003, + "step": 10120 + }, + { + "epoch": 0.58, + "learning_rate": 1.3377837116154874e-05, + "loss": 0.0003, + "step": 10130 + }, + { + "epoch": 0.58, + "learning_rate": 1.3359631023182424e-05, + "loss": 0.0001, + "step": 10140 + }, + { + "epoch": 0.58, + "learning_rate": 1.3341424930209976e-05, + "loss": 0.0002, + "step": 10150 + }, + { + "epoch": 0.58, + "learning_rate": 1.332321883723753e-05, + "loss": 0.1315, + "step": 10160 + }, + { + "epoch": 0.58, + "learning_rate": 1.330501274426508e-05, + "loss": 0.0002, + "step": 10170 + }, + { + "epoch": 0.58, + "learning_rate": 1.3286806651292633e-05, + "loss": 0.0061, + "step": 10180 + }, + { + "epoch": 0.58, + "learning_rate": 1.3268600558320185e-05, + "loss": 0.0005, + "step": 10190 + }, + { + "epoch": 0.58, + "learning_rate": 1.3250394465347736e-05, + "loss": 0.0013, + "step": 10200 + }, + { + "epoch": 0.58, + "learning_rate": 1.3232188372375288e-05, + "loss": 0.0001, + "step": 10210 + }, + { + "epoch": 0.58, + "learning_rate": 1.321398227940284e-05, + "loss": 0.014, + "step": 10220 + }, + { + "epoch": 0.59, + "learning_rate": 1.3195776186430392e-05, + "loss": 0.0018, + "step": 10230 + }, + { + "epoch": 0.59, + "learning_rate": 1.3177570093457945e-05, + "loss": 0.0194, + "step": 10240 + }, + { + "epoch": 0.59, + "learning_rate": 1.3159364000485497e-05, + "loss": 0.0039, + "step": 10250 + }, + { + "epoch": 0.59, + "learning_rate": 1.3141157907513047e-05, + "loss": 0.0005, + "step": 10260 + }, + { + "epoch": 0.59, + "learning_rate": 1.31229518145406e-05, + "loss": 0.0221, + "step": 10270 + }, + { + "epoch": 0.59, + "learning_rate": 1.3104745721568152e-05, + "loss": 0.0004, + "step": 10280 + }, + { + "epoch": 0.59, + "learning_rate": 1.3086539628595704e-05, + "loss": 0.0005, + "step": 10290 + }, + { + "epoch": 0.59, + "learning_rate": 1.3068333535623255e-05, + "loss": 0.0004, + "step": 10300 + }, + { + "epoch": 0.59, + "learning_rate": 1.3050127442650808e-05, + "loss": 0.0012, + "step": 10310 + }, + { + "epoch": 0.59, + "learning_rate": 1.303192134967836e-05, + "loss": 0.0007, + "step": 10320 + }, + { + "epoch": 0.59, + "learning_rate": 1.3013715256705911e-05, + "loss": 0.0001, + "step": 10330 + }, + { + "epoch": 0.59, + "learning_rate": 1.2995509163733463e-05, + "loss": 0.0001, + "step": 10340 + }, + { + "epoch": 0.59, + "learning_rate": 1.2977303070761016e-05, + "loss": 0.0005, + "step": 10350 + }, + { + "epoch": 0.59, + "learning_rate": 1.2959096977788566e-05, + "loss": 0.0002, + "step": 10360 + }, + { + "epoch": 0.59, + "learning_rate": 1.2940890884816118e-05, + "loss": 0.0317, + "step": 10370 + }, + { + "epoch": 0.59, + "learning_rate": 1.292268479184367e-05, + "loss": 0.0001, + "step": 10380 + }, + { + "epoch": 0.59, + "learning_rate": 1.2904478698871223e-05, + "loss": 0.0155, + "step": 10390 + }, + { + "epoch": 0.59, + "learning_rate": 1.2886272605898775e-05, + "loss": 0.0285, + "step": 10400 + }, + { + "epoch": 0.6, + "learning_rate": 1.2868066512926327e-05, + "loss": 0.0001, + "step": 10410 + }, + { + "epoch": 0.6, + "learning_rate": 1.2849860419953878e-05, + "loss": 0.0233, + "step": 10420 + }, + { + "epoch": 0.6, + "learning_rate": 1.283165432698143e-05, + "loss": 0.0001, + "step": 10430 + }, + { + "epoch": 0.6, + "learning_rate": 1.2813448234008982e-05, + "loss": 0.0003, + "step": 10440 + }, + { + "epoch": 0.6, + "learning_rate": 1.2795242141036533e-05, + "loss": 0.0001, + "step": 10450 + }, + { + "epoch": 0.6, + "learning_rate": 1.2777036048064085e-05, + "loss": 0.0011, + "step": 10460 + }, + { + "epoch": 0.6, + "learning_rate": 1.2758829955091639e-05, + "loss": 0.0003, + "step": 10470 + }, + { + "epoch": 0.6, + "learning_rate": 1.274062386211919e-05, + "loss": 0.0002, + "step": 10480 + }, + { + "epoch": 0.6, + "learning_rate": 1.2722417769146742e-05, + "loss": 0.0003, + "step": 10490 + }, + { + "epoch": 0.6, + "learning_rate": 1.2704211676174294e-05, + "loss": 0.0001, + "step": 10500 + }, + { + "epoch": 0.6, + "learning_rate": 1.2686005583201844e-05, + "loss": 0.0195, + "step": 10510 + }, + { + "epoch": 0.6, + "learning_rate": 1.2667799490229397e-05, + "loss": 0.0001, + "step": 10520 + }, + { + "epoch": 0.6, + "learning_rate": 1.2649593397256949e-05, + "loss": 0.0533, + "step": 10530 + }, + { + "epoch": 0.6, + "learning_rate": 1.2631387304284501e-05, + "loss": 0.0309, + "step": 10540 + }, + { + "epoch": 0.6, + "learning_rate": 1.2613181211312053e-05, + "loss": 0.0001, + "step": 10550 + }, + { + "epoch": 0.6, + "learning_rate": 1.2594975118339605e-05, + "loss": 0.0135, + "step": 10560 + }, + { + "epoch": 0.6, + "learning_rate": 1.2576769025367156e-05, + "loss": 0.0001, + "step": 10570 + }, + { + "epoch": 0.61, + "learning_rate": 1.2558562932394708e-05, + "loss": 0.0001, + "step": 10580 + }, + { + "epoch": 0.61, + "learning_rate": 1.254035683942226e-05, + "loss": 0.0026, + "step": 10590 + }, + { + "epoch": 0.61, + "learning_rate": 1.2522150746449811e-05, + "loss": 0.0009, + "step": 10600 + }, + { + "epoch": 0.61, + "learning_rate": 1.2503944653477363e-05, + "loss": 0.0001, + "step": 10610 + }, + { + "epoch": 0.61, + "learning_rate": 1.2485738560504917e-05, + "loss": 0.0005, + "step": 10620 + }, + { + "epoch": 0.61, + "learning_rate": 1.246753246753247e-05, + "loss": 0.0035, + "step": 10630 + }, + { + "epoch": 0.61, + "learning_rate": 1.244932637456002e-05, + "loss": 0.0035, + "step": 10640 + }, + { + "epoch": 0.61, + "learning_rate": 1.2431120281587572e-05, + "loss": 0.0023, + "step": 10650 + }, + { + "epoch": 0.61, + "learning_rate": 1.2412914188615124e-05, + "loss": 0.0, + "step": 10660 + }, + { + "epoch": 0.61, + "learning_rate": 1.2394708095642675e-05, + "loss": 0.0016, + "step": 10670 + }, + { + "epoch": 0.61, + "learning_rate": 1.2376502002670227e-05, + "loss": 0.0173, + "step": 10680 + }, + { + "epoch": 0.61, + "learning_rate": 1.235829590969778e-05, + "loss": 0.0009, + "step": 10690 + }, + { + "epoch": 0.61, + "learning_rate": 1.2340089816725331e-05, + "loss": 0.0123, + "step": 10700 + }, + { + "epoch": 0.61, + "learning_rate": 1.2321883723752884e-05, + "loss": 0.0002, + "step": 10710 + }, + { + "epoch": 0.61, + "learning_rate": 1.2303677630780436e-05, + "loss": 0.0266, + "step": 10720 + }, + { + "epoch": 0.61, + "learning_rate": 1.2285471537807986e-05, + "loss": 0.0, + "step": 10730 + }, + { + "epoch": 0.61, + "learning_rate": 1.2267265444835539e-05, + "loss": 0.0, + "step": 10740 + }, + { + "epoch": 0.62, + "learning_rate": 1.224905935186309e-05, + "loss": 0.0001, + "step": 10750 + }, + { + "epoch": 0.62, + "learning_rate": 1.2230853258890641e-05, + "loss": 0.0001, + "step": 10760 + }, + { + "epoch": 0.62, + "learning_rate": 1.2212647165918194e-05, + "loss": 0.0, + "step": 10770 + }, + { + "epoch": 0.62, + "learning_rate": 1.2194441072945747e-05, + "loss": 0.0001, + "step": 10780 + }, + { + "epoch": 0.62, + "learning_rate": 1.2176234979973298e-05, + "loss": 0.0117, + "step": 10790 + }, + { + "epoch": 0.62, + "learning_rate": 1.215802888700085e-05, + "loss": 0.0006, + "step": 10800 + }, + { + "epoch": 0.62, + "learning_rate": 1.2139822794028402e-05, + "loss": 0.0, + "step": 10810 + }, + { + "epoch": 0.62, + "learning_rate": 1.2121616701055953e-05, + "loss": 0.0664, + "step": 10820 + }, + { + "epoch": 0.62, + "learning_rate": 1.2103410608083505e-05, + "loss": 0.0001, + "step": 10830 + }, + { + "epoch": 0.62, + "learning_rate": 1.2085204515111057e-05, + "loss": 0.0016, + "step": 10840 + }, + { + "epoch": 0.62, + "learning_rate": 1.2066998422138608e-05, + "loss": 0.0773, + "step": 10850 + }, + { + "epoch": 0.62, + "learning_rate": 1.2048792329166162e-05, + "loss": 0.0018, + "step": 10860 + }, + { + "epoch": 0.62, + "learning_rate": 1.2030586236193714e-05, + "loss": 0.0448, + "step": 10870 + }, + { + "epoch": 0.62, + "learning_rate": 1.2012380143221265e-05, + "loss": 0.0524, + "step": 10880 + }, + { + "epoch": 0.62, + "learning_rate": 1.1994174050248817e-05, + "loss": 0.0003, + "step": 10890 + }, + { + "epoch": 0.62, + "learning_rate": 1.1975967957276369e-05, + "loss": 0.0003, + "step": 10900 + }, + { + "epoch": 0.62, + "learning_rate": 1.195776186430392e-05, + "loss": 0.0004, + "step": 10910 + }, + { + "epoch": 0.62, + "learning_rate": 1.1939555771331472e-05, + "loss": 0.0004, + "step": 10920 + }, + { + "epoch": 0.63, + "learning_rate": 1.1921349678359026e-05, + "loss": 0.0377, + "step": 10930 + }, + { + "epoch": 0.63, + "learning_rate": 1.1903143585386576e-05, + "loss": 0.001, + "step": 10940 + }, + { + "epoch": 0.63, + "learning_rate": 1.1884937492414128e-05, + "loss": 0.0012, + "step": 10950 + }, + { + "epoch": 0.63, + "learning_rate": 1.186673139944168e-05, + "loss": 0.0006, + "step": 10960 + }, + { + "epoch": 0.63, + "learning_rate": 1.1848525306469233e-05, + "loss": 0.007, + "step": 10970 + }, + { + "epoch": 0.63, + "learning_rate": 1.1830319213496783e-05, + "loss": 0.0002, + "step": 10980 + }, + { + "epoch": 0.63, + "learning_rate": 1.1812113120524336e-05, + "loss": 0.0001, + "step": 10990 + }, + { + "epoch": 0.63, + "learning_rate": 1.1793907027551888e-05, + "loss": 0.0589, + "step": 11000 + }, + { + "epoch": 0.63, + "eval_loss": 0.017277490347623825, + "eval_runtime": 373.2487, + "eval_samples_per_second": 187.312, + "eval_steps_per_second": 11.708, + "step": 11000 + }, + { + "epoch": 0.63, + "learning_rate": 1.177570093457944e-05, + "loss": 0.1127, + "step": 11010 + }, + { + "epoch": 0.63, + "learning_rate": 1.1757494841606992e-05, + "loss": 0.0031, + "step": 11020 + }, + { + "epoch": 0.63, + "learning_rate": 1.1739288748634544e-05, + "loss": 0.0004, + "step": 11030 + }, + { + "epoch": 0.63, + "learning_rate": 1.1721082655662095e-05, + "loss": 0.0003, + "step": 11040 + }, + { + "epoch": 0.63, + "learning_rate": 1.1702876562689647e-05, + "loss": 0.0561, + "step": 11050 + }, + { + "epoch": 0.63, + "learning_rate": 1.16846704697172e-05, + "loss": 0.0004, + "step": 11060 + }, + { + "epoch": 0.63, + "learning_rate": 1.166646437674475e-05, + "loss": 0.0496, + "step": 11070 + }, + { + "epoch": 0.63, + "learning_rate": 1.1648258283772302e-05, + "loss": 0.0337, + "step": 11080 + }, + { + "epoch": 0.63, + "learning_rate": 1.1630052190799856e-05, + "loss": 0.0035, + "step": 11090 + }, + { + "epoch": 0.64, + "learning_rate": 1.1611846097827407e-05, + "loss": 0.0111, + "step": 11100 + }, + { + "epoch": 0.64, + "learning_rate": 1.1593640004854959e-05, + "loss": 0.0007, + "step": 11110 + }, + { + "epoch": 0.64, + "learning_rate": 1.1575433911882511e-05, + "loss": 0.0004, + "step": 11120 + }, + { + "epoch": 0.64, + "learning_rate": 1.1557227818910061e-05, + "loss": 0.0058, + "step": 11130 + }, + { + "epoch": 0.64, + "learning_rate": 1.1539021725937614e-05, + "loss": 0.0006, + "step": 11140 + }, + { + "epoch": 0.64, + "learning_rate": 1.1520815632965166e-05, + "loss": 0.0344, + "step": 11150 + }, + { + "epoch": 0.64, + "learning_rate": 1.1502609539992716e-05, + "loss": 0.0017, + "step": 11160 + }, + { + "epoch": 0.64, + "learning_rate": 1.148440344702027e-05, + "loss": 0.0002, + "step": 11170 + }, + { + "epoch": 0.64, + "learning_rate": 1.1466197354047823e-05, + "loss": 0.0518, + "step": 11180 + }, + { + "epoch": 0.64, + "learning_rate": 1.1447991261075373e-05, + "loss": 0.0251, + "step": 11190 + }, + { + "epoch": 0.64, + "learning_rate": 1.1429785168102925e-05, + "loss": 0.0004, + "step": 11200 + }, + { + "epoch": 0.64, + "learning_rate": 1.1411579075130478e-05, + "loss": 0.0005, + "step": 11210 + }, + { + "epoch": 0.64, + "learning_rate": 1.1393372982158028e-05, + "loss": 0.0003, + "step": 11220 + }, + { + "epoch": 0.64, + "learning_rate": 1.137516688918558e-05, + "loss": 0.0003, + "step": 11230 + }, + { + "epoch": 0.64, + "learning_rate": 1.1356960796213132e-05, + "loss": 0.0075, + "step": 11240 + }, + { + "epoch": 0.64, + "learning_rate": 1.1338754703240685e-05, + "loss": 0.0004, + "step": 11250 + }, + { + "epoch": 0.64, + "learning_rate": 1.1320548610268237e-05, + "loss": 0.0004, + "step": 11260 + }, + { + "epoch": 0.64, + "learning_rate": 1.1302342517295789e-05, + "loss": 0.0005, + "step": 11270 + }, + { + "epoch": 0.65, + "learning_rate": 1.128413642432334e-05, + "loss": 0.0002, + "step": 11280 + }, + { + "epoch": 0.65, + "learning_rate": 1.1265930331350892e-05, + "loss": 0.0023, + "step": 11290 + }, + { + "epoch": 0.65, + "learning_rate": 1.1247724238378444e-05, + "loss": 0.0157, + "step": 11300 + }, + { + "epoch": 0.65, + "learning_rate": 1.1229518145405996e-05, + "loss": 0.0317, + "step": 11310 + }, + { + "epoch": 0.65, + "learning_rate": 1.1211312052433549e-05, + "loss": 0.0302, + "step": 11320 + }, + { + "epoch": 0.65, + "learning_rate": 1.11931059594611e-05, + "loss": 0.0308, + "step": 11330 + }, + { + "epoch": 0.65, + "learning_rate": 1.1174899866488653e-05, + "loss": 0.0014, + "step": 11340 + }, + { + "epoch": 0.65, + "learning_rate": 1.1156693773516203e-05, + "loss": 0.0162, + "step": 11350 + }, + { + "epoch": 0.65, + "learning_rate": 1.1138487680543756e-05, + "loss": 0.0071, + "step": 11360 + }, + { + "epoch": 0.65, + "learning_rate": 1.1120281587571308e-05, + "loss": 0.0175, + "step": 11370 + }, + { + "epoch": 0.65, + "learning_rate": 1.1102075494598858e-05, + "loss": 0.0009, + "step": 11380 + }, + { + "epoch": 0.65, + "learning_rate": 1.108386940162641e-05, + "loss": 0.0001, + "step": 11390 + }, + { + "epoch": 0.65, + "learning_rate": 1.1065663308653965e-05, + "loss": 0.0003, + "step": 11400 + }, + { + "epoch": 0.65, + "learning_rate": 1.1047457215681515e-05, + "loss": 0.0008, + "step": 11410 + }, + { + "epoch": 0.65, + "learning_rate": 1.1029251122709067e-05, + "loss": 0.0457, + "step": 11420 + }, + { + "epoch": 0.65, + "learning_rate": 1.101104502973662e-05, + "loss": 0.0005, + "step": 11430 + }, + { + "epoch": 0.65, + "learning_rate": 1.099283893676417e-05, + "loss": 0.0004, + "step": 11440 + }, + { + "epoch": 0.66, + "learning_rate": 1.0974632843791722e-05, + "loss": 0.0646, + "step": 11450 + }, + { + "epoch": 0.66, + "learning_rate": 1.0956426750819274e-05, + "loss": 0.016, + "step": 11460 + }, + { + "epoch": 0.66, + "learning_rate": 1.0938220657846825e-05, + "loss": 0.0463, + "step": 11470 + }, + { + "epoch": 0.66, + "learning_rate": 1.0920014564874379e-05, + "loss": 0.0314, + "step": 11480 + }, + { + "epoch": 0.66, + "learning_rate": 1.0901808471901931e-05, + "loss": 0.0053, + "step": 11490 + }, + { + "epoch": 0.66, + "learning_rate": 1.0883602378929482e-05, + "loss": 0.0013, + "step": 11500 + }, + { + "epoch": 0.66, + "learning_rate": 1.0865396285957034e-05, + "loss": 0.0399, + "step": 11510 + }, + { + "epoch": 0.66, + "learning_rate": 1.0847190192984586e-05, + "loss": 0.0636, + "step": 11520 + }, + { + "epoch": 0.66, + "learning_rate": 1.0828984100012137e-05, + "loss": 0.0654, + "step": 11530 + }, + { + "epoch": 0.66, + "learning_rate": 1.0810778007039689e-05, + "loss": 0.016, + "step": 11540 + }, + { + "epoch": 0.66, + "learning_rate": 1.0792571914067241e-05, + "loss": 0.0007, + "step": 11550 + }, + { + "epoch": 0.66, + "learning_rate": 1.0774365821094793e-05, + "loss": 0.0109, + "step": 11560 + }, + { + "epoch": 0.66, + "learning_rate": 1.0756159728122345e-05, + "loss": 0.0009, + "step": 11570 + }, + { + "epoch": 0.66, + "learning_rate": 1.0737953635149898e-05, + "loss": 0.0273, + "step": 11580 + }, + { + "epoch": 0.66, + "learning_rate": 1.0719747542177448e-05, + "loss": 0.0068, + "step": 11590 + }, + { + "epoch": 0.66, + "learning_rate": 1.0701541449205e-05, + "loss": 0.0007, + "step": 11600 + }, + { + "epoch": 0.66, + "learning_rate": 1.0683335356232553e-05, + "loss": 0.0015, + "step": 11610 + }, + { + "epoch": 0.66, + "learning_rate": 1.0665129263260103e-05, + "loss": 0.0175, + "step": 11620 + }, + { + "epoch": 0.67, + "learning_rate": 1.0646923170287657e-05, + "loss": 0.0236, + "step": 11630 + }, + { + "epoch": 0.67, + "learning_rate": 1.062871707731521e-05, + "loss": 0.0006, + "step": 11640 + }, + { + "epoch": 0.67, + "learning_rate": 1.0610510984342762e-05, + "loss": 0.0008, + "step": 11650 + }, + { + "epoch": 0.67, + "learning_rate": 1.0592304891370312e-05, + "loss": 0.0005, + "step": 11660 + }, + { + "epoch": 0.67, + "learning_rate": 1.0574098798397864e-05, + "loss": 0.0002, + "step": 11670 + }, + { + "epoch": 0.67, + "learning_rate": 1.0555892705425417e-05, + "loss": 0.0002, + "step": 11680 + }, + { + "epoch": 0.67, + "learning_rate": 1.0537686612452967e-05, + "loss": 0.0012, + "step": 11690 + }, + { + "epoch": 0.67, + "learning_rate": 1.051948051948052e-05, + "loss": 0.058, + "step": 11700 + }, + { + "epoch": 0.67, + "learning_rate": 1.0501274426508073e-05, + "loss": 0.0005, + "step": 11710 + }, + { + "epoch": 0.67, + "learning_rate": 1.0483068333535624e-05, + "loss": 0.0507, + "step": 11720 + }, + { + "epoch": 0.67, + "learning_rate": 1.0464862240563176e-05, + "loss": 0.0013, + "step": 11730 + }, + { + "epoch": 0.67, + "learning_rate": 1.0446656147590728e-05, + "loss": 0.0006, + "step": 11740 + }, + { + "epoch": 0.67, + "learning_rate": 1.0428450054618279e-05, + "loss": 0.0007, + "step": 11750 + }, + { + "epoch": 0.67, + "learning_rate": 1.0410243961645831e-05, + "loss": 0.0004, + "step": 11760 + }, + { + "epoch": 0.67, + "learning_rate": 1.0392037868673383e-05, + "loss": 0.0004, + "step": 11770 + }, + { + "epoch": 0.67, + "learning_rate": 1.0373831775700934e-05, + "loss": 0.0004, + "step": 11780 + }, + { + "epoch": 0.67, + "learning_rate": 1.0355625682728488e-05, + "loss": 0.0003, + "step": 11790 + }, + { + "epoch": 0.68, + "learning_rate": 1.033741958975604e-05, + "loss": 0.0378, + "step": 11800 + }, + { + "epoch": 0.68, + "learning_rate": 1.031921349678359e-05, + "loss": 0.0003, + "step": 11810 + }, + { + "epoch": 0.68, + "learning_rate": 1.0301007403811142e-05, + "loss": 0.0276, + "step": 11820 + }, + { + "epoch": 0.68, + "learning_rate": 1.0282801310838695e-05, + "loss": 0.0002, + "step": 11830 + }, + { + "epoch": 0.68, + "learning_rate": 1.0264595217866245e-05, + "loss": 0.0002, + "step": 11840 + }, + { + "epoch": 0.68, + "learning_rate": 1.0246389124893797e-05, + "loss": 0.0002, + "step": 11850 + }, + { + "epoch": 0.68, + "learning_rate": 1.022818303192135e-05, + "loss": 0.0173, + "step": 11860 + }, + { + "epoch": 0.68, + "learning_rate": 1.0209976938948902e-05, + "loss": 0.0002, + "step": 11870 + }, + { + "epoch": 0.68, + "learning_rate": 1.0191770845976454e-05, + "loss": 0.001, + "step": 11880 + }, + { + "epoch": 0.68, + "learning_rate": 1.0173564753004006e-05, + "loss": 0.0005, + "step": 11890 + }, + { + "epoch": 0.68, + "learning_rate": 1.0155358660031557e-05, + "loss": 0.0002, + "step": 11900 + }, + { + "epoch": 0.68, + "learning_rate": 1.0137152567059109e-05, + "loss": 0.0002, + "step": 11910 + }, + { + "epoch": 0.68, + "learning_rate": 1.0118946474086661e-05, + "loss": 0.0028, + "step": 11920 + }, + { + "epoch": 0.68, + "learning_rate": 1.0100740381114212e-05, + "loss": 0.0022, + "step": 11930 + }, + { + "epoch": 0.68, + "learning_rate": 1.0082534288141764e-05, + "loss": 0.0001, + "step": 11940 + }, + { + "epoch": 0.68, + "learning_rate": 1.0064328195169318e-05, + "loss": 0.0002, + "step": 11950 + }, + { + "epoch": 0.68, + "learning_rate": 1.0046122102196868e-05, + "loss": 0.0582, + "step": 11960 + }, + { + "epoch": 0.68, + "learning_rate": 1.002791600922442e-05, + "loss": 0.0002, + "step": 11970 + }, + { + "epoch": 0.69, + "learning_rate": 1.0009709916251973e-05, + "loss": 0.0001, + "step": 11980 + }, + { + "epoch": 0.69, + "learning_rate": 9.991503823279525e-06, + "loss": 0.0002, + "step": 11990 + }, + { + "epoch": 0.69, + "learning_rate": 9.973297730307076e-06, + "loss": 0.0005, + "step": 12000 + }, + { + "epoch": 0.69, + "eval_loss": 0.013699620962142944, + "eval_runtime": 374.908, + "eval_samples_per_second": 186.483, + "eval_steps_per_second": 11.656, + "step": 12000 + }, + { + "epoch": 0.69, + "learning_rate": 9.955091637334628e-06, + "loss": 0.0002, + "step": 12010 + }, + { + "epoch": 0.69, + "learning_rate": 9.936885544362182e-06, + "loss": 0.0002, + "step": 12020 + }, + { + "epoch": 0.69, + "learning_rate": 9.918679451389732e-06, + "loss": 0.0001, + "step": 12030 + }, + { + "epoch": 0.69, + "learning_rate": 9.900473358417284e-06, + "loss": 0.0001, + "step": 12040 + }, + { + "epoch": 0.69, + "learning_rate": 9.882267265444837e-06, + "loss": 0.0004, + "step": 12050 + }, + { + "epoch": 0.69, + "learning_rate": 9.864061172472387e-06, + "loss": 0.049, + "step": 12060 + }, + { + "epoch": 0.69, + "learning_rate": 9.84585507949994e-06, + "loss": 0.0534, + "step": 12070 + }, + { + "epoch": 0.69, + "learning_rate": 9.827648986527492e-06, + "loss": 0.0003, + "step": 12080 + }, + { + "epoch": 0.69, + "learning_rate": 9.809442893555042e-06, + "loss": 0.0002, + "step": 12090 + }, + { + "epoch": 0.69, + "learning_rate": 9.791236800582596e-06, + "loss": 0.0002, + "step": 12100 + }, + { + "epoch": 0.69, + "learning_rate": 9.773030707610148e-06, + "loss": 0.0002, + "step": 12110 + }, + { + "epoch": 0.69, + "learning_rate": 9.754824614637699e-06, + "loss": 0.0002, + "step": 12120 + }, + { + "epoch": 0.69, + "learning_rate": 9.736618521665251e-06, + "loss": 0.0117, + "step": 12130 + }, + { + "epoch": 0.69, + "learning_rate": 9.718412428692803e-06, + "loss": 0.0009, + "step": 12140 + }, + { + "epoch": 0.7, + "learning_rate": 9.700206335720354e-06, + "loss": 0.042, + "step": 12150 + }, + { + "epoch": 0.7, + "learning_rate": 9.682000242747906e-06, + "loss": 0.0004, + "step": 12160 + }, + { + "epoch": 0.7, + "learning_rate": 9.663794149775458e-06, + "loss": 0.0003, + "step": 12170 + }, + { + "epoch": 0.7, + "learning_rate": 9.64558805680301e-06, + "loss": 0.0002, + "step": 12180 + }, + { + "epoch": 0.7, + "learning_rate": 9.627381963830563e-06, + "loss": 0.0506, + "step": 12190 + }, + { + "epoch": 0.7, + "learning_rate": 9.609175870858115e-06, + "loss": 0.0002, + "step": 12200 + }, + { + "epoch": 0.7, + "learning_rate": 9.590969777885665e-06, + "loss": 0.0004, + "step": 12210 + }, + { + "epoch": 0.7, + "learning_rate": 9.572763684913218e-06, + "loss": 0.0423, + "step": 12220 + }, + { + "epoch": 0.7, + "learning_rate": 9.55455759194077e-06, + "loss": 0.0373, + "step": 12230 + }, + { + "epoch": 0.7, + "learning_rate": 9.53635149896832e-06, + "loss": 0.003, + "step": 12240 + }, + { + "epoch": 0.7, + "learning_rate": 9.518145405995873e-06, + "loss": 0.0007, + "step": 12250 + }, + { + "epoch": 0.7, + "learning_rate": 9.499939313023426e-06, + "loss": 0.0004, + "step": 12260 + }, + { + "epoch": 0.7, + "learning_rate": 9.481733220050977e-06, + "loss": 0.0003, + "step": 12270 + }, + { + "epoch": 0.7, + "learning_rate": 9.46352712707853e-06, + "loss": 0.0004, + "step": 12280 + }, + { + "epoch": 0.7, + "learning_rate": 9.445321034106081e-06, + "loss": 0.0003, + "step": 12290 + }, + { + "epoch": 0.7, + "learning_rate": 9.427114941133632e-06, + "loss": 0.0006, + "step": 12300 + }, + { + "epoch": 0.7, + "learning_rate": 9.408908848161184e-06, + "loss": 0.0007, + "step": 12310 + }, + { + "epoch": 0.7, + "learning_rate": 9.390702755188736e-06, + "loss": 0.0441, + "step": 12320 + }, + { + "epoch": 0.71, + "learning_rate": 9.372496662216289e-06, + "loss": 0.0022, + "step": 12330 + }, + { + "epoch": 0.71, + "learning_rate": 9.35429056924384e-06, + "loss": 0.0967, + "step": 12340 + }, + { + "epoch": 0.71, + "learning_rate": 9.336084476271393e-06, + "loss": 0.0451, + "step": 12350 + }, + { + "epoch": 0.71, + "learning_rate": 9.317878383298945e-06, + "loss": 0.0015, + "step": 12360 + }, + { + "epoch": 0.71, + "learning_rate": 9.299672290326496e-06, + "loss": 0.0233, + "step": 12370 + }, + { + "epoch": 0.71, + "learning_rate": 9.281466197354048e-06, + "loss": 0.0005, + "step": 12380 + }, + { + "epoch": 0.71, + "learning_rate": 9.2632601043816e-06, + "loss": 0.0004, + "step": 12390 + }, + { + "epoch": 0.71, + "learning_rate": 9.24505401140915e-06, + "loss": 0.0002, + "step": 12400 + }, + { + "epoch": 0.71, + "learning_rate": 9.226847918436705e-06, + "loss": 0.0297, + "step": 12410 + }, + { + "epoch": 0.71, + "learning_rate": 9.208641825464257e-06, + "loss": 0.0309, + "step": 12420 + }, + { + "epoch": 0.71, + "learning_rate": 9.190435732491807e-06, + "loss": 0.0242, + "step": 12430 + }, + { + "epoch": 0.71, + "learning_rate": 9.17222963951936e-06, + "loss": 0.0004, + "step": 12440 + }, + { + "epoch": 0.71, + "learning_rate": 9.154023546546912e-06, + "loss": 0.0011, + "step": 12450 + }, + { + "epoch": 0.71, + "learning_rate": 9.135817453574462e-06, + "loss": 0.0006, + "step": 12460 + }, + { + "epoch": 0.71, + "learning_rate": 9.117611360602015e-06, + "loss": 0.0023, + "step": 12470 + }, + { + "epoch": 0.71, + "learning_rate": 9.099405267629567e-06, + "loss": 0.0006, + "step": 12480 + }, + { + "epoch": 0.71, + "learning_rate": 9.081199174657119e-06, + "loss": 0.0004, + "step": 12490 + }, + { + "epoch": 0.72, + "learning_rate": 9.062993081684671e-06, + "loss": 0.0376, + "step": 12500 + }, + { + "epoch": 0.72, + "learning_rate": 9.044786988712223e-06, + "loss": 0.0006, + "step": 12510 + }, + { + "epoch": 0.72, + "learning_rate": 9.026580895739774e-06, + "loss": 0.0003, + "step": 12520 + }, + { + "epoch": 0.72, + "learning_rate": 9.008374802767326e-06, + "loss": 0.0075, + "step": 12530 + }, + { + "epoch": 0.72, + "learning_rate": 8.990168709794878e-06, + "loss": 0.0006, + "step": 12540 + }, + { + "epoch": 0.72, + "learning_rate": 8.971962616822429e-06, + "loss": 0.0001, + "step": 12550 + }, + { + "epoch": 0.72, + "learning_rate": 8.953756523849981e-06, + "loss": 0.0003, + "step": 12560 + }, + { + "epoch": 0.72, + "learning_rate": 8.935550430877535e-06, + "loss": 0.0319, + "step": 12570 + }, + { + "epoch": 0.72, + "learning_rate": 8.917344337905086e-06, + "loss": 0.0005, + "step": 12580 + }, + { + "epoch": 0.72, + "learning_rate": 8.899138244932638e-06, + "loss": 0.0478, + "step": 12590 + }, + { + "epoch": 0.72, + "learning_rate": 8.88093215196019e-06, + "loss": 0.0008, + "step": 12600 + }, + { + "epoch": 0.72, + "learning_rate": 8.86272605898774e-06, + "loss": 0.0585, + "step": 12610 + }, + { + "epoch": 0.72, + "learning_rate": 8.844519966015293e-06, + "loss": 0.0003, + "step": 12620 + }, + { + "epoch": 0.72, + "learning_rate": 8.826313873042845e-06, + "loss": 0.0017, + "step": 12630 + }, + { + "epoch": 0.72, + "learning_rate": 8.808107780070395e-06, + "loss": 0.001, + "step": 12640 + }, + { + "epoch": 0.72, + "learning_rate": 8.78990168709795e-06, + "loss": 0.0003, + "step": 12650 + }, + { + "epoch": 0.72, + "learning_rate": 8.771695594125502e-06, + "loss": 0.0011, + "step": 12660 + }, + { + "epoch": 0.72, + "learning_rate": 8.753489501153054e-06, + "loss": 0.0006, + "step": 12670 + }, + { + "epoch": 0.73, + "learning_rate": 8.735283408180604e-06, + "loss": 0.0351, + "step": 12680 + }, + { + "epoch": 0.73, + "learning_rate": 8.717077315208157e-06, + "loss": 0.0006, + "step": 12690 + }, + { + "epoch": 0.73, + "learning_rate": 8.698871222235709e-06, + "loss": 0.0002, + "step": 12700 + }, + { + "epoch": 0.73, + "learning_rate": 8.68066512926326e-06, + "loss": 0.0003, + "step": 12710 + }, + { + "epoch": 0.73, + "learning_rate": 8.662459036290812e-06, + "loss": 0.0004, + "step": 12720 + }, + { + "epoch": 0.73, + "learning_rate": 8.644252943318365e-06, + "loss": 0.0056, + "step": 12730 + }, + { + "epoch": 0.73, + "learning_rate": 8.626046850345916e-06, + "loss": 0.0549, + "step": 12740 + }, + { + "epoch": 0.73, + "learning_rate": 8.607840757373468e-06, + "loss": 0.0002, + "step": 12750 + }, + { + "epoch": 0.73, + "learning_rate": 8.58963466440102e-06, + "loss": 0.0002, + "step": 12760 + }, + { + "epoch": 0.73, + "learning_rate": 8.571428571428571e-06, + "loss": 0.0003, + "step": 12770 + }, + { + "epoch": 0.73, + "learning_rate": 8.553222478456123e-06, + "loss": 0.0151, + "step": 12780 + }, + { + "epoch": 0.73, + "learning_rate": 8.535016385483675e-06, + "loss": 0.015, + "step": 12790 + }, + { + "epoch": 0.73, + "learning_rate": 8.516810292511228e-06, + "loss": 0.0234, + "step": 12800 + }, + { + "epoch": 0.73, + "learning_rate": 8.49860419953878e-06, + "loss": 0.0208, + "step": 12810 + }, + { + "epoch": 0.73, + "learning_rate": 8.480398106566332e-06, + "loss": 0.0001, + "step": 12820 + }, + { + "epoch": 0.73, + "learning_rate": 8.462192013593883e-06, + "loss": 0.0004, + "step": 12830 + }, + { + "epoch": 0.73, + "learning_rate": 8.443985920621435e-06, + "loss": 0.0001, + "step": 12840 + }, + { + "epoch": 0.74, + "learning_rate": 8.425779827648987e-06, + "loss": 0.0481, + "step": 12850 + }, + { + "epoch": 0.74, + "learning_rate": 8.407573734676537e-06, + "loss": 0.0321, + "step": 12860 + }, + { + "epoch": 0.74, + "learning_rate": 8.38936764170409e-06, + "loss": 0.0008, + "step": 12870 + }, + { + "epoch": 0.74, + "learning_rate": 8.371161548731644e-06, + "loss": 0.0017, + "step": 12880 + }, + { + "epoch": 0.74, + "learning_rate": 8.352955455759194e-06, + "loss": 0.0003, + "step": 12890 + }, + { + "epoch": 0.74, + "learning_rate": 8.334749362786746e-06, + "loss": 0.0002, + "step": 12900 + }, + { + "epoch": 0.74, + "learning_rate": 8.316543269814299e-06, + "loss": 0.0003, + "step": 12910 + }, + { + "epoch": 0.74, + "learning_rate": 8.298337176841849e-06, + "loss": 0.018, + "step": 12920 + }, + { + "epoch": 0.74, + "learning_rate": 8.280131083869401e-06, + "loss": 0.0006, + "step": 12930 + }, + { + "epoch": 0.74, + "learning_rate": 8.261924990896954e-06, + "loss": 0.0239, + "step": 12940 + }, + { + "epoch": 0.74, + "learning_rate": 8.243718897924504e-06, + "loss": 0.0001, + "step": 12950 + }, + { + "epoch": 0.74, + "learning_rate": 8.225512804952058e-06, + "loss": 0.0002, + "step": 12960 + }, + { + "epoch": 0.74, + "learning_rate": 8.20730671197961e-06, + "loss": 0.0002, + "step": 12970 + }, + { + "epoch": 0.74, + "learning_rate": 8.18910061900716e-06, + "loss": 0.0425, + "step": 12980 + }, + { + "epoch": 0.74, + "learning_rate": 8.170894526034713e-06, + "loss": 0.0002, + "step": 12990 + }, + { + "epoch": 0.74, + "learning_rate": 8.152688433062265e-06, + "loss": 0.0264, + "step": 13000 + }, + { + "epoch": 0.74, + "eval_loss": 0.010751000605523586, + "eval_runtime": 606.5318, + "eval_samples_per_second": 115.268, + "eval_steps_per_second": 7.205, + "step": 13000 + }, + { + "epoch": 0.74, + "learning_rate": 8.134482340089817e-06, + "loss": 0.0225, + "step": 13010 + }, + { + "epoch": 0.74, + "learning_rate": 8.116276247117368e-06, + "loss": 0.048, + "step": 13020 + }, + { + "epoch": 0.75, + "learning_rate": 8.09807015414492e-06, + "loss": 0.0012, + "step": 13030 + }, + { + "epoch": 0.75, + "learning_rate": 8.079864061172474e-06, + "loss": 0.0008, + "step": 13040 + }, + { + "epoch": 0.75, + "learning_rate": 8.061657968200025e-06, + "loss": 0.0007, + "step": 13050 + }, + { + "epoch": 0.75, + "learning_rate": 8.043451875227577e-06, + "loss": 0.0001, + "step": 13060 + }, + { + "epoch": 0.75, + "learning_rate": 8.025245782255129e-06, + "loss": 0.0002, + "step": 13070 + }, + { + "epoch": 0.75, + "learning_rate": 8.00703968928268e-06, + "loss": 0.0015, + "step": 13080 + }, + { + "epoch": 0.75, + "learning_rate": 7.988833596310232e-06, + "loss": 0.0002, + "step": 13090 + }, + { + "epoch": 0.75, + "learning_rate": 7.970627503337784e-06, + "loss": 0.0002, + "step": 13100 + }, + { + "epoch": 0.75, + "learning_rate": 7.952421410365336e-06, + "loss": 0.0211, + "step": 13110 + }, + { + "epoch": 0.75, + "learning_rate": 7.934215317392888e-06, + "loss": 0.0002, + "step": 13120 + }, + { + "epoch": 0.75, + "learning_rate": 7.91600922442044e-06, + "loss": 0.0002, + "step": 13130 + }, + { + "epoch": 0.75, + "learning_rate": 7.897803131447991e-06, + "loss": 0.0002, + "step": 13140 + }, + { + "epoch": 0.75, + "learning_rate": 7.879597038475543e-06, + "loss": 0.0005, + "step": 13150 + }, + { + "epoch": 0.75, + "learning_rate": 7.861390945503096e-06, + "loss": 0.0005, + "step": 13160 + }, + { + "epoch": 0.75, + "learning_rate": 7.843184852530646e-06, + "loss": 0.0062, + "step": 13170 + }, + { + "epoch": 0.75, + "learning_rate": 7.824978759558198e-06, + "loss": 0.0001, + "step": 13180 + }, + { + "epoch": 0.75, + "learning_rate": 7.806772666585752e-06, + "loss": 0.0002, + "step": 13190 + }, + { + "epoch": 0.76, + "learning_rate": 7.788566573613303e-06, + "loss": 0.0001, + "step": 13200 + }, + { + "epoch": 0.76, + "learning_rate": 7.770360480640855e-06, + "loss": 0.0002, + "step": 13210 + }, + { + "epoch": 0.76, + "learning_rate": 7.752154387668407e-06, + "loss": 0.0212, + "step": 13220 + }, + { + "epoch": 0.76, + "learning_rate": 7.733948294695958e-06, + "loss": 0.0002, + "step": 13230 + }, + { + "epoch": 0.76, + "learning_rate": 7.71574220172351e-06, + "loss": 0.0006, + "step": 13240 + }, + { + "epoch": 0.76, + "learning_rate": 7.697536108751062e-06, + "loss": 0.0001, + "step": 13250 + }, + { + "epoch": 0.76, + "learning_rate": 7.679330015778613e-06, + "loss": 0.0194, + "step": 13260 + }, + { + "epoch": 0.76, + "learning_rate": 7.661123922806167e-06, + "loss": 0.0446, + "step": 13270 + }, + { + "epoch": 0.76, + "learning_rate": 7.642917829833719e-06, + "loss": 0.0001, + "step": 13280 + }, + { + "epoch": 0.76, + "learning_rate": 7.624711736861269e-06, + "loss": 0.0011, + "step": 13290 + }, + { + "epoch": 0.76, + "learning_rate": 7.6065056438888215e-06, + "loss": 0.039, + "step": 13300 + }, + { + "epoch": 0.76, + "learning_rate": 7.588299550916374e-06, + "loss": 0.0004, + "step": 13310 + }, + { + "epoch": 0.76, + "learning_rate": 7.570093457943924e-06, + "loss": 0.0001, + "step": 13320 + }, + { + "epoch": 0.76, + "learning_rate": 7.551887364971477e-06, + "loss": 0.0004, + "step": 13330 + }, + { + "epoch": 0.76, + "learning_rate": 7.5336812719990295e-06, + "loss": 0.0001, + "step": 13340 + }, + { + "epoch": 0.76, + "learning_rate": 7.515475179026582e-06, + "loss": 0.0004, + "step": 13350 + }, + { + "epoch": 0.76, + "learning_rate": 7.497269086054132e-06, + "loss": 0.0005, + "step": 13360 + }, + { + "epoch": 0.76, + "learning_rate": 7.479062993081685e-06, + "loss": 0.0533, + "step": 13370 + }, + { + "epoch": 0.77, + "learning_rate": 7.460856900109237e-06, + "loss": 0.0007, + "step": 13380 + }, + { + "epoch": 0.77, + "learning_rate": 7.442650807136788e-06, + "loss": 0.0001, + "step": 13390 + }, + { + "epoch": 0.77, + "learning_rate": 7.42444471416434e-06, + "loss": 0.0142, + "step": 13400 + }, + { + "epoch": 0.77, + "learning_rate": 7.4062386211918925e-06, + "loss": 0.061, + "step": 13410 + }, + { + "epoch": 0.77, + "learning_rate": 7.388032528219445e-06, + "loss": 0.0001, + "step": 13420 + }, + { + "epoch": 0.77, + "learning_rate": 7.369826435246996e-06, + "loss": 0.0089, + "step": 13430 + }, + { + "epoch": 0.77, + "learning_rate": 7.3516203422745475e-06, + "loss": 0.0001, + "step": 13440 + }, + { + "epoch": 0.77, + "learning_rate": 7.3334142493021005e-06, + "loss": 0.0001, + "step": 13450 + }, + { + "epoch": 0.77, + "learning_rate": 7.315208156329652e-06, + "loss": 0.0139, + "step": 13460 + }, + { + "epoch": 0.77, + "learning_rate": 7.297002063357203e-06, + "loss": 0.0451, + "step": 13470 + }, + { + "epoch": 0.77, + "learning_rate": 7.278795970384756e-06, + "loss": 0.0001, + "step": 13480 + }, + { + "epoch": 0.77, + "learning_rate": 7.260589877412308e-06, + "loss": 0.0001, + "step": 13490 + }, + { + "epoch": 0.77, + "learning_rate": 7.242383784439859e-06, + "loss": 0.0007, + "step": 13500 + }, + { + "epoch": 0.77, + "learning_rate": 7.224177691467411e-06, + "loss": 0.0005, + "step": 13510 + }, + { + "epoch": 0.77, + "learning_rate": 7.2059715984949635e-06, + "loss": 0.0001, + "step": 13520 + }, + { + "epoch": 0.77, + "learning_rate": 7.187765505522515e-06, + "loss": 0.0003, + "step": 13530 + }, + { + "epoch": 0.77, + "learning_rate": 7.169559412550067e-06, + "loss": 0.0003, + "step": 13540 + }, + { + "epoch": 0.78, + "learning_rate": 7.1513533195776185e-06, + "loss": 0.0003, + "step": 13550 + }, + { + "epoch": 0.78, + "learning_rate": 7.133147226605171e-06, + "loss": 0.0005, + "step": 13560 + }, + { + "epoch": 0.78, + "learning_rate": 7.114941133632723e-06, + "loss": 0.0143, + "step": 13570 + }, + { + "epoch": 0.78, + "learning_rate": 7.096735040660274e-06, + "loss": 0.0007, + "step": 13580 + }, + { + "epoch": 0.78, + "learning_rate": 7.0785289476878265e-06, + "loss": 0.0124, + "step": 13590 + }, + { + "epoch": 0.78, + "learning_rate": 7.060322854715379e-06, + "loss": 0.0041, + "step": 13600 + }, + { + "epoch": 0.78, + "learning_rate": 7.04211676174293e-06, + "loss": 0.0001, + "step": 13610 + }, + { + "epoch": 0.78, + "learning_rate": 7.023910668770482e-06, + "loss": 0.0002, + "step": 13620 + }, + { + "epoch": 0.78, + "learning_rate": 7.005704575798034e-06, + "loss": 0.0005, + "step": 13630 + }, + { + "epoch": 0.78, + "learning_rate": 6.987498482825586e-06, + "loss": 0.0468, + "step": 13640 + }, + { + "epoch": 0.78, + "learning_rate": 6.969292389853138e-06, + "loss": 0.0296, + "step": 13650 + }, + { + "epoch": 0.78, + "learning_rate": 6.9510862968806895e-06, + "loss": 0.0005, + "step": 13660 + }, + { + "epoch": 0.78, + "learning_rate": 6.932880203908241e-06, + "loss": 0.0239, + "step": 13670 + }, + { + "epoch": 0.78, + "learning_rate": 6.914674110935794e-06, + "loss": 0.0001, + "step": 13680 + }, + { + "epoch": 0.78, + "learning_rate": 6.896468017963345e-06, + "loss": 0.0078, + "step": 13690 + }, + { + "epoch": 0.78, + "learning_rate": 6.878261924990897e-06, + "loss": 0.0007, + "step": 13700 + }, + { + "epoch": 0.78, + "learning_rate": 6.860055832018449e-06, + "loss": 0.0005, + "step": 13710 + }, + { + "epoch": 0.78, + "learning_rate": 6.841849739046001e-06, + "loss": 0.0002, + "step": 13720 + }, + { + "epoch": 0.79, + "learning_rate": 6.8236436460735524e-06, + "loss": 0.0002, + "step": 13730 + }, + { + "epoch": 0.79, + "learning_rate": 6.805437553101105e-06, + "loss": 0.0016, + "step": 13740 + }, + { + "epoch": 0.79, + "learning_rate": 6.787231460128656e-06, + "loss": 0.0004, + "step": 13750 + }, + { + "epoch": 0.79, + "learning_rate": 6.769025367156209e-06, + "loss": 0.0001, + "step": 13760 + }, + { + "epoch": 0.79, + "learning_rate": 6.7508192741837605e-06, + "loss": 0.0001, + "step": 13770 + }, + { + "epoch": 0.79, + "learning_rate": 6.732613181211312e-06, + "loss": 0.0001, + "step": 13780 + }, + { + "epoch": 0.79, + "learning_rate": 6.714407088238864e-06, + "loss": 0.0194, + "step": 13790 + }, + { + "epoch": 0.79, + "learning_rate": 6.696200995266416e-06, + "loss": 0.0284, + "step": 13800 + }, + { + "epoch": 0.79, + "learning_rate": 6.677994902293968e-06, + "loss": 0.0001, + "step": 13810 + }, + { + "epoch": 0.79, + "learning_rate": 6.65978880932152e-06, + "loss": 0.0001, + "step": 13820 + }, + { + "epoch": 0.79, + "learning_rate": 6.641582716349072e-06, + "loss": 0.0285, + "step": 13830 + }, + { + "epoch": 0.79, + "learning_rate": 6.6233766233766234e-06, + "loss": 0.0001, + "step": 13840 + }, + { + "epoch": 0.79, + "learning_rate": 6.605170530404176e-06, + "loss": 0.0001, + "step": 13850 + }, + { + "epoch": 0.79, + "learning_rate": 6.586964437431727e-06, + "loss": 0.0149, + "step": 13860 + }, + { + "epoch": 0.79, + "learning_rate": 6.568758344459279e-06, + "loss": 0.0123, + "step": 13870 + }, + { + "epoch": 0.79, + "learning_rate": 6.5505522514868315e-06, + "loss": 0.0001, + "step": 13880 + }, + { + "epoch": 0.79, + "learning_rate": 6.532346158514383e-06, + "loss": 0.0015, + "step": 13890 + }, + { + "epoch": 0.8, + "learning_rate": 6.514140065541934e-06, + "loss": 0.0, + "step": 13900 + }, + { + "epoch": 0.8, + "learning_rate": 6.495933972569487e-06, + "loss": 0.0016, + "step": 13910 + }, + { + "epoch": 0.8, + "learning_rate": 6.477727879597039e-06, + "loss": 0.0502, + "step": 13920 + }, + { + "epoch": 0.8, + "learning_rate": 6.459521786624591e-06, + "loss": 0.0147, + "step": 13930 + }, + { + "epoch": 0.8, + "learning_rate": 6.441315693652142e-06, + "loss": 0.0001, + "step": 13940 + }, + { + "epoch": 0.8, + "learning_rate": 6.4231096006796944e-06, + "loss": 0.0004, + "step": 13950 + }, + { + "epoch": 0.8, + "learning_rate": 6.404903507707247e-06, + "loss": 0.0001, + "step": 13960 + }, + { + "epoch": 0.8, + "learning_rate": 6.386697414734798e-06, + "loss": 0.0, + "step": 13970 + }, + { + "epoch": 0.8, + "learning_rate": 6.368491321762349e-06, + "loss": 0.0619, + "step": 13980 + }, + { + "epoch": 0.8, + "learning_rate": 6.3502852287899025e-06, + "loss": 0.0001, + "step": 13990 + }, + { + "epoch": 0.8, + "learning_rate": 6.332079135817454e-06, + "loss": 0.0001, + "step": 14000 + }, + { + "epoch": 0.8, + "eval_loss": 0.011908884160220623, + "eval_runtime": 373.7901, + "eval_samples_per_second": 187.041, + "eval_steps_per_second": 11.691, + "step": 14000 + }, + { + "epoch": 0.8, + "learning_rate": 6.313873042845005e-06, + "loss": 0.0008, + "step": 14010 + }, + { + "epoch": 0.8, + "learning_rate": 6.2956669498725574e-06, + "loss": 0.0002, + "step": 14020 + }, + { + "epoch": 0.8, + "learning_rate": 6.27746085690011e-06, + "loss": 0.0003, + "step": 14030 + }, + { + "epoch": 0.8, + "learning_rate": 6.259254763927661e-06, + "loss": 0.0203, + "step": 14040 + }, + { + "epoch": 0.8, + "learning_rate": 6.241048670955213e-06, + "loss": 0.0001, + "step": 14050 + }, + { + "epoch": 0.8, + "learning_rate": 6.222842577982765e-06, + "loss": 0.0033, + "step": 14060 + }, + { + "epoch": 0.8, + "learning_rate": 6.204636485010317e-06, + "loss": 0.0008, + "step": 14070 + }, + { + "epoch": 0.81, + "learning_rate": 6.186430392037869e-06, + "loss": 0.0001, + "step": 14080 + }, + { + "epoch": 0.81, + "learning_rate": 6.16822429906542e-06, + "loss": 0.0662, + "step": 14090 + }, + { + "epoch": 0.81, + "learning_rate": 6.150018206092973e-06, + "loss": 0.0191, + "step": 14100 + }, + { + "epoch": 0.81, + "learning_rate": 6.131812113120525e-06, + "loss": 0.0002, + "step": 14110 + }, + { + "epoch": 0.81, + "learning_rate": 6.113606020148076e-06, + "loss": 0.0001, + "step": 14120 + }, + { + "epoch": 0.81, + "learning_rate": 6.0953999271756284e-06, + "loss": 0.0003, + "step": 14130 + }, + { + "epoch": 0.81, + "learning_rate": 6.07719383420318e-06, + "loss": 0.0443, + "step": 14140 + }, + { + "epoch": 0.81, + "learning_rate": 6.058987741230732e-06, + "loss": 0.012, + "step": 14150 + }, + { + "epoch": 0.81, + "learning_rate": 6.040781648258284e-06, + "loss": 0.0013, + "step": 14160 + }, + { + "epoch": 0.81, + "learning_rate": 6.022575555285836e-06, + "loss": 0.0244, + "step": 14170 + }, + { + "epoch": 0.81, + "learning_rate": 6.004369462313388e-06, + "loss": 0.0003, + "step": 14180 + }, + { + "epoch": 0.81, + "learning_rate": 5.98616336934094e-06, + "loss": 0.0002, + "step": 14190 + }, + { + "epoch": 0.81, + "learning_rate": 5.967957276368491e-06, + "loss": 0.0002, + "step": 14200 + }, + { + "epoch": 0.81, + "learning_rate": 5.949751183396043e-06, + "loss": 0.0005, + "step": 14210 + }, + { + "epoch": 0.81, + "learning_rate": 5.931545090423596e-06, + "loss": 0.026, + "step": 14220 + }, + { + "epoch": 0.81, + "learning_rate": 5.913338997451147e-06, + "loss": 0.0001, + "step": 14230 + }, + { + "epoch": 0.81, + "learning_rate": 5.895132904478699e-06, + "loss": 0.0001, + "step": 14240 + }, + { + "epoch": 0.82, + "learning_rate": 5.876926811506251e-06, + "loss": 0.0001, + "step": 14250 + }, + { + "epoch": 0.82, + "learning_rate": 5.858720718533803e-06, + "loss": 0.0308, + "step": 14260 + }, + { + "epoch": 0.82, + "learning_rate": 5.840514625561355e-06, + "loss": 0.0002, + "step": 14270 + }, + { + "epoch": 0.82, + "learning_rate": 5.822308532588907e-06, + "loss": 0.0015, + "step": 14280 + }, + { + "epoch": 0.82, + "learning_rate": 5.804102439616458e-06, + "loss": 0.0002, + "step": 14290 + }, + { + "epoch": 0.82, + "learning_rate": 5.785896346644011e-06, + "loss": 0.0007, + "step": 14300 + }, + { + "epoch": 0.82, + "learning_rate": 5.767690253671562e-06, + "loss": 0.0018, + "step": 14310 + }, + { + "epoch": 0.82, + "learning_rate": 5.749484160699114e-06, + "loss": 0.0001, + "step": 14320 + }, + { + "epoch": 0.82, + "learning_rate": 5.731278067726666e-06, + "loss": 0.0001, + "step": 14330 + }, + { + "epoch": 0.82, + "learning_rate": 5.713071974754218e-06, + "loss": 0.0002, + "step": 14340 + }, + { + "epoch": 0.82, + "learning_rate": 5.69486588178177e-06, + "loss": 0.0004, + "step": 14350 + }, + { + "epoch": 0.82, + "learning_rate": 5.676659788809322e-06, + "loss": 0.0003, + "step": 14360 + }, + { + "epoch": 0.82, + "learning_rate": 5.658453695836873e-06, + "loss": 0.0001, + "step": 14370 + }, + { + "epoch": 0.82, + "learning_rate": 5.640247602864425e-06, + "loss": 0.0006, + "step": 14380 + }, + { + "epoch": 0.82, + "learning_rate": 5.622041509891978e-06, + "loss": 0.011, + "step": 14390 + }, + { + "epoch": 0.82, + "learning_rate": 5.603835416919529e-06, + "loss": 0.0001, + "step": 14400 + }, + { + "epoch": 0.82, + "learning_rate": 5.58562932394708e-06, + "loss": 0.0011, + "step": 14410 + }, + { + "epoch": 0.82, + "learning_rate": 5.567423230974633e-06, + "loss": 0.0546, + "step": 14420 + }, + { + "epoch": 0.83, + "learning_rate": 5.549217138002185e-06, + "loss": 0.0849, + "step": 14430 + }, + { + "epoch": 0.83, + "learning_rate": 5.531011045029737e-06, + "loss": 0.0004, + "step": 14440 + }, + { + "epoch": 0.83, + "learning_rate": 5.512804952057288e-06, + "loss": 0.0005, + "step": 14450 + }, + { + "epoch": 0.83, + "learning_rate": 5.494598859084841e-06, + "loss": 0.0005, + "step": 14460 + }, + { + "epoch": 0.83, + "learning_rate": 5.476392766112393e-06, + "loss": 0.0003, + "step": 14470 + }, + { + "epoch": 0.83, + "learning_rate": 5.458186673139944e-06, + "loss": 0.0003, + "step": 14480 + }, + { + "epoch": 0.83, + "learning_rate": 5.4399805801674955e-06, + "loss": 0.0439, + "step": 14490 + }, + { + "epoch": 0.83, + "learning_rate": 5.421774487195049e-06, + "loss": 0.0004, + "step": 14500 + }, + { + "epoch": 0.83, + "learning_rate": 5.4035683942226e-06, + "loss": 0.0379, + "step": 14510 + }, + { + "epoch": 0.83, + "learning_rate": 5.385362301250151e-06, + "loss": 0.0007, + "step": 14520 + }, + { + "epoch": 0.83, + "learning_rate": 5.3671562082777036e-06, + "loss": 0.0241, + "step": 14530 + }, + { + "epoch": 0.83, + "learning_rate": 5.348950115305256e-06, + "loss": 0.0005, + "step": 14540 + }, + { + "epoch": 0.83, + "learning_rate": 5.330744022332807e-06, + "loss": 0.0003, + "step": 14550 + }, + { + "epoch": 0.83, + "learning_rate": 5.312537929360359e-06, + "loss": 0.0004, + "step": 14560 + }, + { + "epoch": 0.83, + "learning_rate": 5.294331836387912e-06, + "loss": 0.0297, + "step": 14570 + }, + { + "epoch": 0.83, + "learning_rate": 5.276125743415463e-06, + "loss": 0.0016, + "step": 14580 + }, + { + "epoch": 0.83, + "learning_rate": 5.257919650443015e-06, + "loss": 0.0005, + "step": 14590 + }, + { + "epoch": 0.84, + "learning_rate": 5.2397135574705666e-06, + "loss": 0.0003, + "step": 14600 + }, + { + "epoch": 0.84, + "learning_rate": 5.22150746449812e-06, + "loss": 0.0001, + "step": 14610 + }, + { + "epoch": 0.84, + "learning_rate": 5.203301371525671e-06, + "loss": 0.0003, + "step": 14620 + }, + { + "epoch": 0.84, + "learning_rate": 5.185095278553222e-06, + "loss": 0.0229, + "step": 14630 + }, + { + "epoch": 0.84, + "learning_rate": 5.1668891855807746e-06, + "loss": 0.0002, + "step": 14640 + }, + { + "epoch": 0.84, + "learning_rate": 5.148683092608327e-06, + "loss": 0.0003, + "step": 14650 + }, + { + "epoch": 0.84, + "learning_rate": 5.130476999635878e-06, + "loss": 0.0004, + "step": 14660 + }, + { + "epoch": 0.84, + "learning_rate": 5.11227090666343e-06, + "loss": 0.0533, + "step": 14670 + }, + { + "epoch": 0.84, + "learning_rate": 5.094064813690982e-06, + "loss": 0.0885, + "step": 14680 + }, + { + "epoch": 0.84, + "learning_rate": 5.075858720718534e-06, + "loss": 0.0379, + "step": 14690 + }, + { + "epoch": 0.84, + "learning_rate": 5.057652627746086e-06, + "loss": 0.0219, + "step": 14700 + }, + { + "epoch": 0.84, + "learning_rate": 5.0394465347736376e-06, + "loss": 0.0007, + "step": 14710 + }, + { + "epoch": 0.84, + "learning_rate": 5.021240441801189e-06, + "loss": 0.0011, + "step": 14720 + }, + { + "epoch": 0.84, + "learning_rate": 5.003034348828742e-06, + "loss": 0.001, + "step": 14730 + }, + { + "epoch": 0.84, + "learning_rate": 4.984828255856293e-06, + "loss": 0.0006, + "step": 14740 + }, + { + "epoch": 0.84, + "learning_rate": 4.966622162883845e-06, + "loss": 0.0018, + "step": 14750 + }, + { + "epoch": 0.84, + "learning_rate": 4.948416069911397e-06, + "loss": 0.0005, + "step": 14760 + }, + { + "epoch": 0.85, + "learning_rate": 4.930209976938949e-06, + "loss": 0.0005, + "step": 14770 + }, + { + "epoch": 0.85, + "learning_rate": 4.912003883966501e-06, + "loss": 0.0002, + "step": 14780 + }, + { + "epoch": 0.85, + "learning_rate": 4.893797790994053e-06, + "loss": 0.0008, + "step": 14790 + }, + { + "epoch": 0.85, + "learning_rate": 4.875591698021604e-06, + "loss": 0.0001, + "step": 14800 + }, + { + "epoch": 0.85, + "learning_rate": 4.857385605049157e-06, + "loss": 0.0003, + "step": 14810 + }, + { + "epoch": 0.85, + "learning_rate": 4.8391795120767086e-06, + "loss": 0.0004, + "step": 14820 + }, + { + "epoch": 0.85, + "learning_rate": 4.82097341910426e-06, + "loss": 0.0002, + "step": 14830 + }, + { + "epoch": 0.85, + "learning_rate": 4.802767326131812e-06, + "loss": 0.0001, + "step": 14840 + }, + { + "epoch": 0.85, + "learning_rate": 4.784561233159364e-06, + "loss": 0.0232, + "step": 14850 + }, + { + "epoch": 0.85, + "learning_rate": 4.766355140186916e-06, + "loss": 0.0427, + "step": 14860 + }, + { + "epoch": 0.85, + "learning_rate": 4.748149047214468e-06, + "loss": 0.0274, + "step": 14870 + }, + { + "epoch": 0.85, + "learning_rate": 4.729942954242019e-06, + "loss": 0.0226, + "step": 14880 + }, + { + "epoch": 0.85, + "learning_rate": 4.7117368612695715e-06, + "loss": 0.0006, + "step": 14890 + }, + { + "epoch": 0.85, + "learning_rate": 4.693530768297124e-06, + "loss": 0.0016, + "step": 14900 + }, + { + "epoch": 0.85, + "learning_rate": 4.675324675324675e-06, + "loss": 0.0403, + "step": 14910 + }, + { + "epoch": 0.85, + "learning_rate": 4.657118582352227e-06, + "loss": 0.025, + "step": 14920 + }, + { + "epoch": 0.85, + "learning_rate": 4.6389124893797796e-06, + "loss": 0.0007, + "step": 14930 + }, + { + "epoch": 0.85, + "learning_rate": 4.620706396407331e-06, + "loss": 0.0011, + "step": 14940 + }, + { + "epoch": 0.86, + "learning_rate": 4.602500303434883e-06, + "loss": 0.0625, + "step": 14950 + }, + { + "epoch": 0.86, + "learning_rate": 4.584294210462435e-06, + "loss": 0.0007, + "step": 14960 + }, + { + "epoch": 0.86, + "learning_rate": 4.566088117489987e-06, + "loss": 0.023, + "step": 14970 + }, + { + "epoch": 0.86, + "learning_rate": 4.547882024517539e-06, + "loss": 0.0004, + "step": 14980 + }, + { + "epoch": 0.86, + "learning_rate": 4.52967593154509e-06, + "loss": 0.0006, + "step": 14990 + }, + { + "epoch": 0.86, + "learning_rate": 4.5114698385726425e-06, + "loss": 0.0008, + "step": 15000 + }, + { + "epoch": 0.86, + "eval_loss": 0.009687372483313084, + "eval_runtime": 373.3001, + "eval_samples_per_second": 187.286, + "eval_steps_per_second": 11.706, + "step": 15000 + }, + { + "epoch": 0.86, + "learning_rate": 4.493263745600195e-06, + "loss": 0.0004, + "step": 15010 + }, + { + "epoch": 0.86, + "learning_rate": 4.475057652627746e-06, + "loss": 0.0256, + "step": 15020 + }, + { + "epoch": 0.86, + "learning_rate": 4.4568515596552975e-06, + "loss": 0.0004, + "step": 15030 + }, + { + "epoch": 0.86, + "learning_rate": 4.4386454666828506e-06, + "loss": 0.0006, + "step": 15040 + }, + { + "epoch": 0.86, + "learning_rate": 4.420439373710402e-06, + "loss": 0.0002, + "step": 15050 + }, + { + "epoch": 0.86, + "learning_rate": 4.402233280737953e-06, + "loss": 0.0006, + "step": 15060 + }, + { + "epoch": 0.86, + "learning_rate": 4.3840271877655055e-06, + "loss": 0.0002, + "step": 15070 + }, + { + "epoch": 0.86, + "learning_rate": 4.365821094793058e-06, + "loss": 0.0002, + "step": 15080 + }, + { + "epoch": 0.86, + "learning_rate": 4.347615001820609e-06, + "loss": 0.0005, + "step": 15090 + }, + { + "epoch": 0.86, + "learning_rate": 4.329408908848161e-06, + "loss": 0.0136, + "step": 15100 + }, + { + "epoch": 0.86, + "learning_rate": 4.311202815875713e-06, + "loss": 0.0002, + "step": 15110 + }, + { + "epoch": 0.87, + "learning_rate": 4.292996722903266e-06, + "loss": 0.0002, + "step": 15120 + }, + { + "epoch": 0.87, + "learning_rate": 4.274790629930817e-06, + "loss": 0.0003, + "step": 15130 + }, + { + "epoch": 0.87, + "learning_rate": 4.2565845369583685e-06, + "loss": 0.0623, + "step": 15140 + }, + { + "epoch": 0.87, + "learning_rate": 4.238378443985921e-06, + "loss": 0.0436, + "step": 15150 + }, + { + "epoch": 0.87, + "learning_rate": 4.220172351013473e-06, + "loss": 0.0002, + "step": 15160 + }, + { + "epoch": 0.87, + "learning_rate": 4.201966258041024e-06, + "loss": 0.0209, + "step": 15170 + }, + { + "epoch": 0.87, + "learning_rate": 4.1837601650685765e-06, + "loss": 0.0004, + "step": 15180 + }, + { + "epoch": 0.87, + "learning_rate": 4.165554072096128e-06, + "loss": 0.0002, + "step": 15190 + }, + { + "epoch": 0.87, + "learning_rate": 4.14734797912368e-06, + "loss": 0.0011, + "step": 15200 + }, + { + "epoch": 0.87, + "learning_rate": 4.129141886151232e-06, + "loss": 0.0367, + "step": 15210 + }, + { + "epoch": 0.87, + "learning_rate": 4.110935793178784e-06, + "loss": 0.0003, + "step": 15220 + }, + { + "epoch": 0.87, + "learning_rate": 4.092729700206335e-06, + "loss": 0.0004, + "step": 15230 + }, + { + "epoch": 0.87, + "learning_rate": 4.074523607233888e-06, + "loss": 0.0008, + "step": 15240 + }, + { + "epoch": 0.87, + "learning_rate": 4.0563175142614395e-06, + "loss": 0.0032, + "step": 15250 + }, + { + "epoch": 0.87, + "learning_rate": 4.038111421288991e-06, + "loss": 0.0006, + "step": 15260 + }, + { + "epoch": 0.87, + "learning_rate": 4.019905328316543e-06, + "loss": 0.0004, + "step": 15270 + }, + { + "epoch": 0.87, + "learning_rate": 4.001699235344095e-06, + "loss": 0.0001, + "step": 15280 + }, + { + "epoch": 0.87, + "learning_rate": 3.9834931423716475e-06, + "loss": 0.0188, + "step": 15290 + }, + { + "epoch": 0.88, + "learning_rate": 3.965287049399199e-06, + "loss": 0.0001, + "step": 15300 + }, + { + "epoch": 0.88, + "learning_rate": 3.947080956426751e-06, + "loss": 0.0002, + "step": 15310 + }, + { + "epoch": 0.88, + "learning_rate": 3.928874863454303e-06, + "loss": 0.0001, + "step": 15320 + }, + { + "epoch": 0.88, + "learning_rate": 3.910668770481855e-06, + "loss": 0.0001, + "step": 15330 + }, + { + "epoch": 0.88, + "learning_rate": 3.892462677509406e-06, + "loss": 0.0003, + "step": 15340 + }, + { + "epoch": 0.88, + "learning_rate": 3.874256584536959e-06, + "loss": 0.0006, + "step": 15350 + }, + { + "epoch": 0.88, + "learning_rate": 3.8560504915645105e-06, + "loss": 0.0001, + "step": 15360 + }, + { + "epoch": 0.88, + "learning_rate": 3.837844398592062e-06, + "loss": 0.0009, + "step": 15370 + }, + { + "epoch": 0.88, + "learning_rate": 3.819638305619614e-06, + "loss": 0.0001, + "step": 15380 + }, + { + "epoch": 0.88, + "learning_rate": 3.801432212647166e-06, + "loss": 0.0002, + "step": 15390 + }, + { + "epoch": 0.88, + "learning_rate": 3.7832261196747177e-06, + "loss": 0.0001, + "step": 15400 + }, + { + "epoch": 0.88, + "learning_rate": 3.76502002670227e-06, + "loss": 0.0024, + "step": 15410 + }, + { + "epoch": 0.88, + "learning_rate": 3.7468139337298217e-06, + "loss": 0.0002, + "step": 15420 + }, + { + "epoch": 0.88, + "learning_rate": 3.7286078407573735e-06, + "loss": 0.0306, + "step": 15430 + }, + { + "epoch": 0.88, + "learning_rate": 3.7104017477849257e-06, + "loss": 0.0002, + "step": 15440 + }, + { + "epoch": 0.88, + "learning_rate": 3.692195654812477e-06, + "loss": 0.0109, + "step": 15450 + }, + { + "epoch": 0.88, + "learning_rate": 3.6739895618400293e-06, + "loss": 0.0006, + "step": 15460 + }, + { + "epoch": 0.89, + "learning_rate": 3.655783468867581e-06, + "loss": 0.0004, + "step": 15470 + }, + { + "epoch": 0.89, + "learning_rate": 3.6375773758951333e-06, + "loss": 0.0001, + "step": 15480 + }, + { + "epoch": 0.89, + "learning_rate": 3.6193712829226847e-06, + "loss": 0.0002, + "step": 15490 + }, + { + "epoch": 0.89, + "learning_rate": 3.601165189950237e-06, + "loss": 0.0204, + "step": 15500 + }, + { + "epoch": 0.89, + "learning_rate": 3.5829590969777887e-06, + "loss": 0.0494, + "step": 15510 + }, + { + "epoch": 0.89, + "learning_rate": 3.5647530040053405e-06, + "loss": 0.0327, + "step": 15520 + }, + { + "epoch": 0.89, + "learning_rate": 3.5465469110328923e-06, + "loss": 0.0006, + "step": 15530 + }, + { + "epoch": 0.89, + "learning_rate": 3.5283408180604445e-06, + "loss": 0.0466, + "step": 15540 + }, + { + "epoch": 0.89, + "learning_rate": 3.510134725087996e-06, + "loss": 0.0003, + "step": 15550 + }, + { + "epoch": 0.89, + "learning_rate": 3.491928632115548e-06, + "loss": 0.0003, + "step": 15560 + }, + { + "epoch": 0.89, + "learning_rate": 3.4737225391431e-06, + "loss": 0.0001, + "step": 15570 + }, + { + "epoch": 0.89, + "learning_rate": 3.455516446170652e-06, + "loss": 0.0008, + "step": 15580 + }, + { + "epoch": 0.89, + "learning_rate": 3.4373103531982035e-06, + "loss": 0.0007, + "step": 15590 + }, + { + "epoch": 0.89, + "learning_rate": 3.4191042602257557e-06, + "loss": 0.0001, + "step": 15600 + }, + { + "epoch": 0.89, + "learning_rate": 3.4008981672533075e-06, + "loss": 0.0009, + "step": 15610 + }, + { + "epoch": 0.89, + "learning_rate": 3.3826920742808593e-06, + "loss": 0.0003, + "step": 15620 + }, + { + "epoch": 0.89, + "learning_rate": 3.364485981308411e-06, + "loss": 0.0002, + "step": 15630 + }, + { + "epoch": 0.89, + "learning_rate": 3.3462798883359633e-06, + "loss": 0.0004, + "step": 15640 + }, + { + "epoch": 0.9, + "learning_rate": 3.328073795363515e-06, + "loss": 0.0211, + "step": 15650 + }, + { + "epoch": 0.9, + "learning_rate": 3.309867702391067e-06, + "loss": 0.0006, + "step": 15660 + }, + { + "epoch": 0.9, + "learning_rate": 3.291661609418619e-06, + "loss": 0.0175, + "step": 15670 + }, + { + "epoch": 0.9, + "learning_rate": 3.273455516446171e-06, + "loss": 0.0006, + "step": 15680 + }, + { + "epoch": 0.9, + "learning_rate": 3.2552494234737227e-06, + "loss": 0.0002, + "step": 15690 + }, + { + "epoch": 0.9, + "learning_rate": 3.2370433305012745e-06, + "loss": 0.0136, + "step": 15700 + }, + { + "epoch": 0.9, + "learning_rate": 3.2188372375288267e-06, + "loss": 0.0002, + "step": 15710 + }, + { + "epoch": 0.9, + "learning_rate": 3.200631144556378e-06, + "loss": 0.0281, + "step": 15720 + }, + { + "epoch": 0.9, + "learning_rate": 3.1824250515839303e-06, + "loss": 0.0157, + "step": 15730 + }, + { + "epoch": 0.9, + "learning_rate": 3.164218958611482e-06, + "loss": 0.0001, + "step": 15740 + }, + { + "epoch": 0.9, + "learning_rate": 3.1460128656390343e-06, + "loss": 0.0382, + "step": 15750 + }, + { + "epoch": 0.9, + "learning_rate": 3.1278067726665856e-06, + "loss": 0.0001, + "step": 15760 + }, + { + "epoch": 0.9, + "learning_rate": 3.109600679694138e-06, + "loss": 0.0001, + "step": 15770 + }, + { + "epoch": 0.9, + "learning_rate": 3.0913945867216897e-06, + "loss": 0.0264, + "step": 15780 + }, + { + "epoch": 0.9, + "learning_rate": 3.0731884937492414e-06, + "loss": 0.0308, + "step": 15790 + }, + { + "epoch": 0.9, + "learning_rate": 3.0549824007767932e-06, + "loss": 0.0002, + "step": 15800 + }, + { + "epoch": 0.9, + "learning_rate": 3.0367763078043455e-06, + "loss": 0.0341, + "step": 15810 + }, + { + "epoch": 0.91, + "learning_rate": 3.0185702148318973e-06, + "loss": 0.0233, + "step": 15820 + }, + { + "epoch": 0.91, + "learning_rate": 3.000364121859449e-06, + "loss": 0.0003, + "step": 15830 + }, + { + "epoch": 0.91, + "learning_rate": 2.982158028887001e-06, + "loss": 0.0217, + "step": 15840 + }, + { + "epoch": 0.91, + "learning_rate": 2.963951935914553e-06, + "loss": 0.0002, + "step": 15850 + }, + { + "epoch": 0.91, + "learning_rate": 2.9457458429421044e-06, + "loss": 0.0492, + "step": 15860 + }, + { + "epoch": 0.91, + "learning_rate": 2.9275397499696566e-06, + "loss": 0.0002, + "step": 15870 + }, + { + "epoch": 0.91, + "learning_rate": 2.9093336569972084e-06, + "loss": 0.0003, + "step": 15880 + }, + { + "epoch": 0.91, + "learning_rate": 2.8911275640247602e-06, + "loss": 0.0352, + "step": 15890 + }, + { + "epoch": 0.91, + "learning_rate": 2.872921471052312e-06, + "loss": 0.0004, + "step": 15900 + }, + { + "epoch": 0.91, + "learning_rate": 2.8547153780798642e-06, + "loss": 0.0007, + "step": 15910 + }, + { + "epoch": 0.91, + "learning_rate": 2.836509285107416e-06, + "loss": 0.0002, + "step": 15920 + }, + { + "epoch": 0.91, + "learning_rate": 2.818303192134968e-06, + "loss": 0.0329, + "step": 15930 + }, + { + "epoch": 0.91, + "learning_rate": 2.8000970991625196e-06, + "loss": 0.0004, + "step": 15940 + }, + { + "epoch": 0.91, + "learning_rate": 2.781891006190072e-06, + "loss": 0.0001, + "step": 15950 + }, + { + "epoch": 0.91, + "learning_rate": 2.7636849132176232e-06, + "loss": 0.0357, + "step": 15960 + }, + { + "epoch": 0.91, + "learning_rate": 2.7454788202451754e-06, + "loss": 0.0341, + "step": 15970 + }, + { + "epoch": 0.91, + "learning_rate": 2.7272727272727272e-06, + "loss": 0.0004, + "step": 15980 + }, + { + "epoch": 0.91, + "learning_rate": 2.7090666343002794e-06, + "loss": 0.0004, + "step": 15990 + }, + { + "epoch": 0.92, + "learning_rate": 2.690860541327831e-06, + "loss": 0.0128, + "step": 16000 + }, + { + "epoch": 0.92, + "eval_loss": 0.009275409393012524, + "eval_runtime": 373.3357, + "eval_samples_per_second": 187.268, + "eval_steps_per_second": 11.705, + "step": 16000 + }, + { + "epoch": 0.92, + "learning_rate": 2.672654448355383e-06, + "loss": 0.0002, + "step": 16010 + }, + { + "epoch": 0.92, + "learning_rate": 2.6544483553829352e-06, + "loss": 0.0005, + "step": 16020 + }, + { + "epoch": 0.92, + "learning_rate": 2.6362422624104866e-06, + "loss": 0.0019, + "step": 16030 + }, + { + "epoch": 0.92, + "learning_rate": 2.618036169438039e-06, + "loss": 0.0031, + "step": 16040 + }, + { + "epoch": 0.92, + "learning_rate": 2.5998300764655906e-06, + "loss": 0.0385, + "step": 16050 + }, + { + "epoch": 0.92, + "learning_rate": 2.5816239834931424e-06, + "loss": 0.0123, + "step": 16060 + }, + { + "epoch": 0.92, + "learning_rate": 2.5634178905206942e-06, + "loss": 0.0005, + "step": 16070 + }, + { + "epoch": 0.92, + "learning_rate": 2.5452117975482464e-06, + "loss": 0.0186, + "step": 16080 + }, + { + "epoch": 0.92, + "learning_rate": 2.5270057045757982e-06, + "loss": 0.0011, + "step": 16090 + }, + { + "epoch": 0.92, + "learning_rate": 2.50879961160335e-06, + "loss": 0.0002, + "step": 16100 + }, + { + "epoch": 0.92, + "learning_rate": 2.490593518630902e-06, + "loss": 0.0544, + "step": 16110 + }, + { + "epoch": 0.92, + "learning_rate": 2.472387425658454e-06, + "loss": 0.0001, + "step": 16120 + }, + { + "epoch": 0.92, + "learning_rate": 2.4541813326860054e-06, + "loss": 0.0169, + "step": 16130 + }, + { + "epoch": 0.92, + "learning_rate": 2.4359752397135576e-06, + "loss": 0.0211, + "step": 16140 + }, + { + "epoch": 0.92, + "learning_rate": 2.4177691467411094e-06, + "loss": 0.0002, + "step": 16150 + }, + { + "epoch": 0.92, + "learning_rate": 2.3995630537686616e-06, + "loss": 0.0002, + "step": 16160 + }, + { + "epoch": 0.93, + "learning_rate": 2.381356960796213e-06, + "loss": 0.0004, + "step": 16170 + }, + { + "epoch": 0.93, + "learning_rate": 2.3631508678237652e-06, + "loss": 0.0008, + "step": 16180 + }, + { + "epoch": 0.93, + "learning_rate": 2.344944774851317e-06, + "loss": 0.0493, + "step": 16190 + }, + { + "epoch": 0.93, + "learning_rate": 2.326738681878869e-06, + "loss": 0.0003, + "step": 16200 + }, + { + "epoch": 0.93, + "learning_rate": 2.3085325889064206e-06, + "loss": 0.0003, + "step": 16210 + }, + { + "epoch": 0.93, + "learning_rate": 2.290326495933973e-06, + "loss": 0.0006, + "step": 16220 + }, + { + "epoch": 0.93, + "learning_rate": 2.272120402961524e-06, + "loss": 0.0004, + "step": 16230 + }, + { + "epoch": 0.93, + "learning_rate": 2.2539143099890764e-06, + "loss": 0.0003, + "step": 16240 + }, + { + "epoch": 0.93, + "learning_rate": 2.235708217016628e-06, + "loss": 0.0418, + "step": 16250 + }, + { + "epoch": 0.93, + "learning_rate": 2.2175021240441804e-06, + "loss": 0.0006, + "step": 16260 + }, + { + "epoch": 0.93, + "learning_rate": 2.1992960310717318e-06, + "loss": 0.0014, + "step": 16270 + }, + { + "epoch": 0.93, + "learning_rate": 2.181089938099284e-06, + "loss": 0.0006, + "step": 16280 + }, + { + "epoch": 0.93, + "learning_rate": 2.162883845126836e-06, + "loss": 0.0136, + "step": 16290 + }, + { + "epoch": 0.93, + "learning_rate": 2.1446777521543876e-06, + "loss": 0.0002, + "step": 16300 + }, + { + "epoch": 0.93, + "learning_rate": 2.1264716591819394e-06, + "loss": 0.0004, + "step": 16310 + }, + { + "epoch": 0.93, + "learning_rate": 2.1082655662094916e-06, + "loss": 0.0062, + "step": 16320 + }, + { + "epoch": 0.93, + "learning_rate": 2.0900594732370434e-06, + "loss": 0.0002, + "step": 16330 + }, + { + "epoch": 0.93, + "learning_rate": 2.071853380264595e-06, + "loss": 0.0002, + "step": 16340 + }, + { + "epoch": 0.94, + "learning_rate": 2.053647287292147e-06, + "loss": 0.0002, + "step": 16350 + }, + { + "epoch": 0.94, + "learning_rate": 2.035441194319699e-06, + "loss": 0.023, + "step": 16360 + }, + { + "epoch": 0.94, + "learning_rate": 2.0172351013472506e-06, + "loss": 0.0002, + "step": 16370 + }, + { + "epoch": 0.94, + "learning_rate": 1.999029008374803e-06, + "loss": 0.0031, + "step": 16380 + }, + { + "epoch": 0.94, + "learning_rate": 1.980822915402355e-06, + "loss": 0.0002, + "step": 16390 + }, + { + "epoch": 0.94, + "learning_rate": 1.9626168224299064e-06, + "loss": 0.0393, + "step": 16400 + }, + { + "epoch": 0.94, + "learning_rate": 1.9444107294574586e-06, + "loss": 0.0144, + "step": 16410 + }, + { + "epoch": 0.94, + "learning_rate": 1.9262046364850104e-06, + "loss": 0.0133, + "step": 16420 + }, + { + "epoch": 0.94, + "learning_rate": 1.9079985435125626e-06, + "loss": 0.0003, + "step": 16430 + }, + { + "epoch": 0.94, + "learning_rate": 1.889792450540114e-06, + "loss": 0.0002, + "step": 16440 + }, + { + "epoch": 0.94, + "learning_rate": 1.871586357567666e-06, + "loss": 0.0003, + "step": 16450 + }, + { + "epoch": 0.94, + "learning_rate": 1.8533802645952178e-06, + "loss": 0.0008, + "step": 16460 + }, + { + "epoch": 0.94, + "learning_rate": 1.8351741716227698e-06, + "loss": 0.0259, + "step": 16470 + }, + { + "epoch": 0.94, + "learning_rate": 1.8169680786503216e-06, + "loss": 0.0221, + "step": 16480 + }, + { + "epoch": 0.94, + "learning_rate": 1.7987619856778736e-06, + "loss": 0.0003, + "step": 16490 + }, + { + "epoch": 0.94, + "learning_rate": 1.7805558927054254e-06, + "loss": 0.0141, + "step": 16500 + }, + { + "epoch": 0.94, + "learning_rate": 1.7623497997329772e-06, + "loss": 0.0003, + "step": 16510 + }, + { + "epoch": 0.95, + "learning_rate": 1.7441437067605292e-06, + "loss": 0.0005, + "step": 16520 + }, + { + "epoch": 0.95, + "learning_rate": 1.725937613788081e-06, + "loss": 0.0008, + "step": 16530 + }, + { + "epoch": 0.95, + "learning_rate": 1.707731520815633e-06, + "loss": 0.0001, + "step": 16540 + }, + { + "epoch": 0.95, + "learning_rate": 1.6895254278431848e-06, + "loss": 0.031, + "step": 16550 + }, + { + "epoch": 0.95, + "learning_rate": 1.6713193348707368e-06, + "loss": 0.0005, + "step": 16560 + }, + { + "epoch": 0.95, + "learning_rate": 1.6531132418982888e-06, + "loss": 0.0003, + "step": 16570 + }, + { + "epoch": 0.95, + "learning_rate": 1.6349071489258406e-06, + "loss": 0.0004, + "step": 16580 + }, + { + "epoch": 0.95, + "learning_rate": 1.6167010559533926e-06, + "loss": 0.0177, + "step": 16590 + }, + { + "epoch": 0.95, + "learning_rate": 1.5984949629809444e-06, + "loss": 0.0161, + "step": 16600 + }, + { + "epoch": 0.95, + "learning_rate": 1.5802888700084964e-06, + "loss": 0.0, + "step": 16610 + }, + { + "epoch": 0.95, + "learning_rate": 1.5620827770360482e-06, + "loss": 0.0277, + "step": 16620 + }, + { + "epoch": 0.95, + "learning_rate": 1.5438766840636e-06, + "loss": 0.0007, + "step": 16630 + }, + { + "epoch": 0.95, + "learning_rate": 1.525670591091152e-06, + "loss": 0.0161, + "step": 16640 + }, + { + "epoch": 0.95, + "learning_rate": 1.5074644981187038e-06, + "loss": 0.0214, + "step": 16650 + }, + { + "epoch": 0.95, + "learning_rate": 1.4892584051462558e-06, + "loss": 0.0002, + "step": 16660 + }, + { + "epoch": 0.95, + "learning_rate": 1.4710523121738076e-06, + "loss": 0.0144, + "step": 16670 + }, + { + "epoch": 0.95, + "learning_rate": 1.4528462192013594e-06, + "loss": 0.0142, + "step": 16680 + }, + { + "epoch": 0.95, + "learning_rate": 1.4346401262289114e-06, + "loss": 0.0003, + "step": 16690 + }, + { + "epoch": 0.96, + "learning_rate": 1.4164340332564632e-06, + "loss": 0.024, + "step": 16700 + }, + { + "epoch": 0.96, + "learning_rate": 1.3982279402840152e-06, + "loss": 0.0001, + "step": 16710 + }, + { + "epoch": 0.96, + "learning_rate": 1.380021847311567e-06, + "loss": 0.0003, + "step": 16720 + }, + { + "epoch": 0.96, + "learning_rate": 1.361815754339119e-06, + "loss": 0.0001, + "step": 16730 + }, + { + "epoch": 0.96, + "learning_rate": 1.3436096613666708e-06, + "loss": 0.0005, + "step": 16740 + }, + { + "epoch": 0.96, + "learning_rate": 1.3254035683942225e-06, + "loss": 0.0002, + "step": 16750 + }, + { + "epoch": 0.96, + "learning_rate": 1.3071974754217746e-06, + "loss": 0.0001, + "step": 16760 + }, + { + "epoch": 0.96, + "learning_rate": 1.2889913824493263e-06, + "loss": 0.0002, + "step": 16770 + }, + { + "epoch": 0.96, + "learning_rate": 1.2707852894768784e-06, + "loss": 0.0161, + "step": 16780 + }, + { + "epoch": 0.96, + "learning_rate": 1.2525791965044301e-06, + "loss": 0.0001, + "step": 16790 + }, + { + "epoch": 0.96, + "learning_rate": 1.234373103531982e-06, + "loss": 0.0004, + "step": 16800 + }, + { + "epoch": 0.96, + "learning_rate": 1.216167010559534e-06, + "loss": 0.0002, + "step": 16810 + }, + { + "epoch": 0.96, + "learning_rate": 1.1979609175870857e-06, + "loss": 0.0221, + "step": 16820 + }, + { + "epoch": 0.96, + "learning_rate": 1.1797548246146377e-06, + "loss": 0.0008, + "step": 16830 + }, + { + "epoch": 0.96, + "learning_rate": 1.1615487316421895e-06, + "loss": 0.0001, + "step": 16840 + }, + { + "epoch": 0.96, + "learning_rate": 1.1433426386697415e-06, + "loss": 0.0004, + "step": 16850 + }, + { + "epoch": 0.96, + "learning_rate": 1.1251365456972933e-06, + "loss": 0.0297, + "step": 16860 + }, + { + "epoch": 0.97, + "learning_rate": 1.1069304527248451e-06, + "loss": 0.001, + "step": 16870 + }, + { + "epoch": 0.97, + "learning_rate": 1.0887243597523971e-06, + "loss": 0.0498, + "step": 16880 + }, + { + "epoch": 0.97, + "learning_rate": 1.070518266779949e-06, + "loss": 0.0186, + "step": 16890 + }, + { + "epoch": 0.97, + "learning_rate": 1.052312173807501e-06, + "loss": 0.0004, + "step": 16900 + }, + { + "epoch": 0.97, + "learning_rate": 1.0341060808350527e-06, + "loss": 0.0002, + "step": 16910 + }, + { + "epoch": 0.97, + "learning_rate": 1.0158999878626045e-06, + "loss": 0.0001, + "step": 16920 + }, + { + "epoch": 0.97, + "learning_rate": 9.976938948901567e-07, + "loss": 0.0134, + "step": 16930 + }, + { + "epoch": 0.97, + "learning_rate": 9.794878019177085e-07, + "loss": 0.0001, + "step": 16940 + }, + { + "epoch": 0.97, + "learning_rate": 9.612817089452605e-07, + "loss": 0.0013, + "step": 16950 + }, + { + "epoch": 0.97, + "learning_rate": 9.430756159728122e-07, + "loss": 0.0004, + "step": 16960 + }, + { + "epoch": 0.97, + "learning_rate": 9.248695230003641e-07, + "loss": 0.0164, + "step": 16970 + }, + { + "epoch": 0.97, + "learning_rate": 9.06663430027916e-07, + "loss": 0.0346, + "step": 16980 + }, + { + "epoch": 0.97, + "learning_rate": 8.884573370554679e-07, + "loss": 0.0012, + "step": 16990 + }, + { + "epoch": 0.97, + "learning_rate": 8.702512440830197e-07, + "loss": 0.0003, + "step": 17000 + }, + { + "epoch": 0.97, + "eval_loss": 0.009779643267393112, + "eval_runtime": 372.8001, + "eval_samples_per_second": 187.537, + "eval_steps_per_second": 11.722, + "step": 17000 + } + ], + "logging_steps": 10, + "max_steps": 17479, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 1000, + "total_flos": 1.8226686133824e+16, + "train_batch_size": 16, + "trial_name": null, + "trial_params": null +}