{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.20346742401763385, "eval_steps": 500, "global_step": 3600, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0005651872889378718, "grad_norm": 388.92431640625, "learning_rate": 4.0000000000000003e-07, "loss": 7.4628, "step": 10 }, { "epoch": 0.0011303745778757435, "grad_norm": 418.426025390625, "learning_rate": 1.0666666666666667e-06, "loss": 7.4553, "step": 20 }, { "epoch": 0.0016955618668136154, "grad_norm": 329.3276672363281, "learning_rate": 1.7333333333333334e-06, "loss": 7.478, "step": 30 }, { "epoch": 0.002260749155751487, "grad_norm": 294.26776123046875, "learning_rate": 2.4000000000000003e-06, "loss": 7.4234, "step": 40 }, { "epoch": 0.002825936444689359, "grad_norm": 233.39239501953125, "learning_rate": 3.066666666666667e-06, "loss": 7.4139, "step": 50 }, { "epoch": 0.003391123733627231, "grad_norm": 165.7160186767578, "learning_rate": 3.7333333333333337e-06, "loss": 7.4218, "step": 60 }, { "epoch": 0.003956311022565102, "grad_norm": 85.9063949584961, "learning_rate": 4.4e-06, "loss": 7.4302, "step": 70 }, { "epoch": 0.004521498311502974, "grad_norm": 49.569210052490234, "learning_rate": 5.066666666666667e-06, "loss": 7.4101, "step": 80 }, { "epoch": 0.005086685600440846, "grad_norm": 32.944725036621094, "learning_rate": 5.733333333333333e-06, "loss": 7.3716, "step": 90 }, { "epoch": 0.005651872889378718, "grad_norm": 20.296159744262695, "learning_rate": 6.4000000000000006e-06, "loss": 7.3607, "step": 100 }, { "epoch": 0.00621706017831659, "grad_norm": 11.820279121398926, "learning_rate": 7.066666666666667e-06, "loss": 7.3988, "step": 110 }, { "epoch": 0.006782247467254462, "grad_norm": 11.601971626281738, "learning_rate": 7.733333333333334e-06, "loss": 7.4044, "step": 120 }, { "epoch": 0.0073474347561923335, "grad_norm": 6.7178144454956055, "learning_rate": 8.400000000000001e-06, "loss": 7.3488, "step": 130 }, { "epoch": 0.007912622045130204, "grad_norm": 6.530295372009277, "learning_rate": 9.066666666666667e-06, "loss": 7.3774, "step": 140 }, { "epoch": 0.008477809334068076, "grad_norm": 8.032118797302246, "learning_rate": 9.733333333333334e-06, "loss": 7.3965, "step": 150 }, { "epoch": 0.009042996623005948, "grad_norm": 8.5325927734375, "learning_rate": 1.04e-05, "loss": 7.3754, "step": 160 }, { "epoch": 0.00960818391194382, "grad_norm": 11.115029335021973, "learning_rate": 1.1066666666666667e-05, "loss": 7.3537, "step": 170 }, { "epoch": 0.010173371200881692, "grad_norm": 5.508138656616211, "learning_rate": 1.1733333333333333e-05, "loss": 7.3833, "step": 180 }, { "epoch": 0.010738558489819564, "grad_norm": 6.041222095489502, "learning_rate": 1.24e-05, "loss": 7.3501, "step": 190 }, { "epoch": 0.011303745778757436, "grad_norm": 6.466294765472412, "learning_rate": 1.3066666666666666e-05, "loss": 7.3538, "step": 200 }, { "epoch": 0.011868933067695308, "grad_norm": 6.852397918701172, "learning_rate": 1.3733333333333335e-05, "loss": 7.3481, "step": 210 }, { "epoch": 0.01243412035663318, "grad_norm": 7.736501693725586, "learning_rate": 1.44e-05, "loss": 7.3431, "step": 220 }, { "epoch": 0.012999307645571051, "grad_norm": 8.353436470031738, "learning_rate": 1.5066666666666668e-05, "loss": 7.3286, "step": 230 }, { "epoch": 0.013564494934508923, "grad_norm": 4.6984333992004395, "learning_rate": 1.5733333333333334e-05, "loss": 7.3275, "step": 240 }, { "epoch": 0.014129682223446795, "grad_norm": 4.275951385498047, "learning_rate": 1.6400000000000002e-05, "loss": 7.3282, "step": 250 }, { "epoch": 0.014694869512384667, "grad_norm": 6.811357498168945, "learning_rate": 1.7066666666666667e-05, "loss": 7.3249, "step": 260 }, { "epoch": 0.015260056801322539, "grad_norm": 8.525443077087402, "learning_rate": 1.7733333333333335e-05, "loss": 7.3264, "step": 270 }, { "epoch": 0.01582524409026041, "grad_norm": 14.670880317687988, "learning_rate": 1.84e-05, "loss": 7.3251, "step": 280 }, { "epoch": 0.01639043137919828, "grad_norm": 16.190635681152344, "learning_rate": 1.9066666666666668e-05, "loss": 7.3187, "step": 290 }, { "epoch": 0.016955618668136153, "grad_norm": 4.505331039428711, "learning_rate": 1.9733333333333333e-05, "loss": 7.3208, "step": 300 }, { "epoch": 0.017520805957074025, "grad_norm": 6.737983226776123, "learning_rate": 2.04e-05, "loss": 7.3014, "step": 310 }, { "epoch": 0.018085993246011896, "grad_norm": 7.480038642883301, "learning_rate": 2.106666666666667e-05, "loss": 7.3089, "step": 320 }, { "epoch": 0.01865118053494977, "grad_norm": 5.7037200927734375, "learning_rate": 2.1733333333333334e-05, "loss": 7.3068, "step": 330 }, { "epoch": 0.01921636782388764, "grad_norm": 6.547840595245361, "learning_rate": 2.2400000000000002e-05, "loss": 7.3128, "step": 340 }, { "epoch": 0.019781555112825512, "grad_norm": 10.3425874710083, "learning_rate": 2.3066666666666667e-05, "loss": 7.3043, "step": 350 }, { "epoch": 0.020346742401763384, "grad_norm": 9.089709281921387, "learning_rate": 2.3733333333333335e-05, "loss": 7.3327, "step": 360 }, { "epoch": 0.020911929690701256, "grad_norm": 5.359627723693848, "learning_rate": 2.44e-05, "loss": 7.3, "step": 370 }, { "epoch": 0.021477116979639128, "grad_norm": 10.904877662658691, "learning_rate": 2.5066666666666665e-05, "loss": 7.316, "step": 380 }, { "epoch": 0.022042304268577, "grad_norm": 14.221054077148438, "learning_rate": 2.5733333333333337e-05, "loss": 7.3174, "step": 390 }, { "epoch": 0.02260749155751487, "grad_norm": 7.274070739746094, "learning_rate": 2.64e-05, "loss": 7.2912, "step": 400 }, { "epoch": 0.023172678846452743, "grad_norm": 5.9511799812316895, "learning_rate": 2.706666666666667e-05, "loss": 7.2899, "step": 410 }, { "epoch": 0.023737866135390615, "grad_norm": 6.152066707611084, "learning_rate": 2.7733333333333334e-05, "loss": 7.3028, "step": 420 }, { "epoch": 0.024303053424328487, "grad_norm": 6.566978931427002, "learning_rate": 2.84e-05, "loss": 7.2696, "step": 430 }, { "epoch": 0.02486824071326636, "grad_norm": 9.3006010055542, "learning_rate": 2.906666666666667e-05, "loss": 7.2893, "step": 440 }, { "epoch": 0.02543342800220423, "grad_norm": 9.530643463134766, "learning_rate": 2.9733333333333336e-05, "loss": 7.2777, "step": 450 }, { "epoch": 0.025998615291142103, "grad_norm": 9.63436508178711, "learning_rate": 3.04e-05, "loss": 7.2978, "step": 460 }, { "epoch": 0.026563802580079975, "grad_norm": 9.731348991394043, "learning_rate": 3.1066666666666665e-05, "loss": 7.2755, "step": 470 }, { "epoch": 0.027128989869017846, "grad_norm": 30.556720733642578, "learning_rate": 3.173333333333334e-05, "loss": 7.2621, "step": 480 }, { "epoch": 0.02769417715795572, "grad_norm": 8.977019309997559, "learning_rate": 3.24e-05, "loss": 7.2778, "step": 490 }, { "epoch": 0.02825936444689359, "grad_norm": 7.0203657150268555, "learning_rate": 3.3066666666666666e-05, "loss": 7.2618, "step": 500 }, { "epoch": 0.028824551735831462, "grad_norm": 11.852314949035645, "learning_rate": 3.373333333333333e-05, "loss": 7.2642, "step": 510 }, { "epoch": 0.029389739024769334, "grad_norm": 14.17752742767334, "learning_rate": 3.4399999999999996e-05, "loss": 7.2596, "step": 520 }, { "epoch": 0.029954926313707206, "grad_norm": 11.621777534484863, "learning_rate": 3.506666666666667e-05, "loss": 7.2946, "step": 530 }, { "epoch": 0.030520113602645078, "grad_norm": 7.2268242835998535, "learning_rate": 3.573333333333333e-05, "loss": 7.2602, "step": 540 }, { "epoch": 0.03108530089158295, "grad_norm": 10.392822265625, "learning_rate": 3.6400000000000004e-05, "loss": 7.2526, "step": 550 }, { "epoch": 0.03165048818052082, "grad_norm": 18.579120635986328, "learning_rate": 3.706666666666667e-05, "loss": 7.2719, "step": 560 }, { "epoch": 0.03221567546945869, "grad_norm": 6.2978973388671875, "learning_rate": 3.773333333333334e-05, "loss": 7.2588, "step": 570 }, { "epoch": 0.03278086275839656, "grad_norm": 11.561802864074707, "learning_rate": 3.8400000000000005e-05, "loss": 7.2588, "step": 580 }, { "epoch": 0.03334605004733444, "grad_norm": 5.9244866371154785, "learning_rate": 3.906666666666667e-05, "loss": 7.2471, "step": 590 }, { "epoch": 0.033911237336272305, "grad_norm": 9.905623435974121, "learning_rate": 3.9733333333333335e-05, "loss": 7.242, "step": 600 }, { "epoch": 0.03447642462521018, "grad_norm": 6.15846586227417, "learning_rate": 4.0400000000000006e-05, "loss": 7.2515, "step": 610 }, { "epoch": 0.03504161191414805, "grad_norm": 6.017207622528076, "learning_rate": 4.106666666666667e-05, "loss": 7.232, "step": 620 }, { "epoch": 0.035606799203085925, "grad_norm": 10.852577209472656, "learning_rate": 4.1733333333333336e-05, "loss": 7.2463, "step": 630 }, { "epoch": 0.03617198649202379, "grad_norm": 11.278721809387207, "learning_rate": 4.24e-05, "loss": 7.2405, "step": 640 }, { "epoch": 0.03673717378096167, "grad_norm": 10.21061897277832, "learning_rate": 4.3066666666666665e-05, "loss": 7.2327, "step": 650 }, { "epoch": 0.03730236106989954, "grad_norm": 9.478323936462402, "learning_rate": 4.373333333333334e-05, "loss": 7.2375, "step": 660 }, { "epoch": 0.03786754835883741, "grad_norm": 6.584554672241211, "learning_rate": 4.44e-05, "loss": 7.2226, "step": 670 }, { "epoch": 0.03843273564777528, "grad_norm": 6.267460823059082, "learning_rate": 4.5066666666666667e-05, "loss": 7.2279, "step": 680 }, { "epoch": 0.038997922936713156, "grad_norm": 7.223781108856201, "learning_rate": 4.573333333333333e-05, "loss": 7.2345, "step": 690 }, { "epoch": 0.039563110225651024, "grad_norm": 9.295626640319824, "learning_rate": 4.64e-05, "loss": 7.252, "step": 700 }, { "epoch": 0.0401282975145889, "grad_norm": 6.802502155303955, "learning_rate": 4.706666666666667e-05, "loss": 7.2322, "step": 710 }, { "epoch": 0.04069348480352677, "grad_norm": 7.009547710418701, "learning_rate": 4.773333333333333e-05, "loss": 7.2359, "step": 720 }, { "epoch": 0.04125867209246464, "grad_norm": 8.277494430541992, "learning_rate": 4.8400000000000004e-05, "loss": 7.2127, "step": 730 }, { "epoch": 0.04182385938140251, "grad_norm": 8.701301574707031, "learning_rate": 4.906666666666667e-05, "loss": 7.2076, "step": 740 }, { "epoch": 0.04238904667034039, "grad_norm": 8.432950973510742, "learning_rate": 4.973333333333334e-05, "loss": 7.2131, "step": 750 }, { "epoch": 0.042954233959278255, "grad_norm": 5.229855060577393, "learning_rate": 5.0400000000000005e-05, "loss": 7.2284, "step": 760 }, { "epoch": 0.04351942124821613, "grad_norm": 6.175259113311768, "learning_rate": 5.106666666666668e-05, "loss": 7.204, "step": 770 }, { "epoch": 0.044084608537154, "grad_norm": 4.937206268310547, "learning_rate": 5.1733333333333335e-05, "loss": 7.1995, "step": 780 }, { "epoch": 0.044649795826091875, "grad_norm": 6.159058094024658, "learning_rate": 5.2400000000000007e-05, "loss": 7.2131, "step": 790 }, { "epoch": 0.04521498311502974, "grad_norm": 8.138545036315918, "learning_rate": 5.3066666666666665e-05, "loss": 7.1933, "step": 800 }, { "epoch": 0.04578017040396761, "grad_norm": 7.782288074493408, "learning_rate": 5.3733333333333336e-05, "loss": 7.204, "step": 810 }, { "epoch": 0.04634535769290549, "grad_norm": 5.030788421630859, "learning_rate": 5.440000000000001e-05, "loss": 7.211, "step": 820 }, { "epoch": 0.046910544981843355, "grad_norm": 5.012758731842041, "learning_rate": 5.5066666666666666e-05, "loss": 7.2194, "step": 830 }, { "epoch": 0.04747573227078123, "grad_norm": 8.302517890930176, "learning_rate": 5.573333333333334e-05, "loss": 7.2009, "step": 840 }, { "epoch": 0.0480409195597191, "grad_norm": 7.122504711151123, "learning_rate": 5.6399999999999995e-05, "loss": 7.206, "step": 850 }, { "epoch": 0.048606106848656974, "grad_norm": 7.099667549133301, "learning_rate": 5.706666666666667e-05, "loss": 7.2067, "step": 860 }, { "epoch": 0.04917129413759484, "grad_norm": 7.823317527770996, "learning_rate": 5.773333333333334e-05, "loss": 7.1947, "step": 870 }, { "epoch": 0.04973648142653272, "grad_norm": 6.886421203613281, "learning_rate": 5.8399999999999997e-05, "loss": 7.197, "step": 880 }, { "epoch": 0.050301668715470586, "grad_norm": 5.232386589050293, "learning_rate": 5.906666666666667e-05, "loss": 7.198, "step": 890 }, { "epoch": 0.05086685600440846, "grad_norm": 9.155698776245117, "learning_rate": 5.973333333333334e-05, "loss": 7.2049, "step": 900 }, { "epoch": 0.05143204329334633, "grad_norm": 7.519978046417236, "learning_rate": 6.04e-05, "loss": 7.1854, "step": 910 }, { "epoch": 0.051997230582284205, "grad_norm": 6.731189250946045, "learning_rate": 6.106666666666667e-05, "loss": 7.1759, "step": 920 }, { "epoch": 0.052562417871222074, "grad_norm": 6.922330856323242, "learning_rate": 6.173333333333333e-05, "loss": 7.1616, "step": 930 }, { "epoch": 0.05312760516015995, "grad_norm": 10.618990898132324, "learning_rate": 6.24e-05, "loss": 7.1744, "step": 940 }, { "epoch": 0.05369279244909782, "grad_norm": 4.870369911193848, "learning_rate": 6.306666666666668e-05, "loss": 7.1829, "step": 950 }, { "epoch": 0.05425797973803569, "grad_norm": 5.137252330780029, "learning_rate": 6.373333333333333e-05, "loss": 7.1839, "step": 960 }, { "epoch": 0.05482316702697356, "grad_norm": 6.411045074462891, "learning_rate": 6.440000000000001e-05, "loss": 7.1685, "step": 970 }, { "epoch": 0.05538835431591144, "grad_norm": 4.805776119232178, "learning_rate": 6.506666666666666e-05, "loss": 7.1714, "step": 980 }, { "epoch": 0.055953541604849305, "grad_norm": 9.826089859008789, "learning_rate": 6.573333333333334e-05, "loss": 7.1625, "step": 990 }, { "epoch": 0.05651872889378718, "grad_norm": 7.1525044441223145, "learning_rate": 6.64e-05, "loss": 7.1745, "step": 1000 }, { "epoch": 0.05708391618272505, "grad_norm": 4.528572082519531, "learning_rate": 6.706666666666667e-05, "loss": 7.1723, "step": 1010 }, { "epoch": 0.057649103471662924, "grad_norm": 5.2590107917785645, "learning_rate": 6.773333333333333e-05, "loss": 7.1736, "step": 1020 }, { "epoch": 0.05821429076060079, "grad_norm": 9.157952308654785, "learning_rate": 6.840000000000001e-05, "loss": 7.1693, "step": 1030 }, { "epoch": 0.05877947804953867, "grad_norm": 6.091181755065918, "learning_rate": 6.906666666666667e-05, "loss": 7.1629, "step": 1040 }, { "epoch": 0.059344665338476536, "grad_norm": 6.99681282043457, "learning_rate": 6.973333333333334e-05, "loss": 7.1352, "step": 1050 }, { "epoch": 0.05990985262741441, "grad_norm": 5.714032173156738, "learning_rate": 7.04e-05, "loss": 7.1567, "step": 1060 }, { "epoch": 0.06047503991635228, "grad_norm": 5.471667766571045, "learning_rate": 7.106666666666667e-05, "loss": 7.1503, "step": 1070 }, { "epoch": 0.061040227205290155, "grad_norm": 6.660628795623779, "learning_rate": 7.173333333333335e-05, "loss": 7.1663, "step": 1080 }, { "epoch": 0.061605414494228024, "grad_norm": 4.059611797332764, "learning_rate": 7.24e-05, "loss": 7.1389, "step": 1090 }, { "epoch": 0.0621706017831659, "grad_norm": 6.8347859382629395, "learning_rate": 7.306666666666668e-05, "loss": 7.1705, "step": 1100 }, { "epoch": 0.06273578907210377, "grad_norm": 5.438681602478027, "learning_rate": 7.373333333333333e-05, "loss": 7.1423, "step": 1110 }, { "epoch": 0.06330097636104164, "grad_norm": 7.186290740966797, "learning_rate": 7.44e-05, "loss": 7.1394, "step": 1120 }, { "epoch": 0.06386616364997952, "grad_norm": 5.357133865356445, "learning_rate": 7.506666666666667e-05, "loss": 7.132, "step": 1130 }, { "epoch": 0.06443135093891739, "grad_norm": 5.482779026031494, "learning_rate": 7.573333333333334e-05, "loss": 7.1614, "step": 1140 }, { "epoch": 0.06499653822785526, "grad_norm": 8.654241561889648, "learning_rate": 7.64e-05, "loss": 7.1276, "step": 1150 }, { "epoch": 0.06556172551679312, "grad_norm": 6.142782688140869, "learning_rate": 7.706666666666668e-05, "loss": 7.1203, "step": 1160 }, { "epoch": 0.066126912805731, "grad_norm": 5.202004432678223, "learning_rate": 7.773333333333333e-05, "loss": 7.1138, "step": 1170 }, { "epoch": 0.06669210009466887, "grad_norm": 4.9742302894592285, "learning_rate": 7.840000000000001e-05, "loss": 7.1371, "step": 1180 }, { "epoch": 0.06725728738360674, "grad_norm": 7.297823905944824, "learning_rate": 7.906666666666667e-05, "loss": 7.1047, "step": 1190 }, { "epoch": 0.06782247467254461, "grad_norm": 3.9097559452056885, "learning_rate": 7.973333333333334e-05, "loss": 7.1234, "step": 1200 }, { "epoch": 0.06838766196148248, "grad_norm": 5.486624240875244, "learning_rate": 8.04e-05, "loss": 7.127, "step": 1210 }, { "epoch": 0.06895284925042036, "grad_norm": 4.645206928253174, "learning_rate": 8.106666666666667e-05, "loss": 7.1204, "step": 1220 }, { "epoch": 0.06951803653935823, "grad_norm": 12.343822479248047, "learning_rate": 8.173333333333335e-05, "loss": 7.0984, "step": 1230 }, { "epoch": 0.0700832238282961, "grad_norm": 3.8376729488372803, "learning_rate": 8.24e-05, "loss": 7.1214, "step": 1240 }, { "epoch": 0.07064841111723397, "grad_norm": 5.065261363983154, "learning_rate": 8.306666666666668e-05, "loss": 7.1048, "step": 1250 }, { "epoch": 0.07121359840617185, "grad_norm": 5.52305269241333, "learning_rate": 8.373333333333334e-05, "loss": 7.1059, "step": 1260 }, { "epoch": 0.07177878569510972, "grad_norm": 4.474567413330078, "learning_rate": 8.44e-05, "loss": 7.1337, "step": 1270 }, { "epoch": 0.07234397298404759, "grad_norm": 4.8178606033325195, "learning_rate": 8.506666666666667e-05, "loss": 7.107, "step": 1280 }, { "epoch": 0.07290916027298545, "grad_norm": 4.829899311065674, "learning_rate": 8.573333333333333e-05, "loss": 7.0931, "step": 1290 }, { "epoch": 0.07347434756192334, "grad_norm": 4.476377010345459, "learning_rate": 8.64e-05, "loss": 7.1007, "step": 1300 }, { "epoch": 0.0740395348508612, "grad_norm": 5.105553150177002, "learning_rate": 8.706666666666668e-05, "loss": 7.0622, "step": 1310 }, { "epoch": 0.07460472213979907, "grad_norm": 4.606741905212402, "learning_rate": 8.773333333333333e-05, "loss": 7.0935, "step": 1320 }, { "epoch": 0.07516990942873694, "grad_norm": 5.436127185821533, "learning_rate": 8.840000000000001e-05, "loss": 7.0831, "step": 1330 }, { "epoch": 0.07573509671767482, "grad_norm": 5.502111434936523, "learning_rate": 8.906666666666667e-05, "loss": 7.1012, "step": 1340 }, { "epoch": 0.07630028400661269, "grad_norm": 5.241184234619141, "learning_rate": 8.973333333333334e-05, "loss": 7.0956, "step": 1350 }, { "epoch": 0.07686547129555056, "grad_norm": 4.030516147613525, "learning_rate": 9.04e-05, "loss": 7.0778, "step": 1360 }, { "epoch": 0.07743065858448843, "grad_norm": 4.32786226272583, "learning_rate": 9.106666666666667e-05, "loss": 7.0998, "step": 1370 }, { "epoch": 0.07799584587342631, "grad_norm": 3.712005376815796, "learning_rate": 9.173333333333333e-05, "loss": 7.071, "step": 1380 }, { "epoch": 0.07856103316236418, "grad_norm": 4.82477331161499, "learning_rate": 9.240000000000001e-05, "loss": 7.0556, "step": 1390 }, { "epoch": 0.07912622045130205, "grad_norm": 6.89573335647583, "learning_rate": 9.306666666666667e-05, "loss": 7.0605, "step": 1400 }, { "epoch": 0.07969140774023992, "grad_norm": 4.6847758293151855, "learning_rate": 9.373333333333334e-05, "loss": 7.0882, "step": 1410 }, { "epoch": 0.0802565950291778, "grad_norm": 4.186715602874756, "learning_rate": 9.44e-05, "loss": 7.0686, "step": 1420 }, { "epoch": 0.08082178231811567, "grad_norm": 4.910926342010498, "learning_rate": 9.506666666666667e-05, "loss": 7.0616, "step": 1430 }, { "epoch": 0.08138696960705354, "grad_norm": 5.143073081970215, "learning_rate": 9.573333333333335e-05, "loss": 7.0624, "step": 1440 }, { "epoch": 0.0819521568959914, "grad_norm": 4.339007377624512, "learning_rate": 9.64e-05, "loss": 7.062, "step": 1450 }, { "epoch": 0.08251734418492929, "grad_norm": 3.640878200531006, "learning_rate": 9.706666666666668e-05, "loss": 7.0282, "step": 1460 }, { "epoch": 0.08308253147386715, "grad_norm": 3.9576308727264404, "learning_rate": 9.773333333333334e-05, "loss": 7.0511, "step": 1470 }, { "epoch": 0.08364771876280502, "grad_norm": 3.8672001361846924, "learning_rate": 9.84e-05, "loss": 7.0696, "step": 1480 }, { "epoch": 0.08421290605174289, "grad_norm": 4.105925559997559, "learning_rate": 9.906666666666667e-05, "loss": 7.0431, "step": 1490 }, { "epoch": 0.08477809334068077, "grad_norm": 3.388482093811035, "learning_rate": 9.973333333333334e-05, "loss": 7.0688, "step": 1500 }, { "epoch": 0.08534328062961864, "grad_norm": 3.9685401916503906, "learning_rate": 9.999997247444261e-05, "loss": 7.0283, "step": 1510 }, { "epoch": 0.08590846791855651, "grad_norm": 3.7773237228393555, "learning_rate": 9.999980426281275e-05, "loss": 7.0332, "step": 1520 }, { "epoch": 0.08647365520749438, "grad_norm": 5.110147476196289, "learning_rate": 9.999948313204316e-05, "loss": 7.0254, "step": 1530 }, { "epoch": 0.08703884249643226, "grad_norm": 5.550497531890869, "learning_rate": 9.999900908311602e-05, "loss": 7.0436, "step": 1540 }, { "epoch": 0.08760402978537013, "grad_norm": 5.89719820022583, "learning_rate": 9.999838211748114e-05, "loss": 7.0484, "step": 1550 }, { "epoch": 0.088169217074308, "grad_norm": 4.800846576690674, "learning_rate": 9.999760223705604e-05, "loss": 7.0263, "step": 1560 }, { "epoch": 0.08873440436324587, "grad_norm": 3.4888455867767334, "learning_rate": 9.99966694442259e-05, "loss": 7.0169, "step": 1570 }, { "epoch": 0.08929959165218375, "grad_norm": 4.237153053283691, "learning_rate": 9.999558374184354e-05, "loss": 7.0391, "step": 1580 }, { "epoch": 0.08986477894112162, "grad_norm": 4.062349796295166, "learning_rate": 9.999434513322952e-05, "loss": 7.0504, "step": 1590 }, { "epoch": 0.09042996623005949, "grad_norm": 4.253184795379639, "learning_rate": 9.999295362217195e-05, "loss": 7.0219, "step": 1600 }, { "epoch": 0.09099515351899735, "grad_norm": 4.127000331878662, "learning_rate": 9.999140921292665e-05, "loss": 7.0219, "step": 1610 }, { "epoch": 0.09156034080793522, "grad_norm": 3.5180132389068604, "learning_rate": 9.998971191021701e-05, "loss": 7.0047, "step": 1620 }, { "epoch": 0.0921255280968731, "grad_norm": 4.196110725402832, "learning_rate": 9.998786171923407e-05, "loss": 6.9919, "step": 1630 }, { "epoch": 0.09269071538581097, "grad_norm": 4.163175106048584, "learning_rate": 9.998585864563642e-05, "loss": 6.9953, "step": 1640 }, { "epoch": 0.09325590267474884, "grad_norm": 4.064554214477539, "learning_rate": 9.998370269555026e-05, "loss": 6.9658, "step": 1650 }, { "epoch": 0.09382108996368671, "grad_norm": 3.5954253673553467, "learning_rate": 9.998139387556936e-05, "loss": 7.01, "step": 1660 }, { "epoch": 0.09438627725262459, "grad_norm": 3.1272354125976562, "learning_rate": 9.997893219275496e-05, "loss": 6.9874, "step": 1670 }, { "epoch": 0.09495146454156246, "grad_norm": 4.052889823913574, "learning_rate": 9.99763176546359e-05, "loss": 7.0049, "step": 1680 }, { "epoch": 0.09551665183050033, "grad_norm": 3.62882661819458, "learning_rate": 9.997355026920845e-05, "loss": 6.974, "step": 1690 }, { "epoch": 0.0960818391194382, "grad_norm": 3.984910726547241, "learning_rate": 9.997063004493638e-05, "loss": 6.9857, "step": 1700 }, { "epoch": 0.09664702640837608, "grad_norm": 3.5285496711730957, "learning_rate": 9.996755699075087e-05, "loss": 6.9798, "step": 1710 }, { "epoch": 0.09721221369731395, "grad_norm": 4.073770523071289, "learning_rate": 9.996433111605052e-05, "loss": 6.9737, "step": 1720 }, { "epoch": 0.09777740098625182, "grad_norm": 3.7412960529327393, "learning_rate": 9.996095243070138e-05, "loss": 6.9692, "step": 1730 }, { "epoch": 0.09834258827518969, "grad_norm": 3.8600759506225586, "learning_rate": 9.995742094503675e-05, "loss": 6.9839, "step": 1740 }, { "epoch": 0.09890777556412757, "grad_norm": 3.1478703022003174, "learning_rate": 9.995373666985733e-05, "loss": 6.9605, "step": 1750 }, { "epoch": 0.09947296285306544, "grad_norm": 3.5501646995544434, "learning_rate": 9.994989961643109e-05, "loss": 6.9913, "step": 1760 }, { "epoch": 0.1000381501420033, "grad_norm": 3.9451208114624023, "learning_rate": 9.994590979649325e-05, "loss": 6.959, "step": 1770 }, { "epoch": 0.10060333743094117, "grad_norm": 3.9134464263916016, "learning_rate": 9.994176722224626e-05, "loss": 6.9724, "step": 1780 }, { "epoch": 0.10116852471987905, "grad_norm": 3.2988054752349854, "learning_rate": 9.993747190635976e-05, "loss": 6.9479, "step": 1790 }, { "epoch": 0.10173371200881692, "grad_norm": 3.197021245956421, "learning_rate": 9.993302386197047e-05, "loss": 6.9528, "step": 1800 }, { "epoch": 0.10229889929775479, "grad_norm": 4.286452293395996, "learning_rate": 9.992842310268233e-05, "loss": 6.955, "step": 1810 }, { "epoch": 0.10286408658669266, "grad_norm": 3.7987899780273438, "learning_rate": 9.992366964256624e-05, "loss": 6.9348, "step": 1820 }, { "epoch": 0.10342927387563054, "grad_norm": 3.3774564266204834, "learning_rate": 9.991876349616016e-05, "loss": 6.9553, "step": 1830 }, { "epoch": 0.10399446116456841, "grad_norm": 3.8282992839813232, "learning_rate": 9.991370467846904e-05, "loss": 6.9348, "step": 1840 }, { "epoch": 0.10455964845350628, "grad_norm": 6.265691757202148, "learning_rate": 9.990849320496471e-05, "loss": 6.9508, "step": 1850 }, { "epoch": 0.10512483574244415, "grad_norm": 3.712921619415283, "learning_rate": 9.990312909158595e-05, "loss": 6.9497, "step": 1860 }, { "epoch": 0.10569002303138203, "grad_norm": 4.4301557540893555, "learning_rate": 9.989761235473832e-05, "loss": 6.9497, "step": 1870 }, { "epoch": 0.1062552103203199, "grad_norm": 4.28318977355957, "learning_rate": 9.989194301129418e-05, "loss": 6.9243, "step": 1880 }, { "epoch": 0.10682039760925777, "grad_norm": 3.330911159515381, "learning_rate": 9.988612107859261e-05, "loss": 6.9364, "step": 1890 }, { "epoch": 0.10738558489819564, "grad_norm": 4.354373455047607, "learning_rate": 9.988014657443941e-05, "loss": 6.9172, "step": 1900 }, { "epoch": 0.10795077218713352, "grad_norm": 3.702962875366211, "learning_rate": 9.987401951710692e-05, "loss": 6.9176, "step": 1910 }, { "epoch": 0.10851595947607139, "grad_norm": 3.8388850688934326, "learning_rate": 9.986773992533414e-05, "loss": 6.9125, "step": 1920 }, { "epoch": 0.10908114676500925, "grad_norm": 3.725412607192993, "learning_rate": 9.986130781832654e-05, "loss": 6.942, "step": 1930 }, { "epoch": 0.10964633405394712, "grad_norm": 3.807227611541748, "learning_rate": 9.985472321575602e-05, "loss": 6.9084, "step": 1940 }, { "epoch": 0.110211521342885, "grad_norm": 31.865251541137695, "learning_rate": 9.984798613776092e-05, "loss": 6.9156, "step": 1950 }, { "epoch": 0.11077670863182287, "grad_norm": 3.346662759780884, "learning_rate": 9.984109660494587e-05, "loss": 6.9232, "step": 1960 }, { "epoch": 0.11134189592076074, "grad_norm": 3.3436596393585205, "learning_rate": 9.983405463838178e-05, "loss": 6.9013, "step": 1970 }, { "epoch": 0.11190708320969861, "grad_norm": 3.5422000885009766, "learning_rate": 9.982686025960575e-05, "loss": 6.8938, "step": 1980 }, { "epoch": 0.11247227049863649, "grad_norm": 4.072020530700684, "learning_rate": 9.981951349062106e-05, "loss": 6.8985, "step": 1990 }, { "epoch": 0.11303745778757436, "grad_norm": 4.684713363647461, "learning_rate": 9.981201435389702e-05, "loss": 6.8931, "step": 2000 }, { "epoch": 0.11360264507651223, "grad_norm": 3.688302993774414, "learning_rate": 9.980436287236895e-05, "loss": 6.8919, "step": 2010 }, { "epoch": 0.1141678323654501, "grad_norm": 3.982142210006714, "learning_rate": 9.97965590694381e-05, "loss": 6.9008, "step": 2020 }, { "epoch": 0.11473301965438797, "grad_norm": 3.714259624481201, "learning_rate": 9.978860296897157e-05, "loss": 6.8962, "step": 2030 }, { "epoch": 0.11529820694332585, "grad_norm": 3.1901533603668213, "learning_rate": 9.978049459530225e-05, "loss": 6.8962, "step": 2040 }, { "epoch": 0.11586339423226372, "grad_norm": 4.302250862121582, "learning_rate": 9.977223397322879e-05, "loss": 6.8736, "step": 2050 }, { "epoch": 0.11642858152120159, "grad_norm": 3.988112449645996, "learning_rate": 9.97638211280154e-05, "loss": 6.8841, "step": 2060 }, { "epoch": 0.11699376881013945, "grad_norm": 3.9468882083892822, "learning_rate": 9.975525608539187e-05, "loss": 6.8902, "step": 2070 }, { "epoch": 0.11755895609907734, "grad_norm": 4.514617443084717, "learning_rate": 9.97465388715535e-05, "loss": 6.8746, "step": 2080 }, { "epoch": 0.1181241433880152, "grad_norm": 3.812955379486084, "learning_rate": 9.973766951316097e-05, "loss": 6.87, "step": 2090 }, { "epoch": 0.11868933067695307, "grad_norm": 3.813168525695801, "learning_rate": 9.972864803734029e-05, "loss": 6.8888, "step": 2100 }, { "epoch": 0.11925451796589094, "grad_norm": 3.489537000656128, "learning_rate": 9.971947447168269e-05, "loss": 6.8603, "step": 2110 }, { "epoch": 0.11981970525482882, "grad_norm": 3.273092746734619, "learning_rate": 9.971014884424453e-05, "loss": 6.8538, "step": 2120 }, { "epoch": 0.12038489254376669, "grad_norm": 3.4794530868530273, "learning_rate": 9.970067118354727e-05, "loss": 6.8706, "step": 2130 }, { "epoch": 0.12095007983270456, "grad_norm": 4.166130542755127, "learning_rate": 9.969104151857737e-05, "loss": 6.8571, "step": 2140 }, { "epoch": 0.12151526712164243, "grad_norm": 4.602911472320557, "learning_rate": 9.968125987878612e-05, "loss": 6.8697, "step": 2150 }, { "epoch": 0.12208045441058031, "grad_norm": 3.3835315704345703, "learning_rate": 9.967132629408962e-05, "loss": 6.8709, "step": 2160 }, { "epoch": 0.12264564169951818, "grad_norm": 4.14102840423584, "learning_rate": 9.966124079486872e-05, "loss": 6.846, "step": 2170 }, { "epoch": 0.12321082898845605, "grad_norm": 5.069469928741455, "learning_rate": 9.965100341196887e-05, "loss": 6.8764, "step": 2180 }, { "epoch": 0.12377601627739392, "grad_norm": 3.8181676864624023, "learning_rate": 9.964061417669999e-05, "loss": 6.8621, "step": 2190 }, { "epoch": 0.1243412035663318, "grad_norm": 3.2151038646698, "learning_rate": 9.963007312083649e-05, "loss": 6.8441, "step": 2200 }, { "epoch": 0.12490639085526967, "grad_norm": 4.495757579803467, "learning_rate": 9.961938027661706e-05, "loss": 6.8397, "step": 2210 }, { "epoch": 0.12547157814420754, "grad_norm": 4.256015300750732, "learning_rate": 9.960853567674466e-05, "loss": 6.8464, "step": 2220 }, { "epoch": 0.1260367654331454, "grad_norm": 3.556025266647339, "learning_rate": 9.959753935438636e-05, "loss": 6.8482, "step": 2230 }, { "epoch": 0.12660195272208327, "grad_norm": 4.299757957458496, "learning_rate": 9.958639134317322e-05, "loss": 6.8337, "step": 2240 }, { "epoch": 0.12716714001102114, "grad_norm": 3.735377073287964, "learning_rate": 9.957509167720029e-05, "loss": 6.8367, "step": 2250 }, { "epoch": 0.12773232729995904, "grad_norm": 3.8254458904266357, "learning_rate": 9.956364039102642e-05, "loss": 6.8326, "step": 2260 }, { "epoch": 0.1282975145888969, "grad_norm": 4.486153602600098, "learning_rate": 9.955203751967412e-05, "loss": 6.8341, "step": 2270 }, { "epoch": 0.12886270187783477, "grad_norm": 3.648494243621826, "learning_rate": 9.95402830986296e-05, "loss": 6.8038, "step": 2280 }, { "epoch": 0.12942788916677264, "grad_norm": 3.378056764602661, "learning_rate": 9.952837716384246e-05, "loss": 6.82, "step": 2290 }, { "epoch": 0.1299930764557105, "grad_norm": 3.7696821689605713, "learning_rate": 9.951631975172582e-05, "loss": 6.8182, "step": 2300 }, { "epoch": 0.13055826374464838, "grad_norm": 4.139465808868408, "learning_rate": 9.950411089915596e-05, "loss": 6.8458, "step": 2310 }, { "epoch": 0.13112345103358625, "grad_norm": 6.562532424926758, "learning_rate": 9.949175064347237e-05, "loss": 6.821, "step": 2320 }, { "epoch": 0.13168863832252412, "grad_norm": 3.5617470741271973, "learning_rate": 9.947923902247762e-05, "loss": 6.828, "step": 2330 }, { "epoch": 0.132253825611462, "grad_norm": 3.613398551940918, "learning_rate": 9.946657607443716e-05, "loss": 6.7808, "step": 2340 }, { "epoch": 0.13281901290039988, "grad_norm": 4.249789237976074, "learning_rate": 9.94537618380793e-05, "loss": 6.8165, "step": 2350 }, { "epoch": 0.13338420018933775, "grad_norm": 3.732841968536377, "learning_rate": 9.944079635259503e-05, "loss": 6.8138, "step": 2360 }, { "epoch": 0.13394938747827562, "grad_norm": Infinity, "learning_rate": 9.94276796576379e-05, "loss": 6.8133, "step": 2370 }, { "epoch": 0.13451457476721349, "grad_norm": 3.5617806911468506, "learning_rate": 9.941574538122356e-05, "loss": 6.7961, "step": 2380 }, { "epoch": 0.13507976205615135, "grad_norm": 3.8023338317871094, "learning_rate": 9.940234149916983e-05, "loss": 6.7989, "step": 2390 }, { "epoch": 0.13564494934508922, "grad_norm": 3.6145825386047363, "learning_rate": 9.938878652525339e-05, "loss": 6.7807, "step": 2400 }, { "epoch": 0.1362101366340271, "grad_norm": 4.136194229125977, "learning_rate": 9.937508050093069e-05, "loss": 6.7938, "step": 2410 }, { "epoch": 0.13677532392296496, "grad_norm": 3.840880870819092, "learning_rate": 9.936122346812016e-05, "loss": 6.7889, "step": 2420 }, { "epoch": 0.13734051121190285, "grad_norm": 4.035423278808594, "learning_rate": 9.934721546920209e-05, "loss": 6.7879, "step": 2430 }, { "epoch": 0.13790569850084072, "grad_norm": 3.7200379371643066, "learning_rate": 9.933305654701846e-05, "loss": 6.7757, "step": 2440 }, { "epoch": 0.1384708857897786, "grad_norm": 3.24151349067688, "learning_rate": 9.931874674487285e-05, "loss": 6.7669, "step": 2450 }, { "epoch": 0.13903607307871646, "grad_norm": 3.7968711853027344, "learning_rate": 9.930428610653027e-05, "loss": 6.7851, "step": 2460 }, { "epoch": 0.13960126036765433, "grad_norm": 3.482286214828491, "learning_rate": 9.928967467621708e-05, "loss": 6.7936, "step": 2470 }, { "epoch": 0.1401664476565922, "grad_norm": 4.01021146774292, "learning_rate": 9.92749124986208e-05, "loss": 6.7719, "step": 2480 }, { "epoch": 0.14073163494553007, "grad_norm": 3.964850425720215, "learning_rate": 9.925999961888999e-05, "loss": 6.774, "step": 2490 }, { "epoch": 0.14129682223446793, "grad_norm": 4.234554290771484, "learning_rate": 9.92449360826341e-05, "loss": 6.7726, "step": 2500 }, { "epoch": 0.14186200952340583, "grad_norm": 3.9307267665863037, "learning_rate": 9.922972193592342e-05, "loss": 6.7819, "step": 2510 }, { "epoch": 0.1424271968123437, "grad_norm": 3.6391077041625977, "learning_rate": 9.921435722528878e-05, "loss": 6.7722, "step": 2520 }, { "epoch": 0.14299238410128157, "grad_norm": 3.7191545963287354, "learning_rate": 9.919884199772155e-05, "loss": 6.7659, "step": 2530 }, { "epoch": 0.14355757139021944, "grad_norm": 4.561165809631348, "learning_rate": 9.91831763006734e-05, "loss": 6.7611, "step": 2540 }, { "epoch": 0.1441227586791573, "grad_norm": 4.071800231933594, "learning_rate": 9.916736018205624e-05, "loss": 6.7523, "step": 2550 }, { "epoch": 0.14468794596809517, "grad_norm": 4.1421122550964355, "learning_rate": 9.915139369024197e-05, "loss": 6.7408, "step": 2560 }, { "epoch": 0.14525313325703304, "grad_norm": 3.9251198768615723, "learning_rate": 9.913527687406247e-05, "loss": 6.7538, "step": 2570 }, { "epoch": 0.1458183205459709, "grad_norm": 3.6621713638305664, "learning_rate": 9.91190097828093e-05, "loss": 6.7499, "step": 2580 }, { "epoch": 0.1463835078349088, "grad_norm": 3.9221556186676025, "learning_rate": 9.910259246623365e-05, "loss": 6.7623, "step": 2590 }, { "epoch": 0.14694869512384667, "grad_norm": 4.0150465965271, "learning_rate": 9.908602497454616e-05, "loss": 6.733, "step": 2600 }, { "epoch": 0.14751388241278454, "grad_norm": 3.7005388736724854, "learning_rate": 9.906930735841675e-05, "loss": 6.752, "step": 2610 }, { "epoch": 0.1480790697017224, "grad_norm": 4.456108093261719, "learning_rate": 9.90524396689745e-05, "loss": 6.7316, "step": 2620 }, { "epoch": 0.14864425699066028, "grad_norm": 3.975951671600342, "learning_rate": 9.903542195780746e-05, "loss": 6.7225, "step": 2630 }, { "epoch": 0.14920944427959815, "grad_norm": 4.13681173324585, "learning_rate": 9.90182542769625e-05, "loss": 6.7244, "step": 2640 }, { "epoch": 0.14977463156853602, "grad_norm": 4.061427593231201, "learning_rate": 9.900093667894516e-05, "loss": 6.7471, "step": 2650 }, { "epoch": 0.15033981885747388, "grad_norm": 3.607797622680664, "learning_rate": 9.898346921671953e-05, "loss": 6.7192, "step": 2660 }, { "epoch": 0.15090500614641178, "grad_norm": 4.354671955108643, "learning_rate": 9.896585194370795e-05, "loss": 6.7334, "step": 2670 }, { "epoch": 0.15147019343534965, "grad_norm": 4.171165943145752, "learning_rate": 9.894808491379105e-05, "loss": 6.7156, "step": 2680 }, { "epoch": 0.15203538072428752, "grad_norm": 4.039210319519043, "learning_rate": 9.893016818130738e-05, "loss": 6.7212, "step": 2690 }, { "epoch": 0.15260056801322539, "grad_norm": 3.7716877460479736, "learning_rate": 9.891210180105342e-05, "loss": 6.6934, "step": 2700 }, { "epoch": 0.15316575530216325, "grad_norm": 3.8514604568481445, "learning_rate": 9.889388582828323e-05, "loss": 6.7129, "step": 2710 }, { "epoch": 0.15373094259110112, "grad_norm": 4.585701942443848, "learning_rate": 9.887552031870852e-05, "loss": 6.7043, "step": 2720 }, { "epoch": 0.154296129880039, "grad_norm": 3.881371021270752, "learning_rate": 9.885700532849821e-05, "loss": 6.7036, "step": 2730 }, { "epoch": 0.15486131716897686, "grad_norm": 3.8516905307769775, "learning_rate": 9.883834091427849e-05, "loss": 6.7394, "step": 2740 }, { "epoch": 0.15542650445791475, "grad_norm": 4.573556423187256, "learning_rate": 9.881952713313248e-05, "loss": 6.7207, "step": 2750 }, { "epoch": 0.15599169174685262, "grad_norm": 3.628282308578491, "learning_rate": 9.880056404260016e-05, "loss": 6.6882, "step": 2760 }, { "epoch": 0.1565568790357905, "grad_norm": 3.902024030685425, "learning_rate": 9.878145170067814e-05, "loss": 6.7065, "step": 2770 }, { "epoch": 0.15712206632472836, "grad_norm": 4.092791557312012, "learning_rate": 9.876219016581952e-05, "loss": 6.67, "step": 2780 }, { "epoch": 0.15768725361366623, "grad_norm": 3.6419739723205566, "learning_rate": 9.874277949693367e-05, "loss": 6.6697, "step": 2790 }, { "epoch": 0.1582524409026041, "grad_norm": 3.5587034225463867, "learning_rate": 9.872321975338607e-05, "loss": 6.6772, "step": 2800 }, { "epoch": 0.15881762819154197, "grad_norm": 3.9504709243774414, "learning_rate": 9.870351099499817e-05, "loss": 6.7041, "step": 2810 }, { "epoch": 0.15938281548047983, "grad_norm": 3.735733985900879, "learning_rate": 9.868365328204709e-05, "loss": 6.6896, "step": 2820 }, { "epoch": 0.1599480027694177, "grad_norm": 4.707046985626221, "learning_rate": 9.866364667526557e-05, "loss": 6.7054, "step": 2830 }, { "epoch": 0.1605131900583556, "grad_norm": 3.932325601577759, "learning_rate": 9.864349123584173e-05, "loss": 6.6883, "step": 2840 }, { "epoch": 0.16107837734729347, "grad_norm": 4.032938003540039, "learning_rate": 9.862318702541883e-05, "loss": 6.6939, "step": 2850 }, { "epoch": 0.16164356463623133, "grad_norm": 4.105648517608643, "learning_rate": 9.860273410609518e-05, "loss": 6.6775, "step": 2860 }, { "epoch": 0.1622087519251692, "grad_norm": 4.012267589569092, "learning_rate": 9.85821325404239e-05, "loss": 6.678, "step": 2870 }, { "epoch": 0.16277393921410707, "grad_norm": 3.8882358074188232, "learning_rate": 9.856138239141266e-05, "loss": 6.6792, "step": 2880 }, { "epoch": 0.16333912650304494, "grad_norm": 4.405274391174316, "learning_rate": 9.854048372252364e-05, "loss": 6.6541, "step": 2890 }, { "epoch": 0.1639043137919828, "grad_norm": 3.766094207763672, "learning_rate": 9.851943659767323e-05, "loss": 6.6759, "step": 2900 }, { "epoch": 0.16446950108092068, "grad_norm": 4.439742088317871, "learning_rate": 9.849824108123182e-05, "loss": 6.6585, "step": 2910 }, { "epoch": 0.16503468836985857, "grad_norm": 4.0348896980285645, "learning_rate": 9.847689723802369e-05, "loss": 6.6666, "step": 2920 }, { "epoch": 0.16559987565879644, "grad_norm": 3.9370694160461426, "learning_rate": 9.845540513332673e-05, "loss": 6.6613, "step": 2930 }, { "epoch": 0.1661650629477343, "grad_norm": 4.366966724395752, "learning_rate": 9.843376483287227e-05, "loss": 6.6483, "step": 2940 }, { "epoch": 0.16673025023667218, "grad_norm": 4.292701244354248, "learning_rate": 9.841197640284489e-05, "loss": 6.6453, "step": 2950 }, { "epoch": 0.16729543752561005, "grad_norm": 4.8376288414001465, "learning_rate": 9.839003990988224e-05, "loss": 6.6545, "step": 2960 }, { "epoch": 0.16786062481454792, "grad_norm": 4.24878454208374, "learning_rate": 9.836795542107475e-05, "loss": 6.6431, "step": 2970 }, { "epoch": 0.16842581210348578, "grad_norm": 4.053425312042236, "learning_rate": 9.83457230039655e-05, "loss": 6.641, "step": 2980 }, { "epoch": 0.16899099939242365, "grad_norm": 3.94399356842041, "learning_rate": 9.832334272655002e-05, "loss": 6.6461, "step": 2990 }, { "epoch": 0.16955618668136155, "grad_norm": 5.247406959533691, "learning_rate": 9.830081465727602e-05, "loss": 6.6487, "step": 3000 }, { "epoch": 0.17012137397029942, "grad_norm": 4.178400993347168, "learning_rate": 9.827813886504323e-05, "loss": 6.6465, "step": 3010 }, { "epoch": 0.17068656125923728, "grad_norm": 4.21041202545166, "learning_rate": 9.825531541920317e-05, "loss": 6.6574, "step": 3020 }, { "epoch": 0.17125174854817515, "grad_norm": 4.469128608703613, "learning_rate": 9.823234438955895e-05, "loss": 6.6337, "step": 3030 }, { "epoch": 0.17181693583711302, "grad_norm": 3.912477731704712, "learning_rate": 9.820922584636505e-05, "loss": 6.6404, "step": 3040 }, { "epoch": 0.1723821231260509, "grad_norm": 4.176887512207031, "learning_rate": 9.818595986032711e-05, "loss": 6.6455, "step": 3050 }, { "epoch": 0.17294731041498876, "grad_norm": 4.220492362976074, "learning_rate": 9.816254650260169e-05, "loss": 6.6649, "step": 3060 }, { "epoch": 0.17351249770392663, "grad_norm": 5.174860954284668, "learning_rate": 9.813898584479608e-05, "loss": 6.6257, "step": 3070 }, { "epoch": 0.17407768499286452, "grad_norm": 3.880764961242676, "learning_rate": 9.811527795896806e-05, "loss": 6.6363, "step": 3080 }, { "epoch": 0.1746428722818024, "grad_norm": 10.297629356384277, "learning_rate": 9.809142291762574e-05, "loss": 6.6297, "step": 3090 }, { "epoch": 0.17520805957074026, "grad_norm": 6.549805164337158, "learning_rate": 9.806742079372721e-05, "loss": 6.6314, "step": 3100 }, { "epoch": 0.17577324685967813, "grad_norm": 3.99611496925354, "learning_rate": 9.804327166068048e-05, "loss": 6.6261, "step": 3110 }, { "epoch": 0.176338434148616, "grad_norm": 4.140940189361572, "learning_rate": 9.802141180915069e-05, "loss": 6.6055, "step": 3120 }, { "epoch": 0.17690362143755387, "grad_norm": 5.720757007598877, "learning_rate": 9.800921603975645e-05, "loss": 6.5968, "step": 3130 }, { "epoch": 0.17746880872649173, "grad_norm": 4.39951229095459, "learning_rate": 9.799943299418315e-05, "loss": 6.6205, "step": 3140 }, { "epoch": 0.1780339960154296, "grad_norm": NaN, "learning_rate": 9.799208029561009e-05, "loss": 6.615, "step": 3150 }, { "epoch": 0.1785991833043675, "grad_norm": NaN, "learning_rate": 9.797979644323716e-05, "loss": 6.6276, "step": 3160 }, { "epoch": 0.17916437059330537, "grad_norm": NaN, "learning_rate": 9.796994294747349e-05, "loss": 6.6171, "step": 3170 }, { "epoch": 0.17972955788224323, "grad_norm": 3.5030713081359863, "learning_rate": 9.796253742072596e-05, "loss": 6.6331, "step": 3180 }, { "epoch": 0.1802947451711811, "grad_norm": NaN, "learning_rate": 9.794024163691515e-05, "loss": 6.6587, "step": 3190 }, { "epoch": 0.18085993246011897, "grad_norm": NaN, "learning_rate": 9.792032345896264e-05, "loss": 6.6609, "step": 3200 }, { "epoch": 0.18142511974905684, "grad_norm": 3.0915441513061523, "learning_rate": 9.790031148307095e-05, "loss": 6.6498, "step": 3210 }, { "epoch": 0.1819903070379947, "grad_norm": NaN, "learning_rate": 9.787768594112317e-05, "loss": 6.6554, "step": 3220 }, { "epoch": 0.18255549432693258, "grad_norm": NaN, "learning_rate": 9.786000629433722e-05, "loss": 6.6584, "step": 3230 }, { "epoch": 0.18312068161587045, "grad_norm": 3.3571183681488037, "learning_rate": 9.784479522419412e-05, "loss": 6.663, "step": 3240 }, { "epoch": 0.18368586890480834, "grad_norm": 3.2182559967041016, "learning_rate": 9.782443185639439e-05, "loss": 6.6795, "step": 3250 }, { "epoch": 0.1842510561937462, "grad_norm": 3.560364246368408, "learning_rate": 9.780141117611772e-05, "loss": 6.657, "step": 3260 }, { "epoch": 0.18481624348268408, "grad_norm": 3.1793437004089355, "learning_rate": 9.777827207741081e-05, "loss": 6.6679, "step": 3270 }, { "epoch": 0.18538143077162195, "grad_norm": 3.265005588531494, "learning_rate": 9.775501461759617e-05, "loss": 6.6661, "step": 3280 }, { "epoch": 0.18594661806055982, "grad_norm": NaN, "learning_rate": 9.773163885428949e-05, "loss": 6.6718, "step": 3290 }, { "epoch": 0.18651180534949768, "grad_norm": 3.2607803344726562, "learning_rate": 9.770814484539954e-05, "loss": 6.6625, "step": 3300 }, { "epoch": 0.18707699263843555, "grad_norm": 3.5719051361083984, "learning_rate": 9.768453264912803e-05, "loss": 6.6635, "step": 3310 }, { "epoch": 0.18764217992737342, "grad_norm": 3.302840232849121, "learning_rate": 9.766608593522349e-05, "loss": 6.6752, "step": 3320 }, { "epoch": 0.18820736721631132, "grad_norm": 3.258258819580078, "learning_rate": 9.763960957919413e-05, "loss": 6.6654, "step": 3330 }, { "epoch": 0.18877255450524918, "grad_norm": 2.9209108352661133, "learning_rate": 9.761298752243213e-05, "loss": 6.646, "step": 3340 }, { "epoch": 0.18933774179418705, "grad_norm": 3.298301935195923, "learning_rate": 9.759158502719481e-05, "loss": 6.6751, "step": 3350 }, { "epoch": 0.18990292908312492, "grad_norm": 3.3015167713165283, "learning_rate": 9.756470091459366e-05, "loss": 6.6577, "step": 3360 }, { "epoch": 0.1904681163720628, "grad_norm": NaN, "learning_rate": 9.754308888097583e-05, "loss": 6.6696, "step": 3370 }, { "epoch": 0.19103330366100066, "grad_norm": 3.131807565689087, "learning_rate": 9.752138378780753e-05, "loss": 6.6711, "step": 3380 }, { "epoch": 0.19159849094993853, "grad_norm": 3.1039297580718994, "learning_rate": 9.749685437565515e-05, "loss": 6.6549, "step": 3390 }, { "epoch": 0.1921636782388764, "grad_norm": 3.200427532196045, "learning_rate": 9.747220729955104e-05, "loss": 6.672, "step": 3400 }, { "epoch": 0.1927288655278143, "grad_norm": NaN, "learning_rate": 9.744744262055345e-05, "loss": 6.6775, "step": 3410 }, { "epoch": 0.19329405281675216, "grad_norm": NaN, "learning_rate": 9.74308675298983e-05, "loss": 6.6466, "step": 3420 }, { "epoch": 0.19385924010569003, "grad_norm": NaN, "learning_rate": 9.741146392205353e-05, "loss": 6.6825, "step": 3430 }, { "epoch": 0.1944244273946279, "grad_norm": 3.3780856132507324, "learning_rate": 9.739198926274269e-05, "loss": 6.6596, "step": 3440 }, { "epoch": 0.19498961468356577, "grad_norm": 2.985156774520874, "learning_rate": 9.736684605988357e-05, "loss": 6.6771, "step": 3450 }, { "epoch": 0.19555480197250363, "grad_norm": 3.4086244106292725, "learning_rate": 9.73472091069856e-05, "loss": 6.6748, "step": 3460 }, { "epoch": 0.1961199892614415, "grad_norm": 3.3101348876953125, "learning_rate": 9.732467999293775e-05, "loss": 6.6658, "step": 3470 }, { "epoch": 0.19668517655037937, "grad_norm": NaN, "learning_rate": 9.730205824684708e-05, "loss": 6.6494, "step": 3480 }, { "epoch": 0.19725036383931727, "grad_norm": 3.281367063522339, "learning_rate": 9.728218826659998e-05, "loss": 6.6761, "step": 3490 }, { "epoch": 0.19781555112825513, "grad_norm": 3.5270464420318604, "learning_rate": 9.726224742862107e-05, "loss": 6.6551, "step": 3500 }, { "epoch": 0.198380738417193, "grad_norm": 3.5579729080200195, "learning_rate": 9.723937117327225e-05, "loss": 6.678, "step": 3510 }, { "epoch": 0.19894592570613087, "grad_norm": 3.244680643081665, "learning_rate": 9.721640245286177e-05, "loss": 6.6683, "step": 3520 }, { "epoch": 0.19951111299506874, "grad_norm": 3.2412514686584473, "learning_rate": 9.719334131234799e-05, "loss": 6.6631, "step": 3530 }, { "epoch": 0.2000763002840066, "grad_norm": 3.540827512741089, "learning_rate": 9.716728711457592e-05, "loss": 6.6806, "step": 3540 }, { "epoch": 0.20064148757294448, "grad_norm": 3.419512987136841, "learning_rate": 9.714111606928908e-05, "loss": 6.6365, "step": 3550 }, { "epoch": 0.20120667486188235, "grad_norm": 3.3318324089050293, "learning_rate": 9.712068006986942e-05, "loss": 6.6757, "step": 3560 }, { "epoch": 0.20177186215082024, "grad_norm": 3.264765977859497, "learning_rate": 9.710310729344725e-05, "loss": 6.6554, "step": 3570 }, { "epoch": 0.2023370494397581, "grad_norm": 3.59761905670166, "learning_rate": 9.707959625468129e-05, "loss": 6.6555, "step": 3580 }, { "epoch": 0.20290223672869598, "grad_norm": 3.3622217178344727, "learning_rate": 9.705303618754551e-05, "loss": 6.6585, "step": 3590 }, { "epoch": 0.20346742401763385, "grad_norm": 3.312781572341919, "learning_rate": 9.702635955592877e-05, "loss": 6.6669, "step": 3600 } ], "logging_steps": 10, "max_steps": 19464, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 7.919193430259712e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }