{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 200, "global_step": 266, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.007518796992481203, "grad_norm": 0.08289683091006875, "learning_rate": 3.7037037037037037e-06, "loss": 0.2087, "step": 1 }, { "epoch": 0.015037593984962405, "grad_norm": 0.03030546873337256, "learning_rate": 7.4074074074074075e-06, "loss": 0.1045, "step": 2 }, { "epoch": 0.022556390977443608, "grad_norm": 0.04340875250649354, "learning_rate": 1.1111111111111112e-05, "loss": 0.1291, "step": 3 }, { "epoch": 0.03007518796992481, "grad_norm": 0.04223285184390201, "learning_rate": 1.4814814814814815e-05, "loss": 0.1263, "step": 4 }, { "epoch": 0.03759398496240601, "grad_norm": 0.04894801143939966, "learning_rate": 1.8518518518518518e-05, "loss": 0.1409, "step": 5 }, { "epoch": 0.045112781954887216, "grad_norm": 0.22261274174154347, "learning_rate": 2.2222222222222223e-05, "loss": 0.2362, "step": 6 }, { "epoch": 0.05263157894736842, "grad_norm": 0.043978295203653116, "learning_rate": 2.5925925925925925e-05, "loss": 0.1195, "step": 7 }, { "epoch": 0.06015037593984962, "grad_norm": 0.04381964595602848, "learning_rate": 2.962962962962963e-05, "loss": 0.1215, "step": 8 }, { "epoch": 0.06766917293233082, "grad_norm": 0.03290036083527209, "learning_rate": 3.3333333333333335e-05, "loss": 0.0881, "step": 9 }, { "epoch": 0.07518796992481203, "grad_norm": 0.03303553719000837, "learning_rate": 3.7037037037037037e-05, "loss": 0.0923, "step": 10 }, { "epoch": 0.08270676691729323, "grad_norm": 0.12832751130733108, "learning_rate": 4.074074074074074e-05, "loss": 0.218, "step": 11 }, { "epoch": 0.09022556390977443, "grad_norm": 0.08479076437214379, "learning_rate": 4.4444444444444447e-05, "loss": 0.149, "step": 12 }, { "epoch": 0.09774436090225563, "grad_norm": 0.13534422076541278, "learning_rate": 4.814814814814815e-05, "loss": 0.1835, "step": 13 }, { "epoch": 0.10526315789473684, "grad_norm": 0.10341781138952844, "learning_rate": 5.185185185185185e-05, "loss": 0.1573, "step": 14 }, { "epoch": 0.11278195488721804, "grad_norm": 0.12256701286625035, "learning_rate": 5.555555555555556e-05, "loss": 0.1701, "step": 15 }, { "epoch": 0.12030075187969924, "grad_norm": 0.05708144315846648, "learning_rate": 5.925925925925926e-05, "loss": 0.0938, "step": 16 }, { "epoch": 0.12781954887218044, "grad_norm": 0.0813311914428683, "learning_rate": 6.296296296296296e-05, "loss": 0.1221, "step": 17 }, { "epoch": 0.13533834586466165, "grad_norm": 0.07670248585638807, "learning_rate": 6.666666666666667e-05, "loss": 0.1068, "step": 18 }, { "epoch": 0.14285714285714285, "grad_norm": 0.12777013083805186, "learning_rate": 7.037037037037038e-05, "loss": 0.1183, "step": 19 }, { "epoch": 0.15037593984962405, "grad_norm": 0.07203864112993859, "learning_rate": 7.407407407407407e-05, "loss": 0.0941, "step": 20 }, { "epoch": 0.15789473684210525, "grad_norm": 0.06622495246697525, "learning_rate": 7.777777777777778e-05, "loss": 0.0851, "step": 21 }, { "epoch": 0.16541353383458646, "grad_norm": 0.05064660711733651, "learning_rate": 8.148148148148148e-05, "loss": 0.0672, "step": 22 }, { "epoch": 0.17293233082706766, "grad_norm": 0.05569880144395339, "learning_rate": 8.518518518518518e-05, "loss": 0.0692, "step": 23 }, { "epoch": 0.18045112781954886, "grad_norm": 0.06341922542018791, "learning_rate": 8.888888888888889e-05, "loss": 0.0719, "step": 24 }, { "epoch": 0.18796992481203006, "grad_norm": 0.09483517480751269, "learning_rate": 9.25925925925926e-05, "loss": 0.1039, "step": 25 }, { "epoch": 0.19548872180451127, "grad_norm": 0.06345422292566975, "learning_rate": 9.62962962962963e-05, "loss": 0.0642, "step": 26 }, { "epoch": 0.20300751879699247, "grad_norm": 0.06565559978972503, "learning_rate": 0.0001, "loss": 0.0806, "step": 27 }, { "epoch": 0.21052631578947367, "grad_norm": 0.07234940226716612, "learning_rate": 9.999568045802217e-05, "loss": 0.0699, "step": 28 }, { "epoch": 0.21804511278195488, "grad_norm": 0.09174614011055109, "learning_rate": 9.998272257842641e-05, "loss": 0.0797, "step": 29 }, { "epoch": 0.22556390977443608, "grad_norm": 0.0799372037045221, "learning_rate": 9.996112860009688e-05, "loss": 0.0599, "step": 30 }, { "epoch": 0.23308270676691728, "grad_norm": 0.07650243821697233, "learning_rate": 9.993090225407743e-05, "loss": 0.0673, "step": 31 }, { "epoch": 0.24060150375939848, "grad_norm": 0.07437978624039222, "learning_rate": 9.989204876292688e-05, "loss": 0.063, "step": 32 }, { "epoch": 0.24812030075187969, "grad_norm": 0.05826090837310029, "learning_rate": 9.984457483981669e-05, "loss": 0.0563, "step": 33 }, { "epoch": 0.2556390977443609, "grad_norm": 0.046830358894256296, "learning_rate": 9.978848868737098e-05, "loss": 0.0449, "step": 34 }, { "epoch": 0.2631578947368421, "grad_norm": 0.059942032653184, "learning_rate": 9.972379999624936e-05, "loss": 0.0492, "step": 35 }, { "epoch": 0.2706766917293233, "grad_norm": 0.04559622889503948, "learning_rate": 9.96505199434725e-05, "loss": 0.0384, "step": 36 }, { "epoch": 0.2781954887218045, "grad_norm": 0.08582556953299057, "learning_rate": 9.956866119049095e-05, "loss": 0.052, "step": 37 }, { "epoch": 0.2857142857142857, "grad_norm": 0.05879365562753825, "learning_rate": 9.947823788099753e-05, "loss": 0.0499, "step": 38 }, { "epoch": 0.2932330827067669, "grad_norm": 0.07725729979493687, "learning_rate": 9.937926563848346e-05, "loss": 0.0382, "step": 39 }, { "epoch": 0.3007518796992481, "grad_norm": 0.06791365316815774, "learning_rate": 9.927176156353899e-05, "loss": 0.0424, "step": 40 }, { "epoch": 0.3082706766917293, "grad_norm": 0.06835456363607172, "learning_rate": 9.91557442308987e-05, "loss": 0.0477, "step": 41 }, { "epoch": 0.3157894736842105, "grad_norm": 0.06785706541381617, "learning_rate": 9.903123368623216e-05, "loss": 0.0423, "step": 42 }, { "epoch": 0.3233082706766917, "grad_norm": 0.037822284484082716, "learning_rate": 9.889825144268029e-05, "loss": 0.0373, "step": 43 }, { "epoch": 0.3308270676691729, "grad_norm": 0.09335172889811039, "learning_rate": 9.875682047713846e-05, "loss": 0.0532, "step": 44 }, { "epoch": 0.3383458646616541, "grad_norm": 0.03552601591664148, "learning_rate": 9.860696522628639e-05, "loss": 0.0302, "step": 45 }, { "epoch": 0.3458646616541353, "grad_norm": 0.06792399841238587, "learning_rate": 9.844871158236591e-05, "loss": 0.043, "step": 46 }, { "epoch": 0.3533834586466165, "grad_norm": 0.07394708716985816, "learning_rate": 9.828208688870735e-05, "loss": 0.0414, "step": 47 }, { "epoch": 0.3609022556390977, "grad_norm": 0.07644206071621325, "learning_rate": 9.810711993500507e-05, "loss": 0.0442, "step": 48 }, { "epoch": 0.3684210526315789, "grad_norm": 0.04448780324279346, "learning_rate": 9.792384095234313e-05, "loss": 0.0397, "step": 49 }, { "epoch": 0.37593984962406013, "grad_norm": 0.040299146373067786, "learning_rate": 9.773228160797188e-05, "loss": 0.0294, "step": 50 }, { "epoch": 0.38345864661654133, "grad_norm": 0.04600091352431098, "learning_rate": 9.753247499983649e-05, "loss": 0.0388, "step": 51 }, { "epoch": 0.39097744360902253, "grad_norm": 0.05174024689025062, "learning_rate": 9.732445565085824e-05, "loss": 0.0464, "step": 52 }, { "epoch": 0.39849624060150374, "grad_norm": 0.06048290755695799, "learning_rate": 9.71082595029695e-05, "loss": 0.0441, "step": 53 }, { "epoch": 0.40601503759398494, "grad_norm": 0.06909111905381797, "learning_rate": 9.688392391090373e-05, "loss": 0.0403, "step": 54 }, { "epoch": 0.41353383458646614, "grad_norm": 0.10580098842980783, "learning_rate": 9.665148763574123e-05, "loss": 0.0414, "step": 55 }, { "epoch": 0.42105263157894735, "grad_norm": 0.06004492721880413, "learning_rate": 9.64109908382119e-05, "loss": 0.0348, "step": 56 }, { "epoch": 0.42857142857142855, "grad_norm": 0.05616302785838828, "learning_rate": 9.616247507175623e-05, "loss": 0.0353, "step": 57 }, { "epoch": 0.43609022556390975, "grad_norm": 0.04963402332052172, "learning_rate": 9.590598327534564e-05, "loss": 0.0354, "step": 58 }, { "epoch": 0.44360902255639095, "grad_norm": 0.09520890937208057, "learning_rate": 9.564155976606339e-05, "loss": 0.0436, "step": 59 }, { "epoch": 0.45112781954887216, "grad_norm": 0.07317691578763187, "learning_rate": 9.536925023144742e-05, "loss": 0.0448, "step": 60 }, { "epoch": 0.45864661654135336, "grad_norm": 0.0653903652099525, "learning_rate": 9.508910172159635e-05, "loss": 0.0456, "step": 61 }, { "epoch": 0.46616541353383456, "grad_norm": 0.08533000644485912, "learning_rate": 9.480116264104011e-05, "loss": 0.0417, "step": 62 }, { "epoch": 0.47368421052631576, "grad_norm": 0.07477194348090598, "learning_rate": 9.450548274037653e-05, "loss": 0.0427, "step": 63 }, { "epoch": 0.48120300751879697, "grad_norm": 0.040320894825821886, "learning_rate": 9.420211310767533e-05, "loss": 0.0317, "step": 64 }, { "epoch": 0.48872180451127817, "grad_norm": 0.04204333897095501, "learning_rate": 9.389110615965102e-05, "loss": 0.0308, "step": 65 }, { "epoch": 0.49624060150375937, "grad_norm": 0.06435209558835227, "learning_rate": 9.35725156326063e-05, "loss": 0.0404, "step": 66 }, { "epoch": 0.5037593984962406, "grad_norm": 0.05292300086818655, "learning_rate": 9.324639657314742e-05, "loss": 0.0383, "step": 67 }, { "epoch": 0.5112781954887218, "grad_norm": 0.0533359959006372, "learning_rate": 9.291280532867302e-05, "loss": 0.0419, "step": 68 }, { "epoch": 0.518796992481203, "grad_norm": 0.0421677134855151, "learning_rate": 9.257179953763845e-05, "loss": 0.0301, "step": 69 }, { "epoch": 0.5263157894736842, "grad_norm": 0.047396091527240565, "learning_rate": 9.222343811959693e-05, "loss": 0.0355, "step": 70 }, { "epoch": 0.5338345864661654, "grad_norm": 0.05055865206409256, "learning_rate": 9.186778126501916e-05, "loss": 0.0379, "step": 71 }, { "epoch": 0.5413533834586466, "grad_norm": 0.03922328494549794, "learning_rate": 9.150489042489367e-05, "loss": 0.03, "step": 72 }, { "epoch": 0.5488721804511278, "grad_norm": 0.08580904921861318, "learning_rate": 9.113482830010918e-05, "loss": 0.038, "step": 73 }, { "epoch": 0.556390977443609, "grad_norm": 0.04615991149700515, "learning_rate": 9.075765883062093e-05, "loss": 0.0321, "step": 74 }, { "epoch": 0.5639097744360902, "grad_norm": 0.21688152384611062, "learning_rate": 9.037344718440322e-05, "loss": 0.0369, "step": 75 }, { "epoch": 0.5714285714285714, "grad_norm": 0.06709856743156827, "learning_rate": 8.99822597461894e-05, "loss": 0.0429, "step": 76 }, { "epoch": 0.5789473684210527, "grad_norm": 0.07300506123989278, "learning_rate": 8.958416410600187e-05, "loss": 0.0351, "step": 77 }, { "epoch": 0.5864661654135338, "grad_norm": 0.08415403445437179, "learning_rate": 8.917922904747384e-05, "loss": 0.0425, "step": 78 }, { "epoch": 0.5939849624060151, "grad_norm": 0.043734956942212244, "learning_rate": 8.876752453596462e-05, "loss": 0.0322, "step": 79 }, { "epoch": 0.6015037593984962, "grad_norm": 0.11340147288766998, "learning_rate": 8.834912170647101e-05, "loss": 0.0446, "step": 80 }, { "epoch": 0.6090225563909775, "grad_norm": 0.061288991507609664, "learning_rate": 8.792409285133642e-05, "loss": 0.0424, "step": 81 }, { "epoch": 0.6165413533834586, "grad_norm": 0.043805649893633086, "learning_rate": 8.749251140776016e-05, "loss": 0.0342, "step": 82 }, { "epoch": 0.6240601503759399, "grad_norm": 0.05953059965877648, "learning_rate": 8.705445194510868e-05, "loss": 0.0321, "step": 83 }, { "epoch": 0.631578947368421, "grad_norm": 0.07945205955271631, "learning_rate": 8.66099901520315e-05, "loss": 0.0371, "step": 84 }, { "epoch": 0.6390977443609023, "grad_norm": 0.04453806753518928, "learning_rate": 8.615920282338355e-05, "loss": 0.0349, "step": 85 }, { "epoch": 0.6466165413533834, "grad_norm": 0.05196927124976879, "learning_rate": 8.570216784695637e-05, "loss": 0.0287, "step": 86 }, { "epoch": 0.6541353383458647, "grad_norm": 0.08901603801098872, "learning_rate": 8.52389641900206e-05, "loss": 0.0379, "step": 87 }, { "epoch": 0.6616541353383458, "grad_norm": 0.04173009472070016, "learning_rate": 8.476967188568188e-05, "loss": 0.0264, "step": 88 }, { "epoch": 0.6691729323308271, "grad_norm": 0.06191267416598679, "learning_rate": 8.429437201905254e-05, "loss": 0.028, "step": 89 }, { "epoch": 0.6766917293233082, "grad_norm": 0.05938205491417802, "learning_rate": 8.381314671324159e-05, "loss": 0.0353, "step": 90 }, { "epoch": 0.6842105263157895, "grad_norm": 0.06594155945203996, "learning_rate": 8.332607911516545e-05, "loss": 0.0423, "step": 91 }, { "epoch": 0.6917293233082706, "grad_norm": 0.03727901580427709, "learning_rate": 8.283325338118153e-05, "loss": 0.0288, "step": 92 }, { "epoch": 0.6992481203007519, "grad_norm": 0.039506792129091334, "learning_rate": 8.233475466254765e-05, "loss": 0.0319, "step": 93 }, { "epoch": 0.706766917293233, "grad_norm": 0.10114676138905467, "learning_rate": 8.183066909070947e-05, "loss": 0.0413, "step": 94 }, { "epoch": 0.7142857142857143, "grad_norm": 0.0519720254987392, "learning_rate": 8.132108376241849e-05, "loss": 0.0319, "step": 95 }, { "epoch": 0.7218045112781954, "grad_norm": 0.06828535688055823, "learning_rate": 8.08060867246834e-05, "loss": 0.0415, "step": 96 }, { "epoch": 0.7293233082706767, "grad_norm": 0.04423778552147402, "learning_rate": 8.028576695955711e-05, "loss": 0.0307, "step": 97 }, { "epoch": 0.7368421052631579, "grad_norm": 0.04301708267503238, "learning_rate": 7.97602143687623e-05, "loss": 0.0292, "step": 98 }, { "epoch": 0.7443609022556391, "grad_norm": 0.07557692217243188, "learning_rate": 7.922951975815811e-05, "loss": 0.0304, "step": 99 }, { "epoch": 0.7518796992481203, "grad_norm": 0.061041885279450855, "learning_rate": 7.869377482205042e-05, "loss": 0.0318, "step": 100 }, { "epoch": 0.7593984962406015, "grad_norm": 0.040342152719196084, "learning_rate": 7.815307212734888e-05, "loss": 0.027, "step": 101 }, { "epoch": 0.7669172932330827, "grad_norm": 0.07790755826343725, "learning_rate": 7.760750509757298e-05, "loss": 0.0339, "step": 102 }, { "epoch": 0.7744360902255639, "grad_norm": 0.05210408795431101, "learning_rate": 7.705716799671019e-05, "loss": 0.0228, "step": 103 }, { "epoch": 0.7819548872180451, "grad_norm": 0.08000736959421384, "learning_rate": 7.650215591292888e-05, "loss": 0.0357, "step": 104 }, { "epoch": 0.7894736842105263, "grad_norm": 0.05843028390975531, "learning_rate": 7.594256474214882e-05, "loss": 0.0285, "step": 105 }, { "epoch": 0.7969924812030075, "grad_norm": 0.13537509841914472, "learning_rate": 7.537849117147212e-05, "loss": 0.0359, "step": 106 }, { "epoch": 0.8045112781954887, "grad_norm": 0.08230566866298178, "learning_rate": 7.481003266247744e-05, "loss": 0.0367, "step": 107 }, { "epoch": 0.8120300751879699, "grad_norm": 0.09678557492723187, "learning_rate": 7.423728743438048e-05, "loss": 0.0358, "step": 108 }, { "epoch": 0.8195488721804511, "grad_norm": 0.049541914871144996, "learning_rate": 7.366035444706347e-05, "loss": 0.0329, "step": 109 }, { "epoch": 0.8270676691729323, "grad_norm": 0.08823757922929092, "learning_rate": 7.307933338397667e-05, "loss": 0.0364, "step": 110 }, { "epoch": 0.8345864661654135, "grad_norm": 0.044744299992948704, "learning_rate": 7.249432463491498e-05, "loss": 0.0328, "step": 111 }, { "epoch": 0.8421052631578947, "grad_norm": 0.03814585189064516, "learning_rate": 7.190542927867234e-05, "loss": 0.0242, "step": 112 }, { "epoch": 0.849624060150376, "grad_norm": 0.03553642928460275, "learning_rate": 7.131274906557725e-05, "loss": 0.0277, "step": 113 }, { "epoch": 0.8571428571428571, "grad_norm": 0.044176381361140944, "learning_rate": 7.071638639991207e-05, "loss": 0.0282, "step": 114 }, { "epoch": 0.8646616541353384, "grad_norm": 0.04113727259330019, "learning_rate": 7.011644432221958e-05, "loss": 0.0311, "step": 115 }, { "epoch": 0.8721804511278195, "grad_norm": 0.060773829286428965, "learning_rate": 6.95130264914993e-05, "loss": 0.0414, "step": 116 }, { "epoch": 0.8796992481203008, "grad_norm": 0.05757846085257315, "learning_rate": 6.890623716729724e-05, "loss": 0.0279, "step": 117 }, { "epoch": 0.8872180451127819, "grad_norm": 0.08428255259620104, "learning_rate": 6.82961811916917e-05, "loss": 0.0298, "step": 118 }, { "epoch": 0.8947368421052632, "grad_norm": 0.04529601746123181, "learning_rate": 6.768296397117848e-05, "loss": 0.0263, "step": 119 }, { "epoch": 0.9022556390977443, "grad_norm": 0.0559976345746786, "learning_rate": 6.706669145845863e-05, "loss": 0.0331, "step": 120 }, { "epoch": 0.9097744360902256, "grad_norm": 0.046985300077111235, "learning_rate": 6.644747013413168e-05, "loss": 0.0323, "step": 121 }, { "epoch": 0.9172932330827067, "grad_norm": 0.06973194335422163, "learning_rate": 6.582540698829781e-05, "loss": 0.0356, "step": 122 }, { "epoch": 0.924812030075188, "grad_norm": 0.0550307651636393, "learning_rate": 6.520060950207185e-05, "loss": 0.0374, "step": 123 }, { "epoch": 0.9323308270676691, "grad_norm": 0.04136098377224926, "learning_rate": 6.457318562901256e-05, "loss": 0.0281, "step": 124 }, { "epoch": 0.9398496240601504, "grad_norm": 0.04471839673788357, "learning_rate": 6.394324377647028e-05, "loss": 0.0344, "step": 125 }, { "epoch": 0.9473684210526315, "grad_norm": 0.04057335071418551, "learning_rate": 6.331089278685599e-05, "loss": 0.0289, "step": 126 }, { "epoch": 0.9548872180451128, "grad_norm": 0.036632585834280834, "learning_rate": 6.26762419188355e-05, "loss": 0.0254, "step": 127 }, { "epoch": 0.9624060150375939, "grad_norm": 0.05253467833143005, "learning_rate": 6.203940082845144e-05, "loss": 0.0423, "step": 128 }, { "epoch": 0.9699248120300752, "grad_norm": 0.05828434847478486, "learning_rate": 6.140047955017671e-05, "loss": 0.0331, "step": 129 }, { "epoch": 0.9774436090225563, "grad_norm": 0.052528332979290625, "learning_rate": 6.075958847790262e-05, "loss": 0.0344, "step": 130 }, { "epoch": 0.9849624060150376, "grad_norm": 0.039125799054480936, "learning_rate": 6.011683834586473e-05, "loss": 0.0264, "step": 131 }, { "epoch": 0.9924812030075187, "grad_norm": 0.03707157930189228, "learning_rate": 5.947234020951015e-05, "loss": 0.0237, "step": 132 }, { "epoch": 1.0, "grad_norm": 0.054189982183542575, "learning_rate": 5.882620542630901e-05, "loss": 0.0317, "step": 133 }, { "epoch": 1.0075187969924813, "grad_norm": 0.04357846265860899, "learning_rate": 5.8178545636514145e-05, "loss": 0.0268, "step": 134 }, { "epoch": 1.0150375939849625, "grad_norm": 0.056012933476124856, "learning_rate": 5.752947274387147e-05, "loss": 0.0223, "step": 135 }, { "epoch": 1.0225563909774436, "grad_norm": 0.049689439936320044, "learning_rate": 5.687909889628529e-05, "loss": 0.0304, "step": 136 }, { "epoch": 1.0300751879699248, "grad_norm": 0.04830994322048754, "learning_rate": 5.622753646644102e-05, "loss": 0.0278, "step": 137 }, { "epoch": 1.037593984962406, "grad_norm": 0.04418639970975713, "learning_rate": 5.557489803238933e-05, "loss": 0.0259, "step": 138 }, { "epoch": 1.045112781954887, "grad_norm": 0.042738363591787835, "learning_rate": 5.492129635809473e-05, "loss": 0.0198, "step": 139 }, { "epoch": 1.0526315789473684, "grad_norm": 0.03885713180148723, "learning_rate": 5.426684437395196e-05, "loss": 0.0191, "step": 140 }, { "epoch": 1.0601503759398496, "grad_norm": 0.04951650926676435, "learning_rate": 5.361165515727374e-05, "loss": 0.0214, "step": 141 }, { "epoch": 1.0676691729323309, "grad_norm": 0.059968470212708236, "learning_rate": 5.295584191275308e-05, "loss": 0.0243, "step": 142 }, { "epoch": 1.0751879699248121, "grad_norm": 0.0676386940224187, "learning_rate": 5.229951795290353e-05, "loss": 0.029, "step": 143 }, { "epoch": 1.0827067669172932, "grad_norm": 0.04250436122379926, "learning_rate": 5.164279667848094e-05, "loss": 0.0204, "step": 144 }, { "epoch": 1.0902255639097744, "grad_norm": 0.04124846102938738, "learning_rate": 5.0985791558889785e-05, "loss": 0.0209, "step": 145 }, { "epoch": 1.0977443609022557, "grad_norm": 0.05914558229310168, "learning_rate": 5.032861611257783e-05, "loss": 0.0285, "step": 146 }, { "epoch": 1.1052631578947367, "grad_norm": 0.0465029543723527, "learning_rate": 4.967138388742218e-05, "loss": 0.0204, "step": 147 }, { "epoch": 1.112781954887218, "grad_norm": 0.06469458945659604, "learning_rate": 4.901420844111021e-05, "loss": 0.0314, "step": 148 }, { "epoch": 1.1203007518796992, "grad_norm": 0.06440915952496404, "learning_rate": 4.835720332151907e-05, "loss": 0.0281, "step": 149 }, { "epoch": 1.1278195488721805, "grad_norm": 0.0571757163158284, "learning_rate": 4.770048204709648e-05, "loss": 0.0248, "step": 150 }, { "epoch": 1.1353383458646618, "grad_norm": 0.05910301690921271, "learning_rate": 4.7044158087246926e-05, "loss": 0.0311, "step": 151 }, { "epoch": 1.1428571428571428, "grad_norm": 0.04613839631194596, "learning_rate": 4.6388344842726264e-05, "loss": 0.0218, "step": 152 }, { "epoch": 1.150375939849624, "grad_norm": 0.05741866552084954, "learning_rate": 4.5733155626048036e-05, "loss": 0.0271, "step": 153 }, { "epoch": 1.1578947368421053, "grad_norm": 0.04682544810113655, "learning_rate": 4.507870364190527e-05, "loss": 0.0264, "step": 154 }, { "epoch": 1.1654135338345863, "grad_norm": 0.06282838577083374, "learning_rate": 4.4425101967610674e-05, "loss": 0.024, "step": 155 }, { "epoch": 1.1729323308270676, "grad_norm": 0.05388737782363021, "learning_rate": 4.377246353355899e-05, "loss": 0.0271, "step": 156 }, { "epoch": 1.1804511278195489, "grad_norm": 0.05086578069156835, "learning_rate": 4.312090110371473e-05, "loss": 0.0278, "step": 157 }, { "epoch": 1.1879699248120301, "grad_norm": 0.05863572980738164, "learning_rate": 4.247052725612852e-05, "loss": 0.0292, "step": 158 }, { "epoch": 1.1954887218045114, "grad_norm": 0.04227523648124146, "learning_rate": 4.1821454363485866e-05, "loss": 0.0234, "step": 159 }, { "epoch": 1.2030075187969924, "grad_norm": 0.04268704545270105, "learning_rate": 4.1173794573690996e-05, "loss": 0.0206, "step": 160 }, { "epoch": 1.2105263157894737, "grad_norm": 0.04778787432486908, "learning_rate": 4.052765979048986e-05, "loss": 0.0227, "step": 161 }, { "epoch": 1.218045112781955, "grad_norm": 0.0459311125342993, "learning_rate": 3.988316165413528e-05, "loss": 0.0205, "step": 162 }, { "epoch": 1.225563909774436, "grad_norm": 0.05603215690118315, "learning_rate": 3.924041152209739e-05, "loss": 0.029, "step": 163 }, { "epoch": 1.2330827067669172, "grad_norm": 0.060179119443112154, "learning_rate": 3.859952044982329e-05, "loss": 0.0271, "step": 164 }, { "epoch": 1.2406015037593985, "grad_norm": 0.04740279415347567, "learning_rate": 3.7960599171548574e-05, "loss": 0.0213, "step": 165 }, { "epoch": 1.2481203007518797, "grad_norm": 0.052482110362426594, "learning_rate": 3.732375808116451e-05, "loss": 0.0258, "step": 166 }, { "epoch": 1.255639097744361, "grad_norm": 0.04835120393099329, "learning_rate": 3.668910721314402e-05, "loss": 0.0229, "step": 167 }, { "epoch": 1.263157894736842, "grad_norm": 0.08311507045185516, "learning_rate": 3.605675622352973e-05, "loss": 0.0265, "step": 168 }, { "epoch": 1.2706766917293233, "grad_norm": 0.053563077833150494, "learning_rate": 3.542681437098745e-05, "loss": 0.0256, "step": 169 }, { "epoch": 1.2781954887218046, "grad_norm": 0.05567682482783888, "learning_rate": 3.479939049792817e-05, "loss": 0.0213, "step": 170 }, { "epoch": 1.2857142857142856, "grad_norm": 0.054588031712222006, "learning_rate": 3.417459301170219e-05, "loss": 0.0266, "step": 171 }, { "epoch": 1.2932330827067668, "grad_norm": 0.07694344232267265, "learning_rate": 3.355252986586832e-05, "loss": 0.0193, "step": 172 }, { "epoch": 1.300751879699248, "grad_norm": 0.05943952613035603, "learning_rate": 3.293330854154136e-05, "loss": 0.0258, "step": 173 }, { "epoch": 1.3082706766917294, "grad_norm": 0.038766556860819104, "learning_rate": 3.2317036028821523e-05, "loss": 0.0159, "step": 174 }, { "epoch": 1.3157894736842106, "grad_norm": 0.05092188135687549, "learning_rate": 3.1703818808308324e-05, "loss": 0.0215, "step": 175 }, { "epoch": 1.3233082706766917, "grad_norm": 0.04779789780883562, "learning_rate": 3.109376283270277e-05, "loss": 0.0268, "step": 176 }, { "epoch": 1.330827067669173, "grad_norm": 0.04433720319245774, "learning_rate": 3.0486973508500727e-05, "loss": 0.0238, "step": 177 }, { "epoch": 1.3383458646616542, "grad_norm": 0.049878475563895956, "learning_rate": 2.988355567778043e-05, "loss": 0.0259, "step": 178 }, { "epoch": 1.3458646616541352, "grad_norm": 0.05962755604807658, "learning_rate": 2.9283613600087933e-05, "loss": 0.025, "step": 179 }, { "epoch": 1.3533834586466165, "grad_norm": 0.04955718527923681, "learning_rate": 2.8687250934422772e-05, "loss": 0.0194, "step": 180 }, { "epoch": 1.3609022556390977, "grad_norm": 0.03676456890831394, "learning_rate": 2.8094570721327662e-05, "loss": 0.0189, "step": 181 }, { "epoch": 1.368421052631579, "grad_norm": 0.04868946152583533, "learning_rate": 2.750567536508504e-05, "loss": 0.0243, "step": 182 }, { "epoch": 1.3759398496240602, "grad_norm": 0.0555305400721802, "learning_rate": 2.6920666616023327e-05, "loss": 0.0257, "step": 183 }, { "epoch": 1.3834586466165413, "grad_norm": 0.04963192556183434, "learning_rate": 2.6339645552936536e-05, "loss": 0.0275, "step": 184 }, { "epoch": 1.3909774436090225, "grad_norm": 0.05542091349920839, "learning_rate": 2.5762712565619528e-05, "loss": 0.023, "step": 185 }, { "epoch": 1.3984962406015038, "grad_norm": 0.0426183120843919, "learning_rate": 2.5189967337522573e-05, "loss": 0.0206, "step": 186 }, { "epoch": 1.4060150375939848, "grad_norm": 0.05205246245376388, "learning_rate": 2.46215088285279e-05, "loss": 0.0229, "step": 187 }, { "epoch": 1.413533834586466, "grad_norm": 0.04337666332691105, "learning_rate": 2.4057435257851175e-05, "loss": 0.019, "step": 188 }, { "epoch": 1.4210526315789473, "grad_norm": 0.05985729489503263, "learning_rate": 2.349784408707112e-05, "loss": 0.0274, "step": 189 }, { "epoch": 1.4285714285714286, "grad_norm": 0.062032022184375604, "learning_rate": 2.2942832003289823e-05, "loss": 0.0271, "step": 190 }, { "epoch": 1.4360902255639099, "grad_norm": 0.05773389436675615, "learning_rate": 2.2392494902427025e-05, "loss": 0.0263, "step": 191 }, { "epoch": 1.443609022556391, "grad_norm": 0.048522536078850126, "learning_rate": 2.1846927872651137e-05, "loss": 0.0242, "step": 192 }, { "epoch": 1.4511278195488722, "grad_norm": 0.05010560342148772, "learning_rate": 2.1306225177949585e-05, "loss": 0.024, "step": 193 }, { "epoch": 1.4586466165413534, "grad_norm": 0.058011679310299026, "learning_rate": 2.07704802418419e-05, "loss": 0.0301, "step": 194 }, { "epoch": 1.4661654135338344, "grad_norm": 0.052695628737558814, "learning_rate": 2.0239785631237705e-05, "loss": 0.0262, "step": 195 }, { "epoch": 1.4736842105263157, "grad_norm": 0.0397195089948912, "learning_rate": 1.9714233040442915e-05, "loss": 0.0179, "step": 196 }, { "epoch": 1.481203007518797, "grad_norm": 0.05532938780742867, "learning_rate": 1.9193913275316626e-05, "loss": 0.0234, "step": 197 }, { "epoch": 1.4887218045112782, "grad_norm": 0.07349266479809795, "learning_rate": 1.8678916237581522e-05, "loss": 0.0236, "step": 198 }, { "epoch": 1.4962406015037595, "grad_norm": 0.03995824607041351, "learning_rate": 1.816933090929055e-05, "loss": 0.0176, "step": 199 }, { "epoch": 1.5037593984962405, "grad_norm": 0.07166373724308431, "learning_rate": 1.7665245337452368e-05, "loss": 0.0258, "step": 200 }, { "epoch": 1.5037593984962405, "eval_loss": 0.029665347188711166, "eval_runtime": 6.5066, "eval_samples_per_second": 0.922, "eval_steps_per_second": 0.307, "step": 200 }, { "epoch": 1.5112781954887218, "grad_norm": 0.048692577901512116, "learning_rate": 1.716674661881848e-05, "loss": 0.0224, "step": 201 }, { "epoch": 1.518796992481203, "grad_norm": 0.04675059057360818, "learning_rate": 1.667392088483456e-05, "loss": 0.0223, "step": 202 }, { "epoch": 1.526315789473684, "grad_norm": 0.05459458244813264, "learning_rate": 1.6186853286758397e-05, "loss": 0.0242, "step": 203 }, { "epoch": 1.5338345864661656, "grad_norm": 0.051543551392068274, "learning_rate": 1.570562798094747e-05, "loss": 0.025, "step": 204 }, { "epoch": 1.5413533834586466, "grad_norm": 0.14671926401344376, "learning_rate": 1.5230328114318127e-05, "loss": 0.0241, "step": 205 }, { "epoch": 1.5488721804511278, "grad_norm": 0.058979726559234814, "learning_rate": 1.4761035809979395e-05, "loss": 0.0253, "step": 206 }, { "epoch": 1.556390977443609, "grad_norm": 0.06494643885270886, "learning_rate": 1.4297832153043656e-05, "loss": 0.0236, "step": 207 }, { "epoch": 1.5639097744360901, "grad_norm": 0.06627104647345526, "learning_rate": 1.3840797176616466e-05, "loss": 0.0278, "step": 208 }, { "epoch": 1.5714285714285714, "grad_norm": 0.06190650675134399, "learning_rate": 1.3390009847968504e-05, "loss": 0.0255, "step": 209 }, { "epoch": 1.5789473684210527, "grad_norm": 0.06250699899282167, "learning_rate": 1.2945548054891321e-05, "loss": 0.0254, "step": 210 }, { "epoch": 1.5864661654135337, "grad_norm": 0.06214391708977836, "learning_rate": 1.2507488592239847e-05, "loss": 0.0233, "step": 211 }, { "epoch": 1.5939849624060152, "grad_norm": 0.054608347620115995, "learning_rate": 1.2075907148663579e-05, "loss": 0.024, "step": 212 }, { "epoch": 1.6015037593984962, "grad_norm": 0.05333683650123989, "learning_rate": 1.1650878293528994e-05, "loss": 0.0261, "step": 213 }, { "epoch": 1.6090225563909775, "grad_norm": 0.047407562918454, "learning_rate": 1.1232475464035385e-05, "loss": 0.0192, "step": 214 }, { "epoch": 1.6165413533834587, "grad_norm": 0.06549580580637923, "learning_rate": 1.0820770952526155e-05, "loss": 0.0192, "step": 215 }, { "epoch": 1.6240601503759398, "grad_norm": 0.0582730317262946, "learning_rate": 1.0415835893998116e-05, "loss": 0.0267, "step": 216 }, { "epoch": 1.631578947368421, "grad_norm": 0.06724858724013988, "learning_rate": 1.0017740253810609e-05, "loss": 0.0244, "step": 217 }, { "epoch": 1.6390977443609023, "grad_norm": 0.07353126997097047, "learning_rate": 9.62655281559679e-06, "loss": 0.0265, "step": 218 }, { "epoch": 1.6466165413533833, "grad_norm": 0.057567868642984674, "learning_rate": 9.242341169379076e-06, "loss": 0.0239, "step": 219 }, { "epoch": 1.6541353383458648, "grad_norm": 0.06325334373179048, "learning_rate": 8.865171699890834e-06, "loss": 0.023, "step": 220 }, { "epoch": 1.6616541353383458, "grad_norm": 0.057849806459398294, "learning_rate": 8.49510957510633e-06, "loss": 0.0286, "step": 221 }, { "epoch": 1.669172932330827, "grad_norm": 0.06257054012996921, "learning_rate": 8.132218734980852e-06, "loss": 0.0205, "step": 222 }, { "epoch": 1.6766917293233083, "grad_norm": 0.053291552200528655, "learning_rate": 7.776561880403072e-06, "loss": 0.0222, "step": 223 }, { "epoch": 1.6842105263157894, "grad_norm": 0.055884993872003165, "learning_rate": 7.4282004623615396e-06, "loss": 0.0257, "step": 224 }, { "epoch": 1.6917293233082706, "grad_norm": 0.04781226703104293, "learning_rate": 7.0871946713269856e-06, "loss": 0.021, "step": 225 }, { "epoch": 1.699248120300752, "grad_norm": 0.04617454207758738, "learning_rate": 6.753603426852589e-06, "loss": 0.0206, "step": 226 }, { "epoch": 1.706766917293233, "grad_norm": 0.05934488856386534, "learning_rate": 6.427484367393699e-06, "loss": 0.0221, "step": 227 }, { "epoch": 1.7142857142857144, "grad_norm": 0.0563063349000768, "learning_rate": 6.108893840348995e-06, "loss": 0.0217, "step": 228 }, { "epoch": 1.7218045112781954, "grad_norm": 0.058919681414065804, "learning_rate": 5.797886892324694e-06, "loss": 0.0241, "step": 229 }, { "epoch": 1.7293233082706767, "grad_norm": 0.04652279001651371, "learning_rate": 5.494517259623477e-06, "loss": 0.023, "step": 230 }, { "epoch": 1.736842105263158, "grad_norm": 0.05206753304811755, "learning_rate": 5.198837358959901e-06, "loss": 0.0247, "step": 231 }, { "epoch": 1.744360902255639, "grad_norm": 0.05759411719610633, "learning_rate": 4.910898278403669e-06, "loss": 0.0275, "step": 232 }, { "epoch": 1.7518796992481203, "grad_norm": 0.05493938568305548, "learning_rate": 4.630749768552589e-06, "loss": 0.0236, "step": 233 }, { "epoch": 1.7593984962406015, "grad_norm": 0.045214515268897214, "learning_rate": 4.358440233936617e-06, "loss": 0.0196, "step": 234 }, { "epoch": 1.7669172932330826, "grad_norm": 0.08670874372319154, "learning_rate": 4.094016724654359e-06, "loss": 0.0292, "step": 235 }, { "epoch": 1.774436090225564, "grad_norm": 0.049117351787292686, "learning_rate": 3.837524928243774e-06, "loss": 0.0224, "step": 236 }, { "epoch": 1.781954887218045, "grad_norm": 0.058397389390063136, "learning_rate": 3.589009161788104e-06, "loss": 0.0278, "step": 237 }, { "epoch": 1.7894736842105263, "grad_norm": 0.05422155962388968, "learning_rate": 3.3485123642587658e-06, "loss": 0.0243, "step": 238 }, { "epoch": 1.7969924812030076, "grad_norm": 0.07090059571835504, "learning_rate": 3.116076089096265e-06, "loss": 0.027, "step": 239 }, { "epoch": 1.8045112781954886, "grad_norm": 0.05963059250846481, "learning_rate": 2.8917404970305097e-06, "loss": 0.0288, "step": 240 }, { "epoch": 1.8120300751879699, "grad_norm": 0.06946365704174999, "learning_rate": 2.675544349141779e-06, "loss": 0.0259, "step": 241 }, { "epoch": 1.8195488721804511, "grad_norm": 0.06143740644726876, "learning_rate": 2.4675250001635232e-06, "loss": 0.0247, "step": 242 }, { "epoch": 1.8270676691729322, "grad_norm": 0.04728168437977354, "learning_rate": 2.2677183920281343e-06, "loss": 0.0193, "step": 243 }, { "epoch": 1.8345864661654137, "grad_norm": 0.07042127314230426, "learning_rate": 2.076159047656889e-06, "loss": 0.0227, "step": 244 }, { "epoch": 1.8421052631578947, "grad_norm": 0.05266415047166696, "learning_rate": 1.892880064994934e-06, "loss": 0.0256, "step": 245 }, { "epoch": 1.849624060150376, "grad_norm": 0.05204878417509025, "learning_rate": 1.7179131112926627e-06, "loss": 0.024, "step": 246 }, { "epoch": 1.8571428571428572, "grad_norm": 0.04727065912696429, "learning_rate": 1.551288417634106e-06, "loss": 0.0159, "step": 247 }, { "epoch": 1.8646616541353382, "grad_norm": 0.049637487718030344, "learning_rate": 1.3930347737136196e-06, "loss": 0.0209, "step": 248 }, { "epoch": 1.8721804511278195, "grad_norm": 0.0505669836884092, "learning_rate": 1.2431795228615372e-06, "loss": 0.0206, "step": 249 }, { "epoch": 1.8796992481203008, "grad_norm": 0.07557073448805833, "learning_rate": 1.101748557319715e-06, "loss": 0.0315, "step": 250 }, { "epoch": 1.8872180451127818, "grad_norm": 0.04855407299966349, "learning_rate": 9.687663137678604e-07, "loss": 0.0193, "step": 251 }, { "epoch": 1.8947368421052633, "grad_norm": 0.05981871688003821, "learning_rate": 8.442557691013043e-07, "loss": 0.0245, "step": 252 }, { "epoch": 1.9022556390977443, "grad_norm": 0.055297053623164526, "learning_rate": 7.282384364610206e-07, "loss": 0.0242, "step": 253 }, { "epoch": 1.9097744360902256, "grad_norm": 0.05097924138111233, "learning_rate": 6.207343615165561e-07, "loss": 0.0207, "step": 254 }, { "epoch": 1.9172932330827068, "grad_norm": 0.05870296620626846, "learning_rate": 5.217621190024779e-07, "loss": 0.0259, "step": 255 }, { "epoch": 1.9248120300751879, "grad_norm": 0.05289043509456049, "learning_rate": 4.3133880950905205e-07, "loss": 0.0217, "step": 256 }, { "epoch": 1.9323308270676691, "grad_norm": 0.05040687502136238, "learning_rate": 3.494800565275125e-07, "loss": 0.0226, "step": 257 }, { "epoch": 1.9398496240601504, "grad_norm": 0.05483598628420617, "learning_rate": 2.762000037506485e-07, "loss": 0.0226, "step": 258 }, { "epoch": 1.9473684210526314, "grad_norm": 0.052171052589092846, "learning_rate": 2.115113126290258e-07, "loss": 0.0224, "step": 259 }, { "epoch": 1.954887218045113, "grad_norm": 0.060066029686361856, "learning_rate": 1.554251601833201e-07, "loss": 0.0242, "step": 260 }, { "epoch": 1.962406015037594, "grad_norm": 0.04560282840465627, "learning_rate": 1.0795123707312283e-07, "loss": 0.0199, "step": 261 }, { "epoch": 1.9699248120300752, "grad_norm": 0.055943707431487216, "learning_rate": 6.909774592258056e-08, "loss": 0.0218, "step": 262 }, { "epoch": 1.9774436090225564, "grad_norm": 0.057987573660367824, "learning_rate": 3.8871399903134265e-08, "loss": 0.0242, "step": 263 }, { "epoch": 1.9849624060150375, "grad_norm": 0.05438020219150765, "learning_rate": 1.7277421573608232e-08, "loss": 0.0278, "step": 264 }, { "epoch": 1.9924812030075187, "grad_norm": 0.05442881774912085, "learning_rate": 4.319541977831909e-09, "loss": 0.0193, "step": 265 }, { "epoch": 2.0, "grad_norm": 0.059490023866208885, "learning_rate": 0.0, "loss": 0.0224, "step": 266 }, { "epoch": 2.0, "step": 266, "total_flos": 673614818967552.0, "train_loss": 0.039493271835932604, "train_runtime": 2026.6163, "train_samples_per_second": 0.522, "train_steps_per_second": 0.131 } ], "logging_steps": 1, "max_steps": 266, "num_input_tokens_seen": 0, "num_train_epochs": 2, "save_steps": 300, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 673614818967552.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }