{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 279, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.010752688172043012, "grad_norm": 5.117406670103657, "learning_rate": 0.0, "loss": 0.8565, "step": 1 }, { "epoch": 0.021505376344086023, "grad_norm": 3.932349183270455, "learning_rate": 3.5714285714285716e-07, "loss": 0.7654, "step": 2 }, { "epoch": 0.03225806451612903, "grad_norm": 4.430618628715762, "learning_rate": 7.142857142857143e-07, "loss": 0.8602, "step": 3 }, { "epoch": 0.043010752688172046, "grad_norm": 4.629935061064256, "learning_rate": 1.0714285714285714e-06, "loss": 0.8179, "step": 4 }, { "epoch": 0.053763440860215055, "grad_norm": 4.607689206667246, "learning_rate": 1.4285714285714286e-06, "loss": 0.7984, "step": 5 }, { "epoch": 0.06451612903225806, "grad_norm": 4.470859498641417, "learning_rate": 1.7857142857142859e-06, "loss": 0.8393, "step": 6 }, { "epoch": 0.07526881720430108, "grad_norm": 3.615495688035928, "learning_rate": 2.1428571428571427e-06, "loss": 0.7408, "step": 7 }, { "epoch": 0.08602150537634409, "grad_norm": 3.6184582310708753, "learning_rate": 2.5e-06, "loss": 0.7991, "step": 8 }, { "epoch": 0.0967741935483871, "grad_norm": 3.5286647768187804, "learning_rate": 2.8571428571428573e-06, "loss": 0.7439, "step": 9 }, { "epoch": 0.10752688172043011, "grad_norm": 3.2631493323575773, "learning_rate": 3.2142857142857147e-06, "loss": 0.7656, "step": 10 }, { "epoch": 0.11827956989247312, "grad_norm": 1.9183483696552464, "learning_rate": 3.5714285714285718e-06, "loss": 0.6424, "step": 11 }, { "epoch": 0.12903225806451613, "grad_norm": 2.5758188598022036, "learning_rate": 3.928571428571429e-06, "loss": 0.6746, "step": 12 }, { "epoch": 0.13978494623655913, "grad_norm": 2.711107640562582, "learning_rate": 4.2857142857142855e-06, "loss": 0.6786, "step": 13 }, { "epoch": 0.15053763440860216, "grad_norm": 2.2557127395574335, "learning_rate": 4.642857142857144e-06, "loss": 0.6464, "step": 14 }, { "epoch": 0.16129032258064516, "grad_norm": 2.08589822549775, "learning_rate": 5e-06, "loss": 0.5924, "step": 15 }, { "epoch": 0.17204301075268819, "grad_norm": 2.442258395861131, "learning_rate": 5.357142857142857e-06, "loss": 0.6771, "step": 16 }, { "epoch": 0.1827956989247312, "grad_norm": 2.4088790285819353, "learning_rate": 5.7142857142857145e-06, "loss": 0.6609, "step": 17 }, { "epoch": 0.1935483870967742, "grad_norm": 2.599278835350385, "learning_rate": 6.071428571428571e-06, "loss": 0.665, "step": 18 }, { "epoch": 0.20430107526881722, "grad_norm": 2.135693738895623, "learning_rate": 6.4285714285714295e-06, "loss": 0.5946, "step": 19 }, { "epoch": 0.21505376344086022, "grad_norm": 2.0880720029245343, "learning_rate": 6.785714285714287e-06, "loss": 0.6027, "step": 20 }, { "epoch": 0.22580645161290322, "grad_norm": 1.7878249901331582, "learning_rate": 7.1428571428571436e-06, "loss": 0.6523, "step": 21 }, { "epoch": 0.23655913978494625, "grad_norm": 1.8499308052576442, "learning_rate": 7.500000000000001e-06, "loss": 0.5775, "step": 22 }, { "epoch": 0.24731182795698925, "grad_norm": 1.545055962271408, "learning_rate": 7.857142857142858e-06, "loss": 0.5343, "step": 23 }, { "epoch": 0.25806451612903225, "grad_norm": 1.5990557909426337, "learning_rate": 8.214285714285714e-06, "loss": 0.6303, "step": 24 }, { "epoch": 0.26881720430107525, "grad_norm": 1.5047883914372557, "learning_rate": 8.571428571428571e-06, "loss": 0.5673, "step": 25 }, { "epoch": 0.27956989247311825, "grad_norm": 1.660959104374015, "learning_rate": 8.92857142857143e-06, "loss": 0.5834, "step": 26 }, { "epoch": 0.2903225806451613, "grad_norm": 1.4855731115284816, "learning_rate": 9.285714285714288e-06, "loss": 0.5861, "step": 27 }, { "epoch": 0.3010752688172043, "grad_norm": 1.5890489850514156, "learning_rate": 9.642857142857144e-06, "loss": 0.58, "step": 28 }, { "epoch": 0.3118279569892473, "grad_norm": 1.3375504302217296, "learning_rate": 1e-05, "loss": 0.5669, "step": 29 }, { "epoch": 0.3225806451612903, "grad_norm": 1.4010773743864648, "learning_rate": 9.999608360361114e-06, "loss": 0.551, "step": 30 }, { "epoch": 0.3333333333333333, "grad_norm": 1.3303386154338483, "learning_rate": 9.998433502797097e-06, "loss": 0.6109, "step": 31 }, { "epoch": 0.34408602150537637, "grad_norm": 1.3895786100086411, "learning_rate": 9.996475611356265e-06, "loss": 0.5155, "step": 32 }, { "epoch": 0.3548387096774194, "grad_norm": 1.211244402418308, "learning_rate": 9.993734992753777e-06, "loss": 0.5167, "step": 33 }, { "epoch": 0.3655913978494624, "grad_norm": 1.205621464067494, "learning_rate": 9.990212076323587e-06, "loss": 0.626, "step": 34 }, { "epoch": 0.3763440860215054, "grad_norm": 1.281327619636724, "learning_rate": 9.98590741395118e-06, "loss": 0.5301, "step": 35 }, { "epoch": 0.3870967741935484, "grad_norm": 1.4425953234642075, "learning_rate": 9.980821679987125e-06, "loss": 0.5705, "step": 36 }, { "epoch": 0.3978494623655914, "grad_norm": 1.3476830260596382, "learning_rate": 9.974955671141425e-06, "loss": 0.5742, "step": 37 }, { "epoch": 0.40860215053763443, "grad_norm": 1.3027265736180367, "learning_rate": 9.968310306358715e-06, "loss": 0.5443, "step": 38 }, { "epoch": 0.41935483870967744, "grad_norm": 1.3618324591712858, "learning_rate": 9.960886626674302e-06, "loss": 0.6328, "step": 39 }, { "epoch": 0.43010752688172044, "grad_norm": 1.3924706399344635, "learning_rate": 9.952685795051078e-06, "loss": 0.531, "step": 40 }, { "epoch": 0.44086021505376344, "grad_norm": 1.3681689870094362, "learning_rate": 9.943709096197334e-06, "loss": 0.5771, "step": 41 }, { "epoch": 0.45161290322580644, "grad_norm": 1.169520090357751, "learning_rate": 9.933957936365515e-06, "loss": 0.6155, "step": 42 }, { "epoch": 0.46236559139784944, "grad_norm": 1.2592535480126792, "learning_rate": 9.9234338431319e-06, "loss": 0.5614, "step": 43 }, { "epoch": 0.4731182795698925, "grad_norm": 1.188489938742699, "learning_rate": 9.912138465157325e-06, "loss": 0.5821, "step": 44 }, { "epoch": 0.4838709677419355, "grad_norm": 1.1821647113837632, "learning_rate": 9.900073571928887e-06, "loss": 0.5793, "step": 45 }, { "epoch": 0.4946236559139785, "grad_norm": 1.363884821931327, "learning_rate": 9.887241053482756e-06, "loss": 0.5629, "step": 46 }, { "epoch": 0.5053763440860215, "grad_norm": 1.3092899719841664, "learning_rate": 9.87364292010809e-06, "loss": 0.5235, "step": 47 }, { "epoch": 0.5161290322580645, "grad_norm": 1.3352852678722897, "learning_rate": 9.859281302032107e-06, "loss": 0.5151, "step": 48 }, { "epoch": 0.5268817204301075, "grad_norm": 1.2505866887814554, "learning_rate": 9.844158449086372e-06, "loss": 0.5452, "step": 49 }, { "epoch": 0.5376344086021505, "grad_norm": 1.4936981012829829, "learning_rate": 9.828276730354353e-06, "loss": 0.5463, "step": 50 }, { "epoch": 0.5483870967741935, "grad_norm": 1.2994897728299255, "learning_rate": 9.811638633800287e-06, "loss": 0.524, "step": 51 }, { "epoch": 0.5591397849462365, "grad_norm": 1.1528734529208322, "learning_rate": 9.794246765879421e-06, "loss": 0.5134, "step": 52 }, { "epoch": 0.5698924731182796, "grad_norm": 1.3662191872593852, "learning_rate": 9.776103851129706e-06, "loss": 0.5074, "step": 53 }, { "epoch": 0.5806451612903226, "grad_norm": 1.3197245386738852, "learning_rate": 9.757212731744973e-06, "loss": 0.4936, "step": 54 }, { "epoch": 0.5913978494623656, "grad_norm": 1.1826061568448532, "learning_rate": 9.737576367129694e-06, "loss": 0.5291, "step": 55 }, { "epoch": 0.6021505376344086, "grad_norm": 1.2279962807050635, "learning_rate": 9.717197833435367e-06, "loss": 0.5401, "step": 56 }, { "epoch": 0.6129032258064516, "grad_norm": 1.1622891891860894, "learning_rate": 9.696080323078621e-06, "loss": 0.5341, "step": 57 }, { "epoch": 0.6236559139784946, "grad_norm": 1.15595461480515, "learning_rate": 9.67422714424111e-06, "loss": 0.4811, "step": 58 }, { "epoch": 0.6344086021505376, "grad_norm": 1.1381808394142663, "learning_rate": 9.651641720351262e-06, "loss": 0.5126, "step": 59 }, { "epoch": 0.6451612903225806, "grad_norm": 1.2816655929131089, "learning_rate": 9.628327589547977e-06, "loss": 0.5147, "step": 60 }, { "epoch": 0.6559139784946236, "grad_norm": 1.176343266853311, "learning_rate": 9.604288404126362e-06, "loss": 0.533, "step": 61 }, { "epoch": 0.6666666666666666, "grad_norm": 1.3546093456513846, "learning_rate": 9.579527929965581e-06, "loss": 0.5972, "step": 62 }, { "epoch": 0.6774193548387096, "grad_norm": 1.3159036668873394, "learning_rate": 9.554050045938893e-06, "loss": 0.5211, "step": 63 }, { "epoch": 0.6881720430107527, "grad_norm": 1.3256416815543717, "learning_rate": 9.52785874330602e-06, "loss": 0.5664, "step": 64 }, { "epoch": 0.6989247311827957, "grad_norm": 1.137833912080069, "learning_rate": 9.500958125087882e-06, "loss": 0.52, "step": 65 }, { "epoch": 0.7096774193548387, "grad_norm": 1.3219928059082766, "learning_rate": 9.473352405423845e-06, "loss": 0.5192, "step": 66 }, { "epoch": 0.7204301075268817, "grad_norm": 1.2000849146820651, "learning_rate": 9.445045908911536e-06, "loss": 0.5093, "step": 67 }, { "epoch": 0.7311827956989247, "grad_norm": 1.0948499067842512, "learning_rate": 9.416043069929389e-06, "loss": 0.4891, "step": 68 }, { "epoch": 0.7419354838709677, "grad_norm": 1.1326577666179933, "learning_rate": 9.386348431941953e-06, "loss": 0.4979, "step": 69 }, { "epoch": 0.7526881720430108, "grad_norm": 1.1971786924652708, "learning_rate": 9.355966646788152e-06, "loss": 0.4716, "step": 70 }, { "epoch": 0.7634408602150538, "grad_norm": 1.1712532314666788, "learning_rate": 9.324902473952529e-06, "loss": 0.4697, "step": 71 }, { "epoch": 0.7741935483870968, "grad_norm": 1.174242198418526, "learning_rate": 9.293160779819658e-06, "loss": 0.5306, "step": 72 }, { "epoch": 0.7849462365591398, "grad_norm": 1.2287418966719115, "learning_rate": 9.260746536911792e-06, "loss": 0.5267, "step": 73 }, { "epoch": 0.7956989247311828, "grad_norm": 1.3303630719030897, "learning_rate": 9.227664823109884e-06, "loss": 0.5243, "step": 74 }, { "epoch": 0.8064516129032258, "grad_norm": 1.3096448496558815, "learning_rate": 9.193920820858113e-06, "loss": 0.4986, "step": 75 }, { "epoch": 0.8172043010752689, "grad_norm": 1.3030805645002468, "learning_rate": 9.159519816352021e-06, "loss": 0.5732, "step": 76 }, { "epoch": 0.8279569892473119, "grad_norm": 1.2151108401849033, "learning_rate": 9.124467198710401e-06, "loss": 0.5374, "step": 77 }, { "epoch": 0.8387096774193549, "grad_norm": 1.2507532704479085, "learning_rate": 9.08876845913106e-06, "loss": 0.5251, "step": 78 }, { "epoch": 0.8494623655913979, "grad_norm": 1.397611316956257, "learning_rate": 9.052429190030589e-06, "loss": 0.5325, "step": 79 }, { "epoch": 0.8602150537634409, "grad_norm": 1.2260544279462335, "learning_rate": 9.015455084168279e-06, "loss": 0.5008, "step": 80 }, { "epoch": 0.8709677419354839, "grad_norm": 1.219464661892977, "learning_rate": 8.977851933754317e-06, "loss": 0.5294, "step": 81 }, { "epoch": 0.8817204301075269, "grad_norm": 1.2576277212991538, "learning_rate": 8.939625629542401e-06, "loss": 0.5065, "step": 82 }, { "epoch": 0.8924731182795699, "grad_norm": 1.2231909063495303, "learning_rate": 8.900782159906927e-06, "loss": 0.5577, "step": 83 }, { "epoch": 0.9032258064516129, "grad_norm": 1.240487970070817, "learning_rate": 8.861327609904859e-06, "loss": 0.5607, "step": 84 }, { "epoch": 0.9139784946236559, "grad_norm": 1.1803222245984772, "learning_rate": 8.821268160322482e-06, "loss": 0.4559, "step": 85 }, { "epoch": 0.9247311827956989, "grad_norm": 1.1172971063227777, "learning_rate": 8.780610086707149e-06, "loss": 0.4524, "step": 86 }, { "epoch": 0.9354838709677419, "grad_norm": 1.1952992924028192, "learning_rate": 8.739359758384162e-06, "loss": 0.5183, "step": 87 }, { "epoch": 0.946236559139785, "grad_norm": 1.2423449341948143, "learning_rate": 8.697523637458997e-06, "loss": 0.6781, "step": 88 }, { "epoch": 0.956989247311828, "grad_norm": 1.223456106162861, "learning_rate": 8.655108277804975e-06, "loss": 0.4719, "step": 89 }, { "epoch": 0.967741935483871, "grad_norm": 1.2180325223266957, "learning_rate": 8.612120324036548e-06, "loss": 0.5298, "step": 90 }, { "epoch": 0.978494623655914, "grad_norm": 1.1908812611967874, "learning_rate": 8.568566510468392e-06, "loss": 0.4908, "step": 91 }, { "epoch": 0.989247311827957, "grad_norm": 1.1329246631137397, "learning_rate": 8.524453660060434e-06, "loss": 0.4884, "step": 92 }, { "epoch": 1.0, "grad_norm": 1.1739661223625193, "learning_rate": 8.479788683348996e-06, "loss": 0.5282, "step": 93 }, { "epoch": 1.010752688172043, "grad_norm": 1.2895603002016933, "learning_rate": 8.434578577364218e-06, "loss": 0.4053, "step": 94 }, { "epoch": 1.021505376344086, "grad_norm": 1.2372418394561484, "learning_rate": 8.388830424533935e-06, "loss": 0.337, "step": 95 }, { "epoch": 1.032258064516129, "grad_norm": 1.1718375574305269, "learning_rate": 8.342551391574165e-06, "loss": 0.3569, "step": 96 }, { "epoch": 1.043010752688172, "grad_norm": 1.2444221432485463, "learning_rate": 8.295748728366414e-06, "loss": 0.3488, "step": 97 }, { "epoch": 1.053763440860215, "grad_norm": 1.5344510346454978, "learning_rate": 8.248429766821925e-06, "loss": 0.387, "step": 98 }, { "epoch": 1.064516129032258, "grad_norm": 1.83437388566894, "learning_rate": 8.200601919733106e-06, "loss": 0.3476, "step": 99 }, { "epoch": 1.075268817204301, "grad_norm": 1.1645823937573538, "learning_rate": 8.15227267961226e-06, "loss": 0.338, "step": 100 }, { "epoch": 1.086021505376344, "grad_norm": 1.07943356765298, "learning_rate": 8.10344961751785e-06, "loss": 0.3756, "step": 101 }, { "epoch": 1.096774193548387, "grad_norm": 1.136359022672489, "learning_rate": 8.054140381868435e-06, "loss": 0.3643, "step": 102 }, { "epoch": 1.10752688172043, "grad_norm": 1.1334256185564782, "learning_rate": 8.004352697244516e-06, "loss": 0.3537, "step": 103 }, { "epoch": 1.118279569892473, "grad_norm": 1.272152321916641, "learning_rate": 7.954094363178421e-06, "loss": 0.3851, "step": 104 }, { "epoch": 1.129032258064516, "grad_norm": 1.6926984652817842, "learning_rate": 7.903373252932474e-06, "loss": 0.3236, "step": 105 }, { "epoch": 1.139784946236559, "grad_norm": 1.1769426909749126, "learning_rate": 7.852197312265592e-06, "loss": 0.4107, "step": 106 }, { "epoch": 1.1505376344086022, "grad_norm": 1.2179134329370982, "learning_rate": 7.800574558188548e-06, "loss": 0.3655, "step": 107 }, { "epoch": 1.1612903225806452, "grad_norm": 1.1914193859243891, "learning_rate": 7.748513077708044e-06, "loss": 0.319, "step": 108 }, { "epoch": 1.1720430107526882, "grad_norm": 1.1623447008406969, "learning_rate": 7.69602102655985e-06, "loss": 0.3257, "step": 109 }, { "epoch": 1.1827956989247312, "grad_norm": 1.219276989748195, "learning_rate": 7.643106627931148e-06, "loss": 0.5513, "step": 110 }, { "epoch": 1.1935483870967742, "grad_norm": 1.246553411484507, "learning_rate": 7.5897781711723215e-06, "loss": 0.3581, "step": 111 }, { "epoch": 1.2043010752688172, "grad_norm": 1.1736474380398347, "learning_rate": 7.536044010498396e-06, "loss": 0.3513, "step": 112 }, { "epoch": 1.2150537634408602, "grad_norm": 1.2797115429626638, "learning_rate": 7.48191256368028e-06, "loss": 0.3443, "step": 113 }, { "epoch": 1.2258064516129032, "grad_norm": 1.197978350617973, "learning_rate": 7.427392310726088e-06, "loss": 0.3603, "step": 114 }, { "epoch": 1.2365591397849462, "grad_norm": 1.1727521029345562, "learning_rate": 7.372491792552694e-06, "loss": 0.3738, "step": 115 }, { "epoch": 1.2473118279569892, "grad_norm": 1.1707826597566307, "learning_rate": 7.31721960964774e-06, "loss": 0.3881, "step": 116 }, { "epoch": 1.2580645161290323, "grad_norm": 1.2094231500149508, "learning_rate": 7.261584420722328e-06, "loss": 0.5288, "step": 117 }, { "epoch": 1.2688172043010753, "grad_norm": 1.1809429787295744, "learning_rate": 7.20559494135458e-06, "loss": 0.3781, "step": 118 }, { "epoch": 1.2795698924731183, "grad_norm": 1.1434463967884962, "learning_rate": 7.149259942624287e-06, "loss": 0.3717, "step": 119 }, { "epoch": 1.2903225806451613, "grad_norm": 1.1430462929379024, "learning_rate": 7.092588249738871e-06, "loss": 0.373, "step": 120 }, { "epoch": 1.3010752688172043, "grad_norm": 1.4627760719280838, "learning_rate": 7.03558874065087e-06, "loss": 0.3809, "step": 121 }, { "epoch": 1.3118279569892473, "grad_norm": 1.182317091439007, "learning_rate": 6.978270344667143e-06, "loss": 0.3583, "step": 122 }, { "epoch": 1.3225806451612903, "grad_norm": 1.243697527950775, "learning_rate": 6.920642041050055e-06, "loss": 0.3207, "step": 123 }, { "epoch": 1.3333333333333333, "grad_norm": 1.2759794387408534, "learning_rate": 6.862712857610812e-06, "loss": 0.3633, "step": 124 }, { "epoch": 1.3440860215053765, "grad_norm": 1.1295106977198248, "learning_rate": 6.804491869295207e-06, "loss": 0.4274, "step": 125 }, { "epoch": 1.3548387096774195, "grad_norm": 1.1901126832185107, "learning_rate": 6.745988196761976e-06, "loss": 0.3779, "step": 126 }, { "epoch": 1.3655913978494625, "grad_norm": 1.3373142316442945, "learning_rate": 6.687211004953992e-06, "loss": 0.3618, "step": 127 }, { "epoch": 1.3763440860215055, "grad_norm": 1.116240494926489, "learning_rate": 6.628169501662527e-06, "loss": 0.3347, "step": 128 }, { "epoch": 1.3870967741935485, "grad_norm": 1.3073080378383377, "learning_rate": 6.568872936084789e-06, "loss": 0.3924, "step": 129 }, { "epoch": 1.3978494623655915, "grad_norm": 1.1658881438715565, "learning_rate": 6.509330597374993e-06, "loss": 0.3349, "step": 130 }, { "epoch": 1.4086021505376345, "grad_norm": 1.3285197694874702, "learning_rate": 6.44955181318915e-06, "loss": 0.383, "step": 131 }, { "epoch": 1.4193548387096775, "grad_norm": 1.1421963318126769, "learning_rate": 6.389545948223841e-06, "loss": 0.35, "step": 132 }, { "epoch": 1.4301075268817205, "grad_norm": 1.1800566601708844, "learning_rate": 6.329322402749181e-06, "loss": 0.36, "step": 133 }, { "epoch": 1.4408602150537635, "grad_norm": 1.181427392470128, "learning_rate": 6.2688906111362115e-06, "loss": 0.366, "step": 134 }, { "epoch": 1.4516129032258065, "grad_norm": 1.155888875463247, "learning_rate": 6.208260040378946e-06, "loss": 0.3497, "step": 135 }, { "epoch": 1.4623655913978495, "grad_norm": 1.1786815694111499, "learning_rate": 6.147440188611324e-06, "loss": 0.3537, "step": 136 }, { "epoch": 1.4731182795698925, "grad_norm": 1.2051193700127212, "learning_rate": 6.0864405836192575e-06, "loss": 0.3527, "step": 137 }, { "epoch": 1.4838709677419355, "grad_norm": 1.2284826404113511, "learning_rate": 6.025270781348055e-06, "loss": 0.3378, "step": 138 }, { "epoch": 1.4946236559139785, "grad_norm": 1.247829453357803, "learning_rate": 5.963940364405425e-06, "loss": 0.3696, "step": 139 }, { "epoch": 1.5053763440860215, "grad_norm": 1.201613514704844, "learning_rate": 5.902458940560304e-06, "loss": 0.3738, "step": 140 }, { "epoch": 1.5161290322580645, "grad_norm": 1.169777798872826, "learning_rate": 5.8408361412377475e-06, "loss": 0.3335, "step": 141 }, { "epoch": 1.5268817204301075, "grad_norm": 1.122966037731356, "learning_rate": 5.779081620010104e-06, "loss": 0.3232, "step": 142 }, { "epoch": 1.5376344086021505, "grad_norm": 1.194793658559918, "learning_rate": 5.717205051084731e-06, "loss": 0.3392, "step": 143 }, { "epoch": 1.5483870967741935, "grad_norm": 1.2783006705254338, "learning_rate": 5.655216127788472e-06, "loss": 0.3711, "step": 144 }, { "epoch": 1.5591397849462365, "grad_norm": 1.128328576854692, "learning_rate": 5.593124561049141e-06, "loss": 0.3435, "step": 145 }, { "epoch": 1.5698924731182795, "grad_norm": 1.191976250642684, "learning_rate": 5.530940077874248e-06, "loss": 0.3617, "step": 146 }, { "epoch": 1.5806451612903225, "grad_norm": 1.1652853933490293, "learning_rate": 5.468672419827208e-06, "loss": 0.3399, "step": 147 }, { "epoch": 1.5913978494623655, "grad_norm": 1.0915560758197622, "learning_rate": 5.406331341501264e-06, "loss": 0.339, "step": 148 }, { "epoch": 1.6021505376344085, "grad_norm": 1.1053574420353864, "learning_rate": 5.34392660899138e-06, "loss": 0.3207, "step": 149 }, { "epoch": 1.6129032258064515, "grad_norm": 1.1460690041968786, "learning_rate": 5.281467998364314e-06, "loss": 0.3308, "step": 150 }, { "epoch": 1.6236559139784945, "grad_norm": 1.1570813052418365, "learning_rate": 5.218965294127155e-06, "loss": 0.3501, "step": 151 }, { "epoch": 1.6344086021505375, "grad_norm": 1.2691321046241564, "learning_rate": 5.156428287694508e-06, "loss": 0.3542, "step": 152 }, { "epoch": 1.6451612903225805, "grad_norm": 1.1765795742693084, "learning_rate": 5.093866775854618e-06, "loss": 0.334, "step": 153 }, { "epoch": 1.6559139784946235, "grad_norm": 1.114227715473016, "learning_rate": 5.03129055923465e-06, "loss": 0.3124, "step": 154 }, { "epoch": 1.6666666666666665, "grad_norm": 1.2728424503735456, "learning_rate": 4.968709440765352e-06, "loss": 0.3608, "step": 155 }, { "epoch": 1.6774193548387095, "grad_norm": 1.2957106875665612, "learning_rate": 4.906133224145384e-06, "loss": 0.4535, "step": 156 }, { "epoch": 1.6881720430107527, "grad_norm": 1.1832693336037738, "learning_rate": 4.843571712305493e-06, "loss": 0.347, "step": 157 }, { "epoch": 1.6989247311827957, "grad_norm": 1.1976541159478242, "learning_rate": 4.781034705872846e-06, "loss": 0.3429, "step": 158 }, { "epoch": 1.7096774193548387, "grad_norm": 1.1965466685156962, "learning_rate": 4.7185320016356865e-06, "loss": 0.353, "step": 159 }, { "epoch": 1.7204301075268817, "grad_norm": 1.3091493751262704, "learning_rate": 4.656073391008622e-06, "loss": 0.3955, "step": 160 }, { "epoch": 1.7311827956989247, "grad_norm": 1.1853179338764237, "learning_rate": 4.593668658498737e-06, "loss": 0.3522, "step": 161 }, { "epoch": 1.7419354838709677, "grad_norm": 1.0940886869833208, "learning_rate": 4.531327580172794e-06, "loss": 0.3609, "step": 162 }, { "epoch": 1.7526881720430108, "grad_norm": 1.241588019056234, "learning_rate": 4.469059922125753e-06, "loss": 0.3518, "step": 163 }, { "epoch": 1.7634408602150538, "grad_norm": 1.3864224154338305, "learning_rate": 4.4068754389508616e-06, "loss": 0.4151, "step": 164 }, { "epoch": 1.7741935483870968, "grad_norm": 1.2098619933759385, "learning_rate": 4.34478387221153e-06, "loss": 0.348, "step": 165 }, { "epoch": 1.7849462365591398, "grad_norm": 1.2016121769392047, "learning_rate": 4.282794948915271e-06, "loss": 0.3336, "step": 166 }, { "epoch": 1.7956989247311828, "grad_norm": 1.2364712139446496, "learning_rate": 4.220918379989898e-06, "loss": 0.3815, "step": 167 }, { "epoch": 1.8064516129032258, "grad_norm": 1.1677279665442852, "learning_rate": 4.159163858762255e-06, "loss": 0.3284, "step": 168 }, { "epoch": 1.817204301075269, "grad_norm": 1.2119363388446562, "learning_rate": 4.097541059439698e-06, "loss": 0.3662, "step": 169 }, { "epoch": 1.827956989247312, "grad_norm": 1.1480161774722477, "learning_rate": 4.036059635594578e-06, "loss": 0.3589, "step": 170 }, { "epoch": 1.838709677419355, "grad_norm": 1.2274813656457675, "learning_rate": 3.974729218651946e-06, "loss": 0.3249, "step": 171 }, { "epoch": 1.849462365591398, "grad_norm": 1.2174884876788425, "learning_rate": 3.913559416380743e-06, "loss": 0.3605, "step": 172 }, { "epoch": 1.860215053763441, "grad_norm": 1.2173044748787643, "learning_rate": 3.852559811388676e-06, "loss": 0.3622, "step": 173 }, { "epoch": 1.870967741935484, "grad_norm": 1.0993262002539315, "learning_rate": 3.791739959621054e-06, "loss": 0.3159, "step": 174 }, { "epoch": 1.881720430107527, "grad_norm": 1.1781627168157496, "learning_rate": 3.7311093888637906e-06, "loss": 0.37, "step": 175 }, { "epoch": 1.89247311827957, "grad_norm": 1.120376466539403, "learning_rate": 3.670677597250819e-06, "loss": 0.3628, "step": 176 }, { "epoch": 1.903225806451613, "grad_norm": 1.1144596517150382, "learning_rate": 3.6104540517761594e-06, "loss": 0.3525, "step": 177 }, { "epoch": 1.913978494623656, "grad_norm": 1.1541300654588889, "learning_rate": 3.55044818681085e-06, "loss": 0.3224, "step": 178 }, { "epoch": 1.924731182795699, "grad_norm": 1.2475568699772912, "learning_rate": 3.4906694026250075e-06, "loss": 0.3474, "step": 179 }, { "epoch": 1.935483870967742, "grad_norm": 1.1498672361648068, "learning_rate": 3.431127063915213e-06, "loss": 0.3339, "step": 180 }, { "epoch": 1.946236559139785, "grad_norm": 1.2308326285216238, "learning_rate": 3.371830498337475e-06, "loss": 0.3123, "step": 181 }, { "epoch": 1.956989247311828, "grad_norm": 1.1895143093091571, "learning_rate": 3.3127889950460094e-06, "loss": 0.343, "step": 182 }, { "epoch": 1.967741935483871, "grad_norm": 1.1762159546277886, "learning_rate": 3.254011803238026e-06, "loss": 0.3402, "step": 183 }, { "epoch": 1.978494623655914, "grad_norm": 1.153653621278308, "learning_rate": 3.195508130704795e-06, "loss": 0.3766, "step": 184 }, { "epoch": 1.989247311827957, "grad_norm": 1.2087190097752418, "learning_rate": 3.1372871423891894e-06, "loss": 0.3827, "step": 185 }, { "epoch": 2.0, "grad_norm": 1.089032118871395, "learning_rate": 3.079357958949946e-06, "loss": 0.3326, "step": 186 }, { "epoch": 2.010752688172043, "grad_norm": 1.2353249862535516, "learning_rate": 3.021729655332858e-06, "loss": 0.2291, "step": 187 }, { "epoch": 2.021505376344086, "grad_norm": 1.1205213073958726, "learning_rate": 2.9644112593491315e-06, "loss": 0.2793, "step": 188 }, { "epoch": 2.032258064516129, "grad_norm": 1.0679682742372525, "learning_rate": 2.90741175026113e-06, "loss": 0.2318, "step": 189 }, { "epoch": 2.043010752688172, "grad_norm": 1.0416057740465434, "learning_rate": 2.850740057375716e-06, "loss": 0.2268, "step": 190 }, { "epoch": 2.053763440860215, "grad_norm": 1.1650862570167908, "learning_rate": 2.7944050586454215e-06, "loss": 0.2683, "step": 191 }, { "epoch": 2.064516129032258, "grad_norm": 1.0439734734555002, "learning_rate": 2.7384155792776724e-06, "loss": 0.2025, "step": 192 }, { "epoch": 2.075268817204301, "grad_norm": 1.0872608821496301, "learning_rate": 2.682780390352262e-06, "loss": 0.2393, "step": 193 }, { "epoch": 2.086021505376344, "grad_norm": 1.1996863353483587, "learning_rate": 2.627508207447308e-06, "loss": 0.2294, "step": 194 }, { "epoch": 2.096774193548387, "grad_norm": 1.2259184666219345, "learning_rate": 2.5726076892739127e-06, "loss": 0.2282, "step": 195 }, { "epoch": 2.10752688172043, "grad_norm": 1.169799186561526, "learning_rate": 2.5180874363197217e-06, "loss": 0.4074, "step": 196 }, { "epoch": 2.118279569892473, "grad_norm": 1.2450757774784624, "learning_rate": 2.463955989501607e-06, "loss": 0.2049, "step": 197 }, { "epoch": 2.129032258064516, "grad_norm": 1.2928234399217249, "learning_rate": 2.41022182882768e-06, "loss": 0.2867, "step": 198 }, { "epoch": 2.139784946236559, "grad_norm": 1.4079638381400967, "learning_rate": 2.356893372068855e-06, "loss": 0.2632, "step": 199 }, { "epoch": 2.150537634408602, "grad_norm": 1.2856070305392429, "learning_rate": 2.3039789734401524e-06, "loss": 0.2136, "step": 200 }, { "epoch": 2.161290322580645, "grad_norm": 1.257947749337111, "learning_rate": 2.251486922291957e-06, "loss": 0.2032, "step": 201 }, { "epoch": 2.172043010752688, "grad_norm": 1.2185848133318558, "learning_rate": 2.1994254418114524e-06, "loss": 0.2516, "step": 202 }, { "epoch": 2.182795698924731, "grad_norm": 1.1801170107899257, "learning_rate": 2.147802687734409e-06, "loss": 0.1965, "step": 203 }, { "epoch": 2.193548387096774, "grad_norm": 1.0247500981424174, "learning_rate": 2.0966267470675273e-06, "loss": 0.198, "step": 204 }, { "epoch": 2.204301075268817, "grad_norm": 1.16238195309318, "learning_rate": 2.0459056368215786e-06, "loss": 0.3509, "step": 205 }, { "epoch": 2.21505376344086, "grad_norm": 1.034172470881347, "learning_rate": 1.9956473027554846e-06, "loss": 0.2416, "step": 206 }, { "epoch": 2.225806451612903, "grad_norm": 1.2244901538313122, "learning_rate": 1.9458596181315643e-06, "loss": 0.2525, "step": 207 }, { "epoch": 2.236559139784946, "grad_norm": 1.0823123036421982, "learning_rate": 1.8965503824821496e-06, "loss": 0.2103, "step": 208 }, { "epoch": 2.247311827956989, "grad_norm": 1.1187165499095806, "learning_rate": 1.84772732038774e-06, "loss": 0.2403, "step": 209 }, { "epoch": 2.258064516129032, "grad_norm": 1.0442209176999298, "learning_rate": 1.7993980802668947e-06, "loss": 0.2059, "step": 210 }, { "epoch": 2.268817204301075, "grad_norm": 1.039636339404873, "learning_rate": 1.7515702331780753e-06, "loss": 0.2106, "step": 211 }, { "epoch": 2.279569892473118, "grad_norm": 0.971952637708957, "learning_rate": 1.7042512716335873e-06, "loss": 0.1833, "step": 212 }, { "epoch": 2.2903225806451615, "grad_norm": 1.0335059735288603, "learning_rate": 1.6574486084258369e-06, "loss": 0.2071, "step": 213 }, { "epoch": 2.3010752688172045, "grad_norm": 1.1712890998348404, "learning_rate": 1.6111695754660667e-06, "loss": 0.2277, "step": 214 }, { "epoch": 2.3118279569892475, "grad_norm": 1.0093534018268129, "learning_rate": 1.5654214226357822e-06, "loss": 0.2318, "step": 215 }, { "epoch": 2.3225806451612905, "grad_norm": 1.1389615413860168, "learning_rate": 1.5202113166510058e-06, "loss": 0.1953, "step": 216 }, { "epoch": 2.3333333333333335, "grad_norm": 1.246098734753724, "learning_rate": 1.475546339939568e-06, "loss": 0.2623, "step": 217 }, { "epoch": 2.3440860215053765, "grad_norm": 1.1558696943090916, "learning_rate": 1.4314334895316095e-06, "loss": 0.2445, "step": 218 }, { "epoch": 2.3548387096774195, "grad_norm": 1.2104135716011495, "learning_rate": 1.3878796759634544e-06, "loss": 0.2306, "step": 219 }, { "epoch": 2.3655913978494625, "grad_norm": 1.2234866527768256, "learning_rate": 1.3448917221950264e-06, "loss": 0.2374, "step": 220 }, { "epoch": 2.3763440860215055, "grad_norm": 1.0431434616717088, "learning_rate": 1.3024763625410025e-06, "loss": 0.2015, "step": 221 }, { "epoch": 2.3870967741935485, "grad_norm": 1.0687881028758524, "learning_rate": 1.2606402416158391e-06, "loss": 0.2067, "step": 222 }, { "epoch": 2.3978494623655915, "grad_norm": 1.134243323797628, "learning_rate": 1.2193899132928539e-06, "loss": 0.2183, "step": 223 }, { "epoch": 2.4086021505376345, "grad_norm": 1.0372879190394384, "learning_rate": 1.1787318396775188e-06, "loss": 0.1999, "step": 224 }, { "epoch": 2.4193548387096775, "grad_norm": 1.1665054400030295, "learning_rate": 1.138672390095143e-06, "loss": 0.2359, "step": 225 }, { "epoch": 2.4301075268817205, "grad_norm": 1.0236202702671575, "learning_rate": 1.0992178400930753e-06, "loss": 0.2212, "step": 226 }, { "epoch": 2.4408602150537635, "grad_norm": 1.0558233259176077, "learning_rate": 1.0603743704575992e-06, "loss": 0.2345, "step": 227 }, { "epoch": 2.4516129032258065, "grad_norm": 1.0155424223780078, "learning_rate": 1.0221480662456845e-06, "loss": 0.2339, "step": 228 }, { "epoch": 2.4623655913978495, "grad_norm": 1.1436634892190285, "learning_rate": 9.845449158317216e-07, "loss": 0.2091, "step": 229 }, { "epoch": 2.4731182795698925, "grad_norm": 1.0556139362512549, "learning_rate": 9.475708099694125e-07, "loss": 0.2178, "step": 230 }, { "epoch": 2.4838709677419355, "grad_norm": 1.0522117165285618, "learning_rate": 9.112315408689415e-07, "loss": 0.4077, "step": 231 }, { "epoch": 2.4946236559139785, "grad_norm": 1.181359684461707, "learning_rate": 8.755328012896002e-07, "loss": 0.2357, "step": 232 }, { "epoch": 2.5053763440860215, "grad_norm": 1.0897935630524107, "learning_rate": 8.404801836479809e-07, "loss": 0.2112, "step": 233 }, { "epoch": 2.5161290322580645, "grad_norm": 1.2518780229754654, "learning_rate": 8.060791791418887e-07, "loss": 0.2562, "step": 234 }, { "epoch": 2.5268817204301075, "grad_norm": 1.1188351065056708, "learning_rate": 7.723351768901172e-07, "loss": 0.2323, "step": 235 }, { "epoch": 2.5376344086021505, "grad_norm": 1.065402387910212, "learning_rate": 7.392534630882092e-07, "loss": 0.2481, "step": 236 }, { "epoch": 2.5483870967741935, "grad_norm": 1.1032094587545522, "learning_rate": 7.06839220180342e-07, "loss": 0.2124, "step": 237 }, { "epoch": 2.5591397849462365, "grad_norm": 1.0607815817961583, "learning_rate": 6.750975260474718e-07, "loss": 0.2528, "step": 238 }, { "epoch": 2.5698924731182795, "grad_norm": 1.1102586160747114, "learning_rate": 6.440333532118503e-07, "loss": 0.218, "step": 239 }, { "epoch": 2.5806451612903225, "grad_norm": 1.067767516141593, "learning_rate": 6.136515680580479e-07, "loss": 0.2233, "step": 240 }, { "epoch": 2.5913978494623655, "grad_norm": 0.998507674449185, "learning_rate": 5.839569300706127e-07, "loss": 0.2116, "step": 241 }, { "epoch": 2.6021505376344085, "grad_norm": 1.0336044812206406, "learning_rate": 5.549540910884649e-07, "loss": 0.1977, "step": 242 }, { "epoch": 2.6129032258064515, "grad_norm": 1.0581929188450587, "learning_rate": 5.266475945761562e-07, "loss": 0.2062, "step": 243 }, { "epoch": 2.6236559139784945, "grad_norm": 1.1943327940895927, "learning_rate": 4.990418749121179e-07, "loss": 0.2217, "step": 244 }, { "epoch": 2.6344086021505375, "grad_norm": 1.0573079691578624, "learning_rate": 4.721412566939804e-07, "loss": 0.2265, "step": 245 }, { "epoch": 2.6451612903225805, "grad_norm": 1.010938446897227, "learning_rate": 4.4594995406110785e-07, "loss": 0.2379, "step": 246 }, { "epoch": 2.6559139784946235, "grad_norm": 1.1607031036965616, "learning_rate": 4.2047207003442003e-07, "loss": 0.2079, "step": 247 }, { "epoch": 2.6666666666666665, "grad_norm": 1.0632285683620692, "learning_rate": 3.957115958736374e-07, "loss": 0.2321, "step": 248 }, { "epoch": 2.6774193548387095, "grad_norm": 0.9910529748392375, "learning_rate": 3.7167241045202474e-07, "loss": 0.1987, "step": 249 }, { "epoch": 2.688172043010753, "grad_norm": 1.0775742035983213, "learning_rate": 3.483582796487395e-07, "loss": 0.2094, "step": 250 }, { "epoch": 2.698924731182796, "grad_norm": 0.9984569332006167, "learning_rate": 3.257728557588902e-07, "loss": 0.25, "step": 251 }, { "epoch": 2.709677419354839, "grad_norm": 1.206448802708809, "learning_rate": 3.039196769213787e-07, "loss": 0.2763, "step": 252 }, { "epoch": 2.720430107526882, "grad_norm": 1.1154480238255622, "learning_rate": 2.828021665646341e-07, "loss": 0.221, "step": 253 }, { "epoch": 2.731182795698925, "grad_norm": 1.1493470631886933, "learning_rate": 2.6242363287030617e-07, "loss": 0.3025, "step": 254 }, { "epoch": 2.741935483870968, "grad_norm": 1.0349657874746057, "learning_rate": 2.4278726825502696e-07, "loss": 0.2539, "step": 255 }, { "epoch": 2.752688172043011, "grad_norm": 1.109346692196228, "learning_rate": 2.2389614887029564e-07, "loss": 0.2281, "step": 256 }, { "epoch": 2.763440860215054, "grad_norm": 1.0353141380673936, "learning_rate": 2.0575323412058036e-07, "loss": 0.2141, "step": 257 }, { "epoch": 2.774193548387097, "grad_norm": 1.0819606199339722, "learning_rate": 1.8836136619971468e-07, "loss": 0.2195, "step": 258 }, { "epoch": 2.78494623655914, "grad_norm": 1.177939271195523, "learning_rate": 1.7172326964564777e-07, "loss": 0.2508, "step": 259 }, { "epoch": 2.795698924731183, "grad_norm": 1.1223938711713661, "learning_rate": 1.5584155091362907e-07, "loss": 0.2264, "step": 260 }, { "epoch": 2.806451612903226, "grad_norm": 0.9908185773525874, "learning_rate": 1.4071869796789427e-07, "loss": 0.1976, "step": 261 }, { "epoch": 2.817204301075269, "grad_norm": 1.002478958639444, "learning_rate": 1.263570798919106e-07, "loss": 0.1927, "step": 262 }, { "epoch": 2.827956989247312, "grad_norm": 1.0056557952222767, "learning_rate": 1.1275894651724517e-07, "loss": 0.1868, "step": 263 }, { "epoch": 2.838709677419355, "grad_norm": 1.0197297289564395, "learning_rate": 9.992642807111486e-08, "loss": 0.1927, "step": 264 }, { "epoch": 2.849462365591398, "grad_norm": 1.0517533923654494, "learning_rate": 8.78615348426759e-08, "loss": 0.2234, "step": 265 }, { "epoch": 2.860215053763441, "grad_norm": 0.9940345005525202, "learning_rate": 7.656615686809976e-08, "loss": 0.1817, "step": 266 }, { "epoch": 2.870967741935484, "grad_norm": 1.0497686699125726, "learning_rate": 6.604206363448662e-08, "loss": 0.2152, "step": 267 }, { "epoch": 2.881720430107527, "grad_norm": 1.0384511431694428, "learning_rate": 5.6290903802665444e-08, "loss": 0.2158, "step": 268 }, { "epoch": 2.89247311827957, "grad_norm": 1.3090254246994417, "learning_rate": 4.7314204948923356e-08, "loss": 0.2409, "step": 269 }, { "epoch": 2.903225806451613, "grad_norm": 1.0831200870108442, "learning_rate": 3.911337332569876e-08, "loss": 0.215, "step": 270 }, { "epoch": 2.913978494623656, "grad_norm": 1.0200774345835755, "learning_rate": 3.168969364128527e-08, "loss": 0.1853, "step": 271 }, { "epoch": 2.924731182795699, "grad_norm": 1.0411062374812041, "learning_rate": 2.5044328858576105e-08, "loss": 0.1822, "step": 272 }, { "epoch": 2.935483870967742, "grad_norm": 1.0955663825580222, "learning_rate": 1.917832001287645e-08, "loss": 0.2366, "step": 273 }, { "epoch": 2.946236559139785, "grad_norm": 1.0058951894911308, "learning_rate": 1.4092586048820578e-08, "loss": 0.2088, "step": 274 }, { "epoch": 2.956989247311828, "grad_norm": 1.0534367805397553, "learning_rate": 9.787923676414235e-09, "loss": 0.2006, "step": 275 }, { "epoch": 2.967741935483871, "grad_norm": 1.0711677289438932, "learning_rate": 6.265007246223365e-09, "loss": 0.2288, "step": 276 }, { "epoch": 2.978494623655914, "grad_norm": 1.1018665243256054, "learning_rate": 3.524388643736387e-09, "loss": 0.2359, "step": 277 }, { "epoch": 2.989247311827957, "grad_norm": 0.9977813212471681, "learning_rate": 1.566497202904471e-09, "loss": 0.2032, "step": 278 }, { "epoch": 3.0, "grad_norm": 1.121191187403273, "learning_rate": 3.916396388869981e-10, "loss": 0.2414, "step": 279 }, { "epoch": 3.0, "step": 279, "total_flos": 2.2819812112387277e+17, "train_loss": 0.38972266467027766, "train_runtime": 34674.5164, "train_samples_per_second": 0.386, "train_steps_per_second": 0.008 } ], "logging_steps": 1, "max_steps": 279, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 2.2819812112387277e+17, "train_batch_size": 1, "trial_name": null, "trial_params": null }