| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9541284403669725, | |
| "eval_steps": 500, | |
| "global_step": 162, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01834862385321101, | |
| "grad_norm": 0.04378490149974823, | |
| "learning_rate": 4.999989423013716e-05, | |
| "loss": 0.6713, | |
| "num_input_tokens_seen": 44136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03669724770642202, | |
| "grad_norm": 0.040646992623806, | |
| "learning_rate": 4.999957692144361e-05, | |
| "loss": 0.533, | |
| "num_input_tokens_seen": 83096, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05504587155963303, | |
| "grad_norm": 0.04658753052353859, | |
| "learning_rate": 4.999904807660428e-05, | |
| "loss": 0.6048, | |
| "num_input_tokens_seen": 122112, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07339449541284404, | |
| "grad_norm": 0.04322144016623497, | |
| "learning_rate": 4.999830770009406e-05, | |
| "loss": 0.4948, | |
| "num_input_tokens_seen": 163064, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09174311926605505, | |
| "grad_norm": 0.06536195427179337, | |
| "learning_rate": 4.999735579817769e-05, | |
| "loss": 0.6607, | |
| "num_input_tokens_seen": 203808, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.11009174311926606, | |
| "grad_norm": 0.059904925525188446, | |
| "learning_rate": 4.9996192378909786e-05, | |
| "loss": 0.5802, | |
| "num_input_tokens_seen": 241824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12844036697247707, | |
| "grad_norm": 0.19818365573883057, | |
| "learning_rate": 4.999481745213471e-05, | |
| "loss": 0.5148, | |
| "num_input_tokens_seen": 287608, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14678899082568808, | |
| "grad_norm": 0.05985472351312637, | |
| "learning_rate": 4.9993231029486544e-05, | |
| "loss": 0.5714, | |
| "num_input_tokens_seen": 325320, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1651376146788991, | |
| "grad_norm": 0.061375778168439865, | |
| "learning_rate": 4.999143312438893e-05, | |
| "loss": 0.6812, | |
| "num_input_tokens_seen": 369848, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1834862385321101, | |
| "grad_norm": 0.06196414306759834, | |
| "learning_rate": 4.998942375205502e-05, | |
| "loss": 0.5358, | |
| "num_input_tokens_seen": 415104, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.2018348623853211, | |
| "grad_norm": 0.07861393690109253, | |
| "learning_rate": 4.9987202929487275e-05, | |
| "loss": 0.6527, | |
| "num_input_tokens_seen": 467224, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.22018348623853212, | |
| "grad_norm": 0.05596446990966797, | |
| "learning_rate": 4.99847706754774e-05, | |
| "loss": 0.5354, | |
| "num_input_tokens_seen": 502824, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23853211009174313, | |
| "grad_norm": 0.05289844051003456, | |
| "learning_rate": 4.998212701060612e-05, | |
| "loss": 0.5263, | |
| "num_input_tokens_seen": 544744, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.25688073394495414, | |
| "grad_norm": 0.04996591433882713, | |
| "learning_rate": 4.997927195724303e-05, | |
| "loss": 0.5536, | |
| "num_input_tokens_seen": 591136, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.27522935779816515, | |
| "grad_norm": 0.05822828412055969, | |
| "learning_rate": 4.997620553954645e-05, | |
| "loss": 0.6106, | |
| "num_input_tokens_seen": 629664, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.29357798165137616, | |
| "grad_norm": 0.06353770196437836, | |
| "learning_rate": 4.997292778346312e-05, | |
| "loss": 0.5129, | |
| "num_input_tokens_seen": 663392, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3119266055045872, | |
| "grad_norm": 0.07256966829299927, | |
| "learning_rate": 4.996943871672807e-05, | |
| "loss": 0.6377, | |
| "num_input_tokens_seen": 698360, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3302752293577982, | |
| "grad_norm": 0.055458713322877884, | |
| "learning_rate": 4.996573836886435e-05, | |
| "loss": 0.4083, | |
| "num_input_tokens_seen": 737520, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3486238532110092, | |
| "grad_norm": 0.07792335003614426, | |
| "learning_rate": 4.9961826771182784e-05, | |
| "loss": 0.6086, | |
| "num_input_tokens_seen": 768056, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3669724770642202, | |
| "grad_norm": 0.06627275049686432, | |
| "learning_rate": 4.995770395678171e-05, | |
| "loss": 0.4591, | |
| "num_input_tokens_seen": 806256, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3853211009174312, | |
| "grad_norm": 0.05830290913581848, | |
| "learning_rate": 4.9953369960546676e-05, | |
| "loss": 0.3731, | |
| "num_input_tokens_seen": 842336, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4036697247706422, | |
| "grad_norm": 0.07277437299489975, | |
| "learning_rate": 4.9948824819150185e-05, | |
| "loss": 0.6243, | |
| "num_input_tokens_seen": 876672, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.42201834862385323, | |
| "grad_norm": 0.07477546483278275, | |
| "learning_rate": 4.994406857105136e-05, | |
| "loss": 0.5788, | |
| "num_input_tokens_seen": 915192, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.44036697247706424, | |
| "grad_norm": 0.06912907212972641, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.4753, | |
| "num_input_tokens_seen": 951904, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.45871559633027525, | |
| "grad_norm": 0.0655476376414299, | |
| "learning_rate": 4.993392291751431e-05, | |
| "loss": 0.4518, | |
| "num_input_tokens_seen": 1001816, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.47706422018348627, | |
| "grad_norm": 0.06466512382030487, | |
| "learning_rate": 4.992853359792444e-05, | |
| "loss": 0.5638, | |
| "num_input_tokens_seen": 1053064, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4954128440366973, | |
| "grad_norm": 0.0645688995718956, | |
| "learning_rate": 4.99229333433282e-05, | |
| "loss": 0.4644, | |
| "num_input_tokens_seen": 1086688, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5137614678899083, | |
| "grad_norm": 0.07181251049041748, | |
| "learning_rate": 4.9917122201112656e-05, | |
| "loss": 0.6191, | |
| "num_input_tokens_seen": 1134824, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5321100917431193, | |
| "grad_norm": 0.07322589308023453, | |
| "learning_rate": 4.9911100220449293e-05, | |
| "loss": 0.6752, | |
| "num_input_tokens_seen": 1172072, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5504587155963303, | |
| "grad_norm": 0.06396070122718811, | |
| "learning_rate": 4.990486745229364e-05, | |
| "loss": 0.3587, | |
| "num_input_tokens_seen": 1211096, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5688073394495413, | |
| "grad_norm": 0.07803395390510559, | |
| "learning_rate": 4.989842394938482e-05, | |
| "loss": 0.459, | |
| "num_input_tokens_seen": 1259456, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5871559633027523, | |
| "grad_norm": 0.05974648892879486, | |
| "learning_rate": 4.989176976624511e-05, | |
| "loss": 0.4148, | |
| "num_input_tokens_seen": 1306944, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6055045871559633, | |
| "grad_norm": 0.09784268587827682, | |
| "learning_rate": 4.988490495917947e-05, | |
| "loss": 0.539, | |
| "num_input_tokens_seen": 1353744, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.6238532110091743, | |
| "grad_norm": 0.09906516224145889, | |
| "learning_rate": 4.987782958627508e-05, | |
| "loss": 0.5453, | |
| "num_input_tokens_seen": 1394736, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6422018348623854, | |
| "grad_norm": 0.08984062820672989, | |
| "learning_rate": 4.987054370740083e-05, | |
| "loss": 0.468, | |
| "num_input_tokens_seen": 1442048, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6605504587155964, | |
| "grad_norm": 0.08672655373811722, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.4078, | |
| "num_input_tokens_seen": 1478440, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6788990825688074, | |
| "grad_norm": 0.1327345073223114, | |
| "learning_rate": 4.9855340680123905e-05, | |
| "loss": 0.5299, | |
| "num_input_tokens_seen": 1525992, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6972477064220184, | |
| "grad_norm": 0.09178602695465088, | |
| "learning_rate": 4.9847423660363e-05, | |
| "loss": 0.439, | |
| "num_input_tokens_seen": 1555608, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.7155963302752294, | |
| "grad_norm": 0.09418320655822754, | |
| "learning_rate": 4.983929639191469e-05, | |
| "loss": 0.5337, | |
| "num_input_tokens_seen": 1597392, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7339449541284404, | |
| "grad_norm": 0.08294719457626343, | |
| "learning_rate": 4.983095894354858e-05, | |
| "loss": 0.4536, | |
| "num_input_tokens_seen": 1649656, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7522935779816514, | |
| "grad_norm": 0.09774205833673477, | |
| "learning_rate": 4.982241138581273e-05, | |
| "loss": 0.5221, | |
| "num_input_tokens_seen": 1695952, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7706422018348624, | |
| "grad_norm": 0.09319107979536057, | |
| "learning_rate": 4.9813653791033057e-05, | |
| "loss": 0.4279, | |
| "num_input_tokens_seen": 1737224, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7889908256880734, | |
| "grad_norm": 0.09561405330896378, | |
| "learning_rate": 4.980468623331273e-05, | |
| "loss": 0.5121, | |
| "num_input_tokens_seen": 1772320, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.8073394495412844, | |
| "grad_norm": 0.08274025470018387, | |
| "learning_rate": 4.979550878853154e-05, | |
| "loss": 0.54, | |
| "num_input_tokens_seen": 1823888, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.8256880733944955, | |
| "grad_norm": 0.08728913217782974, | |
| "learning_rate": 4.9786121534345265e-05, | |
| "loss": 0.4488, | |
| "num_input_tokens_seen": 1872488, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8440366972477065, | |
| "grad_norm": 0.0787016749382019, | |
| "learning_rate": 4.9776524550184965e-05, | |
| "loss": 0.4353, | |
| "num_input_tokens_seen": 1924744, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8623853211009175, | |
| "grad_norm": 0.10952188074588776, | |
| "learning_rate": 4.97667179172564e-05, | |
| "loss": 0.4784, | |
| "num_input_tokens_seen": 1959936, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8807339449541285, | |
| "grad_norm": 0.08525826781988144, | |
| "learning_rate": 4.975670171853926e-05, | |
| "loss": 0.3586, | |
| "num_input_tokens_seen": 2003896, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8990825688073395, | |
| "grad_norm": 0.10409987717866898, | |
| "learning_rate": 4.9746476038786496e-05, | |
| "loss": 0.4451, | |
| "num_input_tokens_seen": 2047632, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.9174311926605505, | |
| "grad_norm": 0.0782993957400322, | |
| "learning_rate": 4.973604096452361e-05, | |
| "loss": 0.3591, | |
| "num_input_tokens_seen": 2096928, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9357798165137615, | |
| "grad_norm": 0.09829951077699661, | |
| "learning_rate": 4.9725396584047925e-05, | |
| "loss": 0.3415, | |
| "num_input_tokens_seen": 2129536, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9541284403669725, | |
| "grad_norm": 0.10606162995100021, | |
| "learning_rate": 4.971454298742779e-05, | |
| "loss": 0.3758, | |
| "num_input_tokens_seen": 2169144, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9724770642201835, | |
| "grad_norm": 0.09280356764793396, | |
| "learning_rate": 4.97034802665019e-05, | |
| "loss": 0.485, | |
| "num_input_tokens_seen": 2207720, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9908256880733946, | |
| "grad_norm": 0.11888203024864197, | |
| "learning_rate": 4.9692208514878444e-05, | |
| "loss": 0.3469, | |
| "num_input_tokens_seen": 2236392, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.13222463428974152, | |
| "learning_rate": 4.9680727827934354e-05, | |
| "loss": 0.4284, | |
| "num_input_tokens_seen": 2259088, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.018348623853211, | |
| "grad_norm": 0.10572745651006699, | |
| "learning_rate": 4.966903830281449e-05, | |
| "loss": 0.4186, | |
| "num_input_tokens_seen": 2298496, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.036697247706422, | |
| "grad_norm": 0.11462350189685822, | |
| "learning_rate": 4.965714003843079e-05, | |
| "loss": 0.4696, | |
| "num_input_tokens_seen": 2333016, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 1.0550458715596331, | |
| "grad_norm": 0.11215240508317947, | |
| "learning_rate": 4.9645033135461494e-05, | |
| "loss": 0.3905, | |
| "num_input_tokens_seen": 2367992, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 1.073394495412844, | |
| "grad_norm": 0.0973561555147171, | |
| "learning_rate": 4.963271769635024e-05, | |
| "loss": 0.3588, | |
| "num_input_tokens_seen": 2415328, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 1.091743119266055, | |
| "grad_norm": 0.10240709036588669, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.5532, | |
| "num_input_tokens_seen": 2454792, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.110091743119266, | |
| "grad_norm": 0.0959337130188942, | |
| "learning_rate": 4.9607461628298244e-05, | |
| "loss": 0.331, | |
| "num_input_tokens_seen": 2503072, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 1.1284403669724772, | |
| "grad_norm": 0.10228750854730606, | |
| "learning_rate": 4.9594521213063974e-05, | |
| "loss": 0.3728, | |
| "num_input_tokens_seen": 2546960, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 1.146788990825688, | |
| "grad_norm": 0.09403488785028458, | |
| "learning_rate": 4.958137268909887e-05, | |
| "loss": 0.4695, | |
| "num_input_tokens_seen": 2595432, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 1.165137614678899, | |
| "grad_norm": 0.11396344751119614, | |
| "learning_rate": 4.9568016167660334e-05, | |
| "loss": 0.3653, | |
| "num_input_tokens_seen": 2633912, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 1.18348623853211, | |
| "grad_norm": 0.09487481415271759, | |
| "learning_rate": 4.9554451761765766e-05, | |
| "loss": 0.3498, | |
| "num_input_tokens_seen": 2680792, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.2018348623853212, | |
| "grad_norm": 0.1249895691871643, | |
| "learning_rate": 4.9540679586191605e-05, | |
| "loss": 0.4053, | |
| "num_input_tokens_seen": 2716584, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 1.2201834862385321, | |
| "grad_norm": 0.12268221378326416, | |
| "learning_rate": 4.952669975747232e-05, | |
| "loss": 0.4189, | |
| "num_input_tokens_seen": 2757088, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 1.238532110091743, | |
| "grad_norm": 0.12126032263040543, | |
| "learning_rate": 4.951251239389948e-05, | |
| "loss": 0.4994, | |
| "num_input_tokens_seen": 2795664, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 1.2568807339449541, | |
| "grad_norm": 0.1069057360291481, | |
| "learning_rate": 4.949811761552074e-05, | |
| "loss": 0.3275, | |
| "num_input_tokens_seen": 2840936, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 1.2752293577981653, | |
| "grad_norm": 0.10893313586711884, | |
| "learning_rate": 4.948351554413879e-05, | |
| "loss": 0.4366, | |
| "num_input_tokens_seen": 2886768, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.2935779816513762, | |
| "grad_norm": 0.12898756563663483, | |
| "learning_rate": 4.9468706303310355e-05, | |
| "loss": 0.3916, | |
| "num_input_tokens_seen": 2919328, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 1.311926605504587, | |
| "grad_norm": 0.12405356019735336, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 0.3249, | |
| "num_input_tokens_seen": 2966744, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 1.3302752293577982, | |
| "grad_norm": 0.13137595355510712, | |
| "learning_rate": 4.943846681630479e-05, | |
| "loss": 0.3956, | |
| "num_input_tokens_seen": 3007248, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 1.3486238532110093, | |
| "grad_norm": 0.13920250535011292, | |
| "learning_rate": 4.942303682600178e-05, | |
| "loss": 0.3956, | |
| "num_input_tokens_seen": 3050960, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 1.3669724770642202, | |
| "grad_norm": 0.1255589872598648, | |
| "learning_rate": 4.940740017799833e-05, | |
| "loss": 0.3773, | |
| "num_input_tokens_seen": 3088592, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.385321100917431, | |
| "grad_norm": 0.10222747176885605, | |
| "learning_rate": 4.939155700460536e-05, | |
| "loss": 0.4, | |
| "num_input_tokens_seen": 3153520, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 1.4036697247706422, | |
| "grad_norm": 0.13205283880233765, | |
| "learning_rate": 4.9375507439881266e-05, | |
| "loss": 0.4343, | |
| "num_input_tokens_seen": 3199272, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 1.4220183486238533, | |
| "grad_norm": 0.11005694419145584, | |
| "learning_rate": 4.9359251619630886e-05, | |
| "loss": 0.3881, | |
| "num_input_tokens_seen": 3247128, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 1.4403669724770642, | |
| "grad_norm": 0.14799247682094574, | |
| "learning_rate": 4.9342789681404275e-05, | |
| "loss": 0.3972, | |
| "num_input_tokens_seen": 3294192, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 1.4587155963302751, | |
| "grad_norm": 0.1279418021440506, | |
| "learning_rate": 4.9326121764495596e-05, | |
| "loss": 0.3438, | |
| "num_input_tokens_seen": 3329736, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.4770642201834863, | |
| "grad_norm": 0.11036807298660278, | |
| "learning_rate": 4.9309248009941914e-05, | |
| "loss": 0.3189, | |
| "num_input_tokens_seen": 3371376, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 1.4954128440366974, | |
| "grad_norm": 0.11855707317590714, | |
| "learning_rate": 4.9292168560522014e-05, | |
| "loss": 0.401, | |
| "num_input_tokens_seen": 3412368, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 1.5137614678899083, | |
| "grad_norm": 0.13195356726646423, | |
| "learning_rate": 4.9274883560755156e-05, | |
| "loss": 0.4973, | |
| "num_input_tokens_seen": 3455000, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 1.5321100917431192, | |
| "grad_norm": 0.1462787538766861, | |
| "learning_rate": 4.925739315689991e-05, | |
| "loss": 0.3768, | |
| "num_input_tokens_seen": 3488960, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 1.5504587155963303, | |
| "grad_norm": 0.13765974342823029, | |
| "learning_rate": 4.92396974969529e-05, | |
| "loss": 0.2999, | |
| "num_input_tokens_seen": 3521320, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.5688073394495414, | |
| "grad_norm": 0.15276113152503967, | |
| "learning_rate": 4.9221796730647516e-05, | |
| "loss": 0.3638, | |
| "num_input_tokens_seen": 3559464, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 1.5871559633027523, | |
| "grad_norm": 0.1441674381494522, | |
| "learning_rate": 4.92036910094527e-05, | |
| "loss": 0.3919, | |
| "num_input_tokens_seen": 3598080, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 1.6055045871559632, | |
| "grad_norm": 0.1780252456665039, | |
| "learning_rate": 4.9185380486571595e-05, | |
| "loss": 0.3626, | |
| "num_input_tokens_seen": 3630064, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 1.6238532110091743, | |
| "grad_norm": 0.16947726905345917, | |
| "learning_rate": 4.916686531694035e-05, | |
| "loss": 0.3439, | |
| "num_input_tokens_seen": 3661408, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.6422018348623855, | |
| "grad_norm": 0.1552971601486206, | |
| "learning_rate": 4.914814565722671e-05, | |
| "loss": 0.3236, | |
| "num_input_tokens_seen": 3695480, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.6605504587155964, | |
| "grad_norm": 0.14925938844680786, | |
| "learning_rate": 4.912922166582874e-05, | |
| "loss": 0.4255, | |
| "num_input_tokens_seen": 3734560, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 1.6788990825688073, | |
| "grad_norm": 0.1332874596118927, | |
| "learning_rate": 4.9110093502873476e-05, | |
| "loss": 0.3061, | |
| "num_input_tokens_seen": 3773112, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 1.6972477064220184, | |
| "grad_norm": 0.15471243858337402, | |
| "learning_rate": 4.909076133021557e-05, | |
| "loss": 0.3275, | |
| "num_input_tokens_seen": 3813392, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 1.7155963302752295, | |
| "grad_norm": 0.16010524332523346, | |
| "learning_rate": 4.907122531143594e-05, | |
| "loss": 0.4179, | |
| "num_input_tokens_seen": 3856416, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 1.7339449541284404, | |
| "grad_norm": 0.13423003256320953, | |
| "learning_rate": 4.905148561184033e-05, | |
| "loss": 0.3593, | |
| "num_input_tokens_seen": 3899472, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.7522935779816513, | |
| "grad_norm": 0.14900773763656616, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.5007, | |
| "num_input_tokens_seen": 3962976, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 1.7706422018348624, | |
| "grad_norm": 0.15728624165058136, | |
| "learning_rate": 4.9011395840040144e-05, | |
| "loss": 0.3484, | |
| "num_input_tokens_seen": 4000696, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 1.7889908256880735, | |
| "grad_norm": 0.11092367768287659, | |
| "learning_rate": 4.8991046107058735e-05, | |
| "loss": 0.2889, | |
| "num_input_tokens_seen": 4045256, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 1.8073394495412844, | |
| "grad_norm": 0.1289113610982895, | |
| "learning_rate": 4.8970493371704826e-05, | |
| "loss": 0.2203, | |
| "num_input_tokens_seen": 4076800, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 1.8256880733944953, | |
| "grad_norm": 0.18886639177799225, | |
| "learning_rate": 4.894973780788722e-05, | |
| "loss": 0.3966, | |
| "num_input_tokens_seen": 4119840, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.8440366972477065, | |
| "grad_norm": 0.1563039869070053, | |
| "learning_rate": 4.892877959123097e-05, | |
| "loss": 0.4417, | |
| "num_input_tokens_seen": 4165848, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 1.8623853211009176, | |
| "grad_norm": 0.16883380711078644, | |
| "learning_rate": 4.890761889907589e-05, | |
| "loss": 0.4258, | |
| "num_input_tokens_seen": 4202824, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.8807339449541285, | |
| "grad_norm": 0.18241995573043823, | |
| "learning_rate": 4.8886255910475054e-05, | |
| "loss": 0.3952, | |
| "num_input_tokens_seen": 4233888, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 1.8990825688073394, | |
| "grad_norm": 0.19913265109062195, | |
| "learning_rate": 4.88646908061933e-05, | |
| "loss": 0.3241, | |
| "num_input_tokens_seen": 4267064, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 1.9174311926605505, | |
| "grad_norm": 0.18295545876026154, | |
| "learning_rate": 4.884292376870567e-05, | |
| "loss": 0.4239, | |
| "num_input_tokens_seen": 4312536, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.9357798165137616, | |
| "grad_norm": 0.16657495498657227, | |
| "learning_rate": 4.8820954982195905e-05, | |
| "loss": 0.2579, | |
| "num_input_tokens_seen": 4356656, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 1.9541284403669725, | |
| "grad_norm": 0.18504932522773743, | |
| "learning_rate": 4.879878463255483e-05, | |
| "loss": 0.44, | |
| "num_input_tokens_seen": 4400216, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 1.9724770642201834, | |
| "grad_norm": 0.1923118382692337, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.2662, | |
| "num_input_tokens_seen": 4436968, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 1.9908256880733946, | |
| "grad_norm": 0.19636788964271545, | |
| "learning_rate": 4.875383999596828e-05, | |
| "loss": 0.4211, | |
| "num_input_tokens_seen": 4488232, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.3168099820613861, | |
| "learning_rate": 4.873106608932585e-05, | |
| "loss": 0.2499, | |
| "num_input_tokens_seen": 4518176, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.018348623853211, | |
| "grad_norm": 0.14410308003425598, | |
| "learning_rate": 4.8708091380154984e-05, | |
| "loss": 0.2722, | |
| "num_input_tokens_seen": 4570896, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 2.036697247706422, | |
| "grad_norm": 0.17840909957885742, | |
| "learning_rate": 4.868491606285823e-05, | |
| "loss": 0.2758, | |
| "num_input_tokens_seen": 4613576, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 2.055045871559633, | |
| "grad_norm": 0.178523987531662, | |
| "learning_rate": 4.866154033353561e-05, | |
| "loss": 0.3361, | |
| "num_input_tokens_seen": 4652896, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 2.073394495412844, | |
| "grad_norm": 0.17396725714206696, | |
| "learning_rate": 4.8637964389982926e-05, | |
| "loss": 0.2667, | |
| "num_input_tokens_seen": 4694256, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 2.091743119266055, | |
| "grad_norm": 0.19471587240695953, | |
| "learning_rate": 4.8614188431690125e-05, | |
| "loss": 0.3628, | |
| "num_input_tokens_seen": 4747552, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.1100917431192663, | |
| "grad_norm": 0.1722450852394104, | |
| "learning_rate": 4.859021265983959e-05, | |
| "loss": 0.3599, | |
| "num_input_tokens_seen": 4794080, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 2.128440366972477, | |
| "grad_norm": 0.20137006044387817, | |
| "learning_rate": 4.856603727730447e-05, | |
| "loss": 0.4262, | |
| "num_input_tokens_seen": 4847912, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 2.146788990825688, | |
| "grad_norm": 0.19395771622657776, | |
| "learning_rate": 4.854166248864689e-05, | |
| "loss": 0.3118, | |
| "num_input_tokens_seen": 4885480, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 2.165137614678899, | |
| "grad_norm": 0.209548681974411, | |
| "learning_rate": 4.85170885001163e-05, | |
| "loss": 0.3725, | |
| "num_input_tokens_seen": 4921240, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 2.18348623853211, | |
| "grad_norm": 0.18228279054164886, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.3816, | |
| "num_input_tokens_seen": 4960224, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.2018348623853212, | |
| "grad_norm": 0.24349354207515717, | |
| "learning_rate": 4.846734375685989e-05, | |
| "loss": 0.3383, | |
| "num_input_tokens_seen": 4990536, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 2.220183486238532, | |
| "grad_norm": 0.17600344121456146, | |
| "learning_rate": 4.844217342305363e-05, | |
| "loss": 0.3011, | |
| "num_input_tokens_seen": 5044296, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 2.238532110091743, | |
| "grad_norm": 0.18766675889492035, | |
| "learning_rate": 4.8416804731209945e-05, | |
| "loss": 0.4458, | |
| "num_input_tokens_seen": 5088368, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 2.2568807339449544, | |
| "grad_norm": 0.17657820880413055, | |
| "learning_rate": 4.839123789598829e-05, | |
| "loss": 0.2564, | |
| "num_input_tokens_seen": 5133472, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 2.2752293577981653, | |
| "grad_norm": 0.20606014132499695, | |
| "learning_rate": 4.836547313372471e-05, | |
| "loss": 0.313, | |
| "num_input_tokens_seen": 5167768, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.293577981651376, | |
| "grad_norm": 0.23511061072349548, | |
| "learning_rate": 4.8339510662430046e-05, | |
| "loss": 0.2963, | |
| "num_input_tokens_seen": 5209400, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 2.311926605504587, | |
| "grad_norm": 0.18234293162822723, | |
| "learning_rate": 4.8313350701788054e-05, | |
| "loss": 0.2566, | |
| "num_input_tokens_seen": 5249360, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 2.330275229357798, | |
| "grad_norm": 0.2223992496728897, | |
| "learning_rate": 4.828699347315356e-05, | |
| "loss": 0.2833, | |
| "num_input_tokens_seen": 5300808, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 2.3486238532110093, | |
| "grad_norm": 0.23101739585399628, | |
| "learning_rate": 4.826043919955062e-05, | |
| "loss": 0.3099, | |
| "num_input_tokens_seen": 5332960, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 2.36697247706422, | |
| "grad_norm": 0.26640889048576355, | |
| "learning_rate": 4.823368810567056e-05, | |
| "loss": 0.3238, | |
| "num_input_tokens_seen": 5365008, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.385321100917431, | |
| "grad_norm": 0.2374572902917862, | |
| "learning_rate": 4.820674041787017e-05, | |
| "loss": 0.3153, | |
| "num_input_tokens_seen": 5400184, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 2.4036697247706424, | |
| "grad_norm": 0.22812288999557495, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 0.2997, | |
| "num_input_tokens_seen": 5440320, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 2.4220183486238533, | |
| "grad_norm": 0.20079149305820465, | |
| "learning_rate": 4.815225617425095e-05, | |
| "loss": 0.2373, | |
| "num_input_tokens_seen": 5480832, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 2.4403669724770642, | |
| "grad_norm": 0.196709543466568, | |
| "learning_rate": 4.81247200794554e-05, | |
| "loss": 0.2456, | |
| "num_input_tokens_seen": 5526936, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 2.458715596330275, | |
| "grad_norm": 0.17305873334407806, | |
| "learning_rate": 4.8096988312782174e-05, | |
| "loss": 0.2099, | |
| "num_input_tokens_seen": 5566384, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.477064220183486, | |
| "grad_norm": 3.584635019302368, | |
| "learning_rate": 4.806906110888606e-05, | |
| "loss": 0.3485, | |
| "num_input_tokens_seen": 5629896, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 2.4954128440366974, | |
| "grad_norm": 0.23481500148773193, | |
| "learning_rate": 4.80409387040756e-05, | |
| "loss": 0.2231, | |
| "num_input_tokens_seen": 5674504, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 2.5137614678899083, | |
| "grad_norm": 0.27899855375289917, | |
| "learning_rate": 4.8012621336311016e-05, | |
| "loss": 0.4285, | |
| "num_input_tokens_seen": 5714000, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 2.532110091743119, | |
| "grad_norm": 0.24404938519001007, | |
| "learning_rate": 4.798410924520223e-05, | |
| "loss": 0.3343, | |
| "num_input_tokens_seen": 5756856, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 2.5504587155963305, | |
| "grad_norm": 0.26869162917137146, | |
| "learning_rate": 4.7955402672006854e-05, | |
| "loss": 0.2497, | |
| "num_input_tokens_seen": 5781192, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.5688073394495414, | |
| "grad_norm": 0.2057972550392151, | |
| "learning_rate": 4.79265018596281e-05, | |
| "loss": 0.2991, | |
| "num_input_tokens_seen": 5824024, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 2.5871559633027523, | |
| "grad_norm": 0.2184937596321106, | |
| "learning_rate": 4.789740705261278e-05, | |
| "loss": 0.2406, | |
| "num_input_tokens_seen": 5862584, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 2.6055045871559632, | |
| "grad_norm": 0.23603741824626923, | |
| "learning_rate": 4.786811849714918e-05, | |
| "loss": 0.2722, | |
| "num_input_tokens_seen": 5897344, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 2.623853211009174, | |
| "grad_norm": 0.22983981668949127, | |
| "learning_rate": 4.783863644106502e-05, | |
| "loss": 0.374, | |
| "num_input_tokens_seen": 5931736, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 2.6422018348623855, | |
| "grad_norm": 0.2825419306755066, | |
| "learning_rate": 4.780896113382536e-05, | |
| "loss": 0.3386, | |
| "num_input_tokens_seen": 5972784, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.6605504587155964, | |
| "grad_norm": 0.4502134621143341, | |
| "learning_rate": 4.777909282653042e-05, | |
| "loss": 0.2289, | |
| "num_input_tokens_seen": 6018968, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 2.6788990825688073, | |
| "grad_norm": 0.2428288459777832, | |
| "learning_rate": 4.7749031771913584e-05, | |
| "loss": 0.4061, | |
| "num_input_tokens_seen": 6062520, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 2.6972477064220186, | |
| "grad_norm": 0.2685629725456238, | |
| "learning_rate": 4.771877822433911e-05, | |
| "loss": 0.2198, | |
| "num_input_tokens_seen": 6087928, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 2.7155963302752295, | |
| "grad_norm": 0.24021446704864502, | |
| "learning_rate": 4.7688332439800096e-05, | |
| "loss": 0.34, | |
| "num_input_tokens_seen": 6134792, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 2.7339449541284404, | |
| "grad_norm": 0.2568534314632416, | |
| "learning_rate": 4.765769467591625e-05, | |
| "loss": 0.3292, | |
| "num_input_tokens_seen": 6183296, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.7522935779816513, | |
| "grad_norm": 0.20823974907398224, | |
| "learning_rate": 4.762686519193175e-05, | |
| "loss": 0.2539, | |
| "num_input_tokens_seen": 6225840, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 2.770642201834862, | |
| "grad_norm": 0.23333317041397095, | |
| "learning_rate": 4.759584424871302e-05, | |
| "loss": 0.3571, | |
| "num_input_tokens_seen": 6274760, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 2.7889908256880735, | |
| "grad_norm": 0.20232398808002472, | |
| "learning_rate": 4.756463210874652e-05, | |
| "loss": 0.2783, | |
| "num_input_tokens_seen": 6326168, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 2.8073394495412844, | |
| "grad_norm": 0.3479433059692383, | |
| "learning_rate": 4.7533229036136553e-05, | |
| "loss": 0.2925, | |
| "num_input_tokens_seen": 6360312, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 2.8256880733944953, | |
| "grad_norm": 0.2659524083137512, | |
| "learning_rate": 4.750163529660303e-05, | |
| "loss": 0.2606, | |
| "num_input_tokens_seen": 6395496, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.8440366972477067, | |
| "grad_norm": 0.24823158979415894, | |
| "learning_rate": 4.7469851157479177e-05, | |
| "loss": 0.3721, | |
| "num_input_tokens_seen": 6437064, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 2.8623853211009176, | |
| "grad_norm": 0.32034072279930115, | |
| "learning_rate": 4.743787688770932e-05, | |
| "loss": 0.3931, | |
| "num_input_tokens_seen": 6477616, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 2.8807339449541285, | |
| "grad_norm": 0.23295725882053375, | |
| "learning_rate": 4.740571275784659e-05, | |
| "loss": 0.2201, | |
| "num_input_tokens_seen": 6518680, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 2.8990825688073394, | |
| "grad_norm": 0.2758423984050751, | |
| "learning_rate": 4.737335904005063e-05, | |
| "loss": 0.2579, | |
| "num_input_tokens_seen": 6549768, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 2.9174311926605503, | |
| "grad_norm": 0.26690953969955444, | |
| "learning_rate": 4.734081600808531e-05, | |
| "loss": 0.2575, | |
| "num_input_tokens_seen": 6581000, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.9357798165137616, | |
| "grad_norm": 0.26657482981681824, | |
| "learning_rate": 4.730808393731639e-05, | |
| "loss": 0.2597, | |
| "num_input_tokens_seen": 6612632, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 2.9541284403669725, | |
| "grad_norm": 0.22647295892238617, | |
| "learning_rate": 4.72751631047092e-05, | |
| "loss": 0.3335, | |
| "num_input_tokens_seen": 6654288, | |
| "step": 162 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1080, | |
| "num_input_tokens_seen": 6654288, | |
| "num_train_epochs": 20, | |
| "save_steps": 54, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.613668673991475e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |