{ "best_metric": 0.6280399320587036, "best_model_checkpoint": "train/20241107-Compress:16x-Lr:5e-5-Llama3-8B-instruct-GPT2-Large-RAG-no-ft_token-onlySquad-everymem/checkpoint-2000", "epoch": 2.9476787030213707, "eval_steps": 250, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0014738393515106854, "grad_norm": 12.329447434814407, "learning_rate": 1.0000000000000002e-06, "loss": 4.6517, "step": 1 }, { "epoch": 0.0029476787030213707, "grad_norm": 13.160015373800741, "learning_rate": 2.0000000000000003e-06, "loss": 4.8694, "step": 2 }, { "epoch": 0.004421518054532056, "grad_norm": 12.280388954787197, "learning_rate": 3e-06, "loss": 4.5873, "step": 3 }, { "epoch": 0.0058953574060427415, "grad_norm": 11.881848739475412, "learning_rate": 4.000000000000001e-06, "loss": 4.8303, "step": 4 }, { "epoch": 0.007369196757553427, "grad_norm": 14.27541828244174, "learning_rate": 5e-06, "loss": 4.9164, "step": 5 }, { "epoch": 0.008843036109064112, "grad_norm": 12.16306896231503, "learning_rate": 6e-06, "loss": 4.822, "step": 6 }, { "epoch": 0.010316875460574797, "grad_norm": 12.028277458479417, "learning_rate": 7.000000000000001e-06, "loss": 5.0014, "step": 7 }, { "epoch": 0.011790714812085483, "grad_norm": 12.790265100757539, "learning_rate": 8.000000000000001e-06, "loss": 4.4441, "step": 8 }, { "epoch": 0.013264554163596167, "grad_norm": 13.067252868685893, "learning_rate": 9e-06, "loss": 4.4297, "step": 9 }, { "epoch": 0.014738393515106854, "grad_norm": 10.370150616250033, "learning_rate": 1e-05, "loss": 3.9395, "step": 10 }, { "epoch": 0.016212232866617538, "grad_norm": 10.222695804996077, "learning_rate": 1.1000000000000001e-05, "loss": 3.9828, "step": 11 }, { "epoch": 0.017686072218128224, "grad_norm": 15.472631102447375, "learning_rate": 1.2e-05, "loss": 3.8695, "step": 12 }, { "epoch": 0.01915991156963891, "grad_norm": 10.732053103025178, "learning_rate": 1.3000000000000001e-05, "loss": 3.42, "step": 13 }, { "epoch": 0.020633750921149593, "grad_norm": 11.278153520243102, "learning_rate": 1.4000000000000001e-05, "loss": 3.1193, "step": 14 }, { "epoch": 0.02210759027266028, "grad_norm": 9.542489051083006, "learning_rate": 1.5e-05, "loss": 2.6316, "step": 15 }, { "epoch": 0.023581429624170966, "grad_norm": 9.603695364839751, "learning_rate": 1.6000000000000003e-05, "loss": 2.8228, "step": 16 }, { "epoch": 0.025055268975681652, "grad_norm": 8.756547058860757, "learning_rate": 1.7000000000000003e-05, "loss": 2.3643, "step": 17 }, { "epoch": 0.026529108327192335, "grad_norm": 7.696390361141024, "learning_rate": 1.8e-05, "loss": 2.2024, "step": 18 }, { "epoch": 0.02800294767870302, "grad_norm": 6.924276860899391, "learning_rate": 1.9e-05, "loss": 2.2313, "step": 19 }, { "epoch": 0.029476787030213707, "grad_norm": 6.145567945364672, "learning_rate": 2e-05, "loss": 1.9094, "step": 20 }, { "epoch": 0.030950626381724394, "grad_norm": 7.234561398702191, "learning_rate": 2.1e-05, "loss": 1.8546, "step": 21 }, { "epoch": 0.032424465733235076, "grad_norm": 5.791110810242186, "learning_rate": 2.2000000000000003e-05, "loss": 1.5955, "step": 22 }, { "epoch": 0.03389830508474576, "grad_norm": 5.564590232822945, "learning_rate": 2.3000000000000003e-05, "loss": 1.8265, "step": 23 }, { "epoch": 0.03537214443625645, "grad_norm": 5.638744093482362, "learning_rate": 2.4e-05, "loss": 1.6518, "step": 24 }, { "epoch": 0.036845983787767135, "grad_norm": 5.508233236922161, "learning_rate": 2.5e-05, "loss": 1.5391, "step": 25 }, { "epoch": 0.03831982313927782, "grad_norm": 5.417976670922923, "learning_rate": 2.6000000000000002e-05, "loss": 1.4789, "step": 26 }, { "epoch": 0.0397936624907885, "grad_norm": 5.046895785923721, "learning_rate": 2.7000000000000002e-05, "loss": 1.3845, "step": 27 }, { "epoch": 0.04126750184229919, "grad_norm": 4.620353220198054, "learning_rate": 2.8000000000000003e-05, "loss": 1.3114, "step": 28 }, { "epoch": 0.04274134119380987, "grad_norm": 4.457906304464548, "learning_rate": 2.9e-05, "loss": 1.1748, "step": 29 }, { "epoch": 0.04421518054532056, "grad_norm": 4.322839036114266, "learning_rate": 3e-05, "loss": 1.2295, "step": 30 }, { "epoch": 0.045689019896831246, "grad_norm": 3.8201252710063893, "learning_rate": 3.1e-05, "loss": 1.1997, "step": 31 }, { "epoch": 0.04716285924834193, "grad_norm": 4.247596958933028, "learning_rate": 3.2000000000000005e-05, "loss": 1.2423, "step": 32 }, { "epoch": 0.04863669859985262, "grad_norm": 4.038693911116616, "learning_rate": 3.3e-05, "loss": 1.1828, "step": 33 }, { "epoch": 0.050110537951363304, "grad_norm": 4.093308752609489, "learning_rate": 3.4000000000000007e-05, "loss": 1.2044, "step": 34 }, { "epoch": 0.051584377302873984, "grad_norm": 4.047943563301594, "learning_rate": 3.5e-05, "loss": 1.4093, "step": 35 }, { "epoch": 0.05305821665438467, "grad_norm": 3.3654882830068864, "learning_rate": 3.6e-05, "loss": 1.2194, "step": 36 }, { "epoch": 0.054532056005895356, "grad_norm": 4.235411344725941, "learning_rate": 3.7e-05, "loss": 1.2096, "step": 37 }, { "epoch": 0.05600589535740604, "grad_norm": 3.8719115716594046, "learning_rate": 3.8e-05, "loss": 1.1598, "step": 38 }, { "epoch": 0.05747973470891673, "grad_norm": 3.916213367825352, "learning_rate": 3.9000000000000006e-05, "loss": 1.1067, "step": 39 }, { "epoch": 0.058953574060427415, "grad_norm": 3.7242370643429483, "learning_rate": 4e-05, "loss": 1.0433, "step": 40 }, { "epoch": 0.0604274134119381, "grad_norm": 6.326469148233074, "learning_rate": 4.1e-05, "loss": 1.1784, "step": 41 }, { "epoch": 0.06190125276344879, "grad_norm": 4.2222953310431555, "learning_rate": 4.2e-05, "loss": 1.0625, "step": 42 }, { "epoch": 0.06337509211495947, "grad_norm": 3.9824357642903947, "learning_rate": 4.3e-05, "loss": 0.9374, "step": 43 }, { "epoch": 0.06484893146647015, "grad_norm": 4.034315259802897, "learning_rate": 4.4000000000000006e-05, "loss": 1.021, "step": 44 }, { "epoch": 0.06632277081798084, "grad_norm": 5.667350204231457, "learning_rate": 4.5e-05, "loss": 1.0723, "step": 45 }, { "epoch": 0.06779661016949153, "grad_norm": 3.6301911115123837, "learning_rate": 4.600000000000001e-05, "loss": 1.0347, "step": 46 }, { "epoch": 0.06927044952100221, "grad_norm": 4.455717061879318, "learning_rate": 4.7e-05, "loss": 0.9665, "step": 47 }, { "epoch": 0.0707442888725129, "grad_norm": 3.5367344489569703, "learning_rate": 4.8e-05, "loss": 0.9322, "step": 48 }, { "epoch": 0.07221812822402358, "grad_norm": 4.413604226418139, "learning_rate": 4.9e-05, "loss": 1.0983, "step": 49 }, { "epoch": 0.07369196757553427, "grad_norm": 3.3463499709918167, "learning_rate": 5e-05, "loss": 0.9691, "step": 50 }, { "epoch": 0.07516580692704496, "grad_norm": 5.520702931525504, "learning_rate": 4.9999992358301984e-05, "loss": 1.0616, "step": 51 }, { "epoch": 0.07663964627855564, "grad_norm": 3.841992728628082, "learning_rate": 4.99999694332126e-05, "loss": 1.0268, "step": 52 }, { "epoch": 0.07811348563006633, "grad_norm": 3.332762303714305, "learning_rate": 4.999993122474586e-05, "loss": 0.8452, "step": 53 }, { "epoch": 0.079587324981577, "grad_norm": 4.865714203807573, "learning_rate": 4.999987773292513e-05, "loss": 1.0923, "step": 54 }, { "epoch": 0.08106116433308769, "grad_norm": 4.118796799528433, "learning_rate": 4.999980895778311e-05, "loss": 0.9789, "step": 55 }, { "epoch": 0.08253500368459837, "grad_norm": 4.577711275434509, "learning_rate": 4.9999724899361844e-05, "loss": 1.0584, "step": 56 }, { "epoch": 0.08400884303610906, "grad_norm": 7.060884274009668, "learning_rate": 4.999962555771271e-05, "loss": 1.0576, "step": 57 }, { "epoch": 0.08548268238761975, "grad_norm": 3.4115390137117934, "learning_rate": 4.9999510932896456e-05, "loss": 0.8324, "step": 58 }, { "epoch": 0.08695652173913043, "grad_norm": 3.5966269214497584, "learning_rate": 4.999938102498315e-05, "loss": 0.9287, "step": 59 }, { "epoch": 0.08843036109064112, "grad_norm": 3.3796875507920854, "learning_rate": 4.9999235834052204e-05, "loss": 0.8617, "step": 60 }, { "epoch": 0.0899042004421518, "grad_norm": 3.1841155391030367, "learning_rate": 4.9999075360192384e-05, "loss": 1.003, "step": 61 }, { "epoch": 0.09137803979366249, "grad_norm": 4.5203098163933015, "learning_rate": 4.9998899603501784e-05, "loss": 0.8672, "step": 62 }, { "epoch": 0.09285187914517318, "grad_norm": 3.829868962608506, "learning_rate": 4.999870856408787e-05, "loss": 0.8179, "step": 63 }, { "epoch": 0.09432571849668386, "grad_norm": 2.9720642863902733, "learning_rate": 4.999850224206741e-05, "loss": 0.8379, "step": 64 }, { "epoch": 0.09579955784819455, "grad_norm": 3.0610514737885586, "learning_rate": 4.999828063756655e-05, "loss": 0.8232, "step": 65 }, { "epoch": 0.09727339719970524, "grad_norm": 3.397681141137411, "learning_rate": 4.999804375072076e-05, "loss": 0.839, "step": 66 }, { "epoch": 0.09874723655121592, "grad_norm": 3.3456167553978777, "learning_rate": 4.999779158167485e-05, "loss": 0.8486, "step": 67 }, { "epoch": 0.10022107590272661, "grad_norm": 3.432660111529276, "learning_rate": 4.999752413058299e-05, "loss": 0.9253, "step": 68 }, { "epoch": 0.1016949152542373, "grad_norm": 3.287216139457484, "learning_rate": 4.9997241397608685e-05, "loss": 0.8577, "step": 69 }, { "epoch": 0.10316875460574797, "grad_norm": 3.213099287961976, "learning_rate": 4.999694338292478e-05, "loss": 0.8935, "step": 70 }, { "epoch": 0.10464259395725865, "grad_norm": 4.0888857297839065, "learning_rate": 4.999663008671344e-05, "loss": 0.8001, "step": 71 }, { "epoch": 0.10611643330876934, "grad_norm": 2.95356190189493, "learning_rate": 4.999630150916622e-05, "loss": 0.8685, "step": 72 }, { "epoch": 0.10759027266028003, "grad_norm": 3.2634905542745725, "learning_rate": 4.999595765048398e-05, "loss": 0.9747, "step": 73 }, { "epoch": 0.10906411201179071, "grad_norm": 3.679708363338213, "learning_rate": 4.999559851087694e-05, "loss": 0.8448, "step": 74 }, { "epoch": 0.1105379513633014, "grad_norm": 3.2069830757267876, "learning_rate": 4.9995224090564645e-05, "loss": 0.8043, "step": 75 }, { "epoch": 0.11201179071481208, "grad_norm": 3.0537332668775075, "learning_rate": 4.9994834389776005e-05, "loss": 0.7834, "step": 76 }, { "epoch": 0.11348563006632277, "grad_norm": 3.3167196783944264, "learning_rate": 4.999442940874923e-05, "loss": 0.849, "step": 77 }, { "epoch": 0.11495946941783346, "grad_norm": 4.654708709617253, "learning_rate": 4.999400914773193e-05, "loss": 0.8192, "step": 78 }, { "epoch": 0.11643330876934414, "grad_norm": 3.847093446108797, "learning_rate": 4.9993573606981026e-05, "loss": 0.8459, "step": 79 }, { "epoch": 0.11790714812085483, "grad_norm": 3.613296294309897, "learning_rate": 4.999312278676276e-05, "loss": 0.8567, "step": 80 }, { "epoch": 0.11938098747236552, "grad_norm": 3.4641448372917885, "learning_rate": 4.999265668735274e-05, "loss": 0.8859, "step": 81 }, { "epoch": 0.1208548268238762, "grad_norm": 3.487949881027334, "learning_rate": 4.9992175309035916e-05, "loss": 0.8156, "step": 82 }, { "epoch": 0.12232866617538689, "grad_norm": 3.9405990999052816, "learning_rate": 4.999167865210657e-05, "loss": 0.889, "step": 83 }, { "epoch": 0.12380250552689757, "grad_norm": 3.128789663821621, "learning_rate": 4.999116671686832e-05, "loss": 0.712, "step": 84 }, { "epoch": 0.12527634487840825, "grad_norm": 3.2557208255426433, "learning_rate": 4.999063950363413e-05, "loss": 0.9125, "step": 85 }, { "epoch": 0.12675018422991893, "grad_norm": 2.894655294501716, "learning_rate": 4.999009701272632e-05, "loss": 0.7371, "step": 86 }, { "epoch": 0.12822402358142962, "grad_norm": 3.8726797232840906, "learning_rate": 4.998953924447651e-05, "loss": 0.8491, "step": 87 }, { "epoch": 0.1296978629329403, "grad_norm": 3.3920675979572295, "learning_rate": 4.9988966199225706e-05, "loss": 0.6713, "step": 88 }, { "epoch": 0.131171702284451, "grad_norm": 3.3190797918508754, "learning_rate": 4.998837787732422e-05, "loss": 0.7912, "step": 89 }, { "epoch": 0.13264554163596168, "grad_norm": 3.067090544914768, "learning_rate": 4.998777427913172e-05, "loss": 0.8257, "step": 90 }, { "epoch": 0.13411938098747236, "grad_norm": 3.0764088760388795, "learning_rate": 4.99871554050172e-05, "loss": 0.7062, "step": 91 }, { "epoch": 0.13559322033898305, "grad_norm": 4.089416539889126, "learning_rate": 4.9986521255359004e-05, "loss": 0.8995, "step": 92 }, { "epoch": 0.13706705969049374, "grad_norm": 3.737629386167752, "learning_rate": 4.9985871830544806e-05, "loss": 0.9262, "step": 93 }, { "epoch": 0.13854089904200442, "grad_norm": 3.4233005289092673, "learning_rate": 4.998520713097163e-05, "loss": 0.7893, "step": 94 }, { "epoch": 0.1400147383935151, "grad_norm": 3.9138653795017406, "learning_rate": 4.998452715704583e-05, "loss": 0.7559, "step": 95 }, { "epoch": 0.1414885777450258, "grad_norm": 3.1170404920594446, "learning_rate": 4.998383190918309e-05, "loss": 0.809, "step": 96 }, { "epoch": 0.14296241709653648, "grad_norm": 2.9289448928624116, "learning_rate": 4.998312138780845e-05, "loss": 0.7276, "step": 97 }, { "epoch": 0.14443625644804717, "grad_norm": 2.98517042814081, "learning_rate": 4.998239559335627e-05, "loss": 0.7405, "step": 98 }, { "epoch": 0.14591009579955785, "grad_norm": 3.058021384674008, "learning_rate": 4.998165452627025e-05, "loss": 0.8767, "step": 99 }, { "epoch": 0.14738393515106854, "grad_norm": 2.5338489706228575, "learning_rate": 4.9980898187003444e-05, "loss": 0.7543, "step": 100 }, { "epoch": 0.14885777450257923, "grad_norm": 2.99807900277981, "learning_rate": 4.998012657601823e-05, "loss": 0.9056, "step": 101 }, { "epoch": 0.1503316138540899, "grad_norm": 3.966753359790249, "learning_rate": 4.99793396937863e-05, "loss": 0.8474, "step": 102 }, { "epoch": 0.1518054532056006, "grad_norm": 3.007961834259588, "learning_rate": 4.997853754078873e-05, "loss": 0.7155, "step": 103 }, { "epoch": 0.15327929255711129, "grad_norm": 3.3433615200366993, "learning_rate": 4.997772011751589e-05, "loss": 0.853, "step": 104 }, { "epoch": 0.15475313190862197, "grad_norm": 2.9054570910965327, "learning_rate": 4.99768874244675e-05, "loss": 0.7344, "step": 105 }, { "epoch": 0.15622697126013266, "grad_norm": 4.592923252161323, "learning_rate": 4.997603946215262e-05, "loss": 0.8149, "step": 106 }, { "epoch": 0.15770081061164334, "grad_norm": 4.372117318997081, "learning_rate": 4.997517623108964e-05, "loss": 0.8956, "step": 107 }, { "epoch": 0.159174649963154, "grad_norm": 3.318757247198493, "learning_rate": 4.997429773180628e-05, "loss": 0.726, "step": 108 }, { "epoch": 0.1606484893146647, "grad_norm": 3.954303671282624, "learning_rate": 4.997340396483959e-05, "loss": 0.7776, "step": 109 }, { "epoch": 0.16212232866617537, "grad_norm": 3.064138791439305, "learning_rate": 4.997249493073598e-05, "loss": 0.7783, "step": 110 }, { "epoch": 0.16359616801768606, "grad_norm": 4.294445779944691, "learning_rate": 4.9971570630051166e-05, "loss": 0.8027, "step": 111 }, { "epoch": 0.16507000736919675, "grad_norm": 3.278056452555407, "learning_rate": 4.99706310633502e-05, "loss": 0.7253, "step": 112 }, { "epoch": 0.16654384672070743, "grad_norm": 3.080097631418099, "learning_rate": 4.9969676231207494e-05, "loss": 0.7492, "step": 113 }, { "epoch": 0.16801768607221812, "grad_norm": 3.128255293016171, "learning_rate": 4.996870613420675e-05, "loss": 0.8157, "step": 114 }, { "epoch": 0.1694915254237288, "grad_norm": 2.894928898440576, "learning_rate": 4.996772077294103e-05, "loss": 0.8165, "step": 115 }, { "epoch": 0.1709653647752395, "grad_norm": 5.343425540108662, "learning_rate": 4.996672014801271e-05, "loss": 0.9843, "step": 116 }, { "epoch": 0.17243920412675018, "grad_norm": 3.0929875831194433, "learning_rate": 4.996570426003354e-05, "loss": 0.7303, "step": 117 }, { "epoch": 0.17391304347826086, "grad_norm": 3.1212211649719643, "learning_rate": 4.996467310962453e-05, "loss": 0.8305, "step": 118 }, { "epoch": 0.17538688282977155, "grad_norm": 3.201477669243157, "learning_rate": 4.9963626697416085e-05, "loss": 0.6772, "step": 119 }, { "epoch": 0.17686072218128224, "grad_norm": 3.839124920795194, "learning_rate": 4.99625650240479e-05, "loss": 0.8638, "step": 120 }, { "epoch": 0.17833456153279292, "grad_norm": 3.3258085830852084, "learning_rate": 4.9961488090169015e-05, "loss": 0.878, "step": 121 }, { "epoch": 0.1798084008843036, "grad_norm": 3.4438275447914286, "learning_rate": 4.9960395896437814e-05, "loss": 0.8101, "step": 122 }, { "epoch": 0.1812822402358143, "grad_norm": 3.759176090143821, "learning_rate": 4.995928844352198e-05, "loss": 0.7858, "step": 123 }, { "epoch": 0.18275607958732498, "grad_norm": 3.331016895948772, "learning_rate": 4.995816573209854e-05, "loss": 0.7199, "step": 124 }, { "epoch": 0.18422991893883567, "grad_norm": 3.756734522895209, "learning_rate": 4.995702776285385e-05, "loss": 0.896, "step": 125 }, { "epoch": 0.18570375829034635, "grad_norm": 2.7367722819954414, "learning_rate": 4.995587453648359e-05, "loss": 0.7133, "step": 126 }, { "epoch": 0.18717759764185704, "grad_norm": 3.286685764445543, "learning_rate": 4.995470605369277e-05, "loss": 0.77, "step": 127 }, { "epoch": 0.18865143699336773, "grad_norm": 2.9384153847175063, "learning_rate": 4.995352231519572e-05, "loss": 0.8405, "step": 128 }, { "epoch": 0.1901252763448784, "grad_norm": 2.973645801233948, "learning_rate": 4.995232332171611e-05, "loss": 0.7966, "step": 129 }, { "epoch": 0.1915991156963891, "grad_norm": 2.726342834543162, "learning_rate": 4.995110907398693e-05, "loss": 0.7462, "step": 130 }, { "epoch": 0.19307295504789979, "grad_norm": 3.7426368905452496, "learning_rate": 4.994987957275048e-05, "loss": 0.8397, "step": 131 }, { "epoch": 0.19454679439941047, "grad_norm": 3.684353795528464, "learning_rate": 4.994863481875841e-05, "loss": 0.8523, "step": 132 }, { "epoch": 0.19602063375092116, "grad_norm": 2.790021459025233, "learning_rate": 4.9947374812771675e-05, "loss": 0.732, "step": 133 }, { "epoch": 0.19749447310243184, "grad_norm": 3.9922736171683395, "learning_rate": 4.9946099555560565e-05, "loss": 0.9114, "step": 134 }, { "epoch": 0.19896831245394253, "grad_norm": 2.778951316470212, "learning_rate": 4.9944809047904695e-05, "loss": 0.7061, "step": 135 }, { "epoch": 0.20044215180545322, "grad_norm": 3.550253985278427, "learning_rate": 4.9943503290593e-05, "loss": 0.8602, "step": 136 }, { "epoch": 0.2019159911569639, "grad_norm": 3.1593599011582056, "learning_rate": 4.994218228442372e-05, "loss": 0.7798, "step": 137 }, { "epoch": 0.2033898305084746, "grad_norm": 4.326218608664058, "learning_rate": 4.994084603020444e-05, "loss": 0.9498, "step": 138 }, { "epoch": 0.20486366985998525, "grad_norm": 3.4184484875379773, "learning_rate": 4.993949452875207e-05, "loss": 0.7909, "step": 139 }, { "epoch": 0.20633750921149593, "grad_norm": 3.472476504021861, "learning_rate": 4.993812778089283e-05, "loss": 0.7026, "step": 140 }, { "epoch": 0.20781134856300662, "grad_norm": 3.320703102024762, "learning_rate": 4.993674578746225e-05, "loss": 0.78, "step": 141 }, { "epoch": 0.2092851879145173, "grad_norm": 2.9839611465542757, "learning_rate": 4.99353485493052e-05, "loss": 0.8597, "step": 142 }, { "epoch": 0.210759027266028, "grad_norm": 4.317202892407187, "learning_rate": 4.993393606727587e-05, "loss": 0.9759, "step": 143 }, { "epoch": 0.21223286661753868, "grad_norm": 3.1272612973240217, "learning_rate": 4.993250834223774e-05, "loss": 0.7259, "step": 144 }, { "epoch": 0.21370670596904937, "grad_norm": 2.985030017490991, "learning_rate": 4.9931065375063646e-05, "loss": 0.7123, "step": 145 }, { "epoch": 0.21518054532056005, "grad_norm": 2.815917926415922, "learning_rate": 4.992960716663572e-05, "loss": 0.7078, "step": 146 }, { "epoch": 0.21665438467207074, "grad_norm": 3.1556418560059165, "learning_rate": 4.992813371784542e-05, "loss": 0.7496, "step": 147 }, { "epoch": 0.21812822402358142, "grad_norm": 3.4966317727160354, "learning_rate": 4.992664502959351e-05, "loss": 0.6527, "step": 148 }, { "epoch": 0.2196020633750921, "grad_norm": 3.168309053518289, "learning_rate": 4.99251411027901e-05, "loss": 0.6767, "step": 149 }, { "epoch": 0.2210759027266028, "grad_norm": 2.820181296723088, "learning_rate": 4.992362193835456e-05, "loss": 0.685, "step": 150 }, { "epoch": 0.22254974207811348, "grad_norm": 4.364018199571515, "learning_rate": 4.9922087537215636e-05, "loss": 0.6786, "step": 151 }, { "epoch": 0.22402358142962417, "grad_norm": 3.668691480647532, "learning_rate": 4.992053790031136e-05, "loss": 0.8102, "step": 152 }, { "epoch": 0.22549742078113486, "grad_norm": 3.3837728568785823, "learning_rate": 4.991897302858907e-05, "loss": 0.8222, "step": 153 }, { "epoch": 0.22697126013264554, "grad_norm": 4.4107850456849835, "learning_rate": 4.9917392923005435e-05, "loss": 0.7573, "step": 154 }, { "epoch": 0.22844509948415623, "grad_norm": 2.821211653057107, "learning_rate": 4.991579758452644e-05, "loss": 0.6623, "step": 155 }, { "epoch": 0.22991893883566691, "grad_norm": 3.4255883261491045, "learning_rate": 4.9914187014127346e-05, "loss": 0.7783, "step": 156 }, { "epoch": 0.2313927781871776, "grad_norm": 3.1359158411119106, "learning_rate": 4.9912561212792776e-05, "loss": 0.8081, "step": 157 }, { "epoch": 0.2328666175386883, "grad_norm": 3.817406170984112, "learning_rate": 4.991092018151663e-05, "loss": 0.6327, "step": 158 }, { "epoch": 0.23434045689019897, "grad_norm": 3.1721352155711613, "learning_rate": 4.990926392130213e-05, "loss": 0.7125, "step": 159 }, { "epoch": 0.23581429624170966, "grad_norm": 4.417772742391574, "learning_rate": 4.990759243316181e-05, "loss": 0.6484, "step": 160 }, { "epoch": 0.23728813559322035, "grad_norm": 3.4393017295257406, "learning_rate": 4.990590571811751e-05, "loss": 0.7863, "step": 161 }, { "epoch": 0.23876197494473103, "grad_norm": 3.7051041219600602, "learning_rate": 4.990420377720038e-05, "loss": 0.6519, "step": 162 }, { "epoch": 0.24023581429624172, "grad_norm": 2.6986519733275225, "learning_rate": 4.990248661145087e-05, "loss": 0.6894, "step": 163 }, { "epoch": 0.2417096536477524, "grad_norm": 3.5987060870677716, "learning_rate": 4.9900754221918766e-05, "loss": 0.6871, "step": 164 }, { "epoch": 0.2431834929992631, "grad_norm": 4.285288444434278, "learning_rate": 4.989900660966311e-05, "loss": 0.7489, "step": 165 }, { "epoch": 0.24465733235077378, "grad_norm": 3.228840538701971, "learning_rate": 4.9897243775752304e-05, "loss": 0.864, "step": 166 }, { "epoch": 0.24613117170228446, "grad_norm": 2.66638708635849, "learning_rate": 4.9895465721264026e-05, "loss": 0.6366, "step": 167 }, { "epoch": 0.24760501105379515, "grad_norm": 2.8363122613628984, "learning_rate": 4.989367244728526e-05, "loss": 0.6753, "step": 168 }, { "epoch": 0.24907885040530583, "grad_norm": 3.0315641260098496, "learning_rate": 4.989186395491229e-05, "loss": 0.6393, "step": 169 }, { "epoch": 0.2505526897568165, "grad_norm": 3.3938973804036765, "learning_rate": 4.989004024525073e-05, "loss": 0.6752, "step": 170 }, { "epoch": 0.2520265291083272, "grad_norm": 2.5145209122700507, "learning_rate": 4.9888201319415464e-05, "loss": 0.6309, "step": 171 }, { "epoch": 0.25350036845983787, "grad_norm": 3.7994559350282877, "learning_rate": 4.988634717853071e-05, "loss": 0.6897, "step": 172 }, { "epoch": 0.25497420781134855, "grad_norm": 2.5599681162338785, "learning_rate": 4.9884477823729956e-05, "loss": 0.7459, "step": 173 }, { "epoch": 0.25644804716285924, "grad_norm": 3.3655259708439043, "learning_rate": 4.9882593256156014e-05, "loss": 0.9192, "step": 174 }, { "epoch": 0.2579218865143699, "grad_norm": 2.670619379560367, "learning_rate": 4.9880693476960986e-05, "loss": 0.7027, "step": 175 }, { "epoch": 0.2593957258658806, "grad_norm": 3.3604262015831594, "learning_rate": 4.987877848730627e-05, "loss": 0.7789, "step": 176 }, { "epoch": 0.2608695652173913, "grad_norm": 2.950189655479101, "learning_rate": 4.987684828836257e-05, "loss": 0.6618, "step": 177 }, { "epoch": 0.262343404568902, "grad_norm": 2.664086931849342, "learning_rate": 4.9874902881309895e-05, "loss": 0.5992, "step": 178 }, { "epoch": 0.26381724392041267, "grad_norm": 3.283589573525553, "learning_rate": 4.9872942267337526e-05, "loss": 0.7167, "step": 179 }, { "epoch": 0.26529108327192336, "grad_norm": 3.0838062507932693, "learning_rate": 4.987096644764406e-05, "loss": 0.7894, "step": 180 }, { "epoch": 0.26676492262343404, "grad_norm": 2.741195716720523, "learning_rate": 4.9868975423437406e-05, "loss": 0.7343, "step": 181 }, { "epoch": 0.26823876197494473, "grad_norm": 3.8275984421422202, "learning_rate": 4.9866969195934724e-05, "loss": 0.7817, "step": 182 }, { "epoch": 0.2697126013264554, "grad_norm": 3.0732311712842755, "learning_rate": 4.9864947766362505e-05, "loss": 0.6949, "step": 183 }, { "epoch": 0.2711864406779661, "grad_norm": 3.3662701483405764, "learning_rate": 4.986291113595652e-05, "loss": 0.8558, "step": 184 }, { "epoch": 0.2726602800294768, "grad_norm": 2.6605939463012254, "learning_rate": 4.9860859305961836e-05, "loss": 0.642, "step": 185 }, { "epoch": 0.2741341193809875, "grad_norm": 2.878904593685921, "learning_rate": 4.9858792277632805e-05, "loss": 0.7436, "step": 186 }, { "epoch": 0.27560795873249816, "grad_norm": 3.0575591733357683, "learning_rate": 4.985671005223307e-05, "loss": 0.8218, "step": 187 }, { "epoch": 0.27708179808400885, "grad_norm": 3.040633161010454, "learning_rate": 4.985461263103559e-05, "loss": 0.7678, "step": 188 }, { "epoch": 0.27855563743551953, "grad_norm": 2.734404907063009, "learning_rate": 4.985250001532258e-05, "loss": 0.6922, "step": 189 }, { "epoch": 0.2800294767870302, "grad_norm": 2.4399081341068682, "learning_rate": 4.985037220638555e-05, "loss": 0.7589, "step": 190 }, { "epoch": 0.2815033161385409, "grad_norm": 3.1246111818659608, "learning_rate": 4.984822920552532e-05, "loss": 0.6833, "step": 191 }, { "epoch": 0.2829771554900516, "grad_norm": 3.368524909771193, "learning_rate": 4.984607101405198e-05, "loss": 0.7492, "step": 192 }, { "epoch": 0.2844509948415623, "grad_norm": 3.6454677870827106, "learning_rate": 4.9843897633284905e-05, "loss": 0.6299, "step": 193 }, { "epoch": 0.28592483419307296, "grad_norm": 3.436409378435394, "learning_rate": 4.9841709064552766e-05, "loss": 0.6792, "step": 194 }, { "epoch": 0.28739867354458365, "grad_norm": 2.7112998170615596, "learning_rate": 4.983950530919351e-05, "loss": 0.6904, "step": 195 }, { "epoch": 0.28887251289609434, "grad_norm": 2.702347483746788, "learning_rate": 4.983728636855438e-05, "loss": 0.6884, "step": 196 }, { "epoch": 0.290346352247605, "grad_norm": 2.642408502270437, "learning_rate": 4.9835052243991874e-05, "loss": 0.7183, "step": 197 }, { "epoch": 0.2918201915991157, "grad_norm": 2.9306830990613815, "learning_rate": 4.983280293687182e-05, "loss": 0.6939, "step": 198 }, { "epoch": 0.2932940309506264, "grad_norm": 2.795268359190247, "learning_rate": 4.9830538448569276e-05, "loss": 0.7312, "step": 199 }, { "epoch": 0.2947678703021371, "grad_norm": 3.1653789277760556, "learning_rate": 4.9828258780468616e-05, "loss": 0.6609, "step": 200 }, { "epoch": 0.29624170965364777, "grad_norm": 3.51307103955603, "learning_rate": 4.9825963933963484e-05, "loss": 0.7224, "step": 201 }, { "epoch": 0.29771554900515845, "grad_norm": 2.4073488773121245, "learning_rate": 4.982365391045679e-05, "loss": 0.6952, "step": 202 }, { "epoch": 0.29918938835666914, "grad_norm": 2.6979848688604795, "learning_rate": 4.9821328711360746e-05, "loss": 0.6675, "step": 203 }, { "epoch": 0.3006632277081798, "grad_norm": 2.6516239948144023, "learning_rate": 4.981898833809683e-05, "loss": 0.6416, "step": 204 }, { "epoch": 0.3021370670596905, "grad_norm": 2.9691601921594093, "learning_rate": 4.9816632792095794e-05, "loss": 0.858, "step": 205 }, { "epoch": 0.3036109064112012, "grad_norm": 2.9816354690321267, "learning_rate": 4.981426207479767e-05, "loss": 0.8966, "step": 206 }, { "epoch": 0.3050847457627119, "grad_norm": 2.3596727802240345, "learning_rate": 4.981187618765175e-05, "loss": 0.6309, "step": 207 }, { "epoch": 0.30655858511422257, "grad_norm": 3.047767234645249, "learning_rate": 4.9809475132116624e-05, "loss": 0.8372, "step": 208 }, { "epoch": 0.30803242446573326, "grad_norm": 3.6584451720594817, "learning_rate": 4.980705890966014e-05, "loss": 0.709, "step": 209 }, { "epoch": 0.30950626381724394, "grad_norm": 3.2345085669318707, "learning_rate": 4.980462752175943e-05, "loss": 0.7293, "step": 210 }, { "epoch": 0.31098010316875463, "grad_norm": 2.413945167430757, "learning_rate": 4.980218096990087e-05, "loss": 0.6602, "step": 211 }, { "epoch": 0.3124539425202653, "grad_norm": 2.6816326232924137, "learning_rate": 4.979971925558013e-05, "loss": 0.6706, "step": 212 }, { "epoch": 0.313927781871776, "grad_norm": 4.507393802654913, "learning_rate": 4.979724238030217e-05, "loss": 0.6977, "step": 213 }, { "epoch": 0.3154016212232867, "grad_norm": 2.401222029150234, "learning_rate": 4.979475034558115e-05, "loss": 0.6336, "step": 214 }, { "epoch": 0.3168754605747974, "grad_norm": 2.9726357177346103, "learning_rate": 4.979224315294058e-05, "loss": 0.7261, "step": 215 }, { "epoch": 0.318349299926308, "grad_norm": 2.6351731581135587, "learning_rate": 4.978972080391317e-05, "loss": 0.6728, "step": 216 }, { "epoch": 0.3198231392778187, "grad_norm": 2.8245872162224197, "learning_rate": 4.978718330004093e-05, "loss": 0.6032, "step": 217 }, { "epoch": 0.3212969786293294, "grad_norm": 2.6392998615168164, "learning_rate": 4.978463064287513e-05, "loss": 0.645, "step": 218 }, { "epoch": 0.32277081798084006, "grad_norm": 2.228882019788393, "learning_rate": 4.978206283397631e-05, "loss": 0.6145, "step": 219 }, { "epoch": 0.32424465733235075, "grad_norm": 2.6417633853218385, "learning_rate": 4.977947987491424e-05, "loss": 0.6426, "step": 220 }, { "epoch": 0.32571849668386144, "grad_norm": 3.131898665863068, "learning_rate": 4.977688176726799e-05, "loss": 0.788, "step": 221 }, { "epoch": 0.3271923360353721, "grad_norm": 2.768759637475732, "learning_rate": 4.977426851262588e-05, "loss": 0.8008, "step": 222 }, { "epoch": 0.3286661753868828, "grad_norm": 2.5739778397264956, "learning_rate": 4.977164011258547e-05, "loss": 0.7031, "step": 223 }, { "epoch": 0.3301400147383935, "grad_norm": 3.4447836264551164, "learning_rate": 4.9768996568753615e-05, "loss": 0.7216, "step": 224 }, { "epoch": 0.3316138540899042, "grad_norm": 3.442508585911545, "learning_rate": 4.97663378827464e-05, "loss": 0.6635, "step": 225 }, { "epoch": 0.33308769344141487, "grad_norm": 2.9105275166909244, "learning_rate": 4.9763664056189165e-05, "loss": 0.792, "step": 226 }, { "epoch": 0.33456153279292555, "grad_norm": 2.4105338074474134, "learning_rate": 4.9760975090716536e-05, "loss": 0.6441, "step": 227 }, { "epoch": 0.33603537214443624, "grad_norm": 4.364241751306036, "learning_rate": 4.975827098797236e-05, "loss": 0.7779, "step": 228 }, { "epoch": 0.3375092114959469, "grad_norm": 3.1839150108706975, "learning_rate": 4.975555174960975e-05, "loss": 0.6986, "step": 229 }, { "epoch": 0.3389830508474576, "grad_norm": 2.569541838807661, "learning_rate": 4.975281737729108e-05, "loss": 0.5795, "step": 230 }, { "epoch": 0.3404568901989683, "grad_norm": 3.179621365395999, "learning_rate": 4.975006787268797e-05, "loss": 0.7907, "step": 231 }, { "epoch": 0.341930729550479, "grad_norm": 2.5628272987313365, "learning_rate": 4.974730323748129e-05, "loss": 0.6742, "step": 232 }, { "epoch": 0.34340456890198967, "grad_norm": 3.231087751022799, "learning_rate": 4.974452347336116e-05, "loss": 0.6875, "step": 233 }, { "epoch": 0.34487840825350036, "grad_norm": 3.0162842973639625, "learning_rate": 4.9741728582026955e-05, "loss": 0.733, "step": 234 }, { "epoch": 0.34635224760501104, "grad_norm": 3.4015271403586773, "learning_rate": 4.9738918565187276e-05, "loss": 0.7895, "step": 235 }, { "epoch": 0.34782608695652173, "grad_norm": 2.7379674364359046, "learning_rate": 4.9736093424560005e-05, "loss": 0.6629, "step": 236 }, { "epoch": 0.3492999263080324, "grad_norm": 3.1519242661086686, "learning_rate": 4.973325316187224e-05, "loss": 0.7192, "step": 237 }, { "epoch": 0.3507737656595431, "grad_norm": 2.821576709548874, "learning_rate": 4.973039777886035e-05, "loss": 0.6795, "step": 238 }, { "epoch": 0.3522476050110538, "grad_norm": 2.5791684899968206, "learning_rate": 4.9727527277269915e-05, "loss": 0.5789, "step": 239 }, { "epoch": 0.3537214443625645, "grad_norm": 2.890781377738025, "learning_rate": 4.972464165885578e-05, "loss": 0.6122, "step": 240 }, { "epoch": 0.35519528371407516, "grad_norm": 2.7328138854174324, "learning_rate": 4.972174092538203e-05, "loss": 0.6865, "step": 241 }, { "epoch": 0.35666912306558585, "grad_norm": 2.3234592254587523, "learning_rate": 4.9718825078621995e-05, "loss": 0.5775, "step": 242 }, { "epoch": 0.35814296241709653, "grad_norm": 2.7245317564268845, "learning_rate": 4.9715894120358225e-05, "loss": 0.61, "step": 243 }, { "epoch": 0.3596168017686072, "grad_norm": 3.8211384447939367, "learning_rate": 4.9712948052382524e-05, "loss": 0.5938, "step": 244 }, { "epoch": 0.3610906411201179, "grad_norm": 3.3232212385469597, "learning_rate": 4.970998687649593e-05, "loss": 0.8374, "step": 245 }, { "epoch": 0.3625644804716286, "grad_norm": 2.943205466799728, "learning_rate": 4.970701059450872e-05, "loss": 0.5702, "step": 246 }, { "epoch": 0.3640383198231393, "grad_norm": 3.8717927272821138, "learning_rate": 4.970401920824039e-05, "loss": 0.705, "step": 247 }, { "epoch": 0.36551215917464996, "grad_norm": 2.651999090214684, "learning_rate": 4.970101271951969e-05, "loss": 0.6704, "step": 248 }, { "epoch": 0.36698599852616065, "grad_norm": 2.6913079187067126, "learning_rate": 4.969799113018459e-05, "loss": 0.6531, "step": 249 }, { "epoch": 0.36845983787767134, "grad_norm": 2.5245324938974623, "learning_rate": 4.9694954442082296e-05, "loss": 0.6416, "step": 250 }, { "epoch": 0.36845983787767134, "eval_bleu": 0.18672054226165744, "eval_bleu_1gram": 0.49541191454091393, "eval_bleu_2gram": 0.2847971648494783, "eval_bleu_3gram": 0.17405810478515746, "eval_bleu_4gram": 0.11593214790115401, "eval_rag_val_loss": 0.6963785106456408, "eval_rouge1": 0.49914364368379965, "eval_rouge2": 0.2814906483822396, "eval_rougeL": 0.4932983461636626, "step": 250 }, { "epoch": 0.369933677229182, "grad_norm": 3.6691397360816156, "learning_rate": 4.969190265706926e-05, "loss": 0.6161, "step": 251 }, { "epoch": 0.3714075165806927, "grad_norm": 4.300299594112147, "learning_rate": 4.9688835777011126e-05, "loss": 0.6998, "step": 252 }, { "epoch": 0.3728813559322034, "grad_norm": 3.6241896151016904, "learning_rate": 4.96857538037828e-05, "loss": 0.7687, "step": 253 }, { "epoch": 0.3743551952837141, "grad_norm": 2.8836714956034197, "learning_rate": 4.9682656739268385e-05, "loss": 0.6761, "step": 254 }, { "epoch": 0.37582903463522477, "grad_norm": 3.552381232663546, "learning_rate": 4.967954458536126e-05, "loss": 0.7088, "step": 255 }, { "epoch": 0.37730287398673545, "grad_norm": 2.990220342063741, "learning_rate": 4.967641734396396e-05, "loss": 0.69, "step": 256 }, { "epoch": 0.37877671333824614, "grad_norm": 2.5946638037256413, "learning_rate": 4.967327501698831e-05, "loss": 0.6623, "step": 257 }, { "epoch": 0.3802505526897568, "grad_norm": 2.498718887143036, "learning_rate": 4.9670117606355315e-05, "loss": 0.6328, "step": 258 }, { "epoch": 0.3817243920412675, "grad_norm": 2.651785475752445, "learning_rate": 4.966694511399521e-05, "loss": 0.5959, "step": 259 }, { "epoch": 0.3831982313927782, "grad_norm": 3.499226757192851, "learning_rate": 4.966375754184746e-05, "loss": 0.7555, "step": 260 }, { "epoch": 0.3846720707442889, "grad_norm": 3.110544109522898, "learning_rate": 4.966055489186072e-05, "loss": 0.6787, "step": 261 }, { "epoch": 0.38614591009579957, "grad_norm": 3.2829958676124242, "learning_rate": 4.965733716599292e-05, "loss": 0.7696, "step": 262 }, { "epoch": 0.38761974944731026, "grad_norm": 2.7213911184816815, "learning_rate": 4.965410436621115e-05, "loss": 0.7118, "step": 263 }, { "epoch": 0.38909358879882094, "grad_norm": 3.0781243803536813, "learning_rate": 4.9650856494491745e-05, "loss": 0.7584, "step": 264 }, { "epoch": 0.39056742815033163, "grad_norm": 3.533381131286732, "learning_rate": 4.964759355282024e-05, "loss": 0.7717, "step": 265 }, { "epoch": 0.3920412675018423, "grad_norm": 2.179673936589744, "learning_rate": 4.9644315543191376e-05, "loss": 0.6532, "step": 266 }, { "epoch": 0.393515106853353, "grad_norm": 2.4455494141298155, "learning_rate": 4.964102246760914e-05, "loss": 0.6368, "step": 267 }, { "epoch": 0.3949889462048637, "grad_norm": 2.380827630498739, "learning_rate": 4.9637714328086705e-05, "loss": 0.5887, "step": 268 }, { "epoch": 0.3964627855563744, "grad_norm": 2.649094221675118, "learning_rate": 4.963439112664644e-05, "loss": 0.6662, "step": 269 }, { "epoch": 0.39793662490788506, "grad_norm": 2.389973869659719, "learning_rate": 4.963105286531994e-05, "loss": 0.7021, "step": 270 }, { "epoch": 0.39941046425939575, "grad_norm": 2.4611087800018008, "learning_rate": 4.962769954614802e-05, "loss": 0.5836, "step": 271 }, { "epoch": 0.40088430361090643, "grad_norm": 2.706352468052794, "learning_rate": 4.962433117118067e-05, "loss": 0.7838, "step": 272 }, { "epoch": 0.4023581429624171, "grad_norm": 3.9273039792082534, "learning_rate": 4.96209477424771e-05, "loss": 0.8055, "step": 273 }, { "epoch": 0.4038319823139278, "grad_norm": 2.831034981013252, "learning_rate": 4.9617549262105724e-05, "loss": 0.7641, "step": 274 }, { "epoch": 0.4053058216654385, "grad_norm": 2.6274228495006517, "learning_rate": 4.961413573214415e-05, "loss": 0.7543, "step": 275 }, { "epoch": 0.4067796610169492, "grad_norm": 2.4688381710483656, "learning_rate": 4.96107071546792e-05, "loss": 0.6557, "step": 276 }, { "epoch": 0.40825350036845987, "grad_norm": 2.6100411849590834, "learning_rate": 4.960726353180688e-05, "loss": 0.6803, "step": 277 }, { "epoch": 0.4097273397199705, "grad_norm": 3.1808686932850434, "learning_rate": 4.96038048656324e-05, "loss": 0.7644, "step": 278 }, { "epoch": 0.4112011790714812, "grad_norm": 2.835759769471633, "learning_rate": 4.960033115827017e-05, "loss": 0.6785, "step": 279 }, { "epoch": 0.41267501842299187, "grad_norm": 2.556677646820615, "learning_rate": 4.9596842411843784e-05, "loss": 0.7481, "step": 280 }, { "epoch": 0.41414885777450255, "grad_norm": 2.8073262417185156, "learning_rate": 4.9593338628486055e-05, "loss": 0.5913, "step": 281 }, { "epoch": 0.41562269712601324, "grad_norm": 3.1821576395650157, "learning_rate": 4.958981981033895e-05, "loss": 0.6118, "step": 282 }, { "epoch": 0.4170965364775239, "grad_norm": 2.9322581495376197, "learning_rate": 4.958628595955366e-05, "loss": 0.7343, "step": 283 }, { "epoch": 0.4185703758290346, "grad_norm": 3.0805604855729483, "learning_rate": 4.9582737078290554e-05, "loss": 0.636, "step": 284 }, { "epoch": 0.4200442151805453, "grad_norm": 2.3471894522140646, "learning_rate": 4.9579173168719186e-05, "loss": 0.672, "step": 285 }, { "epoch": 0.421518054532056, "grad_norm": 4.951772414886221, "learning_rate": 4.957559423301831e-05, "loss": 0.6231, "step": 286 }, { "epoch": 0.42299189388356667, "grad_norm": 2.5854577486727797, "learning_rate": 4.957200027337585e-05, "loss": 0.6531, "step": 287 }, { "epoch": 0.42446573323507736, "grad_norm": 2.6754966417411667, "learning_rate": 4.9568391291988927e-05, "loss": 0.6216, "step": 288 }, { "epoch": 0.42593957258658804, "grad_norm": 2.9077421890113206, "learning_rate": 4.956476729106384e-05, "loss": 0.6421, "step": 289 }, { "epoch": 0.42741341193809873, "grad_norm": 2.2687798994632007, "learning_rate": 4.9561128272816063e-05, "loss": 0.6122, "step": 290 }, { "epoch": 0.4288872512896094, "grad_norm": 2.720765167208073, "learning_rate": 4.955747423947027e-05, "loss": 0.6712, "step": 291 }, { "epoch": 0.4303610906411201, "grad_norm": 3.236567836579176, "learning_rate": 4.95538051932603e-05, "loss": 0.6963, "step": 292 }, { "epoch": 0.4318349299926308, "grad_norm": 2.20392242501431, "learning_rate": 4.955012113642916e-05, "loss": 0.5796, "step": 293 }, { "epoch": 0.4333087693441415, "grad_norm": 3.6831722402658342, "learning_rate": 4.954642207122907e-05, "loss": 0.5861, "step": 294 }, { "epoch": 0.43478260869565216, "grad_norm": 3.0646487113432737, "learning_rate": 4.954270799992138e-05, "loss": 0.6469, "step": 295 }, { "epoch": 0.43625644804716285, "grad_norm": 2.8314593980839717, "learning_rate": 4.9538978924776634e-05, "loss": 0.7103, "step": 296 }, { "epoch": 0.43773028739867353, "grad_norm": 3.210408485067159, "learning_rate": 4.953523484807456e-05, "loss": 0.6511, "step": 297 }, { "epoch": 0.4392041267501842, "grad_norm": 3.064554887471457, "learning_rate": 4.953147577210405e-05, "loss": 0.5858, "step": 298 }, { "epoch": 0.4406779661016949, "grad_norm": 2.953964679163349, "learning_rate": 4.952770169916315e-05, "loss": 0.6706, "step": 299 }, { "epoch": 0.4421518054532056, "grad_norm": 3.005204454724714, "learning_rate": 4.95239126315591e-05, "loss": 0.6801, "step": 300 }, { "epoch": 0.4436256448047163, "grad_norm": 2.5767035062294017, "learning_rate": 4.9520108571608274e-05, "loss": 0.5707, "step": 301 }, { "epoch": 0.44509948415622697, "grad_norm": 2.437358558659197, "learning_rate": 4.9516289521636244e-05, "loss": 0.6463, "step": 302 }, { "epoch": 0.44657332350773765, "grad_norm": 3.4351405976463534, "learning_rate": 4.951245548397773e-05, "loss": 0.7538, "step": 303 }, { "epoch": 0.44804716285924834, "grad_norm": 3.121112388965778, "learning_rate": 4.950860646097661e-05, "loss": 0.6829, "step": 304 }, { "epoch": 0.449521002210759, "grad_norm": 2.898318882080459, "learning_rate": 4.950474245498594e-05, "loss": 0.6839, "step": 305 }, { "epoch": 0.4509948415622697, "grad_norm": 4.733292156810482, "learning_rate": 4.9500863468367916e-05, "loss": 0.6353, "step": 306 }, { "epoch": 0.4524686809137804, "grad_norm": 2.3480397956829, "learning_rate": 4.9496969503493906e-05, "loss": 0.6229, "step": 307 }, { "epoch": 0.4539425202652911, "grad_norm": 2.363290329592579, "learning_rate": 4.949306056274443e-05, "loss": 0.7819, "step": 308 }, { "epoch": 0.45541635961680177, "grad_norm": 4.0939554643393645, "learning_rate": 4.948913664850917e-05, "loss": 0.5987, "step": 309 }, { "epoch": 0.45689019896831246, "grad_norm": 2.618669232782219, "learning_rate": 4.948519776318694e-05, "loss": 0.6329, "step": 310 }, { "epoch": 0.45836403831982314, "grad_norm": 2.5512535978120874, "learning_rate": 4.948124390918574e-05, "loss": 0.6945, "step": 311 }, { "epoch": 0.45983787767133383, "grad_norm": 2.997034037231594, "learning_rate": 4.9477275088922684e-05, "loss": 0.8929, "step": 312 }, { "epoch": 0.4613117170228445, "grad_norm": 2.565950814861725, "learning_rate": 4.9473291304824066e-05, "loss": 0.5798, "step": 313 }, { "epoch": 0.4627855563743552, "grad_norm": 3.0169001438001115, "learning_rate": 4.9469292559325314e-05, "loss": 0.7081, "step": 314 }, { "epoch": 0.4642593957258659, "grad_norm": 2.7196531878286705, "learning_rate": 4.9465278854871006e-05, "loss": 0.59, "step": 315 }, { "epoch": 0.4657332350773766, "grad_norm": 2.7878510224206154, "learning_rate": 4.946125019391486e-05, "loss": 0.6899, "step": 316 }, { "epoch": 0.46720707442888726, "grad_norm": 2.5500685439527744, "learning_rate": 4.945720657891974e-05, "loss": 0.7389, "step": 317 }, { "epoch": 0.46868091378039795, "grad_norm": 2.8151376012368745, "learning_rate": 4.9453148012357656e-05, "loss": 0.6576, "step": 318 }, { "epoch": 0.47015475313190863, "grad_norm": 2.453917842960269, "learning_rate": 4.944907449670976e-05, "loss": 0.6038, "step": 319 }, { "epoch": 0.4716285924834193, "grad_norm": 2.815158774063597, "learning_rate": 4.944498603446632e-05, "loss": 0.7254, "step": 320 }, { "epoch": 0.47310243183493, "grad_norm": 2.247642235418867, "learning_rate": 4.944088262812678e-05, "loss": 0.5097, "step": 321 }, { "epoch": 0.4745762711864407, "grad_norm": 3.0248340466588677, "learning_rate": 4.9436764280199694e-05, "loss": 0.7059, "step": 322 }, { "epoch": 0.4760501105379514, "grad_norm": 2.7130522381161084, "learning_rate": 4.943263099320275e-05, "loss": 0.687, "step": 323 }, { "epoch": 0.47752394988946206, "grad_norm": 2.3039804182147665, "learning_rate": 4.9428482769662776e-05, "loss": 0.7163, "step": 324 }, { "epoch": 0.47899778924097275, "grad_norm": 2.504872247327865, "learning_rate": 4.9424319612115724e-05, "loss": 0.6511, "step": 325 }, { "epoch": 0.48047162859248344, "grad_norm": 2.8363542907289667, "learning_rate": 4.94201415231067e-05, "loss": 0.6158, "step": 326 }, { "epoch": 0.4819454679439941, "grad_norm": 2.301057808645147, "learning_rate": 4.9415948505189905e-05, "loss": 0.5661, "step": 327 }, { "epoch": 0.4834193072955048, "grad_norm": 2.3109063508137764, "learning_rate": 4.941174056092868e-05, "loss": 0.6087, "step": 328 }, { "epoch": 0.4848931466470155, "grad_norm": 2.333339509501685, "learning_rate": 4.94075176928955e-05, "loss": 0.7552, "step": 329 }, { "epoch": 0.4863669859985262, "grad_norm": 2.693736270595178, "learning_rate": 4.940327990367195e-05, "loss": 0.6215, "step": 330 }, { "epoch": 0.48784082535003687, "grad_norm": 2.21970046196297, "learning_rate": 4.939902719584875e-05, "loss": 0.6275, "step": 331 }, { "epoch": 0.48931466470154755, "grad_norm": 2.3632408958331523, "learning_rate": 4.9394759572025715e-05, "loss": 0.648, "step": 332 }, { "epoch": 0.49078850405305824, "grad_norm": 2.770828008049076, "learning_rate": 4.939047703481182e-05, "loss": 0.5703, "step": 333 }, { "epoch": 0.4922623434045689, "grad_norm": 2.384399985886196, "learning_rate": 4.938617958682511e-05, "loss": 0.6057, "step": 334 }, { "epoch": 0.4937361827560796, "grad_norm": 2.32868100893919, "learning_rate": 4.938186723069279e-05, "loss": 0.6393, "step": 335 }, { "epoch": 0.4952100221075903, "grad_norm": 2.8411331712607875, "learning_rate": 4.9377539969051146e-05, "loss": 0.7434, "step": 336 }, { "epoch": 0.496683861459101, "grad_norm": 2.4021693716882453, "learning_rate": 4.937319780454559e-05, "loss": 0.6897, "step": 337 }, { "epoch": 0.49815770081061167, "grad_norm": 3.2677293048186096, "learning_rate": 4.9368840739830645e-05, "loss": 0.6818, "step": 338 }, { "epoch": 0.49963154016212236, "grad_norm": 2.459231315012088, "learning_rate": 4.936446877756994e-05, "loss": 0.6435, "step": 339 }, { "epoch": 0.501105379513633, "grad_norm": 2.528178293918339, "learning_rate": 4.9360081920436216e-05, "loss": 0.6434, "step": 340 }, { "epoch": 0.5025792188651437, "grad_norm": 2.3248992693009822, "learning_rate": 4.9355680171111305e-05, "loss": 0.5085, "step": 341 }, { "epoch": 0.5040530582166544, "grad_norm": 2.088198004881906, "learning_rate": 4.9351263532286165e-05, "loss": 0.5983, "step": 342 }, { "epoch": 0.505526897568165, "grad_norm": 3.9547950323068064, "learning_rate": 4.934683200666084e-05, "loss": 0.6385, "step": 343 }, { "epoch": 0.5070007369196757, "grad_norm": 2.2295628727365164, "learning_rate": 4.934238559694448e-05, "loss": 0.5656, "step": 344 }, { "epoch": 0.5084745762711864, "grad_norm": 2.3779961609997895, "learning_rate": 4.933792430585534e-05, "loss": 0.6982, "step": 345 }, { "epoch": 0.5099484156226971, "grad_norm": 2.4336579193423398, "learning_rate": 4.933344813612076e-05, "loss": 0.6082, "step": 346 }, { "epoch": 0.5114222549742078, "grad_norm": 2.9065710731267536, "learning_rate": 4.9328957090477183e-05, "loss": 0.7353, "step": 347 }, { "epoch": 0.5128960943257185, "grad_norm": 2.5001912997487525, "learning_rate": 4.932445117167016e-05, "loss": 0.6096, "step": 348 }, { "epoch": 0.5143699336772292, "grad_norm": 2.665305555193469, "learning_rate": 4.9319930382454306e-05, "loss": 0.647, "step": 349 }, { "epoch": 0.5158437730287398, "grad_norm": 2.254208972508059, "learning_rate": 4.931539472559334e-05, "loss": 0.5336, "step": 350 }, { "epoch": 0.5173176123802505, "grad_norm": 2.051104187743044, "learning_rate": 4.9310844203860084e-05, "loss": 0.6415, "step": 351 }, { "epoch": 0.5187914517317612, "grad_norm": 2.4763727446342627, "learning_rate": 4.9306278820036434e-05, "loss": 0.6563, "step": 352 }, { "epoch": 0.5202652910832719, "grad_norm": 3.1541349670617924, "learning_rate": 4.930169857691336e-05, "loss": 0.5822, "step": 353 }, { "epoch": 0.5217391304347826, "grad_norm": 3.3378194820351386, "learning_rate": 4.929710347729094e-05, "loss": 0.6608, "step": 354 }, { "epoch": 0.5232129697862933, "grad_norm": 2.1034732343250706, "learning_rate": 4.929249352397831e-05, "loss": 0.583, "step": 355 }, { "epoch": 0.524686809137804, "grad_norm": 4.918238092368805, "learning_rate": 4.9287868719793717e-05, "loss": 0.6182, "step": 356 }, { "epoch": 0.5261606484893147, "grad_norm": 2.726851308659824, "learning_rate": 4.928322906756446e-05, "loss": 0.5914, "step": 357 }, { "epoch": 0.5276344878408253, "grad_norm": 3.2087323489742046, "learning_rate": 4.927857457012692e-05, "loss": 0.5788, "step": 358 }, { "epoch": 0.529108327192336, "grad_norm": 3.096645656989377, "learning_rate": 4.927390523032658e-05, "loss": 0.6642, "step": 359 }, { "epoch": 0.5305821665438467, "grad_norm": 3.6150615863117945, "learning_rate": 4.926922105101794e-05, "loss": 0.5889, "step": 360 }, { "epoch": 0.5320560058953574, "grad_norm": 2.69375751255342, "learning_rate": 4.926452203506464e-05, "loss": 0.6235, "step": 361 }, { "epoch": 0.5335298452468681, "grad_norm": 3.3329188248082535, "learning_rate": 4.925980818533934e-05, "loss": 0.7904, "step": 362 }, { "epoch": 0.5350036845983788, "grad_norm": 2.618403547945308, "learning_rate": 4.9255079504723783e-05, "loss": 0.6018, "step": 363 }, { "epoch": 0.5364775239498895, "grad_norm": 2.524520594343054, "learning_rate": 4.925033599610879e-05, "loss": 0.6948, "step": 364 }, { "epoch": 0.5379513633014001, "grad_norm": 2.7286012563737083, "learning_rate": 4.924557766239423e-05, "loss": 0.644, "step": 365 }, { "epoch": 0.5394252026529108, "grad_norm": 2.2933957483795298, "learning_rate": 4.9240804506489045e-05, "loss": 0.5758, "step": 366 }, { "epoch": 0.5408990420044215, "grad_norm": 3.763437229160602, "learning_rate": 4.9236016531311246e-05, "loss": 0.6056, "step": 367 }, { "epoch": 0.5423728813559322, "grad_norm": 2.980278999017928, "learning_rate": 4.923121373978788e-05, "loss": 0.7522, "step": 368 }, { "epoch": 0.5438467207074429, "grad_norm": 3.715533749010909, "learning_rate": 4.922639613485508e-05, "loss": 0.6162, "step": 369 }, { "epoch": 0.5453205600589536, "grad_norm": 2.6760274286560812, "learning_rate": 4.9221563719458e-05, "loss": 0.6239, "step": 370 }, { "epoch": 0.5467943994104643, "grad_norm": 2.6709425341995088, "learning_rate": 4.921671649655088e-05, "loss": 0.6429, "step": 371 }, { "epoch": 0.548268238761975, "grad_norm": 3.2790013919139813, "learning_rate": 4.921185446909702e-05, "loss": 0.5752, "step": 372 }, { "epoch": 0.5497420781134856, "grad_norm": 2.5738002685855017, "learning_rate": 4.9206977640068716e-05, "loss": 0.7432, "step": 373 }, { "epoch": 0.5512159174649963, "grad_norm": 2.2380402919629723, "learning_rate": 4.920208601244737e-05, "loss": 0.5571, "step": 374 }, { "epoch": 0.552689756816507, "grad_norm": 3.4383901657262075, "learning_rate": 4.9197179589223406e-05, "loss": 0.6782, "step": 375 }, { "epoch": 0.5541635961680177, "grad_norm": 2.5608740509533443, "learning_rate": 4.919225837339629e-05, "loss": 0.6074, "step": 376 }, { "epoch": 0.5556374355195284, "grad_norm": 2.883562688213223, "learning_rate": 4.9187322367974554e-05, "loss": 0.6337, "step": 377 }, { "epoch": 0.5571112748710391, "grad_norm": 2.4590315931663396, "learning_rate": 4.9182371575975736e-05, "loss": 0.6082, "step": 378 }, { "epoch": 0.5585851142225498, "grad_norm": 2.8662944515090323, "learning_rate": 4.917740600042645e-05, "loss": 0.5857, "step": 379 }, { "epoch": 0.5600589535740604, "grad_norm": 2.765230829630267, "learning_rate": 4.917242564436231e-05, "loss": 0.7341, "step": 380 }, { "epoch": 0.5615327929255711, "grad_norm": 2.3819624588423873, "learning_rate": 4.9167430510828e-05, "loss": 0.5207, "step": 381 }, { "epoch": 0.5630066322770818, "grad_norm": 2.436691639202993, "learning_rate": 4.916242060287722e-05, "loss": 0.5964, "step": 382 }, { "epoch": 0.5644804716285925, "grad_norm": 2.885599747965151, "learning_rate": 4.915739592357271e-05, "loss": 0.7033, "step": 383 }, { "epoch": 0.5659543109801032, "grad_norm": 2.98090500344902, "learning_rate": 4.915235647598624e-05, "loss": 0.6878, "step": 384 }, { "epoch": 0.5674281503316139, "grad_norm": 2.7951706109836723, "learning_rate": 4.914730226319859e-05, "loss": 0.6304, "step": 385 }, { "epoch": 0.5689019896831246, "grad_norm": 2.9475705827669447, "learning_rate": 4.914223328829959e-05, "loss": 0.6734, "step": 386 }, { "epoch": 0.5703758290346352, "grad_norm": 2.306242544270691, "learning_rate": 4.9137149554388094e-05, "loss": 0.543, "step": 387 }, { "epoch": 0.5718496683861459, "grad_norm": 3.014613639153711, "learning_rate": 4.913205106457196e-05, "loss": 0.6954, "step": 388 }, { "epoch": 0.5733235077376566, "grad_norm": 2.5574470571219434, "learning_rate": 4.9126937821968084e-05, "loss": 0.5417, "step": 389 }, { "epoch": 0.5747973470891673, "grad_norm": 3.038953136839677, "learning_rate": 4.912180982970237e-05, "loss": 0.7243, "step": 390 }, { "epoch": 0.576271186440678, "grad_norm": 2.366853898213466, "learning_rate": 4.911666709090974e-05, "loss": 0.6968, "step": 391 }, { "epoch": 0.5777450257921887, "grad_norm": 2.530163849813501, "learning_rate": 4.911150960873414e-05, "loss": 0.5868, "step": 392 }, { "epoch": 0.5792188651436994, "grad_norm": 2.866849541560441, "learning_rate": 4.9106337386328524e-05, "loss": 0.7135, "step": 393 }, { "epoch": 0.58069270449521, "grad_norm": 3.8388778698019776, "learning_rate": 4.910115042685486e-05, "loss": 0.6974, "step": 394 }, { "epoch": 0.5821665438467207, "grad_norm": 2.4800404096202966, "learning_rate": 4.909594873348412e-05, "loss": 0.5712, "step": 395 }, { "epoch": 0.5836403831982314, "grad_norm": 2.2898252082316084, "learning_rate": 4.9090732309396275e-05, "loss": 0.5991, "step": 396 }, { "epoch": 0.5851142225497421, "grad_norm": 2.7280029164687423, "learning_rate": 4.908550115778032e-05, "loss": 0.5117, "step": 397 }, { "epoch": 0.5865880619012528, "grad_norm": 2.3749758066651694, "learning_rate": 4.908025528183425e-05, "loss": 0.5033, "step": 398 }, { "epoch": 0.5880619012527635, "grad_norm": 2.613986936435877, "learning_rate": 4.907499468476506e-05, "loss": 0.5775, "step": 399 }, { "epoch": 0.5895357406042742, "grad_norm": 3.4376410715459786, "learning_rate": 4.9069719369788734e-05, "loss": 0.7072, "step": 400 }, { "epoch": 0.5910095799557848, "grad_norm": 2.366735031143453, "learning_rate": 4.906442934013026e-05, "loss": 0.6687, "step": 401 }, { "epoch": 0.5924834193072955, "grad_norm": 2.561775849529943, "learning_rate": 4.905912459902362e-05, "loss": 0.6791, "step": 402 }, { "epoch": 0.5939572586588062, "grad_norm": 2.149683254773994, "learning_rate": 4.9053805149711794e-05, "loss": 0.5495, "step": 403 }, { "epoch": 0.5954310980103169, "grad_norm": 2.8193308635648835, "learning_rate": 4.904847099544676e-05, "loss": 0.5781, "step": 404 }, { "epoch": 0.5969049373618276, "grad_norm": 2.5131084104045907, "learning_rate": 4.904312213948948e-05, "loss": 0.5812, "step": 405 }, { "epoch": 0.5983787767133383, "grad_norm": 3.0154607065936467, "learning_rate": 4.903775858510988e-05, "loss": 0.5538, "step": 406 }, { "epoch": 0.599852616064849, "grad_norm": 3.095755495416643, "learning_rate": 4.903238033558692e-05, "loss": 0.6484, "step": 407 }, { "epoch": 0.6013264554163597, "grad_norm": 2.087111696230929, "learning_rate": 4.90269873942085e-05, "loss": 0.5691, "step": 408 }, { "epoch": 0.6028002947678703, "grad_norm": 2.4707299513736314, "learning_rate": 4.902157976427152e-05, "loss": 0.612, "step": 409 }, { "epoch": 0.604274134119381, "grad_norm": 2.6060830554506005, "learning_rate": 4.9016157449081855e-05, "loss": 0.6125, "step": 410 }, { "epoch": 0.6057479734708917, "grad_norm": 3.1911771918544436, "learning_rate": 4.9010720451954375e-05, "loss": 0.6494, "step": 411 }, { "epoch": 0.6072218128224024, "grad_norm": 2.4732061802070713, "learning_rate": 4.90052687762129e-05, "loss": 0.6799, "step": 412 }, { "epoch": 0.6086956521739131, "grad_norm": 2.399981868198567, "learning_rate": 4.8999802425190235e-05, "loss": 0.6502, "step": 413 }, { "epoch": 0.6101694915254238, "grad_norm": 2.8768457210094245, "learning_rate": 4.899432140222816e-05, "loss": 0.6778, "step": 414 }, { "epoch": 0.6116433308769345, "grad_norm": 2.491779832173209, "learning_rate": 4.898882571067742e-05, "loss": 0.6701, "step": 415 }, { "epoch": 0.6131171702284451, "grad_norm": 2.5301316227807145, "learning_rate": 4.898331535389772e-05, "loss": 0.7427, "step": 416 }, { "epoch": 0.6145910095799558, "grad_norm": 2.8579091134485752, "learning_rate": 4.897779033525775e-05, "loss": 0.6611, "step": 417 }, { "epoch": 0.6160648489314665, "grad_norm": 2.693620056416884, "learning_rate": 4.897225065813515e-05, "loss": 0.645, "step": 418 }, { "epoch": 0.6175386882829772, "grad_norm": 2.79636553167993, "learning_rate": 4.8966696325916515e-05, "loss": 0.6924, "step": 419 }, { "epoch": 0.6190125276344879, "grad_norm": 2.3292450738674413, "learning_rate": 4.896112734199742e-05, "loss": 0.6124, "step": 420 }, { "epoch": 0.6204863669859986, "grad_norm": 2.4289098151258415, "learning_rate": 4.895554370978238e-05, "loss": 0.7328, "step": 421 }, { "epoch": 0.6219602063375093, "grad_norm": 2.303120743270108, "learning_rate": 4.894994543268486e-05, "loss": 0.5555, "step": 422 }, { "epoch": 0.6234340456890199, "grad_norm": 2.6586570156034477, "learning_rate": 4.894433251412729e-05, "loss": 0.6917, "step": 423 }, { "epoch": 0.6249078850405306, "grad_norm": 2.1875134058950265, "learning_rate": 4.893870495754106e-05, "loss": 0.59, "step": 424 }, { "epoch": 0.6263817243920413, "grad_norm": 2.1512783065077334, "learning_rate": 4.8933062766366486e-05, "loss": 0.5713, "step": 425 }, { "epoch": 0.627855563743552, "grad_norm": 2.277756825275765, "learning_rate": 4.892740594405285e-05, "loss": 0.5935, "step": 426 }, { "epoch": 0.6293294030950627, "grad_norm": 2.6330944781885237, "learning_rate": 4.892173449405837e-05, "loss": 0.5853, "step": 427 }, { "epoch": 0.6308032424465734, "grad_norm": 1.912158751118102, "learning_rate": 4.89160484198502e-05, "loss": 0.5207, "step": 428 }, { "epoch": 0.6322770817980841, "grad_norm": 3.0543559252988515, "learning_rate": 4.891034772490444e-05, "loss": 0.5806, "step": 429 }, { "epoch": 0.6337509211495947, "grad_norm": 2.710568537600108, "learning_rate": 4.890463241270613e-05, "loss": 0.5693, "step": 430 }, { "epoch": 0.6352247605011054, "grad_norm": 3.8279091287587623, "learning_rate": 4.889890248674925e-05, "loss": 0.5803, "step": 431 }, { "epoch": 0.636698599852616, "grad_norm": 3.0463840186841895, "learning_rate": 4.8893157950536704e-05, "loss": 0.5737, "step": 432 }, { "epoch": 0.6381724392041267, "grad_norm": 2.9105142462794116, "learning_rate": 4.8887398807580345e-05, "loss": 0.603, "step": 433 }, { "epoch": 0.6396462785556374, "grad_norm": 2.5039067260932173, "learning_rate": 4.888162506140093e-05, "loss": 0.5926, "step": 434 }, { "epoch": 0.6411201179071481, "grad_norm": 2.661524752530267, "learning_rate": 4.887583671552816e-05, "loss": 0.6994, "step": 435 }, { "epoch": 0.6425939572586588, "grad_norm": 2.8849401711750913, "learning_rate": 4.887003377350066e-05, "loss": 0.5972, "step": 436 }, { "epoch": 0.6440677966101694, "grad_norm": 2.665030653099136, "learning_rate": 4.886421623886598e-05, "loss": 0.6606, "step": 437 }, { "epoch": 0.6455416359616801, "grad_norm": 2.6807272981783297, "learning_rate": 4.885838411518057e-05, "loss": 0.8094, "step": 438 }, { "epoch": 0.6470154753131908, "grad_norm": 1.8517549310152206, "learning_rate": 4.885253740600985e-05, "loss": 0.4985, "step": 439 }, { "epoch": 0.6484893146647015, "grad_norm": 2.438715802710094, "learning_rate": 4.884667611492808e-05, "loss": 0.5931, "step": 440 }, { "epoch": 0.6499631540162122, "grad_norm": 2.3698499958838584, "learning_rate": 4.884080024551851e-05, "loss": 0.4848, "step": 441 }, { "epoch": 0.6514369933677229, "grad_norm": 2.374844997768851, "learning_rate": 4.8834909801373264e-05, "loss": 0.6673, "step": 442 }, { "epoch": 0.6529108327192336, "grad_norm": 1.9428012065488647, "learning_rate": 4.882900478609338e-05, "loss": 0.6001, "step": 443 }, { "epoch": 0.6543846720707442, "grad_norm": 2.2606099363990015, "learning_rate": 4.882308520328879e-05, "loss": 0.5523, "step": 444 }, { "epoch": 0.6558585114222549, "grad_norm": 2.3732257037814306, "learning_rate": 4.881715105657837e-05, "loss": 0.7133, "step": 445 }, { "epoch": 0.6573323507737656, "grad_norm": 2.4062778421748092, "learning_rate": 4.881120234958986e-05, "loss": 0.7196, "step": 446 }, { "epoch": 0.6588061901252763, "grad_norm": 2.2730410515316795, "learning_rate": 4.880523908595993e-05, "loss": 0.6729, "step": 447 }, { "epoch": 0.660280029476787, "grad_norm": 2.743402369554874, "learning_rate": 4.879926126933412e-05, "loss": 0.7412, "step": 448 }, { "epoch": 0.6617538688282977, "grad_norm": 2.8755681678944787, "learning_rate": 4.8793268903366905e-05, "loss": 0.5981, "step": 449 }, { "epoch": 0.6632277081798084, "grad_norm": 2.1083579543212783, "learning_rate": 4.8787261991721624e-05, "loss": 0.5641, "step": 450 }, { "epoch": 0.664701547531319, "grad_norm": 2.2141294050640727, "learning_rate": 4.8781240538070506e-05, "loss": 0.5569, "step": 451 }, { "epoch": 0.6661753868828297, "grad_norm": 2.5137368455388054, "learning_rate": 4.87752045460947e-05, "loss": 0.6778, "step": 452 }, { "epoch": 0.6676492262343404, "grad_norm": 2.4368349782040095, "learning_rate": 4.876915401948421e-05, "loss": 0.6366, "step": 453 }, { "epoch": 0.6691230655858511, "grad_norm": 2.6014630639487466, "learning_rate": 4.876308896193794e-05, "loss": 0.5254, "step": 454 }, { "epoch": 0.6705969049373618, "grad_norm": 2.480753436234476, "learning_rate": 4.87570093771637e-05, "loss": 0.5852, "step": 455 }, { "epoch": 0.6720707442888725, "grad_norm": 3.2878610042884278, "learning_rate": 4.875091526887813e-05, "loss": 0.6689, "step": 456 }, { "epoch": 0.6735445836403832, "grad_norm": 2.668972647534278, "learning_rate": 4.874480664080678e-05, "loss": 0.6473, "step": 457 }, { "epoch": 0.6750184229918939, "grad_norm": 2.7160089640574783, "learning_rate": 4.873868349668409e-05, "loss": 0.6477, "step": 458 }, { "epoch": 0.6764922623434045, "grad_norm": 2.2234783026784157, "learning_rate": 4.873254584025335e-05, "loss": 0.5546, "step": 459 }, { "epoch": 0.6779661016949152, "grad_norm": 2.4332974714310325, "learning_rate": 4.8726393675266716e-05, "loss": 0.635, "step": 460 }, { "epoch": 0.6794399410464259, "grad_norm": 2.5871575465232546, "learning_rate": 4.8720227005485245e-05, "loss": 0.5595, "step": 461 }, { "epoch": 0.6809137803979366, "grad_norm": 2.254085963338765, "learning_rate": 4.871404583467884e-05, "loss": 0.5869, "step": 462 }, { "epoch": 0.6823876197494473, "grad_norm": 2.7002967636061315, "learning_rate": 4.8707850166626266e-05, "loss": 0.6378, "step": 463 }, { "epoch": 0.683861459100958, "grad_norm": 2.287541010754782, "learning_rate": 4.8701640005115155e-05, "loss": 0.6205, "step": 464 }, { "epoch": 0.6853352984524687, "grad_norm": 2.5051759544601206, "learning_rate": 4.869541535394202e-05, "loss": 0.5095, "step": 465 }, { "epoch": 0.6868091378039793, "grad_norm": 2.394643460455827, "learning_rate": 4.8689176216912184e-05, "loss": 0.552, "step": 466 }, { "epoch": 0.68828297715549, "grad_norm": 2.5449119444717034, "learning_rate": 4.8682922597839874e-05, "loss": 0.5395, "step": 467 }, { "epoch": 0.6897568165070007, "grad_norm": 2.475598553807842, "learning_rate": 4.867665450054816e-05, "loss": 0.6437, "step": 468 }, { "epoch": 0.6912306558585114, "grad_norm": 2.8050460373743515, "learning_rate": 4.867037192886893e-05, "loss": 0.6079, "step": 469 }, { "epoch": 0.6927044952100221, "grad_norm": 3.143636749229847, "learning_rate": 4.866407488664296e-05, "loss": 0.6244, "step": 470 }, { "epoch": 0.6941783345615328, "grad_norm": 2.8758782413690063, "learning_rate": 4.8657763377719854e-05, "loss": 0.6113, "step": 471 }, { "epoch": 0.6956521739130435, "grad_norm": 2.4833914291276944, "learning_rate": 4.865143740595807e-05, "loss": 0.5623, "step": 472 }, { "epoch": 0.6971260132645541, "grad_norm": 2.9592671778532322, "learning_rate": 4.8645096975224894e-05, "loss": 0.6469, "step": 473 }, { "epoch": 0.6985998526160648, "grad_norm": 2.5946253023499803, "learning_rate": 4.863874208939646e-05, "loss": 0.6566, "step": 474 }, { "epoch": 0.7000736919675755, "grad_norm": 3.1375409066622546, "learning_rate": 4.863237275235774e-05, "loss": 0.5333, "step": 475 }, { "epoch": 0.7015475313190862, "grad_norm": 2.607744358422715, "learning_rate": 4.862598896800253e-05, "loss": 0.6264, "step": 476 }, { "epoch": 0.7030213706705969, "grad_norm": 2.845767803936382, "learning_rate": 4.861959074023348e-05, "loss": 0.7394, "step": 477 }, { "epoch": 0.7044952100221076, "grad_norm": 2.491163180800825, "learning_rate": 4.861317807296205e-05, "loss": 0.6163, "step": 478 }, { "epoch": 0.7059690493736183, "grad_norm": 2.512546717271089, "learning_rate": 4.860675097010853e-05, "loss": 0.5647, "step": 479 }, { "epoch": 0.707442888725129, "grad_norm": 2.0589458012536417, "learning_rate": 4.860030943560204e-05, "loss": 0.6474, "step": 480 }, { "epoch": 0.7089167280766396, "grad_norm": 2.4361527461001993, "learning_rate": 4.859385347338052e-05, "loss": 0.5388, "step": 481 }, { "epoch": 0.7103905674281503, "grad_norm": 4.064182813272216, "learning_rate": 4.858738308739073e-05, "loss": 0.6327, "step": 482 }, { "epoch": 0.711864406779661, "grad_norm": 3.397404515915522, "learning_rate": 4.858089828158825e-05, "loss": 0.766, "step": 483 }, { "epoch": 0.7133382461311717, "grad_norm": 3.2597676729135268, "learning_rate": 4.857439905993748e-05, "loss": 0.6865, "step": 484 }, { "epoch": 0.7148120854826824, "grad_norm": 2.4929400895161904, "learning_rate": 4.856788542641162e-05, "loss": 0.6043, "step": 485 }, { "epoch": 0.7162859248341931, "grad_norm": 2.5624401736835294, "learning_rate": 4.856135738499269e-05, "loss": 0.552, "step": 486 }, { "epoch": 0.7177597641857038, "grad_norm": 2.5705472612857485, "learning_rate": 4.855481493967152e-05, "loss": 0.5389, "step": 487 }, { "epoch": 0.7192336035372144, "grad_norm": 2.387052072577908, "learning_rate": 4.854825809444773e-05, "loss": 0.6024, "step": 488 }, { "epoch": 0.7207074428887251, "grad_norm": 2.7104759153145044, "learning_rate": 4.854168685332977e-05, "loss": 0.6059, "step": 489 }, { "epoch": 0.7221812822402358, "grad_norm": 2.7771730008331126, "learning_rate": 4.8535101220334864e-05, "loss": 0.5591, "step": 490 }, { "epoch": 0.7236551215917465, "grad_norm": 2.4312949796698313, "learning_rate": 4.852850119948904e-05, "loss": 0.6201, "step": 491 }, { "epoch": 0.7251289609432572, "grad_norm": 2.1567638724745293, "learning_rate": 4.8521886794827144e-05, "loss": 0.5951, "step": 492 }, { "epoch": 0.7266028002947679, "grad_norm": 2.5894404999267957, "learning_rate": 4.851525801039278e-05, "loss": 0.6458, "step": 493 }, { "epoch": 0.7280766396462786, "grad_norm": 3.30028498603904, "learning_rate": 4.850861485023839e-05, "loss": 0.594, "step": 494 }, { "epoch": 0.7295504789977892, "grad_norm": 3.0152068960077054, "learning_rate": 4.8501957318425136e-05, "loss": 0.6937, "step": 495 }, { "epoch": 0.7310243183492999, "grad_norm": 2.3319062114785147, "learning_rate": 4.849528541902305e-05, "loss": 0.5934, "step": 496 }, { "epoch": 0.7324981577008106, "grad_norm": 2.4390696826660436, "learning_rate": 4.848859915611086e-05, "loss": 0.5363, "step": 497 }, { "epoch": 0.7339719970523213, "grad_norm": 2.63427757001563, "learning_rate": 4.848189853377615e-05, "loss": 0.6225, "step": 498 }, { "epoch": 0.735445836403832, "grad_norm": 2.7959744159635833, "learning_rate": 4.847518355611524e-05, "loss": 0.7873, "step": 499 }, { "epoch": 0.7369196757553427, "grad_norm": 2.2673101012129453, "learning_rate": 4.846845422723324e-05, "loss": 0.6497, "step": 500 }, { "epoch": 0.7369196757553427, "eval_bleu": 0.19619680273875795, "eval_bleu_1gram": 0.506799976846296, "eval_bleu_2gram": 0.2968943546325363, "eval_bleu_3gram": 0.18387575615987026, "eval_bleu_4gram": 0.117854696405487, "eval_rag_val_loss": 0.6428658632181024, "eval_rouge1": 0.5058257083451594, "eval_rouge2": 0.28821616922677856, "eval_rougeL": 0.49944249021187154, "step": 500 }, { "epoch": 0.7383935151068534, "grad_norm": 2.793288590050865, "learning_rate": 4.846171055124401e-05, "loss": 0.5833, "step": 501 }, { "epoch": 0.739867354458364, "grad_norm": 2.6647252128315038, "learning_rate": 4.8454952532270223e-05, "loss": 0.6275, "step": 502 }, { "epoch": 0.7413411938098747, "grad_norm": 2.7992474600543713, "learning_rate": 4.8448180174443305e-05, "loss": 0.5945, "step": 503 }, { "epoch": 0.7428150331613854, "grad_norm": 3.1571800447972733, "learning_rate": 4.844139348190341e-05, "loss": 0.7075, "step": 504 }, { "epoch": 0.7442888725128961, "grad_norm": 2.8441619574657504, "learning_rate": 4.843459245879951e-05, "loss": 0.6347, "step": 505 }, { "epoch": 0.7457627118644068, "grad_norm": 2.4878511880608025, "learning_rate": 4.842777710928932e-05, "loss": 0.6169, "step": 506 }, { "epoch": 0.7472365512159175, "grad_norm": 2.8601149972057436, "learning_rate": 4.8420947437539285e-05, "loss": 0.6954, "step": 507 }, { "epoch": 0.7487103905674282, "grad_norm": 2.735179935234004, "learning_rate": 4.841410344772464e-05, "loss": 0.6846, "step": 508 }, { "epoch": 0.7501842299189388, "grad_norm": 2.562848974516528, "learning_rate": 4.8407245144029356e-05, "loss": 0.635, "step": 509 }, { "epoch": 0.7516580692704495, "grad_norm": 2.3268386051877954, "learning_rate": 4.8400372530646174e-05, "loss": 0.6238, "step": 510 }, { "epoch": 0.7531319086219602, "grad_norm": 2.9576452466909275, "learning_rate": 4.8393485611776555e-05, "loss": 0.6185, "step": 511 }, { "epoch": 0.7546057479734709, "grad_norm": 2.5751389290080304, "learning_rate": 4.8386584391630716e-05, "loss": 0.6688, "step": 512 }, { "epoch": 0.7560795873249816, "grad_norm": 2.0315063314825075, "learning_rate": 4.837966887442764e-05, "loss": 0.5346, "step": 513 }, { "epoch": 0.7575534266764923, "grad_norm": 2.5842025791573096, "learning_rate": 4.8372739064395014e-05, "loss": 0.5793, "step": 514 }, { "epoch": 0.759027266028003, "grad_norm": 3.5383771691741694, "learning_rate": 4.836579496576928e-05, "loss": 0.637, "step": 515 }, { "epoch": 0.7605011053795137, "grad_norm": 3.295363237796185, "learning_rate": 4.835883658279562e-05, "loss": 0.7166, "step": 516 }, { "epoch": 0.7619749447310243, "grad_norm": 3.388984529434602, "learning_rate": 4.835186391972794e-05, "loss": 0.6375, "step": 517 }, { "epoch": 0.763448784082535, "grad_norm": 2.514663038489164, "learning_rate": 4.834487698082888e-05, "loss": 0.4969, "step": 518 }, { "epoch": 0.7649226234340457, "grad_norm": 2.8609174726650872, "learning_rate": 4.833787577036981e-05, "loss": 0.6324, "step": 519 }, { "epoch": 0.7663964627855564, "grad_norm": 3.731680308821496, "learning_rate": 4.833086029263081e-05, "loss": 0.6005, "step": 520 }, { "epoch": 0.7678703021370671, "grad_norm": 4.10633859756553, "learning_rate": 4.8323830551900704e-05, "loss": 0.5575, "step": 521 }, { "epoch": 0.7693441414885778, "grad_norm": 2.858685352977249, "learning_rate": 4.831678655247702e-05, "loss": 0.6961, "step": 522 }, { "epoch": 0.7708179808400885, "grad_norm": 2.6773390196376363, "learning_rate": 4.8309728298666e-05, "loss": 0.6312, "step": 523 }, { "epoch": 0.7722918201915991, "grad_norm": 6.801371873584988, "learning_rate": 4.830265579478263e-05, "loss": 0.5885, "step": 524 }, { "epoch": 0.7737656595431098, "grad_norm": 2.7074273770526442, "learning_rate": 4.829556904515056e-05, "loss": 0.622, "step": 525 }, { "epoch": 0.7752394988946205, "grad_norm": 2.139659691784927, "learning_rate": 4.8288468054102186e-05, "loss": 0.5929, "step": 526 }, { "epoch": 0.7767133382461312, "grad_norm": 2.2501570328909173, "learning_rate": 4.828135282597859e-05, "loss": 0.6382, "step": 527 }, { "epoch": 0.7781871775976419, "grad_norm": 3.388000597686895, "learning_rate": 4.827422336512958e-05, "loss": 0.6564, "step": 528 }, { "epoch": 0.7796610169491526, "grad_norm": 2.1060984842833177, "learning_rate": 4.826707967591364e-05, "loss": 0.5741, "step": 529 }, { "epoch": 0.7811348563006633, "grad_norm": 3.0709092819642523, "learning_rate": 4.825992176269797e-05, "loss": 0.6775, "step": 530 }, { "epoch": 0.782608695652174, "grad_norm": 3.4700640689530733, "learning_rate": 4.825274962985845e-05, "loss": 0.6764, "step": 531 }, { "epoch": 0.7840825350036846, "grad_norm": 2.6067878552369184, "learning_rate": 4.8245563281779675e-05, "loss": 0.6661, "step": 532 }, { "epoch": 0.7855563743551953, "grad_norm": 2.7033670129649634, "learning_rate": 4.823836272285491e-05, "loss": 0.6673, "step": 533 }, { "epoch": 0.787030213706706, "grad_norm": 2.3711846474030818, "learning_rate": 4.823114795748611e-05, "loss": 0.557, "step": 534 }, { "epoch": 0.7885040530582167, "grad_norm": 4.47663961880017, "learning_rate": 4.8223918990083924e-05, "loss": 0.6035, "step": 535 }, { "epoch": 0.7899778924097274, "grad_norm": 2.664513960813376, "learning_rate": 4.821667582506768e-05, "loss": 0.6945, "step": 536 }, { "epoch": 0.7914517317612381, "grad_norm": 2.177403172509188, "learning_rate": 4.820941846686538e-05, "loss": 0.5279, "step": 537 }, { "epoch": 0.7929255711127488, "grad_norm": 2.7018521349449243, "learning_rate": 4.820214691991372e-05, "loss": 0.7024, "step": 538 }, { "epoch": 0.7943994104642594, "grad_norm": 3.082728782015901, "learning_rate": 4.819486118865804e-05, "loss": 0.7544, "step": 539 }, { "epoch": 0.7958732498157701, "grad_norm": 4.6220887790474645, "learning_rate": 4.8187561277552374e-05, "loss": 0.669, "step": 540 }, { "epoch": 0.7973470891672808, "grad_norm": 2.5644840840012924, "learning_rate": 4.818024719105942e-05, "loss": 0.6414, "step": 541 }, { "epoch": 0.7988209285187915, "grad_norm": 2.3678534549847985, "learning_rate": 4.817291893365055e-05, "loss": 0.5912, "step": 542 }, { "epoch": 0.8002947678703022, "grad_norm": 2.846154841464497, "learning_rate": 4.816557650980578e-05, "loss": 0.6712, "step": 543 }, { "epoch": 0.8017686072218129, "grad_norm": 2.335491431267711, "learning_rate": 4.8158219924013796e-05, "loss": 0.5835, "step": 544 }, { "epoch": 0.8032424465733236, "grad_norm": 3.1688950544936074, "learning_rate": 4.815084918077195e-05, "loss": 0.6998, "step": 545 }, { "epoch": 0.8047162859248342, "grad_norm": 2.5515216027537075, "learning_rate": 4.8143464284586244e-05, "loss": 0.5666, "step": 546 }, { "epoch": 0.8061901252763449, "grad_norm": 2.743229420834953, "learning_rate": 4.813606523997132e-05, "loss": 0.5391, "step": 547 }, { "epoch": 0.8076639646278556, "grad_norm": 2.0462180677752535, "learning_rate": 4.8128652051450476e-05, "loss": 0.5693, "step": 548 }, { "epoch": 0.8091378039793663, "grad_norm": 2.566650564795515, "learning_rate": 4.812122472355568e-05, "loss": 0.6144, "step": 549 }, { "epoch": 0.810611643330877, "grad_norm": 2.182351839120616, "learning_rate": 4.8113783260827506e-05, "loss": 0.6686, "step": 550 }, { "epoch": 0.8120854826823877, "grad_norm": 3.7283743046734874, "learning_rate": 4.8106327667815186e-05, "loss": 0.6379, "step": 551 }, { "epoch": 0.8135593220338984, "grad_norm": 2.261650440192526, "learning_rate": 4.80988579490766e-05, "loss": 0.5586, "step": 552 }, { "epoch": 0.815033161385409, "grad_norm": 3.243048643167895, "learning_rate": 4.809137410917825e-05, "loss": 0.6092, "step": 553 }, { "epoch": 0.8165070007369197, "grad_norm": 3.0644456560616438, "learning_rate": 4.808387615269528e-05, "loss": 0.5936, "step": 554 }, { "epoch": 0.8179808400884304, "grad_norm": 3.564112515832335, "learning_rate": 4.8076364084211454e-05, "loss": 0.6102, "step": 555 }, { "epoch": 0.819454679439941, "grad_norm": 2.92139728741246, "learning_rate": 4.806883790831917e-05, "loss": 0.6597, "step": 556 }, { "epoch": 0.8209285187914517, "grad_norm": 2.688697725476848, "learning_rate": 4.806129762961946e-05, "loss": 0.5796, "step": 557 }, { "epoch": 0.8224023581429624, "grad_norm": 2.560686632848059, "learning_rate": 4.805374325272195e-05, "loss": 0.5182, "step": 558 }, { "epoch": 0.823876197494473, "grad_norm": 3.574342285689572, "learning_rate": 4.804617478224491e-05, "loss": 0.5646, "step": 559 }, { "epoch": 0.8253500368459837, "grad_norm": 2.5597321984169175, "learning_rate": 4.803859222281522e-05, "loss": 0.671, "step": 560 }, { "epoch": 0.8268238761974944, "grad_norm": 2.813922776518914, "learning_rate": 4.8030995579068356e-05, "loss": 0.7008, "step": 561 }, { "epoch": 0.8282977155490051, "grad_norm": 3.0113439660714, "learning_rate": 4.802338485564843e-05, "loss": 0.6661, "step": 562 }, { "epoch": 0.8297715549005158, "grad_norm": 3.693204702026322, "learning_rate": 4.801576005720816e-05, "loss": 0.5954, "step": 563 }, { "epoch": 0.8312453942520265, "grad_norm": 3.166926239484502, "learning_rate": 4.800812118840884e-05, "loss": 0.5845, "step": 564 }, { "epoch": 0.8327192336035372, "grad_norm": 2.1662586512670763, "learning_rate": 4.800046825392038e-05, "loss": 0.4924, "step": 565 }, { "epoch": 0.8341930729550479, "grad_norm": 2.3013866515357524, "learning_rate": 4.7992801258421324e-05, "loss": 0.6039, "step": 566 }, { "epoch": 0.8356669123065585, "grad_norm": 2.3355819788832566, "learning_rate": 4.798512020659875e-05, "loss": 0.5335, "step": 567 }, { "epoch": 0.8371407516580692, "grad_norm": 2.830016120352511, "learning_rate": 4.797742510314838e-05, "loss": 0.5999, "step": 568 }, { "epoch": 0.8386145910095799, "grad_norm": 2.2736826761186637, "learning_rate": 4.796971595277449e-05, "loss": 0.5823, "step": 569 }, { "epoch": 0.8400884303610906, "grad_norm": 2.5952823203098805, "learning_rate": 4.796199276018998e-05, "loss": 0.6185, "step": 570 }, { "epoch": 0.8415622697126013, "grad_norm": 2.740869797807834, "learning_rate": 4.795425553011629e-05, "loss": 0.5975, "step": 571 }, { "epoch": 0.843036109064112, "grad_norm": 2.782837232665087, "learning_rate": 4.7946504267283486e-05, "loss": 0.5849, "step": 572 }, { "epoch": 0.8445099484156227, "grad_norm": 2.2584470497395, "learning_rate": 4.7938738976430186e-05, "loss": 0.4965, "step": 573 }, { "epoch": 0.8459837877671333, "grad_norm": 2.453928821827898, "learning_rate": 4.7930959662303586e-05, "loss": 0.6052, "step": 574 }, { "epoch": 0.847457627118644, "grad_norm": 3.1588382495165668, "learning_rate": 4.7923166329659466e-05, "loss": 0.7553, "step": 575 }, { "epoch": 0.8489314664701547, "grad_norm": 2.461510001302296, "learning_rate": 4.791535898326217e-05, "loss": 0.5472, "step": 576 }, { "epoch": 0.8504053058216654, "grad_norm": 2.3520416075860386, "learning_rate": 4.790753762788461e-05, "loss": 0.5724, "step": 577 }, { "epoch": 0.8518791451731761, "grad_norm": 2.510767161698769, "learning_rate": 4.789970226830825e-05, "loss": 0.6674, "step": 578 }, { "epoch": 0.8533529845246868, "grad_norm": 3.2805756375477575, "learning_rate": 4.789185290932313e-05, "loss": 0.6188, "step": 579 }, { "epoch": 0.8548268238761975, "grad_norm": 2.925039281336796, "learning_rate": 4.788398955572786e-05, "loss": 0.6413, "step": 580 }, { "epoch": 0.8563006632277081, "grad_norm": 2.2900807065776436, "learning_rate": 4.787611221232957e-05, "loss": 0.5599, "step": 581 }, { "epoch": 0.8577745025792188, "grad_norm": 2.429721746172689, "learning_rate": 4.786822088394397e-05, "loss": 0.6088, "step": 582 }, { "epoch": 0.8592483419307295, "grad_norm": 4.3740691148332225, "learning_rate": 4.7860315575395316e-05, "loss": 0.5687, "step": 583 }, { "epoch": 0.8607221812822402, "grad_norm": 3.19323663038183, "learning_rate": 4.78523962915164e-05, "loss": 0.6227, "step": 584 }, { "epoch": 0.8621960206337509, "grad_norm": 2.7806572443198, "learning_rate": 4.7844463037148566e-05, "loss": 0.5672, "step": 585 }, { "epoch": 0.8636698599852616, "grad_norm": 3.223792413356366, "learning_rate": 4.783651581714169e-05, "loss": 0.6163, "step": 586 }, { "epoch": 0.8651436993367723, "grad_norm": 2.1785057446585947, "learning_rate": 4.782855463635421e-05, "loss": 0.5937, "step": 587 }, { "epoch": 0.866617538688283, "grad_norm": 2.6244391795934714, "learning_rate": 4.782057949965307e-05, "loss": 0.6099, "step": 588 }, { "epoch": 0.8680913780397936, "grad_norm": 4.590288583829661, "learning_rate": 4.781259041191375e-05, "loss": 0.5578, "step": 589 }, { "epoch": 0.8695652173913043, "grad_norm": 2.876137715667465, "learning_rate": 4.7804587378020285e-05, "loss": 0.6407, "step": 590 }, { "epoch": 0.871039056742815, "grad_norm": 2.2170949861501885, "learning_rate": 4.7796570402865194e-05, "loss": 0.5639, "step": 591 }, { "epoch": 0.8725128960943257, "grad_norm": 3.0281274187296843, "learning_rate": 4.778853949134956e-05, "loss": 0.6731, "step": 592 }, { "epoch": 0.8739867354458364, "grad_norm": 2.395454067120283, "learning_rate": 4.778049464838295e-05, "loss": 0.629, "step": 593 }, { "epoch": 0.8754605747973471, "grad_norm": 2.1664144907208938, "learning_rate": 4.777243587888348e-05, "loss": 0.5084, "step": 594 }, { "epoch": 0.8769344141488578, "grad_norm": 2.212160560733796, "learning_rate": 4.7764363187777763e-05, "loss": 0.6384, "step": 595 }, { "epoch": 0.8784082535003684, "grad_norm": 2.2755939965780283, "learning_rate": 4.775627658000091e-05, "loss": 0.6695, "step": 596 }, { "epoch": 0.8798820928518791, "grad_norm": 2.772736280742174, "learning_rate": 4.774817606049657e-05, "loss": 0.7565, "step": 597 }, { "epoch": 0.8813559322033898, "grad_norm": 3.0102944178767306, "learning_rate": 4.774006163421687e-05, "loss": 0.6485, "step": 598 }, { "epoch": 0.8828297715549005, "grad_norm": 2.496898157348955, "learning_rate": 4.773193330612246e-05, "loss": 0.5904, "step": 599 }, { "epoch": 0.8843036109064112, "grad_norm": 2.954647257191408, "learning_rate": 4.7723791081182464e-05, "loss": 0.7691, "step": 600 }, { "epoch": 0.8857774502579219, "grad_norm": 2.0428541454022624, "learning_rate": 4.7715634964374536e-05, "loss": 0.517, "step": 601 }, { "epoch": 0.8872512896094326, "grad_norm": 3.0061734576404393, "learning_rate": 4.770746496068479e-05, "loss": 0.7943, "step": 602 }, { "epoch": 0.8887251289609432, "grad_norm": 3.6683905768242973, "learning_rate": 4.7699281075107835e-05, "loss": 0.7015, "step": 603 }, { "epoch": 0.8901989683124539, "grad_norm": 3.161689075342967, "learning_rate": 4.7691083312646795e-05, "loss": 0.6315, "step": 604 }, { "epoch": 0.8916728076639646, "grad_norm": 2.906865372675666, "learning_rate": 4.768287167831323e-05, "loss": 0.5703, "step": 605 }, { "epoch": 0.8931466470154753, "grad_norm": 3.9768687431961283, "learning_rate": 4.767464617712724e-05, "loss": 0.7452, "step": 606 }, { "epoch": 0.894620486366986, "grad_norm": 3.829946154820995, "learning_rate": 4.7666406814117326e-05, "loss": 0.6754, "step": 607 }, { "epoch": 0.8960943257184967, "grad_norm": 2.9491624839417465, "learning_rate": 4.7658153594320534e-05, "loss": 0.6869, "step": 608 }, { "epoch": 0.8975681650700074, "grad_norm": 2.3541005780781252, "learning_rate": 4.764988652278235e-05, "loss": 0.6349, "step": 609 }, { "epoch": 0.899042004421518, "grad_norm": 2.8839097661413757, "learning_rate": 4.764160560455673e-05, "loss": 0.6602, "step": 610 }, { "epoch": 0.9005158437730287, "grad_norm": 5.318863950196802, "learning_rate": 4.763331084470609e-05, "loss": 0.5093, "step": 611 }, { "epoch": 0.9019896831245394, "grad_norm": 2.416101477291833, "learning_rate": 4.762500224830132e-05, "loss": 0.5564, "step": 612 }, { "epoch": 0.9034635224760501, "grad_norm": 2.5428442389832826, "learning_rate": 4.7616679820421764e-05, "loss": 0.5685, "step": 613 }, { "epoch": 0.9049373618275608, "grad_norm": 3.353354377402474, "learning_rate": 4.760834356615521e-05, "loss": 0.5307, "step": 614 }, { "epoch": 0.9064112011790715, "grad_norm": 2.3884182387507056, "learning_rate": 4.7599993490597925e-05, "loss": 0.5558, "step": 615 }, { "epoch": 0.9078850405305822, "grad_norm": 3.371928760287371, "learning_rate": 4.75916295988546e-05, "loss": 0.7371, "step": 616 }, { "epoch": 0.9093588798820929, "grad_norm": 2.2297926644731088, "learning_rate": 4.7583251896038386e-05, "loss": 0.5776, "step": 617 }, { "epoch": 0.9108327192336035, "grad_norm": 2.697001052686509, "learning_rate": 4.757486038727086e-05, "loss": 0.6545, "step": 618 }, { "epoch": 0.9123065585851142, "grad_norm": 2.681743578174392, "learning_rate": 4.7566455077682065e-05, "loss": 0.7585, "step": 619 }, { "epoch": 0.9137803979366249, "grad_norm": 3.2205743156663056, "learning_rate": 4.755803597241046e-05, "loss": 0.5202, "step": 620 }, { "epoch": 0.9152542372881356, "grad_norm": 2.529461829502794, "learning_rate": 4.754960307660297e-05, "loss": 0.6255, "step": 621 }, { "epoch": 0.9167280766396463, "grad_norm": 1.999112945774087, "learning_rate": 4.7541156395414886e-05, "loss": 0.5037, "step": 622 }, { "epoch": 0.918201915991157, "grad_norm": 2.701774303810907, "learning_rate": 4.7532695934009996e-05, "loss": 0.5762, "step": 623 }, { "epoch": 0.9196757553426677, "grad_norm": 2.1290082714588467, "learning_rate": 4.752422169756048e-05, "loss": 0.5378, "step": 624 }, { "epoch": 0.9211495946941783, "grad_norm": 2.459636138275078, "learning_rate": 4.751573369124693e-05, "loss": 0.7174, "step": 625 }, { "epoch": 0.922623434045689, "grad_norm": 2.283862042531288, "learning_rate": 4.7507231920258386e-05, "loss": 0.6156, "step": 626 }, { "epoch": 0.9240972733971997, "grad_norm": 2.2098921066805377, "learning_rate": 4.749871638979227e-05, "loss": 0.6436, "step": 627 }, { "epoch": 0.9255711127487104, "grad_norm": 2.502484803358462, "learning_rate": 4.749018710505444e-05, "loss": 0.6829, "step": 628 }, { "epoch": 0.9270449521002211, "grad_norm": 2.258977569617321, "learning_rate": 4.7481644071259144e-05, "loss": 0.646, "step": 629 }, { "epoch": 0.9285187914517318, "grad_norm": 2.2794203017941745, "learning_rate": 4.747308729362906e-05, "loss": 0.6192, "step": 630 }, { "epoch": 0.9299926308032425, "grad_norm": 2.8085979095555516, "learning_rate": 4.7464516777395234e-05, "loss": 0.5695, "step": 631 }, { "epoch": 0.9314664701547531, "grad_norm": 2.5926265811458302, "learning_rate": 4.745593252779714e-05, "loss": 0.6458, "step": 632 }, { "epoch": 0.9329403095062638, "grad_norm": 2.8009009342345537, "learning_rate": 4.7447334550082646e-05, "loss": 0.6162, "step": 633 }, { "epoch": 0.9344141488577745, "grad_norm": 2.3083918397652456, "learning_rate": 4.743872284950799e-05, "loss": 0.5692, "step": 634 }, { "epoch": 0.9358879882092852, "grad_norm": 2.4602298748572036, "learning_rate": 4.743009743133782e-05, "loss": 0.5559, "step": 635 }, { "epoch": 0.9373618275607959, "grad_norm": 2.3721961486280847, "learning_rate": 4.7421458300845156e-05, "loss": 0.5969, "step": 636 }, { "epoch": 0.9388356669123066, "grad_norm": 2.72890994390876, "learning_rate": 4.741280546331142e-05, "loss": 0.623, "step": 637 }, { "epoch": 0.9403095062638173, "grad_norm": 2.189414140556699, "learning_rate": 4.740413892402639e-05, "loss": 0.5069, "step": 638 }, { "epoch": 0.941783345615328, "grad_norm": 2.374379829950082, "learning_rate": 4.739545868828824e-05, "loss": 0.5792, "step": 639 }, { "epoch": 0.9432571849668386, "grad_norm": 2.803043064038396, "learning_rate": 4.738676476140351e-05, "loss": 0.6503, "step": 640 }, { "epoch": 0.9447310243183493, "grad_norm": 3.3340126934759544, "learning_rate": 4.73780571486871e-05, "loss": 0.6284, "step": 641 }, { "epoch": 0.94620486366986, "grad_norm": 2.22780577096874, "learning_rate": 4.736933585546229e-05, "loss": 0.6072, "step": 642 }, { "epoch": 0.9476787030213707, "grad_norm": 1.9190529674199475, "learning_rate": 4.736060088706073e-05, "loss": 0.5412, "step": 643 }, { "epoch": 0.9491525423728814, "grad_norm": 2.8586268045412297, "learning_rate": 4.7351852248822405e-05, "loss": 0.674, "step": 644 }, { "epoch": 0.9506263817243921, "grad_norm": 2.262962829291314, "learning_rate": 4.7343089946095674e-05, "loss": 0.6512, "step": 645 }, { "epoch": 0.9521002210759028, "grad_norm": 2.424891605117603, "learning_rate": 4.733431398423725e-05, "loss": 0.5933, "step": 646 }, { "epoch": 0.9535740604274134, "grad_norm": 3.4171762474094565, "learning_rate": 4.7325524368612196e-05, "loss": 0.6711, "step": 647 }, { "epoch": 0.9550478997789241, "grad_norm": 3.4387254784672425, "learning_rate": 4.731672110459391e-05, "loss": 0.6241, "step": 648 }, { "epoch": 0.9565217391304348, "grad_norm": 2.1509683025370894, "learning_rate": 4.7307904197564146e-05, "loss": 0.6263, "step": 649 }, { "epoch": 0.9579955784819455, "grad_norm": 2.45770603732665, "learning_rate": 4.7299073652912995e-05, "loss": 0.6643, "step": 650 }, { "epoch": 0.9594694178334562, "grad_norm": 2.6814648486580284, "learning_rate": 4.7290229476038896e-05, "loss": 0.5026, "step": 651 }, { "epoch": 0.9609432571849669, "grad_norm": 3.0618185725466174, "learning_rate": 4.7281371672348595e-05, "loss": 0.5973, "step": 652 }, { "epoch": 0.9624170965364776, "grad_norm": 4.056853375574854, "learning_rate": 4.7272500247257196e-05, "loss": 0.6802, "step": 653 }, { "epoch": 0.9638909358879882, "grad_norm": 3.1650452394551727, "learning_rate": 4.7263615206188115e-05, "loss": 0.6316, "step": 654 }, { "epoch": 0.9653647752394989, "grad_norm": 2.8189650933525736, "learning_rate": 4.7254716554573095e-05, "loss": 0.5873, "step": 655 }, { "epoch": 0.9668386145910096, "grad_norm": 2.323430288235645, "learning_rate": 4.72458042978522e-05, "loss": 0.5967, "step": 656 }, { "epoch": 0.9683124539425203, "grad_norm": 5.581883465230099, "learning_rate": 4.7236878441473824e-05, "loss": 0.5402, "step": 657 }, { "epoch": 0.969786293294031, "grad_norm": 1.9960035688181068, "learning_rate": 4.722793899089465e-05, "loss": 0.5782, "step": 658 }, { "epoch": 0.9712601326455417, "grad_norm": 2.0670670316371575, "learning_rate": 4.7218985951579685e-05, "loss": 0.4728, "step": 659 }, { "epoch": 0.9727339719970524, "grad_norm": 2.4388627375555023, "learning_rate": 4.721001932900224e-05, "loss": 0.524, "step": 660 }, { "epoch": 0.974207811348563, "grad_norm": 2.068330787987056, "learning_rate": 4.7201039128643946e-05, "loss": 0.5645, "step": 661 }, { "epoch": 0.9756816507000737, "grad_norm": 2.6799404369681468, "learning_rate": 4.719204535599472e-05, "loss": 0.6025, "step": 662 }, { "epoch": 0.9771554900515844, "grad_norm": 2.7410877772252413, "learning_rate": 4.718303801655276e-05, "loss": 0.6057, "step": 663 }, { "epoch": 0.9786293294030951, "grad_norm": 1.9605190240919097, "learning_rate": 4.7174017115824585e-05, "loss": 0.4697, "step": 664 }, { "epoch": 0.9801031687546058, "grad_norm": 2.1766237446095604, "learning_rate": 4.716498265932501e-05, "loss": 0.6668, "step": 665 }, { "epoch": 0.9815770081061165, "grad_norm": 3.1450792297183954, "learning_rate": 4.715593465257709e-05, "loss": 0.5474, "step": 666 }, { "epoch": 0.9830508474576272, "grad_norm": 2.5627003102980286, "learning_rate": 4.7146873101112234e-05, "loss": 0.6042, "step": 667 }, { "epoch": 0.9845246868091379, "grad_norm": 2.323528796456512, "learning_rate": 4.7137798010470055e-05, "loss": 0.5208, "step": 668 }, { "epoch": 0.9859985261606485, "grad_norm": 2.745818860985952, "learning_rate": 4.712870938619851e-05, "loss": 0.7287, "step": 669 }, { "epoch": 0.9874723655121592, "grad_norm": 3.0345687788621665, "learning_rate": 4.71196072338538e-05, "loss": 0.6931, "step": 670 }, { "epoch": 0.9889462048636699, "grad_norm": 2.5279789263535015, "learning_rate": 4.711049155900037e-05, "loss": 0.5895, "step": 671 }, { "epoch": 0.9904200442151806, "grad_norm": 2.5073128556065543, "learning_rate": 4.710136236721099e-05, "loss": 0.6581, "step": 672 }, { "epoch": 0.9918938835666913, "grad_norm": 2.706205343886759, "learning_rate": 4.7092219664066636e-05, "loss": 0.4669, "step": 673 }, { "epoch": 0.993367722918202, "grad_norm": 2.815851122448189, "learning_rate": 4.70830634551566e-05, "loss": 0.7612, "step": 674 }, { "epoch": 0.9948415622697127, "grad_norm": 2.1308745917765566, "learning_rate": 4.707389374607837e-05, "loss": 0.5099, "step": 675 }, { "epoch": 0.9963154016212233, "grad_norm": 2.293893033175293, "learning_rate": 4.706471054243773e-05, "loss": 0.5601, "step": 676 }, { "epoch": 0.997789240972734, "grad_norm": 2.3662119450962567, "learning_rate": 4.705551384984871e-05, "loss": 0.6702, "step": 677 }, { "epoch": 0.9992630803242447, "grad_norm": 2.307878257522305, "learning_rate": 4.7046303673933564e-05, "loss": 0.638, "step": 678 }, { "epoch": 1.0007369196757554, "grad_norm": 2.6065913903016855, "learning_rate": 4.703708002032281e-05, "loss": 0.5933, "step": 679 }, { "epoch": 1.002210759027266, "grad_norm": 2.2183302361370947, "learning_rate": 4.7027842894655205e-05, "loss": 0.4304, "step": 680 }, { "epoch": 1.0036845983787768, "grad_norm": 2.5402589766572126, "learning_rate": 4.701859230257772e-05, "loss": 0.4745, "step": 681 }, { "epoch": 1.0051584377302873, "grad_norm": 2.4527388347713375, "learning_rate": 4.700932824974558e-05, "loss": 0.4328, "step": 682 }, { "epoch": 1.0066322770817981, "grad_norm": 1.9009670155817628, "learning_rate": 4.7000050741822233e-05, "loss": 0.44, "step": 683 }, { "epoch": 1.0081061164333087, "grad_norm": 1.6637886789183667, "learning_rate": 4.699075978447935e-05, "loss": 0.411, "step": 684 }, { "epoch": 1.0095799557848195, "grad_norm": 3.254044583644138, "learning_rate": 4.698145538339685e-05, "loss": 0.4753, "step": 685 }, { "epoch": 1.01105379513633, "grad_norm": 1.6372132931210401, "learning_rate": 4.6972137544262794e-05, "loss": 0.4387, "step": 686 }, { "epoch": 1.0125276344878409, "grad_norm": 2.3246464696381834, "learning_rate": 4.6962806272773564e-05, "loss": 0.4651, "step": 687 }, { "epoch": 1.0140014738393515, "grad_norm": 2.3111432193498262, "learning_rate": 4.6953461574633674e-05, "loss": 0.4935, "step": 688 }, { "epoch": 1.0154753131908623, "grad_norm": 4.843375111500566, "learning_rate": 4.694410345555587e-05, "loss": 0.4093, "step": 689 }, { "epoch": 1.0169491525423728, "grad_norm": 2.2914218656239984, "learning_rate": 4.693473192126112e-05, "loss": 0.46, "step": 690 }, { "epoch": 1.0184229918938836, "grad_norm": 2.0315157203000354, "learning_rate": 4.692534697747857e-05, "loss": 0.465, "step": 691 }, { "epoch": 1.0198968312453942, "grad_norm": 2.3863760894186243, "learning_rate": 4.6915948629945586e-05, "loss": 0.4255, "step": 692 }, { "epoch": 1.021370670596905, "grad_norm": 2.137484732233142, "learning_rate": 4.6906536884407694e-05, "loss": 0.4836, "step": 693 }, { "epoch": 1.0228445099484156, "grad_norm": 2.17506953161185, "learning_rate": 4.689711174661864e-05, "loss": 0.3718, "step": 694 }, { "epoch": 1.0243183492999264, "grad_norm": 2.2986955758435768, "learning_rate": 4.688767322234035e-05, "loss": 0.4457, "step": 695 }, { "epoch": 1.025792188651437, "grad_norm": 2.230341972850113, "learning_rate": 4.687822131734293e-05, "loss": 0.3769, "step": 696 }, { "epoch": 1.0272660280029478, "grad_norm": 2.3785438198874957, "learning_rate": 4.686875603740468e-05, "loss": 0.4596, "step": 697 }, { "epoch": 1.0287398673544583, "grad_norm": 2.0306498888157125, "learning_rate": 4.685927738831205e-05, "loss": 0.4459, "step": 698 }, { "epoch": 1.0302137067059691, "grad_norm": 2.509390456364632, "learning_rate": 4.684978537585968e-05, "loss": 0.4628, "step": 699 }, { "epoch": 1.0316875460574797, "grad_norm": 2.3464293360268247, "learning_rate": 4.684028000585038e-05, "loss": 0.4775, "step": 700 }, { "epoch": 1.0331613854089905, "grad_norm": 2.662522572882874, "learning_rate": 4.683076128409512e-05, "loss": 0.4378, "step": 701 }, { "epoch": 1.034635224760501, "grad_norm": 1.9987998580201232, "learning_rate": 4.682122921641304e-05, "loss": 0.4257, "step": 702 }, { "epoch": 1.0361090641120119, "grad_norm": 2.130222298748124, "learning_rate": 4.6811683808631446e-05, "loss": 0.4684, "step": 703 }, { "epoch": 1.0375829034635224, "grad_norm": 2.353962835979491, "learning_rate": 4.680212506658577e-05, "loss": 0.4999, "step": 704 }, { "epoch": 1.0390567428150332, "grad_norm": 2.947214499018125, "learning_rate": 4.679255299611961e-05, "loss": 0.5084, "step": 705 }, { "epoch": 1.0405305821665438, "grad_norm": 2.15445269438749, "learning_rate": 4.678296760308474e-05, "loss": 0.4126, "step": 706 }, { "epoch": 1.0420044215180546, "grad_norm": 2.5482159226462215, "learning_rate": 4.677336889334103e-05, "loss": 0.4697, "step": 707 }, { "epoch": 1.0434782608695652, "grad_norm": 2.9781854965614065, "learning_rate": 4.6763756872756525e-05, "loss": 0.6482, "step": 708 }, { "epoch": 1.044952100221076, "grad_norm": 1.8758121003359056, "learning_rate": 4.6754131547207406e-05, "loss": 0.3872, "step": 709 }, { "epoch": 1.0464259395725866, "grad_norm": 2.225099102770679, "learning_rate": 4.6744492922577963e-05, "loss": 0.4176, "step": 710 }, { "epoch": 1.0478997789240974, "grad_norm": 2.21385975665245, "learning_rate": 4.673484100476064e-05, "loss": 0.4307, "step": 711 }, { "epoch": 1.049373618275608, "grad_norm": 2.419217922479352, "learning_rate": 4.6725175799656005e-05, "loss": 0.4609, "step": 712 }, { "epoch": 1.0508474576271187, "grad_norm": 1.9988567541836828, "learning_rate": 4.671549731317274e-05, "loss": 0.3798, "step": 713 }, { "epoch": 1.0523212969786293, "grad_norm": 2.0322345401693487, "learning_rate": 4.670580555122765e-05, "loss": 0.4072, "step": 714 }, { "epoch": 1.05379513633014, "grad_norm": 2.251313885550656, "learning_rate": 4.669610051974566e-05, "loss": 0.4039, "step": 715 }, { "epoch": 1.0552689756816507, "grad_norm": 2.4659912533570147, "learning_rate": 4.66863822246598e-05, "loss": 0.4113, "step": 716 }, { "epoch": 1.0567428150331615, "grad_norm": 2.9740671827145744, "learning_rate": 4.6676650671911206e-05, "loss": 0.4997, "step": 717 }, { "epoch": 1.058216654384672, "grad_norm": 2.7321543368286254, "learning_rate": 4.666690586744914e-05, "loss": 0.4037, "step": 718 }, { "epoch": 1.0596904937361828, "grad_norm": 2.4528217492698907, "learning_rate": 4.665714781723094e-05, "loss": 0.4645, "step": 719 }, { "epoch": 1.0611643330876934, "grad_norm": 2.5662096665339535, "learning_rate": 4.6647376527222056e-05, "loss": 0.4468, "step": 720 }, { "epoch": 1.0626381724392042, "grad_norm": 2.165127708950036, "learning_rate": 4.6637592003396026e-05, "loss": 0.4277, "step": 721 }, { "epoch": 1.0641120117907148, "grad_norm": 2.792404779434649, "learning_rate": 4.662779425173448e-05, "loss": 0.4507, "step": 722 }, { "epoch": 1.0655858511422256, "grad_norm": 2.1296126847199623, "learning_rate": 4.6617983278227135e-05, "loss": 0.444, "step": 723 }, { "epoch": 1.0670596904937362, "grad_norm": 2.2221686661412607, "learning_rate": 4.660815908887179e-05, "loss": 0.4348, "step": 724 }, { "epoch": 1.068533529845247, "grad_norm": 1.8299826940124684, "learning_rate": 4.6598321689674326e-05, "loss": 0.3849, "step": 725 }, { "epoch": 1.0700073691967575, "grad_norm": 1.8299408721752046, "learning_rate": 4.658847108664869e-05, "loss": 0.3882, "step": 726 }, { "epoch": 1.0714812085482683, "grad_norm": 2.6642674342112382, "learning_rate": 4.6578607285816923e-05, "loss": 0.4768, "step": 727 }, { "epoch": 1.072955047899779, "grad_norm": 2.882561732191104, "learning_rate": 4.6568730293209104e-05, "loss": 0.4563, "step": 728 }, { "epoch": 1.0744288872512897, "grad_norm": 2.0326941418332383, "learning_rate": 4.655884011486341e-05, "loss": 0.3961, "step": 729 }, { "epoch": 1.0759027266028003, "grad_norm": 2.1758038230286645, "learning_rate": 4.654893675682605e-05, "loss": 0.5273, "step": 730 }, { "epoch": 1.077376565954311, "grad_norm": 2.105268989103172, "learning_rate": 4.65390202251513e-05, "loss": 0.4033, "step": 731 }, { "epoch": 1.0788504053058217, "grad_norm": 1.9950121433203984, "learning_rate": 4.65290905259015e-05, "loss": 0.4027, "step": 732 }, { "epoch": 1.0803242446573322, "grad_norm": 2.548691552255792, "learning_rate": 4.651914766514702e-05, "loss": 0.461, "step": 733 }, { "epoch": 1.081798084008843, "grad_norm": 2.43907916437843, "learning_rate": 4.65091916489663e-05, "loss": 0.4388, "step": 734 }, { "epoch": 1.0832719233603538, "grad_norm": 2.4306362053948085, "learning_rate": 4.649922248344581e-05, "loss": 0.4349, "step": 735 }, { "epoch": 1.0847457627118644, "grad_norm": 2.4082262915172206, "learning_rate": 4.648924017468003e-05, "loss": 0.454, "step": 736 }, { "epoch": 1.086219602063375, "grad_norm": 1.9915250985922206, "learning_rate": 4.6479244728771536e-05, "loss": 0.4222, "step": 737 }, { "epoch": 1.0876934414148858, "grad_norm": 2.5597533415638347, "learning_rate": 4.6469236151830884e-05, "loss": 0.5068, "step": 738 }, { "epoch": 1.0891672807663966, "grad_norm": 2.116660978154426, "learning_rate": 4.6459214449976694e-05, "loss": 0.4624, "step": 739 }, { "epoch": 1.0906411201179071, "grad_norm": 2.9356539180729015, "learning_rate": 4.644917962933558e-05, "loss": 0.4754, "step": 740 }, { "epoch": 1.0921149594694177, "grad_norm": 2.5648923731600854, "learning_rate": 4.6439131696042174e-05, "loss": 0.4434, "step": 741 }, { "epoch": 1.0935887988209285, "grad_norm": 2.4839656660560476, "learning_rate": 4.642907065623916e-05, "loss": 0.5279, "step": 742 }, { "epoch": 1.0950626381724393, "grad_norm": 2.0308727207468062, "learning_rate": 4.6418996516077205e-05, "loss": 0.4435, "step": 743 }, { "epoch": 1.09653647752395, "grad_norm": 2.3143792635563933, "learning_rate": 4.6408909281714986e-05, "loss": 0.4426, "step": 744 }, { "epoch": 1.0980103168754605, "grad_norm": 1.6971342784422572, "learning_rate": 4.6398808959319195e-05, "loss": 0.3655, "step": 745 }, { "epoch": 1.0994841562269713, "grad_norm": 2.79601807493226, "learning_rate": 4.6388695555064524e-05, "loss": 0.5545, "step": 746 }, { "epoch": 1.100957995578482, "grad_norm": 1.9638556542193042, "learning_rate": 4.637856907513366e-05, "loss": 0.4157, "step": 747 }, { "epoch": 1.1024318349299926, "grad_norm": 2.088179508560781, "learning_rate": 4.6368429525717274e-05, "loss": 0.4516, "step": 748 }, { "epoch": 1.1039056742815032, "grad_norm": 1.892030556026769, "learning_rate": 4.635827691301404e-05, "loss": 0.3939, "step": 749 }, { "epoch": 1.105379513633014, "grad_norm": 2.0238477372053247, "learning_rate": 4.634811124323062e-05, "loss": 0.4401, "step": 750 }, { "epoch": 1.105379513633014, "eval_bleu": 0.186077081491278, "eval_bleu_1gram": 0.4966636712627205, "eval_bleu_2gram": 0.28624764084472576, "eval_bleu_3gram": 0.17315556615644356, "eval_bleu_4gram": 0.10805551817154282, "eval_rag_val_loss": 0.6539723948445372, "eval_rouge1": 0.5005953831928798, "eval_rouge2": 0.2828116168393861, "eval_rougeL": 0.4952038617349146, "step": 750 }, { "epoch": 1.1068533529845246, "grad_norm": 2.2810838194635585, "learning_rate": 4.633793252258165e-05, "loss": 0.3932, "step": 751 }, { "epoch": 1.1083271923360354, "grad_norm": 2.261647804741952, "learning_rate": 4.632774075728974e-05, "loss": 0.4243, "step": 752 }, { "epoch": 1.109801031687546, "grad_norm": 1.7576372525489585, "learning_rate": 4.631753595358549e-05, "loss": 0.3639, "step": 753 }, { "epoch": 1.1112748710390568, "grad_norm": 2.1655528311105816, "learning_rate": 4.6307318117707465e-05, "loss": 0.4148, "step": 754 }, { "epoch": 1.1127487103905673, "grad_norm": 7.106493288302569, "learning_rate": 4.6297087255902184e-05, "loss": 0.4367, "step": 755 }, { "epoch": 1.1142225497420781, "grad_norm": 1.8090690499070352, "learning_rate": 4.628684337442414e-05, "loss": 0.4092, "step": 756 }, { "epoch": 1.1156963890935887, "grad_norm": 2.607562046355185, "learning_rate": 4.627658647953579e-05, "loss": 0.4299, "step": 757 }, { "epoch": 1.1171702284450995, "grad_norm": 2.3245837013238413, "learning_rate": 4.6266316577507536e-05, "loss": 0.4306, "step": 758 }, { "epoch": 1.11864406779661, "grad_norm": 2.3318985433215604, "learning_rate": 4.625603367461775e-05, "loss": 0.3803, "step": 759 }, { "epoch": 1.1201179071481209, "grad_norm": 3.185839051974831, "learning_rate": 4.624573777715272e-05, "loss": 0.4541, "step": 760 }, { "epoch": 1.1215917464996314, "grad_norm": 2.3895419790408345, "learning_rate": 4.6235428891406704e-05, "loss": 0.5823, "step": 761 }, { "epoch": 1.1230655858511422, "grad_norm": 3.371750998492831, "learning_rate": 4.6225107023681914e-05, "loss": 0.4069, "step": 762 }, { "epoch": 1.1245394252026528, "grad_norm": 2.1445771648445993, "learning_rate": 4.621477218028845e-05, "loss": 0.4595, "step": 763 }, { "epoch": 1.1260132645541636, "grad_norm": 1.900496696499405, "learning_rate": 4.620442436754438e-05, "loss": 0.4159, "step": 764 }, { "epoch": 1.1274871039056742, "grad_norm": 2.409047172993456, "learning_rate": 4.61940635917757e-05, "loss": 0.5425, "step": 765 }, { "epoch": 1.128960943257185, "grad_norm": 2.0589008717475004, "learning_rate": 4.6183689859316314e-05, "loss": 0.4694, "step": 766 }, { "epoch": 1.1304347826086956, "grad_norm": 2.4862303133991124, "learning_rate": 4.617330317650806e-05, "loss": 0.542, "step": 767 }, { "epoch": 1.1319086219602064, "grad_norm": 1.769152737654149, "learning_rate": 4.6162903549700706e-05, "loss": 0.3809, "step": 768 }, { "epoch": 1.133382461311717, "grad_norm": 2.1628455310465915, "learning_rate": 4.615249098525189e-05, "loss": 0.4374, "step": 769 }, { "epoch": 1.1348563006632277, "grad_norm": 2.3812468841612446, "learning_rate": 4.61420654895272e-05, "loss": 0.5205, "step": 770 }, { "epoch": 1.1363301400147383, "grad_norm": 1.8826188110509197, "learning_rate": 4.613162706890011e-05, "loss": 0.3262, "step": 771 }, { "epoch": 1.137803979366249, "grad_norm": 2.638813458307146, "learning_rate": 4.6121175729752006e-05, "loss": 0.385, "step": 772 }, { "epoch": 1.1392778187177597, "grad_norm": 2.4752224446527418, "learning_rate": 4.6110711478472157e-05, "loss": 0.5475, "step": 773 }, { "epoch": 1.1407516580692705, "grad_norm": 2.200525901532779, "learning_rate": 4.610023432145775e-05, "loss": 0.4474, "step": 774 }, { "epoch": 1.142225497420781, "grad_norm": 2.4750028205624317, "learning_rate": 4.608974426511383e-05, "loss": 0.3969, "step": 775 }, { "epoch": 1.1436993367722919, "grad_norm": 2.5468657323750574, "learning_rate": 4.607924131585336e-05, "loss": 0.4334, "step": 776 }, { "epoch": 1.1451731761238024, "grad_norm": 1.9917058025755363, "learning_rate": 4.606872548009716e-05, "loss": 0.4928, "step": 777 }, { "epoch": 1.1466470154753132, "grad_norm": 2.0143533879847872, "learning_rate": 4.605819676427393e-05, "loss": 0.4681, "step": 778 }, { "epoch": 1.1481208548268238, "grad_norm": 2.524404145743336, "learning_rate": 4.604765517482027e-05, "loss": 0.46, "step": 779 }, { "epoch": 1.1495946941783346, "grad_norm": 1.9129990094985432, "learning_rate": 4.603710071818062e-05, "loss": 0.4307, "step": 780 }, { "epoch": 1.1510685335298452, "grad_norm": 2.150187053971219, "learning_rate": 4.60265334008073e-05, "loss": 0.3919, "step": 781 }, { "epoch": 1.152542372881356, "grad_norm": 2.2953946280020125, "learning_rate": 4.601595322916049e-05, "loss": 0.3961, "step": 782 }, { "epoch": 1.1540162122328665, "grad_norm": 2.2525448712315637, "learning_rate": 4.600536020970822e-05, "loss": 0.4698, "step": 783 }, { "epoch": 1.1554900515843773, "grad_norm": 3.9402027844754497, "learning_rate": 4.5994754348926396e-05, "loss": 0.4451, "step": 784 }, { "epoch": 1.156963890935888, "grad_norm": 2.633004110817719, "learning_rate": 4.598413565329875e-05, "loss": 0.4375, "step": 785 }, { "epoch": 1.1584377302873987, "grad_norm": 3.1426227345924835, "learning_rate": 4.597350412931688e-05, "loss": 0.5953, "step": 786 }, { "epoch": 1.1599115696389093, "grad_norm": 2.4774370544628743, "learning_rate": 4.5962859783480215e-05, "loss": 0.4742, "step": 787 }, { "epoch": 1.16138540899042, "grad_norm": 2.6754759677013658, "learning_rate": 4.595220262229601e-05, "loss": 0.486, "step": 788 }, { "epoch": 1.1628592483419307, "grad_norm": 2.134988310735002, "learning_rate": 4.5941532652279406e-05, "loss": 0.4029, "step": 789 }, { "epoch": 1.1643330876934415, "grad_norm": 1.9354619412692373, "learning_rate": 4.5930849879953294e-05, "loss": 0.3668, "step": 790 }, { "epoch": 1.165806927044952, "grad_norm": 1.9788036682793533, "learning_rate": 4.592015431184848e-05, "loss": 0.4429, "step": 791 }, { "epoch": 1.1672807663964628, "grad_norm": 2.7469479356962303, "learning_rate": 4.5909445954503506e-05, "loss": 0.5163, "step": 792 }, { "epoch": 1.1687546057479734, "grad_norm": 3.1723904496224855, "learning_rate": 4.58987248144648e-05, "loss": 0.4765, "step": 793 }, { "epoch": 1.1702284450994842, "grad_norm": 2.6331759691500447, "learning_rate": 4.588799089828657e-05, "loss": 0.4549, "step": 794 }, { "epoch": 1.1717022844509948, "grad_norm": 2.7319077177756905, "learning_rate": 4.587724421253085e-05, "loss": 0.5316, "step": 795 }, { "epoch": 1.1731761238025056, "grad_norm": 2.619851194480229, "learning_rate": 4.586648476376747e-05, "loss": 0.4417, "step": 796 }, { "epoch": 1.1746499631540162, "grad_norm": 2.889107795719233, "learning_rate": 4.585571255857407e-05, "loss": 0.489, "step": 797 }, { "epoch": 1.176123802505527, "grad_norm": 2.129370850429405, "learning_rate": 4.5844927603536073e-05, "loss": 0.3995, "step": 798 }, { "epoch": 1.1775976418570375, "grad_norm": 1.7510077435961113, "learning_rate": 4.5834129905246725e-05, "loss": 0.3515, "step": 799 }, { "epoch": 1.1790714812085483, "grad_norm": 2.956392609783686, "learning_rate": 4.582331947030704e-05, "loss": 0.4217, "step": 800 }, { "epoch": 1.180545320560059, "grad_norm": 2.6144424846346586, "learning_rate": 4.5812496305325824e-05, "loss": 0.464, "step": 801 }, { "epoch": 1.1820191599115697, "grad_norm": 1.7654522161421076, "learning_rate": 4.580166041691966e-05, "loss": 0.3787, "step": 802 }, { "epoch": 1.1834929992630803, "grad_norm": 1.7375968357243539, "learning_rate": 4.5790811811712926e-05, "loss": 0.3429, "step": 803 }, { "epoch": 1.184966838614591, "grad_norm": 2.1730056125166377, "learning_rate": 4.5779950496337755e-05, "loss": 0.4706, "step": 804 }, { "epoch": 1.1864406779661016, "grad_norm": 3.058545420375669, "learning_rate": 4.576907647743406e-05, "loss": 0.3614, "step": 805 }, { "epoch": 1.1879145173176124, "grad_norm": 1.6532448910827935, "learning_rate": 4.5758189761649514e-05, "loss": 0.3806, "step": 806 }, { "epoch": 1.189388356669123, "grad_norm": 2.0628599372983722, "learning_rate": 4.574729035563957e-05, "loss": 0.4337, "step": 807 }, { "epoch": 1.1908621960206338, "grad_norm": 2.5079585237860793, "learning_rate": 4.573637826606741e-05, "loss": 0.4048, "step": 808 }, { "epoch": 1.1923360353721444, "grad_norm": 2.3676691855670917, "learning_rate": 4.5725453499604006e-05, "loss": 0.489, "step": 809 }, { "epoch": 1.1938098747236552, "grad_norm": 2.4791775444069946, "learning_rate": 4.571451606292803e-05, "loss": 0.4429, "step": 810 }, { "epoch": 1.1952837140751658, "grad_norm": 3.1207281287625652, "learning_rate": 4.570356596272596e-05, "loss": 0.4747, "step": 811 }, { "epoch": 1.1967575534266766, "grad_norm": 2.6835528818986014, "learning_rate": 4.5692603205691955e-05, "loss": 0.5161, "step": 812 }, { "epoch": 1.1982313927781871, "grad_norm": 2.3289244642444396, "learning_rate": 4.5681627798527965e-05, "loss": 0.4505, "step": 813 }, { "epoch": 1.199705232129698, "grad_norm": 2.323038163592944, "learning_rate": 4.5670639747943634e-05, "loss": 0.5248, "step": 814 }, { "epoch": 1.2011790714812085, "grad_norm": 2.298399853738421, "learning_rate": 4.565963906065637e-05, "loss": 0.4029, "step": 815 }, { "epoch": 1.2026529108327193, "grad_norm": 2.0621194199355175, "learning_rate": 4.564862574339126e-05, "loss": 0.5089, "step": 816 }, { "epoch": 1.2041267501842299, "grad_norm": 2.2531388958252476, "learning_rate": 4.563759980288117e-05, "loss": 0.4268, "step": 817 }, { "epoch": 1.2056005895357407, "grad_norm": 2.443672288210256, "learning_rate": 4.562656124586663e-05, "loss": 0.4367, "step": 818 }, { "epoch": 1.2070744288872512, "grad_norm": 3.2841854951814544, "learning_rate": 4.5615510079095914e-05, "loss": 0.5083, "step": 819 }, { "epoch": 1.208548268238762, "grad_norm": 2.592154690176722, "learning_rate": 4.5604446309324986e-05, "loss": 0.4778, "step": 820 }, { "epoch": 1.2100221075902726, "grad_norm": 2.1311029422622454, "learning_rate": 4.559336994331755e-05, "loss": 0.4395, "step": 821 }, { "epoch": 1.2114959469417834, "grad_norm": 1.9847846622075838, "learning_rate": 4.558228098784496e-05, "loss": 0.4265, "step": 822 }, { "epoch": 1.212969786293294, "grad_norm": 1.9625932610578305, "learning_rate": 4.5571179449686306e-05, "loss": 0.421, "step": 823 }, { "epoch": 1.2144436256448048, "grad_norm": 2.391959422555155, "learning_rate": 4.556006533562836e-05, "loss": 0.3985, "step": 824 }, { "epoch": 1.2159174649963154, "grad_norm": 3.1279205407882187, "learning_rate": 4.554893865246555e-05, "loss": 0.4593, "step": 825 }, { "epoch": 1.2173913043478262, "grad_norm": 2.185769186568125, "learning_rate": 4.553779940700005e-05, "loss": 0.4202, "step": 826 }, { "epoch": 1.2188651436993367, "grad_norm": 2.3149042776268733, "learning_rate": 4.5526647606041666e-05, "loss": 0.4294, "step": 827 }, { "epoch": 1.2203389830508475, "grad_norm": 2.578839567166518, "learning_rate": 4.551548325640789e-05, "loss": 0.4057, "step": 828 }, { "epoch": 1.2218128224023581, "grad_norm": 2.666974129435844, "learning_rate": 4.55043063649239e-05, "loss": 0.5446, "step": 829 }, { "epoch": 1.223286661753869, "grad_norm": 3.114878628786411, "learning_rate": 4.549311693842252e-05, "loss": 0.4867, "step": 830 }, { "epoch": 1.2247605011053795, "grad_norm": 2.9067142895054943, "learning_rate": 4.548191498374425e-05, "loss": 0.4619, "step": 831 }, { "epoch": 1.2262343404568903, "grad_norm": 2.613092754961583, "learning_rate": 4.547070050773725e-05, "loss": 0.5231, "step": 832 }, { "epoch": 1.2277081798084009, "grad_norm": 2.0045223367254845, "learning_rate": 4.5459473517257325e-05, "loss": 0.4341, "step": 833 }, { "epoch": 1.2291820191599117, "grad_norm": 1.7256898357586519, "learning_rate": 4.5448234019167945e-05, "loss": 0.3634, "step": 834 }, { "epoch": 1.2306558585114222, "grad_norm": 2.2426879536975073, "learning_rate": 4.543698202034021e-05, "loss": 0.4769, "step": 835 }, { "epoch": 1.232129697862933, "grad_norm": 2.703996815414359, "learning_rate": 4.542571752765288e-05, "loss": 0.4786, "step": 836 }, { "epoch": 1.2336035372144436, "grad_norm": 2.2314745878139797, "learning_rate": 4.541444054799233e-05, "loss": 0.3925, "step": 837 }, { "epoch": 1.2350773765659544, "grad_norm": 1.9944614970482653, "learning_rate": 4.5403151088252585e-05, "loss": 0.415, "step": 838 }, { "epoch": 1.236551215917465, "grad_norm": 3.408962324780798, "learning_rate": 4.539184915533531e-05, "loss": 0.4618, "step": 839 }, { "epoch": 1.2380250552689758, "grad_norm": 2.3149691622103443, "learning_rate": 4.5380534756149764e-05, "loss": 0.4754, "step": 840 }, { "epoch": 1.2394988946204863, "grad_norm": 2.0632099894734033, "learning_rate": 4.5369207897612854e-05, "loss": 0.4023, "step": 841 }, { "epoch": 1.2409727339719971, "grad_norm": 2.7276236756254555, "learning_rate": 4.535786858664909e-05, "loss": 0.5044, "step": 842 }, { "epoch": 1.2424465733235077, "grad_norm": 2.445160492386259, "learning_rate": 4.5346516830190606e-05, "loss": 0.5742, "step": 843 }, { "epoch": 1.2439204126750185, "grad_norm": 1.9222133927825438, "learning_rate": 4.5335152635177134e-05, "loss": 0.3721, "step": 844 }, { "epoch": 1.245394252026529, "grad_norm": 2.2909056237911503, "learning_rate": 4.5323776008556004e-05, "loss": 0.4267, "step": 845 }, { "epoch": 1.2468680913780399, "grad_norm": 2.254388555957129, "learning_rate": 4.531238695728218e-05, "loss": 0.416, "step": 846 }, { "epoch": 1.2483419307295505, "grad_norm": 2.863463267204487, "learning_rate": 4.530098548831817e-05, "loss": 0.4844, "step": 847 }, { "epoch": 1.2498157700810613, "grad_norm": 2.3374005587228144, "learning_rate": 4.5289571608634116e-05, "loss": 0.4451, "step": 848 }, { "epoch": 1.2512896094325718, "grad_norm": 2.8617890387090372, "learning_rate": 4.5278145325207735e-05, "loss": 0.4822, "step": 849 }, { "epoch": 1.2527634487840826, "grad_norm": 2.4801877801314025, "learning_rate": 4.526670664502431e-05, "loss": 0.3764, "step": 850 }, { "epoch": 1.2542372881355932, "grad_norm": 2.103227600950536, "learning_rate": 4.5255255575076726e-05, "loss": 0.4606, "step": 851 }, { "epoch": 1.2557111274871038, "grad_norm": 2.3516229260560757, "learning_rate": 4.5243792122365436e-05, "loss": 0.4821, "step": 852 }, { "epoch": 1.2571849668386146, "grad_norm": 2.1062078364195953, "learning_rate": 4.5232316293898445e-05, "loss": 0.3952, "step": 853 }, { "epoch": 1.2586588061901254, "grad_norm": 1.8293819833719298, "learning_rate": 4.522082809669135e-05, "loss": 0.4279, "step": 854 }, { "epoch": 1.260132645541636, "grad_norm": 2.138687036190553, "learning_rate": 4.5209327537767295e-05, "loss": 0.325, "step": 855 }, { "epoch": 1.2616064848931465, "grad_norm": 2.882299362041833, "learning_rate": 4.519781462415698e-05, "loss": 0.5113, "step": 856 }, { "epoch": 1.2630803242446573, "grad_norm": 1.8862410862777148, "learning_rate": 4.5186289362898664e-05, "loss": 0.4, "step": 857 }, { "epoch": 1.2645541635961681, "grad_norm": 1.551672768107928, "learning_rate": 4.517475176103816e-05, "loss": 0.3675, "step": 858 }, { "epoch": 1.2660280029476787, "grad_norm": 2.4586215308274157, "learning_rate": 4.51632018256288e-05, "loss": 0.4537, "step": 859 }, { "epoch": 1.2675018422991893, "grad_norm": 2.7148902943964255, "learning_rate": 4.51516395637315e-05, "loss": 0.3981, "step": 860 }, { "epoch": 1.2689756816507, "grad_norm": 2.5615223205773394, "learning_rate": 4.514006498241466e-05, "loss": 0.5149, "step": 861 }, { "epoch": 1.2704495210022109, "grad_norm": 2.237448971981636, "learning_rate": 4.512847808875424e-05, "loss": 0.4154, "step": 862 }, { "epoch": 1.2719233603537214, "grad_norm": 2.77683430437743, "learning_rate": 4.5116878889833734e-05, "loss": 0.4926, "step": 863 }, { "epoch": 1.273397199705232, "grad_norm": 2.63149484324326, "learning_rate": 4.5105267392744146e-05, "loss": 0.3712, "step": 864 }, { "epoch": 1.2748710390567428, "grad_norm": 2.6893171332833883, "learning_rate": 4.509364360458399e-05, "loss": 0.3779, "step": 865 }, { "epoch": 1.2763448784082536, "grad_norm": 2.73240102087847, "learning_rate": 4.508200753245932e-05, "loss": 0.4481, "step": 866 }, { "epoch": 1.2778187177597642, "grad_norm": 2.286605818618235, "learning_rate": 4.5070359183483676e-05, "loss": 0.506, "step": 867 }, { "epoch": 1.2792925571112748, "grad_norm": 3.0883306953376364, "learning_rate": 4.505869856477811e-05, "loss": 0.4716, "step": 868 }, { "epoch": 1.2807663964627856, "grad_norm": 2.214325697929008, "learning_rate": 4.504702568347117e-05, "loss": 0.4922, "step": 869 }, { "epoch": 1.2822402358142964, "grad_norm": 2.2192517640026352, "learning_rate": 4.503534054669892e-05, "loss": 0.5394, "step": 870 }, { "epoch": 1.283714075165807, "grad_norm": 1.9456177743887246, "learning_rate": 4.502364316160489e-05, "loss": 0.4058, "step": 871 }, { "epoch": 1.2851879145173175, "grad_norm": 1.7631145623299418, "learning_rate": 4.501193353534013e-05, "loss": 0.3397, "step": 872 }, { "epoch": 1.2866617538688283, "grad_norm": 2.0517940672368034, "learning_rate": 4.500021167506313e-05, "loss": 0.4487, "step": 873 }, { "epoch": 1.288135593220339, "grad_norm": 2.1194825068042364, "learning_rate": 4.49884775879399e-05, "loss": 0.4708, "step": 874 }, { "epoch": 1.2896094325718497, "grad_norm": 2.4275549456332812, "learning_rate": 4.497673128114391e-05, "loss": 0.5194, "step": 875 }, { "epoch": 1.2910832719233603, "grad_norm": 2.340014316156398, "learning_rate": 4.4964972761856084e-05, "loss": 0.4231, "step": 876 }, { "epoch": 1.292557111274871, "grad_norm": 2.646529599186935, "learning_rate": 4.495320203726483e-05, "loss": 0.476, "step": 877 }, { "epoch": 1.2940309506263818, "grad_norm": 1.9665401711704926, "learning_rate": 4.4941419114566026e-05, "loss": 0.4183, "step": 878 }, { "epoch": 1.2955047899778924, "grad_norm": 3.1191389433797125, "learning_rate": 4.492962400096298e-05, "loss": 0.5208, "step": 879 }, { "epoch": 1.296978629329403, "grad_norm": 2.0120381222141193, "learning_rate": 4.491781670366648e-05, "loss": 0.4397, "step": 880 }, { "epoch": 1.2984524686809138, "grad_norm": 2.3768065759247494, "learning_rate": 4.4905997229894735e-05, "loss": 0.4026, "step": 881 }, { "epoch": 1.2999263080324246, "grad_norm": 2.3285167799679445, "learning_rate": 4.4894165586873424e-05, "loss": 0.4321, "step": 882 }, { "epoch": 1.3014001473839352, "grad_norm": 2.1613868670924004, "learning_rate": 4.488232178183567e-05, "loss": 0.4279, "step": 883 }, { "epoch": 1.3028739867354457, "grad_norm": 2.8823939900949944, "learning_rate": 4.4870465822021976e-05, "loss": 0.5112, "step": 884 }, { "epoch": 1.3043478260869565, "grad_norm": 2.3537193368463214, "learning_rate": 4.485859771468035e-05, "loss": 0.4566, "step": 885 }, { "epoch": 1.3058216654384673, "grad_norm": 2.051057459077988, "learning_rate": 4.4846717467066177e-05, "loss": 0.4776, "step": 886 }, { "epoch": 1.307295504789978, "grad_norm": 2.6894134097467037, "learning_rate": 4.4834825086442275e-05, "loss": 0.4308, "step": 887 }, { "epoch": 1.3087693441414885, "grad_norm": 2.5575294668936936, "learning_rate": 4.482292058007889e-05, "loss": 0.4604, "step": 888 }, { "epoch": 1.3102431834929993, "grad_norm": 2.1389605880323654, "learning_rate": 4.4811003955253675e-05, "loss": 0.4262, "step": 889 }, { "epoch": 1.31171702284451, "grad_norm": 1.9756906871018738, "learning_rate": 4.479907521925168e-05, "loss": 0.3747, "step": 890 }, { "epoch": 1.3131908621960207, "grad_norm": 1.8344346408798968, "learning_rate": 4.478713437936537e-05, "loss": 0.4592, "step": 891 }, { "epoch": 1.3146647015475312, "grad_norm": 1.9964618380802184, "learning_rate": 4.477518144289462e-05, "loss": 0.47, "step": 892 }, { "epoch": 1.316138540899042, "grad_norm": 2.119796552972684, "learning_rate": 4.476321641714669e-05, "loss": 0.4286, "step": 893 }, { "epoch": 1.3176123802505528, "grad_norm": 2.262343562497834, "learning_rate": 4.4751239309436205e-05, "loss": 0.4154, "step": 894 }, { "epoch": 1.3190862196020634, "grad_norm": 3.1153381521703487, "learning_rate": 4.473925012708522e-05, "loss": 0.466, "step": 895 }, { "epoch": 1.320560058953574, "grad_norm": 2.139681865895875, "learning_rate": 4.4727248877423153e-05, "loss": 0.4811, "step": 896 }, { "epoch": 1.3220338983050848, "grad_norm": 2.050605693750672, "learning_rate": 4.471523556778679e-05, "loss": 0.5448, "step": 897 }, { "epoch": 1.3235077376565954, "grad_norm": 2.095113850961907, "learning_rate": 4.4703210205520296e-05, "loss": 0.4386, "step": 898 }, { "epoch": 1.3249815770081061, "grad_norm": 1.8532115176301782, "learning_rate": 4.469117279797522e-05, "loss": 0.3343, "step": 899 }, { "epoch": 1.3264554163596167, "grad_norm": 2.3946642690928353, "learning_rate": 4.467912335251044e-05, "loss": 0.4265, "step": 900 }, { "epoch": 1.3279292557111275, "grad_norm": 2.602247359942298, "learning_rate": 4.4667061876492236e-05, "loss": 0.4465, "step": 901 }, { "epoch": 1.329403095062638, "grad_norm": 1.6897209528494743, "learning_rate": 4.4654988377294196e-05, "loss": 0.3432, "step": 902 }, { "epoch": 1.330876934414149, "grad_norm": 2.4480466334694513, "learning_rate": 4.4642902862297306e-05, "loss": 0.5104, "step": 903 }, { "epoch": 1.3323507737656595, "grad_norm": 2.295983173813788, "learning_rate": 4.4630805338889866e-05, "loss": 0.4293, "step": 904 }, { "epoch": 1.3338246131171703, "grad_norm": 2.799432533526326, "learning_rate": 4.461869581446752e-05, "loss": 0.4252, "step": 905 }, { "epoch": 1.3352984524686808, "grad_norm": 2.008023024628389, "learning_rate": 4.460657429643326e-05, "loss": 0.3887, "step": 906 }, { "epoch": 1.3367722918201916, "grad_norm": 3.4906701668162485, "learning_rate": 4.45944407921974e-05, "loss": 0.3902, "step": 907 }, { "epoch": 1.3382461311717022, "grad_norm": 3.218859179969076, "learning_rate": 4.45822953091776e-05, "loss": 0.4336, "step": 908 }, { "epoch": 1.339719970523213, "grad_norm": 2.1745174442660793, "learning_rate": 4.457013785479881e-05, "loss": 0.3741, "step": 909 }, { "epoch": 1.3411938098747236, "grad_norm": 1.9473180275985613, "learning_rate": 4.4557968436493325e-05, "loss": 0.4244, "step": 910 }, { "epoch": 1.3426676492262344, "grad_norm": 2.1762528242326233, "learning_rate": 4.454578706170075e-05, "loss": 0.4756, "step": 911 }, { "epoch": 1.344141488577745, "grad_norm": 1.9053587784417299, "learning_rate": 4.453359373786799e-05, "loss": 0.3927, "step": 912 }, { "epoch": 1.3456153279292558, "grad_norm": 2.4626460850173477, "learning_rate": 4.4521388472449266e-05, "loss": 0.525, "step": 913 }, { "epoch": 1.3470891672807663, "grad_norm": 2.419376191691029, "learning_rate": 4.450917127290609e-05, "loss": 0.4307, "step": 914 }, { "epoch": 1.3485630066322771, "grad_norm": 3.558795408194359, "learning_rate": 4.4496942146707285e-05, "loss": 0.4334, "step": 915 }, { "epoch": 1.3500368459837877, "grad_norm": 2.4606450951656544, "learning_rate": 4.448470110132894e-05, "loss": 0.4969, "step": 916 }, { "epoch": 1.3515106853352985, "grad_norm": 2.1264378787935856, "learning_rate": 4.447244814425445e-05, "loss": 0.4064, "step": 917 }, { "epoch": 1.352984524686809, "grad_norm": 2.4097681459514795, "learning_rate": 4.446018328297449e-05, "loss": 0.4609, "step": 918 }, { "epoch": 1.3544583640383199, "grad_norm": 2.061111907867433, "learning_rate": 4.4447906524987004e-05, "loss": 0.4217, "step": 919 }, { "epoch": 1.3559322033898304, "grad_norm": 2.1071136786632017, "learning_rate": 4.443561787779722e-05, "loss": 0.4875, "step": 920 }, { "epoch": 1.3574060427413412, "grad_norm": 2.4882340119817044, "learning_rate": 4.442331734891762e-05, "loss": 0.4217, "step": 921 }, { "epoch": 1.3588798820928518, "grad_norm": 2.8652852995857954, "learning_rate": 4.4411004945867973e-05, "loss": 0.4418, "step": 922 }, { "epoch": 1.3603537214443626, "grad_norm": 2.2204059277823185, "learning_rate": 4.439868067617527e-05, "loss": 0.3894, "step": 923 }, { "epoch": 1.3618275607958732, "grad_norm": 1.9793301230409173, "learning_rate": 4.4386344547373805e-05, "loss": 0.4153, "step": 924 }, { "epoch": 1.363301400147384, "grad_norm": 2.161390176334261, "learning_rate": 4.437399656700507e-05, "loss": 0.4395, "step": 925 }, { "epoch": 1.3647752394988946, "grad_norm": 2.2084745565878605, "learning_rate": 4.436163674261785e-05, "loss": 0.4832, "step": 926 }, { "epoch": 1.3662490788504054, "grad_norm": 1.6939940357711267, "learning_rate": 4.434926508176813e-05, "loss": 0.42, "step": 927 }, { "epoch": 1.367722918201916, "grad_norm": 2.1010063030978126, "learning_rate": 4.4336881592019164e-05, "loss": 0.4452, "step": 928 }, { "epoch": 1.3691967575534267, "grad_norm": 1.958394137581609, "learning_rate": 4.4324486280941415e-05, "loss": 0.3795, "step": 929 }, { "epoch": 1.3706705969049373, "grad_norm": 2.5351256852151622, "learning_rate": 4.4312079156112585e-05, "loss": 0.4242, "step": 930 }, { "epoch": 1.372144436256448, "grad_norm": 2.2131642696814726, "learning_rate": 4.429966022511759e-05, "loss": 0.5122, "step": 931 }, { "epoch": 1.3736182756079587, "grad_norm": 2.1510165184589134, "learning_rate": 4.428722949554857e-05, "loss": 0.4044, "step": 932 }, { "epoch": 1.3750921149594695, "grad_norm": 1.8494609382466611, "learning_rate": 4.427478697500488e-05, "loss": 0.35, "step": 933 }, { "epoch": 1.37656595431098, "grad_norm": 2.203604679779773, "learning_rate": 4.4262332671093076e-05, "loss": 0.4184, "step": 934 }, { "epoch": 1.3780397936624909, "grad_norm": 2.036506775835146, "learning_rate": 4.4249866591426917e-05, "loss": 0.4646, "step": 935 }, { "epoch": 1.3795136330140014, "grad_norm": 2.313856500269434, "learning_rate": 4.423738874362736e-05, "loss": 0.4193, "step": 936 }, { "epoch": 1.3809874723655122, "grad_norm": 2.1115608475246628, "learning_rate": 4.422489913532258e-05, "loss": 0.475, "step": 937 }, { "epoch": 1.3824613117170228, "grad_norm": 2.5397657154196707, "learning_rate": 4.42123977741479e-05, "loss": 0.4091, "step": 938 }, { "epoch": 1.3839351510685336, "grad_norm": 2.336881312943058, "learning_rate": 4.419988466774586e-05, "loss": 0.4837, "step": 939 }, { "epoch": 1.3854089904200442, "grad_norm": 1.8643123564776527, "learning_rate": 4.418735982376617e-05, "loss": 0.3896, "step": 940 }, { "epoch": 1.386882829771555, "grad_norm": 1.9443671445770643, "learning_rate": 4.417482324986571e-05, "loss": 0.4685, "step": 941 }, { "epoch": 1.3883566691230655, "grad_norm": 2.379025511108976, "learning_rate": 4.416227495370855e-05, "loss": 0.5036, "step": 942 }, { "epoch": 1.3898305084745763, "grad_norm": 2.2625469476876545, "learning_rate": 4.41497149429659e-05, "loss": 0.4873, "step": 943 }, { "epoch": 1.391304347826087, "grad_norm": 2.5149078294613574, "learning_rate": 4.413714322531616e-05, "loss": 0.5219, "step": 944 }, { "epoch": 1.3927781871775977, "grad_norm": 2.049871101048626, "learning_rate": 4.412455980844485e-05, "loss": 0.4139, "step": 945 }, { "epoch": 1.3942520265291083, "grad_norm": 2.484116066928469, "learning_rate": 4.4111964700044686e-05, "loss": 0.428, "step": 946 }, { "epoch": 1.395725865880619, "grad_norm": 2.4538812139934842, "learning_rate": 4.409935790781549e-05, "loss": 0.4547, "step": 947 }, { "epoch": 1.3971997052321297, "grad_norm": 2.009123377967189, "learning_rate": 4.408673943946427e-05, "loss": 0.3562, "step": 948 }, { "epoch": 1.3986735445836405, "grad_norm": 2.2520308336413573, "learning_rate": 4.4074109302705116e-05, "loss": 0.4441, "step": 949 }, { "epoch": 1.400147383935151, "grad_norm": 2.5893815722832128, "learning_rate": 4.406146750525931e-05, "loss": 0.4638, "step": 950 }, { "epoch": 1.4016212232866618, "grad_norm": 2.47693349664741, "learning_rate": 4.404881405485522e-05, "loss": 0.538, "step": 951 }, { "epoch": 1.4030950626381724, "grad_norm": 4.053504021422031, "learning_rate": 4.4036148959228365e-05, "loss": 0.5226, "step": 952 }, { "epoch": 1.4045689019896832, "grad_norm": 2.0490668987711573, "learning_rate": 4.402347222612137e-05, "loss": 0.4534, "step": 953 }, { "epoch": 1.4060427413411938, "grad_norm": 2.95749143700799, "learning_rate": 4.401078386328396e-05, "loss": 0.4597, "step": 954 }, { "epoch": 1.4075165806927046, "grad_norm": 2.4772670958950505, "learning_rate": 4.399808387847301e-05, "loss": 0.4814, "step": 955 }, { "epoch": 1.4089904200442152, "grad_norm": 3.020500392762872, "learning_rate": 4.3985372279452464e-05, "loss": 0.4521, "step": 956 }, { "epoch": 1.410464259395726, "grad_norm": 2.023560627022717, "learning_rate": 4.397264907399337e-05, "loss": 0.4474, "step": 957 }, { "epoch": 1.4119380987472365, "grad_norm": 1.9596864273343308, "learning_rate": 4.3959914269873896e-05, "loss": 0.4377, "step": 958 }, { "epoch": 1.413411938098747, "grad_norm": 1.5602658129689797, "learning_rate": 4.394716787487928e-05, "loss": 0.3406, "step": 959 }, { "epoch": 1.414885777450258, "grad_norm": 4.2479299103868895, "learning_rate": 4.393440989680184e-05, "loss": 0.4458, "step": 960 }, { "epoch": 1.4163596168017687, "grad_norm": 1.9010720516197772, "learning_rate": 4.392164034344099e-05, "loss": 0.3894, "step": 961 }, { "epoch": 1.4178334561532793, "grad_norm": 2.2715880746696673, "learning_rate": 4.390885922260323e-05, "loss": 0.467, "step": 962 }, { "epoch": 1.4193072955047898, "grad_norm": 2.1387656274042897, "learning_rate": 4.389606654210209e-05, "loss": 0.4623, "step": 963 }, { "epoch": 1.4207811348563006, "grad_norm": 2.094257577890377, "learning_rate": 4.3883262309758224e-05, "loss": 0.4616, "step": 964 }, { "epoch": 1.4222549742078114, "grad_norm": 2.895711845941609, "learning_rate": 4.387044653339929e-05, "loss": 0.4703, "step": 965 }, { "epoch": 1.423728813559322, "grad_norm": 2.354662300081334, "learning_rate": 4.385761922086006e-05, "loss": 0.4326, "step": 966 }, { "epoch": 1.4252026529108326, "grad_norm": 1.6978427270185237, "learning_rate": 4.3844780379982296e-05, "loss": 0.366, "step": 967 }, { "epoch": 1.4266764922623434, "grad_norm": 2.001419636424524, "learning_rate": 4.3831930018614875e-05, "loss": 0.4446, "step": 968 }, { "epoch": 1.4281503316138542, "grad_norm": 2.038244441421249, "learning_rate": 4.3819068144613665e-05, "loss": 0.4007, "step": 969 }, { "epoch": 1.4296241709653648, "grad_norm": 3.147850417309542, "learning_rate": 4.380619476584159e-05, "loss": 0.4728, "step": 970 }, { "epoch": 1.4310980103168753, "grad_norm": 2.115994050196051, "learning_rate": 4.379330989016861e-05, "loss": 0.4124, "step": 971 }, { "epoch": 1.4325718496683861, "grad_norm": 2.425841891257172, "learning_rate": 4.378041352547172e-05, "loss": 0.5014, "step": 972 }, { "epoch": 1.434045689019897, "grad_norm": 2.1836883033111816, "learning_rate": 4.376750567963492e-05, "loss": 0.4825, "step": 973 }, { "epoch": 1.4355195283714075, "grad_norm": 2.691623274824443, "learning_rate": 4.375458636054924e-05, "loss": 0.5021, "step": 974 }, { "epoch": 1.436993367722918, "grad_norm": 2.4388338987464993, "learning_rate": 4.374165557611273e-05, "loss": 0.4681, "step": 975 }, { "epoch": 1.4384672070744289, "grad_norm": 2.0722219047284787, "learning_rate": 4.3728713334230435e-05, "loss": 0.3988, "step": 976 }, { "epoch": 1.4399410464259397, "grad_norm": 2.631458330401816, "learning_rate": 4.3715759642814415e-05, "loss": 0.51, "step": 977 }, { "epoch": 1.4414148857774502, "grad_norm": 2.176900743435777, "learning_rate": 4.3702794509783725e-05, "loss": 0.4186, "step": 978 }, { "epoch": 1.4428887251289608, "grad_norm": 2.2239064218744446, "learning_rate": 4.368981794306441e-05, "loss": 0.5233, "step": 979 }, { "epoch": 1.4443625644804716, "grad_norm": 1.983006042702106, "learning_rate": 4.3676829950589516e-05, "loss": 0.4406, "step": 980 }, { "epoch": 1.4458364038319824, "grad_norm": 2.5913534467835966, "learning_rate": 4.366383054029906e-05, "loss": 0.3978, "step": 981 }, { "epoch": 1.447310243183493, "grad_norm": 2.0074886550677764, "learning_rate": 4.365081972014007e-05, "loss": 0.4542, "step": 982 }, { "epoch": 1.4487840825350036, "grad_norm": 1.9486985362893625, "learning_rate": 4.36377974980665e-05, "loss": 0.4073, "step": 983 }, { "epoch": 1.4502579218865144, "grad_norm": 1.7482290844281894, "learning_rate": 4.362476388203932e-05, "loss": 0.3626, "step": 984 }, { "epoch": 1.4517317612380252, "grad_norm": 2.5550865305004304, "learning_rate": 4.3611718880026436e-05, "loss": 0.4914, "step": 985 }, { "epoch": 1.4532056005895357, "grad_norm": 1.8116522154572379, "learning_rate": 4.359866250000273e-05, "loss": 0.3908, "step": 986 }, { "epoch": 1.4546794399410463, "grad_norm": 2.556207886887592, "learning_rate": 4.358559474995003e-05, "loss": 0.5318, "step": 987 }, { "epoch": 1.4561532792925571, "grad_norm": 1.8333044772333635, "learning_rate": 4.357251563785713e-05, "loss": 0.3629, "step": 988 }, { "epoch": 1.457627118644068, "grad_norm": 2.6646904079546205, "learning_rate": 4.3559425171719745e-05, "loss": 0.4266, "step": 989 }, { "epoch": 1.4591009579955785, "grad_norm": 1.9016445371035053, "learning_rate": 4.354632335954056e-05, "loss": 0.3978, "step": 990 }, { "epoch": 1.460574797347089, "grad_norm": 2.3492901237157118, "learning_rate": 4.3533210209329176e-05, "loss": 0.4278, "step": 991 }, { "epoch": 1.4620486366985999, "grad_norm": 2.4934214822551333, "learning_rate": 4.352008572910213e-05, "loss": 0.3687, "step": 992 }, { "epoch": 1.4635224760501107, "grad_norm": 2.2956810787090665, "learning_rate": 4.350694992688289e-05, "loss": 0.5155, "step": 993 }, { "epoch": 1.4649963154016212, "grad_norm": 2.3785466265275166, "learning_rate": 4.3493802810701846e-05, "loss": 0.4035, "step": 994 }, { "epoch": 1.4664701547531318, "grad_norm": 1.9740195218737446, "learning_rate": 4.348064438859629e-05, "loss": 0.3963, "step": 995 }, { "epoch": 1.4679439941046426, "grad_norm": 2.4878706421111736, "learning_rate": 4.346747466861045e-05, "loss": 0.5291, "step": 996 }, { "epoch": 1.4694178334561534, "grad_norm": 2.0919636179967895, "learning_rate": 4.345429365879545e-05, "loss": 0.4122, "step": 997 }, { "epoch": 1.470891672807664, "grad_norm": 1.8355802797215415, "learning_rate": 4.3441101367209304e-05, "loss": 0.3769, "step": 998 }, { "epoch": 1.4723655121591745, "grad_norm": 2.0921526836891413, "learning_rate": 4.3427897801916926e-05, "loss": 0.3747, "step": 999 }, { "epoch": 1.4738393515106853, "grad_norm": 2.3652529223570893, "learning_rate": 4.341468297099014e-05, "loss": 0.5376, "step": 1000 }, { "epoch": 1.4738393515106853, "eval_bleu": 0.201927934105831, "eval_bleu_1gram": 0.5123679186946342, "eval_bleu_2gram": 0.30180801073234914, "eval_bleu_3gram": 0.1900578318550993, "eval_bleu_4gram": 0.12578867786709128, "eval_rag_val_loss": 0.6162106047074, "eval_rouge1": 0.5125204573076769, "eval_rouge2": 0.29503973062939304, "eval_rougeL": 0.5073775484827798, "step": 1000 }, { "epoch": 1.4753131908621961, "grad_norm": 2.575923002425074, "learning_rate": 4.340145688250765e-05, "loss": 0.4559, "step": 1001 }, { "epoch": 1.4767870302137067, "grad_norm": 1.9651825083843397, "learning_rate": 4.338821954455503e-05, "loss": 0.4405, "step": 1002 }, { "epoch": 1.4782608695652173, "grad_norm": 2.3971283660624745, "learning_rate": 4.3374970965224735e-05, "loss": 0.5008, "step": 1003 }, { "epoch": 1.479734708916728, "grad_norm": 1.6339502340603476, "learning_rate": 4.3361711152616105e-05, "loss": 0.3275, "step": 1004 }, { "epoch": 1.481208548268239, "grad_norm": 2.8031360298543624, "learning_rate": 4.3348440114835336e-05, "loss": 0.5527, "step": 1005 }, { "epoch": 1.4826823876197495, "grad_norm": 2.275844806971403, "learning_rate": 4.333515785999549e-05, "loss": 0.432, "step": 1006 }, { "epoch": 1.48415622697126, "grad_norm": 2.4553704159860903, "learning_rate": 4.3321864396216484e-05, "loss": 0.3812, "step": 1007 }, { "epoch": 1.4856300663227708, "grad_norm": 2.3173988621441692, "learning_rate": 4.330855973162509e-05, "loss": 0.4489, "step": 1008 }, { "epoch": 1.4871039056742816, "grad_norm": 1.7727362636969495, "learning_rate": 4.3295243874354926e-05, "loss": 0.3836, "step": 1009 }, { "epoch": 1.4885777450257922, "grad_norm": 1.7048567620571764, "learning_rate": 4.3281916832546455e-05, "loss": 0.3014, "step": 1010 }, { "epoch": 1.4900515843773028, "grad_norm": 1.936287900727362, "learning_rate": 4.326857861434697e-05, "loss": 0.3465, "step": 1011 }, { "epoch": 1.4915254237288136, "grad_norm": 2.3665503724050785, "learning_rate": 4.32552292279106e-05, "loss": 0.4742, "step": 1012 }, { "epoch": 1.4929992630803244, "grad_norm": 3.054180444649033, "learning_rate": 4.3241868681398307e-05, "loss": 0.4092, "step": 1013 }, { "epoch": 1.494473102431835, "grad_norm": 2.1804030689719673, "learning_rate": 4.322849698297787e-05, "loss": 0.4339, "step": 1014 }, { "epoch": 1.4959469417833455, "grad_norm": 2.047692987199062, "learning_rate": 4.32151141408239e-05, "loss": 0.4393, "step": 1015 }, { "epoch": 1.4974207811348563, "grad_norm": 2.3492243602750396, "learning_rate": 4.3201720163117795e-05, "loss": 0.4734, "step": 1016 }, { "epoch": 1.4988946204863671, "grad_norm": 2.1778110097222356, "learning_rate": 4.318831505804778e-05, "loss": 0.5004, "step": 1017 }, { "epoch": 1.5003684598378777, "grad_norm": 2.3062652876846053, "learning_rate": 4.317489883380887e-05, "loss": 0.4817, "step": 1018 }, { "epoch": 1.5018422991893883, "grad_norm": 2.1441135242853147, "learning_rate": 4.316147149860289e-05, "loss": 0.4796, "step": 1019 }, { "epoch": 1.503316138540899, "grad_norm": 2.131451294641621, "learning_rate": 4.314803306063844e-05, "loss": 0.3934, "step": 1020 }, { "epoch": 1.5047899778924099, "grad_norm": 2.325137891064394, "learning_rate": 4.313458352813094e-05, "loss": 0.5448, "step": 1021 }, { "epoch": 1.5062638172439204, "grad_norm": 1.7261658640142004, "learning_rate": 4.312112290930255e-05, "loss": 0.3815, "step": 1022 }, { "epoch": 1.507737656595431, "grad_norm": 2.0762839515845184, "learning_rate": 4.3107651212382236e-05, "loss": 0.4768, "step": 1023 }, { "epoch": 1.5092114959469418, "grad_norm": 2.149306908605174, "learning_rate": 4.3094168445605735e-05, "loss": 0.3833, "step": 1024 }, { "epoch": 1.5106853352984526, "grad_norm": 2.870234645063816, "learning_rate": 4.308067461721553e-05, "loss": 0.4639, "step": 1025 }, { "epoch": 1.5121591746499632, "grad_norm": 2.749001408381984, "learning_rate": 4.30671697354609e-05, "loss": 0.4266, "step": 1026 }, { "epoch": 1.5136330140014738, "grad_norm": 2.0078419486532013, "learning_rate": 4.305365380859786e-05, "loss": 0.4761, "step": 1027 }, { "epoch": 1.5151068533529846, "grad_norm": 2.626927440191581, "learning_rate": 4.3040126844889174e-05, "loss": 0.4463, "step": 1028 }, { "epoch": 1.5165806927044954, "grad_norm": 2.0594260688435084, "learning_rate": 4.302658885260436e-05, "loss": 0.4305, "step": 1029 }, { "epoch": 1.518054532056006, "grad_norm": 2.1289339116250505, "learning_rate": 4.301303984001967e-05, "loss": 0.4995, "step": 1030 }, { "epoch": 1.5195283714075165, "grad_norm": 3.1930983503793477, "learning_rate": 4.299947981541813e-05, "loss": 0.428, "step": 1031 }, { "epoch": 1.5210022107590273, "grad_norm": 2.268687106014745, "learning_rate": 4.298590878708944e-05, "loss": 0.379, "step": 1032 }, { "epoch": 1.522476050110538, "grad_norm": 1.9312309856775014, "learning_rate": 4.297232676333007e-05, "loss": 0.4214, "step": 1033 }, { "epoch": 1.5239498894620487, "grad_norm": 1.8526563672624454, "learning_rate": 4.2958733752443195e-05, "loss": 0.4062, "step": 1034 }, { "epoch": 1.5254237288135593, "grad_norm": 2.227947888283681, "learning_rate": 4.29451297627387e-05, "loss": 0.4679, "step": 1035 }, { "epoch": 1.52689756816507, "grad_norm": 2.043234346532143, "learning_rate": 4.293151480253321e-05, "loss": 0.4559, "step": 1036 }, { "epoch": 1.5283714075165808, "grad_norm": 2.446902504640922, "learning_rate": 4.291788888015002e-05, "loss": 0.3922, "step": 1037 }, { "epoch": 1.5298452468680914, "grad_norm": 2.5936475067110805, "learning_rate": 4.2904252003919164e-05, "loss": 0.4154, "step": 1038 }, { "epoch": 1.531319086219602, "grad_norm": 2.196495741859371, "learning_rate": 4.2890604182177336e-05, "loss": 0.4637, "step": 1039 }, { "epoch": 1.5327929255711128, "grad_norm": 3.3336534028563882, "learning_rate": 4.2876945423267947e-05, "loss": 0.474, "step": 1040 }, { "epoch": 1.5342667649226236, "grad_norm": 1.810028298193661, "learning_rate": 4.286327573554108e-05, "loss": 0.4732, "step": 1041 }, { "epoch": 1.5357406042741342, "grad_norm": 2.2056736914734367, "learning_rate": 4.2849595127353515e-05, "loss": 0.4213, "step": 1042 }, { "epoch": 1.5372144436256447, "grad_norm": 1.7524071894951212, "learning_rate": 4.2835903607068685e-05, "loss": 0.4177, "step": 1043 }, { "epoch": 1.5386882829771555, "grad_norm": 1.9034332351499008, "learning_rate": 4.282220118305672e-05, "loss": 0.4166, "step": 1044 }, { "epoch": 1.5401621223286663, "grad_norm": 2.222868951096483, "learning_rate": 4.280848786369439e-05, "loss": 0.4675, "step": 1045 }, { "epoch": 1.541635961680177, "grad_norm": 2.5809014369053815, "learning_rate": 4.279476365736516e-05, "loss": 0.4082, "step": 1046 }, { "epoch": 1.5431098010316875, "grad_norm": 2.344563355777393, "learning_rate": 4.27810285724591e-05, "loss": 0.5274, "step": 1047 }, { "epoch": 1.5445836403831983, "grad_norm": 2.100155384127967, "learning_rate": 4.276728261737298e-05, "loss": 0.3592, "step": 1048 }, { "epoch": 1.5460574797347089, "grad_norm": 3.1146944636461016, "learning_rate": 4.275352580051018e-05, "loss": 0.499, "step": 1049 }, { "epoch": 1.5475313190862194, "grad_norm": 2.3228231391267915, "learning_rate": 4.273975813028076e-05, "loss": 0.4883, "step": 1050 }, { "epoch": 1.5490051584377302, "grad_norm": 2.260253115126644, "learning_rate": 4.272597961510137e-05, "loss": 0.4374, "step": 1051 }, { "epoch": 1.550478997789241, "grad_norm": 2.0683692881460978, "learning_rate": 4.271219026339531e-05, "loss": 0.3994, "step": 1052 }, { "epoch": 1.5519528371407516, "grad_norm": 2.0888273530490613, "learning_rate": 4.269839008359252e-05, "loss": 0.4061, "step": 1053 }, { "epoch": 1.5534266764922622, "grad_norm": 2.107162445476085, "learning_rate": 4.2684579084129525e-05, "loss": 0.553, "step": 1054 }, { "epoch": 1.554900515843773, "grad_norm": 3.809603231601234, "learning_rate": 4.2670757273449504e-05, "loss": 0.4891, "step": 1055 }, { "epoch": 1.5563743551952838, "grad_norm": 3.1055621055150286, "learning_rate": 4.2656924660002205e-05, "loss": 0.4769, "step": 1056 }, { "epoch": 1.5578481945467944, "grad_norm": 2.220901198599715, "learning_rate": 4.264308125224402e-05, "loss": 0.4928, "step": 1057 }, { "epoch": 1.559322033898305, "grad_norm": 2.8172993718688155, "learning_rate": 4.2629227058637904e-05, "loss": 0.4977, "step": 1058 }, { "epoch": 1.5607958732498157, "grad_norm": 2.0252681978427844, "learning_rate": 4.261536208765343e-05, "loss": 0.4175, "step": 1059 }, { "epoch": 1.5622697126013265, "grad_norm": 1.7605797581112366, "learning_rate": 4.260148634776675e-05, "loss": 0.4212, "step": 1060 }, { "epoch": 1.563743551952837, "grad_norm": 1.8398192580226902, "learning_rate": 4.25875998474606e-05, "loss": 0.4161, "step": 1061 }, { "epoch": 1.5652173913043477, "grad_norm": 1.9778214617999446, "learning_rate": 4.25737025952243e-05, "loss": 0.432, "step": 1062 }, { "epoch": 1.5666912306558585, "grad_norm": 1.8366208367188566, "learning_rate": 4.2559794599553734e-05, "loss": 0.4042, "step": 1063 }, { "epoch": 1.5681650700073693, "grad_norm": 2.1265858735111056, "learning_rate": 4.2545875868951355e-05, "loss": 0.5111, "step": 1064 }, { "epoch": 1.5696389093588798, "grad_norm": 2.2025625173678542, "learning_rate": 4.253194641192621e-05, "loss": 0.5032, "step": 1065 }, { "epoch": 1.5711127487103904, "grad_norm": 1.96718074685317, "learning_rate": 4.251800623699383e-05, "loss": 0.3971, "step": 1066 }, { "epoch": 1.5725865880619012, "grad_norm": 2.5301593267459426, "learning_rate": 4.250405535267636e-05, "loss": 0.5213, "step": 1067 }, { "epoch": 1.574060427413412, "grad_norm": 1.9646480151869141, "learning_rate": 4.249009376750249e-05, "loss": 0.3504, "step": 1068 }, { "epoch": 1.5755342667649226, "grad_norm": 1.8989011724186478, "learning_rate": 4.247612149000743e-05, "loss": 0.4143, "step": 1069 }, { "epoch": 1.5770081061164332, "grad_norm": 2.508773096849743, "learning_rate": 4.246213852873293e-05, "loss": 0.4215, "step": 1070 }, { "epoch": 1.578481945467944, "grad_norm": 2.083407006550532, "learning_rate": 4.2448144892227276e-05, "loss": 0.3498, "step": 1071 }, { "epoch": 1.5799557848194548, "grad_norm": 3.0948134627078123, "learning_rate": 4.243414058904528e-05, "loss": 0.4398, "step": 1072 }, { "epoch": 1.5814296241709653, "grad_norm": 2.86544222815656, "learning_rate": 4.2420125627748286e-05, "loss": 0.5178, "step": 1073 }, { "epoch": 1.582903463522476, "grad_norm": 2.0914198021775614, "learning_rate": 4.240610001690413e-05, "loss": 0.4723, "step": 1074 }, { "epoch": 1.5843773028739867, "grad_norm": 2.758848001306256, "learning_rate": 4.239206376508717e-05, "loss": 0.4495, "step": 1075 }, { "epoch": 1.5858511422254975, "grad_norm": 2.3060325706146996, "learning_rate": 4.237801688087826e-05, "loss": 0.45, "step": 1076 }, { "epoch": 1.587324981577008, "grad_norm": 2.138705095703744, "learning_rate": 4.2363959372864795e-05, "loss": 0.4681, "step": 1077 }, { "epoch": 1.5887988209285187, "grad_norm": 2.233069405214683, "learning_rate": 4.234989124964061e-05, "loss": 0.4082, "step": 1078 }, { "epoch": 1.5902726602800294, "grad_norm": 2.527763886000174, "learning_rate": 4.233581251980604e-05, "loss": 0.4764, "step": 1079 }, { "epoch": 1.5917464996315402, "grad_norm": 2.274251051646838, "learning_rate": 4.232172319196796e-05, "loss": 0.453, "step": 1080 }, { "epoch": 1.5932203389830508, "grad_norm": 2.223882514560541, "learning_rate": 4.230762327473964e-05, "loss": 0.4789, "step": 1081 }, { "epoch": 1.5946941783345614, "grad_norm": 1.8102302809432687, "learning_rate": 4.2293512776740885e-05, "loss": 0.3998, "step": 1082 }, { "epoch": 1.5961680176860722, "grad_norm": 2.12677141294353, "learning_rate": 4.227939170659794e-05, "loss": 0.4531, "step": 1083 }, { "epoch": 1.597641857037583, "grad_norm": 1.7832188349655391, "learning_rate": 4.226526007294354e-05, "loss": 0.3714, "step": 1084 }, { "epoch": 1.5991156963890936, "grad_norm": 2.245769231821568, "learning_rate": 4.225111788441683e-05, "loss": 0.4656, "step": 1085 }, { "epoch": 1.6005895357406041, "grad_norm": 1.7045171105311274, "learning_rate": 4.223696514966346e-05, "loss": 0.3628, "step": 1086 }, { "epoch": 1.602063375092115, "grad_norm": 3.959673376966628, "learning_rate": 4.2222801877335484e-05, "loss": 0.433, "step": 1087 }, { "epoch": 1.6035372144436257, "grad_norm": 1.8021754496703848, "learning_rate": 4.2208628076091434e-05, "loss": 0.3672, "step": 1088 }, { "epoch": 1.6050110537951363, "grad_norm": 2.452377399798257, "learning_rate": 4.219444375459626e-05, "loss": 0.4607, "step": 1089 }, { "epoch": 1.6064848931466469, "grad_norm": 2.4579064488870834, "learning_rate": 4.2180248921521334e-05, "loss": 0.4078, "step": 1090 }, { "epoch": 1.6079587324981577, "grad_norm": 2.4831870255691735, "learning_rate": 4.216604358554449e-05, "loss": 0.4096, "step": 1091 }, { "epoch": 1.6094325718496685, "grad_norm": 2.1648465605669007, "learning_rate": 4.215182775534994e-05, "loss": 0.3503, "step": 1092 }, { "epoch": 1.610906411201179, "grad_norm": 2.2578173574639573, "learning_rate": 4.213760143962834e-05, "loss": 0.4957, "step": 1093 }, { "epoch": 1.6123802505526896, "grad_norm": 2.5005467770599967, "learning_rate": 4.212336464707674e-05, "loss": 0.4123, "step": 1094 }, { "epoch": 1.6138540899042004, "grad_norm": 2.3421597998917068, "learning_rate": 4.2109117386398595e-05, "loss": 0.4378, "step": 1095 }, { "epoch": 1.6153279292557112, "grad_norm": 2.5775412158649225, "learning_rate": 4.2094859666303774e-05, "loss": 0.3973, "step": 1096 }, { "epoch": 1.6168017686072218, "grad_norm": 2.0598216149952906, "learning_rate": 4.208059149550855e-05, "loss": 0.3534, "step": 1097 }, { "epoch": 1.6182756079587324, "grad_norm": 2.048962293219283, "learning_rate": 4.2066312882735535e-05, "loss": 0.3897, "step": 1098 }, { "epoch": 1.6197494473102432, "grad_norm": 2.0025358812639316, "learning_rate": 4.205202383671378e-05, "loss": 0.3852, "step": 1099 }, { "epoch": 1.621223286661754, "grad_norm": 3.170680530557355, "learning_rate": 4.203772436617868e-05, "loss": 0.5251, "step": 1100 }, { "epoch": 1.6226971260132645, "grad_norm": 3.5540226241182173, "learning_rate": 4.202341447987202e-05, "loss": 0.4863, "step": 1101 }, { "epoch": 1.6241709653647751, "grad_norm": 2.2165884314859103, "learning_rate": 4.2009094186541945e-05, "loss": 0.415, "step": 1102 }, { "epoch": 1.625644804716286, "grad_norm": 2.174905981026801, "learning_rate": 4.199476349494296e-05, "loss": 0.3798, "step": 1103 }, { "epoch": 1.6271186440677967, "grad_norm": 2.4494029193366456, "learning_rate": 4.1980422413835926e-05, "loss": 0.4348, "step": 1104 }, { "epoch": 1.6285924834193073, "grad_norm": 2.594878812837742, "learning_rate": 4.196607095198807e-05, "loss": 0.4257, "step": 1105 }, { "epoch": 1.6300663227708179, "grad_norm": 2.8408520363367042, "learning_rate": 4.195170911817295e-05, "loss": 0.5072, "step": 1106 }, { "epoch": 1.6315401621223287, "grad_norm": 2.946472748924763, "learning_rate": 4.1937336921170476e-05, "loss": 0.4501, "step": 1107 }, { "epoch": 1.6330140014738395, "grad_norm": 2.4683311203614626, "learning_rate": 4.192295436976688e-05, "loss": 0.4474, "step": 1108 }, { "epoch": 1.63448784082535, "grad_norm": 2.9614901467268395, "learning_rate": 4.1908561472754737e-05, "loss": 0.4291, "step": 1109 }, { "epoch": 1.6359616801768606, "grad_norm": 3.0222105548047513, "learning_rate": 4.189415823893293e-05, "loss": 0.4316, "step": 1110 }, { "epoch": 1.6374355195283714, "grad_norm": 2.317545464325895, "learning_rate": 4.1879744677106685e-05, "loss": 0.424, "step": 1111 }, { "epoch": 1.6389093588798822, "grad_norm": 1.91493292499333, "learning_rate": 4.186532079608753e-05, "loss": 0.4147, "step": 1112 }, { "epoch": 1.6403831982313928, "grad_norm": 2.382923561384598, "learning_rate": 4.185088660469328e-05, "loss": 0.4056, "step": 1113 }, { "epoch": 1.6418570375829034, "grad_norm": 2.2908855378535145, "learning_rate": 4.183644211174809e-05, "loss": 0.4804, "step": 1114 }, { "epoch": 1.6433308769344142, "grad_norm": 2.640392496380534, "learning_rate": 4.1821987326082394e-05, "loss": 0.4297, "step": 1115 }, { "epoch": 1.644804716285925, "grad_norm": 2.707875394008206, "learning_rate": 4.180752225653292e-05, "loss": 0.4899, "step": 1116 }, { "epoch": 1.6462785556374355, "grad_norm": 2.357186420252802, "learning_rate": 4.179304691194269e-05, "loss": 0.4176, "step": 1117 }, { "epoch": 1.647752394988946, "grad_norm": 2.313851554368931, "learning_rate": 4.177856130116099e-05, "loss": 0.392, "step": 1118 }, { "epoch": 1.649226234340457, "grad_norm": 2.869417160345963, "learning_rate": 4.176406543304339e-05, "loss": 0.4112, "step": 1119 }, { "epoch": 1.6507000736919677, "grad_norm": 2.3242126977665425, "learning_rate": 4.1749559316451745e-05, "loss": 0.5059, "step": 1120 }, { "epoch": 1.6521739130434783, "grad_norm": 3.3963580203998482, "learning_rate": 4.173504296025417e-05, "loss": 0.509, "step": 1121 }, { "epoch": 1.6536477523949888, "grad_norm": 2.586814892870773, "learning_rate": 4.172051637332501e-05, "loss": 0.4941, "step": 1122 }, { "epoch": 1.6551215917464996, "grad_norm": 1.7883633242696786, "learning_rate": 4.170597956454492e-05, "loss": 0.3811, "step": 1123 }, { "epoch": 1.6565954310980104, "grad_norm": 2.9149656149143186, "learning_rate": 4.169143254280074e-05, "loss": 0.479, "step": 1124 }, { "epoch": 1.658069270449521, "grad_norm": 2.5930542529778893, "learning_rate": 4.1676875316985606e-05, "loss": 0.4276, "step": 1125 }, { "epoch": 1.6595431098010316, "grad_norm": 1.809441056964595, "learning_rate": 4.1662307895998867e-05, "loss": 0.4026, "step": 1126 }, { "epoch": 1.6610169491525424, "grad_norm": 2.5538205416847246, "learning_rate": 4.16477302887461e-05, "loss": 0.5797, "step": 1127 }, { "epoch": 1.6624907885040532, "grad_norm": 2.3700578365431446, "learning_rate": 4.163314250413913e-05, "loss": 0.4551, "step": 1128 }, { "epoch": 1.6639646278555638, "grad_norm": 2.2156471800131103, "learning_rate": 4.161854455109601e-05, "loss": 0.4725, "step": 1129 }, { "epoch": 1.6654384672070743, "grad_norm": 2.8843001168925957, "learning_rate": 4.160393643854095e-05, "loss": 0.5225, "step": 1130 }, { "epoch": 1.6669123065585851, "grad_norm": 3.0858478774564917, "learning_rate": 4.158931817540444e-05, "loss": 0.4539, "step": 1131 }, { "epoch": 1.668386145910096, "grad_norm": 1.8637831549762416, "learning_rate": 4.1574689770623145e-05, "loss": 0.2933, "step": 1132 }, { "epoch": 1.6698599852616065, "grad_norm": 1.9446460240946422, "learning_rate": 4.156005123313993e-05, "loss": 0.3515, "step": 1133 }, { "epoch": 1.671333824613117, "grad_norm": 1.9083949044413233, "learning_rate": 4.1545402571903855e-05, "loss": 0.3491, "step": 1134 }, { "epoch": 1.6728076639646279, "grad_norm": 4.054121327056834, "learning_rate": 4.153074379587018e-05, "loss": 0.4618, "step": 1135 }, { "epoch": 1.6742815033161387, "grad_norm": 2.128707232490869, "learning_rate": 4.151607491400034e-05, "loss": 0.3957, "step": 1136 }, { "epoch": 1.6757553426676493, "grad_norm": 3.1175192749602263, "learning_rate": 4.1501395935261934e-05, "loss": 0.4342, "step": 1137 }, { "epoch": 1.6772291820191598, "grad_norm": 2.741137529075859, "learning_rate": 4.1486706868628764e-05, "loss": 0.5081, "step": 1138 }, { "epoch": 1.6787030213706706, "grad_norm": 2.218429972174662, "learning_rate": 4.147200772308077e-05, "loss": 0.4869, "step": 1139 }, { "epoch": 1.6801768607221814, "grad_norm": 1.721620139976316, "learning_rate": 4.145729850760408e-05, "loss": 0.3838, "step": 1140 }, { "epoch": 1.681650700073692, "grad_norm": 2.152304758040639, "learning_rate": 4.144257923119096e-05, "loss": 0.4629, "step": 1141 }, { "epoch": 1.6831245394252026, "grad_norm": 1.889261116333337, "learning_rate": 4.142784990283982e-05, "loss": 0.406, "step": 1142 }, { "epoch": 1.6845983787767134, "grad_norm": 2.8367328631891247, "learning_rate": 4.141311053155524e-05, "loss": 0.4573, "step": 1143 }, { "epoch": 1.6860722181282242, "grad_norm": 2.274730720932191, "learning_rate": 4.139836112634792e-05, "loss": 0.5352, "step": 1144 }, { "epoch": 1.6875460574797347, "grad_norm": 3.2339419752304948, "learning_rate": 4.138360169623471e-05, "loss": 0.4347, "step": 1145 }, { "epoch": 1.6890198968312453, "grad_norm": 2.4874725225263266, "learning_rate": 4.136883225023857e-05, "loss": 0.5202, "step": 1146 }, { "epoch": 1.6904937361827561, "grad_norm": 2.182231116232495, "learning_rate": 4.1354052797388576e-05, "loss": 0.5071, "step": 1147 }, { "epoch": 1.691967575534267, "grad_norm": 2.6051420495957176, "learning_rate": 4.133926334671996e-05, "loss": 0.4433, "step": 1148 }, { "epoch": 1.6934414148857775, "grad_norm": 2.3685537493491484, "learning_rate": 4.132446390727404e-05, "loss": 0.4713, "step": 1149 }, { "epoch": 1.694915254237288, "grad_norm": 2.159589641408989, "learning_rate": 4.130965448809824e-05, "loss": 0.5203, "step": 1150 }, { "epoch": 1.6963890935887989, "grad_norm": 2.6088938012402694, "learning_rate": 4.129483509824608e-05, "loss": 0.5408, "step": 1151 }, { "epoch": 1.6978629329403097, "grad_norm": 2.0823911316476535, "learning_rate": 4.12800057467772e-05, "loss": 0.3524, "step": 1152 }, { "epoch": 1.6993367722918202, "grad_norm": 5.913102630163268, "learning_rate": 4.126516644275731e-05, "loss": 0.5483, "step": 1153 }, { "epoch": 1.7008106116433308, "grad_norm": 2.9753659063401474, "learning_rate": 4.12503171952582e-05, "loss": 0.4683, "step": 1154 }, { "epoch": 1.7022844509948416, "grad_norm": 2.429304871681695, "learning_rate": 4.123545801335775e-05, "loss": 0.4425, "step": 1155 }, { "epoch": 1.7037582903463524, "grad_norm": 2.5328001762151504, "learning_rate": 4.122058890613991e-05, "loss": 0.4164, "step": 1156 }, { "epoch": 1.705232129697863, "grad_norm": 2.158401521565415, "learning_rate": 4.120570988269472e-05, "loss": 0.4139, "step": 1157 }, { "epoch": 1.7067059690493736, "grad_norm": 2.7831265408871246, "learning_rate": 4.1190820952118226e-05, "loss": 0.4102, "step": 1158 }, { "epoch": 1.7081798084008843, "grad_norm": 2.0147455943686974, "learning_rate": 4.1175922123512576e-05, "loss": 0.4029, "step": 1159 }, { "epoch": 1.7096536477523951, "grad_norm": 1.9376552888720049, "learning_rate": 4.116101340598597e-05, "loss": 0.4442, "step": 1160 }, { "epoch": 1.7111274871039057, "grad_norm": 1.9669066988484984, "learning_rate": 4.114609480865264e-05, "loss": 0.3699, "step": 1161 }, { "epoch": 1.7126013264554163, "grad_norm": 2.0770171231118213, "learning_rate": 4.113116634063284e-05, "loss": 0.4175, "step": 1162 }, { "epoch": 1.714075165806927, "grad_norm": 2.4245806931252227, "learning_rate": 4.11162280110529e-05, "loss": 0.452, "step": 1163 }, { "epoch": 1.715549005158438, "grad_norm": 2.5767291365038187, "learning_rate": 4.1101279829045134e-05, "loss": 0.4579, "step": 1164 }, { "epoch": 1.7170228445099485, "grad_norm": 2.74442784445509, "learning_rate": 4.1086321803747935e-05, "loss": 0.4319, "step": 1165 }, { "epoch": 1.718496683861459, "grad_norm": 2.9641422854208965, "learning_rate": 4.107135394430565e-05, "loss": 0.3739, "step": 1166 }, { "epoch": 1.7199705232129698, "grad_norm": 3.6010405520142337, "learning_rate": 4.105637625986867e-05, "loss": 0.4693, "step": 1167 }, { "epoch": 1.7214443625644806, "grad_norm": 2.204142450537338, "learning_rate": 4.10413887595934e-05, "loss": 0.4766, "step": 1168 }, { "epoch": 1.7229182019159912, "grad_norm": 2.2395442042518052, "learning_rate": 4.102639145264223e-05, "loss": 0.4157, "step": 1169 }, { "epoch": 1.7243920412675018, "grad_norm": 1.9778623867629617, "learning_rate": 4.101138434818357e-05, "loss": 0.3997, "step": 1170 }, { "epoch": 1.7258658806190126, "grad_norm": 1.9849763094355524, "learning_rate": 4.0996367455391776e-05, "loss": 0.4651, "step": 1171 }, { "epoch": 1.7273397199705232, "grad_norm": 2.3113593303926403, "learning_rate": 4.098134078344722e-05, "loss": 0.4478, "step": 1172 }, { "epoch": 1.7288135593220337, "grad_norm": 3.5846879897284802, "learning_rate": 4.0966304341536246e-05, "loss": 0.4713, "step": 1173 }, { "epoch": 1.7302873986735445, "grad_norm": 2.376296843779897, "learning_rate": 4.0951258138851184e-05, "loss": 0.3622, "step": 1174 }, { "epoch": 1.7317612380250553, "grad_norm": 2.189355771489146, "learning_rate": 4.093620218459029e-05, "loss": 0.4542, "step": 1175 }, { "epoch": 1.733235077376566, "grad_norm": 2.3455435438926275, "learning_rate": 4.0921136487957834e-05, "loss": 0.421, "step": 1176 }, { "epoch": 1.7347089167280765, "grad_norm": 1.95447164269128, "learning_rate": 4.0906061058163995e-05, "loss": 0.3731, "step": 1177 }, { "epoch": 1.7361827560795873, "grad_norm": 2.617985117060568, "learning_rate": 4.089097590442494e-05, "loss": 0.4649, "step": 1178 }, { "epoch": 1.737656595431098, "grad_norm": 1.9262577728570145, "learning_rate": 4.0875881035962756e-05, "loss": 0.3656, "step": 1179 }, { "epoch": 1.7391304347826086, "grad_norm": 3.5551727969724634, "learning_rate": 4.0860776462005476e-05, "loss": 0.4846, "step": 1180 }, { "epoch": 1.7406042741341192, "grad_norm": 2.282631756091472, "learning_rate": 4.084566219178708e-05, "loss": 0.3965, "step": 1181 }, { "epoch": 1.74207811348563, "grad_norm": 2.08738389748794, "learning_rate": 4.0830538234547454e-05, "loss": 0.4572, "step": 1182 }, { "epoch": 1.7435519528371408, "grad_norm": 2.209707612248376, "learning_rate": 4.08154045995324e-05, "loss": 0.4122, "step": 1183 }, { "epoch": 1.7450257921886514, "grad_norm": 2.231063202376949, "learning_rate": 4.080026129599368e-05, "loss": 0.4806, "step": 1184 }, { "epoch": 1.746499631540162, "grad_norm": 3.199130661418906, "learning_rate": 4.078510833318891e-05, "loss": 0.4107, "step": 1185 }, { "epoch": 1.7479734708916728, "grad_norm": 2.4128027533275165, "learning_rate": 4.0769945720381674e-05, "loss": 0.4256, "step": 1186 }, { "epoch": 1.7494473102431836, "grad_norm": 3.7552070070953074, "learning_rate": 4.0754773466841387e-05, "loss": 0.486, "step": 1187 }, { "epoch": 1.7509211495946941, "grad_norm": 2.578846223693647, "learning_rate": 4.0739591581843405e-05, "loss": 0.5296, "step": 1188 }, { "epoch": 1.7523949889462047, "grad_norm": 2.963136042952704, "learning_rate": 4.0724400074668955e-05, "loss": 0.468, "step": 1189 }, { "epoch": 1.7538688282977155, "grad_norm": 2.9652790860707485, "learning_rate": 4.0709198954605164e-05, "loss": 0.4699, "step": 1190 }, { "epoch": 1.7553426676492263, "grad_norm": 2.3974716776745173, "learning_rate": 4.0693988230945004e-05, "loss": 0.4432, "step": 1191 }, { "epoch": 1.7568165070007369, "grad_norm": 2.840847672232035, "learning_rate": 4.067876791298734e-05, "loss": 0.5794, "step": 1192 }, { "epoch": 1.7582903463522475, "grad_norm": 2.290709544204997, "learning_rate": 4.0663538010036905e-05, "loss": 0.4598, "step": 1193 }, { "epoch": 1.7597641857037583, "grad_norm": 2.2666159731675135, "learning_rate": 4.0648298531404276e-05, "loss": 0.4966, "step": 1194 }, { "epoch": 1.761238025055269, "grad_norm": 1.7700801444363081, "learning_rate": 4.06330494864059e-05, "loss": 0.3534, "step": 1195 }, { "epoch": 1.7627118644067796, "grad_norm": 2.216330807799971, "learning_rate": 4.061779088436406e-05, "loss": 0.4017, "step": 1196 }, { "epoch": 1.7641857037582902, "grad_norm": 2.5617447647304803, "learning_rate": 4.060252273460688e-05, "loss": 0.4121, "step": 1197 }, { "epoch": 1.765659543109801, "grad_norm": 2.4634021829766235, "learning_rate": 4.058724504646834e-05, "loss": 0.4189, "step": 1198 }, { "epoch": 1.7671333824613118, "grad_norm": 7.47010490864696, "learning_rate": 4.057195782928823e-05, "loss": 0.502, "step": 1199 }, { "epoch": 1.7686072218128224, "grad_norm": 2.010614836681649, "learning_rate": 4.055666109241218e-05, "loss": 0.4518, "step": 1200 }, { "epoch": 1.770081061164333, "grad_norm": 1.9034609167737542, "learning_rate": 4.0541354845191625e-05, "loss": 0.4573, "step": 1201 }, { "epoch": 1.7715549005158437, "grad_norm": 2.5635219490029764, "learning_rate": 4.0526039096983834e-05, "loss": 0.4671, "step": 1202 }, { "epoch": 1.7730287398673545, "grad_norm": 2.3978486472082037, "learning_rate": 4.051071385715186e-05, "loss": 0.3446, "step": 1203 }, { "epoch": 1.7745025792188651, "grad_norm": 2.164066466179804, "learning_rate": 4.049537913506458e-05, "loss": 0.3672, "step": 1204 }, { "epoch": 1.7759764185703757, "grad_norm": 2.3121510835273376, "learning_rate": 4.048003494009666e-05, "loss": 0.4339, "step": 1205 }, { "epoch": 1.7774502579218865, "grad_norm": 2.521464896625482, "learning_rate": 4.046468128162855e-05, "loss": 0.4889, "step": 1206 }, { "epoch": 1.7789240972733973, "grad_norm": 2.7924328696737764, "learning_rate": 4.0449318169046494e-05, "loss": 0.3893, "step": 1207 }, { "epoch": 1.7803979366249079, "grad_norm": 2.0162105449072683, "learning_rate": 4.043394561174251e-05, "loss": 0.4848, "step": 1208 }, { "epoch": 1.7818717759764184, "grad_norm": 2.336568791747184, "learning_rate": 4.0418563619114404e-05, "loss": 0.5346, "step": 1209 }, { "epoch": 1.7833456153279292, "grad_norm": 2.5606574901021437, "learning_rate": 4.040317220056573e-05, "loss": 0.4502, "step": 1210 }, { "epoch": 1.78481945467944, "grad_norm": 2.5596243377072163, "learning_rate": 4.0387771365505824e-05, "loss": 0.516, "step": 1211 }, { "epoch": 1.7862932940309506, "grad_norm": 2.302795668183414, "learning_rate": 4.0372361123349756e-05, "loss": 0.4614, "step": 1212 }, { "epoch": 1.7877671333824612, "grad_norm": 1.8159353650811991, "learning_rate": 4.035694148351836e-05, "loss": 0.389, "step": 1213 }, { "epoch": 1.789240972733972, "grad_norm": 2.2126803049876136, "learning_rate": 4.0341512455438224e-05, "loss": 0.4098, "step": 1214 }, { "epoch": 1.7907148120854828, "grad_norm": 2.217042185112324, "learning_rate": 4.0326074048541665e-05, "loss": 0.4352, "step": 1215 }, { "epoch": 1.7921886514369934, "grad_norm": 1.845797226540477, "learning_rate": 4.031062627226672e-05, "loss": 0.4011, "step": 1216 }, { "epoch": 1.793662490788504, "grad_norm": 1.796589837044622, "learning_rate": 4.029516913605719e-05, "loss": 0.4384, "step": 1217 }, { "epoch": 1.7951363301400147, "grad_norm": 2.8796832874782674, "learning_rate": 4.0279702649362554e-05, "loss": 0.443, "step": 1218 }, { "epoch": 1.7966101694915255, "grad_norm": 2.3084784929192015, "learning_rate": 4.026422682163804e-05, "loss": 0.5614, "step": 1219 }, { "epoch": 1.798084008843036, "grad_norm": 1.9259808110026917, "learning_rate": 4.024874166234459e-05, "loss": 0.4263, "step": 1220 }, { "epoch": 1.7995578481945467, "grad_norm": 2.0836703091527875, "learning_rate": 4.023324718094881e-05, "loss": 0.3885, "step": 1221 }, { "epoch": 1.8010316875460575, "grad_norm": 2.3215764260628555, "learning_rate": 4.0217743386923055e-05, "loss": 0.441, "step": 1222 }, { "epoch": 1.8025055268975683, "grad_norm": 2.0309325923880928, "learning_rate": 4.0202230289745334e-05, "loss": 0.4849, "step": 1223 }, { "epoch": 1.8039793662490788, "grad_norm": 7.115288524018495, "learning_rate": 4.0186707898899375e-05, "loss": 0.4162, "step": 1224 }, { "epoch": 1.8054532056005894, "grad_norm": 2.421963499359605, "learning_rate": 4.017117622387455e-05, "loss": 0.4893, "step": 1225 }, { "epoch": 1.8069270449521002, "grad_norm": 2.2902937041927274, "learning_rate": 4.015563527416595e-05, "loss": 0.4051, "step": 1226 }, { "epoch": 1.808400884303611, "grad_norm": 1.9032868665689513, "learning_rate": 4.0140085059274306e-05, "loss": 0.4307, "step": 1227 }, { "epoch": 1.8098747236551216, "grad_norm": 1.9074553759193575, "learning_rate": 4.012452558870602e-05, "loss": 0.4268, "step": 1228 }, { "epoch": 1.8113485630066322, "grad_norm": 1.9681920668803483, "learning_rate": 4.010895687197316e-05, "loss": 0.4725, "step": 1229 }, { "epoch": 1.812822402358143, "grad_norm": 2.662512901883811, "learning_rate": 4.0093378918593426e-05, "loss": 0.3916, "step": 1230 }, { "epoch": 1.8142962417096538, "grad_norm": 2.060342411545644, "learning_rate": 4.00777917380902e-05, "loss": 0.4905, "step": 1231 }, { "epoch": 1.8157700810611643, "grad_norm": 3.088001034504218, "learning_rate": 4.006219533999246e-05, "loss": 0.4745, "step": 1232 }, { "epoch": 1.817243920412675, "grad_norm": 2.5176453622106587, "learning_rate": 4.0046589733834875e-05, "loss": 0.4396, "step": 1233 }, { "epoch": 1.8187177597641857, "grad_norm": 2.5053233690610144, "learning_rate": 4.003097492915768e-05, "loss": 0.4287, "step": 1234 }, { "epoch": 1.8201915991156965, "grad_norm": 2.418516525316199, "learning_rate": 4.001535093550678e-05, "loss": 0.5091, "step": 1235 }, { "epoch": 1.821665438467207, "grad_norm": 2.6996297123214292, "learning_rate": 3.9999717762433684e-05, "loss": 0.4058, "step": 1236 }, { "epoch": 1.8231392778187177, "grad_norm": 2.8709580577522478, "learning_rate": 3.99840754194955e-05, "loss": 0.5521, "step": 1237 }, { "epoch": 1.8246131171702284, "grad_norm": 2.1657856715106076, "learning_rate": 3.996842391625497e-05, "loss": 0.4303, "step": 1238 }, { "epoch": 1.8260869565217392, "grad_norm": 2.068834806703517, "learning_rate": 3.9952763262280405e-05, "loss": 0.5054, "step": 1239 }, { "epoch": 1.8275607958732498, "grad_norm": 2.0894466985552698, "learning_rate": 3.9937093467145726e-05, "loss": 0.4932, "step": 1240 }, { "epoch": 1.8290346352247604, "grad_norm": 2.630074818058221, "learning_rate": 3.992141454043044e-05, "loss": 0.4804, "step": 1241 }, { "epoch": 1.8305084745762712, "grad_norm": 2.004205811475812, "learning_rate": 3.990572649171964e-05, "loss": 0.392, "step": 1242 }, { "epoch": 1.831982313927782, "grad_norm": 2.2970248841667877, "learning_rate": 3.9890029330604e-05, "loss": 0.534, "step": 1243 }, { "epoch": 1.8334561532792926, "grad_norm": 2.1391813881871173, "learning_rate": 3.987432306667974e-05, "loss": 0.4597, "step": 1244 }, { "epoch": 1.8349299926308031, "grad_norm": 1.9799823351756, "learning_rate": 3.9858607709548676e-05, "loss": 0.3804, "step": 1245 }, { "epoch": 1.836403831982314, "grad_norm": 2.2856263288536307, "learning_rate": 3.984288326881817e-05, "loss": 0.4417, "step": 1246 }, { "epoch": 1.8378776713338247, "grad_norm": 1.9459092783623544, "learning_rate": 3.982714975410111e-05, "loss": 0.4286, "step": 1247 }, { "epoch": 1.8393515106853353, "grad_norm": 2.1816135223808906, "learning_rate": 3.981140717501599e-05, "loss": 0.4744, "step": 1248 }, { "epoch": 1.8408253500368459, "grad_norm": 2.0593130747814476, "learning_rate": 3.9795655541186805e-05, "loss": 0.4143, "step": 1249 }, { "epoch": 1.8422991893883567, "grad_norm": 2.2135139254159335, "learning_rate": 3.977989486224308e-05, "loss": 0.4435, "step": 1250 }, { "epoch": 1.8422991893883567, "eval_bleu": 0.19266923993005022, "eval_bleu_1gram": 0.5090585156030639, "eval_bleu_2gram": 0.29714577554652544, "eval_bleu_3gram": 0.18304871106543422, "eval_bleu_4gram": 0.11801174212321147, "eval_rag_val_loss": 0.6100707903344144, "eval_rouge1": 0.5100594419487949, "eval_rouge2": 0.28809237484679107, "eval_rougeL": 0.5056494742670452, "step": 1250 }, { "epoch": 1.8437730287398675, "grad_norm": 2.370167081391812, "learning_rate": 3.9764125147819897e-05, "loss": 0.4643, "step": 1251 }, { "epoch": 1.845246868091378, "grad_norm": 1.9285762537033029, "learning_rate": 3.9748346407557844e-05, "loss": 0.3146, "step": 1252 }, { "epoch": 1.8467207074428886, "grad_norm": 1.830340811360833, "learning_rate": 3.9732558651103024e-05, "loss": 0.3441, "step": 1253 }, { "epoch": 1.8481945467943994, "grad_norm": 2.0779610475959185, "learning_rate": 3.971676188810707e-05, "loss": 0.4265, "step": 1254 }, { "epoch": 1.8496683861459102, "grad_norm": 2.352534501960866, "learning_rate": 3.97009561282271e-05, "loss": 0.4608, "step": 1255 }, { "epoch": 1.8511422254974208, "grad_norm": 1.7116258882433777, "learning_rate": 3.9685141381125744e-05, "loss": 0.3771, "step": 1256 }, { "epoch": 1.8526160648489314, "grad_norm": 5.91464105595604, "learning_rate": 3.9669317656471123e-05, "loss": 0.3639, "step": 1257 }, { "epoch": 1.8540899042004422, "grad_norm": 1.6847295271227742, "learning_rate": 3.965348496393685e-05, "loss": 0.3949, "step": 1258 }, { "epoch": 1.855563743551953, "grad_norm": 2.138126223557386, "learning_rate": 3.963764331320201e-05, "loss": 0.3914, "step": 1259 }, { "epoch": 1.8570375829034635, "grad_norm": 2.794502317445715, "learning_rate": 3.9621792713951175e-05, "loss": 0.5039, "step": 1260 }, { "epoch": 1.8585114222549741, "grad_norm": 1.8204848572170123, "learning_rate": 3.96059331758744e-05, "loss": 0.4327, "step": 1261 }, { "epoch": 1.859985261606485, "grad_norm": 1.859155850358337, "learning_rate": 3.959006470866717e-05, "loss": 0.3807, "step": 1262 }, { "epoch": 1.8614591009579957, "grad_norm": 3.409197450764737, "learning_rate": 3.957418732203045e-05, "loss": 0.5233, "step": 1263 }, { "epoch": 1.8629329403095063, "grad_norm": 2.370464411112942, "learning_rate": 3.955830102567066e-05, "loss": 0.4517, "step": 1264 }, { "epoch": 1.8644067796610169, "grad_norm": 2.5454010237912854, "learning_rate": 3.954240582929966e-05, "loss": 0.3987, "step": 1265 }, { "epoch": 1.8658806190125277, "grad_norm": 2.2373559447219318, "learning_rate": 3.952650174263476e-05, "loss": 0.4094, "step": 1266 }, { "epoch": 1.8673544583640385, "grad_norm": 2.000475946062013, "learning_rate": 3.951058877539869e-05, "loss": 0.394, "step": 1267 }, { "epoch": 1.868828297715549, "grad_norm": 4.398487151765157, "learning_rate": 3.949466693731962e-05, "loss": 0.4616, "step": 1268 }, { "epoch": 1.8703021370670596, "grad_norm": 2.3811647815424095, "learning_rate": 3.947873623813113e-05, "loss": 0.4417, "step": 1269 }, { "epoch": 1.8717759764185704, "grad_norm": 2.4583775360098996, "learning_rate": 3.946279668757226e-05, "loss": 0.4497, "step": 1270 }, { "epoch": 1.8732498157700812, "grad_norm": 1.9559273109347393, "learning_rate": 3.944684829538739e-05, "loss": 0.4069, "step": 1271 }, { "epoch": 1.8747236551215918, "grad_norm": 2.2599856995661836, "learning_rate": 3.9430891071326365e-05, "loss": 0.4529, "step": 1272 }, { "epoch": 1.8761974944731024, "grad_norm": 1.9416299303478841, "learning_rate": 3.94149250251444e-05, "loss": 0.4518, "step": 1273 }, { "epoch": 1.8776713338246132, "grad_norm": 2.198149778710722, "learning_rate": 3.939895016660212e-05, "loss": 0.4424, "step": 1274 }, { "epoch": 1.879145173176124, "grad_norm": 2.2602275880643994, "learning_rate": 3.938296650546552e-05, "loss": 0.4119, "step": 1275 }, { "epoch": 1.8806190125276345, "grad_norm": 2.3473363268001717, "learning_rate": 3.9366974051505986e-05, "loss": 0.4953, "step": 1276 }, { "epoch": 1.882092851879145, "grad_norm": 2.9547080988899728, "learning_rate": 3.9350972814500275e-05, "loss": 0.4489, "step": 1277 }, { "epoch": 1.883566691230656, "grad_norm": 2.6156146889031007, "learning_rate": 3.9334962804230534e-05, "loss": 0.3821, "step": 1278 }, { "epoch": 1.8850405305821667, "grad_norm": 2.120598329465734, "learning_rate": 3.931894403048424e-05, "loss": 0.3938, "step": 1279 }, { "epoch": 1.8865143699336773, "grad_norm": 1.9476462463783033, "learning_rate": 3.9302916503054246e-05, "loss": 0.3836, "step": 1280 }, { "epoch": 1.8879882092851878, "grad_norm": 2.2092501938247726, "learning_rate": 3.928688023173875e-05, "loss": 0.4635, "step": 1281 }, { "epoch": 1.8894620486366986, "grad_norm": 1.8962671251724441, "learning_rate": 3.927083522634132e-05, "loss": 0.3812, "step": 1282 }, { "epoch": 1.8909358879882094, "grad_norm": 2.0960753324526307, "learning_rate": 3.925478149667081e-05, "loss": 0.4124, "step": 1283 }, { "epoch": 1.89240972733972, "grad_norm": 1.7660692719409585, "learning_rate": 3.923871905254146e-05, "loss": 0.3796, "step": 1284 }, { "epoch": 1.8938835666912306, "grad_norm": 2.775553495177105, "learning_rate": 3.9222647903772826e-05, "loss": 0.5386, "step": 1285 }, { "epoch": 1.8953574060427414, "grad_norm": 2.7453277083764327, "learning_rate": 3.9206568060189766e-05, "loss": 0.4603, "step": 1286 }, { "epoch": 1.8968312453942522, "grad_norm": 2.8321662818023805, "learning_rate": 3.919047953162246e-05, "loss": 0.4378, "step": 1287 }, { "epoch": 1.8983050847457628, "grad_norm": 2.379847248048023, "learning_rate": 3.917438232790641e-05, "loss": 0.5131, "step": 1288 }, { "epoch": 1.8997789240972733, "grad_norm": 2.4841379496405263, "learning_rate": 3.915827645888241e-05, "loss": 0.4981, "step": 1289 }, { "epoch": 1.9012527634487841, "grad_norm": 2.0388144857474653, "learning_rate": 3.914216193439656e-05, "loss": 0.4473, "step": 1290 }, { "epoch": 1.902726602800295, "grad_norm": 2.284948408016015, "learning_rate": 3.9126038764300246e-05, "loss": 0.4459, "step": 1291 }, { "epoch": 1.9042004421518055, "grad_norm": 2.365739536914103, "learning_rate": 3.910990695845013e-05, "loss": 0.4882, "step": 1292 }, { "epoch": 1.905674281503316, "grad_norm": 2.2648136132963375, "learning_rate": 3.9093766526708175e-05, "loss": 0.4385, "step": 1293 }, { "epoch": 1.9071481208548269, "grad_norm": 2.0544789719739063, "learning_rate": 3.90776174789416e-05, "loss": 0.4285, "step": 1294 }, { "epoch": 1.9086219602063377, "grad_norm": 1.7745387485430029, "learning_rate": 3.90614598250229e-05, "loss": 0.414, "step": 1295 }, { "epoch": 1.910095799557848, "grad_norm": 2.785029639834571, "learning_rate": 3.9045293574829814e-05, "loss": 0.4753, "step": 1296 }, { "epoch": 1.9115696389093588, "grad_norm": 2.375728495450235, "learning_rate": 3.902911873824536e-05, "loss": 0.4073, "step": 1297 }, { "epoch": 1.9130434782608696, "grad_norm": 2.339064836214233, "learning_rate": 3.9012935325157805e-05, "loss": 0.4012, "step": 1298 }, { "epoch": 1.9145173176123802, "grad_norm": 2.0830840406674422, "learning_rate": 3.899674334546064e-05, "loss": 0.4842, "step": 1299 }, { "epoch": 1.9159911569638908, "grad_norm": 2.4392439643368418, "learning_rate": 3.89805428090526e-05, "loss": 0.4723, "step": 1300 }, { "epoch": 1.9174649963154016, "grad_norm": 2.190415755222076, "learning_rate": 3.8964333725837656e-05, "loss": 0.4458, "step": 1301 }, { "epoch": 1.9189388356669124, "grad_norm": 2.6086368087683334, "learning_rate": 3.894811610572501e-05, "loss": 0.5075, "step": 1302 }, { "epoch": 1.920412675018423, "grad_norm": 1.973034208744578, "learning_rate": 3.8931889958629066e-05, "loss": 0.4129, "step": 1303 }, { "epoch": 1.9218865143699335, "grad_norm": 2.919140683805449, "learning_rate": 3.8915655294469447e-05, "loss": 0.469, "step": 1304 }, { "epoch": 1.9233603537214443, "grad_norm": 1.9471106740200812, "learning_rate": 3.889941212317098e-05, "loss": 0.4327, "step": 1305 }, { "epoch": 1.9248341930729551, "grad_norm": 2.240452643539496, "learning_rate": 3.888316045466372e-05, "loss": 0.4788, "step": 1306 }, { "epoch": 1.9263080324244657, "grad_norm": 1.987646994763005, "learning_rate": 3.886690029888287e-05, "loss": 0.3862, "step": 1307 }, { "epoch": 1.9277818717759763, "grad_norm": 3.8337095048405643, "learning_rate": 3.885063166576886e-05, "loss": 0.4791, "step": 1308 }, { "epoch": 1.929255711127487, "grad_norm": 2.233652918519929, "learning_rate": 3.8834354565267284e-05, "loss": 0.4582, "step": 1309 }, { "epoch": 1.9307295504789979, "grad_norm": 2.1809631771178184, "learning_rate": 3.881806900732893e-05, "loss": 0.4797, "step": 1310 }, { "epoch": 1.9322033898305084, "grad_norm": 2.4096848383876313, "learning_rate": 3.880177500190971e-05, "loss": 0.4592, "step": 1311 }, { "epoch": 1.933677229182019, "grad_norm": 3.663261277170174, "learning_rate": 3.878547255897077e-05, "loss": 0.5289, "step": 1312 }, { "epoch": 1.9351510685335298, "grad_norm": 2.1141822572383133, "learning_rate": 3.876916168847836e-05, "loss": 0.409, "step": 1313 }, { "epoch": 1.9366249078850406, "grad_norm": 2.03876618903379, "learning_rate": 3.87528424004039e-05, "loss": 0.5089, "step": 1314 }, { "epoch": 1.9380987472365512, "grad_norm": 1.9165700874321483, "learning_rate": 3.873651470472396e-05, "loss": 0.3629, "step": 1315 }, { "epoch": 1.9395725865880618, "grad_norm": 1.8945643471255258, "learning_rate": 3.8720178611420246e-05, "loss": 0.3703, "step": 1316 }, { "epoch": 1.9410464259395726, "grad_norm": 2.0383672588620363, "learning_rate": 3.870383413047959e-05, "loss": 0.4503, "step": 1317 }, { "epoch": 1.9425202652910833, "grad_norm": 2.3158135258872052, "learning_rate": 3.8687481271893964e-05, "loss": 0.4512, "step": 1318 }, { "epoch": 1.943994104642594, "grad_norm": 1.9431855857240696, "learning_rate": 3.8671120045660454e-05, "loss": 0.4165, "step": 1319 }, { "epoch": 1.9454679439941045, "grad_norm": 2.228180307608729, "learning_rate": 3.8654750461781266e-05, "loss": 0.5329, "step": 1320 }, { "epoch": 1.9469417833456153, "grad_norm": 2.241307102375898, "learning_rate": 3.8638372530263715e-05, "loss": 0.4538, "step": 1321 }, { "epoch": 1.948415622697126, "grad_norm": 2.567038633798118, "learning_rate": 3.8621986261120226e-05, "loss": 0.486, "step": 1322 }, { "epoch": 1.9498894620486367, "grad_norm": 2.168914093933366, "learning_rate": 3.860559166436829e-05, "loss": 0.4988, "step": 1323 }, { "epoch": 1.9513633014001472, "grad_norm": 1.8513540158616664, "learning_rate": 3.858918875003053e-05, "loss": 0.4521, "step": 1324 }, { "epoch": 1.952837140751658, "grad_norm": 4.6159027945797115, "learning_rate": 3.857277752813463e-05, "loss": 0.3806, "step": 1325 }, { "epoch": 1.9543109801031688, "grad_norm": 1.7974374968759779, "learning_rate": 3.8556358008713354e-05, "loss": 0.367, "step": 1326 }, { "epoch": 1.9557848194546794, "grad_norm": 1.7942442502145857, "learning_rate": 3.853993020180455e-05, "loss": 0.4667, "step": 1327 }, { "epoch": 1.95725865880619, "grad_norm": 2.3856313572739687, "learning_rate": 3.852349411745113e-05, "loss": 0.4179, "step": 1328 }, { "epoch": 1.9587324981577008, "grad_norm": 2.2845524960299555, "learning_rate": 3.850704976570104e-05, "loss": 0.4665, "step": 1329 }, { "epoch": 1.9602063375092116, "grad_norm": 3.2425836895544653, "learning_rate": 3.8490597156607324e-05, "loss": 0.564, "step": 1330 }, { "epoch": 1.9616801768607222, "grad_norm": 2.584772590949507, "learning_rate": 3.847413630022804e-05, "loss": 0.4919, "step": 1331 }, { "epoch": 1.9631540162122327, "grad_norm": 1.8856734703340878, "learning_rate": 3.84576672066263e-05, "loss": 0.3826, "step": 1332 }, { "epoch": 1.9646278555637435, "grad_norm": 1.9955302000960145, "learning_rate": 3.844118988587025e-05, "loss": 0.3936, "step": 1333 }, { "epoch": 1.9661016949152543, "grad_norm": 2.3240801601603223, "learning_rate": 3.842470434803309e-05, "loss": 0.4381, "step": 1334 }, { "epoch": 1.967575534266765, "grad_norm": 2.2772838656631214, "learning_rate": 3.840821060319298e-05, "loss": 0.3766, "step": 1335 }, { "epoch": 1.9690493736182755, "grad_norm": 2.2106874142529462, "learning_rate": 3.839170866143317e-05, "loss": 0.3924, "step": 1336 }, { "epoch": 1.9705232129697863, "grad_norm": 2.1875032697380696, "learning_rate": 3.8375198532841863e-05, "loss": 0.5253, "step": 1337 }, { "epoch": 1.971997052321297, "grad_norm": 2.2825197840289673, "learning_rate": 3.835868022751231e-05, "loss": 0.4148, "step": 1338 }, { "epoch": 1.9734708916728076, "grad_norm": 3.748952846553116, "learning_rate": 3.834215375554274e-05, "loss": 0.5981, "step": 1339 }, { "epoch": 1.9749447310243182, "grad_norm": 2.0995160317187023, "learning_rate": 3.832561912703638e-05, "loss": 0.4476, "step": 1340 }, { "epoch": 1.976418570375829, "grad_norm": 2.4979266151906723, "learning_rate": 3.830907635210143e-05, "loss": 0.3983, "step": 1341 }, { "epoch": 1.9778924097273398, "grad_norm": 2.1852890830774383, "learning_rate": 3.829252544085109e-05, "loss": 0.4729, "step": 1342 }, { "epoch": 1.9793662490788504, "grad_norm": 2.1706526355867912, "learning_rate": 3.827596640340353e-05, "loss": 0.4103, "step": 1343 }, { "epoch": 1.980840088430361, "grad_norm": 1.9729313724645143, "learning_rate": 3.8259399249881874e-05, "loss": 0.4287, "step": 1344 }, { "epoch": 1.9823139277818718, "grad_norm": 2.2711474233504325, "learning_rate": 3.8242823990414214e-05, "loss": 0.451, "step": 1345 }, { "epoch": 1.9837877671333826, "grad_norm": 2.2589980448072264, "learning_rate": 3.8226240635133615e-05, "loss": 0.4083, "step": 1346 }, { "epoch": 1.9852616064848931, "grad_norm": 1.927596654484797, "learning_rate": 3.820964919417806e-05, "loss": 0.3954, "step": 1347 }, { "epoch": 1.9867354458364037, "grad_norm": 2.1138863252592754, "learning_rate": 3.8193049677690494e-05, "loss": 0.4478, "step": 1348 }, { "epoch": 1.9882092851879145, "grad_norm": 1.7124141782988542, "learning_rate": 3.817644209581881e-05, "loss": 0.4196, "step": 1349 }, { "epoch": 1.9896831245394253, "grad_norm": 2.406765176688963, "learning_rate": 3.815982645871581e-05, "loss": 0.4128, "step": 1350 }, { "epoch": 1.9911569638909359, "grad_norm": 2.0163847208628853, "learning_rate": 3.814320277653922e-05, "loss": 0.4819, "step": 1351 }, { "epoch": 1.9926308032424465, "grad_norm": 2.3827557666465835, "learning_rate": 3.812657105945171e-05, "loss": 0.4087, "step": 1352 }, { "epoch": 1.9941046425939573, "grad_norm": 2.4252337392260506, "learning_rate": 3.8109931317620825e-05, "loss": 0.523, "step": 1353 }, { "epoch": 1.995578481945468, "grad_norm": 1.9165888093255639, "learning_rate": 3.8093283561219064e-05, "loss": 0.3861, "step": 1354 }, { "epoch": 1.9970523212969786, "grad_norm": 1.78222589362145, "learning_rate": 3.807662780042376e-05, "loss": 0.4177, "step": 1355 }, { "epoch": 1.9985261606484892, "grad_norm": 2.46928206878876, "learning_rate": 3.8059964045417195e-05, "loss": 0.4606, "step": 1356 }, { "epoch": 2.0, "grad_norm": 2.4278406317882184, "learning_rate": 3.804329230638652e-05, "loss": 0.4022, "step": 1357 }, { "epoch": 2.001473839351511, "grad_norm": 1.5835152906300525, "learning_rate": 3.802661259352379e-05, "loss": 0.2922, "step": 1358 }, { "epoch": 2.002947678703021, "grad_norm": 3.8415359695500286, "learning_rate": 3.8009924917025864e-05, "loss": 0.2808, "step": 1359 }, { "epoch": 2.004421518054532, "grad_norm": 3.8025721126944076, "learning_rate": 3.7993229287094547e-05, "loss": 0.3463, "step": 1360 }, { "epoch": 2.0058953574060427, "grad_norm": 1.7349541874094738, "learning_rate": 3.797652571393647e-05, "loss": 0.2678, "step": 1361 }, { "epoch": 2.0073691967575535, "grad_norm": 1.6853296663756456, "learning_rate": 3.7959814207763135e-05, "loss": 0.3619, "step": 1362 }, { "epoch": 2.008843036109064, "grad_norm": 1.3522750651934574, "learning_rate": 3.794309477879087e-05, "loss": 0.2766, "step": 1363 }, { "epoch": 2.0103168754605747, "grad_norm": 1.793272769725452, "learning_rate": 3.792636743724085e-05, "loss": 0.3328, "step": 1364 }, { "epoch": 2.0117907148120855, "grad_norm": 1.6179115038460365, "learning_rate": 3.790963219333913e-05, "loss": 0.324, "step": 1365 }, { "epoch": 2.0132645541635963, "grad_norm": 2.751336379889812, "learning_rate": 3.789288905731655e-05, "loss": 0.284, "step": 1366 }, { "epoch": 2.0147383935151066, "grad_norm": 1.6779865257486044, "learning_rate": 3.787613803940878e-05, "loss": 0.2329, "step": 1367 }, { "epoch": 2.0162122328666174, "grad_norm": 2.7063122960204185, "learning_rate": 3.785937914985633e-05, "loss": 0.3249, "step": 1368 }, { "epoch": 2.0176860722181282, "grad_norm": 2.0134139834707243, "learning_rate": 3.784261239890452e-05, "loss": 0.3722, "step": 1369 }, { "epoch": 2.019159911569639, "grad_norm": 2.493263036464513, "learning_rate": 3.782583779680344e-05, "loss": 0.3155, "step": 1370 }, { "epoch": 2.0206337509211494, "grad_norm": 2.425900761951308, "learning_rate": 3.780905535380801e-05, "loss": 0.2824, "step": 1371 }, { "epoch": 2.02210759027266, "grad_norm": 2.423732906318655, "learning_rate": 3.7792265080177955e-05, "loss": 0.3126, "step": 1372 }, { "epoch": 2.023581429624171, "grad_norm": 1.73998884701717, "learning_rate": 3.777546698617776e-05, "loss": 0.2402, "step": 1373 }, { "epoch": 2.0250552689756818, "grad_norm": 1.5767533790717896, "learning_rate": 3.775866108207671e-05, "loss": 0.3149, "step": 1374 }, { "epoch": 2.026529108327192, "grad_norm": 2.5031404797174193, "learning_rate": 3.774184737814884e-05, "loss": 0.4101, "step": 1375 }, { "epoch": 2.028002947678703, "grad_norm": 2.2620561575356546, "learning_rate": 3.772502588467299e-05, "loss": 0.2697, "step": 1376 }, { "epoch": 2.0294767870302137, "grad_norm": 2.307783110372698, "learning_rate": 3.770819661193273e-05, "loss": 0.3259, "step": 1377 }, { "epoch": 2.0309506263817245, "grad_norm": 3.0320480711857862, "learning_rate": 3.76913595702164e-05, "loss": 0.3369, "step": 1378 }, { "epoch": 2.032424465733235, "grad_norm": 3.080979006845876, "learning_rate": 3.767451476981708e-05, "loss": 0.3483, "step": 1379 }, { "epoch": 2.0338983050847457, "grad_norm": 3.951043708144342, "learning_rate": 3.765766222103262e-05, "loss": 0.3068, "step": 1380 }, { "epoch": 2.0353721444362565, "grad_norm": 2.2202333676480106, "learning_rate": 3.7640801934165556e-05, "loss": 0.2241, "step": 1381 }, { "epoch": 2.0368459837877673, "grad_norm": 1.9470634699871618, "learning_rate": 3.762393391952323e-05, "loss": 0.2822, "step": 1382 }, { "epoch": 2.0383198231392776, "grad_norm": 2.0094202632759806, "learning_rate": 3.760705818741762e-05, "loss": 0.3082, "step": 1383 }, { "epoch": 2.0397936624907884, "grad_norm": 1.7966999134509778, "learning_rate": 3.7590174748165487e-05, "loss": 0.3381, "step": 1384 }, { "epoch": 2.041267501842299, "grad_norm": 1.9439875368652826, "learning_rate": 3.7573283612088276e-05, "loss": 0.3295, "step": 1385 }, { "epoch": 2.04274134119381, "grad_norm": 1.8268385705438064, "learning_rate": 3.7556384789512154e-05, "loss": 0.3064, "step": 1386 }, { "epoch": 2.0442151805453204, "grad_norm": 1.9940676923336595, "learning_rate": 3.753947829076797e-05, "loss": 0.3382, "step": 1387 }, { "epoch": 2.045689019896831, "grad_norm": 2.660366324533689, "learning_rate": 3.7522564126191274e-05, "loss": 0.2751, "step": 1388 }, { "epoch": 2.047162859248342, "grad_norm": 2.1343514615683667, "learning_rate": 3.750564230612229e-05, "loss": 0.2643, "step": 1389 }, { "epoch": 2.0486366985998528, "grad_norm": 2.76428069293417, "learning_rate": 3.748871284090596e-05, "loss": 0.3195, "step": 1390 }, { "epoch": 2.050110537951363, "grad_norm": 2.0663455600876266, "learning_rate": 3.747177574089184e-05, "loss": 0.2469, "step": 1391 }, { "epoch": 2.051584377302874, "grad_norm": 1.3182268542336395, "learning_rate": 3.7454831016434205e-05, "loss": 0.2496, "step": 1392 }, { "epoch": 2.0530582166543847, "grad_norm": 2.642003619327997, "learning_rate": 3.7437878677891976e-05, "loss": 0.2827, "step": 1393 }, { "epoch": 2.0545320560058955, "grad_norm": 1.7056060358309273, "learning_rate": 3.742091873562871e-05, "loss": 0.2654, "step": 1394 }, { "epoch": 2.056005895357406, "grad_norm": 1.6226399229400967, "learning_rate": 3.740395120001264e-05, "loss": 0.2802, "step": 1395 }, { "epoch": 2.0574797347089167, "grad_norm": 1.7980058511632437, "learning_rate": 3.738697608141664e-05, "loss": 0.2966, "step": 1396 }, { "epoch": 2.0589535740604274, "grad_norm": 1.8369375548820075, "learning_rate": 3.736999339021817e-05, "loss": 0.3374, "step": 1397 }, { "epoch": 2.0604274134119382, "grad_norm": 1.8802857598788276, "learning_rate": 3.735300313679939e-05, "loss": 0.307, "step": 1398 }, { "epoch": 2.0619012527634486, "grad_norm": 1.617135825690687, "learning_rate": 3.733600533154705e-05, "loss": 0.3097, "step": 1399 }, { "epoch": 2.0633750921149594, "grad_norm": 2.4611291235538975, "learning_rate": 3.7318999984852496e-05, "loss": 0.2913, "step": 1400 }, { "epoch": 2.06484893146647, "grad_norm": 1.7268399667240908, "learning_rate": 3.730198710711173e-05, "loss": 0.2886, "step": 1401 }, { "epoch": 2.066322770817981, "grad_norm": 2.0522432474737875, "learning_rate": 3.7284966708725315e-05, "loss": 0.276, "step": 1402 }, { "epoch": 2.0677966101694913, "grad_norm": 1.9395602562580105, "learning_rate": 3.726793880009845e-05, "loss": 0.378, "step": 1403 }, { "epoch": 2.069270449521002, "grad_norm": 1.684801911729016, "learning_rate": 3.725090339164089e-05, "loss": 0.2862, "step": 1404 }, { "epoch": 2.070744288872513, "grad_norm": 2.288538433403147, "learning_rate": 3.7233860493766994e-05, "loss": 0.3613, "step": 1405 }, { "epoch": 2.0722181282240237, "grad_norm": 3.2074163208034054, "learning_rate": 3.72168101168957e-05, "loss": 0.3098, "step": 1406 }, { "epoch": 2.073691967575534, "grad_norm": 3.289111211782989, "learning_rate": 3.719975227145051e-05, "loss": 0.3658, "step": 1407 }, { "epoch": 2.075165806927045, "grad_norm": 1.85455286811598, "learning_rate": 3.71826869678595e-05, "loss": 0.2726, "step": 1408 }, { "epoch": 2.0766396462785557, "grad_norm": 1.7094743298781439, "learning_rate": 3.71656142165553e-05, "loss": 0.2938, "step": 1409 }, { "epoch": 2.0781134856300665, "grad_norm": 1.8775741073875885, "learning_rate": 3.71485340279751e-05, "loss": 0.3124, "step": 1410 }, { "epoch": 2.079587324981577, "grad_norm": 1.6622523101776818, "learning_rate": 3.7131446412560625e-05, "loss": 0.281, "step": 1411 }, { "epoch": 2.0810611643330876, "grad_norm": 2.7036197628517438, "learning_rate": 3.7114351380758146e-05, "loss": 0.3638, "step": 1412 }, { "epoch": 2.0825350036845984, "grad_norm": 1.9061644488038771, "learning_rate": 3.709724894301846e-05, "loss": 0.2918, "step": 1413 }, { "epoch": 2.0840088430361092, "grad_norm": 15.016357149976956, "learning_rate": 3.708013910979693e-05, "loss": 0.2956, "step": 1414 }, { "epoch": 2.0854826823876196, "grad_norm": 1.91897413702906, "learning_rate": 3.706302189155338e-05, "loss": 0.3074, "step": 1415 }, { "epoch": 2.0869565217391304, "grad_norm": 3.4507996337345666, "learning_rate": 3.7045897298752196e-05, "loss": 0.2781, "step": 1416 }, { "epoch": 2.088430361090641, "grad_norm": 1.682566034798129, "learning_rate": 3.702876534186225e-05, "loss": 0.2638, "step": 1417 }, { "epoch": 2.089904200442152, "grad_norm": 2.0357393392297545, "learning_rate": 3.7011626031356924e-05, "loss": 0.2335, "step": 1418 }, { "epoch": 2.0913780397936623, "grad_norm": 2.098289692460001, "learning_rate": 3.6994479377714084e-05, "loss": 0.3659, "step": 1419 }, { "epoch": 2.092851879145173, "grad_norm": 1.9086137718246663, "learning_rate": 3.6977325391416104e-05, "loss": 0.307, "step": 1420 }, { "epoch": 2.094325718496684, "grad_norm": 2.7929267506676085, "learning_rate": 3.696016408294983e-05, "loss": 0.3899, "step": 1421 }, { "epoch": 2.0957995578481947, "grad_norm": 2.6586408738167244, "learning_rate": 3.694299546280657e-05, "loss": 0.3752, "step": 1422 }, { "epoch": 2.097273397199705, "grad_norm": 2.0437463042899497, "learning_rate": 3.6925819541482146e-05, "loss": 0.3085, "step": 1423 }, { "epoch": 2.098747236551216, "grad_norm": 2.5923983257665584, "learning_rate": 3.690863632947678e-05, "loss": 0.3156, "step": 1424 }, { "epoch": 2.1002210759027267, "grad_norm": 2.2789642169682436, "learning_rate": 3.689144583729521e-05, "loss": 0.3143, "step": 1425 }, { "epoch": 2.1016949152542375, "grad_norm": 1.7360450333630115, "learning_rate": 3.6874248075446585e-05, "loss": 0.2776, "step": 1426 }, { "epoch": 2.103168754605748, "grad_norm": 3.3580718595757757, "learning_rate": 3.6857043054444534e-05, "loss": 0.3296, "step": 1427 }, { "epoch": 2.1046425939572586, "grad_norm": 1.7081157111520069, "learning_rate": 3.683983078480708e-05, "loss": 0.2962, "step": 1428 }, { "epoch": 2.1061164333087694, "grad_norm": 2.061936850682482, "learning_rate": 3.682261127705671e-05, "loss": 0.2757, "step": 1429 }, { "epoch": 2.10759027266028, "grad_norm": 1.3468768533574427, "learning_rate": 3.680538454172033e-05, "loss": 0.2109, "step": 1430 }, { "epoch": 2.1090641120117906, "grad_norm": 1.7213291583839174, "learning_rate": 3.6788150589329256e-05, "loss": 0.3229, "step": 1431 }, { "epoch": 2.1105379513633014, "grad_norm": 1.8461338731406705, "learning_rate": 3.677090943041922e-05, "loss": 0.3294, "step": 1432 }, { "epoch": 2.112011790714812, "grad_norm": 2.0177580909193398, "learning_rate": 3.675366107553036e-05, "loss": 0.3241, "step": 1433 }, { "epoch": 2.113485630066323, "grad_norm": 2.5285307795510827, "learning_rate": 3.673640553520721e-05, "loss": 0.2503, "step": 1434 }, { "epoch": 2.1149594694178333, "grad_norm": 2.2250336333743848, "learning_rate": 3.671914281999872e-05, "loss": 0.3387, "step": 1435 }, { "epoch": 2.116433308769344, "grad_norm": 1.9667574169212558, "learning_rate": 3.6701872940458186e-05, "loss": 0.2602, "step": 1436 }, { "epoch": 2.117907148120855, "grad_norm": 1.6891776328851424, "learning_rate": 3.66845959071433e-05, "loss": 0.2439, "step": 1437 }, { "epoch": 2.1193809874723657, "grad_norm": 2.4981621662703115, "learning_rate": 3.666731173061616e-05, "loss": 0.2969, "step": 1438 }, { "epoch": 2.120854826823876, "grad_norm": 1.7521860909766718, "learning_rate": 3.665002042144318e-05, "loss": 0.2506, "step": 1439 }, { "epoch": 2.122328666175387, "grad_norm": 2.0782289407306243, "learning_rate": 3.663272199019516e-05, "loss": 0.3368, "step": 1440 }, { "epoch": 2.1238025055268976, "grad_norm": 1.7463905713702752, "learning_rate": 3.661541644744725e-05, "loss": 0.3559, "step": 1441 }, { "epoch": 2.1252763448784084, "grad_norm": 1.752751503391625, "learning_rate": 3.659810380377895e-05, "loss": 0.2853, "step": 1442 }, { "epoch": 2.126750184229919, "grad_norm": 2.1923449676577715, "learning_rate": 3.6580784069774105e-05, "loss": 0.2963, "step": 1443 }, { "epoch": 2.1282240235814296, "grad_norm": 1.6518146939478684, "learning_rate": 3.656345725602089e-05, "loss": 0.3342, "step": 1444 }, { "epoch": 2.1296978629329404, "grad_norm": 2.5255352548250554, "learning_rate": 3.654612337311179e-05, "loss": 0.293, "step": 1445 }, { "epoch": 2.131171702284451, "grad_norm": 1.9126223381656708, "learning_rate": 3.652878243164365e-05, "loss": 0.284, "step": 1446 }, { "epoch": 2.1326455416359615, "grad_norm": 1.4981784887079042, "learning_rate": 3.65114344422176e-05, "loss": 0.2377, "step": 1447 }, { "epoch": 2.1341193809874723, "grad_norm": 1.7705599255895745, "learning_rate": 3.649407941543909e-05, "loss": 0.3113, "step": 1448 }, { "epoch": 2.135593220338983, "grad_norm": 2.8233266347410084, "learning_rate": 3.647671736191787e-05, "loss": 0.333, "step": 1449 }, { "epoch": 2.137067059690494, "grad_norm": 2.131553306140319, "learning_rate": 3.645934829226797e-05, "loss": 0.2472, "step": 1450 }, { "epoch": 2.1385408990420043, "grad_norm": 1.7233901763533328, "learning_rate": 3.644197221710775e-05, "loss": 0.346, "step": 1451 }, { "epoch": 2.140014738393515, "grad_norm": 2.0121564962904763, "learning_rate": 3.642458914705982e-05, "loss": 0.3058, "step": 1452 }, { "epoch": 2.141488577745026, "grad_norm": 1.9744377325754046, "learning_rate": 3.640719909275105e-05, "loss": 0.3163, "step": 1453 }, { "epoch": 2.1429624170965367, "grad_norm": 2.1745550511685705, "learning_rate": 3.638980206481264e-05, "loss": 0.311, "step": 1454 }, { "epoch": 2.144436256448047, "grad_norm": 1.8831506955646993, "learning_rate": 3.637239807388e-05, "loss": 0.2727, "step": 1455 }, { "epoch": 2.145910095799558, "grad_norm": 1.826750670726711, "learning_rate": 3.6354987130592814e-05, "loss": 0.3094, "step": 1456 }, { "epoch": 2.1473839351510686, "grad_norm": 2.154805238424009, "learning_rate": 3.6337569245595005e-05, "loss": 0.2681, "step": 1457 }, { "epoch": 2.1488577745025794, "grad_norm": 1.7123856360123757, "learning_rate": 3.632014442953476e-05, "loss": 0.2743, "step": 1458 }, { "epoch": 2.1503316138540898, "grad_norm": 4.04996611027608, "learning_rate": 3.630271269306451e-05, "loss": 0.2948, "step": 1459 }, { "epoch": 2.1518054532056006, "grad_norm": 2.8977355929712534, "learning_rate": 3.628527404684088e-05, "loss": 0.3334, "step": 1460 }, { "epoch": 2.1532792925571114, "grad_norm": 2.070729915357079, "learning_rate": 3.6267828501524734e-05, "loss": 0.3396, "step": 1461 }, { "epoch": 2.154753131908622, "grad_norm": 2.2054745746012685, "learning_rate": 3.6250376067781164e-05, "loss": 0.2415, "step": 1462 }, { "epoch": 2.1562269712601325, "grad_norm": 3.0083910893384744, "learning_rate": 3.623291675627949e-05, "loss": 0.2783, "step": 1463 }, { "epoch": 2.1577008106116433, "grad_norm": 6.611428232716982, "learning_rate": 3.6215450577693196e-05, "loss": 0.325, "step": 1464 }, { "epoch": 2.159174649963154, "grad_norm": 1.80688870762917, "learning_rate": 3.619797754269997e-05, "loss": 0.3029, "step": 1465 }, { "epoch": 2.1606484893146645, "grad_norm": 1.9049637629348997, "learning_rate": 3.6180497661981736e-05, "loss": 0.2585, "step": 1466 }, { "epoch": 2.1621223286661753, "grad_norm": 1.962060189015106, "learning_rate": 3.616301094622455e-05, "loss": 0.2326, "step": 1467 }, { "epoch": 2.163596168017686, "grad_norm": 2.015302765394335, "learning_rate": 3.6145517406118676e-05, "loss": 0.3234, "step": 1468 }, { "epoch": 2.165070007369197, "grad_norm": 1.8061446875260139, "learning_rate": 3.612801705235853e-05, "loss": 0.3222, "step": 1469 }, { "epoch": 2.1665438467207077, "grad_norm": 2.6710079637906468, "learning_rate": 3.611050989564272e-05, "loss": 0.327, "step": 1470 }, { "epoch": 2.168017686072218, "grad_norm": 2.0989387328287363, "learning_rate": 3.6092995946673994e-05, "loss": 0.2644, "step": 1471 }, { "epoch": 2.169491525423729, "grad_norm": 2.4885758685165773, "learning_rate": 3.607547521615926e-05, "loss": 0.2642, "step": 1472 }, { "epoch": 2.1709653647752396, "grad_norm": 1.8885649499932529, "learning_rate": 3.6057947714809553e-05, "loss": 0.3197, "step": 1473 }, { "epoch": 2.17243920412675, "grad_norm": 1.7806865403268266, "learning_rate": 3.604041345334008e-05, "loss": 0.2417, "step": 1474 }, { "epoch": 2.1739130434782608, "grad_norm": 1.4416039804196208, "learning_rate": 3.602287244247017e-05, "loss": 0.2645, "step": 1475 }, { "epoch": 2.1753868828297716, "grad_norm": 2.2231203476302417, "learning_rate": 3.600532469292324e-05, "loss": 0.3776, "step": 1476 }, { "epoch": 2.1768607221812823, "grad_norm": 2.499680880206242, "learning_rate": 3.598777021542689e-05, "loss": 0.4147, "step": 1477 }, { "epoch": 2.178334561532793, "grad_norm": 1.9835847497580374, "learning_rate": 3.597020902071278e-05, "loss": 0.2836, "step": 1478 }, { "epoch": 2.1798084008843035, "grad_norm": 2.35096880239721, "learning_rate": 3.595264111951672e-05, "loss": 0.2993, "step": 1479 }, { "epoch": 2.1812822402358143, "grad_norm": 1.8621346006451305, "learning_rate": 3.593506652257858e-05, "loss": 0.2909, "step": 1480 }, { "epoch": 2.182756079587325, "grad_norm": 2.6361373599475946, "learning_rate": 3.591748524064233e-05, "loss": 0.3819, "step": 1481 }, { "epoch": 2.1842299189388354, "grad_norm": 2.2329064725156855, "learning_rate": 3.589989728445607e-05, "loss": 0.2269, "step": 1482 }, { "epoch": 2.1857037582903462, "grad_norm": 3.0797314784424117, "learning_rate": 3.588230266477193e-05, "loss": 0.3266, "step": 1483 }, { "epoch": 2.187177597641857, "grad_norm": 1.8158468718226102, "learning_rate": 3.586470139234612e-05, "loss": 0.2878, "step": 1484 }, { "epoch": 2.188651436993368, "grad_norm": 2.4409166501265442, "learning_rate": 3.5847093477938956e-05, "loss": 0.2998, "step": 1485 }, { "epoch": 2.1901252763448786, "grad_norm": 2.3321889954957915, "learning_rate": 3.5829478932314765e-05, "loss": 0.4221, "step": 1486 }, { "epoch": 2.191599115696389, "grad_norm": 3.6047846681406797, "learning_rate": 3.581185776624196e-05, "loss": 0.2941, "step": 1487 }, { "epoch": 2.1930729550479, "grad_norm": 1.6691975054254455, "learning_rate": 3.579422999049299e-05, "loss": 0.3825, "step": 1488 }, { "epoch": 2.1945467943994106, "grad_norm": 2.073542655342342, "learning_rate": 3.577659561584434e-05, "loss": 0.3967, "step": 1489 }, { "epoch": 2.196020633750921, "grad_norm": 2.246476593561282, "learning_rate": 3.5758954653076546e-05, "loss": 0.3541, "step": 1490 }, { "epoch": 2.1974944731024317, "grad_norm": 2.598072357121594, "learning_rate": 3.574130711297416e-05, "loss": 0.2932, "step": 1491 }, { "epoch": 2.1989683124539425, "grad_norm": 1.9068902613286376, "learning_rate": 3.572365300632574e-05, "loss": 0.3124, "step": 1492 }, { "epoch": 2.2004421518054533, "grad_norm": 1.6250419611281568, "learning_rate": 3.570599234392389e-05, "loss": 0.2772, "step": 1493 }, { "epoch": 2.201915991156964, "grad_norm": 1.924986638604895, "learning_rate": 3.56883251365652e-05, "loss": 0.3049, "step": 1494 }, { "epoch": 2.2033898305084745, "grad_norm": 2.3138563972299475, "learning_rate": 3.567065139505027e-05, "loss": 0.2966, "step": 1495 }, { "epoch": 2.2048636698599853, "grad_norm": 1.7226468386576816, "learning_rate": 3.565297113018369e-05, "loss": 0.269, "step": 1496 }, { "epoch": 2.206337509211496, "grad_norm": 2.4478121038519602, "learning_rate": 3.5635284352774034e-05, "loss": 0.2613, "step": 1497 }, { "epoch": 2.2078113485630064, "grad_norm": 1.939429153340337, "learning_rate": 3.561759107363388e-05, "loss": 0.3386, "step": 1498 }, { "epoch": 2.2092851879145172, "grad_norm": 2.8110414749771566, "learning_rate": 3.5599891303579746e-05, "loss": 0.3051, "step": 1499 }, { "epoch": 2.210759027266028, "grad_norm": 1.8396233104654764, "learning_rate": 3.558218505343214e-05, "loss": 0.2964, "step": 1500 }, { "epoch": 2.210759027266028, "eval_bleu": 0.1994255446549623, "eval_bleu_1gram": 0.5058144731863301, "eval_bleu_2gram": 0.2986066746967081, "eval_bleu_3gram": 0.18738026007865916, "eval_bleu_4gram": 0.1217969285920883, "eval_rag_val_loss": 0.6347189045721485, "eval_rouge1": 0.5114723215394744, "eval_rouge2": 0.29274178880188145, "eval_rougeL": 0.505267357169367, "step": 1500 }, { "epoch": 2.212232866617539, "grad_norm": 2.0849119944489667, "learning_rate": 3.556447233401553e-05, "loss": 0.2997, "step": 1501 }, { "epoch": 2.213706705969049, "grad_norm": 2.246495060106794, "learning_rate": 3.554675315615833e-05, "loss": 0.3447, "step": 1502 }, { "epoch": 2.21518054532056, "grad_norm": 2.193743922559357, "learning_rate": 3.552902753069293e-05, "loss": 0.3121, "step": 1503 }, { "epoch": 2.2166543846720708, "grad_norm": 1.9733401482159412, "learning_rate": 3.551129546845561e-05, "loss": 0.2818, "step": 1504 }, { "epoch": 2.2181282240235816, "grad_norm": 2.2317547139164686, "learning_rate": 3.549355698028663e-05, "loss": 0.3679, "step": 1505 }, { "epoch": 2.219602063375092, "grad_norm": 1.931530585785235, "learning_rate": 3.547581207703017e-05, "loss": 0.3374, "step": 1506 }, { "epoch": 2.2210759027266027, "grad_norm": 2.9779779868250618, "learning_rate": 3.545806076953432e-05, "loss": 0.2286, "step": 1507 }, { "epoch": 2.2225497420781135, "grad_norm": 1.972691118291002, "learning_rate": 3.5440303068651073e-05, "loss": 0.2855, "step": 1508 }, { "epoch": 2.2240235814296243, "grad_norm": 3.2826378203466664, "learning_rate": 3.542253898523638e-05, "loss": 0.3141, "step": 1509 }, { "epoch": 2.2254974207811347, "grad_norm": 3.0610109718622116, "learning_rate": 3.540476853015004e-05, "loss": 0.3491, "step": 1510 }, { "epoch": 2.2269712601326455, "grad_norm": 1.9705619345560146, "learning_rate": 3.5386991714255776e-05, "loss": 0.2695, "step": 1511 }, { "epoch": 2.2284450994841563, "grad_norm": 2.3960208211322107, "learning_rate": 3.536920854842119e-05, "loss": 0.3409, "step": 1512 }, { "epoch": 2.229918938835667, "grad_norm": 1.3139022420984683, "learning_rate": 3.535141904351776e-05, "loss": 0.2237, "step": 1513 }, { "epoch": 2.2313927781871774, "grad_norm": 2.284156097903522, "learning_rate": 3.533362321042087e-05, "loss": 0.2877, "step": 1514 }, { "epoch": 2.232866617538688, "grad_norm": 2.1809991424502893, "learning_rate": 3.5315821060009746e-05, "loss": 0.3261, "step": 1515 }, { "epoch": 2.234340456890199, "grad_norm": 1.660070583152775, "learning_rate": 3.5298012603167465e-05, "loss": 0.2719, "step": 1516 }, { "epoch": 2.23581429624171, "grad_norm": 2.715821014810229, "learning_rate": 3.528019785078098e-05, "loss": 0.3658, "step": 1517 }, { "epoch": 2.23728813559322, "grad_norm": 2.3973415989901263, "learning_rate": 3.5262376813741094e-05, "loss": 0.3573, "step": 1518 }, { "epoch": 2.238761974944731, "grad_norm": 1.8723223958759108, "learning_rate": 3.524454950294244e-05, "loss": 0.3069, "step": 1519 }, { "epoch": 2.2402358142962417, "grad_norm": 2.139992279324018, "learning_rate": 3.5226715929283506e-05, "loss": 0.3274, "step": 1520 }, { "epoch": 2.2417096536477525, "grad_norm": 2.616108777371515, "learning_rate": 3.520887610366657e-05, "loss": 0.2852, "step": 1521 }, { "epoch": 2.243183492999263, "grad_norm": 2.423577872858751, "learning_rate": 3.5191030036997773e-05, "loss": 0.2801, "step": 1522 }, { "epoch": 2.2446573323507737, "grad_norm": 1.7899757952625317, "learning_rate": 3.517317774018706e-05, "loss": 0.2427, "step": 1523 }, { "epoch": 2.2461311717022845, "grad_norm": 2.140680354161412, "learning_rate": 3.515531922414816e-05, "loss": 0.276, "step": 1524 }, { "epoch": 2.2476050110537953, "grad_norm": 2.2596608552244173, "learning_rate": 3.513745449979864e-05, "loss": 0.2968, "step": 1525 }, { "epoch": 2.2490788504053056, "grad_norm": 2.009728018925071, "learning_rate": 3.5119583578059846e-05, "loss": 0.3307, "step": 1526 }, { "epoch": 2.2505526897568164, "grad_norm": 2.08441094820745, "learning_rate": 3.510170646985691e-05, "loss": 0.2742, "step": 1527 }, { "epoch": 2.2520265291083272, "grad_norm": 2.33944336995352, "learning_rate": 3.508382318611875e-05, "loss": 0.2914, "step": 1528 }, { "epoch": 2.253500368459838, "grad_norm": 1.7161931526788108, "learning_rate": 3.506593373777805e-05, "loss": 0.3176, "step": 1529 }, { "epoch": 2.2549742078113484, "grad_norm": 1.5702205650025598, "learning_rate": 3.504803813577128e-05, "loss": 0.2192, "step": 1530 }, { "epoch": 2.256448047162859, "grad_norm": 2.166589466578062, "learning_rate": 3.503013639103867e-05, "loss": 0.4556, "step": 1531 }, { "epoch": 2.25792188651437, "grad_norm": 2.1461396847403096, "learning_rate": 3.5012228514524173e-05, "loss": 0.3266, "step": 1532 }, { "epoch": 2.2593957258658808, "grad_norm": 2.297198837183798, "learning_rate": 3.499431451717554e-05, "loss": 0.2648, "step": 1533 }, { "epoch": 2.260869565217391, "grad_norm": 2.3701695961771034, "learning_rate": 3.497639440994424e-05, "loss": 0.3078, "step": 1534 }, { "epoch": 2.262343404568902, "grad_norm": 1.8116084569840183, "learning_rate": 3.4958468203785454e-05, "loss": 0.2746, "step": 1535 }, { "epoch": 2.2638172439204127, "grad_norm": 2.248100326525709, "learning_rate": 3.4940535909658136e-05, "loss": 0.3645, "step": 1536 }, { "epoch": 2.2652910832719235, "grad_norm": 1.791087241701323, "learning_rate": 3.492259753852493e-05, "loss": 0.3266, "step": 1537 }, { "epoch": 2.266764922623434, "grad_norm": 2.7311918204459387, "learning_rate": 3.4904653101352205e-05, "loss": 0.3227, "step": 1538 }, { "epoch": 2.2682387619749447, "grad_norm": 1.7085136070345952, "learning_rate": 3.4886702609110044e-05, "loss": 0.2474, "step": 1539 }, { "epoch": 2.2697126013264555, "grad_norm": 2.2753246117704222, "learning_rate": 3.4868746072772225e-05, "loss": 0.3827, "step": 1540 }, { "epoch": 2.2711864406779663, "grad_norm": 1.6858247282619732, "learning_rate": 3.485078350331622e-05, "loss": 0.2646, "step": 1541 }, { "epoch": 2.2726602800294766, "grad_norm": 2.394211814694566, "learning_rate": 3.4832814911723186e-05, "loss": 0.2436, "step": 1542 }, { "epoch": 2.2741341193809874, "grad_norm": 2.4947646636669556, "learning_rate": 3.481484030897798e-05, "loss": 0.3872, "step": 1543 }, { "epoch": 2.275607958732498, "grad_norm": 1.899698411697147, "learning_rate": 3.479685970606912e-05, "loss": 0.3177, "step": 1544 }, { "epoch": 2.277081798084009, "grad_norm": 2.322696065192557, "learning_rate": 3.4778873113988774e-05, "loss": 0.3397, "step": 1545 }, { "epoch": 2.2785556374355194, "grad_norm": 2.0035049006814143, "learning_rate": 3.476088054373282e-05, "loss": 0.3132, "step": 1546 }, { "epoch": 2.28002947678703, "grad_norm": 3.1012643819749934, "learning_rate": 3.474288200630073e-05, "loss": 0.3068, "step": 1547 }, { "epoch": 2.281503316138541, "grad_norm": 1.735482146030337, "learning_rate": 3.4724877512695674e-05, "loss": 0.2453, "step": 1548 }, { "epoch": 2.2829771554900518, "grad_norm": 2.1177519436492847, "learning_rate": 3.470686707392444e-05, "loss": 0.273, "step": 1549 }, { "epoch": 2.284450994841562, "grad_norm": 2.47944785908952, "learning_rate": 3.4688850700997456e-05, "loss": 0.3516, "step": 1550 }, { "epoch": 2.285924834193073, "grad_norm": 1.6761366816257357, "learning_rate": 3.467082840492878e-05, "loss": 0.2586, "step": 1551 }, { "epoch": 2.2873986735445837, "grad_norm": 2.0072119144841722, "learning_rate": 3.465280019673608e-05, "loss": 0.2775, "step": 1552 }, { "epoch": 2.2888725128960945, "grad_norm": 2.15738095464514, "learning_rate": 3.4634766087440644e-05, "loss": 0.2637, "step": 1553 }, { "epoch": 2.290346352247605, "grad_norm": 1.9939814848733732, "learning_rate": 3.461672608806738e-05, "loss": 0.3632, "step": 1554 }, { "epoch": 2.2918201915991157, "grad_norm": 2.1136292683994085, "learning_rate": 3.459868020964478e-05, "loss": 0.2585, "step": 1555 }, { "epoch": 2.2932940309506264, "grad_norm": 2.1500470045407423, "learning_rate": 3.4580628463204936e-05, "loss": 0.4093, "step": 1556 }, { "epoch": 2.2947678703021372, "grad_norm": 1.9981453163753589, "learning_rate": 3.456257085978352e-05, "loss": 0.2929, "step": 1557 }, { "epoch": 2.2962417096536476, "grad_norm": 2.923506663659821, "learning_rate": 3.4544507410419806e-05, "loss": 0.297, "step": 1558 }, { "epoch": 2.2977155490051584, "grad_norm": 1.8751000059796616, "learning_rate": 3.4526438126156626e-05, "loss": 0.3405, "step": 1559 }, { "epoch": 2.299189388356669, "grad_norm": 2.2810592571623998, "learning_rate": 3.450836301804038e-05, "loss": 0.28, "step": 1560 }, { "epoch": 2.30066322770818, "grad_norm": 3.505167416262429, "learning_rate": 3.4490282097121016e-05, "loss": 0.3404, "step": 1561 }, { "epoch": 2.3021370670596903, "grad_norm": 1.8000351028198498, "learning_rate": 3.447219537445207e-05, "loss": 0.2867, "step": 1562 }, { "epoch": 2.303610906411201, "grad_norm": 2.0386471380109685, "learning_rate": 3.445410286109059e-05, "loss": 0.2671, "step": 1563 }, { "epoch": 2.305084745762712, "grad_norm": 2.3719664826172027, "learning_rate": 3.4436004568097176e-05, "loss": 0.2982, "step": 1564 }, { "epoch": 2.3065585851142227, "grad_norm": 2.359958803819486, "learning_rate": 3.4417900506535977e-05, "loss": 0.3142, "step": 1565 }, { "epoch": 2.308032424465733, "grad_norm": 1.866876296919994, "learning_rate": 3.4399790687474635e-05, "loss": 0.3251, "step": 1566 }, { "epoch": 2.309506263817244, "grad_norm": 2.3801080082980586, "learning_rate": 3.438167512198436e-05, "loss": 0.2754, "step": 1567 }, { "epoch": 2.3109801031687547, "grad_norm": 1.7034316880458173, "learning_rate": 3.436355382113982e-05, "loss": 0.2194, "step": 1568 }, { "epoch": 2.3124539425202655, "grad_norm": 2.030463785456789, "learning_rate": 3.434542679601922e-05, "loss": 0.3997, "step": 1569 }, { "epoch": 2.313927781871776, "grad_norm": 1.6172587061146593, "learning_rate": 3.4327294057704265e-05, "loss": 0.2892, "step": 1570 }, { "epoch": 2.3154016212232866, "grad_norm": 3.2231274809355304, "learning_rate": 3.430915561728016e-05, "loss": 0.4041, "step": 1571 }, { "epoch": 2.3168754605747974, "grad_norm": 1.842355491737295, "learning_rate": 3.4291011485835565e-05, "loss": 0.3421, "step": 1572 }, { "epoch": 2.3183492999263082, "grad_norm": 2.0387706328470045, "learning_rate": 3.427286167446265e-05, "loss": 0.2661, "step": 1573 }, { "epoch": 2.3198231392778186, "grad_norm": 2.985217070490315, "learning_rate": 3.425470619425704e-05, "loss": 0.3094, "step": 1574 }, { "epoch": 2.3212969786293294, "grad_norm": 1.871974857067737, "learning_rate": 3.4236545056317824e-05, "loss": 0.2692, "step": 1575 }, { "epoch": 2.32277081798084, "grad_norm": 1.8842190755477992, "learning_rate": 3.421837827174757e-05, "loss": 0.2787, "step": 1576 }, { "epoch": 2.3242446573323505, "grad_norm": 2.0114568150924677, "learning_rate": 3.420020585165227e-05, "loss": 0.2808, "step": 1577 }, { "epoch": 2.3257184966838613, "grad_norm": 1.6864863282822034, "learning_rate": 3.418202780714138e-05, "loss": 0.2692, "step": 1578 }, { "epoch": 2.327192336035372, "grad_norm": 1.928496947187441, "learning_rate": 3.416384414932781e-05, "loss": 0.3053, "step": 1579 }, { "epoch": 2.328666175386883, "grad_norm": 1.4572884585727213, "learning_rate": 3.414565488932785e-05, "loss": 0.2598, "step": 1580 }, { "epoch": 2.3301400147383937, "grad_norm": 2.134309348217915, "learning_rate": 3.412746003826127e-05, "loss": 0.2394, "step": 1581 }, { "epoch": 2.331613854089904, "grad_norm": 2.1747094190446443, "learning_rate": 3.4109259607251225e-05, "loss": 0.289, "step": 1582 }, { "epoch": 2.333087693441415, "grad_norm": 2.0316424650900147, "learning_rate": 3.4091053607424295e-05, "loss": 0.2995, "step": 1583 }, { "epoch": 2.3345615327929257, "grad_norm": 2.3364470573580642, "learning_rate": 3.407284204991046e-05, "loss": 0.2747, "step": 1584 }, { "epoch": 2.336035372144436, "grad_norm": 2.2957631229065867, "learning_rate": 3.4054624945843084e-05, "loss": 0.3714, "step": 1585 }, { "epoch": 2.337509211495947, "grad_norm": 1.9617913807344673, "learning_rate": 3.403640230635895e-05, "loss": 0.3157, "step": 1586 }, { "epoch": 2.3389830508474576, "grad_norm": 2.477967835261453, "learning_rate": 3.4018174142598215e-05, "loss": 0.3104, "step": 1587 }, { "epoch": 2.3404568901989684, "grad_norm": 1.682054351350338, "learning_rate": 3.3999940465704395e-05, "loss": 0.3031, "step": 1588 }, { "epoch": 2.341930729550479, "grad_norm": 1.7492557714240857, "learning_rate": 3.3981701286824394e-05, "loss": 0.2878, "step": 1589 }, { "epoch": 2.3434045689019896, "grad_norm": 2.2498868278015762, "learning_rate": 3.396345661710849e-05, "loss": 0.3063, "step": 1590 }, { "epoch": 2.3448784082535004, "grad_norm": 1.9278986125579152, "learning_rate": 3.394520646771029e-05, "loss": 0.3134, "step": 1591 }, { "epoch": 2.346352247605011, "grad_norm": 2.1047431105847467, "learning_rate": 3.3926950849786765e-05, "loss": 0.3317, "step": 1592 }, { "epoch": 2.3478260869565215, "grad_norm": 2.1441651189832838, "learning_rate": 3.390868977449822e-05, "loss": 0.4177, "step": 1593 }, { "epoch": 2.3492999263080323, "grad_norm": 2.1812610483846155, "learning_rate": 3.389042325300832e-05, "loss": 0.3394, "step": 1594 }, { "epoch": 2.350773765659543, "grad_norm": 2.072806069444481, "learning_rate": 3.387215129648405e-05, "loss": 0.3046, "step": 1595 }, { "epoch": 2.352247605011054, "grad_norm": 4.749694212055364, "learning_rate": 3.385387391609569e-05, "loss": 0.3625, "step": 1596 }, { "epoch": 2.3537214443625647, "grad_norm": 2.4460141086436598, "learning_rate": 3.3835591123016865e-05, "loss": 0.2934, "step": 1597 }, { "epoch": 2.355195283714075, "grad_norm": 1.5256173994663418, "learning_rate": 3.381730292842452e-05, "loss": 0.2338, "step": 1598 }, { "epoch": 2.356669123065586, "grad_norm": 1.8756509922340507, "learning_rate": 3.379900934349886e-05, "loss": 0.2621, "step": 1599 }, { "epoch": 2.3581429624170966, "grad_norm": 1.7801106473200676, "learning_rate": 3.378071037942342e-05, "loss": 0.2954, "step": 1600 }, { "epoch": 2.359616801768607, "grad_norm": 3.095479154457143, "learning_rate": 3.376240604738501e-05, "loss": 0.2468, "step": 1601 }, { "epoch": 2.361090641120118, "grad_norm": 2.2708862251864796, "learning_rate": 3.374409635857372e-05, "loss": 0.3419, "step": 1602 }, { "epoch": 2.3625644804716286, "grad_norm": 1.9562682836488643, "learning_rate": 3.3725781324182944e-05, "loss": 0.314, "step": 1603 }, { "epoch": 2.3640383198231394, "grad_norm": 1.3010787852693262, "learning_rate": 3.370746095540928e-05, "loss": 0.1959, "step": 1604 }, { "epoch": 2.36551215917465, "grad_norm": 1.8436231407876726, "learning_rate": 3.368913526345265e-05, "loss": 0.2943, "step": 1605 }, { "epoch": 2.3669859985261605, "grad_norm": 1.8989957765649772, "learning_rate": 3.3670804259516205e-05, "loss": 0.3267, "step": 1606 }, { "epoch": 2.3684598378776713, "grad_norm": 1.8701726442087447, "learning_rate": 3.3652467954806336e-05, "loss": 0.3169, "step": 1607 }, { "epoch": 2.369933677229182, "grad_norm": 1.5472050324372952, "learning_rate": 3.363412636053269e-05, "loss": 0.2758, "step": 1608 }, { "epoch": 2.3714075165806925, "grad_norm": 2.268593573103556, "learning_rate": 3.361577948790814e-05, "loss": 0.2861, "step": 1609 }, { "epoch": 2.3728813559322033, "grad_norm": 1.9555067265199062, "learning_rate": 3.359742734814879e-05, "loss": 0.3225, "step": 1610 }, { "epoch": 2.374355195283714, "grad_norm": 2.1908333585421604, "learning_rate": 3.357906995247396e-05, "loss": 0.2853, "step": 1611 }, { "epoch": 2.375829034635225, "grad_norm": 2.3572784607759396, "learning_rate": 3.3560707312106174e-05, "loss": 0.3181, "step": 1612 }, { "epoch": 2.3773028739867357, "grad_norm": 2.450099075026867, "learning_rate": 3.3542339438271184e-05, "loss": 0.2992, "step": 1613 }, { "epoch": 2.378776713338246, "grad_norm": 2.545706919909756, "learning_rate": 3.352396634219792e-05, "loss": 0.3492, "step": 1614 }, { "epoch": 2.380250552689757, "grad_norm": 1.9642751792526119, "learning_rate": 3.3505588035118515e-05, "loss": 0.2838, "step": 1615 }, { "epoch": 2.3817243920412676, "grad_norm": 2.28350154600515, "learning_rate": 3.3487204528268304e-05, "loss": 0.2542, "step": 1616 }, { "epoch": 2.383198231392778, "grad_norm": 1.7659709895247133, "learning_rate": 3.346881583288577e-05, "loss": 0.2658, "step": 1617 }, { "epoch": 2.3846720707442888, "grad_norm": 1.8895591695040308, "learning_rate": 3.3450421960212566e-05, "loss": 0.2492, "step": 1618 }, { "epoch": 2.3861459100957996, "grad_norm": 1.8308635316886621, "learning_rate": 3.3432022921493555e-05, "loss": 0.2775, "step": 1619 }, { "epoch": 2.3876197494473104, "grad_norm": 1.9367190602230364, "learning_rate": 3.341361872797672e-05, "loss": 0.24, "step": 1620 }, { "epoch": 2.389093588798821, "grad_norm": 1.7598497580210888, "learning_rate": 3.3395209390913186e-05, "loss": 0.3243, "step": 1621 }, { "epoch": 2.3905674281503315, "grad_norm": 1.6792482733320793, "learning_rate": 3.337679492155726e-05, "loss": 0.2735, "step": 1622 }, { "epoch": 2.3920412675018423, "grad_norm": 1.7808732420692488, "learning_rate": 3.335837533116636e-05, "loss": 0.2941, "step": 1623 }, { "epoch": 2.393515106853353, "grad_norm": 2.547210203239718, "learning_rate": 3.333995063100105e-05, "loss": 0.2633, "step": 1624 }, { "epoch": 2.3949889462048635, "grad_norm": 1.5666407840024634, "learning_rate": 3.3321520832325e-05, "loss": 0.2199, "step": 1625 }, { "epoch": 2.3964627855563743, "grad_norm": 2.4873425496173547, "learning_rate": 3.3303085946405005e-05, "loss": 0.3904, "step": 1626 }, { "epoch": 2.397936624907885, "grad_norm": 1.4398546422338365, "learning_rate": 3.3284645984510975e-05, "loss": 0.2122, "step": 1627 }, { "epoch": 2.399410464259396, "grad_norm": 1.3558571118968121, "learning_rate": 3.3266200957915926e-05, "loss": 0.2292, "step": 1628 }, { "epoch": 2.4008843036109067, "grad_norm": 2.3190783162844126, "learning_rate": 3.3247750877895955e-05, "loss": 0.3053, "step": 1629 }, { "epoch": 2.402358142962417, "grad_norm": 2.7059864047964313, "learning_rate": 3.322929575573026e-05, "loss": 0.3585, "step": 1630 }, { "epoch": 2.403831982313928, "grad_norm": 2.6721582095312275, "learning_rate": 3.3210835602701116e-05, "loss": 0.3634, "step": 1631 }, { "epoch": 2.4053058216654386, "grad_norm": 2.692275572679518, "learning_rate": 3.319237043009389e-05, "loss": 0.3027, "step": 1632 }, { "epoch": 2.406779661016949, "grad_norm": 3.4211087697168296, "learning_rate": 3.317390024919699e-05, "loss": 0.3391, "step": 1633 }, { "epoch": 2.4082535003684598, "grad_norm": 2.7557422334578363, "learning_rate": 3.315542507130189e-05, "loss": 0.3344, "step": 1634 }, { "epoch": 2.4097273397199706, "grad_norm": 1.7600270880435258, "learning_rate": 3.313694490770316e-05, "loss": 0.2445, "step": 1635 }, { "epoch": 2.4112011790714813, "grad_norm": 2.219743747871222, "learning_rate": 3.311845976969836e-05, "loss": 0.3317, "step": 1636 }, { "epoch": 2.4126750184229917, "grad_norm": 2.577428920294867, "learning_rate": 3.3099969668588117e-05, "loss": 0.3501, "step": 1637 }, { "epoch": 2.4141488577745025, "grad_norm": 2.208170207014616, "learning_rate": 3.30814746156761e-05, "loss": 0.3701, "step": 1638 }, { "epoch": 2.4156226971260133, "grad_norm": 1.9090285141355519, "learning_rate": 3.306297462226901e-05, "loss": 0.3018, "step": 1639 }, { "epoch": 2.417096536477524, "grad_norm": 2.067035427828924, "learning_rate": 3.304446969967654e-05, "loss": 0.3008, "step": 1640 }, { "epoch": 2.4185703758290344, "grad_norm": 1.8341005266192458, "learning_rate": 3.302595985921141e-05, "loss": 0.3058, "step": 1641 }, { "epoch": 2.4200442151805452, "grad_norm": 1.6122035382414535, "learning_rate": 3.300744511218936e-05, "loss": 0.2569, "step": 1642 }, { "epoch": 2.421518054532056, "grad_norm": 2.6600867891135533, "learning_rate": 3.298892546992912e-05, "loss": 0.3473, "step": 1643 }, { "epoch": 2.422991893883567, "grad_norm": 1.7595833907359597, "learning_rate": 3.29704009437524e-05, "loss": 0.2359, "step": 1644 }, { "epoch": 2.424465733235077, "grad_norm": 1.9396769691207227, "learning_rate": 3.295187154498391e-05, "loss": 0.3035, "step": 1645 }, { "epoch": 2.425939572586588, "grad_norm": 1.8682975502001773, "learning_rate": 3.2933337284951336e-05, "loss": 0.3053, "step": 1646 }, { "epoch": 2.427413411938099, "grad_norm": 1.608536362886506, "learning_rate": 3.291479817498534e-05, "loss": 0.2412, "step": 1647 }, { "epoch": 2.4288872512896096, "grad_norm": 2.4544223343510643, "learning_rate": 3.289625422641954e-05, "loss": 0.3286, "step": 1648 }, { "epoch": 2.43036109064112, "grad_norm": 2.4039527529042246, "learning_rate": 3.2877705450590526e-05, "loss": 0.276, "step": 1649 }, { "epoch": 2.4318349299926307, "grad_norm": 2.356304874337707, "learning_rate": 3.2859151858837806e-05, "loss": 0.3689, "step": 1650 }, { "epoch": 2.4333087693441415, "grad_norm": 3.1140809605535043, "learning_rate": 3.2840593462503875e-05, "loss": 0.3057, "step": 1651 }, { "epoch": 2.4347826086956523, "grad_norm": 2.487885591918435, "learning_rate": 3.282203027293415e-05, "loss": 0.3264, "step": 1652 }, { "epoch": 2.4362564480471627, "grad_norm": 2.172941755501683, "learning_rate": 3.2803462301476964e-05, "loss": 0.3552, "step": 1653 }, { "epoch": 2.4377302873986735, "grad_norm": 1.9354983418959402, "learning_rate": 3.278488955948358e-05, "loss": 0.3108, "step": 1654 }, { "epoch": 2.4392041267501843, "grad_norm": 2.2350047897867853, "learning_rate": 3.276631205830818e-05, "loss": 0.3096, "step": 1655 }, { "epoch": 2.440677966101695, "grad_norm": 2.0411494891059405, "learning_rate": 3.274772980930787e-05, "loss": 0.3206, "step": 1656 }, { "epoch": 2.4421518054532054, "grad_norm": 1.9253336481048313, "learning_rate": 3.272914282384265e-05, "loss": 0.2939, "step": 1657 }, { "epoch": 2.4436256448047162, "grad_norm": 2.4425785271506846, "learning_rate": 3.271055111327538e-05, "loss": 0.2885, "step": 1658 }, { "epoch": 2.445099484156227, "grad_norm": 2.1326112757067297, "learning_rate": 3.269195468897186e-05, "loss": 0.3542, "step": 1659 }, { "epoch": 2.446573323507738, "grad_norm": 1.8486697620985435, "learning_rate": 3.267335356230075e-05, "loss": 0.3034, "step": 1660 }, { "epoch": 2.448047162859248, "grad_norm": 2.1985455256683406, "learning_rate": 3.265474774463358e-05, "loss": 0.3028, "step": 1661 }, { "epoch": 2.449521002210759, "grad_norm": 1.877329396650583, "learning_rate": 3.263613724734475e-05, "loss": 0.2675, "step": 1662 }, { "epoch": 2.4509948415622698, "grad_norm": 1.9813923685324453, "learning_rate": 3.261752208181154e-05, "loss": 0.3564, "step": 1663 }, { "epoch": 2.4524686809137806, "grad_norm": 2.540039531820651, "learning_rate": 3.2598902259414055e-05, "loss": 0.3034, "step": 1664 }, { "epoch": 2.453942520265291, "grad_norm": 1.673599637081479, "learning_rate": 3.258027779153527e-05, "loss": 0.2709, "step": 1665 }, { "epoch": 2.4554163596168017, "grad_norm": 1.6100018215761482, "learning_rate": 3.256164868956097e-05, "loss": 0.3294, "step": 1666 }, { "epoch": 2.4568901989683125, "grad_norm": 1.821453342750144, "learning_rate": 3.2543014964879816e-05, "loss": 0.3748, "step": 1667 }, { "epoch": 2.4583640383198233, "grad_norm": 2.114134216219939, "learning_rate": 3.2524376628883255e-05, "loss": 0.3252, "step": 1668 }, { "epoch": 2.4598378776713337, "grad_norm": 2.3579886702442496, "learning_rate": 3.250573369296557e-05, "loss": 0.3254, "step": 1669 }, { "epoch": 2.4613117170228445, "grad_norm": 2.326952952867943, "learning_rate": 3.2487086168523864e-05, "loss": 0.3068, "step": 1670 }, { "epoch": 2.4627855563743553, "grad_norm": 3.120564479137874, "learning_rate": 3.2468434066958045e-05, "loss": 0.2564, "step": 1671 }, { "epoch": 2.464259395725866, "grad_norm": 2.218410734645763, "learning_rate": 3.244977739967079e-05, "loss": 0.3375, "step": 1672 }, { "epoch": 2.4657332350773764, "grad_norm": 1.805057372135085, "learning_rate": 3.243111617806761e-05, "loss": 0.2913, "step": 1673 }, { "epoch": 2.467207074428887, "grad_norm": 2.0204536500790904, "learning_rate": 3.241245041355675e-05, "loss": 0.279, "step": 1674 }, { "epoch": 2.468680913780398, "grad_norm": 2.2362091432595164, "learning_rate": 3.2393780117549294e-05, "loss": 0.3, "step": 1675 }, { "epoch": 2.470154753131909, "grad_norm": 2.3526454725700794, "learning_rate": 3.237510530145905e-05, "loss": 0.4338, "step": 1676 }, { "epoch": 2.471628592483419, "grad_norm": 5.892331146941323, "learning_rate": 3.235642597670259e-05, "loss": 0.2848, "step": 1677 }, { "epoch": 2.47310243183493, "grad_norm": 2.0411583663453126, "learning_rate": 3.233774215469927e-05, "loss": 0.2989, "step": 1678 }, { "epoch": 2.4745762711864407, "grad_norm": 2.8130886733382083, "learning_rate": 3.231905384687117e-05, "loss": 0.2855, "step": 1679 }, { "epoch": 2.4760501105379515, "grad_norm": 1.662205694435747, "learning_rate": 3.230036106464313e-05, "loss": 0.2978, "step": 1680 }, { "epoch": 2.477523949889462, "grad_norm": 2.0292259108441355, "learning_rate": 3.228166381944272e-05, "loss": 0.2683, "step": 1681 }, { "epoch": 2.4789977892409727, "grad_norm": 2.241207214219402, "learning_rate": 3.2262962122700226e-05, "loss": 0.2883, "step": 1682 }, { "epoch": 2.4804716285924835, "grad_norm": 2.0696184254448737, "learning_rate": 3.2244255985848667e-05, "loss": 0.2963, "step": 1683 }, { "epoch": 2.4819454679439943, "grad_norm": 2.114422220440834, "learning_rate": 3.222554542032379e-05, "loss": 0.2683, "step": 1684 }, { "epoch": 2.4834193072955046, "grad_norm": 1.9259216381226327, "learning_rate": 3.220683043756402e-05, "loss": 0.2885, "step": 1685 }, { "epoch": 2.4848931466470154, "grad_norm": 2.3469578470573897, "learning_rate": 3.218811104901049e-05, "loss": 0.3285, "step": 1686 }, { "epoch": 2.4863669859985262, "grad_norm": 2.716159243869074, "learning_rate": 3.216938726610705e-05, "loss": 0.299, "step": 1687 }, { "epoch": 2.487840825350037, "grad_norm": 2.382076262251767, "learning_rate": 3.215065910030021e-05, "loss": 0.3196, "step": 1688 }, { "epoch": 2.4893146647015474, "grad_norm": 1.831620876004843, "learning_rate": 3.2131926563039186e-05, "loss": 0.2844, "step": 1689 }, { "epoch": 2.490788504053058, "grad_norm": 2.148608724533473, "learning_rate": 3.211318966577581e-05, "loss": 0.289, "step": 1690 }, { "epoch": 2.492262343404569, "grad_norm": 1.950907371394676, "learning_rate": 3.2094448419964655e-05, "loss": 0.2654, "step": 1691 }, { "epoch": 2.4937361827560798, "grad_norm": 2.199263631521937, "learning_rate": 3.2075702837062916e-05, "loss": 0.3667, "step": 1692 }, { "epoch": 2.49521002210759, "grad_norm": 1.6041721575093941, "learning_rate": 3.2056952928530416e-05, "loss": 0.2277, "step": 1693 }, { "epoch": 2.496683861459101, "grad_norm": 2.411092665914757, "learning_rate": 3.203819870582966e-05, "loss": 0.3822, "step": 1694 }, { "epoch": 2.4981577008106117, "grad_norm": 1.796828559607073, "learning_rate": 3.201944018042577e-05, "loss": 0.28, "step": 1695 }, { "epoch": 2.4996315401621225, "grad_norm": 2.236653906401588, "learning_rate": 3.2000677363786526e-05, "loss": 0.2461, "step": 1696 }, { "epoch": 2.501105379513633, "grad_norm": 2.045781666193248, "learning_rate": 3.1981910267382294e-05, "loss": 0.3817, "step": 1697 }, { "epoch": 2.5025792188651437, "grad_norm": 1.970249513228886, "learning_rate": 3.196313890268606e-05, "loss": 0.3258, "step": 1698 }, { "epoch": 2.5040530582166545, "grad_norm": 2.4379977182717165, "learning_rate": 3.1944363281173445e-05, "loss": 0.3317, "step": 1699 }, { "epoch": 2.5055268975681653, "grad_norm": 3.221122681984879, "learning_rate": 3.1925583414322675e-05, "loss": 0.3065, "step": 1700 }, { "epoch": 2.5070007369196756, "grad_norm": 2.219668131242597, "learning_rate": 3.1906799313614526e-05, "loss": 0.2969, "step": 1701 }, { "epoch": 2.5084745762711864, "grad_norm": 1.4616538346849917, "learning_rate": 3.1888010990532415e-05, "loss": 0.2947, "step": 1702 }, { "epoch": 2.509948415622697, "grad_norm": 1.759626004081581, "learning_rate": 3.18692184565623e-05, "loss": 0.2992, "step": 1703 }, { "epoch": 2.5114222549742076, "grad_norm": 1.8308561090237165, "learning_rate": 3.1850421723192746e-05, "loss": 0.2984, "step": 1704 }, { "epoch": 2.5128960943257184, "grad_norm": 2.088324506192479, "learning_rate": 3.1831620801914867e-05, "loss": 0.2973, "step": 1705 }, { "epoch": 2.514369933677229, "grad_norm": 1.756306388737106, "learning_rate": 3.181281570422233e-05, "loss": 0.3041, "step": 1706 }, { "epoch": 2.51584377302874, "grad_norm": 1.8617815103969786, "learning_rate": 3.179400644161137e-05, "loss": 0.3599, "step": 1707 }, { "epoch": 2.5173176123802508, "grad_norm": 1.8926145315851393, "learning_rate": 3.1775193025580776e-05, "loss": 0.2825, "step": 1708 }, { "epoch": 2.518791451731761, "grad_norm": 1.550021583652963, "learning_rate": 3.175637546763183e-05, "loss": 0.2682, "step": 1709 }, { "epoch": 2.520265291083272, "grad_norm": 1.7374434262952034, "learning_rate": 3.173755377926841e-05, "loss": 0.2649, "step": 1710 }, { "epoch": 2.5217391304347827, "grad_norm": 2.391444146928721, "learning_rate": 3.171872797199689e-05, "loss": 0.2806, "step": 1711 }, { "epoch": 2.523212969786293, "grad_norm": 1.8880532167661006, "learning_rate": 3.169989805732615e-05, "loss": 0.363, "step": 1712 }, { "epoch": 2.524686809137804, "grad_norm": 3.3642070705534777, "learning_rate": 3.168106404676759e-05, "loss": 0.2901, "step": 1713 }, { "epoch": 2.5261606484893147, "grad_norm": 1.8319302594099474, "learning_rate": 3.1662225951835126e-05, "loss": 0.26, "step": 1714 }, { "epoch": 2.5276344878408255, "grad_norm": 1.9034589126878072, "learning_rate": 3.164338378404514e-05, "loss": 0.3856, "step": 1715 }, { "epoch": 2.5291083271923362, "grad_norm": 2.196199068402721, "learning_rate": 3.162453755491655e-05, "loss": 0.3133, "step": 1716 }, { "epoch": 2.5305821665438466, "grad_norm": 2.003509422704684, "learning_rate": 3.1605687275970706e-05, "loss": 0.269, "step": 1717 }, { "epoch": 2.5320560058953574, "grad_norm": 2.4846079975008366, "learning_rate": 3.1586832958731475e-05, "loss": 0.2498, "step": 1718 }, { "epoch": 2.533529845246868, "grad_norm": 2.096339659709769, "learning_rate": 3.1567974614725185e-05, "loss": 0.3387, "step": 1719 }, { "epoch": 2.5350036845983785, "grad_norm": 1.7307210010753415, "learning_rate": 3.15491122554806e-05, "loss": 0.2689, "step": 1720 }, { "epoch": 2.5364775239498893, "grad_norm": 2.2352899132089665, "learning_rate": 3.1530245892528965e-05, "loss": 0.3756, "step": 1721 }, { "epoch": 2.5379513633014, "grad_norm": 1.8989218262807555, "learning_rate": 3.151137553740396e-05, "loss": 0.3253, "step": 1722 }, { "epoch": 2.539425202652911, "grad_norm": 1.9359340492199306, "learning_rate": 3.149250120164171e-05, "loss": 0.3313, "step": 1723 }, { "epoch": 2.5408990420044217, "grad_norm": 2.6790372988335305, "learning_rate": 3.147362289678079e-05, "loss": 0.314, "step": 1724 }, { "epoch": 2.542372881355932, "grad_norm": 1.7102453495269658, "learning_rate": 3.145474063436214e-05, "loss": 0.2759, "step": 1725 }, { "epoch": 2.543846720707443, "grad_norm": 2.3073945262935602, "learning_rate": 3.1435854425929205e-05, "loss": 0.3855, "step": 1726 }, { "epoch": 2.5453205600589537, "grad_norm": 1.8590406229383438, "learning_rate": 3.1416964283027795e-05, "loss": 0.2815, "step": 1727 }, { "epoch": 2.546794399410464, "grad_norm": 1.649029376904722, "learning_rate": 3.139807021720613e-05, "loss": 0.3455, "step": 1728 }, { "epoch": 2.548268238761975, "grad_norm": 2.0663885970344147, "learning_rate": 3.137917224001481e-05, "loss": 0.3201, "step": 1729 }, { "epoch": 2.5497420781134856, "grad_norm": 2.5682452854591125, "learning_rate": 3.136027036300687e-05, "loss": 0.3293, "step": 1730 }, { "epoch": 2.5512159174649964, "grad_norm": 1.6920746854617321, "learning_rate": 3.1341364597737686e-05, "loss": 0.3409, "step": 1731 }, { "epoch": 2.5526897568165072, "grad_norm": 1.8736176163196234, "learning_rate": 3.132245495576505e-05, "loss": 0.3121, "step": 1732 }, { "epoch": 2.5541635961680176, "grad_norm": 1.6568835504254396, "learning_rate": 3.130354144864909e-05, "loss": 0.268, "step": 1733 }, { "epoch": 2.5556374355195284, "grad_norm": 1.7477875074908111, "learning_rate": 3.128462408795231e-05, "loss": 0.3416, "step": 1734 }, { "epoch": 2.557111274871039, "grad_norm": 2.7864040666566408, "learning_rate": 3.1265702885239574e-05, "loss": 0.3193, "step": 1735 }, { "epoch": 2.5585851142225495, "grad_norm": 1.772221421381425, "learning_rate": 3.1246777852078097e-05, "loss": 0.2785, "step": 1736 }, { "epoch": 2.5600589535740603, "grad_norm": 2.1941684986671404, "learning_rate": 3.122784900003742e-05, "loss": 0.3187, "step": 1737 }, { "epoch": 2.561532792925571, "grad_norm": 2.1879031218607907, "learning_rate": 3.1208916340689434e-05, "loss": 0.2876, "step": 1738 }, { "epoch": 2.563006632277082, "grad_norm": 1.798392873785385, "learning_rate": 3.118997988560835e-05, "loss": 0.3195, "step": 1739 }, { "epoch": 2.5644804716285927, "grad_norm": 2.1596408663762623, "learning_rate": 3.117103964637072e-05, "loss": 0.282, "step": 1740 }, { "epoch": 2.565954310980103, "grad_norm": 2.768231128441925, "learning_rate": 3.115209563455536e-05, "loss": 0.3337, "step": 1741 }, { "epoch": 2.567428150331614, "grad_norm": 1.8658858993824248, "learning_rate": 3.113314786174343e-05, "loss": 0.237, "step": 1742 }, { "epoch": 2.5689019896831247, "grad_norm": 2.501883655450216, "learning_rate": 3.111419633951841e-05, "loss": 0.3396, "step": 1743 }, { "epoch": 2.570375829034635, "grad_norm": 2.21420973326589, "learning_rate": 3.109524107946602e-05, "loss": 0.3125, "step": 1744 }, { "epoch": 2.571849668386146, "grad_norm": 2.0057214914269315, "learning_rate": 3.1076282093174285e-05, "loss": 0.3006, "step": 1745 }, { "epoch": 2.5733235077376566, "grad_norm": 1.631037061685352, "learning_rate": 3.105731939223354e-05, "loss": 0.2312, "step": 1746 }, { "epoch": 2.5747973470891674, "grad_norm": 1.8378649394625184, "learning_rate": 3.103835298823633e-05, "loss": 0.2023, "step": 1747 }, { "epoch": 2.576271186440678, "grad_norm": 2.761984115002452, "learning_rate": 3.1019382892777525e-05, "loss": 0.2689, "step": 1748 }, { "epoch": 2.5777450257921886, "grad_norm": 1.8699293236457621, "learning_rate": 3.100040911745421e-05, "loss": 0.2844, "step": 1749 }, { "epoch": 2.5792188651436994, "grad_norm": 1.6560755223914934, "learning_rate": 3.098143167386574e-05, "loss": 0.3103, "step": 1750 }, { "epoch": 2.5792188651436994, "eval_bleu": 0.19990189401542888, "eval_bleu_1gram": 0.5096689067470342, "eval_bleu_2gram": 0.3022634418270453, "eval_bleu_3gram": 0.18767472523264417, "eval_bleu_4gram": 0.11807536761951311, "eval_rag_val_loss": 0.6315249130930952, "eval_rouge1": 0.5149348920519669, "eval_rouge2": 0.29927327647508534, "eval_rougeL": 0.5099457503676121, "step": 1750 }, { "epoch": 2.58069270449521, "grad_norm": 1.7801924125743693, "learning_rate": 3.0962450573613704e-05, "loss": 0.2688, "step": 1751 }, { "epoch": 2.5821665438467205, "grad_norm": 2.6815542942050934, "learning_rate": 3.094346582830193e-05, "loss": 0.3517, "step": 1752 }, { "epoch": 2.5836403831982313, "grad_norm": 2.42078951228581, "learning_rate": 3.092447744953647e-05, "loss": 0.2722, "step": 1753 }, { "epoch": 2.585114222549742, "grad_norm": 2.056858207010473, "learning_rate": 3.09054854489256e-05, "loss": 0.2821, "step": 1754 }, { "epoch": 2.586588061901253, "grad_norm": 2.6569002141049975, "learning_rate": 3.0886489838079815e-05, "loss": 0.3241, "step": 1755 }, { "epoch": 2.5880619012527637, "grad_norm": 2.08468487450765, "learning_rate": 3.0867490628611815e-05, "loss": 0.2841, "step": 1756 }, { "epoch": 2.589535740604274, "grad_norm": 2.639091452693277, "learning_rate": 3.0848487832136496e-05, "loss": 0.3592, "step": 1757 }, { "epoch": 2.591009579955785, "grad_norm": 2.0728929093371713, "learning_rate": 3.0829481460270936e-05, "loss": 0.3486, "step": 1758 }, { "epoch": 2.5924834193072956, "grad_norm": 1.5761785306163691, "learning_rate": 3.081047152463443e-05, "loss": 0.2611, "step": 1759 }, { "epoch": 2.593957258658806, "grad_norm": 2.643098474037059, "learning_rate": 3.079145803684843e-05, "loss": 0.4669, "step": 1760 }, { "epoch": 2.595431098010317, "grad_norm": 1.9149092689115723, "learning_rate": 3.077244100853654e-05, "loss": 0.3103, "step": 1761 }, { "epoch": 2.5969049373618276, "grad_norm": 2.9132645156146486, "learning_rate": 3.075342045132459e-05, "loss": 0.4046, "step": 1762 }, { "epoch": 2.5983787767133384, "grad_norm": 1.6210491863697805, "learning_rate": 3.073439637684049e-05, "loss": 0.2875, "step": 1763 }, { "epoch": 2.599852616064849, "grad_norm": 4.449947468308264, "learning_rate": 3.071536879671436e-05, "loss": 0.2925, "step": 1764 }, { "epoch": 2.6013264554163595, "grad_norm": 2.3181494703772874, "learning_rate": 3.0696337722578444e-05, "loss": 0.2787, "step": 1765 }, { "epoch": 2.6028002947678703, "grad_norm": 2.1931670759355133, "learning_rate": 3.0677303166067105e-05, "loss": 0.3521, "step": 1766 }, { "epoch": 2.604274134119381, "grad_norm": 1.9106645590368352, "learning_rate": 3.0658265138816864e-05, "loss": 0.2663, "step": 1767 }, { "epoch": 2.6057479734708915, "grad_norm": 2.5119775902726484, "learning_rate": 3.0639223652466334e-05, "loss": 0.2572, "step": 1768 }, { "epoch": 2.6072218128224023, "grad_norm": 2.1200603967736433, "learning_rate": 3.062017871865627e-05, "loss": 0.3043, "step": 1769 }, { "epoch": 2.608695652173913, "grad_norm": 2.131280257829681, "learning_rate": 3.0601130349029524e-05, "loss": 0.3812, "step": 1770 }, { "epoch": 2.610169491525424, "grad_norm": 1.441884610161009, "learning_rate": 3.058207855523104e-05, "loss": 0.238, "step": 1771 }, { "epoch": 2.6116433308769347, "grad_norm": 2.6665670753796498, "learning_rate": 3.056302334890786e-05, "loss": 0.3539, "step": 1772 }, { "epoch": 2.613117170228445, "grad_norm": 2.1077766296637415, "learning_rate": 3.054396474170913e-05, "loss": 0.3252, "step": 1773 }, { "epoch": 2.614591009579956, "grad_norm": 1.734936185207382, "learning_rate": 3.052490274528604e-05, "loss": 0.2938, "step": 1774 }, { "epoch": 2.6160648489314666, "grad_norm": 2.1121910230412784, "learning_rate": 3.0505837371291885e-05, "loss": 0.3612, "step": 1775 }, { "epoch": 2.617538688282977, "grad_norm": 1.6787414725535146, "learning_rate": 3.048676863138201e-05, "loss": 0.315, "step": 1776 }, { "epoch": 2.6190125276344878, "grad_norm": 1.8999180299243223, "learning_rate": 3.0467696537213807e-05, "loss": 0.2921, "step": 1777 }, { "epoch": 2.6204863669859986, "grad_norm": 1.884119933216766, "learning_rate": 3.044862110044675e-05, "loss": 0.2692, "step": 1778 }, { "epoch": 2.6219602063375094, "grad_norm": 2.5196129127693587, "learning_rate": 3.0429542332742323e-05, "loss": 0.3119, "step": 1779 }, { "epoch": 2.62343404568902, "grad_norm": 3.9487093060151497, "learning_rate": 3.0410460245764065e-05, "loss": 0.3012, "step": 1780 }, { "epoch": 2.6249078850405305, "grad_norm": 2.4447008044263496, "learning_rate": 3.0391374851177544e-05, "loss": 0.2951, "step": 1781 }, { "epoch": 2.6263817243920413, "grad_norm": 2.093068139940465, "learning_rate": 3.037228616065033e-05, "loss": 0.2713, "step": 1782 }, { "epoch": 2.627855563743552, "grad_norm": 2.3884258252709136, "learning_rate": 3.0353194185852052e-05, "loss": 0.3301, "step": 1783 }, { "epoch": 2.6293294030950625, "grad_norm": 2.2238839082675095, "learning_rate": 3.0334098938454293e-05, "loss": 0.3102, "step": 1784 }, { "epoch": 2.6308032424465733, "grad_norm": 1.951368289565767, "learning_rate": 3.031500043013067e-05, "loss": 0.2887, "step": 1785 }, { "epoch": 2.632277081798084, "grad_norm": 2.1067970629467183, "learning_rate": 3.029589867255678e-05, "loss": 0.2868, "step": 1786 }, { "epoch": 2.633750921149595, "grad_norm": 2.5575986368468624, "learning_rate": 3.0276793677410224e-05, "loss": 0.3333, "step": 1787 }, { "epoch": 2.6352247605011057, "grad_norm": 2.224774415656905, "learning_rate": 3.025768545637057e-05, "loss": 0.3501, "step": 1788 }, { "epoch": 2.636698599852616, "grad_norm": 1.9949625471610226, "learning_rate": 3.0238574021119355e-05, "loss": 0.3061, "step": 1789 }, { "epoch": 2.638172439204127, "grad_norm": 2.0240378649038298, "learning_rate": 3.021945938334007e-05, "loss": 0.32, "step": 1790 }, { "epoch": 2.639646278555637, "grad_norm": 2.150635860363589, "learning_rate": 3.02003415547182e-05, "loss": 0.2842, "step": 1791 }, { "epoch": 2.641120117907148, "grad_norm": 2.3406754736557636, "learning_rate": 3.0181220546941147e-05, "loss": 0.3116, "step": 1792 }, { "epoch": 2.6425939572586588, "grad_norm": 1.8338363636484927, "learning_rate": 3.0162096371698267e-05, "loss": 0.2365, "step": 1793 }, { "epoch": 2.6440677966101696, "grad_norm": 1.908015324888924, "learning_rate": 3.0142969040680862e-05, "loss": 0.2635, "step": 1794 }, { "epoch": 2.6455416359616803, "grad_norm": 1.474818577358112, "learning_rate": 3.0123838565582146e-05, "loss": 0.2135, "step": 1795 }, { "epoch": 2.6470154753131907, "grad_norm": 1.8109643942388618, "learning_rate": 3.0104704958097274e-05, "loss": 0.3, "step": 1796 }, { "epoch": 2.6484893146647015, "grad_norm": 2.489602976020564, "learning_rate": 3.00855682299233e-05, "loss": 0.2931, "step": 1797 }, { "epoch": 2.6499631540162123, "grad_norm": 1.539821147317346, "learning_rate": 3.0066428392759187e-05, "loss": 0.2913, "step": 1798 }, { "epoch": 2.6514369933677226, "grad_norm": 2.081870582779728, "learning_rate": 3.004728545830582e-05, "loss": 0.3, "step": 1799 }, { "epoch": 2.6529108327192334, "grad_norm": 2.4526117844921336, "learning_rate": 3.0028139438265944e-05, "loss": 0.2521, "step": 1800 }, { "epoch": 2.6543846720707442, "grad_norm": 1.7343228993881274, "learning_rate": 3.0008990344344212e-05, "loss": 0.2664, "step": 1801 }, { "epoch": 2.655858511422255, "grad_norm": 2.409535530570881, "learning_rate": 2.9989838188247156e-05, "loss": 0.3821, "step": 1802 }, { "epoch": 2.657332350773766, "grad_norm": 2.1568325195727582, "learning_rate": 2.997068298168316e-05, "loss": 0.3097, "step": 1803 }, { "epoch": 2.658806190125276, "grad_norm": 2.912331729333829, "learning_rate": 2.9951524736362514e-05, "loss": 0.3598, "step": 1804 }, { "epoch": 2.660280029476787, "grad_norm": 2.1773698852415917, "learning_rate": 2.9932363463997327e-05, "loss": 0.3371, "step": 1805 }, { "epoch": 2.661753868828298, "grad_norm": 2.1178973932744523, "learning_rate": 2.9913199176301564e-05, "loss": 0.3194, "step": 1806 }, { "epoch": 2.663227708179808, "grad_norm": 2.0182693050864158, "learning_rate": 2.989403188499105e-05, "loss": 0.2871, "step": 1807 }, { "epoch": 2.664701547531319, "grad_norm": 1.914809474381499, "learning_rate": 2.987486160178344e-05, "loss": 0.2354, "step": 1808 }, { "epoch": 2.6661753868828297, "grad_norm": 1.505742841632313, "learning_rate": 2.9855688338398204e-05, "loss": 0.2486, "step": 1809 }, { "epoch": 2.6676492262343405, "grad_norm": 2.185767332247189, "learning_rate": 2.983651210655665e-05, "loss": 0.3662, "step": 1810 }, { "epoch": 2.6691230655858513, "grad_norm": 1.5893132404864367, "learning_rate": 2.9817332917981898e-05, "loss": 0.3086, "step": 1811 }, { "epoch": 2.6705969049373617, "grad_norm": 2.3753828442845557, "learning_rate": 2.979815078439888e-05, "loss": 0.3311, "step": 1812 }, { "epoch": 2.6720707442888725, "grad_norm": 2.2960107955147158, "learning_rate": 2.9778965717534313e-05, "loss": 0.2798, "step": 1813 }, { "epoch": 2.6735445836403833, "grad_norm": 2.0376009910221633, "learning_rate": 2.975977772911671e-05, "loss": 0.2909, "step": 1814 }, { "epoch": 2.6750184229918936, "grad_norm": 1.948858988554402, "learning_rate": 2.974058683087639e-05, "loss": 0.287, "step": 1815 }, { "epoch": 2.6764922623434044, "grad_norm": 1.8095871110888855, "learning_rate": 2.972139303454543e-05, "loss": 0.2994, "step": 1816 }, { "epoch": 2.6779661016949152, "grad_norm": 1.7276132415665009, "learning_rate": 2.9702196351857687e-05, "loss": 0.2846, "step": 1817 }, { "epoch": 2.679439941046426, "grad_norm": 3.2399788928816124, "learning_rate": 2.968299679454878e-05, "loss": 0.3552, "step": 1818 }, { "epoch": 2.680913780397937, "grad_norm": 2.48259791508603, "learning_rate": 2.966379437435608e-05, "loss": 0.2366, "step": 1819 }, { "epoch": 2.682387619749447, "grad_norm": 2.0762272250529974, "learning_rate": 2.9644589103018726e-05, "loss": 0.3293, "step": 1820 }, { "epoch": 2.683861459100958, "grad_norm": 2.1656457500922395, "learning_rate": 2.9625380992277584e-05, "loss": 0.2475, "step": 1821 }, { "epoch": 2.6853352984524688, "grad_norm": 2.1428302626967457, "learning_rate": 2.960617005387526e-05, "loss": 0.2977, "step": 1822 }, { "epoch": 2.686809137803979, "grad_norm": 2.217451548428715, "learning_rate": 2.958695629955609e-05, "loss": 0.3389, "step": 1823 }, { "epoch": 2.68828297715549, "grad_norm": 2.956956104044346, "learning_rate": 2.9567739741066135e-05, "loss": 0.2999, "step": 1824 }, { "epoch": 2.6897568165070007, "grad_norm": 1.8872679864630437, "learning_rate": 2.9548520390153155e-05, "loss": 0.3094, "step": 1825 }, { "epoch": 2.6912306558585115, "grad_norm": 3.7775428190903457, "learning_rate": 2.952929825856664e-05, "loss": 0.3587, "step": 1826 }, { "epoch": 2.6927044952100223, "grad_norm": 2.4674012568078925, "learning_rate": 2.951007335805776e-05, "loss": 0.3757, "step": 1827 }, { "epoch": 2.6941783345615327, "grad_norm": 1.815582022757403, "learning_rate": 2.949084570037939e-05, "loss": 0.3014, "step": 1828 }, { "epoch": 2.6956521739130435, "grad_norm": 2.067603991844145, "learning_rate": 2.9471615297286086e-05, "loss": 0.3303, "step": 1829 }, { "epoch": 2.6971260132645543, "grad_norm": 1.7974103047324363, "learning_rate": 2.9452382160534075e-05, "loss": 0.3008, "step": 1830 }, { "epoch": 2.6985998526160646, "grad_norm": 1.8377075752775973, "learning_rate": 2.943314630188127e-05, "loss": 0.2745, "step": 1831 }, { "epoch": 2.7000736919675754, "grad_norm": 1.9541683004517494, "learning_rate": 2.9413907733087255e-05, "loss": 0.3473, "step": 1832 }, { "epoch": 2.701547531319086, "grad_norm": 2.583893766422061, "learning_rate": 2.9394666465913222e-05, "loss": 0.3927, "step": 1833 }, { "epoch": 2.703021370670597, "grad_norm": 2.169567941115683, "learning_rate": 2.937542251212207e-05, "loss": 0.323, "step": 1834 }, { "epoch": 2.704495210022108, "grad_norm": 1.7143834219630774, "learning_rate": 2.9356175883478322e-05, "loss": 0.269, "step": 1835 }, { "epoch": 2.705969049373618, "grad_norm": 1.7634915991621711, "learning_rate": 2.9336926591748115e-05, "loss": 0.2546, "step": 1836 }, { "epoch": 2.707442888725129, "grad_norm": 1.678158370100009, "learning_rate": 2.9317674648699255e-05, "loss": 0.2449, "step": 1837 }, { "epoch": 2.7089167280766397, "grad_norm": 1.5461555117799974, "learning_rate": 2.929842006610112e-05, "loss": 0.2593, "step": 1838 }, { "epoch": 2.71039056742815, "grad_norm": 2.6062281472733058, "learning_rate": 2.9279162855724734e-05, "loss": 0.3099, "step": 1839 }, { "epoch": 2.711864406779661, "grad_norm": 2.169998785625065, "learning_rate": 2.9259903029342735e-05, "loss": 0.2917, "step": 1840 }, { "epoch": 2.7133382461311717, "grad_norm": 1.8354170041150732, "learning_rate": 2.9240640598729323e-05, "loss": 0.2476, "step": 1841 }, { "epoch": 2.7148120854826825, "grad_norm": 3.159867734434638, "learning_rate": 2.922137557566032e-05, "loss": 0.3299, "step": 1842 }, { "epoch": 2.7162859248341933, "grad_norm": 2.062192951813145, "learning_rate": 2.9202107971913134e-05, "loss": 0.2743, "step": 1843 }, { "epoch": 2.7177597641857036, "grad_norm": 2.676125163231762, "learning_rate": 2.9182837799266726e-05, "loss": 0.2937, "step": 1844 }, { "epoch": 2.7192336035372144, "grad_norm": 2.1795116066462823, "learning_rate": 2.9163565069501663e-05, "loss": 0.3956, "step": 1845 }, { "epoch": 2.7207074428887252, "grad_norm": 2.2448657053858, "learning_rate": 2.9144289794400042e-05, "loss": 0.3601, "step": 1846 }, { "epoch": 2.7221812822402356, "grad_norm": 2.076352733295859, "learning_rate": 2.9125011985745526e-05, "loss": 0.3567, "step": 1847 }, { "epoch": 2.7236551215917464, "grad_norm": 2.585150838173591, "learning_rate": 2.9105731655323343e-05, "loss": 0.3041, "step": 1848 }, { "epoch": 2.725128960943257, "grad_norm": 2.0093519194658227, "learning_rate": 2.9086448814920242e-05, "loss": 0.2123, "step": 1849 }, { "epoch": 2.726602800294768, "grad_norm": 1.9758311490492355, "learning_rate": 2.906716347632451e-05, "loss": 0.2733, "step": 1850 }, { "epoch": 2.728076639646279, "grad_norm": 2.303895872551283, "learning_rate": 2.904787565132598e-05, "loss": 0.2775, "step": 1851 }, { "epoch": 2.729550478997789, "grad_norm": 2.5966801465834966, "learning_rate": 2.9028585351715975e-05, "loss": 0.2899, "step": 1852 }, { "epoch": 2.7310243183493, "grad_norm": 2.1512466099040193, "learning_rate": 2.9009292589287355e-05, "loss": 0.3302, "step": 1853 }, { "epoch": 2.7324981577008107, "grad_norm": 2.521452888038057, "learning_rate": 2.8989997375834482e-05, "loss": 0.3131, "step": 1854 }, { "epoch": 2.733971997052321, "grad_norm": 2.882649734988437, "learning_rate": 2.89706997231532e-05, "loss": 0.3783, "step": 1855 }, { "epoch": 2.735445836403832, "grad_norm": 2.1295177456433674, "learning_rate": 2.8951399643040867e-05, "loss": 0.3086, "step": 1856 }, { "epoch": 2.7369196757553427, "grad_norm": 1.8864256194753903, "learning_rate": 2.8932097147296304e-05, "loss": 0.3688, "step": 1857 }, { "epoch": 2.7383935151068535, "grad_norm": 1.6963223029675238, "learning_rate": 2.8912792247719824e-05, "loss": 0.2678, "step": 1858 }, { "epoch": 2.7398673544583643, "grad_norm": 1.9093340955183082, "learning_rate": 2.88934849561132e-05, "loss": 0.2815, "step": 1859 }, { "epoch": 2.7413411938098746, "grad_norm": 2.2321546499758234, "learning_rate": 2.887417528427967e-05, "loss": 0.3203, "step": 1860 }, { "epoch": 2.7428150331613854, "grad_norm": 1.8545747872147622, "learning_rate": 2.8854863244023944e-05, "loss": 0.2899, "step": 1861 }, { "epoch": 2.744288872512896, "grad_norm": 2.43523379885594, "learning_rate": 2.8835548847152145e-05, "loss": 0.3021, "step": 1862 }, { "epoch": 2.7457627118644066, "grad_norm": 2.8919189856065337, "learning_rate": 2.8816232105471863e-05, "loss": 0.3263, "step": 1863 }, { "epoch": 2.7472365512159174, "grad_norm": 1.906615988195704, "learning_rate": 2.8796913030792115e-05, "loss": 0.373, "step": 1864 }, { "epoch": 2.748710390567428, "grad_norm": 2.0767282940745204, "learning_rate": 2.877759163492335e-05, "loss": 0.345, "step": 1865 }, { "epoch": 2.750184229918939, "grad_norm": 2.534286091064607, "learning_rate": 2.875826792967742e-05, "loss": 0.3311, "step": 1866 }, { "epoch": 2.7516580692704498, "grad_norm": 1.579915909521278, "learning_rate": 2.8738941926867607e-05, "loss": 0.2861, "step": 1867 }, { "epoch": 2.75313190862196, "grad_norm": 2.532661138832598, "learning_rate": 2.871961363830858e-05, "loss": 0.2956, "step": 1868 }, { "epoch": 2.754605747973471, "grad_norm": 1.9566398427165472, "learning_rate": 2.870028307581642e-05, "loss": 0.2405, "step": 1869 }, { "epoch": 2.7560795873249817, "grad_norm": 1.961800313246783, "learning_rate": 2.8680950251208595e-05, "loss": 0.292, "step": 1870 }, { "epoch": 2.757553426676492, "grad_norm": 2.303035855476707, "learning_rate": 2.866161517630394e-05, "loss": 0.3883, "step": 1871 }, { "epoch": 2.759027266028003, "grad_norm": 2.17683031963415, "learning_rate": 2.86422778629227e-05, "loss": 0.421, "step": 1872 }, { "epoch": 2.7605011053795137, "grad_norm": 1.7802514071207869, "learning_rate": 2.862293832288646e-05, "loss": 0.2756, "step": 1873 }, { "epoch": 2.7619749447310245, "grad_norm": 1.5707182858107074, "learning_rate": 2.8603596568018164e-05, "loss": 0.2625, "step": 1874 }, { "epoch": 2.7634487840825352, "grad_norm": 1.845235258677422, "learning_rate": 2.858425261014213e-05, "loss": 0.2853, "step": 1875 }, { "epoch": 2.7649226234340456, "grad_norm": 1.9935723970048365, "learning_rate": 2.8564906461084012e-05, "loss": 0.3079, "step": 1876 }, { "epoch": 2.7663964627855564, "grad_norm": 2.8110990637955413, "learning_rate": 2.8545558132670803e-05, "loss": 0.3994, "step": 1877 }, { "epoch": 2.767870302137067, "grad_norm": 1.7765640728489767, "learning_rate": 2.852620763673083e-05, "loss": 0.2922, "step": 1878 }, { "epoch": 2.7693441414885775, "grad_norm": 1.6304131359930079, "learning_rate": 2.8506854985093738e-05, "loss": 0.2263, "step": 1879 }, { "epoch": 2.7708179808400883, "grad_norm": 2.1684429028228376, "learning_rate": 2.8487500189590512e-05, "loss": 0.4003, "step": 1880 }, { "epoch": 2.772291820191599, "grad_norm": 2.1827942505430644, "learning_rate": 2.8468143262053414e-05, "loss": 0.332, "step": 1881 }, { "epoch": 2.77376565954311, "grad_norm": 2.1203407370051206, "learning_rate": 2.8448784214316036e-05, "loss": 0.2538, "step": 1882 }, { "epoch": 2.7752394988946207, "grad_norm": 1.959277905943852, "learning_rate": 2.8429423058213266e-05, "loss": 0.2634, "step": 1883 }, { "epoch": 2.776713338246131, "grad_norm": 3.3013889453078207, "learning_rate": 2.8410059805581258e-05, "loss": 0.2779, "step": 1884 }, { "epoch": 2.778187177597642, "grad_norm": 2.1961419652899865, "learning_rate": 2.839069446825747e-05, "loss": 0.3115, "step": 1885 }, { "epoch": 2.7796610169491527, "grad_norm": 1.844396380898758, "learning_rate": 2.8371327058080634e-05, "loss": 0.2905, "step": 1886 }, { "epoch": 2.781134856300663, "grad_norm": 2.0791060347753096, "learning_rate": 2.835195758689072e-05, "loss": 0.2954, "step": 1887 }, { "epoch": 2.782608695652174, "grad_norm": 1.981386713070464, "learning_rate": 2.833258606652901e-05, "loss": 0.2928, "step": 1888 }, { "epoch": 2.7840825350036846, "grad_norm": 1.9692532335201312, "learning_rate": 2.8313212508837982e-05, "loss": 0.2465, "step": 1889 }, { "epoch": 2.7855563743551954, "grad_norm": 2.5139068043200976, "learning_rate": 2.8293836925661398e-05, "loss": 0.3053, "step": 1890 }, { "epoch": 2.7870302137067062, "grad_norm": 2.3777009763921084, "learning_rate": 2.8274459328844248e-05, "loss": 0.326, "step": 1891 }, { "epoch": 2.7885040530582166, "grad_norm": 2.321776573590172, "learning_rate": 2.825507973023274e-05, "loss": 0.2571, "step": 1892 }, { "epoch": 2.7899778924097274, "grad_norm": 3.102781272513587, "learning_rate": 2.8235698141674337e-05, "loss": 0.2949, "step": 1893 }, { "epoch": 2.791451731761238, "grad_norm": 2.113876287205825, "learning_rate": 2.821631457501769e-05, "loss": 0.2947, "step": 1894 }, { "epoch": 2.7929255711127485, "grad_norm": 1.9222241836542744, "learning_rate": 2.8196929042112652e-05, "loss": 0.2511, "step": 1895 }, { "epoch": 2.7943994104642593, "grad_norm": 1.518226514479173, "learning_rate": 2.8177541554810316e-05, "loss": 0.2613, "step": 1896 }, { "epoch": 2.79587324981577, "grad_norm": 2.0833598580261325, "learning_rate": 2.815815212496294e-05, "loss": 0.3091, "step": 1897 }, { "epoch": 2.797347089167281, "grad_norm": 2.5928596898906737, "learning_rate": 2.813876076442397e-05, "loss": 0.416, "step": 1898 }, { "epoch": 2.7988209285187917, "grad_norm": 1.7253428850916779, "learning_rate": 2.811936748504806e-05, "loss": 0.2634, "step": 1899 }, { "epoch": 2.800294767870302, "grad_norm": 2.064720576780467, "learning_rate": 2.8099972298690992e-05, "loss": 0.3422, "step": 1900 }, { "epoch": 2.801768607221813, "grad_norm": 1.8236052892740016, "learning_rate": 2.8080575217209753e-05, "loss": 0.2405, "step": 1901 }, { "epoch": 2.8032424465733237, "grad_norm": 2.2440274760354213, "learning_rate": 2.8061176252462472e-05, "loss": 0.2582, "step": 1902 }, { "epoch": 2.804716285924834, "grad_norm": 2.6926496094744814, "learning_rate": 2.804177541630843e-05, "loss": 0.3812, "step": 1903 }, { "epoch": 2.806190125276345, "grad_norm": 1.6874391756751985, "learning_rate": 2.802237272060806e-05, "loss": 0.225, "step": 1904 }, { "epoch": 2.8076639646278556, "grad_norm": 1.7455259078241303, "learning_rate": 2.8002968177222917e-05, "loss": 0.3541, "step": 1905 }, { "epoch": 2.8091378039793664, "grad_norm": 1.8560814418106855, "learning_rate": 2.798356179801569e-05, "loss": 0.2859, "step": 1906 }, { "epoch": 2.810611643330877, "grad_norm": 2.0768773054855734, "learning_rate": 2.7964153594850206e-05, "loss": 0.3101, "step": 1907 }, { "epoch": 2.8120854826823876, "grad_norm": 2.734144190174914, "learning_rate": 2.7944743579591382e-05, "loss": 0.3392, "step": 1908 }, { "epoch": 2.8135593220338984, "grad_norm": 1.8603104233886365, "learning_rate": 2.7925331764105274e-05, "loss": 0.2995, "step": 1909 }, { "epoch": 2.815033161385409, "grad_norm": 1.749643766384997, "learning_rate": 2.7905918160259002e-05, "loss": 0.2677, "step": 1910 }, { "epoch": 2.8165070007369195, "grad_norm": 3.314248253464985, "learning_rate": 2.788650277992081e-05, "loss": 0.1835, "step": 1911 }, { "epoch": 2.8179808400884303, "grad_norm": 2.3466814146698285, "learning_rate": 2.7867085634960016e-05, "loss": 0.3132, "step": 1912 }, { "epoch": 2.819454679439941, "grad_norm": 2.5998474516499206, "learning_rate": 2.784766673724701e-05, "loss": 0.2998, "step": 1913 }, { "epoch": 2.820928518791452, "grad_norm": 3.8952907789644597, "learning_rate": 2.7828246098653255e-05, "loss": 0.301, "step": 1914 }, { "epoch": 2.8224023581429623, "grad_norm": 1.6894648380645265, "learning_rate": 2.7808823731051304e-05, "loss": 0.2537, "step": 1915 }, { "epoch": 2.823876197494473, "grad_norm": 1.9176778475610463, "learning_rate": 2.7789399646314724e-05, "loss": 0.3368, "step": 1916 }, { "epoch": 2.825350036845984, "grad_norm": 2.067718147107208, "learning_rate": 2.7769973856318166e-05, "loss": 0.3086, "step": 1917 }, { "epoch": 2.826823876197494, "grad_norm": 2.6220209383444946, "learning_rate": 2.7750546372937315e-05, "loss": 0.3345, "step": 1918 }, { "epoch": 2.828297715549005, "grad_norm": 2.0680469712875627, "learning_rate": 2.7731117208048872e-05, "loss": 0.2683, "step": 1919 }, { "epoch": 2.829771554900516, "grad_norm": 4.097572231249575, "learning_rate": 2.77116863735306e-05, "loss": 0.2448, "step": 1920 }, { "epoch": 2.8312453942520266, "grad_norm": 1.9747220242116343, "learning_rate": 2.769225388126126e-05, "loss": 0.252, "step": 1921 }, { "epoch": 2.8327192336035374, "grad_norm": 2.1075976760692168, "learning_rate": 2.767281974312062e-05, "loss": 0.2727, "step": 1922 }, { "epoch": 2.8341930729550477, "grad_norm": 1.8397987182030504, "learning_rate": 2.7653383970989475e-05, "loss": 0.2725, "step": 1923 }, { "epoch": 2.8356669123065585, "grad_norm": 1.8634061311662493, "learning_rate": 2.7633946576749608e-05, "loss": 0.2516, "step": 1924 }, { "epoch": 2.8371407516580693, "grad_norm": 2.904425099357165, "learning_rate": 2.7614507572283798e-05, "loss": 0.3933, "step": 1925 }, { "epoch": 2.8386145910095797, "grad_norm": 2.1299110211336947, "learning_rate": 2.75950669694758e-05, "loss": 0.3282, "step": 1926 }, { "epoch": 2.8400884303610905, "grad_norm": 1.7457765295336505, "learning_rate": 2.7575624780210345e-05, "loss": 0.248, "step": 1927 }, { "epoch": 2.8415622697126013, "grad_norm": 2.130797947348724, "learning_rate": 2.755618101637315e-05, "loss": 0.3197, "step": 1928 }, { "epoch": 2.843036109064112, "grad_norm": 1.912123589467722, "learning_rate": 2.7536735689850896e-05, "loss": 0.3074, "step": 1929 }, { "epoch": 2.844509948415623, "grad_norm": 2.000363197727114, "learning_rate": 2.7517288812531177e-05, "loss": 0.3216, "step": 1930 }, { "epoch": 2.8459837877671332, "grad_norm": 1.7912431778282056, "learning_rate": 2.7497840396302595e-05, "loss": 0.2378, "step": 1931 }, { "epoch": 2.847457627118644, "grad_norm": 2.0667288227373706, "learning_rate": 2.747839045305464e-05, "loss": 0.2433, "step": 1932 }, { "epoch": 2.848931466470155, "grad_norm": 8.303170611996002, "learning_rate": 2.7458938994677786e-05, "loss": 0.4134, "step": 1933 }, { "epoch": 2.850405305821665, "grad_norm": 2.1431312090588257, "learning_rate": 2.7439486033063388e-05, "loss": 0.2908, "step": 1934 }, { "epoch": 2.851879145173176, "grad_norm": 1.9924156507110569, "learning_rate": 2.7420031580103734e-05, "loss": 0.2696, "step": 1935 }, { "epoch": 2.8533529845246868, "grad_norm": 2.4350024412483653, "learning_rate": 2.7400575647692046e-05, "loss": 0.3082, "step": 1936 }, { "epoch": 2.8548268238761976, "grad_norm": 2.048707796678051, "learning_rate": 2.7381118247722426e-05, "loss": 0.3451, "step": 1937 }, { "epoch": 2.8563006632277084, "grad_norm": 1.7886180075643996, "learning_rate": 2.736165939208987e-05, "loss": 0.3036, "step": 1938 }, { "epoch": 2.8577745025792187, "grad_norm": 3.0473587043433223, "learning_rate": 2.7342199092690285e-05, "loss": 0.2955, "step": 1939 }, { "epoch": 2.8592483419307295, "grad_norm": 2.0998096743121653, "learning_rate": 2.7322737361420454e-05, "loss": 0.2295, "step": 1940 }, { "epoch": 2.8607221812822403, "grad_norm": 1.7178465115790642, "learning_rate": 2.730327421017802e-05, "loss": 0.32, "step": 1941 }, { "epoch": 2.8621960206337507, "grad_norm": 1.6591230700500388, "learning_rate": 2.728380965086151e-05, "loss": 0.2677, "step": 1942 }, { "epoch": 2.8636698599852615, "grad_norm": 2.3596623732014987, "learning_rate": 2.7264343695370292e-05, "loss": 0.2906, "step": 1943 }, { "epoch": 2.8651436993367723, "grad_norm": 2.0276235045647475, "learning_rate": 2.7244876355604626e-05, "loss": 0.3154, "step": 1944 }, { "epoch": 2.866617538688283, "grad_norm": 1.8803138456740787, "learning_rate": 2.7225407643465588e-05, "loss": 0.2741, "step": 1945 }, { "epoch": 2.868091378039794, "grad_norm": 1.702076720556007, "learning_rate": 2.7205937570855088e-05, "loss": 0.3079, "step": 1946 }, { "epoch": 2.869565217391304, "grad_norm": 1.7289338548803397, "learning_rate": 2.7186466149675887e-05, "loss": 0.2905, "step": 1947 }, { "epoch": 2.871039056742815, "grad_norm": 2.6083320772048153, "learning_rate": 2.716699339183157e-05, "loss": 0.296, "step": 1948 }, { "epoch": 2.872512896094326, "grad_norm": 2.441410742183367, "learning_rate": 2.714751930922652e-05, "loss": 0.3133, "step": 1949 }, { "epoch": 2.873986735445836, "grad_norm": 2.1323471959096643, "learning_rate": 2.712804391376594e-05, "loss": 0.2497, "step": 1950 }, { "epoch": 2.875460574797347, "grad_norm": 2.4488363499821992, "learning_rate": 2.710856721735585e-05, "loss": 0.3478, "step": 1951 }, { "epoch": 2.8769344141488578, "grad_norm": 1.6081396750571133, "learning_rate": 2.7089089231903043e-05, "loss": 0.2622, "step": 1952 }, { "epoch": 2.8784082535003686, "grad_norm": 2.148242400587543, "learning_rate": 2.706960996931512e-05, "loss": 0.2979, "step": 1953 }, { "epoch": 2.8798820928518793, "grad_norm": 2.3843727881745047, "learning_rate": 2.7050129441500436e-05, "loss": 0.3183, "step": 1954 }, { "epoch": 2.8813559322033897, "grad_norm": 5.267704855724311, "learning_rate": 2.703064766036814e-05, "loss": 0.3176, "step": 1955 }, { "epoch": 2.8828297715549005, "grad_norm": 8.172098598010518, "learning_rate": 2.7011164637828157e-05, "loss": 0.3671, "step": 1956 }, { "epoch": 2.8843036109064113, "grad_norm": 2.3243154810162383, "learning_rate": 2.699168038579115e-05, "loss": 0.3149, "step": 1957 }, { "epoch": 2.8857774502579217, "grad_norm": 1.8183500656397706, "learning_rate": 2.697219491616853e-05, "loss": 0.3509, "step": 1958 }, { "epoch": 2.8872512896094324, "grad_norm": 1.6300444434256156, "learning_rate": 2.6952708240872476e-05, "loss": 0.2502, "step": 1959 }, { "epoch": 2.8887251289609432, "grad_norm": 1.9059754470972978, "learning_rate": 2.6933220371815883e-05, "loss": 0.3138, "step": 1960 }, { "epoch": 2.890198968312454, "grad_norm": 2.041667107822085, "learning_rate": 2.69137313209124e-05, "loss": 0.3094, "step": 1961 }, { "epoch": 2.891672807663965, "grad_norm": 2.021050536553025, "learning_rate": 2.6894241100076356e-05, "loss": 0.2905, "step": 1962 }, { "epoch": 2.893146647015475, "grad_norm": 2.2052472221202195, "learning_rate": 2.687474972122283e-05, "loss": 0.3167, "step": 1963 }, { "epoch": 2.894620486366986, "grad_norm": 2.542522713588807, "learning_rate": 2.685525719626762e-05, "loss": 0.3332, "step": 1964 }, { "epoch": 2.896094325718497, "grad_norm": 2.1409185723361883, "learning_rate": 2.6835763537127184e-05, "loss": 0.2649, "step": 1965 }, { "epoch": 2.897568165070007, "grad_norm": 1.7886871210611908, "learning_rate": 2.6816268755718698e-05, "loss": 0.2985, "step": 1966 }, { "epoch": 2.899042004421518, "grad_norm": 1.5683391564991132, "learning_rate": 2.679677286396003e-05, "loss": 0.2337, "step": 1967 }, { "epoch": 2.9005158437730287, "grad_norm": 1.8374412060109229, "learning_rate": 2.67772758737697e-05, "loss": 0.315, "step": 1968 }, { "epoch": 2.9019896831245395, "grad_norm": 1.699180234275233, "learning_rate": 2.6757777797066945e-05, "loss": 0.2333, "step": 1969 }, { "epoch": 2.9034635224760503, "grad_norm": 2.2173720903287735, "learning_rate": 2.6738278645771615e-05, "loss": 0.2987, "step": 1970 }, { "epoch": 2.9049373618275607, "grad_norm": 1.861693403461271, "learning_rate": 2.6718778431804243e-05, "loss": 0.2856, "step": 1971 }, { "epoch": 2.9064112011790715, "grad_norm": 1.9248694685239602, "learning_rate": 2.669927716708601e-05, "loss": 0.3003, "step": 1972 }, { "epoch": 2.9078850405305823, "grad_norm": 2.2710269063869966, "learning_rate": 2.6679774863538747e-05, "loss": 0.3051, "step": 1973 }, { "epoch": 2.9093588798820926, "grad_norm": 2.486911846002016, "learning_rate": 2.6660271533084895e-05, "loss": 0.3851, "step": 1974 }, { "epoch": 2.9108327192336034, "grad_norm": 1.524344541050655, "learning_rate": 2.664076718764756e-05, "loss": 0.267, "step": 1975 }, { "epoch": 2.9123065585851142, "grad_norm": 3.1417411984238193, "learning_rate": 2.6621261839150423e-05, "loss": 0.3365, "step": 1976 }, { "epoch": 2.913780397936625, "grad_norm": 1.6035397861161251, "learning_rate": 2.6601755499517826e-05, "loss": 0.2396, "step": 1977 }, { "epoch": 2.915254237288136, "grad_norm": 2.0744948266278147, "learning_rate": 2.6582248180674678e-05, "loss": 0.2521, "step": 1978 }, { "epoch": 2.916728076639646, "grad_norm": 3.497319284805236, "learning_rate": 2.6562739894546507e-05, "loss": 0.4065, "step": 1979 }, { "epoch": 2.918201915991157, "grad_norm": 2.463569517294068, "learning_rate": 2.6543230653059427e-05, "loss": 0.2668, "step": 1980 }, { "epoch": 2.9196757553426678, "grad_norm": 2.956382932355788, "learning_rate": 2.652372046814014e-05, "loss": 0.3499, "step": 1981 }, { "epoch": 2.921149594694178, "grad_norm": 2.4598698313319685, "learning_rate": 2.6504209351715914e-05, "loss": 0.3055, "step": 1982 }, { "epoch": 2.922623434045689, "grad_norm": 1.688568695184636, "learning_rate": 2.6484697315714603e-05, "loss": 0.301, "step": 1983 }, { "epoch": 2.9240972733971997, "grad_norm": 2.0660145033099266, "learning_rate": 2.64651843720646e-05, "loss": 0.3375, "step": 1984 }, { "epoch": 2.9255711127487105, "grad_norm": 1.470943193232174, "learning_rate": 2.6445670532694888e-05, "loss": 0.2392, "step": 1985 }, { "epoch": 2.9270449521002213, "grad_norm": 4.424030115766614, "learning_rate": 2.642615580953496e-05, "loss": 0.3549, "step": 1986 }, { "epoch": 2.9285187914517317, "grad_norm": 2.1938675982046294, "learning_rate": 2.6406640214514867e-05, "loss": 0.2389, "step": 1987 }, { "epoch": 2.9299926308032425, "grad_norm": 3.5671181443532154, "learning_rate": 2.6387123759565198e-05, "loss": 0.3654, "step": 1988 }, { "epoch": 2.9314664701547533, "grad_norm": 1.9734523262197912, "learning_rate": 2.6367606456617055e-05, "loss": 0.2945, "step": 1989 }, { "epoch": 2.9329403095062636, "grad_norm": 2.248737192758898, "learning_rate": 2.634808831760207e-05, "loss": 0.325, "step": 1990 }, { "epoch": 2.9344141488577744, "grad_norm": 1.8049411347742064, "learning_rate": 2.632856935445238e-05, "loss": 0.3346, "step": 1991 }, { "epoch": 2.935887988209285, "grad_norm": 1.8437675863170813, "learning_rate": 2.630904957910062e-05, "loss": 0.2996, "step": 1992 }, { "epoch": 2.937361827560796, "grad_norm": 1.8158635466981132, "learning_rate": 2.628952900347994e-05, "loss": 0.2703, "step": 1993 }, { "epoch": 2.938835666912307, "grad_norm": 1.7821037521899044, "learning_rate": 2.6270007639523963e-05, "loss": 0.3112, "step": 1994 }, { "epoch": 2.940309506263817, "grad_norm": 2.2779040947704368, "learning_rate": 2.625048549916679e-05, "loss": 0.3425, "step": 1995 }, { "epoch": 2.941783345615328, "grad_norm": 1.6604728845566556, "learning_rate": 2.623096259434302e-05, "loss": 0.2569, "step": 1996 }, { "epoch": 2.9432571849668387, "grad_norm": 2.3370900452503225, "learning_rate": 2.6211438936987692e-05, "loss": 0.3341, "step": 1997 }, { "epoch": 2.944731024318349, "grad_norm": 1.6868398576081411, "learning_rate": 2.6191914539036315e-05, "loss": 0.2425, "step": 1998 }, { "epoch": 2.94620486366986, "grad_norm": 1.8171605010581302, "learning_rate": 2.6172389412424876e-05, "loss": 0.2762, "step": 1999 }, { "epoch": 2.9476787030213707, "grad_norm": 1.7094466450686392, "learning_rate": 2.6152863569089752e-05, "loss": 0.2965, "step": 2000 }, { "epoch": 2.9476787030213707, "eval_bleu": 0.19793780399389882, "eval_bleu_1gram": 0.5146360010352428, "eval_bleu_2gram": 0.298729948362745, "eval_bleu_3gram": 0.1858397195931557, "eval_bleu_4gram": 0.1190032895227996, "eval_rag_val_loss": 0.6280399320587036, "eval_rouge1": 0.5155773960714235, "eval_rouge2": 0.2925857377639453, "eval_rougeL": 0.5104459110146367, "step": 2000 } ], "logging_steps": 1, "max_steps": 4068, "num_input_tokens_seen": 0, "num_train_epochs": 6, "save_steps": 2000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": true, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }